linux/fs/xfs/kmem.h
Darrick J. Wong 6dcde60efd xfs: more lockdep whackamole with kmem_alloc*
Dave Airlie reported the following lockdep complaint:

>  ======================================================
>  WARNING: possible circular locking dependency detected
>  5.7.0-0.rc5.20200515git1ae7efb38854.1.fc33.x86_64 #1 Not tainted
>  ------------------------------------------------------
>  kswapd0/159 is trying to acquire lock:
>  ffff9b38d01a4470 (&xfs_nondir_ilock_class){++++}-{3:3},
>  at: xfs_ilock+0xde/0x2c0 [xfs]
>
>  but task is already holding lock:
>  ffffffffbbb8bd00 (fs_reclaim){+.+.}-{0:0}, at:
>  __fs_reclaim_acquire+0x5/0x30
>
>  which lock already depends on the new lock.
>
>
>  the existing dependency chain (in reverse order) is:
>
>  -> #1 (fs_reclaim){+.+.}-{0:0}:
>         fs_reclaim_acquire+0x34/0x40
>         __kmalloc+0x4f/0x270
>         kmem_alloc+0x93/0x1d0 [xfs]
>         kmem_alloc_large+0x4c/0x130 [xfs]
>         xfs_attr_copy_value+0x74/0xa0 [xfs]
>         xfs_attr_get+0x9d/0xc0 [xfs]
>         xfs_get_acl+0xb6/0x200 [xfs]
>         get_acl+0x81/0x160
>         posix_acl_xattr_get+0x3f/0xd0
>         vfs_getxattr+0x148/0x170
>         getxattr+0xa7/0x240
>         path_getxattr+0x52/0x80
>         do_syscall_64+0x5c/0xa0
>         entry_SYSCALL_64_after_hwframe+0x49/0xb3
>
>  -> #0 (&xfs_nondir_ilock_class){++++}-{3:3}:
>         __lock_acquire+0x1257/0x20d0
>         lock_acquire+0xb0/0x310
>         down_write_nested+0x49/0x120
>         xfs_ilock+0xde/0x2c0 [xfs]
>         xfs_reclaim_inode+0x3f/0x400 [xfs]
>         xfs_reclaim_inodes_ag+0x20b/0x410 [xfs]
>         xfs_reclaim_inodes_nr+0x31/0x40 [xfs]
>         super_cache_scan+0x190/0x1e0
>         do_shrink_slab+0x184/0x420
>         shrink_slab+0x182/0x290
>         shrink_node+0x174/0x680
>         balance_pgdat+0x2d0/0x5f0
>         kswapd+0x21f/0x510
>         kthread+0x131/0x150
>         ret_from_fork+0x3a/0x50
>
>  other info that might help us debug this:
>
>   Possible unsafe locking scenario:
>
>         CPU0                    CPU1
>         ----                    ----
>    lock(fs_reclaim);
>                                 lock(&xfs_nondir_ilock_class);
>                                 lock(fs_reclaim);
>    lock(&xfs_nondir_ilock_class);
>
>   *** DEADLOCK ***
>
>  4 locks held by kswapd0/159:
>   #0: ffffffffbbb8bd00 (fs_reclaim){+.+.}-{0:0}, at:
>  __fs_reclaim_acquire+0x5/0x30
>   #1: ffffffffbbb7cef8 (shrinker_rwsem){++++}-{3:3}, at:
>  shrink_slab+0x115/0x290
>   #2: ffff9b39f07a50e8
>  (&type->s_umount_key#56){++++}-{3:3}, at: super_cache_scan+0x38/0x1e0
>   #3: ffff9b39f077f258
>  (&pag->pag_ici_reclaim_lock){+.+.}-{3:3}, at:
>  xfs_reclaim_inodes_ag+0x82/0x410 [xfs]

This is a known false positive because inodes cannot simultaneously be
getting reclaimed and the target of a getxattr operation, but lockdep
doesn't know that.  We can (selectively) shut up lockdep until either
it gets smarter or we change inode reclaim not to require the ILOCK by
applying a stupid GFP_NOLOCKDEP bandaid.

Reported-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Tested-by: Dave Airlie <airlied@gmail.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2020-05-27 08:49:28 -07:00

105 lines
2.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_SUPPORT_KMEM_H__
#define __XFS_SUPPORT_KMEM_H__
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
/*
* General memory allocation interfaces
*/
typedef unsigned __bitwise xfs_km_flags_t;
#define KM_NOFS ((__force xfs_km_flags_t)0x0004u)
#define KM_MAYFAIL ((__force xfs_km_flags_t)0x0008u)
#define KM_ZERO ((__force xfs_km_flags_t)0x0010u)
#define KM_NOLOCKDEP ((__force xfs_km_flags_t)0x0020u)
/*
* We use a special process flag to avoid recursive callbacks into
* the filesystem during transactions. We will also issue our own
* warnings, so we explicitly skip any generic ones (silly of us).
*/
static inline gfp_t
kmem_flags_convert(xfs_km_flags_t flags)
{
gfp_t lflags;
BUG_ON(flags & ~(KM_NOFS | KM_MAYFAIL | KM_ZERO | KM_NOLOCKDEP));
lflags = GFP_KERNEL | __GFP_NOWARN;
if (flags & KM_NOFS)
lflags &= ~__GFP_FS;
/*
* Default page/slab allocator behavior is to retry for ever
* for small allocations. We can override this behavior by using
* __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long
* as it is feasible but rather fail than retry forever for all
* request sizes.
*/
if (flags & KM_MAYFAIL)
lflags |= __GFP_RETRY_MAYFAIL;
if (flags & KM_ZERO)
lflags |= __GFP_ZERO;
if (flags & KM_NOLOCKDEP)
lflags |= __GFP_NOLOCKDEP;
return lflags;
}
extern void *kmem_alloc(size_t, xfs_km_flags_t);
extern void *kmem_alloc_io(size_t size, int align_mask, xfs_km_flags_t flags);
extern void *kmem_alloc_large(size_t size, xfs_km_flags_t);
extern void *kmem_realloc(const void *, size_t, xfs_km_flags_t);
static inline void kmem_free(const void *ptr)
{
kvfree(ptr);
}
static inline void *
kmem_zalloc(size_t size, xfs_km_flags_t flags)
{
return kmem_alloc(size, flags | KM_ZERO);
}
static inline void *
kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
{
return kmem_alloc_large(size, flags | KM_ZERO);
}
/*
* Zone interfaces
*/
#define kmem_zone kmem_cache
#define kmem_zone_t struct kmem_cache
extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t);
static inline void *
kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
{
return kmem_zone_alloc(zone, flags | KM_ZERO);
}
static inline struct page *
kmem_to_page(void *addr)
{
if (is_vmalloc_addr(addr))
return vmalloc_to_page(addr);
return virt_to_page(addr);
}
#endif /* __XFS_SUPPORT_KMEM_H__ */