mm, memcontrol: move swap charge handling into get_swap_page()
Patch series "mm, memcontrol: Implement memory.swap.events", v2.
This patchset implements memory.swap.events which contains max and fail
events so that userland can monitor and respond to swap running out.
This patch (of 2):
get_swap_page() is always followed by mem_cgroup_try_charge_swap().
This patch moves mem_cgroup_try_charge_swap() into get_swap_page() and
makes get_swap_page() call the function even after swap allocation
failure.
This simplifies the callers and consolidates memcg related logic and
will ease adding swap related memcg events.
Link: http://lkml.kernel.org/r/20180416230934.GH1911913@devbig577.frc2.facebook.com
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1695f38..e816652 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6012,6 +6012,9 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
if (!memcg)
return 0;
+ if (!entry.val)
+ return 0;
+
memcg = mem_cgroup_id_get_online(memcg);
if (!mem_cgroup_is_root(memcg) &&
diff --git a/mm/shmem.c b/mm/shmem.c
index 9d6c7e5..8c43e20 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1322,9 +1322,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
if (!swap.val)
goto redirty;
- if (mem_cgroup_try_charge_swap(page, swap))
- goto free_swap;
-
/*
* Add inode to shmem_unuse()'s list of swapped-out inodes,
* if it's not already there. Do it now before the page is
@@ -1353,7 +1350,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
}
mutex_unlock(&shmem_swaplist_mutex);
-free_swap:
put_swap_page(page, swap);
redirty:
set_page_dirty(page);
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index f264189..f51ac05 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -317,7 +317,7 @@ swp_entry_t get_swap_page(struct page *page)
if (PageTransHuge(page)) {
if (IS_ENABLED(CONFIG_THP_SWAP))
get_swap_pages(1, true, &entry);
- return entry;
+ goto out;
}
/*
@@ -347,10 +347,14 @@ swp_entry_t get_swap_page(struct page *page)
}
mutex_unlock(&cache->alloc_lock);
if (entry.val)
- return entry;
+ goto out;
}
get_swap_pages(1, false, &entry);
-
+out:
+ if (mem_cgroup_try_charge_swap(page, entry)) {
+ put_swap_page(page, entry);
+ entry.val = 0;
+ }
return entry;
}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 07f9aa2..ab8e59c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -216,9 +216,6 @@ int add_to_swap(struct page *page)
if (!entry.val)
return 0;
- if (mem_cgroup_try_charge_swap(page, entry))
- goto fail;
-
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC