mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Kirill A. Shutemov](/assets/img/avatar_default.png)
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>
308 lines
7.2 KiB
C
308 lines
7.2 KiB
C
/*
|
|
* 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/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 <asm/tlbflush.h>
|
|
#include "internal.h"
|
|
|
|
static int mcopy_atomic_pte(struct mm_struct *dst_mm,
|
|
pmd_t *dst_pmd,
|
|
struct vm_area_struct *dst_vma,
|
|
unsigned long dst_addr,
|
|
unsigned long src_addr,
|
|
struct page **pagep)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
pte_t _dst_pte, *dst_pte;
|
|
spinlock_t *ptl;
|
|
void *page_kaddr;
|
|
int ret;
|
|
struct page *page;
|
|
|
|
if (!*pagep) {
|
|
ret = -ENOMEM;
|
|
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr);
|
|
if (!page)
|
|
goto out;
|
|
|
|
page_kaddr = kmap_atomic(page);
|
|
ret = copy_from_user(page_kaddr,
|
|
(const void __user *) src_addr,
|
|
PAGE_SIZE);
|
|
kunmap_atomic(page_kaddr);
|
|
|
|
/* fallback to copy_from_user outside mmap_sem */
|
|
if (unlikely(ret)) {
|
|
ret = -EFAULT;
|
|
*pagep = page;
|
|
/* don't free the page */
|
|
goto out;
|
|
}
|
|
} else {
|
|
page = *pagep;
|
|
*pagep = NULL;
|
|
}
|
|
|
|
/*
|
|
* The memory barrier inside __SetPageUptodate makes sure that
|
|
* preceeding stores to the page contents become visible before
|
|
* the set_pte_at() write.
|
|
*/
|
|
__SetPageUptodate(page);
|
|
|
|
ret = -ENOMEM;
|
|
if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
|
|
goto out_release;
|
|
|
|
_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
|
|
if (dst_vma->vm_flags & VM_WRITE)
|
|
_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
|
|
|
|
ret = -EEXIST;
|
|
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
|
|
if (!pte_none(*dst_pte))
|
|
goto out_release_uncharge_unlock;
|
|
|
|
inc_mm_counter(dst_mm, MM_ANONPAGES);
|
|
page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
|
|
mem_cgroup_commit_charge(page, memcg, false, false);
|
|
lru_cache_add_active_or_unevictable(page, dst_vma);
|
|
|
|
set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
|
|
|
|
/* No need to invalidate - it was non-present before */
|
|
update_mmu_cache(dst_vma, dst_addr, dst_pte);
|
|
|
|
pte_unmap_unlock(dst_pte, ptl);
|
|
ret = 0;
|
|
out:
|
|
return ret;
|
|
out_release_uncharge_unlock:
|
|
pte_unmap_unlock(dst_pte, ptl);
|
|
mem_cgroup_cancel_charge(page, memcg, false);
|
|
out_release:
|
|
page_cache_release(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;
|
|
pud_t *pud;
|
|
pmd_t *pmd = NULL;
|
|
|
|
pgd = pgd_offset(mm, address);
|
|
pud = pud_alloc(mm, pgd, address);
|
|
if (pud)
|
|
/*
|
|
* 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.
|
|
*/
|
|
pmd = pmd_alloc(mm, pud, address);
|
|
return pmd;
|
|
}
|
|
|
|
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
|
|
unsigned long dst_start,
|
|
unsigned long src_start,
|
|
unsigned long len,
|
|
bool zeropage)
|
|
{
|
|
struct vm_area_struct *dst_vma;
|
|
ssize_t err;
|
|
pmd_t *dst_pmd;
|
|
unsigned long src_addr, dst_addr;
|
|
long copied;
|
|
struct page *page;
|
|
|
|
/*
|
|
* Sanitize the command parameters:
|
|
*/
|
|
BUG_ON(dst_start & ~PAGE_MASK);
|
|
BUG_ON(len & ~PAGE_MASK);
|
|
|
|
/* Does the address range wrap, or is the span zero-sized? */
|
|
BUG_ON(src_start + len <= src_start);
|
|
BUG_ON(dst_start + len <= dst_start);
|
|
|
|
src_addr = src_start;
|
|
dst_addr = dst_start;
|
|
copied = 0;
|
|
page = NULL;
|
|
retry:
|
|
down_read(&dst_mm->mmap_sem);
|
|
|
|
/*
|
|
* Make sure the vma is not shared, that the dst range is
|
|
* both valid and fully within a single existing vma.
|
|
*/
|
|
err = -EINVAL;
|
|
dst_vma = find_vma(dst_mm, dst_start);
|
|
if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
|
|
goto out_unlock;
|
|
if (dst_start < dst_vma->vm_start ||
|
|
dst_start + len > dst_vma->vm_end)
|
|
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;
|
|
|
|
/*
|
|
* FIXME: only allow copying on anonymous vmas, tmpfs should
|
|
* be added.
|
|
*/
|
|
if (dst_vma->vm_ops)
|
|
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 (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_vma, dst_pmd,
|
|
dst_addr))) {
|
|
err = -ENOMEM;
|
|
break;
|
|
}
|
|
/* If an huge pmd materialized from under us fail */
|
|
if (unlikely(pmd_trans_huge(*dst_pmd))) {
|
|
err = -EFAULT;
|
|
break;
|
|
}
|
|
|
|
BUG_ON(pmd_none(*dst_pmd));
|
|
BUG_ON(pmd_trans_huge(*dst_pmd));
|
|
|
|
if (!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);
|
|
|
|
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)
|
|
page_cache_release(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,
|
|
unsigned long src_start, unsigned long len)
|
|
{
|
|
return __mcopy_atomic(dst_mm, dst_start, src_start, len, false);
|
|
}
|
|
|
|
ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
|
|
unsigned long len)
|
|
{
|
|
return __mcopy_atomic(dst_mm, start, 0, len, true);
|
|
}
|