The scenario on which "Free swap -4kB" happens in my system, which is caused by
get_swap_page_of_type or get_swap_pages racing with show_mem. Remove the race
here.
Signed-off-by: Zhaoyang Huang <[email protected]>
---
mm/swapfile.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cf63b5f..13201b6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -974,6 +974,8 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
/* Only single cluster request supported */
WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
+ spin_lock(&swap_avail_lock);
+
avail_pgs = atomic_long_read(&nr_swap_pages) / size;
if (avail_pgs <= 0)
goto noswap;
@@ -986,8 +988,6 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
atomic_long_sub(n_goal * size, &nr_swap_pages);
- spin_lock(&swap_avail_lock);
-
start_over:
node = numa_node_id();
plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
@@ -1061,14 +1061,13 @@ swp_entry_t get_swap_page_of_type(int type)
spin_lock(&si->lock);
if (si->flags & SWP_WRITEOK) {
- atomic_long_dec(&nr_swap_pages);
/* This is called for allocating swap entry, not cache */
offset = scan_swap_map(si, 1);
if (offset) {
+ atomic_long_dec(&nr_swap_pages);
spin_unlock(&si->lock);
return swp_entry(type, offset);
}
- atomic_long_inc(&nr_swap_pages);
}
spin_unlock(&si->lock);
fail:
--
1.9.1
It is show_swap_cache_info() which races with get_swap_xxx
On Thu, Dec 3, 2020 at 7:36 PM Zhaoyang Huang <[email protected]> wrote:
>
> The scenario on which "Free swap -4kB" happens in my system, which is caused by
> get_swap_page_of_type or get_swap_pages racing with show_mem. Remove the race
> here.
>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> mm/swapfile.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index cf63b5f..13201b6 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -974,6 +974,8 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
> /* Only single cluster request supported */
> WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
>
> + spin_lock(&swap_avail_lock);
> +
> avail_pgs = atomic_long_read(&nr_swap_pages) / size;
> if (avail_pgs <= 0)
> goto noswap;
> @@ -986,8 +988,6 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
>
> atomic_long_sub(n_goal * size, &nr_swap_pages);
>
> - spin_lock(&swap_avail_lock);
> -
> start_over:
> node = numa_node_id();
> plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
> @@ -1061,14 +1061,13 @@ swp_entry_t get_swap_page_of_type(int type)
>
> spin_lock(&si->lock);
> if (si->flags & SWP_WRITEOK) {
> - atomic_long_dec(&nr_swap_pages);
> /* This is called for allocating swap entry, not cache */
> offset = scan_swap_map(si, 1);
> if (offset) {
> + atomic_long_dec(&nr_swap_pages);
> spin_unlock(&si->lock);
> return swp_entry(type, offset);
> }
> - atomic_long_inc(&nr_swap_pages);
> }
> spin_unlock(&si->lock);
> fail:
> --
> 1.9.1
>
On 12/3/20 12:36 PM, Zhaoyang Huang wrote:
> The scenario on which "Free swap -4kB" happens in my system, which is caused by
> get_swap_page_of_type or get_swap_pages racing with show_mem. Remove the race
> here.
>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> mm/swapfile.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index cf63b5f..13201b6 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -974,6 +974,8 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
> /* Only single cluster request supported */
> WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
>
> + spin_lock(&swap_avail_lock);
> +
> avail_pgs = atomic_long_read(&nr_swap_pages) / size;
> if (avail_pgs <= 0)
> goto noswap;
This goto will leave with the spin lock locked, so that's a bug.
> @@ -986,8 +988,6 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
>
> atomic_long_sub(n_goal * size, &nr_swap_pages);
>
> - spin_lock(&swap_avail_lock);
> -
Is the problem that while we adjust n_goal with a min3(..., avail_pgs), somebody
else can decrease nr_swap_pages in the meanwhile and then we underflow? If yes,
the spin lock won't eliminate all such cases it seems, as e.g.
get_swap_page_of_type isn't done under the same lock, AFAIK.
> start_over:
> node = numa_node_id();
> plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
> @@ -1061,14 +1061,13 @@ swp_entry_t get_swap_page_of_type(int type)
>
> spin_lock(&si->lock);
> if (si->flags & SWP_WRITEOK) {
> - atomic_long_dec(&nr_swap_pages);
> /* This is called for allocating swap entry, not cache */
> offset = scan_swap_map(si, 1);
> if (offset) {
> + atomic_long_dec(&nr_swap_pages);
> spin_unlock(&si->lock);
> return swp_entry(type, offset);
> }
> - atomic_long_inc(&nr_swap_pages);
This hunk looks safer, unless I miss something. Did you check if it's enough to
prevent the negative values on your systems?
> }
> spin_unlock(&si->lock);
> fail:
>