linux/mm/mincore.c
Suren Baghdasaryan 49b0638502 mm: enable page walking API to lock vmas during the walk
walk_page_range() and friends often operate under write-locked mmap_lock. 
With introduction of vma locks, the vmas have to be locked as well during
such walks to prevent concurrent page faults in these areas.  Add an
additional member to mm_walk_ops to indicate locking requirements for the
walk.

The change ensures that page walks which prevent concurrent page faults
by write-locking mmap_lock, operate correctly after introduction of
per-vma locks.  With per-vma locks page faults can be handled under vma
lock without taking mmap_lock at all, so write locking mmap_lock would
not stop them.  The change ensures vmas are properly locked during such
walks.

A sample issue this solves is do_mbind() performing queue_pages_range()
to queue pages for migration.  Without this change a concurrent page
can be faulted into the area and be left out of migration.

Link: https://lkml.kernel.org/r/20230804152724.3090321-2-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Suggested-by: Jann Horn <jannh@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michel Lespinasse <michel@lespinasse.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 13:07:20 -07:00

284 lines
7.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/mincore.c
*
* Copyright (C) 1994-2006 Linus Torvalds
*/
/*
* The mincore() system call.
*/
#include <linux/pagemap.h>
#include <linux/gfp.h>
#include <linux/pagewalk.h>
#include <linux/mman.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <linux/uaccess.h>
#include "swap.h"
static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
unsigned char present;
unsigned char *vec = walk->private;
/*
* Hugepages under user process are always in RAM and never
* swapped out, but theoretically it needs to be checked.
*/
present = pte && !huge_pte_none_mostly(huge_ptep_get(pte));
for (; addr != end; vec++, addr += PAGE_SIZE)
*vec = present;
walk->private = vec;
#else
BUG();
#endif
return 0;
}
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
{
unsigned char present = 0;
struct folio *folio;
/*
* When tmpfs swaps out a page from a file, any process mapping that
* file will not get a swp_entry_t in its pte, but rather it is like
* any other file mapping (ie. marked !present and faulted in with
* tmpfs's .fault). So swapped out tmpfs mappings are tested here.
*/
folio = filemap_get_incore_folio(mapping, index);
if (!IS_ERR(folio)) {
present = folio_test_uptodate(folio);
folio_put(folio);
}
return present;
}
static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
struct vm_area_struct *vma, unsigned char *vec)
{
unsigned long nr = (end - addr) >> PAGE_SHIFT;
int i;
if (vma->vm_file) {
pgoff_t pgoff;
pgoff = linear_page_index(vma, addr);
for (i = 0; i < nr; i++, pgoff++)
vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
} else {
for (i = 0; i < nr; i++)
vec[i] = 0;
}
return nr;
}
static int mincore_unmapped_range(unsigned long addr, unsigned long end,
__always_unused int depth,
struct mm_walk *walk)
{
walk->private += __mincore_unmapped_range(addr, end,
walk->vma, walk->private);
return 0;
}
static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
spinlock_t *ptl;
struct vm_area_struct *vma = walk->vma;
pte_t *ptep;
unsigned char *vec = walk->private;
int nr = (end - addr) >> PAGE_SHIFT;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
memset(vec, 1, nr);
spin_unlock(ptl);
goto out;
}
ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
if (!ptep) {
walk->action = ACTION_AGAIN;
return 0;
}
for (; addr != end; ptep++, addr += PAGE_SIZE) {
pte_t pte = ptep_get(ptep);
/* We need to do cache lookup too for pte markers */
if (pte_none_mostly(pte))
__mincore_unmapped_range(addr, addr + PAGE_SIZE,
vma, vec);
else if (pte_present(pte))
*vec = 1;
else { /* pte is a swap entry */
swp_entry_t entry = pte_to_swp_entry(pte);
if (non_swap_entry(entry)) {
/*
* migration or hwpoison entries are always
* uptodate
*/
*vec = 1;
} else {
#ifdef CONFIG_SWAP
*vec = mincore_page(swap_address_space(entry),
swp_offset(entry));
#else
WARN_ON(1);
*vec = 1;
#endif
}
}
vec++;
}
pte_unmap_unlock(ptep - 1, ptl);
out:
walk->private += nr;
cond_resched();
return 0;
}
static inline bool can_do_mincore(struct vm_area_struct *vma)
{
if (vma_is_anonymous(vma))
return true;
if (!vma->vm_file)
return false;
/*
* Reveal pagecache information only for non-anonymous mappings that
* correspond to the files the calling process could (if tried) open
* for writing; otherwise we'd be including shared non-exclusive
* mappings, which opens a side channel.
*/
return inode_owner_or_capable(&nop_mnt_idmap,
file_inode(vma->vm_file)) ||
file_permission(vma->vm_file, MAY_WRITE) == 0;
}
static const struct mm_walk_ops mincore_walk_ops = {
.pmd_entry = mincore_pte_range,
.pte_hole = mincore_unmapped_range,
.hugetlb_entry = mincore_hugetlb,
.walk_lock = PGWALK_RDLOCK,
};
/*
* Do a chunk of "sys_mincore()". We've already checked
* all the arguments, we hold the mmap semaphore: we should
* just return the amount of info we're asked for.
*/
static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
{
struct vm_area_struct *vma;
unsigned long end;
int err;
vma = vma_lookup(current->mm, addr);
if (!vma)
return -ENOMEM;
end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
if (!can_do_mincore(vma)) {
unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE);
memset(vec, 1, pages);
return pages;
}
err = walk_page_range(vma->vm_mm, addr, end, &mincore_walk_ops, vec);
if (err < 0)
return err;
return (end - addr) >> PAGE_SHIFT;
}
/*
* The mincore(2) system call.
*
* mincore() returns the memory residency status of the pages in the
* current process's address space specified by [addr, addr + len).
* The status is returned in a vector of bytes. The least significant
* bit of each byte is 1 if the referenced page is in memory, otherwise
* it is zero.
*
* Because the status of a page can change after mincore() checks it
* but before it returns to the application, the returned vector may
* contain stale information. Only locked pages are guaranteed to
* remain in memory.
*
* return values:
* zero - success
* -EFAULT - vec points to an illegal address
* -EINVAL - addr is not a multiple of PAGE_SIZE
* -ENOMEM - Addresses in the range [addr, addr + len] are
* invalid for the address space of this process, or
* specify one or more pages which are not currently
* mapped
* -EAGAIN - A kernel resource was temporarily unavailable.
*/
SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
unsigned char __user *, vec)
{
long retval;
unsigned long pages;
unsigned char *tmp;
start = untagged_addr(start);
/* Check the start address: needs to be page-aligned.. */
if (start & ~PAGE_MASK)
return -EINVAL;
/* ..and we need to be passed a valid user-space range */
if (!access_ok((void __user *) start, len))
return -ENOMEM;
/* This also avoids any overflows on PAGE_ALIGN */
pages = len >> PAGE_SHIFT;
pages += (offset_in_page(len)) != 0;
if (!access_ok(vec, pages))
return -EFAULT;
tmp = (void *) __get_free_page(GFP_USER);
if (!tmp)
return -EAGAIN;
retval = 0;
while (pages) {
/*
* Do at most PAGE_SIZE entries per iteration, due to
* the temporary buffer size.
*/
mmap_read_lock(current->mm);
retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
mmap_read_unlock(current->mm);
if (retval <= 0)
break;
if (copy_to_user(vec, tmp, retval)) {
retval = -EFAULT;
break;
}
pages -= retval;
vec += retval;
start += retval << PAGE_SHIFT;
retval = 0;
}
free_page((unsigned long) tmp);
return retval;
}