From 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Tue, 4 Aug 2015 12:17:53 -0700 Subject: Add the rt linux 4.1.3-rt3 as base Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang --- kernel/arch/x86/mm/pgtable.c | 627 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 627 insertions(+) create mode 100644 kernel/arch/x86/mm/pgtable.c (limited to 'kernel/arch/x86/mm/pgtable.c') diff --git a/kernel/arch/x86/mm/pgtable.c b/kernel/arch/x86/mm/pgtable.c new file mode 100644 index 000000000..0b97d2c75 --- /dev/null +++ b/kernel/arch/x86/mm/pgtable.c @@ -0,0 +1,627 @@ +#include +#include +#include +#include +#include +#include +#include + +#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO + +#ifdef CONFIG_HIGHPTE +#define PGALLOC_USER_GFP __GFP_HIGHMEM +#else +#define PGALLOC_USER_GFP 0 +#endif + +gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; + +pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + return (pte_t *)__get_free_page(PGALLOC_GFP); +} + +pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + struct page *pte; + + pte = alloc_pages(__userpte_alloc_gfp, 0); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } + return pte; +} + +static int __init setup_userpte(char *arg) +{ + if (!arg) + return -EINVAL; + + /* + * "userpte=nohigh" disables allocation of user pagetables in + * high memory. + */ + if (strcmp(arg, "nohigh") == 0) + __userpte_alloc_gfp &= ~__GFP_HIGHMEM; + else + return -EINVAL; + return 0; +} +early_param("userpte", setup_userpte); + +void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) +{ + pgtable_page_dtor(pte); + paravirt_release_pte(page_to_pfn(pte)); + tlb_remove_page(tlb, pte); +} + +#if CONFIG_PGTABLE_LEVELS > 2 +void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) +{ + struct page *page = virt_to_page(pmd); + paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + /* + * NOTE! For PAE, any changes to the top page-directory-pointer-table + * entries need a full cr3 reload to flush. + */ +#ifdef CONFIG_X86_PAE + tlb->need_flush_all = 1; +#endif + pgtable_pmd_page_dtor(page); + tlb_remove_page(tlb, page); +} + +#if CONFIG_PGTABLE_LEVELS > 3 +void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) +{ + paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(pud)); +} +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ + +static inline void pgd_list_add(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_add(&page->lru, &pgd_list); +} + +static inline void pgd_list_del(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_del(&page->lru); +} + +#define UNSHARED_PTRS_PER_PGD \ + (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) + + +static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) +{ + BUILD_BUG_ON(sizeof(virt_to_page(pgd)->index) < sizeof(mm)); + virt_to_page(pgd)->index = (pgoff_t)mm; +} + +struct mm_struct *pgd_page_get_mm(struct page *page) +{ + return (struct mm_struct *)page->index; +} + +static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) +{ + /* If the pgd points to a shared pagetable level (either the + ptes in non-PAE, or shared PMD in PAE), then just copy the + references from swapper_pg_dir. */ + if (CONFIG_PGTABLE_LEVELS == 2 || + (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || + CONFIG_PGTABLE_LEVELS == 4) { + clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + } + + /* list required to sync kernel mapping updates */ + if (!SHARED_KERNEL_PMD) { + pgd_set_mm(pgd, mm); + pgd_list_add(pgd); + } +} + +static void pgd_dtor(pgd_t *pgd) +{ + if (SHARED_KERNEL_PMD) + return; + + spin_lock(&pgd_lock); + pgd_list_del(pgd); + spin_unlock(&pgd_lock); +} + +/* + * List of all pgd's needed for non-PAE so it can invalidate entries + * in both cached and uncached pgd's; not needed for PAE since the + * kernel pmd is shared. If PAE were not to share the pmd a similar + * tactic would be needed. This is essentially codepath-based locking + * against pageattr.c; it is the unique case in which a valid change + * of kernel pagetables can't be lazily synchronized by vmalloc faults. + * vmalloc faults work because attached pagetables are never freed. + * -- nyc + */ + +#ifdef CONFIG_X86_PAE +/* + * In PAE mode, we need to do a cr3 reload (=tlb flush) when + * updating the top-level pagetable entries to guarantee the + * processor notices the update. Since this is expensive, and + * all 4 top-level entries are used almost immediately in a + * new process's life, we just pre-populate them here. + * + * Also, if we're in a paravirt environment where the kernel pmd is + * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate + * and initialize the kernel pmds here. + */ +#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD + +void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + + /* Note: almost everything apart from _PAGE_PRESENT is + reserved at the pmd (PDPT) level. */ + set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); + + /* + * According to Intel App note "TLBs, Paging-Structure Caches, + * and Their Invalidation", April 2007, document 317080-001, + * section 8.1: in PAE mode we explicitly have to flush the + * TLB via cr3 if the top-level pgd is changed... + */ + flush_tlb_mm(mm); +} +#else /* !CONFIG_X86_PAE */ + +/* No need to prepopulate any pagetable entries in non-PAE modes. */ +#define PREALLOCATED_PMDS 0 + +#endif /* CONFIG_X86_PAE */ + +static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) +{ + int i; + + for(i = 0; i < PREALLOCATED_PMDS; i++) + if (pmds[i]) { + pgtable_pmd_page_dtor(virt_to_page(pmds[i])); + free_page((unsigned long)pmds[i]); + mm_dec_nr_pmds(mm); + } +} + +static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) +{ + int i; + bool failed = false; + + for(i = 0; i < PREALLOCATED_PMDS; i++) { + pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); + if (!pmd) + failed = true; + if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { + free_page((unsigned long)pmd); + pmd = NULL; + failed = true; + } + if (pmd) + mm_inc_nr_pmds(mm); + pmds[i] = pmd; + } + + if (failed) { + free_pmds(mm, pmds); + return -ENOMEM; + } + + return 0; +} + +/* + * Mop up any pmd pages which may still be attached to the pgd. + * Normally they will be freed by munmap/exit_mmap, but any pmd we + * preallocate which never got a corresponding vma will need to be + * freed manually. + */ +static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) +{ + int i; + + for(i = 0; i < PREALLOCATED_PMDS; i++) { + pgd_t pgd = pgdp[i]; + + if (pgd_val(pgd) != 0) { + pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); + + pgdp[i] = native_make_pgd(0); + + paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); + pmd_free(mm, pmd); + mm_dec_nr_pmds(mm); + } + } +} + +static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) +{ + pud_t *pud; + int i; + + if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ + return; + + pud = pud_offset(pgd, 0); + + for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { + pmd_t *pmd = pmds[i]; + + if (i >= KERNEL_PGD_BOUNDARY) + memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), + sizeof(pmd_t) * PTRS_PER_PMD); + + pud_populate(mm, pud, pmd); + } +} + +/* + * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also + * assumes that pgd should be in one page. + * + * But kernel with PAE paging that is not running as a Xen domain + * only needs to allocate 32 bytes for pgd instead of one page. + */ +#ifdef CONFIG_X86_PAE + +#include + +#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) +#define PGD_ALIGN 32 + +static struct kmem_cache *pgd_cache; + +static int __init pgd_cache_init(void) +{ + /* + * When PAE kernel is running as a Xen domain, it does not use + * shared kernel pmd. And this requires a whole page for pgd. + */ + if (!SHARED_KERNEL_PMD) + return 0; + + /* + * when PAE kernel is not running as a Xen domain, it uses + * shared kernel pmd. Shared kernel pmd does not require a whole + * page for pgd. We are able to just allocate a 32-byte for pgd. + * During boot time, we create a 32-byte slab for pgd table allocation. + */ + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, + SLAB_PANIC, NULL); + if (!pgd_cache) + return -ENOMEM; + + return 0; +} +core_initcall(pgd_cache_init); + +static inline pgd_t *_pgd_alloc(void) +{ + /* + * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. + * We allocate one page for pgd. + */ + if (!SHARED_KERNEL_PMD) + return (pgd_t *)__get_free_page(PGALLOC_GFP); + + /* + * Now PAE kernel is not running as a Xen domain. We can allocate + * a 32-byte slab for pgd to save memory space. + */ + return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); +} + +static inline void _pgd_free(pgd_t *pgd) +{ + if (!SHARED_KERNEL_PMD) + free_page((unsigned long)pgd); + else + kmem_cache_free(pgd_cache, pgd); +} +#else +static inline pgd_t *_pgd_alloc(void) +{ + return (pgd_t *)__get_free_page(PGALLOC_GFP); +} + +static inline void _pgd_free(pgd_t *pgd) +{ + free_page((unsigned long)pgd); +} +#endif /* CONFIG_X86_PAE */ + +pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd; + pmd_t *pmds[PREALLOCATED_PMDS]; + + pgd = _pgd_alloc(); + + if (pgd == NULL) + goto out; + + mm->pgd = pgd; + + if (preallocate_pmds(mm, pmds) != 0) + goto out_free_pgd; + + if (paravirt_pgd_alloc(mm) != 0) + goto out_free_pmds; + + /* + * Make sure that pre-populating the pmds is atomic with + * respect to anything walking the pgd_list, so that they + * never see a partially populated pgd. + */ + spin_lock(&pgd_lock); + + pgd_ctor(mm, pgd); + pgd_prepopulate_pmd(mm, pgd, pmds); + + spin_unlock(&pgd_lock); + + return pgd; + +out_free_pmds: + free_pmds(mm, pmds); +out_free_pgd: + _pgd_free(pgd); +out: + return NULL; +} + +void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + pgd_mop_up_pmds(mm, pgd); + pgd_dtor(pgd); + paravirt_pgd_free(mm, pgd); + _pgd_free(pgd); +} + +/* + * Used to set accessed or dirty bits in the page table entries + * on other architectures. On x86, the accessed and dirty bits + * are tracked by hardware. However, do_wp_page calls this function + * to also make the pte writeable at the same time the dirty bit is + * set. In that case we do actually need to write the PTE. + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + int changed = !pte_same(*ptep, entry); + + if (changed && dirty) { + *ptep = entry; + pte_update_defer(vma->vm_mm, address, ptep); + } + + return changed; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + int changed = !pmd_same(*pmdp, entry); + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + if (changed && dirty) { + *pmdp = entry; + pmd_update_defer(vma->vm_mm, address, pmdp); + /* + * We had a write-protection fault here and changed the pmd + * to to more permissive. No need to flush the TLB for that, + * #PF is architecturally guaranteed to do that and in the + * worst-case we'll generate a spurious fault. + */ + } + + return changed; +} +#endif + +int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + int ret = 0; + + if (pte_young(*ptep)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + (unsigned long *) &ptep->pte); + + if (ret) + pte_update(vma->vm_mm, addr, ptep); + + return ret; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + int ret = 0; + + if (pmd_young(*pmdp)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + (unsigned long *)pmdp); + + if (ret) + pmd_update(vma->vm_mm, addr, pmdp); + + return ret; +} +#endif + +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + /* + * On x86 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. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int young; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + young = pmdp_test_and_clear_young(vma, address, pmdp); + if (young) + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + return young; +} + +void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + int set; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + set = !test_and_set_bit(_PAGE_BIT_SPLITTING, + (unsigned long *)pmdp); + if (set) { + pmd_update(vma->vm_mm, address, pmdp); + /* need tlb flush only to serialize against gup-fast */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + } +} +#endif + +/** + * reserve_top_address - reserves a hole in the top of kernel address space + * @reserve - size of hole to reserve + * + * Can be used to relocate the fixmap area and poke a hole in the top + * of kernel address space to make room for a hypervisor. + */ +void __init reserve_top_address(unsigned long reserve) +{ +#ifdef CONFIG_X86_32 + BUG_ON(fixmaps_set > 0); + __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; + printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", + -reserve, __FIXADDR_TOP + PAGE_SIZE); +#endif +} + +int fixmaps_set; + +void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) +{ + unsigned long address = __fix_to_virt(idx); + + if (idx >= __end_of_fixed_addresses) { + BUG(); + return; + } + set_pte_vaddr(address, pte); + fixmaps_set++; +} + +void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, + pgprot_t flags) +{ + __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); +} + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + u8 mtrr; + + /* + * Do not use a huge page when the range is covered by non-WB type + * of MTRRs. + */ + mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE); + if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + return 0; + + prot = pgprot_4k_2_large(prot); + + set_pte((pte_t *)pud, pfn_pte( + (u64)addr >> PAGE_SHIFT, + __pgprot(pgprot_val(prot) | _PAGE_PSE))); + + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + u8 mtrr; + + /* + * Do not use a huge page when the range is covered by non-WB type + * of MTRRs. + */ + mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE); + if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + return 0; + + prot = pgprot_4k_2_large(prot); + + set_pte((pte_t *)pmd, pfn_pte( + (u64)addr >> PAGE_SHIFT, + __pgprot(pgprot_val(prot) | _PAGE_PSE))); + + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (pud_large(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (pmd_large(*pmd)) { + pmd_clear(pmd); + return 1; + } + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -- cgit 1.2.3-korg