linux/mm/userfaultfd.c

616 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/userfaultfd.c
*
* Copyright (C) 2015 Red Hat, Inc.
*/
#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/shmem_fs.h>
#include <asm/tlbflush.h>
#include "internal.h"
static __always_inline
struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
unsigned long dst_start,
unsigned long len)
{
/*
* Make sure that the dst range is both valid and fully within a
* single existing vma.
*/
struct vm_area_struct *dst_vma;
dst_vma = find_vma(dst_mm, dst_start);
if (!dst_vma)
return NULL;
if (dst_start < dst_vma->vm_start ||
dst_start + len > dst_vma->vm_end)
return NULL;
/*
* Check the vma is registered in uffd, this is required to
* enforce the VM_MAYWRITE check done at uffd registration
* time.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
return NULL;
return dst_vma;
}
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;
pgoff_t offset, max_off;
struct inode *inode;
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)) {
userfaultfd: use ENOENT instead of EFAULT if the atomic copy user fails Patch series "userfaultfd shmem updates". Jann found two bugs in the userfaultfd shmem MAP_SHARED backend: the lack of the VM_MAYWRITE check and the lack of i_size checks. Then looking into the above we also fixed the MAP_PRIVATE case. Hugh by source review also found a data loss source if UFFDIO_COPY is used on shmem MAP_SHARED PROT_READ mappings (the production usages incidentally run with PROT_READ|PROT_WRITE, so the data loss couldn't happen in those production usages like with QEMU). The whole patchset is marked for stable. We verified QEMU postcopy live migration with guest running on shmem MAP_PRIVATE run as well as before after the fix of shmem MAP_PRIVATE. Regardless if it's shmem or hugetlbfs or MAP_PRIVATE or MAP_SHARED, QEMU unconditionally invokes a punch hole if the guest mapping is filebacked and a MADV_DONTNEED too (needed to get rid of the MAP_PRIVATE COWs and for the anon backend). This patch (of 5): We internally used EFAULT to communicate with the caller, switch to ENOENT, so EFAULT can be used as a non internal retval. Link: http://lkml.kernel.org/r/20181126173452.26955-2-aarcange@redhat.com Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Hugh Dickins <hughd@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Jann Horn <jannh@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: <stable@vger.kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-11-30 22:09:25 +00:00
ret = -ENOENT;
*pagep = page;
/* don't free the page */
goto out;
}
} else {
page = *pagep;
*pagep = NULL;
}
/*
* The memory barrier inside __SetPageUptodate makes sure that
* preceding stores to the page contents become visible before
* the set_pte_at() write.
*/
__SetPageUptodate(page);
ret = -ENOMEM;
memcg: adjust to support new THP refcounting As with rmap, with new refcounting we cannot rely on PageTransHuge() to check if we need to charge size of huge page form the cgroup. We need to get information from caller to know whether it was mapped with PMD or PTE. We do uncharge when last reference on the page gone. At that point if we see PageTransHuge() it means we need to unchange whole huge page. The tricky part is partial unmap -- when we try to unmap part of huge page. We don't do a special handing of this situation, meaning we don't uncharge the part of huge page unless last user is gone or split_huge_page() is triggered. In case of cgroup memory pressure happens the partial unmapped page will be split through shrinker. This should be good enough. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:52:20 +00:00
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));
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (dst_vma->vm_file) {
/* the shmem MAP_PRIVATE case requires checking the i_size */
inode = dst_vma->vm_file->f_inode;
offset = linear_page_index(dst_vma, dst_addr);
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
ret = -EFAULT;
if (unlikely(offset >= max_off))
goto out_release_uncharge_unlock;
}
ret = -EEXIST;
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);
memcg: adjust to support new THP refcounting As with rmap, with new refcounting we cannot rely on PageTransHuge() to check if we need to charge size of huge page form the cgroup. We need to get information from caller to know whether it was mapped with PMD or PTE. We do uncharge when last reference on the page gone. At that point if we see PageTransHuge() it means we need to unchange whole huge page. The tricky part is partial unmap -- when we try to unmap part of huge page. We don't do a special handing of this situation, meaning we don't uncharge the part of huge page unless last user is gone or split_huge_page() is triggered. In case of cgroup memory pressure happens the partial unmapped page will be split through shrinker. This should be good enough. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:52:20 +00:00
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);
memcg: adjust to support new THP refcounting As with rmap, with new refcounting we cannot rely on PageTransHuge() to check if we need to charge size of huge page form the cgroup. We need to get information from caller to know whether it was mapped with PMD or PTE. We do uncharge when last reference on the page gone. At that point if we see PageTransHuge() it means we need to unchange whole huge page. The tricky part is partial unmap -- when we try to unmap part of huge page. We don't do a special handing of this situation, meaning we don't uncharge the part of huge page unless last user is gone or split_huge_page() is triggered. In case of cgroup memory pressure happens the partial unmapped page will be split through shrinker. This should be good enough. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:52:20 +00:00
mem_cgroup_cancel_charge(page, memcg, false);
out_release:
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
put_page(page);
goto out;
}
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;
pgoff_t offset, max_off;
struct inode *inode;
_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
dst_vma->vm_page_prot));
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (dst_vma->vm_file) {
/* the shmem MAP_PRIVATE case requires checking the i_size */
inode = dst_vma->vm_file->f_inode;
offset = linear_page_index(dst_vma, dst_addr);
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
ret = -EFAULT;
if (unlikely(offset >= max_off))
goto out_unlock;
}
ret = -EEXIST;
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;
}
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);
}
#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;
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_dst_vma(dst_mm, dst_start, len);
if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
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 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;
}
while (src_addr < src_start + len) {
pte_t dst_pteval;
BUG_ON(dst_addr >= dst_start + len);
/*
hugetlbfs: revert "use i_mmap_rwsem for more pmd sharing synchronization" This reverts b43a9990055958e70347c56f90ea2ae32c67334c The reverted commit caused issues with migration and poisoning of anon huge pages. The LTP move_pages12 test will cause an "unable to handle kernel NULL pointer" BUG would occur with stack similar to: RIP: 0010:down_write+0x1b/0x40 Call Trace: migrate_pages+0x81f/0xb90 __ia32_compat_sys_migrate_pages+0x190/0x190 do_move_pages_to_node.isra.53.part.54+0x2a/0x50 kernel_move_pages+0x566/0x7b0 __x64_sys_move_pages+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The purpose of the reverted patch was to fix some long existing races with huge pmd sharing. It used i_mmap_rwsem for this purpose with the idea that this could also be used to address truncate/page fault races with another patch. Further analysis has determined that i_mmap_rwsem can not be used to address all these hugetlbfs synchronization issues. Therefore, revert this patch while working an another approach to the underlying issues. Link: http://lkml.kernel.org/r/20190103235452.29335-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Jan Stancek <jstancek@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Prakash Sangappa <prakash.sangappa@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-08 23:23:36 +00:00
* Serialize via hugetlb_fault_mutex
*/
hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization While looking at BUGs associated with invalid huge page map counts, it was discovered and observed that a huge pte pointer could become 'invalid' and point to another task's page table. Consider the following: A task takes a page fault on a shared hugetlbfs file and calls huge_pte_alloc to get a ptep. Suppose the returned ptep points to a shared pmd. Now, another task truncates the hugetlbfs file. As part of truncation, it unmaps everyone who has the file mapped. If the range being truncated is covered by a shared pmd, huge_pmd_unshare will be called. For all but the last user of the shared pmd, huge_pmd_unshare will clear the pud pointing to the pmd. If the task in the middle of the page fault is not the last user, the ptep returned by huge_pte_alloc now points to another task's page table or worse. This leads to bad things such as incorrect page map/reference counts or invalid memory references. To fix, expand the use of i_mmap_rwsem as follows: - i_mmap_rwsem is held in read mode whenever huge_pmd_share is called. huge_pmd_share is only called via huge_pte_alloc, so callers of huge_pte_alloc take i_mmap_rwsem before calling. In addition, callers of huge_pte_alloc continue to hold the semaphore until finished with the ptep. - i_mmap_rwsem is held in write mode whenever huge_pmd_unshare is called. [mike.kravetz@oracle.com: add explicit check for mapping != null] Link: http://lkml.kernel.org/r/20181218223557.5202-2-mike.kravetz@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Prakash Sangappa <prakash.sangappa@oracle.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:39:38 +00:00
idx = linear_page_index(dst_vma, dst_addr);
hugetlbfs: revert "use i_mmap_rwsem for more pmd sharing synchronization" This reverts b43a9990055958e70347c56f90ea2ae32c67334c The reverted commit caused issues with migration and poisoning of anon huge pages. The LTP move_pages12 test will cause an "unable to handle kernel NULL pointer" BUG would occur with stack similar to: RIP: 0010:down_write+0x1b/0x40 Call Trace: migrate_pages+0x81f/0xb90 __ia32_compat_sys_migrate_pages+0x190/0x190 do_move_pages_to_node.isra.53.part.54+0x2a/0x50 kernel_move_pages+0x566/0x7b0 __x64_sys_move_pages+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The purpose of the reverted patch was to fix some long existing races with huge pmd sharing. It used i_mmap_rwsem for this purpose with the idea that this could also be used to address truncate/page fault races with another patch. Further analysis has determined that i_mmap_rwsem can not be used to address all these hugetlbfs synchronization issues. Therefore, revert this patch while working an another approach to the underlying issues. Link: http://lkml.kernel.org/r/20190103235452.29335-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Jan Stancek <jstancek@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Prakash Sangappa <prakash.sangappa@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-08 23:23:36 +00:00
mapping = dst_vma->vm_file->f_mapping;
hash = hugetlb_fault_mutex_hash(mapping, idx);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
err = -ENOMEM;
dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize);
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();
userfaultfd: use ENOENT instead of EFAULT if the atomic copy user fails Patch series "userfaultfd shmem updates". Jann found two bugs in the userfaultfd shmem MAP_SHARED backend: the lack of the VM_MAYWRITE check and the lack of i_size checks. Then looking into the above we also fixed the MAP_PRIVATE case. Hugh by source review also found a data loss source if UFFDIO_COPY is used on shmem MAP_SHARED PROT_READ mappings (the production usages incidentally run with PROT_READ|PROT_WRITE, so the data loss couldn't happen in those production usages like with QEMU). The whole patchset is marked for stable. We verified QEMU postcopy live migration with guest running on shmem MAP_PRIVATE run as well as before after the fix of shmem MAP_PRIVATE. Regardless if it's shmem or hugetlbfs or MAP_PRIVATE or MAP_SHARED, QEMU unconditionally invokes a punch hole if the guest mapping is filebacked and a MADV_DONTNEED too (needed to get rid of the MAP_PRIVATE COWs and for the anon backend). This patch (of 5): We internally used EFAULT to communicate with the caller, switch to ENOENT, so EFAULT can be used as a non internal retval. Link: http://lkml.kernel.org/r/20181126173452.26955-2-aarcange@redhat.com Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Hugh Dickins <hughd@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Jann Horn <jannh@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: <stable@vger.kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-11-30 22:09:25 +00:00
if (unlikely(err == -ENOENT)) {
up_read(&dst_mm->mmap_sem);
BUG_ON(!page);
err = copy_huge_page_from_user(page,
(const void __user *)src_addr,
vma_hpagesize / PAGE_SIZE,
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;
}
#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 mfill_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 **page,
bool zeropage)
{
ssize_t err;
userfaultfd: shmem: allocate anonymous memory for MAP_PRIVATE shmem Userfaultfd did not create private memory when UFFDIO_COPY was invoked on a MAP_PRIVATE shmem mapping. Instead it wrote to the shmem file, even when that had not been opened for writing. Though, fortunately, that could only happen where there was a hole in the file. Fix the shmem-backed implementation of UFFDIO_COPY to create private memory for MAP_PRIVATE mappings. The hugetlbfs-backed implementation was already correct. This change is visible to userland, if userfaultfd has been used in unintended ways: so it introduces a small risk of incompatibility, but is necessary in order to respect file permissions. An app that uses UFFDIO_COPY for anything like postcopy live migration won't notice the difference, and in fact it'll run faster because there will be no copy-on-write and memory waste in the tmpfs pagecache anymore. Userfaults on MAP_PRIVATE shmem keep triggering only on file holes like before. The real zeropage can also be built on a MAP_PRIVATE shmem mapping through UFFDIO_ZEROPAGE and that's safe because the zeropage pte is never dirty, in turn even an mprotect upgrading the vma permission from PROT_READ to PROT_READ|PROT_WRITE won't make the zeropage pte writable. Link: http://lkml.kernel.org/r/20181126173452.26955-3-aarcange@redhat.com Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Peter Xu <peterx@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-11-30 22:09:28 +00:00
/*
* The normal page fault path for a shmem will invoke the
* fault, fill the hole in the file and COW it right away. The
* result generates plain anonymous memory. So when we are
* asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll
* generate anonymous memory directly without actually filling
* the hole. For the MAP_PRIVATE case the robustness check
* only happens in the pagetable (to verify it's still none)
* and not in the radix tree.
*/
if (!(dst_vma->vm_flags & VM_SHARED)) {
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 {
if (!zeropage)
err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
dst_vma, dst_addr,
src_addr, page);
else
err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd,
dst_vma, dst_addr);
}
return err;
}
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
bool zeropage,
bool *mmap_changing)
{
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);
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
/*
* If memory mappings are changing because of non-cooperative
* operation (e.g. mremap) running in parallel, bail out and
* request the user to retry later
*/
err = -EAGAIN;
if (mmap_changing && READ_ONCE(*mmap_changing))
goto out_unlock;
/*
* 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_dst_vma(dst_mm, dst_start, len);
if (!dst_vma)
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;
userfaultfd: shmem: allocate anonymous memory for MAP_PRIVATE shmem Userfaultfd did not create private memory when UFFDIO_COPY was invoked on a MAP_PRIVATE shmem mapping. Instead it wrote to the shmem file, even when that had not been opened for writing. Though, fortunately, that could only happen where there was a hole in the file. Fix the shmem-backed implementation of UFFDIO_COPY to create private memory for MAP_PRIVATE mappings. The hugetlbfs-backed implementation was already correct. This change is visible to userland, if userfaultfd has been used in unintended ways: so it introduces a small risk of incompatibility, but is necessary in order to respect file permissions. An app that uses UFFDIO_COPY for anything like postcopy live migration won't notice the difference, and in fact it'll run faster because there will be no copy-on-write and memory waste in the tmpfs pagecache anymore. Userfaults on MAP_PRIVATE shmem keep triggering only on file holes like before. The real zeropage can also be built on a MAP_PRIVATE shmem mapping through UFFDIO_ZEROPAGE and that's safe because the zeropage pte is never dirty, in turn even an mprotect upgrading the vma permission from PROT_READ to PROT_READ|PROT_WRITE won't make the zeropage pte writable. Link: http://lkml.kernel.org/r/20181126173452.26955-3-aarcange@redhat.com Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Peter Xu <peterx@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-11-30 22:09:28 +00:00
if (!(dst_vma->vm_flags & VM_SHARED) &&
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)) &&
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-03 23:28:34 +00:00
unlikely(__pte_alloc(dst_mm, dst_pmd))) {
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));
err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
src_addr, &page, zeropage);
cond_resched();
userfaultfd: use ENOENT instead of EFAULT if the atomic copy user fails Patch series "userfaultfd shmem updates". Jann found two bugs in the userfaultfd shmem MAP_SHARED backend: the lack of the VM_MAYWRITE check and the lack of i_size checks. Then looking into the above we also fixed the MAP_PRIVATE case. Hugh by source review also found a data loss source if UFFDIO_COPY is used on shmem MAP_SHARED PROT_READ mappings (the production usages incidentally run with PROT_READ|PROT_WRITE, so the data loss couldn't happen in those production usages like with QEMU). The whole patchset is marked for stable. We verified QEMU postcopy live migration with guest running on shmem MAP_PRIVATE run as well as before after the fix of shmem MAP_PRIVATE. Regardless if it's shmem or hugetlbfs or MAP_PRIVATE or MAP_SHARED, QEMU unconditionally invokes a punch hole if the guest mapping is filebacked and a MADV_DONTNEED too (needed to get rid of the MAP_PRIVATE COWs and for the anon backend). This patch (of 5): We internally used EFAULT to communicate with the caller, switch to ENOENT, so EFAULT can be used as a non internal retval. Link: http://lkml.kernel.org/r/20181126173452.26955-2-aarcange@redhat.com Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Hugh Dickins <hughd@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Jann Horn <jannh@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: <stable@vger.kernel.org> Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-11-30 22:09:25 +00:00
if (unlikely(err == -ENOENT)) {
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)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
put_page(page);
BUG_ON(copied < 0);
BUG_ON(err > 0);
BUG_ON(!copied && !err);
return copied ? copied : err;
}
ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
unsigned long src_start, unsigned long len,
bool *mmap_changing)
{
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
return __mcopy_atomic(dst_mm, dst_start, src_start, len, false,
mmap_changing);
}
ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
unsigned long len, bool *mmap_changing)
{
userfaultfd: prevent non-cooperative events vs mcopy_atomic races If a process monitored with userfaultfd changes it's memory mappings or forks() at the same time as uffd monitor fills the process memory with UFFDIO_COPY, the actual creation of page table entries and copying of the data in mcopy_atomic may happen either before of after the memory mapping modifications and there is no way for the uffd monitor to maintain consistent view of the process memory layout. For instance, let's consider fork() running in parallel with userfaultfd_copy(): process | uffd monitor ---------------------------------+------------------------------ fork() | userfaultfd_copy() ... | ... dup_mmap() | down_read(mmap_sem) down_write(mmap_sem) | /* create PTEs, copy data */ dup_uffd() | up_read(mmap_sem) copy_page_range() | up_write(mmap_sem) | dup_uffd_complete() | /* notify monitor */ | If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will be present by the time copy_page_range() is called and they will appear in the child's memory mappings. However, if the fork() is the first to take the mmap_sem, the new pages won't be mapped in the child's address space. If the pages are not present and child tries to access them, the monitor will get page fault notification and everything is fine. However, if the pages *are present*, the child can access them without uffd noticing. And if we copy them into child it'll see the wrong data. Since we are talking about background copy, we'd need to decide whether the pages should be copied or not regardless #PF notifications. Since userfaultfd monitor has no way to determine what was the order, let's disallow userfaultfd_copy in parallel with the non-cooperative events. In such case we return -EAGAIN and the uffd monitor can understand that userfaultfd_copy() clashed with a non-cooperative event and take an appropriate action. Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-08 00:09:25 +00:00
return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
}