diff options
Diffstat (limited to 'mm/gup.c')
| -rw-r--r-- | mm/gup.c | 376 |
1 files changed, 373 insertions, 3 deletions
@@ -10,6 +10,10 @@ #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/sched.h> +#include <linux/rwsem.h> +#include <asm/pgtable.h> + #include "internal.h" static struct page *no_page_table(struct vm_area_struct *vma, @@ -258,6 +262,11 @@ unmap: return ret; } +/* + * mmap_sem must be held on entry. If @nonblocking != NULL and + * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released. + * If it is, *@nonblocking will be set to 0 and -EBUSY returned. + */ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, unsigned long address, unsigned int *flags, int *nonblocking) { @@ -276,6 +285,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, fault_flags |= FAULT_FLAG_ALLOW_RETRY; if (*flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; + if (*flags & FOLL_TRIED) { + VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY); + fault_flags |= FAULT_FLAG_TRIED; + } ret = handle_mm_fault(mm, vma, address, fault_flags); if (ret & VM_FAULT_ERROR) { @@ -373,7 +386,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * with a put_page() call when it is finished with. vmas will only * remain valid while mmap_sem is held. * - * Must be called with mmap_sem held for read or write. + * Must be called with mmap_sem held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given @@ -396,7 +409,14 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * * If @nonblocking != NULL, __get_user_pages will not wait for disk IO * or mmap_sem contention, and if waiting is needed to pin all pages, - * *@nonblocking will be set to 0. + * *@nonblocking will be set to 0. Further, if @gup_flags does not + * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in + * this case. + * + * A caller using such a combination of @nonblocking and @gup_flags + * must therefore hold the mmap_sem for reading only, and recognize + * when it's been released. Otherwise, it must be held for either + * reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if @@ -528,7 +548,7 @@ EXPORT_SYMBOL(__get_user_pages); * such architectures, gup() will not be enough to make a subsequent access * succeed. * - * This should be called with the mm_sem held for read. + * This has the same semantics wrt the @mm->mmap_sem as does filemap_fault(). */ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags) @@ -660,3 +680,353 @@ struct page *get_dump_page(unsigned long addr) return page; } #endif /* CONFIG_ELF_CORE */ + +/* + * Generic RCU Fast GUP + * + * get_user_pages_fast attempts to pin user pages by walking the page + * tables directly and avoids taking locks. Thus the walker needs to be + * protected from page table pages being freed from under it, and should + * block any THP splits. + * + * One way to achieve this is to have the walker disable interrupts, and + * rely on IPIs from the TLB flushing code blocking before the page table + * pages are freed. This is unsuitable for architectures that do not need + * to broadcast an IPI when invalidating TLBs. + * + * Another way to achieve this is to batch up page table containing pages + * belonging to more than one mm_user, then rcu_sched a callback to free those + * pages. Disabling interrupts will allow the fast_gup walker to both block + * the rcu_sched callback, and an IPI that we broadcast for splitting THPs + * (which is a relatively rare event). The code below adopts this strategy. + * + * Before activating this code, please be aware that the following assumptions + * are currently made: + * + * *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free + * pages containing page tables. + * + * *) THP splits will broadcast an IPI, this can be achieved by overriding + * pmdp_splitting_flush. + * + * *) ptes can be read atomically by the architecture. + * + * *) access_ok is sufficient to validate userspace address ranges. + * + * The last two assumptions can be relaxed by the addition of helper functions. + * + * This code is based heavily on the PowerPC implementation by Nick Piggin. + */ +#ifdef CONFIG_HAVE_GENERIC_RCU_GUP + +#ifdef __HAVE_ARCH_PTE_SPECIAL +static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + pte_t *ptep, *ptem; + int ret = 0; + + ptem = ptep = pte_offset_map(&pmd, addr); + do { + /* + * In the line below we are assuming that the pte can be read + * atomically. If this is not the case for your architecture, + * please wrap this in a helper function! + * + * for an example see gup_get_pte in arch/x86/mm/gup.c + */ + pte_t pte = ACCESS_ONCE(*ptep); + struct page *page; + + /* + * Similar to the PMD case below, NUMA hinting must take slow + * path + */ + if (!pte_present(pte) || pte_special(pte) || + pte_numa(pte) || (write && !pte_write(pte))) + goto pte_unmap; + + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); + + if (!page_cache_get_speculative(page)) + goto pte_unmap; + + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + put_page(page); + goto pte_unmap; + } + + pages[*nr] = page; + (*nr)++; + + } while (ptep++, addr += PAGE_SIZE, addr != end); + + ret = 1; + +pte_unmap: + pte_unmap(ptem); + return ret; +} +#else + +/* + * If we can't determine whether or not a pte is special, then fail immediately + * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not + * to be special. + * + * For a futex to be placed on a THP tail page, get_futex_key requires a + * __get_user_pages_fast implementation that can pin pages. Thus it's still + * useful to have gup_huge_pmd even if we can't operate on ptes. + */ +static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + return 0; +} +#endif /* __HAVE_ARCH_PTE_SPECIAL */ + +static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + struct page *head, *page, *tail; + int refs; + + if (write && !pmd_write(orig)) + return 0; + + refs = 0; + head = pmd_page(orig); + page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + tail = page; + do { + VM_BUG_ON_PAGE(compound_head(page) != head, page); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + if (!page_cache_add_speculative(head, refs)) { + *nr -= refs; + return 0; + } + + if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + /* + * Any tail pages need their mapcount reference taken before we + * return. (This allows the THP code to bump their ref count when + * they are split into base pages). + */ + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; + } + + return 1; +} + +static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + struct page *head, *page, *tail; + int refs; + + if (write && !pud_write(orig)) + return 0; + + refs = 0; + head = pud_page(orig); + page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + tail = page; + do { + VM_BUG_ON_PAGE(compound_head(page) != head, page); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + if (!page_cache_add_speculative(head, refs)) { + *nr -= refs; + return 0; + } + + if (unlikely(pud_val(orig) != pud_val(*pudp))) { + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; + } + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = ACCESS_ONCE(*pmdp); + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + return 0; + + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + /* + * NUMA hinting faults need to be handled in the GUP + * slowpath for accounting purposes and so that they + * can be serialised against THP migration. + */ + if (pmd_numa(pmd)) + return 0; + + if (!gup_huge_pmd(pmd, pmdp, addr, next, write, + pages, nr)) + return 0; + + } else if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(pgdp, addr); + do { + pud_t pud = ACCESS_ONCE(*pudp); + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (pud_huge(pud)) { + if (!gup_huge_pud(pud, pudp, addr, next, write, + pages, nr)) + return 0; + } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } while (pudp++, addr = next, addr != end); + + return 1; +} + +/* + * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to + * the regular GUP. It will only return non-negative values. + */ +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next, flags; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + start, len))) + return 0; + + /* + * Disable interrupts. We use the nested form as we can already have + * interrupts disabled by get_futex_key. + * + * With interrupts disabled, we block page table pages from being + * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h + * for more details. + * + * We do not adopt an rcu_read_lock(.) here as we also want to + * block IPIs that come from THPs splitting. + */ + + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none(*pgdp)) + break; + else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. + */ +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + int nr, ret; + + start &= PAGE_MASK; + nr = __get_user_pages_fast(start, nr_pages, write, pages); + ret = nr; + + if (nr < nr_pages) { + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + nr_pages - nr, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + } + + return ret; +} + +#endif /* CONFIG_HAVE_GENERIC_RCU_GUP */ |