mirror of
https://github.com/torvalds/linux
synced 2024-09-06 18:01:05 +00:00
![Kairui Song](/assets/img/avatar_default.png)
When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit029c4628b2
("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong@tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes:0bcac06f27
("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" <ying.huang@intel.com> Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel.com/ Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song <kasong@tencent.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Yu Zhao <yuzhao@google.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Chris Li <chrisl@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Barry Song <21cnbao@gmail.com> Cc: SeongJae Park <sj@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
154 lines
4.1 KiB
C
154 lines
4.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _MM_SWAP_H
|
|
#define _MM_SWAP_H
|
|
|
|
struct mempolicy;
|
|
|
|
#ifdef CONFIG_SWAP
|
|
#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, bool do_poll,
|
|
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_writepage(struct page *page, 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)
|
|
extern struct address_space *swapper_spaces[];
|
|
#define swap_address_space(entry) \
|
|
(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
|
|
>> SWAP_ADDRESS_SPACE_SHIFT])
|
|
|
|
void show_swap_cache_info(void);
|
|
bool add_to_swap(struct folio *folio);
|
|
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);
|
|
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 page *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;
|
|
}
|
|
#else /* CONFIG_SWAP */
|
|
struct swap_iocb;
|
|
static inline void swap_read_folio(struct folio *folio, bool do_poll,
|
|
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 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 page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
|
|
struct vm_fault *vmf)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
|
|
{
|
|
}
|
|
|
|
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 bool add_to_swap(struct folio *folio)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
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;
|
|
}
|
|
#endif /* CONFIG_SWAP */
|
|
#endif /* _MM_SWAP_H */
|