tmp_suning_uos_patched/mm/userfaultfd.c

588 lines
15 KiB
C
Raw Normal View History

/*
* 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/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;
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 08:52:20 +08:00
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));
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);
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 08:52:20 +08:00
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 08:52:20 +08:00
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 20:29:47 +08:00
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;
_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;
}
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;
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;
}
#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;
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 {
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 08:09:25 +08:00
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 08:09:25 +08:00
/*
* 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_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));
err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
src_addr, &page, zeropage);
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)
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 20:29:47 +08:00
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 08:09:25 +08:00
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 08:09:25 +08:00
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 08:09:25 +08:00
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 08:09:25 +08:00
return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
}