kernel_optimize_test/fs/iomap/swapfile.c
Xu Yu 9295566a13 mm/swap: consider max pages in iomap_swapfile_add_extent
[ Upstream commit 36ca7943ac18aebf8aad4c50829eb2ea5ec847df ]

When the max pages (last_page in the swap header + 1) is smaller than
the total pages (inode size) of the swapfile, iomap_swapfile_activate
overwrites sis->max with total pages.

However, frontswap_map is a swap page state bitmap allocated using the
initial sis->max page count read from the swap header.  If swapfile
activation increases sis->max, it's possible for the frontswap code to
walk off the end of the bitmap, thereby corrupting kernel memory.

[djwong: modify the description a bit; the original paragraph reads:

"However, frontswap_map is allocated using max pages. When test and clear
the sis offset, which is larger than max pages, of frontswap_map in
__frontswap_invalidate_page(), neighbors of frontswap_map may be
overwritten, i.e., slab is polluted."

Note also that this bug resulted in a behavioral change: activating a
swap file that was formatted and later extended results in all pages
being activated, not the number of pages recorded in the swap header.]

This fixes the issue by considering the limitation of max pages of swap
info in iomap_swapfile_add_extent().

To reproduce the case, compile kernel with slub RED ZONE, then run test:
$ sudo stress-ng -a 1 -x softlockup,resources -t 72h --metrics --times \
 --verify -v -Y /root/tmpdir/stress-ng/stress-statistic-12.yaml \
 --log-file /root/tmpdir/stress-ng/stress-logfile-12.txt \
 --temp-path /root/tmpdir/stress-ng/

We'll get the error log as below:

[ 1151.015141] =============================================================================
[ 1151.016489] BUG kmalloc-16 (Not tainted): Right Redzone overwritten
[ 1151.017486] -----------------------------------------------------------------------------
[ 1151.017486]
[ 1151.018997] Disabling lock debugging due to kernel taint
[ 1151.019873] INFO: 0x0000000084e43932-0x0000000098d17cae @offset=7392. First byte 0x0 instead of 0xcc
[ 1151.021303] INFO: Allocated in __do_sys_swapon+0xcf6/0x1170 age=43417 cpu=9 pid=3816
[ 1151.022538]  __slab_alloc+0xe/0x20
[ 1151.023069]  __kmalloc_node+0xfd/0x4b0
[ 1151.023704]  __do_sys_swapon+0xcf6/0x1170
[ 1151.024346]  do_syscall_64+0x33/0x40
[ 1151.024925]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1151.025749] INFO: Freed in put_cred_rcu+0xa1/0xc0 age=43424 cpu=3 pid=2041
[ 1151.026889]  kfree+0x276/0x2b0
[ 1151.027405]  put_cred_rcu+0xa1/0xc0
[ 1151.027949]  rcu_do_batch+0x17d/0x410
[ 1151.028566]  rcu_core+0x14e/0x2b0
[ 1151.029084]  __do_softirq+0x101/0x29e
[ 1151.029645]  asm_call_irq_on_stack+0x12/0x20
[ 1151.030381]  do_softirq_own_stack+0x37/0x40
[ 1151.031037]  do_softirq.part.15+0x2b/0x30
[ 1151.031710]  __local_bh_enable_ip+0x4b/0x50
[ 1151.032412]  copy_fpstate_to_sigframe+0x111/0x360
[ 1151.033197]  __setup_rt_frame+0xce/0x480
[ 1151.033809]  arch_do_signal+0x1a3/0x250
[ 1151.034463]  exit_to_user_mode_prepare+0xcf/0x110
[ 1151.035242]  syscall_exit_to_user_mode+0x27/0x190
[ 1151.035970]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1151.036795] INFO: Slab 0x000000003b9de4dc objects=44 used=9 fp=0x00000000539e349e flags=0xfffffc0010201
[ 1151.038323] INFO: Object 0x000000004855ba01 @offset=7376 fp=0x0000000000000000
[ 1151.038323]
[ 1151.039683] Redzone  000000008d0afd3d: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc  ................
[ 1151.041180] Object   000000004855ba01: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[ 1151.042714] Redzone  0000000084e43932: 00 00 00 c0 cc cc cc cc                          ........
[ 1151.044120] Padding  000000000864c042: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  ZZZZZZZZZZZZZZZZ
[ 1151.045615] CPU: 5 PID: 3816 Comm: stress-ng Tainted: G    B             5.10.50+ #7
[ 1151.046846] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[ 1151.048633] Call Trace:
[ 1151.049072]  dump_stack+0x57/0x6a
[ 1151.049585]  check_bytes_and_report+0xed/0x110
[ 1151.050320]  check_object+0x1eb/0x290
[ 1151.050924]  ? __x64_sys_swapoff+0x39a/0x540
[ 1151.051646]  free_debug_processing+0x151/0x350
[ 1151.052333]  __slab_free+0x21a/0x3a0
[ 1151.052938]  ? _cond_resched+0x2d/0x40
[ 1151.053529]  ? __vunmap+0x1de/0x220
[ 1151.054139]  ? __x64_sys_swapoff+0x39a/0x540
[ 1151.054796]  ? kfree+0x276/0x2b0
[ 1151.055307]  kfree+0x276/0x2b0
[ 1151.055832]  __x64_sys_swapoff+0x39a/0x540
[ 1151.056466]  do_syscall_64+0x33/0x40
[ 1151.057084]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1151.057866] RIP: 0033:0x150340b0ffb7
[ 1151.058481] Code: Unable to access opcode bytes at RIP 0x150340b0ff8d.
[ 1151.059537] RSP: 002b:00007fff7f4ee238 EFLAGS: 00000246 ORIG_RAX: 00000000000000a8
[ 1151.060768] RAX: ffffffffffffffda RBX: 00007fff7f4ee66c RCX: 0000150340b0ffb7
[ 1151.061904] RDX: 000000000000000a RSI: 0000000000018094 RDI: 00007fff7f4ee860
[ 1151.063033] RBP: 00007fff7f4ef980 R08: 0000000000000000 R09: 0000150340a672bd
[ 1151.064135] R10: 00007fff7f4edca0 R11: 0000000000000246 R12: 0000000000018094
[ 1151.065253] R13: 0000000000000005 R14: 000000000160d930 R15: 00007fff7f4ee66c
[ 1151.066413] FIX kmalloc-16: Restoring 0x0000000084e43932-0x0000000098d17cae=0xcc
[ 1151.066413]
[ 1151.067890] FIX kmalloc-16: Object at 0x000000004855ba01 not freed

Fixes: 67482129cd ("iomap: add a swapfile activation function")
Fixes: a45c0eccc5 ("iomap: move the swapfile code into a separate file")
Signed-off-by: Gang Deng <gavin.dg@linux.alibaba.com>
Signed-off-by: Xu Yu <xuyu@linux.alibaba.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-09-15 09:50:42 +02:00

196 lines
5.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2018 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <darrick.wong@oracle.com>
*/
#include <linux/module.h>
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/swap.h>
/* Swapfile activation */
struct iomap_swapfile_info {
struct iomap iomap; /* accumulated iomap */
struct swap_info_struct *sis;
uint64_t lowest_ppage; /* lowest physical addr seen (pages) */
uint64_t highest_ppage; /* highest physical addr seen (pages) */
unsigned long nr_pages; /* number of pages collected */
int nr_extents; /* extent count */
};
/*
* Collect physical extents for this swap file. Physical extents reported to
* the swap code must be trimmed to align to a page boundary. The logical
* offset within the file is irrelevant since the swapfile code maps logical
* page numbers of the swap device to the physical page-aligned extents.
*/
static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
{
struct iomap *iomap = &isi->iomap;
unsigned long nr_pages;
unsigned long max_pages;
uint64_t first_ppage;
uint64_t first_ppage_reported;
uint64_t next_ppage;
int error;
if (unlikely(isi->nr_pages >= isi->sis->max))
return 0;
max_pages = isi->sis->max - isi->nr_pages;
/*
* Round the start up and the end down so that the physical
* extent aligns to a page boundary.
*/
first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
PAGE_SHIFT;
/* Skip too-short physical extents. */
if (first_ppage >= next_ppage)
return 0;
nr_pages = next_ppage - first_ppage;
nr_pages = min(nr_pages, max_pages);
/*
* Calculate how much swap space we're adding; the first page contains
* the swap header and doesn't count. The mm still wants that first
* page fed to add_swap_extent, however.
*/
first_ppage_reported = first_ppage;
if (iomap->offset == 0)
first_ppage_reported++;
if (isi->lowest_ppage > first_ppage_reported)
isi->lowest_ppage = first_ppage_reported;
if (isi->highest_ppage < (next_ppage - 1))
isi->highest_ppage = next_ppage - 1;
/* Add extent, set up for the next call. */
error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
if (error < 0)
return error;
isi->nr_extents += error;
isi->nr_pages += nr_pages;
return 0;
}
/*
* Accumulate iomaps for this swap file. We have to accumulate iomaps because
* swap only cares about contiguous page-aligned physical extents and makes no
* distinction between written and unwritten extents.
*/
static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
loff_t count, void *data, struct iomap *iomap,
struct iomap *srcmap)
{
struct iomap_swapfile_info *isi = data;
int error;
switch (iomap->type) {
case IOMAP_MAPPED:
case IOMAP_UNWRITTEN:
/* Only real or unwritten extents. */
break;
case IOMAP_INLINE:
/* No inline data. */
pr_err("swapon: file is inline\n");
return -EINVAL;
default:
pr_err("swapon: file has unallocated extents\n");
return -EINVAL;
}
/* No uncommitted metadata or shared blocks. */
if (iomap->flags & IOMAP_F_DIRTY) {
pr_err("swapon: file is not committed\n");
return -EINVAL;
}
if (iomap->flags & IOMAP_F_SHARED) {
pr_err("swapon: file has shared extents\n");
return -EINVAL;
}
/* Only one bdev per swap file. */
if (iomap->bdev != isi->sis->bdev) {
pr_err("swapon: file is on multiple devices\n");
return -EINVAL;
}
if (isi->iomap.length == 0) {
/* No accumulated extent, so just store it. */
memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
} else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
/* Append this to the accumulated extent. */
isi->iomap.length += iomap->length;
} else {
/* Otherwise, add the retained iomap and store this one. */
error = iomap_swapfile_add_extent(isi);
if (error)
return error;
memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
}
return count;
}
/*
* Iterate a swap file's iomaps to construct physical extents that can be
* passed to the swapfile subsystem.
*/
int iomap_swapfile_activate(struct swap_info_struct *sis,
struct file *swap_file, sector_t *pagespan,
const struct iomap_ops *ops)
{
struct iomap_swapfile_info isi = {
.sis = sis,
.lowest_ppage = (sector_t)-1ULL,
};
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
loff_t pos = 0;
loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE);
loff_t ret;
/*
* Persist all file mapping metadata so that we won't have any
* IOMAP_F_DIRTY iomaps.
*/
ret = vfs_fsync(swap_file, 1);
if (ret)
return ret;
while (len > 0) {
ret = iomap_apply(inode, pos, len, IOMAP_REPORT,
ops, &isi, iomap_swapfile_activate_actor);
if (ret <= 0)
return ret;
pos += ret;
len -= ret;
}
if (isi.iomap.length) {
ret = iomap_swapfile_add_extent(&isi);
if (ret)
return ret;
}
/*
* If this swapfile doesn't contain even a single page-aligned
* contiguous range of blocks, reject this useless swapfile to
* prevent confusion later on.
*/
if (isi.nr_pages == 0) {
pr_warn("swapon: Cannot find a single usable page in file.\n");
return -EINVAL;
}
*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
sis->max = isi.nr_pages;
sis->pages = isi.nr_pages - 1;
sis->highest_bit = isi.nr_pages - 1;
return isi.nr_extents;
}
EXPORT_SYMBOL_GPL(iomap_swapfile_activate);