security_vm_enough_memory_mm() checks whether a process has enough memory
to allocate a new virtual mapping. And total_swap_pages is considered as
available memory while swapoff tries to make sure there's enough memory
that can hold the swapped out memory. But total_swap_pages contains the
swap space that is being swapoff. So security_vm_enough_memory_mm() will
success even if there's no memory to hold the swapped out memory because
total_swap_pages always greater than or equal to p->pages.
In order to fix it, p->pages should be retracted from total_swap_pages
first and then check whether there's enough memory for inuse swap pages.
Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
---
mm/swapfile.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a2e66d855b19..960d14a4b19e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2396,6 +2396,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
struct filename *pathname;
int err, found = 0;
unsigned int old_block_size;
+ unsigned int inuse_pages;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -2426,9 +2427,13 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
spin_unlock(&swap_lock);
goto out_dput;
}
- if (!security_vm_enough_memory_mm(current->mm, p->pages))
- vm_unacct_memory(p->pages);
+
+ total_swap_pages -= p->pages;
+ inuse_pages = READ_ONCE(p->inuse_pages);
+ if (!security_vm_enough_memory_mm(current->mm, inuse_pages))
+ vm_unacct_memory(inuse_pages);
else {
+ total_swap_pages += p->pages;
err = -ENOMEM;
spin_unlock(&swap_lock);
goto out_dput;
@@ -2451,7 +2456,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
}
plist_del(&p->list, &swap_active_head);
atomic_long_sub(p->pages, &nr_swap_pages);
- total_swap_pages -= p->pages;
p->flags &= ~SWP_WRITEOK;
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
--
2.23.0
