diff options
Diffstat (limited to 'arch/arm64/mm/mmu.c')
| -rw-r--r-- | arch/arm64/mm/mmu.c | 911 |
1 files changed, 782 insertions, 129 deletions
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e2739b69e11b..9ae7ce00a7ef 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -26,6 +26,9 @@ #include <linux/set_memory.h> #include <linux/kfence.h> #include <linux/pkeys.h> +#include <linux/mm_inline.h> +#include <linux/pagewalk.h> +#include <linux/stop_machine.h> #include <asm/barrier.h> #include <asm/cputype.h> @@ -46,6 +49,8 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ +DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); + u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -107,7 +112,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, } EXPORT_SYMBOL(phys_mem_access_prot); -static phys_addr_t __init early_pgtable_alloc(int shift) +static phys_addr_t __init early_pgtable_alloc(enum pgtable_type pgtable_type) { phys_addr_t phys; @@ -189,11 +194,11 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end, } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static int alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { unsigned long next; pmd_t pmd = READ_ONCE(*pmdp); @@ -207,7 +212,9 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, if (flags & NO_EXEC_MAPPINGS) pmdval |= PMD_TABLE_PXN; BUG_ON(!pgtable_alloc); - pte_phys = pgtable_alloc(PAGE_SHIFT); + pte_phys = pgtable_alloc(TABLE_PTE); + if (pte_phys == INVALID_PHYS_ADDR) + return -ENOMEM; ptep = pte_set_fixmap(pte_phys); init_clear_pgtable(ptep); ptep += pte_index(addr); @@ -239,11 +246,13 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, * walker. */ pte_clear_fixmap(); + + return 0; } -static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), int flags) +static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags) { unsigned long next; @@ -264,21 +273,29 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmdp, addr, next, phys, prot, - pgtable_alloc, flags); + int ret; + + ret = alloc_init_cont_pte(pmdp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + return ret; BUG_ON(pmd_val(old_pmd) != 0 && pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; } while (pmdp++, addr = next, addr != end); + + return 0; } -static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), int flags) +static int alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; @@ -294,7 +311,9 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, if (flags & NO_EXEC_MAPPINGS) pudval |= PUD_TABLE_PXN; BUG_ON(!pgtable_alloc); - pmd_phys = pgtable_alloc(PMD_SHIFT); + pmd_phys = pgtable_alloc(TABLE_PMD); + if (pmd_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pmdp = pmd_set_fixmap(pmd_phys); init_clear_pgtable(pmdp); pmdp += pmd_index(addr); @@ -314,20 +333,26 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + ret = init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + if (ret) + goto out; pmdp += pmd_index(next) - pmd_index(addr); phys += next - addr; } while (addr = next, addr != end); +out: pmd_clear_fixmap(); + + return ret; } -static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret = 0; unsigned long next; p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; @@ -339,7 +364,9 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, if (flags & NO_EXEC_MAPPINGS) p4dval |= P4D_TABLE_PXN; BUG_ON(!pgtable_alloc); - pud_phys = pgtable_alloc(PUD_SHIFT); + pud_phys = pgtable_alloc(TABLE_PUD); + if (pud_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pudp = pud_set_fixmap(pud_phys); init_clear_pgtable(pudp); pudp += pud_index(addr); @@ -369,8 +396,10 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pudp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_cont_pmd(pudp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(pud_val(old_pud) != 0 && pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); @@ -378,14 +407,18 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys += next - addr; } while (pudp++, addr = next, addr != end); +out: pud_clear_fixmap(); + + return ret; } -static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pgd_t pgd = READ_ONCE(*pgdp); p4d_t *p4dp; @@ -397,7 +430,9 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, if (flags & NO_EXEC_MAPPINGS) pgdval |= PGD_TABLE_PXN; BUG_ON(!pgtable_alloc); - p4d_phys = pgtable_alloc(P4D_SHIFT); + p4d_phys = pgtable_alloc(TABLE_P4D); + if (p4d_phys == INVALID_PHYS_ADDR) + return -ENOMEM; p4dp = p4d_set_fixmap(p4d_phys); init_clear_pgtable(p4dp); p4dp += p4d_index(addr); @@ -412,8 +447,10 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, next = p4d_addr_end(addr, end); - alloc_init_pud(p4dp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_pud(p4dp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(p4d_val(old_p4d) != 0 && p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); @@ -421,15 +458,19 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, phys += next - addr; } while (p4dp++, addr = next, addr != end); +out: p4d_clear_fixmap(); + + return ret; } -static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static int __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_pgd(pgdir, virt); @@ -438,7 +479,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, * within a page, we cannot map the region as the caller expects. */ if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) - return; + return -EINVAL; phys &= PAGE_MASK; addr = virt & PAGE_MASK; @@ -446,59 +487,486 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, do { next = pgd_addr_end(addr, end); - alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, - flags); + ret = alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, + flags); + if (ret) + return ret; phys += next - addr; } while (pgdp++, addr = next, addr != end); + + return 0; } -static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static int __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; + mutex_lock(&fixmap_lock); - __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, - pgtable_alloc, flags); + ret = __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, + pgtable_alloc, flags); mutex_unlock(&fixmap_lock); + + return ret; } -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -extern __alias(__create_pgd_mapping_locked) -void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, - phys_addr_t size, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), int flags); -#endif +static void early_create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) +{ + int ret; + + ret = __create_pgd_mapping(pgdir, phys, virt, size, prot, pgtable_alloc, + flags); + if (ret) + panic("Failed to create page tables\n"); +} -static phys_addr_t __pgd_pgtable_alloc(int shift) +static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp, + enum pgtable_type pgtable_type) { /* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */ - void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO); + struct ptdesc *ptdesc = pagetable_alloc(gfp & ~__GFP_ZERO, 0); + phys_addr_t pa; + + if (!ptdesc) + return INVALID_PHYS_ADDR; + + pa = page_to_phys(ptdesc_page(ptdesc)); + + switch (pgtable_type) { + case TABLE_PTE: + BUG_ON(!pagetable_pte_ctor(mm, ptdesc)); + break; + case TABLE_PMD: + BUG_ON(!pagetable_pmd_ctor(mm, ptdesc)); + break; + case TABLE_PUD: + pagetable_pud_ctor(ptdesc); + break; + case TABLE_P4D: + pagetable_p4d_ctor(ptdesc); + break; + } + + return pa; +} + +static phys_addr_t +pgd_pgtable_alloc_init_mm_gfp(enum pgtable_type pgtable_type, gfp_t gfp) +{ + return __pgd_pgtable_alloc(&init_mm, gfp, pgtable_type); +} - BUG_ON(!ptr); - return __pa(ptr); +static phys_addr_t __maybe_unused +pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type) +{ + return pgd_pgtable_alloc_init_mm_gfp(pgtable_type, GFP_PGTABLE_KERNEL); +} + +static phys_addr_t +pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type) +{ + return __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type); } -static phys_addr_t pgd_pgtable_alloc(int shift) +static void split_contpte(pte_t *ptep) { - phys_addr_t pa = __pgd_pgtable_alloc(shift); - struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa)); + int i; + + ptep = PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES); + for (i = 0; i < CONT_PTES; i++, ptep++) + __set_pte(ptep, pte_mknoncont(__ptep_get(ptep))); +} + +static int split_pmd(pmd_t *pmdp, pmd_t pmd, gfp_t gfp, bool to_cont) +{ + pmdval_t tableprot = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF; + unsigned long pfn = pmd_pfn(pmd); + pgprot_t prot = pmd_pgprot(pmd); + phys_addr_t pte_phys; + pte_t *ptep; + int i; + + pte_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PTE, gfp); + if (pte_phys == INVALID_PHYS_ADDR) + return -ENOMEM; + ptep = (pte_t *)phys_to_virt(pte_phys); + + if (pgprot_val(prot) & PMD_SECT_PXN) + tableprot |= PMD_TABLE_PXN; + + prot = __pgprot((pgprot_val(prot) & ~PTE_TYPE_MASK) | PTE_TYPE_PAGE); + prot = __pgprot(pgprot_val(prot) & ~PTE_CONT); + if (to_cont) + prot = __pgprot(pgprot_val(prot) | PTE_CONT); + + for (i = 0; i < PTRS_PER_PTE; i++, ptep++, pfn++) + __set_pte(ptep, pfn_pte(pfn, prot)); /* - * Call proper page table ctor in case later we need to - * call core mm functions like apply_to_page_range() on - * this pre-allocated page table. + * Ensure the pte entries are visible to the table walker by the time + * the pmd entry that points to the ptes is visible. + */ + dsb(ishst); + __pmd_populate(pmdp, pte_phys, tableprot); + + return 0; +} + +static void split_contpmd(pmd_t *pmdp) +{ + int i; + + pmdp = PTR_ALIGN_DOWN(pmdp, sizeof(*pmdp) * CONT_PMDS); + for (i = 0; i < CONT_PMDS; i++, pmdp++) + set_pmd(pmdp, pmd_mknoncont(pmdp_get(pmdp))); +} + +static int split_pud(pud_t *pudp, pud_t pud, gfp_t gfp, bool to_cont) +{ + pudval_t tableprot = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF; + unsigned int step = PMD_SIZE >> PAGE_SHIFT; + unsigned long pfn = pud_pfn(pud); + pgprot_t prot = pud_pgprot(pud); + phys_addr_t pmd_phys; + pmd_t *pmdp; + int i; + + pmd_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PMD, gfp); + if (pmd_phys == INVALID_PHYS_ADDR) + return -ENOMEM; + pmdp = (pmd_t *)phys_to_virt(pmd_phys); + + if (pgprot_val(prot) & PMD_SECT_PXN) + tableprot |= PUD_TABLE_PXN; + + prot = __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT); + prot = __pgprot(pgprot_val(prot) & ~PTE_CONT); + if (to_cont) + prot = __pgprot(pgprot_val(prot) | PTE_CONT); + + for (i = 0; i < PTRS_PER_PMD; i++, pmdp++, pfn += step) + set_pmd(pmdp, pfn_pmd(pfn, prot)); + + /* + * Ensure the pmd entries are visible to the table walker by the time + * the pud entry that points to the pmds is visible. + */ + dsb(ishst); + __pud_populate(pudp, pmd_phys, tableprot); + + return 0; +} + +static int split_kernel_leaf_mapping_locked(unsigned long addr) +{ + pgd_t *pgdp, pgd; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + int ret = 0; + + /* + * PGD: If addr is PGD aligned then addr already describes a leaf + * boundary. If not present then there is nothing to split. + */ + if (ALIGN_DOWN(addr, PGDIR_SIZE) == addr) + goto out; + pgdp = pgd_offset_k(addr); + pgd = pgdp_get(pgdp); + if (!pgd_present(pgd)) + goto out; + + /* + * P4D: If addr is P4D aligned then addr already describes a leaf + * boundary. If not present then there is nothing to split. + */ + if (ALIGN_DOWN(addr, P4D_SIZE) == addr) + goto out; + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + if (!p4d_present(p4d)) + goto out; + + /* + * PUD: If addr is PUD aligned then addr already describes a leaf + * boundary. If not present then there is nothing to split. Otherwise, + * if we have a pud leaf, split to contpmd. + */ + if (ALIGN_DOWN(addr, PUD_SIZE) == addr) + goto out; + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + if (!pud_present(pud)) + goto out; + if (pud_leaf(pud)) { + ret = split_pud(pudp, pud, GFP_PGTABLE_KERNEL, true); + if (ret) + goto out; + } + + /* + * CONTPMD: If addr is CONTPMD aligned then addr already describes a + * leaf boundary. If not present then there is nothing to split. + * Otherwise, if we have a contpmd leaf, split to pmd. + */ + if (ALIGN_DOWN(addr, CONT_PMD_SIZE) == addr) + goto out; + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + if (!pmd_present(pmd)) + goto out; + if (pmd_leaf(pmd)) { + if (pmd_cont(pmd)) + split_contpmd(pmdp); + /* + * PMD: If addr is PMD aligned then addr already describes a + * leaf boundary. Otherwise, split to contpte. + */ + if (ALIGN_DOWN(addr, PMD_SIZE) == addr) + goto out; + ret = split_pmd(pmdp, pmd, GFP_PGTABLE_KERNEL, true); + if (ret) + goto out; + } + + /* + * CONTPTE: If addr is CONTPTE aligned then addr already describes a + * leaf boundary. If not present then there is nothing to split. + * Otherwise, if we have a contpte leaf, split to pte. + */ + if (ALIGN_DOWN(addr, CONT_PTE_SIZE) == addr) + goto out; + ptep = pte_offset_kernel(pmdp, addr); + pte = __ptep_get(ptep); + if (!pte_present(pte)) + goto out; + if (pte_cont(pte)) + split_contpte(ptep); + +out: + return ret; +} + +static inline bool force_pte_mapping(void) +{ + const bool bbml2 = system_capabilities_finalized() ? + system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); + + if (debug_pagealloc_enabled()) + return true; + if (bbml2) + return false; + return rodata_full || arm64_kfence_can_set_direct_map() || is_realm_world(); +} + +static inline bool split_leaf_mapping_possible(void) +{ + /* + * !BBML2_NOABORT systems should never run into scenarios where we would + * have to split. So exit early and let calling code detect it and raise + * a warning. + */ + if (!system_supports_bbml2_noabort()) + return false; + return !force_pte_mapping(); +} + +static DEFINE_MUTEX(pgtable_split_lock); + +int split_kernel_leaf_mapping(unsigned long start, unsigned long end) +{ + int ret; + + /* + * Exit early if the region is within a pte-mapped area or if we can't + * split. For the latter case, the permission change code will raise a + * warning if not already pte-mapped. + */ + if (!split_leaf_mapping_possible() || is_kfence_address((void *)start)) + return 0; + + /* + * Ensure start and end are at least page-aligned since this is the + * finest granularity we can split to. + */ + if (start != PAGE_ALIGN(start) || end != PAGE_ALIGN(end)) + return -EINVAL; + + mutex_lock(&pgtable_split_lock); + arch_enter_lazy_mmu_mode(); + + /* + * The split_kernel_leaf_mapping_locked() may sleep, it is not a + * problem for ARM64 since ARM64's lazy MMU implementation allows + * sleeping. * - * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is - * folded, and if so pagetable_pte_ctor() becomes nop. + * Optimize for the common case of splitting out a single page from a + * larger mapping. Here we can just split on the "least aligned" of + * start and end and this will guarantee that there must also be a split + * on the more aligned address since the both addresses must be in the + * same contpte block and it must have been split to ptes. + */ + if (end - start == PAGE_SIZE) { + start = __ffs(start) < __ffs(end) ? start : end; + ret = split_kernel_leaf_mapping_locked(start); + } else { + ret = split_kernel_leaf_mapping_locked(start); + if (!ret) + ret = split_kernel_leaf_mapping_locked(end); + } + + arch_leave_lazy_mmu_mode(); + mutex_unlock(&pgtable_split_lock); + return ret; +} + +static int split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + gfp_t gfp = *(gfp_t *)walk->private; + pud_t pud = pudp_get(pudp); + int ret = 0; + + if (pud_leaf(pud)) + ret = split_pud(pudp, pud, gfp, false); + + return ret; +} + +static int split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + gfp_t gfp = *(gfp_t *)walk->private; + pmd_t pmd = pmdp_get(pmdp); + int ret = 0; + + if (pmd_leaf(pmd)) { + if (pmd_cont(pmd)) + split_contpmd(pmdp); + ret = split_pmd(pmdp, pmd, gfp, false); + + /* + * We have split the pmd directly to ptes so there is no need to + * visit each pte to check if they are contpte. + */ + walk->action = ACTION_CONTINUE; + } + + return ret; +} + +static int split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t pte = __ptep_get(ptep); + + if (pte_cont(pte)) + split_contpte(ptep); + + return 0; +} + +static const struct mm_walk_ops split_to_ptes_ops = { + .pud_entry = split_to_ptes_pud_entry, + .pmd_entry = split_to_ptes_pmd_entry, + .pte_entry = split_to_ptes_pte_entry, +}; + +static int range_split_to_ptes(unsigned long start, unsigned long end, gfp_t gfp) +{ + int ret; + + arch_enter_lazy_mmu_mode(); + ret = walk_kernel_page_table_range_lockless(start, end, + &split_to_ptes_ops, NULL, &gfp); + arch_leave_lazy_mmu_mode(); + + return ret; +} + +static bool linear_map_requires_bbml2 __initdata; + +u32 idmap_kpti_bbml2_flag; + +static void __init init_idmap_kpti_bbml2_flag(void) +{ + WRITE_ONCE(idmap_kpti_bbml2_flag, 1); + /* Must be visible to other CPUs before stop_machine() is called. */ + smp_mb(); +} + +static int __init linear_map_split_to_ptes(void *__unused) +{ + /* + * Repainting the linear map must be done by CPU0 (the boot CPU) because + * that's the only CPU that we know supports BBML2. The other CPUs will + * be held in a waiting area with the idmap active. */ - if (shift == PAGE_SHIFT) - BUG_ON(!pagetable_pte_ctor(ptdesc)); - else if (shift == PMD_SHIFT) - BUG_ON(!pagetable_pmd_ctor(ptdesc)); + if (!smp_processor_id()) { + unsigned long lstart = _PAGE_OFFSET(vabits_actual); + unsigned long lend = PAGE_END; + unsigned long kstart = (unsigned long)lm_alias(_stext); + unsigned long kend = (unsigned long)lm_alias(__init_begin); + int ret; - return pa; + /* + * Wait for all secondary CPUs to be put into the waiting area. + */ + smp_cond_load_acquire(&idmap_kpti_bbml2_flag, VAL == num_online_cpus()); + + /* + * Walk all of the linear map [lstart, lend), except the kernel + * linear map alias [kstart, kend), and split all mappings to + * PTE. The kernel alias remains static throughout runtime so + * can continue to be safely mapped with large mappings. + */ + ret = range_split_to_ptes(lstart, kstart, GFP_ATOMIC); + if (!ret) + ret = range_split_to_ptes(kend, lend, GFP_ATOMIC); + if (ret) + panic("Failed to split linear map\n"); + flush_tlb_kernel_range(lstart, lend); + + /* + * Relies on dsb in flush_tlb_kernel_range() to avoid reordering + * before any page table split operations. + */ + WRITE_ONCE(idmap_kpti_bbml2_flag, 0); + } else { + typedef void (wait_split_fn)(void); + extern wait_split_fn wait_linear_map_split_to_ptes; + wait_split_fn *wait_fn; + + wait_fn = (void *)__pa_symbol(wait_linear_map_split_to_ptes); + + /* + * At least one secondary CPU doesn't support BBML2 so cannot + * tolerate the size of the live mappings changing. So have the + * secondary CPUs wait for the boot CPU to make the changes + * with the idmap active and init_mm inactive. + */ + cpu_install_idmap(); + wait_fn(); + cpu_uninstall_idmap(); + } + + return 0; +} + +void __init linear_map_maybe_split_to_ptes(void) +{ + if (linear_map_requires_bbml2 && !system_supports_bbml2_noabort()) { + init_idmap_kpti_bbml2_flag(); + stop_machine(linear_map_split_to_ptes, NULL, cpu_online_mask); + } } /* @@ -514,8 +982,8 @@ void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, @@ -529,8 +997,8 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, if (page_mappings_only) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - pgd_pgtable_alloc, flags); + early_create_pgd_mapping(mm->pgd, phys, virt, size, prot, + pgd_pgtable_alloc_special_mm, flags); } static void update_mapping_prot(phys_addr_t phys, unsigned long virt, @@ -542,8 +1010,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); /* flush the TLBs after updating live kernel mappings */ flush_tlb_kernel_range(virt, virt + size); @@ -552,8 +1020,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, - prot, early_pgtable_alloc, flags); + early_create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, + prot, early_pgtable_alloc, flags); } void __init mark_linear_text_alias_ro(void) @@ -561,8 +1029,8 @@ void __init mark_linear_text_alias_ro(void) /* * Remove the write permissions from the linear alias of .text/.rodata */ - update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext), - (unsigned long)__init_begin - (unsigned long)_stext, + update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text), + (unsigned long)__init_begin - (unsigned long)_text, PAGE_KERNEL_RO); } @@ -613,6 +1081,33 @@ static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); __kfence_pool = phys_to_virt(kfence_pool); } + +bool arch_kfence_init_pool(void) +{ + unsigned long start = (unsigned long)__kfence_pool; + unsigned long end = start + KFENCE_POOL_SIZE; + int ret; + + /* Exit early if we know the linear map is already pte-mapped. */ + if (!split_leaf_mapping_possible()) + return true; + + /* Kfence pool is already pte-mapped for the early init case. */ + if (kfence_early_init) + return true; + + mutex_lock(&pgtable_split_lock); + ret = range_split_to_ptes(start, end, GFP_PGTABLE_KERNEL); + mutex_unlock(&pgtable_split_lock); + + /* + * Since the system supports bbml2_noabort, tlb invalidation is not + * required here; the pgtable mappings have been split to pte but larger + * entries may safely linger in the TLB. + */ + + return !ret; +} #else /* CONFIG_KFENCE */ static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; } @@ -623,7 +1118,7 @@ static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { static void __init map_mem(pgd_t *pgdp) { static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN); - phys_addr_t kernel_start = __pa_symbol(_stext); + phys_addr_t kernel_start = __pa_symbol(_text); phys_addr_t kernel_end = __pa_symbol(__init_begin); phys_addr_t start, end; phys_addr_t early_kfence_pool; @@ -645,7 +1140,9 @@ static void __init map_mem(pgd_t *pgdp) early_kfence_pool = arm64_kfence_alloc_pool(); - if (can_set_direct_map()) + linear_map_requires_bbml2 = !force_pte_mapping() && can_set_direct_map(); + + if (force_pte_mapping()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* @@ -670,7 +1167,7 @@ static void __init map_mem(pgd_t *pgdp) } /* - * Map the linear alias of the [_stext, __init_begin) interval + * Map the linear alias of the [_text, __init_begin) interval * as non-executable now, and remove the write permission in * mark_linear_text_alias_ro() below (which will be called after * alternative patching has completed). This makes the contents @@ -697,6 +1194,10 @@ void mark_rodata_ro(void) WRITE_ONCE(rodata_is_rw, false); update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); + /* mark the range between _text and _stext as read only. */ + update_mapping_prot(__pa_symbol(_text), (unsigned long)_text, + (unsigned long)_stext - (unsigned long)_text, + PAGE_KERNEL_RO); } static void __init declare_vma(struct vm_struct *vma, @@ -722,7 +1223,97 @@ static void __init declare_vma(struct vm_struct *vma, } #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -static pgprot_t kernel_exec_prot(void) +#define KPTI_NG_TEMP_VA (-(1UL << PMD_SHIFT)) + +static phys_addr_t kpti_ng_temp_alloc __initdata; + +static phys_addr_t __init kpti_ng_pgd_alloc(enum pgtable_type type) +{ + kpti_ng_temp_alloc -= PAGE_SIZE; + return kpti_ng_temp_alloc; +} + +static int __init __kpti_install_ng_mappings(void *__unused) +{ + typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long); + extern kpti_remap_fn idmap_kpti_install_ng_mappings; + kpti_remap_fn *remap_fn; + + int cpu = smp_processor_id(); + int levels = CONFIG_PGTABLE_LEVELS; + int order = order_base_2(levels); + u64 kpti_ng_temp_pgd_pa = 0; + pgd_t *kpti_ng_temp_pgd; + u64 alloc = 0; + + if (levels == 5 && !pgtable_l5_enabled()) + levels = 4; + else if (levels == 4 && !pgtable_l4_enabled()) + levels = 3; + + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); + + if (!cpu) { + int ret; + + alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); + kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE); + kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd); + + // + // Create a minimal page table hierarchy that permits us to map + // the swapper page tables temporarily as we traverse them. + // + // The physical pages are laid out as follows: + // + // +--------+-/-------+-/------ +-/------ +-\\\--------+ + // : PTE[] : | PMD[] : | PUD[] : | P4D[] : ||| PGD[] : + // +--------+-\-------+-\------ +-\------ +-///--------+ + // ^ + // The first page is mapped into this hierarchy at a PMD_SHIFT + // aligned virtual address, so that we can manipulate the PTE + // level entries while the mapping is active. The first entry + // covers the PTE[] page itself, the remaining entries are free + // to be used as a ad-hoc fixmap. + // + ret = __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc), + KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, + kpti_ng_pgd_alloc, 0); + if (ret) + panic("Failed to create page tables\n"); + } + + cpu_install_idmap(); + remap_fn(cpu, num_online_cpus(), kpti_ng_temp_pgd_pa, KPTI_NG_TEMP_VA); + cpu_uninstall_idmap(); + + if (!cpu) { + free_pages(alloc, order); + arm64_use_ng_mappings = true; + } + + return 0; +} + +void __init kpti_install_ng_mappings(void) +{ + /* Check whether KPTI is going to be used */ + if (!arm64_kernel_unmapped_at_el0()) + return; + + /* + * We don't need to rewrite the page-tables if either we've done + * it already or we have KASLR enabled and therefore have not + * created any global mappings at all. + */ + if (arm64_use_ng_mappings) + return; + + init_idmap_kpti_bbml2_flag(); + stop_machine(__kpti_install_ng_mappings, NULL, cpu_online_mask); +} + +static pgprot_t __init kernel_exec_prot(void) { return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; } @@ -742,9 +1333,9 @@ static int __init map_entry_trampoline(void) /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); - __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, - entry_tramp_text_size(), prot, - __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS); + early_create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) @@ -767,38 +1358,41 @@ static void __init declare_kernel_vmas(void) { static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT]; - declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD); + declare_vma(&vmlinux_seg[0], _text, _etext, VM_NO_GUARD); declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD); declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD); declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD); declare_vma(&vmlinux_seg[4], _data, _end, 0); } -void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, - int level, pte_t *tbl, bool may_use_cont, u64 va_offset); +void __pi_map_range(phys_addr_t *pte, u64 start, u64 end, phys_addr_t pa, + pgprot_t prot, int level, pte_t *tbl, bool may_use_cont, + u64 va_offset); static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init, - kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init; + kpti_bbml2_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init; static void __init create_idmap(void) { - u64 start = __pa_symbol(__idmap_text_start); - u64 end = __pa_symbol(__idmap_text_end); - u64 ptep = __pa_symbol(idmap_ptes); + phys_addr_t start = __pa_symbol(__idmap_text_start); + phys_addr_t end = __pa_symbol(__idmap_text_end); + phys_addr_t ptep = __pa_symbol(idmap_ptes); __pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX, IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, __phys_to_virt(ptep) - ptep); - if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) { - extern u32 __idmap_kpti_flag; - u64 pa = __pa_symbol(&__idmap_kpti_flag); + if (linear_map_requires_bbml2 || + (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings)) { + phys_addr_t pa = __pa_symbol(&idmap_kpti_bbml2_flag); /* * The KPTI G-to-nG conversion code needs a read-write mapping - * of its synchronization flag in the ID map. + * of its synchronization flag in the ID map. This is also used + * when splitting the linear map to ptes if a secondary CPU + * doesn't support bbml2. */ - ptep = __pa_symbol(kpti_ptes); + ptep = __pa_symbol(kpti_bbml2_ptes); __pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL, IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, __phys_to_virt(ptep) - ptep); @@ -823,7 +1417,7 @@ static void free_hotplug_page_range(struct page *page, size_t size, vmem_altmap_free(altmap, size >> PAGE_SHIFT); } else { WARN_ON(PageReserved(page)); - free_pages((unsigned long)page_address(page), get_order(size)); + __free_pages(page, get_order(size)); } } @@ -1169,15 +1763,19 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, unsigned long addr, unsigned long next) { vmemmap_verify((pte_t *)pmdp, node, addr, next); - return 1; + + return pmd_sect(READ_ONCE(*pmdp)); } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); + /* [start, end] should be within one section */ + WARN_ON_ONCE(end - start > PAGES_PER_SECTION * sizeof(struct page)); - if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) + if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) || + (end - start < PAGES_PER_SECTION * sizeof(struct page))) return vmemmap_populate_basepages(start, end, node, altmap); else return vmemmap_populate_hugepages(start, end, node, altmap); @@ -1244,7 +1842,8 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) +static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr, + bool acquire_mmap_lock) { pte_t *table; pmd_t pmd; @@ -1256,13 +1855,25 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) return 1; } + /* See comment in pud_free_pmd_page for static key logic */ table = pte_offset_kernel(pmdp, addr); pmd_clear(pmdp); __flush_tlb_kernel_pgtable(addr); + if (static_branch_unlikely(&arm64_ptdump_lock_key) && acquire_mmap_lock) { + mmap_read_lock(&init_mm); + mmap_read_unlock(&init_mm); + } + pte_free_kernel(NULL, table); return 1; } +int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) +{ + /* If ptdump is walking the pagetables, acquire init_mm.mmap_lock */ + return __pmd_free_pte_page(pmdp, addr, /* acquire_mmap_lock = */ true); +} + int pud_free_pmd_page(pud_t *pudp, unsigned long addr) { pmd_t *table; @@ -1278,15 +1889,36 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) } table = pmd_offset(pudp, addr); + + /* + * Our objective is to prevent ptdump from reading a PMD table which has + * been freed. In this race, if pud_free_pmd_page observes the key on + * (which got flipped by ptdump) then the mmap lock sequence here will, + * as a result of the mmap write lock/unlock sequence in ptdump, give + * us the correct synchronization. If not, this means that ptdump has + * yet not started walking the pagetables - the sequence of barriers + * issued by __flush_tlb_kernel_pgtable() guarantees that ptdump will + * observe an empty PUD. + */ + pud_clear(pudp); + __flush_tlb_kernel_pgtable(addr); + if (static_branch_unlikely(&arm64_ptdump_lock_key)) { + mmap_read_lock(&init_mm); + mmap_read_unlock(&init_mm); + } + pmdp = table; next = addr; end = addr + PUD_SIZE; do { - pmd_free_pte_page(pmdp, next); + if (pmd_present(pmdp_get(pmdp))) + /* + * PMD has been isolated, so ptdump won't see it. No + * need to acquire init_mm.mmap_lock. + */ + __pmd_free_pte_page(pmdp, next, /* acquire_mmap_lock = */ false); } while (pmdp++, next += PMD_SIZE, next != end); - pud_clear(pudp); - __flush_tlb_kernel_pgtable(addr); pmd_free(NULL, table); return 1; } @@ -1306,8 +1938,8 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) struct range arch_get_mappable_range(void) { struct range mhp_range; - u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual)); - u64 end_linear_pa = __pa(PAGE_END - 1); + phys_addr_t start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual)); + phys_addr_t end_linear_pa = __pa(PAGE_END - 1); if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { /* @@ -1342,25 +1974,31 @@ int arch_add_memory(int nid, u64 start, u64 size, VM_BUG_ON(!mhp_range_allowed(start, size, true)); - if (can_set_direct_map()) + if (force_pte_mapping()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), - size, params->pgprot, __pgd_pgtable_alloc, - flags); + ret = __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), + size, params->pgprot, pgd_pgtable_alloc_init_mm, + flags); + if (ret) + goto err; memblock_clear_nomap(start, size); ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); if (ret) - __remove_pgd_mapping(swapper_pg_dir, - __phys_to_virt(start), size); - else { - max_pfn = PFN_UP(start + size); - max_low_pfn = max_pfn; - } + goto err; + + /* Address of hotplugged memory can be smaller */ + max_pfn = max(max_pfn, PFN_UP(start + size)); + max_low_pfn = max_pfn; + return 0; + +err: + __remove_pgd_mapping(swapper_pg_dir, + __phys_to_virt(start), size); return ret; } @@ -1499,24 +2137,41 @@ static int __init prevent_bootmem_remove_init(void) early_initcall(prevent_bootmem_remove_init); #endif -pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, unsigned int nr) { + pte_t pte = get_and_clear_ptes(vma->vm_mm, addr, ptep, nr); + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ - if (pte_user_exec(ptep_get(ptep))) - return ptep_clear_flush(vma, addr, ptep); + if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte)) + __flush_tlb_range(vma, addr, nr * PAGE_SIZE, + PAGE_SIZE, true, 3); } - return ptep_get_and_clear(vma->vm_mm, addr, ptep); + + return pte; +} + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + return modify_prot_start_ptes(vma, addr, ptep, 1); +} + +void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte, + unsigned int nr) +{ + set_ptes(vma->vm_mm, addr, ptep, pte, nr); } void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_pte_at(vma->vm_mm, addr, ptep, pte); + modify_prot_commit_ptes(vma, addr, ptep, old_pte, pte, 1); } /* @@ -1554,9 +2209,8 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) #ifdef CONFIG_ARCH_HAS_PKEYS int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - u64 new_por = POE_RXW; + u64 new_por; u64 old_por; - u64 pkey_shift; if (!system_supports_poe()) return -ENOSPC; @@ -1570,7 +2224,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i return -EINVAL; /* Set the bits we need in POR: */ - new_por = POE_RXW; + new_por = POE_RWX; if (init_val & PKEY_DISABLE_WRITE) new_por &= ~POE_W; if (init_val & PKEY_DISABLE_ACCESS) @@ -1581,12 +2235,11 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i new_por &= ~POE_X; /* Shift the bits in to the correct place in POR for pkey: */ - pkey_shift = pkey * POR_BITS_PER_PKEY; - new_por <<= pkey_shift; + new_por = POR_ELx_PERM_PREP(pkey, new_por); /* Get old POR and mask off any old bits in place: */ old_por = read_sysreg_s(SYS_POR_EL0); - old_por &= ~(POE_MASK << pkey_shift); + old_por &= ~(POE_MASK << POR_ELx_PERM_SHIFT(pkey)); /* Write old part along with new part: */ write_sysreg_s(old_por | new_por, SYS_POR_EL0); |