percpu: make pcpu_alloc() aware of current gfp context

Since 5.7-rc1, on btrfs we have a percpu counter initialization for
which we always pass a GFP_KERNEL gfp_t argument (this happens since
commit 2992df73268f78 ("btrfs: Implement DREW lock")).

That is safe in some contextes but not on others where allowing fs
reclaim could lead to a deadlock because we are either holding some
btrfs lock needed for a transaction commit or holding a btrfs
transaction handle open.  Because of that we surround the call to the
function that initializes the percpu counter with a NOFS context using
memalloc_nofs_save() (this is done at btrfs_init_fs_root()).

However it turns out that this is not enough to prevent a possible
deadlock because percpu_alloc() determines if it is in an atomic context
by looking exclusively at the gfp flags passed to it (GFP_KERNEL in this
case) and it is not aware that a NOFS context is set.

Because percpu_alloc() thinks it is in a non atomic context it locks the
pcpu_alloc_mutex.  This can result in a btrfs deadlock when
pcpu_balance_workfn() is running, has acquired that mutex and is waiting
for reclaim, while the btrfs task that called percpu_counter_init() (and
therefore percpu_alloc()) is holding either the btrfs commit_root
semaphore or a transaction handle (done fs/btrfs/backref.c:
iterate_extent_inodes()), which prevents reclaim from finishing as an
attempt to commit the current btrfs transaction will deadlock.

Lockdep reports this issue with the following trace:

  ======================================================
  WARNING: possible circular locking dependency detected
  5.6.0-rc7-btrfs-next-77 #1 Not tainted
  ------------------------------------------------------
  kswapd0/91 is trying to acquire lock:
  ffff8938a3b3fdc8 (&delayed_node->mutex){+.+.}, at: __btrfs_release_delayed_node.part.0+0x3f/0x320 [btrfs]

  but task is already holding lock:
  ffffffffb4f0dbc0 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x5/0x30

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

  -> #4 (fs_reclaim){+.+.}:
         fs_reclaim_acquire.part.0+0x25/0x30
         __kmalloc+0x5f/0x3a0
         pcpu_create_chunk+0x19/0x230
         pcpu_balance_workfn+0x56a/0x680
         process_one_work+0x235/0x5f0
         worker_thread+0x50/0x3b0
         kthread+0x120/0x140
         ret_from_fork+0x3a/0x50

  -> #3 (pcpu_alloc_mutex){+.+.}:
         __mutex_lock+0xa9/0xaf0
         pcpu_alloc+0x480/0x7c0
         __percpu_counter_init+0x50/0xd0
         btrfs_drew_lock_init+0x22/0x70 [btrfs]
         btrfs_get_fs_root+0x29c/0x5c0 [btrfs]
         resolve_indirect_refs+0x120/0xa30 [btrfs]
         find_parent_nodes+0x50b/0xf30 [btrfs]
         btrfs_find_all_leafs+0x60/0xb0 [btrfs]
         iterate_extent_inodes+0x139/0x2f0 [btrfs]
         iterate_inodes_from_logical+0xa1/0xe0 [btrfs]
         btrfs_ioctl_logical_to_ino+0xb4/0x190 [btrfs]
         btrfs_ioctl+0x165a/0x3130 [btrfs]
         ksys_ioctl+0x87/0xc0
         __x64_sys_ioctl+0x16/0x20
         do_syscall_64+0x5c/0x260
         entry_SYSCALL_64_after_hwframe+0x49/0xbe

  -> #2 (&fs_info->commit_root_sem){++++}:
         down_write+0x38/0x70
         btrfs_cache_block_group+0x2ec/0x500 [btrfs]
         find_free_extent+0xc6a/0x1600 [btrfs]
         btrfs_reserve_extent+0x9b/0x180 [btrfs]
         btrfs_alloc_tree_block+0xc1/0x350 [btrfs]
         alloc_tree_block_no_bg_flush+0x4a/0x60 [btrfs]
         __btrfs_cow_block+0x122/0x5a0 [btrfs]
         btrfs_cow_block+0x106/0x240 [btrfs]
         commit_cowonly_roots+0x55/0x310 [btrfs]
         btrfs_commit_transaction+0x509/0xb20 [btrfs]
         sync_filesystem+0x74/0x90
         generic_shutdown_super+0x22/0x100
         kill_anon_super+0x14/0x30
         btrfs_kill_super+0x12/0x20 [btrfs]
         deactivate_locked_super+0x31/0x70
         cleanup_mnt+0x100/0x160
         task_work_run+0x93/0xc0
         exit_to_usermode_loop+0xf9/0x100
         do_syscall_64+0x20d/0x260
         entry_SYSCALL_64_after_hwframe+0x49/0xbe

  -> #1 (&space_info->groups_sem){++++}:
         down_read+0x3c/0x140
         find_free_extent+0xef6/0x1600 [btrfs]
         btrfs_reserve_extent+0x9b/0x180 [btrfs]
         btrfs_alloc_tree_block+0xc1/0x350 [btrfs]
         alloc_tree_block_no_bg_flush+0x4a/0x60 [btrfs]
         __btrfs_cow_block+0x122/0x5a0 [btrfs]
         btrfs_cow_block+0x106/0x240 [btrfs]
         btrfs_search_slot+0x50c/0xd60 [btrfs]
         btrfs_lookup_inode+0x3a/0xc0 [btrfs]
         __btrfs_update_delayed_inode+0x90/0x280 [btrfs]
         __btrfs_commit_inode_delayed_items+0x81f/0x870 [btrfs]
         __btrfs_run_delayed_items+0x8e/0x180 [btrfs]
         btrfs_commit_transaction+0x31b/0xb20 [btrfs]
         iterate_supers+0x87/0xf0
         ksys_sync+0x60/0xb0
         __ia32_sys_sync+0xa/0x10
         do_syscall_64+0x5c/0x260
         entry_SYSCALL_64_after_hwframe+0x49/0xbe

  -> #0 (&delayed_node->mutex){+.+.}:
         __lock_acquire+0xef0/0x1c80
         lock_acquire+0xa2/0x1d0
         __mutex_lock+0xa9/0xaf0
         __btrfs_release_delayed_node.part.0+0x3f/0x320 [btrfs]
         btrfs_evict_inode+0x40d/0x560 [btrfs]
         evict+0xd9/0x1c0
         dispose_list+0x48/0x70
         prune_icache_sb+0x54/0x80
         super_cache_scan+0x124/0x1a0
         do_shrink_slab+0x176/0x440
         shrink_slab+0x23a/0x2c0
         shrink_node+0x188/0x6e0
         balance_pgdat+0x31d/0x7f0
         kswapd+0x238/0x550
         kthread+0x120/0x140
         ret_from_fork+0x3a/0x50

  other info that might help us debug this:

  Chain exists of:
    &delayed_node->mutex --> pcpu_alloc_mutex --> fs_reclaim

   Possible unsafe locking scenario:

         CPU0                    CPU1
         ----                    ----
    lock(fs_reclaim);
                                 lock(pcpu_alloc_mutex);
                                 lock(fs_reclaim);
    lock(&delayed_node->mutex);

   *** DEADLOCK ***

  3 locks held by kswapd0/91:
   #0: (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x5/0x30
   #1: (shrinker_rwsem){++++}, at: shrink_slab+0x12f/0x2c0
   #2: (&type->s_umount_key#43){++++}, at: trylock_super+0x16/0x50

  stack backtrace:
  CPU: 1 PID: 91 Comm: kswapd0 Not tainted 5.6.0-rc7-btrfs-next-77 #1
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014
  Call Trace:
   dump_stack+0x8f/0xd0
   check_noncircular+0x170/0x190
   __lock_acquire+0xef0/0x1c80
   lock_acquire+0xa2/0x1d0
   __mutex_lock+0xa9/0xaf0
   __btrfs_release_delayed_node.part.0+0x3f/0x320 [btrfs]
   btrfs_evict_inode+0x40d/0x560 [btrfs]
   evict+0xd9/0x1c0
   dispose_list+0x48/0x70
   prune_icache_sb+0x54/0x80
   super_cache_scan+0x124/0x1a0
   do_shrink_slab+0x176/0x440
   shrink_slab+0x23a/0x2c0
   shrink_node+0x188/0x6e0
   balance_pgdat+0x31d/0x7f0
   kswapd+0x238/0x550
   kthread+0x120/0x140
   ret_from_fork+0x3a/0x50

This could be fixed by making btrfs pass GFP_NOFS instead of GFP_KERNEL
to percpu_counter_init() in contextes where it is not reclaim safe,
however that type of approach is discouraged since
memalloc_[nofs|noio]_save() were introduced.  Therefore this change
makes pcpu_alloc() look up into an existing nofs/noio context before
deciding whether it is in an atomic context or not.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Link: http://lkml.kernel.org/r/20200430164356.15543-1-fdmanana@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 10 insertions, 4 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index d7e3bc649f4e..7da7d7737dab 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
-	/* whitelisted flags that can be passed to the backing allocators */
-	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
-	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
-	bool do_warn = !(gfp & __GFP_NOWARN);
+	gfp_t pcpu_gfp;
+	bool is_atomic;
+	bool do_warn;
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk, *next;
 	const char *err;
@@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	void __percpu *ptr;
 	size_t bits, bit_align;
 
+	gfp = current_gfp_context(gfp);
+	/* whitelisted flags that can be passed to the backing allocators */
+	pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	do_warn = !(gfp & __GFP_NOWARN);
+
 	/*
 	 * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
 	 * therefore alignment must be a minimum of that many bytes.