diff mbox series

[v2,3/5] swap: fix do_swap_page() race with swapoff

Message ID 20210417094039.51711-4-linmiaohe@huawei.com (mailing list archive)
State New
Headers show
Series close various race windows for swap | expand

Commit Message

Miaohe Lin April 17, 2021, 9:40 a.m. UTC
When I was investigating the swap code, I found the below possible race
window:

CPU 1                                   	CPU 2
-----                                   	-----
do_swap_page
  swap_readpage(skip swap cache case)
    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 <lkp@intel.com> (auto build test ERROR)
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
---
 include/linux/swap.h | 9 +++++++++
 mm/memory.c          | 9 +++++++++
 2 files changed, 18 insertions(+)

Comments

Huang, Ying April 19, 2021, 2:23 a.m. UTC | #1
Miaohe Lin <linmiaohe@huawei.com> writes:

> When I was investigating the swap code, I found the below possible race
> window:
>
> CPU 1                                   	CPU 2
> -----                                   	-----
> do_swap_page

This is OK for swap cache cases.  So

  if (data_race(si->flags & SWP_SYNCHRONOUS_IO))

should be shown here.

>   swap_readpage(skip swap cache case)
>     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).

I still suggest to squash PATCH 1-3, at least PATCH 1-2.  That will
change the relevant code together and make it easier to review.

Best Regards,
Huang, Ying

> Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device")
> Reported-by: kernel test robot <lkp@intel.com> (auto build test ERROR)
> Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
> ---
>  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 993693b38109..523c2411a135 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -528,6 +528,15 @@ 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;
>  }
Miaohe Lin April 19, 2021, 6:54 a.m. UTC | #2
On 2021/4/19 10:23, Huang, Ying wrote:
> Miaohe Lin <linmiaohe@huawei.com> writes:
> 
>> When I was investigating the swap code, I found the below possible race
>> window:
>>
>> CPU 1                                   	CPU 2
>> -----                                   	-----
>> do_swap_page
> 
> This is OK for swap cache cases.  So
> 
>   if (data_race(si->flags & SWP_SYNCHRONOUS_IO))
> 
> should be shown here.

Ok.

> 
>>   swap_readpage(skip swap cache case)
>>     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).
> 
> I still suggest to squash PATCH 1-3, at least PATCH 1-2.  That will
> change the relevant code together and make it easier to review.
> 

Will squash PATCH 1-2. Thanks.

> Best Regards,
> Huang, Ying
> 
>> Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device")
>> Reported-by: kernel test robot <lkp@intel.com> (auto build test ERROR)
>> Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
>> ---
>>  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 993693b38109..523c2411a135 100644
>> --- a/include/linux/swap.h
>> +++ b/include/linux/swap.h
>> @@ -528,6 +528,15 @@ 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;
>>  }
> .
>
diff mbox series

Patch

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 993693b38109..523c2411a135 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -528,6 +528,15 @@  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;
 }