diff options
Diffstat (limited to 'arch/powerpc')
25 files changed, 175 insertions, 147 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b8d36a261009..ad7a2fe63a2a 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -172,6 +172,7 @@ config PPC select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if !HUGETLB_PAGE select ARCH_SUPPORTS_SCHED_MC if SMP select ARCH_SUPPORTS_SCHED_SMT if PPC64 && SMP select SCHED_MC if ARCH_SUPPORTS_SCHED_MC @@ -304,6 +305,7 @@ config PPC select LOCK_MM_AND_FIND_VMA select MMU_GATHER_PAGE_SIZE select MMU_GATHER_RCU_TABLE_FREE + select HAVE_ARCH_TLB_REMOVE_TABLE select MMU_GATHER_MERGE_VMAS select MMU_LAZY_TLB_SHOOTDOWN if PPC_BOOK3S_64 select MODULES_USE_ELF_RELA diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 41ae404d0b7a..001e28f9eabc 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -198,6 +198,7 @@ void unmap_kernel_page(unsigned long va); #ifndef __ASSEMBLER__ #include <linux/sched.h> #include <linux/threads.h> +#include <linux/page_table_check.h> /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0 @@ -311,7 +312,11 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0)); + pte_t old_pte = __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0)); + + page_table_check_pte_clear(mm, addr, old_pte); + + return old_pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT @@ -433,6 +438,11 @@ static inline bool pte_access_permitted(pte_t pte, bool write) return true; } +static inline bool pte_user_accessible_page(pte_t pte, unsigned long addr) +{ + return pte_present(pte) && !is_kernel_addr(addr); +} + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index aac8ce30cd3b..1a91762b455d 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -144,6 +144,8 @@ #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) #ifndef __ASSEMBLER__ +#include <linux/page_table_check.h> + /* * page table defines */ @@ -416,8 +418,11 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); - return __pte(old); + pte_t old_pte = __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0)); + + page_table_check_pte_clear(mm, addr, old_pte); + + return old_pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL @@ -426,11 +431,16 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, pte_t *ptep, int full) { if (full && radix_enabled()) { + pte_t old_pte; + /* * We know that this is a full mm pte clear and * hence can be sure there is no parallel set_pte. */ - return radix__ptep_get_and_clear_full(mm, addr, ptep, full); + old_pte = radix__ptep_get_and_clear_full(mm, addr, ptep, full); + page_table_check_pte_clear(mm, addr, old_pte); + + return old_pte; } return ptep_get_and_clear(mm, addr, ptep); } @@ -539,6 +549,11 @@ static inline bool pte_access_permitted(pte_t pte, bool write) return arch_pte_access_permitted(pte_val(pte), write, 0); } +static inline bool pte_user_accessible_page(pte_t pte, unsigned long addr) +{ + return pte_present(pte) && pte_user(pte); +} + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. @@ -909,6 +924,12 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return pte_access_permitted(pud_pte(pud), write); } +#define pud_user_accessible_page pud_user_accessible_page +static inline bool pud_user_accessible_page(pud_t pud, unsigned long addr) +{ + return pud_leaf(pud) && pte_user_accessible_page(pud_pte(pud), addr); +} + #define __p4d_raw(x) ((p4d_t) { __pgd_raw(x) }) static inline __be64 p4d_raw(p4d_t x) { @@ -1074,6 +1095,12 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write) return pte_access_permitted(pmd_pte(pmd), write); } +#define pmd_user_accessible_page pmd_user_accessible_page +static inline bool pmd_user_accessible_page(pmd_t pmd, unsigned long addr) +{ + return pmd_leaf(pmd) && pte_user_accessible_page(pmd_pte(pmd), addr); +} + #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); @@ -1284,19 +1311,34 @@ extern int pudp_test_and_clear_young(struct vm_area_struct *vma, static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - if (radix_enabled()) - return radix__pmdp_huge_get_and_clear(mm, addr, pmdp); - return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); + pmd_t old_pmd; + + if (radix_enabled()) { + old_pmd = radix__pmdp_huge_get_and_clear(mm, addr, pmdp); + } else { + old_pmd = hash__pmdp_huge_get_and_clear(mm, addr, pmdp); + } + + page_table_check_pmd_clear(mm, addr, old_pmd); + + return old_pmd; } #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; + pud_t old_pud; + + if (radix_enabled()) { + old_pud = radix__pudp_huge_get_and_clear(mm, addr, pudp); + } else { + BUG(); + } + + page_table_check_pud_clear(mm, addr, old_pud); + + return old_pud; } static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index 146287d9580f..6cc9abcd7b3d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -12,7 +12,6 @@ #define PPC64_TLB_BATCH_NR 192 struct ppc64_tlb_batch { - int active; unsigned long index; struct mm_struct *mm; real_pte_t pte[PPC64_TLB_BATCH_NR]; @@ -24,12 +23,8 @@ DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch); -#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE - static inline void arch_enter_lazy_mmu_mode(void) { - struct ppc64_tlb_batch *batch; - if (radix_enabled()) return; /* @@ -37,11 +32,9 @@ static inline void arch_enter_lazy_mmu_mode(void) * operating on kernel page tables. */ preempt_disable(); - batch = this_cpu_ptr(&ppc64_tlb_batch); - batch->active = 1; } -static inline void arch_leave_lazy_mmu_mode(void) +static inline void arch_flush_lazy_mmu_mode(void) { struct ppc64_tlb_batch *batch; @@ -51,11 +44,16 @@ 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) +static inline void arch_leave_lazy_mmu_mode(void) +{ + if (radix_enabled()) + return; + + arch_flush_lazy_mmu_mode(); + preempt_enable(); +} extern void hash__tlbiel_all(unsigned int action); diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 86326587e58d..6d32a4299445 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -68,7 +68,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); -void gigantic_hugetlb_cma_reserve(void) __init; #include <asm-generic/hugetlb.h> #else /* ! CONFIG_HUGETLB_PAGE */ @@ -77,10 +76,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma, { } -static inline void __init gigantic_hugetlb_cma_reserve(void) -{ -} - static inline void __init hugetlbpage_init_defaultsize(void) { } diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 5af168b7f292..e6da5eaccff6 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -29,6 +29,8 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p #ifndef __ASSEMBLER__ +#include <linux/page_table_check.h> + extern int icache_44x_need_flush; #ifndef pte_huge_size @@ -122,7 +124,11 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0)); + pte_t old_pte = __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0)); + + page_table_check_pte_clear(mm, addr, old_pte); + + return old_pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR @@ -243,6 +249,11 @@ static inline bool pte_access_permitted(pte_t pte, bool write) return true; } +static inline bool pte_user_accessible_page(pte_t pte, unsigned long addr) +{ + return pte_present(pte) && !is_kernel_addr(addr); +} + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index b28fbb1d57eb..f2bb1f98eebe 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -271,6 +271,7 @@ static inline const void *pfn_to_kaddr(unsigned long pfn) struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); +#define clear_user_page clear_user_page extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *p); extern int devmem_is_allowed(unsigned long pfn); diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 17fd7ff6e535..dcd3a88caaf6 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -34,6 +34,8 @@ struct mm_struct; void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr); #define set_ptes set_ptes +void set_pte_at_unchecked(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) @@ -202,6 +204,14 @@ static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size) #endif /* CONFIG_PPC64 */ +#ifndef pmd_user_accessible_page +#define pmd_user_accessible_page(pmd, addr) false +#endif + +#ifndef pud_user_accessible_page +#define pud_user_accessible_page(pud, addr) false +#endif + #endif /* __ASSEMBLER__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 50a92b24628d..6d60ea4868ab 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -20,7 +20,11 @@ extern void reloc_got2(unsigned long); void check_for_initrd(void); void mem_topology_setup(void); +#ifdef CONFIG_NUMA void initmem_init(void); +#else +static inline void initmem_init(void) {} +#endif void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index b0f200aba2b3..97f35f9b1a96 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -154,12 +154,10 @@ void arch_setup_new_exec(void); /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */ #define TLF_NAPPING 0 /* idle thread enabled NAP mode */ #define TLF_SLEEPING 1 /* suspend code enabled SLEEP mode */ -#define TLF_LAZY_MMU 3 /* tlb_batch is active */ #define TLF_RUNLATCH 4 /* Is the runlatch enabled? */ #define _TLF_NAPPING (1 << TLF_NAPPING) #define _TLF_SLEEPING (1 << TLF_SLEEPING) -#define _TLF_LAZY_MMU (1 << TLF_LAZY_MMU) #define _TLF_RUNLATCH (1 << TLF_RUNLATCH) #ifndef __ASSEMBLER__ diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 2058e8d3e013..1ca7d4c4b90d 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -37,7 +37,6 @@ extern void tlb_flush(struct mmu_gather *tlb); */ #define tlb_needs_table_invalidate() radix_enabled() -#define __HAVE_ARCH_TLB_REMOVE_TABLE /* Get the generic bits... */ #include <asm-generic/tlb.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a45fe147868b..a15d0b619b1f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1281,9 +1281,6 @@ struct task_struct *__switch_to(struct task_struct *prev, { struct thread_struct *new_thread, *old_thread; struct task_struct *last; -#ifdef CONFIG_PPC_64S_HASH_MMU - struct ppc64_tlb_batch *batch; -#endif new_thread = &new->thread; old_thread = ¤t->thread; @@ -1291,14 +1288,6 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); #ifdef CONFIG_PPC_64S_HASH_MMU - batch = this_cpu_ptr(&ppc64_tlb_batch); - if (batch->active) { - current_thread_info()->local_flags |= _TLF_LAZY_MMU; - if (batch->index) - __flush_tlb_pending(batch); - batch->active = 0; - } - /* * On POWER9 the copy-paste buffer can only paste into * foreign real addresses, so unprivileged processes can not @@ -1369,20 +1358,6 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifdef CONFIG_PPC_BOOK3S_64 -#ifdef CONFIG_PPC_64S_HASH_MMU - /* - * This applies to a process that was context switched while inside - * arch_enter_lazy_mmu_mode(), to re-activate the batch that was - * deactivated above, before _switch(). This will never be the case - * for new tasks. - */ - if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { - current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; - batch = this_cpu_ptr(&ppc64_tlb_batch); - batch->active = 1; - } -#endif - /* * Math facilities are masked out of the child MSR in copy_thread. * A new task does not need to restore_math because it will diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index c8c42b419742..cb5b73adc250 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -1003,7 +1003,6 @@ void __init setup_arch(char **cmdline_p) fadump_cma_init(); kdump_cma_reserve(); kvm_cma_reserve(); - gigantic_hugetlb_cma_reserve(); early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 82d31177630b..ac2a24d15d2e 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/mm.h> +#include <linux/page_table_check.h> #include <linux/stop_machine.h> #include <asm/sections.h> @@ -230,6 +231,9 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres pmd = *pmdp; pmd_clear(pmdp); + + page_table_check_pmd_clear(vma->vm_mm, address, pmd); + /* * Wait for all pending hash_page to finish. This is needed * in case of subpage collapse. When we collapse normal pages diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c index 21fcad97ae80..ec2941cec815 100644 --- a/arch/powerpc/mm/book3s64/hash_tlb.c +++ b/arch/powerpc/mm/book3s64/hash_tlb.c @@ -25,11 +25,12 @@ #include <asm/tlb.h> #include <asm/bug.h> #include <asm/pte-walk.h> - +#include <kunit/visibility.h> #include <trace/events/thp.h> DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); +EXPORT_SYMBOL_IF_KUNIT(ppc64_tlb_batch); /* * A linux PTE was changed and the corresponding hash table entry @@ -100,7 +101,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * Check if we have an active batch on this CPU. If not, just * flush now and return. */ - if (!batch->active) { + if (!is_lazy_mmu_mode_active()) { flush_hash_page(vpn, rpte, psize, ssize, mm_is_thread_local(mm)); put_cpu_var(ppc64_tlb_batch); return; @@ -154,6 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch) flush_hash_range(i, local); batch->index = 0; } +EXPORT_SYMBOL_IF_KUNIT(__flush_tlb_pending); void hash__tlb_flush(struct mmu_gather *tlb) { @@ -205,7 +207,7 @@ void __flush_hash_table_range(unsigned long start, unsigned long end) * way to do things but is fine for our needs here. */ local_irq_save(flags); - arch_enter_lazy_mmu_mode(); + lazy_mmu_mode_enable(); for (; start < end; start += PAGE_SIZE) { pte_t *ptep = find_init_mm_pte(start, &hugepage_shift); unsigned long pte; @@ -217,7 +219,7 @@ void __flush_hash_table_range(unsigned long start, unsigned long end) continue; hpte_need_flush(&init_mm, start, ptep, pte, hugepage_shift); } - arch_leave_lazy_mmu_mode(); + lazy_mmu_mode_disable(); local_irq_restore(flags); } @@ -237,7 +239,7 @@ void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long * way to do things but is fine for our needs here. */ local_irq_save(flags); - arch_enter_lazy_mmu_mode(); + lazy_mmu_mode_enable(); start_pte = pte_offset_map(pmd, addr); if (!start_pte) goto out; @@ -249,6 +251,6 @@ void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long } pte_unmap(start_pte); out: - arch_leave_lazy_mmu_mode(); + lazy_mmu_mode_disable(); local_irq_restore(flags); } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index e3485db7de02..4b09c04654a8 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -10,6 +10,7 @@ #include <linux/pkeys.h> #include <linux/debugfs.h> #include <linux/proc_fs.h> +#include <linux/page_table_check.h> #include <asm/pgalloc.h> #include <asm/tlb.h> @@ -127,7 +128,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, WARN_ON(!(pmd_leaf(pmd))); #endif trace_hugepage_set_pmd(addr, pmd_val(pmd)); - return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); + page_table_check_pmd_set(mm, addr, pmdp, pmd); + return set_pte_at_unchecked(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } void set_pud_at(struct mm_struct *mm, unsigned long addr, @@ -144,7 +146,8 @@ void set_pud_at(struct mm_struct *mm, unsigned long addr, WARN_ON(!(pud_leaf(pud))); #endif trace_hugepage_set_pud(addr, pud_val(pud)); - return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); + page_table_check_pud_set(mm, addr, pudp, pud); + return set_pte_at_unchecked(mm, addr, pudp_ptep(pudp), pud_pte(pud)); } static void do_serialize(void *arg) @@ -179,23 +182,27 @@ void serialize_against_pte_lookup(struct mm_struct *mm) pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - unsigned long old_pmd; + pmd_t old_pmd; VM_WARN_ON_ONCE(!pmd_present(*pmdp)); - old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); + old_pmd = __pmd(pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - return __pmd(old_pmd); + page_table_check_pmd_clear(vma->vm_mm, address, old_pmd); + + return old_pmd; } pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { - unsigned long old_pud; + pud_t old_pud; VM_WARN_ON_ONCE(!pud_present(*pudp)); - old_pud = pud_hugepage_update(vma->vm_mm, address, pudp, _PAGE_PRESENT, _PAGE_INVALID); + old_pud = __pud(pud_hugepage_update(vma->vm_mm, address, pudp, _PAGE_PRESENT, _PAGE_INVALID)); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); - return __pud(old_pud); + page_table_check_pud_clear(vma->vm_mm, address, old_pud); + + return old_pud; } pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, @@ -550,7 +557,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, if (radix_enabled()) return radix__ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); - set_pte_at(vma->vm_mm, addr, ptep, pte); + set_pte_at_unchecked(vma->vm_mm, addr, ptep, pte); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 73977dbabcf2..10aced261cff 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -14,6 +14,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/mm.h> +#include <linux/page_table_check.h> #include <linux/hugetlb.h> #include <linux/string_helpers.h> #include <linux/memory.h> @@ -1474,6 +1475,8 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre pmd = *pmdp; pmd_clear(pmdp); + page_table_check_pmd_clear(vma->vm_mm, address, pmd); + radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); return pmd; @@ -1606,7 +1609,7 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, (atomic_read(&mm->context.copros) > 0)) radix__flush_tlb_page(vma, addr); - set_pte_at(mm, addr, ptep, pte); + set_pte_at_unchecked(mm, addr, ptep, pte); } int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) @@ -1617,7 +1620,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) if (!radix_enabled()) return 0; - set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud); + set_pte_at_unchecked(&init_mm, 0 /* radix unused */, ptep, new_pud); return 1; } @@ -1664,7 +1667,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) if (!radix_enabled()) return 0; - set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd); + set_pte_at_unchecked(&init_mm, 0 /* radix unused */, ptep, new_pmd); return 1; } diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index ec98e526167e..07c47673bba2 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -73,13 +73,13 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return; - arch_enter_lazy_mmu_mode(); + lazy_mmu_mode_enable(); for (; npages > 0; --npages) { pte_update(mm, addr, pte, 0, 0, 0); addr += PAGE_SIZE; ++pte; } - arch_leave_lazy_mmu_mode(); + lazy_mmu_mode_disable(); pte_unmap_unlock(pte - 1, ptl); } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index d3c1b749dcfc..558fafb82b8a 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -200,18 +200,15 @@ static int __init hugetlbpage_init(void) arch_initcall(hugetlbpage_init); -void __init gigantic_hugetlb_cma_reserve(void) +unsigned int __init arch_hugetlb_cma_order(void) { - unsigned long order = 0; - if (radix_enabled()) - order = PUD_SHIFT - PAGE_SHIFT; + return PUD_SHIFT - PAGE_SHIFT; else if (!firmware_has_feature(FW_FEATURE_LPAR) && mmu_psize_defs[MMU_PAGE_16G].shift) /* * For pseries we do use ibm,expected#pages for reserving 16G pages. */ - order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; + return mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; - if (order) - hugetlb_cma_reserve(order); + return 0; } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index bc0f1a9eb0bc..29bf347f6012 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -182,11 +182,6 @@ void __init mem_topology_setup(void) memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); } -void __init initmem_init(void) -{ - sparse_init(); -} - /* mark pages that don't exist as nosave */ static int __init mark_nonram_nosave(void) { @@ -221,7 +216,16 @@ static int __init mark_nonram_nosave(void) * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by * ZONE_DMA. */ -static unsigned long max_zone_pfns[MAX_NR_ZONES]; +void __init arch_zone_limits_init(unsigned long *max_zone_pfns) +{ +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = min((zone_dma_limit >> PAGE_SHIFT) + 1, max_low_pfn); +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; +#ifdef CONFIG_HIGHMEM + max_zone_pfns[ZONE_HIGHMEM] = max_pfn; +#endif +} /* * paging_init() sets up the page tables - in fact we've already done this. @@ -259,17 +263,6 @@ void __init paging_init(void) zone_dma_limit = DMA_BIT_MASK(zone_dma_bits); -#ifdef CONFIG_ZONE_DMA - max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - 1UL << (zone_dma_bits - PAGE_SHIFT)); -#endif - max_zone_pfns[ZONE_NORMAL] = max_low_pfn; -#ifdef CONFIG_HIGHMEM - max_zone_pfns[ZONE_HIGHMEM] = max_pfn; -#endif - - free_area_init(max_zone_pfns); - mark_nonram_nosave(); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 603a0f652ba6..f4cf3ae036de 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1213,8 +1213,6 @@ void __init initmem_init(void) setup_node_data(nid, start_pfn, end_pfn); } - sparse_init(); - /* * We need the numa_cpu_lookup_table to be accurate for all CPUs, * even before we online them, so that we can use cpu_to_{node,mem} diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 56d7e8960e77..a9be337be3e4 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -22,6 +22,7 @@ #include <linux/mm.h> #include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/page_table_check.h> #include <linux/hugetlb.h> #include <asm/tlbflush.h> #include <asm/tlb.h> @@ -206,6 +207,9 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, * and not hw_valid ptes. Hence there is no translation cache flush * involved that need to be batched. */ + + page_table_check_ptes_set(mm, addr, ptep, pte, nr); + for (;;) { /* @@ -224,6 +228,14 @@ void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, } } +void set_pte_at_unchecked(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep)); + pte = set_pte_filter(pte, addr); + __set_pte_at(mm, addr, ptep, pte, 0); +} + void unmap_kernel_page(unsigned long va) { pmd_t *pmdp = pmd_off_k(va); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 4c321a8ea896..f399917c17bd 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -93,6 +93,7 @@ config PPC_BOOK3S_64 select IRQ_WORK select PPC_64S_HASH_MMU if !PPC_RADIX_MMU select KASAN_VMALLOC if KASAN + select ARCH_HAS_LAZY_MMU_MODE config PPC_BOOK3E_64 bool "Embedded processors" diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 3e042218d6cd..f7052b131a4c 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -120,7 +120,7 @@ config PPC_SMLPAR config CMM tristate "Collaborative memory management" depends on PPC_SMLPAR - select MEMORY_BALLOON + select BALLOON default y help Select this option, if you want to enable the kernel interface diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 4cbbe2ee58ab..8d83df12430f 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -19,7 +19,7 @@ #include <linux/stringify.h> #include <linux/swap.h> #include <linux/device.h> -#include <linux/balloon_compaction.h> +#include <linux/balloon.h> #include <asm/firmware.h> #include <asm/hvcall.h> #include <asm/mmu.h> @@ -165,7 +165,6 @@ static long cmm_alloc_pages(long nr) balloon_page_enqueue(&b_dev_info, page); atomic_long_inc(&loaned_pages); - adjust_managed_page_count(page, -1); nr--; } @@ -190,7 +189,6 @@ static long cmm_free_pages(long nr) if (!page) break; plpar_page_set_active(page); - adjust_managed_page_count(page, 1); __free_page(page); atomic_long_dec(&loaned_pages); nr--; @@ -496,13 +494,11 @@ static struct notifier_block cmm_mem_nb = { .priority = CMM_MEM_HOTPLUG_PRI }; -#ifdef CONFIG_BALLOON_COMPACTION +#ifdef CONFIG_BALLOON_MIGRATION static int cmm_migratepage(struct balloon_dev_info *b_dev_info, struct page *newpage, struct page *page, enum migrate_mode mode) { - unsigned long flags; - /* * loan/"inflate" the newpage first. * @@ -517,47 +513,17 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, return -EBUSY; } - /* balloon page list reference */ - get_page(newpage); - - /* - * When we migrate a page to a different zone, we have to fixup the - * count of both involved zones as we adjusted the managed page count - * when inflating. - */ - if (page_zone(page) != page_zone(newpage)) { - adjust_managed_page_count(page, 1); - adjust_managed_page_count(newpage, -1); - } - - spin_lock_irqsave(&b_dev_info->pages_lock, flags); - balloon_page_insert(b_dev_info, newpage); - __count_vm_event(BALLOON_MIGRATE); - b_dev_info->isolated_pages--; - spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); - /* * activate/"deflate" the old page. We ignore any errors just like the * other callers. */ plpar_page_set_active(page); - - balloon_page_finalize(page); - /* balloon page list reference */ - put_page(page); - return 0; } - -static void cmm_balloon_compaction_init(void) -{ - b_dev_info.migratepage = cmm_migratepage; -} -#else /* CONFIG_BALLOON_COMPACTION */ -static void cmm_balloon_compaction_init(void) -{ -} -#endif /* CONFIG_BALLOON_COMPACTION */ +#else /* CONFIG_BALLOON_MIGRATION */ +int cmm_migratepage(struct balloon_dev_info *b_dev_info, struct page *newpage, + struct page *page, enum migrate_mode mode); +#endif /* CONFIG_BALLOON_MIGRATION */ /** * cmm_init - Module initialization @@ -573,11 +539,13 @@ static int cmm_init(void) return -EOPNOTSUPP; balloon_devinfo_init(&b_dev_info); - cmm_balloon_compaction_init(); + b_dev_info.adjust_managed_page_count = true; + if (IS_ENABLED(CONFIG_BALLOON_MIGRATION)) + b_dev_info.migratepage = cmm_migratepage; rc = register_oom_notifier(&cmm_oom_nb); if (rc < 0) - goto out_balloon_compaction; + return rc; if ((rc = register_reboot_notifier(&cmm_reboot_nb))) goto out_oom_notifier; @@ -606,7 +574,6 @@ out_reboot_notifier: unregister_reboot_notifier(&cmm_reboot_nb); out_oom_notifier: unregister_oom_notifier(&cmm_oom_nb); -out_balloon_compaction: return rc; } |