linux-mainline/mm/swap.h
Kairui Song a05dd8ae5c mm/shmem, swap: fix softlockup with mTHP swapin
Following softlockup can be easily reproduced on my test machine with:

echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled
swapon /dev/zram0 # zram0 is a 48G swap device
mkdir -p /sys/fs/cgroup/memory/test
echo 1G > /sys/fs/cgroup/test/memory.max
echo $BASHPID > /sys/fs/cgroup/test/cgroup.procs
while true; do
    dd if=/dev/zero of=/tmp/test.img bs=1M count=5120
    cat /tmp/test.img > /dev/null
    rm /tmp/test.img
done

Then after a while:
watchdog: BUG: soft lockup - CPU#0 stuck for 763s! [cat:5787]
Modules linked in: zram virtiofs
CPU: 0 UID: 0 PID: 5787 Comm: cat Kdump: loaded Tainted: G             L      6.15.0.orig-gf3021d9246bc-dirty #118 PREEMPT(voluntary)·
Tainted: [L]=SOFTLOCKUP
Hardware name: Red Hat KVM/RHEL-AV, BIOS 0.0.0 02/06/2015
RIP: 0010:mpol_shared_policy_lookup+0xd/0x70
Code: e9 b8 b4 ff ff 31 c0 c3 cc cc cc cc 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 41 54 55 53 <48> 8b 1f 48 85 db 74 41 4c 8d 67 08 48 89 fb 48 89 f5 4c 89 e7 e8
RSP: 0018:ffffc90002b1fc28 EFLAGS: 00000202
RAX: 00000000001c20ca RBX: 0000000000724e1e RCX: 0000000000000001
RDX: ffff888118e214c8 RSI: 0000000000057d42 RDI: ffff888118e21518
RBP: 000000000002bec8 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000bf4 R11: 0000000000000000 R12: 0000000000000001
R13: 00000000001c20ca R14: 00000000001c20ca R15: 0000000000000000
FS:  00007f03f995c740(0000) GS:ffff88a07ad9a000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f03f98f1000 CR3: 0000000144626004 CR4: 0000000000770eb0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 shmem_alloc_folio+0x31/0xc0
 shmem_swapin_folio+0x309/0xcf0
 ? filemap_get_entry+0x117/0x1e0
 ? xas_load+0xd/0xb0
 ? filemap_get_entry+0x101/0x1e0
 shmem_get_folio_gfp+0x2ed/0x5b0
 shmem_file_read_iter+0x7f/0x2e0
 vfs_read+0x252/0x330
 ksys_read+0x68/0xf0
 do_syscall_64+0x4c/0x1c0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f03f9a46991
Code: 00 48 8b 15 81 14 10 00 f7 d8 64 89 02 b8 ff ff ff ff eb bd e8 20 ad 01 00 f3 0f 1e fa 80 3d 35 97 10 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 4f c3 66 0f 1f 44 00 00 55 48 89 e5 48 83 ec
RSP: 002b:00007fff3c52bd28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 0000000000040000 RCX: 00007f03f9a46991
RDX: 0000000000040000 RSI: 00007f03f98ba000 RDI: 0000000000000003
RBP: 00007fff3c52bd50 R08: 0000000000000000 R09: 00007f03f9b9a380
R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000040000
R13: 00007f03f98ba000 R14: 0000000000000003 R15: 0000000000000000
 </TASK>

The reason is simple, readahead brought some order 0 folio in swap cache,
and the swapin mTHP folio being allocated is in conflict with it, so
swapcache_prepare fails and causes shmem_swap_alloc_folio to return
-EEXIST, and shmem simply retries again and again causing this loop.

Fix it by applying a similar fix for anon mTHP swapin.

The performance change is very slight, time of swapin 10g zero folios
with shmem (test for 12 times):
Before:  2.47s
After:   2.48s

[kasong@tencent.com: add comment]
  Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20250609171751.36305-1-ryncsn@gmail.com
Fixes: 1dd44c0af4 ("mm: shmem: skip swapcache for swapin of synchronous swap device")
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-06-19 20:48:01 -07:00

246 lines
6.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _MM_SWAP_H
#define _MM_SWAP_H
struct mempolicy;
extern int page_cluster;
#ifdef CONFIG_SWAP
#include <linux/swapops.h> /* for swp_offset */
#include <linux/blk_types.h> /* for bio_end_io_t */
/* linux/mm/page_io.c */
int sio_pool_init(void);
struct swap_iocb;
void swap_read_folio(struct folio *folio, struct swap_iocb **plug);
void __swap_read_unplug(struct swap_iocb *plug);
static inline void swap_read_unplug(struct swap_iocb *plug)
{
if (unlikely(plug))
__swap_read_unplug(plug);
}
void swap_write_unplug(struct swap_iocb *sio);
int swap_writeout(struct folio *folio, struct writeback_control *wbc);
void __swap_writepage(struct folio *folio, struct writeback_control *wbc);
/* linux/mm/swap_state.c */
/* One swap address space for each 64M swap space */
#define SWAP_ADDRESS_SPACE_SHIFT 14
#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT)
#define SWAP_ADDRESS_SPACE_MASK (SWAP_ADDRESS_SPACE_PAGES - 1)
extern struct address_space *swapper_spaces[];
#define swap_address_space(entry) \
(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
>> SWAP_ADDRESS_SPACE_SHIFT])
/*
* Return the swap device position of the swap entry.
*/
static inline loff_t swap_dev_pos(swp_entry_t entry)
{
return ((loff_t)swp_offset(entry)) << PAGE_SHIFT;
}
/*
* Return the swap cache index of the swap entry.
*/
static inline pgoff_t swap_cache_index(swp_entry_t entry)
{
BUILD_BUG_ON((SWP_OFFSET_MASK | SWAP_ADDRESS_SPACE_MASK) != SWP_OFFSET_MASK);
return swp_offset(entry) & SWAP_ADDRESS_SPACE_MASK;
}
void show_swap_cache_info(void);
void *get_shadow_from_swap_cache(swp_entry_t entry);
int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
gfp_t gfp, void **shadowp);
void __delete_from_swap_cache(struct folio *folio,
swp_entry_t entry, void *shadow);
void delete_from_swap_cache(struct folio *folio);
void clear_shadow_from_swap_cache(int type, unsigned long begin,
unsigned long end);
void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
struct folio *swap_cache_get_folio(swp_entry_t entry,
struct vm_area_struct *vma, unsigned long addr);
struct folio *filemap_get_incore_folio(struct address_space *mapping,
pgoff_t index);
struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
struct swap_iocb **plug);
struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_flags,
struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
bool skip_if_exists);
struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
struct mempolicy *mpol, pgoff_t ilx);
struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag,
struct vm_fault *vmf);
static inline unsigned int folio_swap_flags(struct folio *folio)
{
return swp_swap_info(folio->swap)->flags;
}
/*
* Return the count of contiguous swap entries that share the same
* zeromap status as the starting entry. If is_zeromap is not NULL,
* it will return the zeromap status of the starting entry.
*/
static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
bool *is_zeromap)
{
struct swap_info_struct *sis = swp_swap_info(entry);
unsigned long start = swp_offset(entry);
unsigned long end = start + max_nr;
bool first_bit;
first_bit = test_bit(start, sis->zeromap);
if (is_zeromap)
*is_zeromap = first_bit;
if (max_nr <= 1)
return max_nr;
if (first_bit)
return find_next_zero_bit(sis->zeromap, end, start) - start;
else
return find_next_bit(sis->zeromap, end, start) - start;
}
static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
{
struct swap_info_struct *si = swp_swap_info(entry);
pgoff_t offset = swp_offset(entry);
int i;
/*
* While allocating a large folio and doing mTHP swapin, we need to
* ensure all entries are not cached, otherwise, the mTHP folio will
* be in conflict with the folio in swap cache.
*/
for (i = 0; i < max_nr; i++) {
if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
return i;
}
return i;
}
#else /* CONFIG_SWAP */
struct swap_iocb;
static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
{
}
static inline void swap_write_unplug(struct swap_iocb *sio)
{
}
static inline struct address_space *swap_address_space(swp_entry_t entry)
{
return NULL;
}
static inline pgoff_t swap_cache_index(swp_entry_t entry)
{
return 0;
}
static inline void show_swap_cache_info(void)
{
}
static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx)
{
return NULL;
}
static inline struct folio *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
struct vm_fault *vmf)
{
return NULL;
}
static inline int swap_writeout(struct folio *f, struct writeback_control *wbc)
{
return 0;
}
static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr)
{
}
static inline struct folio *swap_cache_get_folio(swp_entry_t entry,
struct vm_area_struct *vma, unsigned long addr)
{
return NULL;
}
static inline
struct folio *filemap_get_incore_folio(struct address_space *mapping,
pgoff_t index)
{
return filemap_get_folio(mapping, index);
}
static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
{
return NULL;
}
static inline int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
gfp_t gfp_mask, void **shadowp)
{
return -1;
}
static inline void __delete_from_swap_cache(struct folio *folio,
swp_entry_t entry, void *shadow)
{
}
static inline void delete_from_swap_cache(struct folio *folio)
{
}
static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
unsigned long end)
{
}
static inline unsigned int folio_swap_flags(struct folio *folio)
{
return 0;
}
static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
bool *has_zeromap)
{
return 0;
}
static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
{
return 0;
}
#endif /* CONFIG_SWAP */
/**
* folio_index - File index of a folio.
* @folio: The folio.
*
* For a folio which is either in the page cache or the swap cache,
* return its index within the address_space it belongs to. If you know
* the folio is definitely in the page cache, you can look at the folio's
* index directly.
*
* Return: The index (offset in units of pages) of a folio in its file.
*/
static inline pgoff_t folio_index(struct folio *folio)
{
if (unlikely(folio_test_swapcache(folio)))
return swap_cache_index(folio->swap);
return folio->index;
}
#endif /* _MM_SWAP_H */