When I was investigating the swap code, I found the below possible race
window:
CPU 1 CPU 2
----- -----
do_swap_page
if (data_race(si->flags & SWP_SYNCHRONOUS_IO)
swap_readpage
if (data_race(sis->flags & SWP_FS_OPS)) {
swapoff
p->flags &= ~SWP_VALID;
..
synchronize_rcu();
..
p->swap_file = NULL;
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;[oops!]
Note that for the pages that are swapped in through swap cache, this isn't
an issue. Because the page is locked, and the swap entry will be marked
with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been
unlocked.
Using current get/put_swap_device() to guard against concurrent swapoff for
swap_readpage() looks terrible because swap_readpage() may take really long
time. And this race may not be really pernicious because swapoff is usually
done when system shutdown only. To reduce the performance overhead on the
hot-path as much as possible, it appears we can use the percpu_ref to close
this race window(as suggested by Huang, Ying).
Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device")
Reported-by: kernel test robot <[email protected]> (auto build test ERROR)
Signed-off-by: Miaohe Lin <[email protected]>
---
include/linux/swap.h | 9 +++++++++
mm/memory.c | 9 +++++++++
2 files changed, 18 insertions(+)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c9e7fea10b83..46d51d058d05 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -527,6 +527,15 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
return NULL;
}
+static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)
+{
+ return NULL;
+}
+
+static inline void put_swap_device(struct swap_info_struct *si)
+{
+}
+
#define swap_address_space(entry) (NULL)
#define get_nr_swap_pages() 0L
#define total_swap_pages 0L
diff --git a/mm/memory.c b/mm/memory.c
index 27014c3bde9f..7a2fe12cf641 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3311,6 +3311,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL, *swapcache;
+ struct swap_info_struct *si = NULL;
swp_entry_t entry;
pte_t pte;
int locked;
@@ -3338,6 +3339,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
goto out;
}
+ /* Prevent swapoff from happening to us. */
+ si = get_swap_device(entry);
+ if (unlikely(!si))
+ goto out;
delayacct_set_flag(current, DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry, vma, vmf->address);
@@ -3514,6 +3519,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
+ if (si)
+ put_swap_device(si);
return ret;
out_nomap:
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -3525,6 +3532,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
unlock_page(swapcache);
put_page(swapcache);
}
+ if (si)
+ put_swap_device(si);
return ret;
}
--
2.19.1
Miaohe Lin <[email protected]> writes:
> When I was investigating the swap code, I found the below possible race
> window:
>
> CPU 1 CPU 2
> ----- -----
> do_swap_page
> if (data_race(si->flags & SWP_SYNCHRONOUS_IO)
> swap_readpage
> if (data_race(sis->flags & SWP_FS_OPS)) {
> swapoff
> p->flags &= ~SWP_VALID;
> ..
> synchronize_rcu();
> ..
You have deleted SWP_VALID and RCU solution in 1/4, so please revise this.
> p->swap_file = NULL;
> struct file *swap_file = sis->swap_file;
> struct address_space *mapping = swap_file->f_mapping;[oops!]
>
> Note that for the pages that are swapped in through swap cache, this isn't
> an issue. Because the page is locked, and the swap entry will be marked
> with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been
> unlocked.
>
> Using current get/put_swap_device() to guard against concurrent swapoff for
> swap_readpage() looks terrible because swap_readpage() may take really long
> time. And this race may not be really pernicious because swapoff is usually
> done when system shutdown only. To reduce the performance overhead on the
> hot-path as much as possible, it appears we can use the percpu_ref to close
> this race window(as suggested by Huang, Ying).
This needs to be revised too. Unless you squash 1/4 and 2/4.
> Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device")
> Reported-by: kernel test robot <[email protected]> (auto build test ERROR)
> Signed-off-by: Miaohe Lin <[email protected]>
> ---
> include/linux/swap.h | 9 +++++++++
> mm/memory.c | 9 +++++++++
> 2 files changed, 18 insertions(+)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index c9e7fea10b83..46d51d058d05 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -527,6 +527,15 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
> return NULL;
> }
>
> +static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)
> +{
> + return NULL;
> +}
> +
> +static inline void put_swap_device(struct swap_info_struct *si)
> +{
> +}
> +
> #define swap_address_space(entry) (NULL)
> #define get_nr_swap_pages() 0L
> #define total_swap_pages 0L
> diff --git a/mm/memory.c b/mm/memory.c
> index 27014c3bde9f..7a2fe12cf641 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3311,6 +3311,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> {
> struct vm_area_struct *vma = vmf->vma;
> struct page *page = NULL, *swapcache;
> + struct swap_info_struct *si = NULL;
> swp_entry_t entry;
> pte_t pte;
> int locked;
> @@ -3338,6 +3339,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> goto out;
> }
>
> + /* Prevent swapoff from happening to us. */
> + si = get_swap_device(entry);
There's
struct swap_info_struct *si = swp_swap_info(entry);
in do_swap_page(), you can remove that.
Best Regards,
Huang, Ying
> + if (unlikely(!si))
> + goto out;
>
> delayacct_set_flag(current, DELAYACCT_PF_SWAPIN);
> page = lookup_swap_cache(entry, vma, vmf->address);
> @@ -3514,6 +3519,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> unlock:
> pte_unmap_unlock(vmf->pte, vmf->ptl);
> out:
> + if (si)
> + put_swap_device(si);
> return ret;
> out_nomap:
> pte_unmap_unlock(vmf->pte, vmf->ptl);
> @@ -3525,6 +3532,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> unlock_page(swapcache);
> put_page(swapcache);
> }
> + if (si)
> + put_swap_device(si);
> return ret;
> }