diff options
Diffstat (limited to 'arch/powerpc/include/asm/book3s')
28 files changed, 1850 insertions, 971 deletions
diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h deleted file mode 100644 index 2a0a467d2985..000000000000 --- a/arch/powerpc/include/asm/book3s/32/hash.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_BOOK3S_32_HASH_H -#define _ASM_POWERPC_BOOK3S_32_HASH_H -#ifdef __KERNEL__ - -/* - * The "classic" 32-bit implementation of the PowerPC MMU uses a hash - * table containing PTEs, together with a set of 16 segment registers, - * to define the virtual to physical address mapping. - * - * We use the hash table as an extended TLB, i.e. a cache of currently - * active mappings. We maintain a two-level page table tree, much - * like that used by the i386, for the sake of the Linux memory - * management code. Low-level assembler code in hash_low_32.S - * (procedure hash_page) is responsible for extracting ptes from the - * tree and putting them into the hash table when necessary, and - * updating the accessed and modified bits in the page table tree. - */ - -#define _PAGE_PRESENT 0x001 /* software: pte contains a translation */ -#define _PAGE_HASHPTE 0x002 /* hash_page has made an HPTE for this pte */ -#define _PAGE_USER 0x004 /* usermode access allowed */ -#define _PAGE_GUARDED 0x008 /* G: prohibit speculative access */ -#define _PAGE_COHERENT 0x010 /* M: enforce memory coherence (SMP systems) */ -#define _PAGE_NO_CACHE 0x020 /* I: cache inhibit */ -#define _PAGE_WRITETHRU 0x040 /* W: cache write-through */ -#define _PAGE_DIRTY 0x080 /* C: page changed */ -#define _PAGE_ACCESSED 0x100 /* R: page referenced */ -#define _PAGE_EXEC 0x200 /* software: exec allowed */ -#define _PAGE_RW 0x400 /* software: user write access allowed */ -#define _PAGE_SPECIAL 0x800 /* software: Special page */ - -#ifdef CONFIG_PTE_64BIT -/* We never clear the high word of the pte */ -#define _PTE_NONE_MASK (0xffffffff00000000ULL | _PAGE_HASHPTE) -#else -#define _PTE_NONE_MASK _PAGE_HASHPTE -#endif - -#define _PMD_PRESENT 0 -#define _PMD_PRESENT_MASK (PAGE_MASK) -#define _PMD_BAD (~PAGE_MASK) - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_BOOK3S_32_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index f9dc597b0b86..4e14a5427a63 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -2,141 +2,170 @@ #ifndef _ASM_POWERPC_BOOK3S_32_KUP_H #define _ASM_POWERPC_BOOK3S_32_KUP_H +#include <asm/bug.h> #include <asm/book3s/32/mmu-hash.h> +#include <asm/mmu.h> +#include <asm/synch.h> -#ifdef __ASSEMBLY__ - -.macro kuep_update_sr gpr1, gpr2 /* NEVER use r0 as gpr2 due to addis */ -101: mtsrin \gpr1, \gpr2 - addi \gpr1, \gpr1, 0x111 /* next VSID */ - rlwinm \gpr1, \gpr1, 0, 0xf0ffffff /* clear VSID overflow */ - addis \gpr2, \gpr2, 0x1000 /* address of next segment */ - bdnz 101b - isync -.endm - -.macro kuep_lock gpr1, gpr2 -#ifdef CONFIG_PPC_KUEP - li \gpr1, NUM_USER_SEGMENTS - li \gpr2, 0 - mtctr \gpr1 - mfsrin \gpr1, \gpr2 - oris \gpr1, \gpr1, SR_NX@h /* set Nx */ - kuep_update_sr \gpr1, \gpr2 -#endif -.endm - -.macro kuep_unlock gpr1, gpr2 -#ifdef CONFIG_PPC_KUEP - li \gpr1, NUM_USER_SEGMENTS - li \gpr2, 0 - mtctr \gpr1 - mfsrin \gpr1, \gpr2 - rlwinm \gpr1, \gpr1, 0, ~SR_NX /* Clear Nx */ - kuep_update_sr \gpr1, \gpr2 -#endif -.endm +#ifndef __ASSEMBLY__ #ifdef CONFIG_PPC_KUAP -.macro kuap_update_sr gpr1, gpr2, gpr3 /* NEVER use r0 as gpr2 due to addis */ -101: mtsrin \gpr1, \gpr2 - addi \gpr1, \gpr1, 0x111 /* next VSID */ - rlwinm \gpr1, \gpr1, 0, 0xf0ffffff /* clear VSID overflow */ - addis \gpr2, \gpr2, 0x1000 /* address of next segment */ - cmplw \gpr2, \gpr3 - blt- 101b - isync -.endm - -.macro kuap_save_and_lock sp, thread, gpr1, gpr2, gpr3 - lwz \gpr2, KUAP(\thread) - rlwinm. \gpr3, \gpr2, 28, 0xf0000000 - stw \gpr2, STACK_REGS_KUAP(\sp) - beq+ 102f - li \gpr1, 0 - stw \gpr1, KUAP(\thread) - mfsrin \gpr1, \gpr2 - oris \gpr1, \gpr1, SR_KS@h /* set Ks */ - kuap_update_sr \gpr1, \gpr2, \gpr3 -102: -.endm - -.macro kuap_restore sp, current, gpr1, gpr2, gpr3 - lwz \gpr2, STACK_REGS_KUAP(\sp) - rlwinm. \gpr3, \gpr2, 28, 0xf0000000 - stw \gpr2, THREAD + KUAP(\current) - beq+ 102f - mfsrin \gpr1, \gpr2 - rlwinm \gpr1, \gpr1, 0, ~SR_KS /* Clear Ks */ - kuap_update_sr \gpr1, \gpr2, \gpr3 -102: -.endm - -.macro kuap_check current, gpr -#ifdef CONFIG_PPC_KUAP_DEBUG - lwz \gpr2, KUAP(thread) -999: twnei \gpr, 0 - EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) -#endif -.endm +#include <linux/sched.h> -#endif /* CONFIG_PPC_KUAP */ +#define KUAP_NONE (~0UL) -#else /* !__ASSEMBLY__ */ +static __always_inline void kuap_lock_one(unsigned long addr) +{ + mtsr(mfsr(addr) | SR_KS, addr); + isync(); /* Context sync required after mtsr() */ +} -#ifdef CONFIG_PPC_KUAP +static __always_inline void kuap_unlock_one(unsigned long addr) +{ + mtsr(mfsr(addr) & ~SR_KS, addr); + isync(); /* Context sync required after mtsr() */ +} -#include <linux/sched.h> +static __always_inline void uaccess_begin_32s(unsigned long addr) +{ + unsigned long tmp; + + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "rlwinm %0, %0, 0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP) + : "memory"); +} -static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) +static __always_inline void uaccess_end_32s(unsigned long addr) { - addr &= 0xf0000000; /* align addr to start of segment */ - barrier(); /* make sure thread.kuap is updated before playing with SRs */ - while (addr < end) { - mtsrin(sr, addr); - sr += 0x111; /* next VSID */ - sr &= 0xf0ffffff; /* clear VSID overflow */ - addr += 0x10000000; /* address of next segment */ - } - isync(); /* Context sync required after mtsrin() */ + unsigned long tmp; + + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "oris %0, %0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP) + : "memory"); } -static inline void allow_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) { - u32 addr, end; + unsigned long kuap = current->thread.kuap; - if (__builtin_constant_p(to) && to == NULL) + regs->kuap = kuap; + if (unlikely(kuap == KUAP_NONE)) return; - addr = (__force u32)to; + current->thread.kuap = KUAP_NONE; + kuap_lock_one(kuap); +} +#define __kuap_save_and_lock __kuap_save_and_lock + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ +} - if (!addr || addr >= TASK_SIZE || !size) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +{ + if (unlikely(kuap != KUAP_NONE)) { + current->thread.kuap = KUAP_NONE; + kuap_lock_one(kuap); + } + + if (likely(regs->kuap == KUAP_NONE)) return; - end = min(addr + size, TASK_SIZE); - current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf); - kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end); /* Clear Ks */ + current->thread.kuap = regs->kuap; + + kuap_unlock_one(regs->kuap); } -static inline void prevent_user_access(void __user *to, const void __user *from, u32 size) +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { - u32 addr = (__force u32)to; - u32 end = min(addr + size, TASK_SIZE); + unsigned long kuap = current->thread.kuap; + + WARN_ON_ONCE(IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && kuap != KUAP_NONE); + + return kuap; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked - if (!addr || addr >= TASK_SIZE || !size) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) +{ + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (!(dir & KUAP_WRITE)) return; - current->thread.kuap = 0; - kuap_update_sr(mfsrin(addr) | SR_KS, addr, end); /* set Ks */ + current->thread.kuap = (__force u32)to; + uaccess_begin_32s((__force u32)to); } -static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) +static __always_inline void prevent_user_access(unsigned long dir) { + u32 kuap = current->thread.kuap; + + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (!(dir & KUAP_WRITE)) + return; + + current->thread.kuap = KUAP_NONE; + uaccess_end_32s(kuap); +} + +static __always_inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = current->thread.kuap; + + if (flags != KUAP_NONE) { + current->thread.kuap = KUAP_NONE; + uaccess_end_32s(flags); + } + + return flags; +} + +static __always_inline void restore_user_access(unsigned long flags) +{ + if (flags != KUAP_NONE) { + current->thread.kuap = flags; + uaccess_begin_32s(flags); + } +} + +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + unsigned long kuap = regs->kuap; + if (!is_write) return false; + if (kuap == KUAP_NONE) + return true; + + /* + * If faulting address doesn't match unlocked segment, change segment. + * In case of unaligned store crossing two segments, emulate store. + */ + if ((kuap ^ address) & 0xf0000000) { + if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) { + regs_add_return_ip(regs, 4); + emulate_single_step(regs); + } else { + regs->kuap = address; + } + } - return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !"); + return false; } #endif /* CONFIG_PPC_KUAP */ diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index 2e277ca0170f..78c6a5fde1d6 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -64,7 +64,92 @@ struct ppc_bat { #define SR_KP 0x20000000 /* User key */ #define SR_KS 0x40000000 /* Supervisor key */ -#ifndef __ASSEMBLY__ +#ifdef __ASSEMBLY__ + +#include <asm/asm-offsets.h> + +.macro uus_addi sr reg1 reg2 imm + .if NUM_USER_SEGMENTS > \sr + addi \reg1,\reg2,\imm + .endif +.endm + +.macro uus_mtsr sr reg1 + .if NUM_USER_SEGMENTS > \sr + mtsr \sr, \reg1 + .endif +.endm + +/* + * This isync() shouldn't be necessary as the kernel is not excepted to run + * any instruction in userspace soon after the update of segments and 'rfi' + * instruction is used to return to userspace, but hash based cores + * (at least G3) seem to exhibit a random behaviour when the 'isync' is not + * there. 603 cores don't have this behaviour so don't do the 'isync' as it + * saves several CPU cycles. + */ +.macro uus_isync +#ifdef CONFIG_PPC_BOOK3S_604 +BEGIN_MMU_FTR_SECTION + isync +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif +.endm + +.macro update_user_segments_by_4 tmp1 tmp2 tmp3 tmp4 + uus_addi 1, \tmp2, \tmp1, 0x111 + uus_addi 2, \tmp3, \tmp1, 0x222 + uus_addi 3, \tmp4, \tmp1, 0x333 + + uus_mtsr 0, \tmp1 + uus_mtsr 1, \tmp2 + uus_mtsr 2, \tmp3 + uus_mtsr 3, \tmp4 + + uus_addi 4, \tmp1, \tmp1, 0x444 + uus_addi 5, \tmp2, \tmp2, 0x444 + uus_addi 6, \tmp3, \tmp3, 0x444 + uus_addi 7, \tmp4, \tmp4, 0x444 + + uus_mtsr 4, \tmp1 + uus_mtsr 5, \tmp2 + uus_mtsr 6, \tmp3 + uus_mtsr 7, \tmp4 + + uus_addi 8, \tmp1, \tmp1, 0x444 + uus_addi 9, \tmp2, \tmp2, 0x444 + uus_addi 10, \tmp3, \tmp3, 0x444 + uus_addi 11, \tmp4, \tmp4, 0x444 + + uus_mtsr 8, \tmp1 + uus_mtsr 9, \tmp2 + uus_mtsr 10, \tmp3 + uus_mtsr 11, \tmp4 + + uus_addi 12, \tmp1, \tmp1, 0x444 + uus_addi 13, \tmp2, \tmp2, 0x444 + uus_addi 14, \tmp3, \tmp3, 0x444 + uus_addi 15, \tmp4, \tmp4, 0x444 + + uus_mtsr 12, \tmp1 + uus_mtsr 13, \tmp2 + uus_mtsr 14, \tmp3 + uus_mtsr 15, \tmp4 + + uus_isync +.endm + +#else + +/* + * This macro defines the mapping from contexts to VSIDs (virtual + * segment IDs). We use a skew on both the context and the high 4 bits + * of the 32-bit virtual address (the "effective segment ID") in order + * to spread out the entries in the MMU hash table. Note, if this + * function is changed then hash functions will have to be + * changed to correspond. + */ +#define CTX_TO_VSID(c, id) ((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff) /* * Hardware Page Table Entry @@ -90,10 +175,16 @@ struct hash_pte { typedef struct { unsigned long id; - unsigned long vdso_base; + unsigned long sr0; + void __user *vdso; } mm_context_t; +#ifdef CONFIG_PPC_KUEP +#define INIT_MM_CONTEXT(mm) .context.sr0 = SR_NX +#endif + void update_bats(void); +static inline void cleanup_cpu_mmu_context(void) { } /* patch sites */ extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2; @@ -101,6 +192,39 @@ extern s32 patch__hash_page_B, patch__hash_page_C; extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2; extern s32 patch__flush_hash_B; +#include <asm/reg.h> +#include <asm/task_size_32.h> + +static __always_inline void update_user_segment(u32 n, u32 val) +{ + if (n << 28 < TASK_SIZE) + mtsr(val + n * 0x111, n << 28); +} + +static __always_inline void update_user_segments(u32 val) +{ + val &= 0xf0ffffff; + + update_user_segment(0, val); + update_user_segment(1, val); + update_user_segment(2, val); + update_user_segment(3, val); + update_user_segment(4, val); + update_user_segment(5, val); + update_user_segment(6, val); + update_user_segment(7, val); + update_user_segment(8, val); + update_user_segment(9, val); + update_user_segment(10, val); + update_user_segment(11, val); + update_user_segment(12, val); + update_user_segment(13, val); + update_user_segment(14, val); + update_user_segment(15, val); +} + +int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 998317702630..dc5c039eb28e 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { @@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, - void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 0796533d37dd..52971ee30717 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -2,27 +2,52 @@ #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> -#include <asm/book3s/32/hash.h> +/* + * The "classic" 32-bit implementation of the PowerPC MMU uses a hash + * table containing PTEs, together with a set of 16 segment registers, + * to define the virtual to physical address mapping. + * + * We use the hash table as an extended TLB, i.e. a cache of currently + * active mappings. We maintain a two-level page table tree, much + * like that used by the i386, for the sake of the Linux memory + * management code. Low-level assembler code in hash_low_32.S + * (procedure hash_page) is responsible for extracting ptes from the + * tree and putting them into the hash table when necessary, and + * updating the accessed and modified bits in the page table tree. + */ -/* And here we include common definitions */ +#define _PAGE_PRESENT 0x001 /* software: pte contains a translation */ +#define _PAGE_HASHPTE 0x002 /* hash_page has made an HPTE for this pte */ +#define _PAGE_READ 0x004 /* software: read access allowed */ +#define _PAGE_GUARDED 0x008 /* G: prohibit speculative access */ +#define _PAGE_COHERENT 0x010 /* M: enforce memory coherence (SMP systems) */ +#define _PAGE_NO_CACHE 0x020 /* I: cache inhibit */ +#define _PAGE_WRITETHRU 0x040 /* W: cache write-through */ +#define _PAGE_DIRTY 0x080 /* C: page changed */ +#define _PAGE_ACCESSED 0x100 /* R: page referenced */ +#define _PAGE_EXEC 0x200 /* software: exec allowed */ +#define _PAGE_WRITE 0x400 /* software: user write access allowed */ +#define _PAGE_SPECIAL 0x800 /* software: Special page */ -#define _PAGE_KERNEL_RO 0 -#define _PAGE_KERNEL_ROX (_PAGE_EXEC) -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) +#ifdef CONFIG_PTE_64BIT +/* We never clear the high word of the pte */ +#define _PTE_NONE_MASK (0xffffffff00000000ULL | _PAGE_HASHPTE) +#else +#define _PTE_NONE_MASK _PAGE_HASHPTE +#endif -#define _PAGE_HPTEFLAGS _PAGE_HASHPTE +#define _PMD_PRESENT 0 +#define _PMD_PRESENT_MASK (PAGE_MASK) +#define _PMD_BAD (~PAGE_MASK) -#ifndef __ASSEMBLY__ +/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_READ -static inline bool pte_user(pte_t pte) -{ - return pte_val(pte) & _PAGE_USER; -} -#endif /* __ASSEMBLY__ */ +/* And here we include common definitions */ + +#define _PAGE_HPTEFLAGS _PAGE_HASHPTE /* * Location of the PFN in the PTE. Most 32-bit platforms use the same @@ -37,8 +62,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* @@ -57,49 +84,16 @@ static inline bool pte_user(pte_t pte) #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -/* - * 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. - */ -#define PAGE_NONE __pgprot(_PAGE_BASE) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#include <asm/pgtable-masks.h> /* 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_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED) #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 - -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP - #define PTE_INDEX_SIZE PTE_SHIFT #define PMD_INDEX_SIZE 0 #define PUD_INDEX_SIZE 0 @@ -113,6 +107,9 @@ static inline bool pte_user(pte_t pte) #define PMD_TABLE_SIZE 0 #define PUD_TABLE_SIZE 0 #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) + +/* Bits to mask out from a PMD to get to the PTE page */ +#define PMD_MASKED_BITS (PTE_TABLE_SIZE - 1) #endif /* __ASSEMBLY__ */ #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) @@ -138,6 +135,7 @@ static inline bool pte_user(pte_t pte) #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ @@ -146,7 +144,14 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); * value (for now) on others, from where we can start layout kernel * virtual space that goes below PKMAP and FIXMAP */ -#include <asm/fixmap.h> + +#define FIXADDR_SIZE 0 +#ifdef CONFIG_KASAN +#include <asm/kasan.h> +#define FIXADDR_TOP (KASAN_SHADOW_START - PAGE_SIZE) +#else +#define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) +#endif /* * ioremap_bot starts at that address. Early ioremaps move down from there, @@ -182,18 +187,16 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define VMALLOC_OFFSET (0x1000000) /* 16M */ -/* - * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules - * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear - * memory shall not share segments. - */ -#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES) -#define VMALLOC_START ((_ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \ - ~(VMALLOC_OFFSET - 1)) -#else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) -#endif + +#ifdef CONFIG_KASAN_VMALLOC +#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else #define VMALLOC_END ioremap_bot +#endif + +#define MODULES_END ALIGN_DOWN(PAGE_OFFSET, SZ_256M) +#define MODULES_VADDR (MODULES_END - SZ_256M) #ifndef __ASSEMBLY__ #include <linux/sched.h> @@ -202,9 +205,6 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0 -#define pte_ERROR(e) \ - pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ - (unsigned long long)pte_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) /* @@ -213,7 +213,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define pte_clear(mm, addr, ptep) \ - do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0) + do { pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0); } while (0) #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) @@ -236,8 +236,14 @@ extern void add_hash_page(unsigned context, unsigned long va, unsigned long pmdval); /* Flush an entry from the TLB/hash table */ -extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, - unsigned long address); +static inline void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + unsigned long ptephys = __pa(ptep) & PAGE_MASK; + + flush_hash_pages(mm->context.id, addr, ptephys, 1); + } +} /* * PTE updates. This function is called whenever an existing @@ -248,84 +254,74 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, * and the PTE may be either 32 or 64 bit wide. In the later case, * when using atomic updates, only the low part of the PTE is * accessed atomically. - * - * In addition, on 44x, we also maintain a global flag indicating - * that an executable user mapping was modified, which is needed - * to properly flush the virtually tagged instruction cache of - * those implementations. */ +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge) +{ + pte_basic_t old; + + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + unsigned long tmp; + + asm volatile( +#ifndef CONFIG_PTE_64BIT + "1: lwarx %0, 0, %3\n" + " andc %1, %0, %4\n" +#else + "1: lwarx %L0, 0, %3\n" + " lwz %0, -4(%3)\n" + " andc %1, %L0, %4\n" +#endif + " or %1, %1, %5\n" + " stwcx. %1, 0, %3\n" + " bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) #ifndef CONFIG_PTE_64BIT -static inline unsigned long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ - unsigned long old, tmp; - - __asm__ __volatile__("\ -1: lwarx %0,0,%3\n\ - andc %1,%0,%4\n\ - or %1,%1,%5\n" -" stwcx. %1,0,%3\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" (clr), "r" (set), "m" (*p) - : "cc" ); + : "r" (p), +#else + : "b" ((unsigned long)(p) + 4), +#endif + "r" (clr), "r" (set), "m" (*p) + : "cc" ); + } else { + old = pte_val(*p); - return old; -} -#else /* CONFIG_PTE_64BIT */ -static inline unsigned long long pte_update(pte_t *p, - unsigned long clr, - unsigned long set) -{ - unsigned long long old; - unsigned long tmp; - - __asm__ __volatile__("\ -1: lwarx %L0,0,%4\n\ - lwzx %0,0,%3\n\ - andc %1,%L0,%5\n\ - or %1,%1,%6\n" -" stwcx. %1,0,%4\n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) - : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p) - : "cc" ); + *p = __pte((old & ~(pte_basic_t)clr) | set); + } return old; } -#endif /* CONFIG_PTE_64BIT */ /* * 2.6 calls this without flushing the TLB entry; this is wrong * for our hash-based implementation, we fix that up here. */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) +static inline int __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { unsigned long old; - old = pte_update(ptep, _PAGE_ACCESSED, 0); - if (old & _PAGE_HASHPTE) { - unsigned long ptephys = __pa(ptep) & PAGE_MASK; - flush_hash_pages(context, addr, ptephys, 1); - } + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + if (old & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); + return (old & _PAGE_ACCESSED) != 0; } #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ - __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) + __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep) #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) { - return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0)); + return __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0)); } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_update(ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); } static inline void __ptep_set_access_flags(struct vm_area_struct *vma, @@ -336,7 +332,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - pte_update(ptep, 0, set); + pte_update(vma->vm_mm, address, ptep, 0, set, 0); flush_tlb_page(vma, address); } @@ -344,43 +340,56 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) -#define pmd_page_vaddr(pmd) \ - ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) -#define pmd_page(pmd) \ - pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) - -/* to find an entry in a kernel page-table-directory */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) - -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -/* Find an entry in the third-level page table.. */ -#define pte_index(address) \ - (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_kernel(dir, addr) \ - ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) -#define pte_offset_map(dir, addr) \ - ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ - (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) -#define pte_unmap(pte) kunmap_atomic(pte) +#define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* - * Encode and decode a swap entry. - * Note that the bits we use in a PTE for representing a swap entry - * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used). - * -- paulus + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs (32bit PTEs): + * + * 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * <----------------- offset --------------------> < type -> E H P + * + * E is the exclusive marker that is not stored in swap entries. + * _PAGE_PRESENT (P) and __PAGE_HASHPTE (H) must be 0. + * + * For 64bit PTEs, the offset is extended by 32bit. */ #define __swp_type(entry) ((entry).val & 0x1f) #define __swp_offset(entry) ((entry).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 5) }) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) & 0x1f) | ((offset) << 5) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); +} + /* Generic accessors to PTE bits */ -static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} -static inline int pte_read(pte_t pte) { return 1; } +static inline bool pte_read(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_READ); +} + +static inline bool pte_write(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_WRITE); +} + static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } @@ -415,10 +424,10 @@ static inline bool pte_ci(pte_t pte) static inline bool pte_access_permitted(pte_t pte, bool write) { /* - * A read-only access is controlled by _PAGE_USER bit. - * We have _PAGE_READ set for WRITE and EXECUTE + * A read-only access is controlled by _PAGE_READ bit. + * We have _PAGE_READ set for WRITE */ - if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + if (!pte_present(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) @@ -439,15 +448,10 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) -{ - return pte_val(pte) >> PTE_RPN_SHIFT; -} - /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_RW); + return __pte(pte_val(pte) & ~_PAGE_WRITE); } static inline pte_t pte_exprotect(pte_t pte) @@ -475,8 +479,11 @@ static inline pte_t pte_mkpte(pte_t pte) return pte; } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { + /* + * write implies read, hence set both + */ return __pte(pte_val(pte) | _PAGE_RW); } @@ -500,16 +507,6 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } -static inline pte_t pte_mkprivileged(pte_t pte) -{ - return __pte(pte_val(pte) & ~_PAGE_USER); -} - -static inline pte_t pte_mkuser(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_USER); -} - static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); @@ -518,58 +515,43 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* 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 + * Setting the PTE depends on the MMU type and other factors. + * + * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating. + * + * Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we fallback to the simple update preserving + * the hash bits (ie, same as the non-SMP case). + * + * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving + * the hash bits instead. */ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) - /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the - * helper pte_update() which does an atomic update. We need to do that - * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a - * per-CPU PTE such as a kmap_atomic, we do a simple update preserving - * the hash bits instead (ie, same as the non-SMP case) - */ - if (percpu) - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - else - pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); - -#elif defined(CONFIG_PTE_64BIT) - /* Second case is 32-bit with 64-bit PTE. In this case, we - * can just store as long as we do the two halves in the right order - * with a barrier in between. This is possible because we take care, - * in the hash code, to pre-invalidate if the PTE was already hashed, - * which synchronizes us with any concurrent invalidation. - * In the percpu case, we also fallback to the simple update preserving - * the hash bits - */ - if (percpu) { - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - return; + if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) | + (pte_val(pte) & ~_PAGE_HASHPTE)); + } else if (IS_ENABLED(CONFIG_PTE_64BIT)) { + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); + + asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" : + "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : + "r" (pte) : "memory"); + } else { + pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0); } - if (pte_val(*ptep) & _PAGE_HASHPTE) - flush_hash_entry(mm, ptep, addr); - __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ - eieio\n\ - stw%U0%X0 %L2,%1" - : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) - : "r" (pte) : "memory"); - -#else - /* Third case is 32-bit hash table in UP mode, we need to preserve - * the _PAGE_HASHPTE bit since we may not have invalidated the previous - * translation in the hash yet (done in a subsequent flush_tlb_xxx()) - * and see we need to keep track that this PTE needs invalidating - */ - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); -#endif } /* diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h index 068085b709fb..e43534da5207 100644 --- a/arch/powerpc/include/asm/book3s/32/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h @@ -2,24 +2,90 @@ #ifndef _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H #define _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H +#include <linux/build_bug.h> + #define MMU_NO_CONTEXT (0) /* * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ -extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +void hash__flush_tlb_mm(struct mm_struct *mm); +void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end); + +#ifdef CONFIG_SMP +void _tlbie(unsigned long address); +#else +static inline void _tlbie(unsigned long address) +{ + asm volatile ("tlbie %0; sync" : : "r" (address) : "memory"); +} +#endif +void _tlbia(void); + +/* + * Called at the end of a mmu_gather operation to make sure the + * TLB flush is completely done. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + /* 603 needs to flush the whole TLB here since it doesn't use a hash table. */ + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + _tlbia(); +} + +static inline void flush_range(struct mm_struct *mm, unsigned long start, unsigned long end) +{ + start &= PAGE_MASK; + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_range(mm, start, end); + else if (end - start <= PAGE_SIZE) + _tlbie(start); + else + _tlbia(); +} + +static inline void flush_tlb_mm(struct mm_struct *mm) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_tlb_mm(mm); + else + _tlbia(); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_tlb_page(vma, vmaddr); + else + _tlbie(vmaddr); +} + +static inline void +flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + flush_range(vma->vm_mm, start, end); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + flush_range(&init_mm, start, end); +} + static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { flush_tlb_page(vma, vmaddr); } + +static inline void local_flush_tlb_page_psize(struct mm_struct *mm, + unsigned long vmaddr, int psize) +{ + flush_range(mm, vmaddr, vmaddr); +} + static inline void local_flush_tlb_mm(struct mm_struct *mm) { flush_tlb_mm(mm); } -#endif /* _ASM_POWERPC_TLBFLUSH_H */ +#endif /* _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 8fd8599c9395..6472b08fa1b0 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,24 @@ */ #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 + * 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) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Limits the linear mapping range */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#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) @@ -34,11 +38,11 @@ #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 53 -#define H_PAGE_F_SECOND _RPAGE_RPN44 /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) -#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ -#define H_PAGE_HASHPTE _RPAGE_RSV2 /* software: PTE & hash are busy */ +#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 | \ @@ -57,11 +61,12 @@ #define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) /* memory key bits, only 8 keys supported */ -#define H_PTE_PKEY_BIT0 0 -#define H_PTE_PKEY_BIT1 0 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#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() @@ -131,12 +136,6 @@ 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(); @@ -156,6 +155,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, 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 index d1d9177d9ebd..0bf6fd0bf42a 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -7,6 +7,19 @@ #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 @@ -32,15 +45,15 @@ */ #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_RPN44 /* software: PTE & hash are busy */ +#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_BIT0 _RPAGE_RSV1 -#define H_PTE_PKEY_BIT1 _RPAGE_RSV2 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#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 @@ -246,15 +259,10 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, */ static inline int hash__pmd_trans_huge(pmd_t pmd) { - return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) == + 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)); @@ -272,6 +280,12 @@ 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 000000000000..6c5564c4fae4 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H +#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H + +/* We use key 3 for KERNEL */ +#define HASH_DEFAULT_KERNEL_KEY (HPTE_R_KEY_BIT0 | HPTE_R_KEY_BIT1) + +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, unsigned long flags) +{ + unsigned long pte_pkey; + + pte_pkey = (((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)); + + if (mmu_has_feature(MMU_FTR_KUAP) || + mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY)) + return HASH_DEFAULT_KERNEL_KEY; + } + + return pte_pkey; +} + +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 index 2781ebf6add4..6e70ae511631 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -18,6 +18,10 @@ #include <asm/book3s/64/hash-4k.h> #endif +#define H_PTRS_PER_PTE (1 << H_PTE_INDEX_SIZE) +#define H_PTRS_PER_PMD (1 << H_PMD_INDEX_SIZE) +#define H_PTRS_PER_PUD (1 << H_PUD_INDEX_SIZE) + /* Bits to set in a PMD/PUD/PGD entry valid bit*/ #define HASH_PMD_VAL_BITS (0x8000000000000000UL) #define HASH_PUD_VAL_BITS (0x8000000000000000UL) @@ -99,10 +103,6 @@ * 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 @@ -132,11 +132,25 @@ static inline int get_region_id(unsigned long ea) return region_id; } +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); +} + #define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) + +/* + * pud comparison that will work with both pte and page table pointer. + */ +static inline int hash__pud_same(pud_t pud_a, pud_t pud_b) +{ + return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} #define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) -static inline int hash__pgd_bad(pgd_t pgd) + +static inline int hash__p4d_bad(p4d_t p4d) { - return (pgd_val(pgd) == 0); + return (p4d_val(p4d) == 0); } #ifdef CONFIG_STRICT_KERNEL_RWX extern void hash__mark_rodata_ro(void); @@ -145,7 +159,7 @@ extern void hash__mark_initmem_nx(void); 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); +unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags); /* Atomic PTE updates */ static inline unsigned long hash__pte_update(struct mm_struct *mm, unsigned long addr, @@ -251,9 +265,12 @@ extern int __meminit hash__vmemmap_create_mapping(unsigned long start, 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); +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); +void hash__kernel_map_pages(struct page *page, int numpages, int enable); + #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 index 12e150e615b7..aa1c67c8bfc8 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H #define _ASM_POWERPC_BOOK3S_64_HUGETLB_H + +#include <asm/firmware.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 @@ -8,10 +11,6 @@ */ 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, 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 000000000000..df37a76c1e9f --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kexec.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_ +#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_ + +#include <asm/plpar_wrappers.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); + if (cpu_has_feature(CPU_FTR_HVMODE)) + mtspr(SPRN_CIABR, 0); + else + plpar_set_ciabr(0); + } + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_DEXCR, 0); + mtspr(SPRN_HASHKEYR, 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 deleted file mode 100644 index f254de956d6a..000000000000 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ /dev/null @@ -1,108 +0,0 @@ -/* 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/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h new file mode 100644 index 000000000000..497a7bd31ecc --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kup.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_KUP_H +#define _ASM_POWERPC_BOOK3S_64_KUP_H + +#include <linux/const.h> +#include <asm/reg.h> + +#define AMR_KUAP_BLOCK_READ UL(0x5455555555555555) +#define AMR_KUAP_BLOCK_WRITE UL(0xa8aaaaaaaaaaaaaa) +#define AMR_KUEP_BLOCKED UL(0x5455555555555555) +#define AMR_KUAP_BLOCKED (AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE) + +#ifdef __ASSEMBLY__ + +.macro kuap_user_restore gpr1, gpr2 +#if defined(CONFIG_PPC_PKEY) + BEGIN_MMU_FTR_SECTION_NESTED(67) + b 100f // skip_restore_amr + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67) + /* + * AMR and IAMR are going to be different when + * returning to userspace. + */ + ld \gpr1, STACK_REGS_AMR(r1) + + /* + * If kuap feature is not enabled, do the mtspr + * only if AMR value is different. + */ + BEGIN_MMU_FTR_SECTION_NESTED(68) + mfspr \gpr2, SPRN_AMR + cmpd \gpr1, \gpr2 + beq 99f + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_KUAP, 68) + + isync + mtspr SPRN_AMR, \gpr1 +99: + /* + * Restore IAMR only when returning to userspace + */ + ld \gpr1, STACK_REGS_IAMR(r1) + + /* + * If kuep feature is not enabled, do the mtspr + * only if IAMR value is different. + */ + BEGIN_MMU_FTR_SECTION_NESTED(69) + mfspr \gpr2, SPRN_IAMR + cmpd \gpr1, \gpr2 + beq 100f + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_BOOK3S_KUEP, 69) + + isync + mtspr SPRN_IAMR, \gpr1 + +100: //skip_restore_amr + /* No isync required, see kuap_user_restore() */ +#endif +.endm + +.macro kuap_kernel_restore gpr1, gpr2 +#if defined(CONFIG_PPC_PKEY) + + BEGIN_MMU_FTR_SECTION_NESTED(67) + /* + * AMR is going to be mostly the same since we are + * returning to the kernel. Compare and do a mtspr. + */ + ld \gpr2, STACK_REGS_AMR(r1) + mfspr \gpr1, SPRN_AMR + cmpd \gpr1, \gpr2 + beq 100f + isync + mtspr SPRN_AMR, \gpr2 + /* + * No isync required, see kuap_restore_amr() + * No need to restore IAMR when returning to kernel space. + */ +100: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_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 + /* Prevent access to userspace using any key values */ + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED) +999: tdne \gpr1, \gpr2 + EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67) +#endif +.endm +#endif + +/* + * if (pkey) { + * + * save AMR -> stack; + * if (kuap) { + * if (AMR != BLOCKED) + * KUAP_BLOCKED -> AMR; + * } + * if (from_user) { + * save IAMR -> stack; + * if (kuep) { + * KUEP_BLOCKED ->IAMR + * } + * } + * return; + * } + * + * if (kuap) { + * if (from_kernel) { + * save AMR -> stack; + * if (AMR != BLOCKED) + * KUAP_BLOCKED -> AMR; + * } + * + * } + */ +.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr +#if defined(CONFIG_PPC_PKEY) + + /* + * if both pkey and kuap is disabled, nothing to do + */ + BEGIN_MMU_FTR_SECTION_NESTED(68) + b 100f // skip_save_amr + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_KUAP, 68) + + /* + * if pkey is disabled and we are entering from userspace + * don't do anything. + */ + BEGIN_MMU_FTR_SECTION_NESTED(67) + .ifnb \msr_pr_cr + /* + * Without pkey we are not changing AMR outside the kernel + * hence skip this completely. + */ + bne \msr_pr_cr, 100f // from userspace + .endif + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67) + + /* + * pkey is enabled or pkey is disabled but entering from kernel + */ + mfspr \gpr1, SPRN_AMR + std \gpr1, STACK_REGS_AMR(r1) + + /* + * update kernel AMR with AMR_KUAP_BLOCKED only + * if KUAP feature is enabled + */ + BEGIN_MMU_FTR_SECTION_NESTED(69) + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED) + cmpd \use_cr, \gpr1, \gpr2 + beq \use_cr, 102f + /* + * We don't isync here because we very recently entered via an interrupt + */ + mtspr SPRN_AMR, \gpr2 + isync +102: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 69) + + /* + * if entering from kernel we don't need save IAMR + */ + .ifnb \msr_pr_cr + beq \msr_pr_cr, 100f // from kernel space + mfspr \gpr1, SPRN_IAMR + std \gpr1, STACK_REGS_IAMR(r1) + + /* + * update kernel IAMR with AMR_KUEP_BLOCKED only + * if KUEP feature is enabled + */ + BEGIN_MMU_FTR_SECTION_NESTED(70) + LOAD_REG_IMMEDIATE(\gpr2, AMR_KUEP_BLOCKED) + mtspr SPRN_IAMR, \gpr2 + isync + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUEP, 70) + .endif + +100: // skip_save_amr +#endif +.endm + +#else /* !__ASSEMBLY__ */ + +#include <linux/jump_label.h> +#include <linux/sched.h> + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + +#ifdef CONFIG_PPC_PKEY + +extern u64 __ro_after_init default_uamor; +extern u64 __ro_after_init default_amr; +extern u64 __ro_after_init default_iamr; + +#include <asm/mmu.h> +#include <asm/ptrace.h> + +/* usage of kthread_use_mm() should inherit the + * AMR value of the operating address space. But, the AMR value is + * thread-specific and we inherit the address space and not thread + * access restrictions. Because of this ignore AMR value when accessing + * userspace via kernel thread. + */ +static __always_inline u64 current_thread_amr(void) +{ + if (current->thread.regs) + return current->thread.regs->amr; + return default_amr; +} + +static __always_inline u64 current_thread_iamr(void) +{ + if (current->thread.regs) + return current->thread.regs->iamr; + return default_iamr; +} +#endif /* CONFIG_PPC_PKEY */ + +#ifdef CONFIG_PPC_KUAP + +static __always_inline void kuap_user_restore(struct pt_regs *regs) +{ + bool restore_amr = false, restore_iamr = false; + unsigned long amr, iamr; + + if (!mmu_has_feature(MMU_FTR_PKEY)) + return; + + if (!mmu_has_feature(MMU_FTR_KUAP)) { + amr = mfspr(SPRN_AMR); + if (amr != regs->amr) + restore_amr = true; + } else { + restore_amr = true; + } + + if (!mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + iamr = mfspr(SPRN_IAMR); + if (iamr != regs->iamr) + restore_iamr = true; + } else { + restore_iamr = true; + } + + + if (restore_amr || restore_iamr) { + isync(); + if (restore_amr) + mtspr(SPRN_AMR, regs->amr); + if (restore_iamr) + mtspr(SPRN_IAMR, regs->iamr); + } + /* + * 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 __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) +{ + if (likely(regs->amr == amr)) + return; + + isync(); + mtspr(SPRN_AMR, regs->amr); + /* + * 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. + * + * No need to restore IAMR when returning to kernel space. + */ +} + +static __always_inline unsigned long __kuap_get_and_assert_locked(void) +{ + 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; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked + +/* __kuap_lock() not required, book3s/64 does that in ASM */ + +/* + * 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 __always_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 (!mmu_has_feature(MMU_FTR_KUAP)) + return AMR_KUAP_BLOCKED; + + return mfspr(SPRN_AMR); +} + +static __always_inline void set_kuap(unsigned long value) +{ + if (!mmu_has_feature(MMU_FTR_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 __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + /* + * For radix this will be a storage protection fault (DSISR_PROTFAULT). + * For hash this will be a key fault (DSISR_KEYFAULT) + */ + /* + * We do have exception table entry, but accessing the + * userspace results in fault. This could be because we + * didn't unlock the AMR or access is denied by userspace + * using a key value that blocks access. We are only interested + * in catching the use case of accessing without unlocking + * the AMR. Hence check for BLOCK_WRITE/READ against AMR. + */ + if (is_write) { + return (regs->amr & AMR_KUAP_BLOCK_WRITE) == AMR_KUAP_BLOCK_WRITE; + } + return (regs->amr & AMR_KUAP_BLOCK_READ) == AMR_KUAP_BLOCK_READ; +} + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + unsigned long thread_amr = 0; + + // This is written so we can resolve to a single case at build time + BUILD_BUG_ON(!__builtin_constant_p(dir)); + + if (mmu_has_feature(MMU_FTR_PKEY)) + thread_amr = current_thread_amr(); + + if (dir == KUAP_READ) + set_kuap(thread_amr | AMR_KUAP_BLOCK_WRITE); + else if (dir == KUAP_WRITE) + set_kuap(thread_amr | AMR_KUAP_BLOCK_READ); + else if (dir == KUAP_READ_WRITE) + set_kuap(thread_amr); + else + BUILD_BUG(); +} + +#else /* CONFIG_PPC_KUAP */ + +static __always_inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static __always_inline void set_kuap(unsigned long value) { } + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ } + +#endif /* !CONFIG_PPC_KUAP */ + +static __always_inline void prevent_user_access(unsigned long dir) +{ + set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); +} + +static __always_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 __always_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_H */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 15b75005bc34..1c4eebbc69c9 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -18,7 +18,7 @@ * complete pgtable.h but only a portion of it. */ #include <asm/book3s/64/pgtable.h> -#include <asm/bug.h> +#include <asm/book3s/64/slice.h> #include <asm/task_size_64.h> #include <asm/cpu_has_feature.h> @@ -86,8 +86,8 @@ #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_BIT0 ASM_CONST(0x2000000000000000) -#define HPTE_R_KEY_BIT1 ASM_CONST(0x1000000000000000) +#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) @@ -103,8 +103,8 @@ #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_BIT3 ASM_CONST(0x0000000000000400) -#define HPTE_R_KEY_BIT4 ASM_CONST(0x0000000000000200) +#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) @@ -452,7 +452,10 @@ static inline unsigned long hpt_hash(unsigned long vpn, #define HPTE_LOCAL_UPDATE 0x1 #define HPTE_NOHPTE_UPDATE 0x2 +#define HPTE_USE_KERNEL_KEY 0x4 +long hpte_insert_repeating(unsigned long hash, unsigned long vpn, unsigned long pa, + unsigned long rlags, unsigned long vflags, int psize, int ssize); 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); @@ -466,6 +469,8 @@ extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long flags); extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap, unsigned long dsisr); +void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc); +int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr, unsigned long msr); 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); @@ -519,7 +524,14 @@ 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); +void preload_new_slb_context(unsigned long start, unsigned long sp); + +#ifdef CONFIG_PPC_64S_HASH_MMU +void slb_set_size(u16 size); +#else +static inline void slb_set_size(u16 size) { } +#endif + #endif /* __ASSEMBLY__ */ /* @@ -577,8 +589,8 @@ extern void slb_set_size(u16 size); * 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 (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) -#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#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 @@ -600,8 +612,11 @@ extern void slb_set_size(u16 size); * */ #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) + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + /* * For platforms that support on 65bit VA we limit the context bits */ @@ -790,7 +805,7 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, } /* - * For kernel space, we use context ids as below + * For kernel space, we use context ids as * below. Range is 512TB per context. * * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] @@ -839,6 +854,32 @@ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) unsigned htab_shift_for_mem_size(unsigned long mem_size); -#endif /* __ASSEMBLY__ */ +enum slb_index { + LINEAR_INDEX = 0, /* Kernel linear map (0xc000000000000000) */ + KSTACK_INDEX = 1, /* Kernel stack map */ +}; + +#define slb_esid_mask(ssize) \ + (((ssize) == MMU_SEGSIZE_256M) ? ESID_MASK : ESID_MASK_1T) +static inline unsigned long mk_esid_data(unsigned long ea, int ssize, + enum slb_index index) +{ + return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index; +} + +static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize, + unsigned long flags) +{ + return (vsid << slb_vsid_shift(ssize)) | flags | + ((unsigned long)ssize << SLB_VSID_SSIZE_SHIFT); +} + +static inline unsigned long mk_vsid_data(unsigned long ea, int ssize, + unsigned long flags) +{ + return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags); +} + +#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 index bb3deb76c951..fedbc5d38191 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -19,6 +19,7 @@ struct mmu_psize_def { int penc[MMU_PAGE_COUNT]; /* HPTE encoding */ unsigned int tlbiel; /* tlbiel supported for that page size */ unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */ + unsigned long h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */ union { unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ unsigned long ap; /* Ap encoding used by PowerISA 3.0 */ @@ -27,21 +28,6 @@ struct mmu_psize_def { extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; #endif /* __ASSEMBLY__ */ -/* - * 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) && \ - 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> @@ -76,19 +62,22 @@ extern struct patb_entry *partition_tb; #define PRTS_MASK 0x1f /* process table size field */ #define PRTB_MASK 0x0ffffffffffff000UL +/* Number of supported LPID bits */ +extern unsigned int mmu_lpid_bits; + /* Number of supported PID bits */ extern unsigned int mmu_pid_bits; /* Base PID to allocate from */ extern unsigned int mmu_base_pid; +extern unsigned long __ro_after_init memory_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 +#define PATB_SIZE_SHIFT (mmu_lpid_bits + 4) +#define PATB_ENTRIES (1ul << mmu_lpid_bits) typedef unsigned long mm_context_id_t; struct spinlock; @@ -107,7 +96,9 @@ typedef struct { * from EA and new context ids to build the new VAs. */ mm_context_id_t id; +#ifdef CONFIG_PPC_64S_HASH_MMU mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE]; +#endif }; /* Number of bits in the mm_cpumask */ @@ -116,9 +107,14 @@ typedef struct { /* 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; + +#ifdef CONFIG_PPC_64S_HASH_MMU struct hash_mm_context *hash_context; +#endif - unsigned long vdso_base; + void __user *vdso; /* * pagetable fragment support */ @@ -139,6 +135,7 @@ typedef struct { #endif } mm_context_t; +#ifdef CONFIG_PPC_64S_HASH_MMU static inline u16 mm_ctx_user_psize(mm_context_t *ctx) { return ctx->hash_context->user_psize; @@ -196,19 +193,32 @@ static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) /* * 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; +#else /* CONFIG_PPC_64S_HASH_MMU */ +#ifdef CONFIG_PPC_64K_PAGES +#define mmu_virtual_psize MMU_PAGE_64K +#else +#define mmu_virtual_psize MMU_PAGE_4K +#endif +#endif +extern int mmu_linear_psize; +extern int mmu_vmemmap_psize; /* MMU initialization */ void mmu_early_init_devtree(void); void hash__early_init_devtree(void); void radix__early_init_devtree(void); +#ifdef CONFIG_PPC_PKEY +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 early_init_mmu(void) +static inline void __init early_init_mmu(void) { if (radix_enabled()) return radix__early_init_mmu(); @@ -225,24 +235,38 @@ static inline void early_init_mmu_secondary(void) extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); -extern void radix__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) { - if (early_radix_enabled()) - return radix__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); - return hash__setup_initial_memory_limit(first_memblock_base, - 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. + */ + if (!early_radix_enabled()) + hash__setup_initial_memory_limit(first_memblock_base, + first_memblock_size); } #ifdef CONFIG_PPC_PSERIES -extern void radix_init_pseries(void); +void __init radix_init_pseries(void); #else -static inline void radix_init_pseries(void) { }; +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))) { \ + dec_mm_active_cpus(mm); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + +#ifdef CONFIG_PPC_64S_HASH_MMU static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; @@ -262,6 +286,7 @@ static inline unsigned long get_user_vsid(mm_context_t *ctx, return get_vsid(context, ea, ssize); } +#endif #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 index f6968c811026..dd2cff53a111 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -19,9 +19,7 @@ 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); -#ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); -#endif void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) @@ -87,9 +85,9 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *pgd, pud_t *pud) { - *pgd = __pgd(__pgtable_ptr_val(pud) | PGD_VAL_BITS); + *pgd = __p4d(__pgtable_ptr_val(pud) | PGD_VAL_BITS); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -109,9 +107,25 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) 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. KFENCE pages have + * both reserved and slab flags set so need to be freed + * kmem_cache_free. + */ + if (PageReserved(page) && !PageSlab(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) { - kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); + return __pud_free(pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 4e697bc2f4cd..48f21820afe2 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -26,16 +26,6 @@ static inline int pud_huge(pud_t pud) 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 diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index 34d1018896b3..2fce3498b000 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -30,15 +30,6 @@ static inline int pud_huge(pud_t pud) 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 diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index b01624e5c467..927d585652bc 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -2,23 +2,21 @@ #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ -#include <asm-generic/5level-fixup.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 */ @@ -32,11 +30,13 @@ #define _RPAGE_SW1 0x00800 #define _RPAGE_SW2 0x00400 #define _RPAGE_SW3 0x00200 -#define _RPAGE_RSV1 0x1000000000000000UL -#define _RPAGE_RSV2 0x0800000000000000UL -#define _RPAGE_RSV3 0x0400000000000000UL -#define _RPAGE_RSV4 0x0200000000000000UL -#define _RPAGE_RSV5 0x00040UL +#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 */ @@ -58,13 +58,12 @@ */ #define _RPAGE_RPN0 0x01000 #define _RPAGE_RPN1 0x02000 -#define _RPAGE_RPN44 0x0100000000000000UL #define _RPAGE_RPN43 0x0080000000000000UL #define _RPAGE_RPN42 0x0040000000000000UL #define _RPAGE_RPN41 0x0020000000000000UL /* Max physical address bit as per radix table */ -#define _RPAGE_PA_MAX 57 +#define _RPAGE_PA_MAX 56 /* * Max physical address bit we will use for now. @@ -103,6 +102,7 @@ * and every thing below PAGE_SHIFT; */ #define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) +#define PTE_RPN_SHIFT PAGE_SHIFT /* * 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. @@ -115,8 +115,8 @@ */ #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) +#define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_READ | _PAGE_EXEC) +#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 @@ -125,8 +125,6 @@ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) -#define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \ - H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4) /* * We define 2 sets of base prot bits, one for basic pages (ie, * cacheable kernel and user pages) and one for non cacheable @@ -136,48 +134,16 @@ #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) +#include <asm/pgtable-masks.h> /* 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_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 @@ -231,6 +197,12 @@ extern unsigned long __pmd_frag_size_shift; #define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) +#define MAX_PTRS_PER_PTE ((H_PTRS_PER_PTE > R_PTRS_PER_PTE) ? H_PTRS_PER_PTE : R_PTRS_PER_PTE) +#define MAX_PTRS_PER_PMD ((H_PTRS_PER_PMD > R_PTRS_PER_PMD) ? H_PTRS_PER_PMD : R_PTRS_PER_PMD) +#define MAX_PTRS_PER_PUD ((H_PTRS_PER_PUD > R_PTRS_PER_PUD) ? H_PTRS_PER_PUD : R_PTRS_PER_PUD) +#define MAX_PTRS_PER_PGD (1 << (H_PGD_INDEX_SIZE > RADIX_PGD_INDEX_SIZE ? \ + H_PGD_INDEX_SIZE : RADIX_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) @@ -251,7 +223,7 @@ extern unsigned long __pmd_frag_size_shift; /* Bits to mask out from a PUD to get to the PMD page */ #define PUD_MASKED_BITS 0xc0000000000000ffUL /* Bits to mask out from a PGD to get to the PUD page */ -#define PGD_MASKED_BITS 0xc0000000000000ffUL +#define P4D_MASKED_BITS 0xc0000000000000ffUL /* * Used as an indicator for rcu callback functions @@ -295,6 +267,13 @@ extern unsigned long pci_io_base; #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 @@ -317,10 +296,9 @@ extern unsigned long pci_io_base; #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) - -/* Advertise special mapping type for AGP */ -#define HAVE_PAGE_AGP +#define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) +#define FIXADDR_SIZE SZ_32M +#define FIXADDR_TOP (IOREMAP_END + FIXADDR_SIZE) #ifndef __ASSEMBLY__ @@ -382,40 +360,34 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, #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; \ + __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ }) -static inline int __pte_write(pte_t pte) -{ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); -} +/* + * On Book3S CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + * + * Note: this optimisation also exists in pte_needs_flush() and + * huge_pmd_needs_flush(). + */ +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young ptep_test_and_clear_young -#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 +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +#define pmdp_clear_flush_young pmdp_test_and_clear_young static inline int pte_write(pte_t pte) { - return __pte_write(pte) || pte_savedwrite(pte); + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); } static inline int pte_read(pte_t pte) @@ -427,24 +399,16 @@ static inline int pte_read(pte_t pte) static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - if (__pte_write(*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)) + 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 @@ -521,38 +485,14 @@ 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); } +#endif /* CONFIG_NUMA_BALANCING */ -#define pte_mk_savedwrite pte_mk_savedwrite -static inline pte_t pte_mk_savedwrite(pte_t pte) +static inline bool pte_hw_valid(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)); + return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE)) == + cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); } -#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 int pte_present(pte_t pte) { /* @@ -561,12 +501,11 @@ static inline int pte_present(pte_t pte) * invalid during ptep_set_access_flags. Hence we look for _PAGE_INVALID * if we find _PAGE_PRESENT cleared. */ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)); -} -static inline bool pte_hw_valid(pte_t pte) -{ - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT)); + 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 @@ -587,8 +526,8 @@ static inline bool pte_user(pte_t pte) 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 + * _PAGE_READ is needed for any access and will be cleared for + * PROT_NONE. Execute-only mapping via PROT_EXEC also returns false. */ if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) return false; @@ -611,19 +550,12 @@ 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)); -} - -static inline unsigned long pte_pfn(pte_t pte) -{ - return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT; + return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE); } /* 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)); } @@ -647,12 +579,7 @@ 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_mkpte(pte_t pte) -{ - return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); -} - -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { /* * write implies read, hence set both @@ -685,16 +612,6 @@ 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. @@ -703,7 +620,7 @@ static inline pte_t pte_mkuser(pte_t pte) */ static inline int pte_devmap(pte_t pte) { - u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); + __be64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); return (pte_raw(pte) & mask) == mask; } @@ -722,17 +639,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * 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 & SWP_TYPE_MASK); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_EXCLUSIVE); \ } while (0) #define SWP_TYPE_BITS 5 -#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ - & ((1UL << SWP_TYPE_BITS) - 1)) +#define SWP_TYPE_MASK ((1UL << SWP_TYPE_BITS) - 1) +#define __swp_type(x) ((x).val & SWP_TYPE_MASK) #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)}) + (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 @@ -745,11 +662,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #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)) +#define _PAGE_SWP_SOFT_DIRTY _PAGE_SOFT_DIRTY #else #define _PAGE_SWP_SOFT_DIRTY 0UL #endif /* CONFIG_MEM_SOFT_DIRTY */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_NON_IDEMPOTENT + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { @@ -767,6 +686,21 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_EXCLUSIVE)); +} + static inline bool check_pte_access(unsigned long access, unsigned long ptev) { /* @@ -815,6 +749,14 @@ static inline int pte_none(pte_t 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); @@ -862,6 +804,13 @@ static inline bool pte_ci(pte_t pte) 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); } @@ -910,6 +859,13 @@ static inline int pmd_bad(pmd_t 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); } @@ -934,8 +890,29 @@ static inline pud_t pte_pud(pte_t pte) { return __pud_raw(pte_raw(pte)); } + +static inline pte_t *pudp_ptep(pud_t *pud) +{ + return (pte_t *)pud; +} + +#define pud_pfn(pud) pte_pfn(pud_pte(pud)) +#define pud_dirty(pud) pte_dirty(pud_pte(pud)) +#define pud_young(pud) pte_young(pud_pte(pud)) +#define pud_mkold(pud) pte_pud(pte_mkold(pud_pte(pud))) +#define pud_wrprotect(pud) pte_pud(pte_wrprotect(pud_pte(pud))) +#define pud_mkdirty(pud) pte_pud(pte_mkdirty(pud_pte(pud))) +#define pud_mkclean(pud) pte_pud(pte_mkclean(pud_pte(pud))) +#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) +#define pud_mkwrite(pud) pte_pud(pte_mkwrite_novma(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pud_soft_dirty(pmd) pte_soft_dirty(pud_pte(pud)) +#define pud_mksoft_dirty(pmd) pte_pud(pte_mksoft_dirty(pud_pte(pud))) +#define pud_clear_soft_dirty(pmd) pte_pud(pte_clear_soft_dirty(pud_pte(pud))) +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + static inline int pud_bad(pud_t pud) { if (radix_enabled()) @@ -949,84 +926,67 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return pte_access_permitted(pud_pte(pud), write); } -#define pgd_write(pgd) pte_write(pgd_pte(pgd)) +#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 pgd_clear(pgd_t *pgdp) +static inline void p4d_clear(p4d_t *p4dp) { - *pgdp = __pgd(0); + *p4dp = __p4d(0); } -static inline int pgd_none(pgd_t pgd) +static inline int p4d_none(p4d_t p4d) { - return !pgd_raw(pgd); + return !p4d_raw(p4d); } -static inline int pgd_present(pgd_t pgd) +static inline int p4d_present(p4d_t p4d) { - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PRESENT)); } -static inline pte_t pgd_pte(pgd_t pgd) +static inline pte_t p4d_pte(p4d_t p4d) { - return __pte_raw(pgd_raw(pgd)); + return __pte_raw(p4d_raw(p4d)); } -static inline pgd_t pte_pgd(pte_t pte) +static inline p4d_t pte_p4d(pte_t pte) { - return __pgd_raw(pte_raw(pte)); + return __p4d_raw(pte_raw(pte)); } -static inline int pgd_bad(pgd_t pgd) +static inline int p4d_bad(p4d_t p4d) { if (radix_enabled()) - return radix__pgd_bad(pgd); - return hash__pgd_bad(pgd); + return radix__p4d_bad(p4d); + return hash__p4d_bad(p4d); } -#define pgd_access_permitted pgd_access_permitted -static inline bool pgd_access_permitted(pgd_t pgd, bool write) +#define p4d_access_permitted p4d_access_permitted +static inline bool p4d_access_permitted(p4d_t p4d, bool write) { - return pte_access_permitted(pgd_pte(pgd), write); + return pte_access_permitted(p4d_pte(p4d), write); } -extern struct page *pgd_page(pgd_t pgd); +extern struct page *p4d_page(p4d_t p4d); /* Pointers in the page table tree are physical addresses */ #define __pgtable_ptr_val(ptr) __pa(ptr) -#define pmd_page_vaddr(pmd) __va(pmd_val(pmd) & ~PMD_MASKED_BITS) -#define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) -#define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) - -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) - -/* - * Find an entry in a page-table-directory. We combine the address region - * (the high order N bits) and the pgd portion of the address. - */ - -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - -#define pud_offset(pgdp, addr) \ - (((pud_t *) pgd_page_vaddr(*(pgdp))) + pud_index(addr)) -#define pmd_offset(pudp,addr) \ - (((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr)) -#define pte_offset_kernel(dir,addr) \ - (((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr)) - -#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) - -static inline void pte_unmap(pte_t *pte) { } +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS); +} -/* to find an entry in a kernel page-table-directory */ -/* This now only contains the vmalloc pages */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) +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) \ @@ -1046,6 +1006,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p 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) @@ -1065,6 +1027,16 @@ static inline void vmemmap_remove_mapping(unsigned long start, } #endif +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (radix_enabled()) + radix__kernel_map_pages(page, numpages, enable); + else + hash__kernel_map_pages(page, numpages, enable); +} +#endif + static inline pte_t pmd_pte(pmd_t pmd) { return __pte_raw(pmd_raw(pmd)); @@ -1087,9 +1059,7 @@ static inline pte_t *pmdp_ptep(pmd_t *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))) +#define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) @@ -1111,8 +1081,6 @@ static inline int pmd_protnone(pmd_t 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) @@ -1135,12 +1103,24 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pud_t pfn_pud(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); -extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd); +extern void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd) +{ +} + +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} + extern int hash__has_transparent_hugepage(void); static inline int has_transparent_hugepage(void) { @@ -1150,6 +1130,14 @@ static inline int has_transparent_hugepage(void) } #define has_transparent_hugepage has_transparent_hugepage +static inline int has_transparent_pud_hugepage(void) +{ + if (radix_enabled()) + return radix__has_transparent_pud_hugepage(); + return 0; +} +#define has_transparent_pud_hugepage has_transparent_pud_hugepage + static inline unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set) @@ -1159,6 +1147,16 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } +static inline unsigned long +pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp, + unsigned long clr, unsigned long set) +{ + if (radix_enabled()) + return radix__pud_hugepage_update(mm, addr, pudp, clr, set); + BUG(); + return pud_val(*pudp); +} + /* * returns true for pmd migration entries, THP, devmap, hugetlb * But compile time dependent on THP config @@ -1168,10 +1166,11 @@ static inline int pmd_large(pmd_t pmd) return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) +static inline int pud_large(pud_t pud) { - return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } + /* * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too @@ -1187,14 +1186,31 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, return ((old & _PAGE_ACCESSED) != 0); } +static inline int __pudp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + unsigned long old; + + if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pud_hugepage_update(mm, addr, pudp, _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))) + 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); +} + +#define __HAVE_ARCH_PUDP_SET_WRPROTECT +static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pud_t *pudp) +{ + if (pud_write(*pudp)) + pud_hugepage_update(mm, addr, pudp, _PAGE_WRITE, 0); } /* @@ -1206,7 +1222,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, * 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 + * The page table walk rule is explained in Documentation/mm/transhuge.rst */ static inline int pmd_trans_huge(pmd_t pmd) { @@ -1218,6 +1234,17 @@ static inline int pmd_trans_huge(pmd_t pmd) return hash__pmd_trans_huge(pmd); } +static inline int pud_trans_huge(pud_t pud) +{ + if (!pud_present(pud)) + return false; + + if (radix_enabled()) + return radix__pud_trans_huge(pud); + return 0; +} + + #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { @@ -1226,21 +1253,73 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) return hash__pmd_same(pmd_a, pmd_b); } -static inline pmd_t pmd_mkhuge(pmd_t pmd) +#define pud_same pud_same +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + if (radix_enabled()) + return radix__pud_same(pud_a, pud_b); + return hash__pud_same(pud_a, pud_b); +} + + +static inline pmd_t __pmd_mkhuge(pmd_t pmd) { if (radix_enabled()) return radix__pmd_mkhuge(pmd); return hash__pmd_mkhuge(pmd); } +static inline pud_t __pud_mkhuge(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkhuge(pud); + BUG(); + return pud; +} + +/* + * pfn_pmd return a pmd_t that can be used as pmd pte entry. + */ +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)) != + cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)); +#endif + return pmd; +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pud_raw(pud) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON(1); +#endif + return pud; +} + + #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_PUDP_SET_ACCESS_FLAGS +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_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_PUDP_TEST_AND_CLEAR_YOUNG +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp); + #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, @@ -1251,6 +1330,16 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + if (radix_enabled()) + return radix__pudp_huge_get_and_clear(mm, addr, pudp); + BUG(); + return *pudp; +} + static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -1260,6 +1349,16 @@ static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, } #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_PUDP_HUGE_GET_AND_CLEAR_FULL +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pud_t *pudp, int full); + #define __HAVE_ARCH_PGTABLE_DEPOSIT static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) @@ -1303,7 +1402,17 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) { - return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); + if (radix_enabled()) + return radix__pmd_mkdevmap(pmd); + return hash__pmd_mkdevmap(pmd); +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkdevmap(pud); + BUG(); + return pud; } static inline int pmd_devmap(pmd_t pmd) @@ -1313,7 +1422,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) @@ -1322,16 +1431,6 @@ static inline int pgd_devmap(pgd_t pgd) } #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, @@ -1355,22 +1454,18 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va * 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 pgd_is_leaf pgd_is_leaf -static inline bool pgd_is_leaf(pgd_t pgd) -{ - return !!(pgd_raw(pgd) & 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 000000000000..5b178139f3c0 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pkeys.h @@ -0,0 +1,25 @@ +/* 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> + +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 index d5f5ab73dc7f..035ceecd6d67 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-4k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -11,7 +11,7 @@ #define RADIX_PGD_INDEX_SIZE 13 // size: 8B << 13 = 64KB, maps 2^13 x 512GB = 4PB /* - * One fragment per per page + * 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) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index d97db3ad9aae..357e23a403d3 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -30,11 +30,16 @@ /* 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_PGD_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) + +#define R_PTRS_PER_PTE (1 << RADIX_PTE_INDEX_SIZE) +#define R_PTRS_PER_PMD (1 << RADIX_PMD_INDEX_SIZE) +#define R_PTRS_PER_PUD (1 << RADIX_PUD_INDEX_SIZE) + /* * Size of EA range mapped by our pagetables. */ @@ -68,11 +73,11 @@ * * * 3rd quadrant expanded: - * +------------------------------+ - * | | + * +------------------------------+ Highest address (0xc010000000000000) + * +------------------------------+ KASAN shadow end (0xc00fc00000000000) * | | * | | - * +------------------------------+ Kernel vmemmap end (0xc010000000000000) + * +------------------------------+ Kernel vmemmap end/shadow start (0xc00e000000000000) * | | * | 512TB | * | | @@ -91,6 +96,23 @@ * +------------------------------+ Kernel linear (0xc.....) */ +/* For the sizes of the shadow area, see kasan.h */ + +/* + * 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 @@ -206,8 +228,10 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr, * 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 to vmalloc region are not tolerated, so there is - * a ptesync in flush_cache_vmap. + * 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. */ } @@ -226,10 +250,14 @@ static inline int radix__pud_bad(pud_t pud) return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); } +static inline int radix__pud_same(pud_t pud_a, pud_t pud_b) +{ + return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0); +} -static inline int radix__pgd_bad(pgd_t pgd) +static inline int radix__p4d_bad(p4d_t p4d) { - return !!(pgd_val(pgd) & RADIX_PGD_BAD_BITS); + return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -244,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE); } +static inline int radix__pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; +} + +static inline pud_t radix__pud_mkhuge(pud_t pud) +{ + return __pud(pud_val(pud) | _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 unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, 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, @@ -254,6 +295,9 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, 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); +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp); + static inline int radix__has_transparent_hugepage(void) { /* For radix 2M at PMD level means thp */ @@ -261,11 +305,35 @@ static inline int radix__has_transparent_hugepage(void) return 1; return 0; } + +static inline int radix__has_transparent_pud_hugepage(void) +{ + /* For radix 1G at PUD level means pud hugepage support */ + if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_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)); +} + +static inline pud_t radix__pud_mkdevmap(pud_t pud) +{ + return __pud(pud_val(pud) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +struct vmem_altmap; +struct dev_pagemap; extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); @@ -289,8 +357,22 @@ static inline unsigned long radix__get_tree_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int radix__create_section_mapping(unsigned long start, unsigned long end, int nid); +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 */ + +void radix__kernel_map_pages(struct page *page, int numpages, int enable); + +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +#define vmemmap_can_optimize vmemmap_can_optimize +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +#endif + +#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h index f0d3194ba41b..5fbe18544cbd 100644 --- a/arch/powerpc/include/asm/book3s/64/slice.h +++ b/arch/powerpc/include/asm/book3s/64/slice.h @@ -2,6 +2,16 @@ #ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H #define _ASM_POWERPC_BOOK3S_64_SLICE_H +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_PPC_64S_HASH_MMU +#ifdef CONFIG_HUGETLB_PAGE +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#endif +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#endif + #define SLICE_LOW_SHIFT 28 #define SLICE_LOW_TOP (0x100000000ul) #define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) @@ -13,4 +23,20 @@ #define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW_USER64 +struct mm_struct; + +unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, + unsigned long flags, unsigned int psize, + int topdown); + +unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); + +void slice_set_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long len, unsigned int psize); + +void slice_init_new_context_exec(struct mm_struct *mm); +void slice_setup_new_exec(void); + +#endif /* __ASSEMBLY__ */ + #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 index 64d02a704bcb..146287d9580f 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void) if (radix_enabled()) return; + /* + * apply_to_page_range can call us this preempt enabled when + * operating on kernel page tables. + */ + preempt_disable(); batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } @@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void) if (batch->index) __flush_tlb_pending(batch); batch->active = 0; + preempt_enable(); } #define arch_flush_lazy_mmu_mode() do {} while (0) @@ -59,62 +65,15 @@ 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); + +#ifdef CONFIG_PPC_64S_HASH_MMU /* Private function for use by PCI IO mapping code */ -extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, - unsigned long end); -extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr); +extern void __flush_hash_table_range(unsigned long start, unsigned long end); +void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); +#else +static inline void __flush_hash_table_range(unsigned long start, unsigned long end) { } +#endif #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 index ca8db193ae38..a38542259fab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -2,10 +2,29 @@ #ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H #define _ASM_POWERPC_TLBFLUSH_RADIX_H +#include <asm/hvcall.h> + +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + 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; @@ -20,7 +39,7 @@ 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__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) @@ -45,8 +64,12 @@ 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); +void radix__flush_tlb_pwc_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_pud_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); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dcb5c3839d2f..fd642b729775 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -5,6 +5,7 @@ #define MMU_NO_CONTEXT ~0UL #include <linux/mm_types.h> +#include <linux/mmu_notifier.h> #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> @@ -14,7 +15,6 @@ enum { TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ }; -#ifdef CONFIG_PPC_NATIVE static inline void tlbiel_all(void) { /* @@ -30,9 +30,6 @@ static inline void tlbiel_all(void) 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) { @@ -51,8 +48,15 @@ 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); + radix__flush_pmd_tlb_range(vma, start, end); +} + +#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE +static inline void flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + radix__flush_pud_tlb_range(vma, start, end); } #define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE @@ -61,91 +65,154 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long end) { if (radix_enabled()) - return radix__flush_hugetlb_tlb_range(vma, start, end); - return hash__flush_tlb_range(vma, start, end); + radix__flush_hugetlb_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); + radix__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); + radix__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); + radix__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); + radix__local_flush_tlb_page(vma, vmaddr); } -static inline void local_flush_all_mm(struct mm_struct *mm) +static inline void local_flush_tlb_page_psize(struct mm_struct *mm, + unsigned long vmaddr, int psize) { if (radix_enabled()) - return radix__local_flush_all_mm(mm); - return hash__local_flush_all_mm(mm); + radix__local_flush_tlb_page_psize(mm, vmaddr, psize); } static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) - return radix__tlb_flush(tlb); - return hash__tlb_flush(tlb); + radix__tlb_flush(tlb); + else + 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); + radix__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); + radix__flush_tlb_page(vma, vmaddr); } #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) + unsigned long address, + pte_t *ptep) +{ + /* + * Book3S 64 does not require spurious fault flushes because the PTE + * must be re-fetched in case of an access permission problem. So the + * only reason for a spurious fault should be concurrent modification + * to the PTE, in which case the PTE will eventually be re-fetched by + * the MMU when it attempts the access again. + * + * See: Power ISA Version 3.1B, 6.10.1.2 Modifying a Translation Table + * Entry, Setting a Reference or Change Bit or Upgrading Access + * Authority (PTE Subject to Atomic Hardware Updates): + * + * "If the only change being made to a valid PTE that is subject to + * atomic hardware updates is to set the Reference or Change bit to + * 1 or to upgrade access authority, a simpler sequence suffices + * because the translation hardware will refetch the PTE if an + * access is attempted for which the only problems were reference + * and/or change bits needing to be set or insufficient access + * authority." + * + * The nest MMU in POWER9 does not perform this PTE re-fetch, but + * it avoids the spurious fault problem by flushing the TLB before + * upgrading PTE permissions, see radix__ptep_set_access_flags. + */ +} + +static inline bool __pte_flags_need_flush(unsigned long oldval, + unsigned long newval) +{ + unsigned long delta = oldval ^ newval; + + /* + * The return value of this function doesn't matter for hash, + * ptep_modify_prot_start() does a pte_update() which does or schedules + * any necessary hash table update and flush. + */ + if (!radix_enabled()) + return true; + + /* + * We do not expect kernel mappings or non-PTEs or not-present PTEs. + */ + VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PRESENT)); + + /* + * Must flush on any change except READ, WRITE, EXEC, DIRTY, ACCESSED. + * + * In theory, some changed software bits could be tolerated, in + * practice those should rarely if ever matter. + */ + + if (delta & ~(_PAGE_RWX | _PAGE_DIRTY | _PAGE_ACCESSED)) + return true; + + /* + * If any of the above was present in old but cleared in new, flush. + * With the exception of _PAGE_ACCESSED, don't worry about flushing + * if that was cleared (see the comment in ptep_clear_flush_young()). + */ + if ((delta & ~_PAGE_ACCESSED) & oldval) + return true; + + return false; +} + +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte)); +} +#define pte_needs_flush pte_needs_flush + +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { - /* See ptep_set_access_flags comment */ - if (atomic_read(&vma->vm_mm->context.copros) > 0) - flush_tlb_page(vma, address); + return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd)); } +#define huge_pmd_needs_flush huge_pmd_needs_flush extern bool tlbie_capable; extern bool tlbie_enabled; diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index 0e1263455d73..f42d68c6b314 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -8,34 +8,4 @@ #include <asm/book3s/32/pgtable.h> #endif -#define FIRST_USER_ADDRESS 0UL -#ifndef __ASSEMBLY__ -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); - - -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - * On machines which use an MMU hash table, we use this to put a - * corresponding HPTE into the hash table ahead of time, instead of - * waiting for the inevitable extra hash-table miss exception. - */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); - -#endif /* __ASSEMBLY__ */ #endif |