cregit-Linux how code gets into the kernel

Release 4.11 mm/userfaultfd.c

Directory: mm
/*
 *  mm/userfaultfd.c
 *
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 */

#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/userfaultfd_k.h>
#include <linux/mmu_notifier.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/shmem_fs.h>
#include <asm/tlbflush.h>
#include "internal.h"


static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep) { struct mem_cgroup *memcg; pte_t _dst_pte, *dst_pte; spinlock_t *ptl; void *page_kaddr; int ret; struct page *page; if (!*pagep) { ret = -ENOMEM; page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr); if (!page) goto out; page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *) src_addr, PAGE_SIZE); kunmap_atomic(page_kaddr); /* fallback to copy_from_user outside mmap_sem */ if (unlikely(ret)) { ret = -EFAULT; *pagep = page; /* don't free the page */ goto out; } } else { page = *pagep; *pagep = NULL; } /* * The memory barrier inside __SetPageUptodate makes sure that * preceeding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); ret = -ENOMEM; if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); ret = -EEXIST; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (!pte_none(*dst_pte)) goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); pte_unmap_unlock(dst_pte, ptl); ret = 0; out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); mem_cgroup_cancel_charge(page, memcg, false); out_release: put_page(page); goto out; }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli34197.43%240.00%
Kirill A. Shutemov92.57%360.00%
Total350100.00%5100.00%


static int mfill_zeropage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { pte_t _dst_pte, *dst_pte; spinlock_t *ptl; int ret; _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); ret = -EEXIST; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (!pte_none(*dst_pte)) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli122100.00%1100.00%
Total122100.00%1100.00%


static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, address); if (!pud) return NULL; /* * Note that we didn't run this because the pmd was * missing, the *pmd may be already established and in * turn it may also be a trans_huge_pmd. */ return pmd_alloc(mm, pud, address); }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli5665.12%150.00%
Kirill A. Shutemov3034.88%150.00%
Total86100.00%2100.00%

#ifdef CONFIG_HUGETLB_PAGE /* * __mcopy_atomic processing for HUGETLB vmas. Note that this routine is * called with mmap_sem held, it will release mmap_sem before returning. */
static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, bool zeropage) { int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; unsigned long src_addr, dst_addr; long copied; struct page *page; struct hstate *h; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; struct address_space *mapping; /* * There is no default zero huge page for all huge page sizes as * supported by hugetlb. A PMD_SIZE huge pages may exist as used * by THP. Since we can not reliably insert a zero page, this * feature is not supported. */ if (zeropage) { up_read(&dst_mm->mmap_sem); return -EINVAL; } src_addr = src_start; dst_addr = dst_start; copied = 0; page = NULL; vma_hpagesize = vma_kernel_pagesize(dst_vma); /* * Validate alignment based on huge page size */ err = -EINVAL; if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1)) goto out_unlock; retry: /* * On routine entry dst_vma is set. If we had to drop mmap_sem and * retry, dst_vma will be set to NULL and we must lookup again. */ if (!dst_vma) { err = -ENOENT; dst_vma = find_vma(dst_mm, dst_start); if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) goto out_unlock; /* * Only allow __mcopy_atomic_hugetlb on userfaultfd * registered ranges. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) goto out_unlock; if (dst_start < dst_vma->vm_start || dst_start + len > dst_vma->vm_end) goto out_unlock; err = -EINVAL; if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) goto out_unlock; vm_shared = dst_vma->vm_flags & VM_SHARED; } if (WARN_ON(dst_addr & (vma_hpagesize - 1) || (len - copied) & (vma_hpagesize - 1))) goto out_unlock; /* * If not shared, ensure the dst_vma has a anon_vma. */ err = -ENOMEM; if (!vm_shared) { if (unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; } h = hstate_vma(dst_vma); while (src_addr < src_start + len) { pte_t dst_pteval; BUG_ON(dst_addr >= dst_start + len); VM_BUG_ON(dst_addr & ~huge_page_mask(h)); /* * Serialize via hugetlb_fault_mutex */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping, idx, dst_addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } err = -EEXIST; dst_pteval = huge_ptep_get(dst_pte); if (!huge_pte_none(dst_pteval)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, src_addr, &page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); vm_alloc_shared = vm_shared; cond_resched(); if (unlikely(err == -EFAULT)) { up_read(&dst_mm->mmap_sem); BUG_ON(!page); err = copy_huge_page_from_user(page, (const void __user *)src_addr, pages_per_huge_page(h), true); if (unlikely(err)) { err = -EFAULT; goto out; } down_read(&dst_mm->mmap_sem); dst_vma = NULL; goto retry; } else BUG_ON(page); if (!err) { dst_addr += vma_hpagesize; src_addr += vma_hpagesize; copied += vma_hpagesize; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: up_read(&dst_mm->mmap_sem); out: if (page) { /* * We encountered an error and are about to free a newly * allocated huge page. * * Reservation handling is very subtle, and is different for * private and shared mappings. See the routine * restore_reserve_on_error for details. Unfortunately, we * can not call restore_reserve_on_error now as it would * require holding mmap_sem. * * If a reservation for the page existed in the reservation * map of a private mapping, the map was modified to indicate * the reservation was consumed when the page was allocated. * We clear the PagePrivate flag now so that the global * reserve count will not be incremented in free_huge_page. * The reservation map will still indicate the reservation * was consumed and possibly prevent later page allocation. * This is better than leaking a global reservation. If no * reservation existed, it is still safe to clear PagePrivate * as no adjustments to reservation counts were made during * allocation. * * The reservation map for shared mappings indicates which * pages have reservations. When a huge page is allocated * for an address with a reservation, no change is made to * the reserve map. In this case PagePrivate will be set * to indicate that the global reservation count should be * incremented when the page is freed. This is the desired * behavior. However, when a huge page is allocated for an * address without a reservation a reservation entry is added * to the reservation map, and PagePrivate will not be set. * When the page is freed, the global reserve count will NOT * be incremented and it will appear as though we have leaked * reserved page. In this case, set PagePrivate so that the * global reserve count will be incremented to match the * reservation map entry which was created. * * Note that vm_alloc_shared is based on the flags of the vma * for which the page was originally allocated. dst_vma could * be different or NULL on error. */ if (vm_alloc_shared) SetPagePrivate(page); else ClearPagePrivate(page); put_page(page); } BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; }

Contributors

PersonTokensPropCommitsCommitProp
Mike Kravetz56281.45%457.14%
Andrea Arcangeli10415.07%228.57%
Mike Rapoport243.48%114.29%
Total690100.00%7100.00%

#else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, bool zeropage); #endif /* CONFIG_HUGETLB_PAGE */
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool zeropage) { struct vm_area_struct *dst_vma; ssize_t err; pmd_t *dst_pmd; unsigned long src_addr, dst_addr; long copied; struct page *page; /* * Sanitize the command parameters: */ BUG_ON(dst_start & ~PAGE_MASK); BUG_ON(len & ~PAGE_MASK); /* Does the address range wrap, or is the span zero-sized? */ BUG_ON(src_start + len <= src_start); BUG_ON(dst_start + len <= dst_start); src_addr = src_start; dst_addr = dst_start; copied = 0; page = NULL; retry: down_read(&dst_mm->mmap_sem); /* * Make sure the vma is not shared, that the dst range is * both valid and fully within a single existing vma. */ err = -ENOENT; dst_vma = find_vma(dst_mm, dst_start); if (!dst_vma) goto out_unlock; /* * Be strict and only allow __mcopy_atomic on userfaultfd * registered ranges to prevent userland errors going * unnoticed. As far as the VM consistency is concerned, it * would be perfectly safe to remove this check, but there's * no useful usage for __mcopy_atomic ouside of userfaultfd * registered ranges. This is after all why these are ioctls * belonging to the userfaultfd and not syscalls. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) goto out_unlock; if (dst_start < dst_vma->vm_start || dst_start + len > dst_vma->vm_end) goto out_unlock; err = -EINVAL; /* * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but * it will overwrite vm_ops, so vma_is_anonymous must return false. */ if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) && dst_vma->vm_flags & VM_SHARED)) goto out_unlock; /* * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, src_start, len, zeropage); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; /* * Ensure the dst_vma has a anon_vma or this page * would get a NULL anon_vma when moved in the * dst_vma. */ err = -ENOMEM; if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; while (src_addr < src_start + len) { pmd_t dst_pmdval; BUG_ON(dst_addr >= dst_start + len); dst_pmd = mm_alloc_pmd(dst_mm, dst_addr); if (unlikely(!dst_pmd)) { err = -ENOMEM; break; } dst_pmdval = pmd_read_atomic(dst_pmd); /* * If the dst_pmd is mapped as THP don't * override it and just be strict. */ if (unlikely(pmd_trans_huge(dst_pmdval))) { err = -EEXIST; break; } if (unlikely(pmd_none(dst_pmdval)) && unlikely(__pte_alloc(dst_mm, dst_pmd, dst_addr))) { err = -ENOMEM; break; } /* If an huge pmd materialized from under us fail */ if (unlikely(pmd_trans_huge(*dst_pmd))) { err = -EFAULT; break; } BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); if (vma_is_anonymous(dst_vma)) { if (!zeropage) err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, &page); else err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, dst_addr); } else { err = -EINVAL; /* if zeropage is true return -EINVAL */ if (likely(!zeropage)) err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, &page); } cond_resched(); if (unlikely(err == -EFAULT)) { void *page_kaddr; up_read(&dst_mm->mmap_sem); BUG_ON(!page); page_kaddr = kmap(page); err = copy_from_user(page_kaddr, (const void __user *) src_addr, PAGE_SIZE); kunmap(page); if (unlikely(err)) { err = -EFAULT; goto out; } goto retry; } else BUG_ON(page); if (!err) { dst_addr += PAGE_SIZE; src_addr += PAGE_SIZE; copied += PAGE_SIZE; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: up_read(&dst_mm->mmap_sem); out: if (page) put_page(page); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli38358.30%342.86%
Mike Kravetz18127.55%114.29%
Mike Rapoport9214.00%228.57%
Kirill A. Shutemov10.15%114.29%
Total657100.00%7100.00%


ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len) { return __mcopy_atomic(dst_mm, dst_start, src_start, len, false); }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli36100.00%1100.00%
Total36100.00%1100.00%


ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, unsigned long len) { return __mcopy_atomic(dst_mm, start, 0, len, true); }

Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli32100.00%1100.00%
Total32100.00%1100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
Andrea Arcangeli110253.65%321.43%
Mike Kravetz79038.46%428.57%
Mike Rapoport1195.79%214.29%
Kirill A. Shutemov401.95%428.57%
Ingo Molnar30.15%17.14%
Total2054100.00%14100.00%
Directory: mm
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.