diff options
author | Ilya Dryomov <idryomov@gmail.com> | 2019-08-30 20:44:24 +0200 |
---|---|---|
committer | Ilya Dryomov <idryomov@gmail.com> | 2019-09-16 12:06:25 +0200 |
commit | 10c12851a022662bf6085bd4384b4ebed4c447ce (patch) | |
tree | 609a2973a0bbbd33afc073e6a122ddec858efe3f /net/ceph | |
parent | 6fd4e634835208ddb331234bfa51d75396a5c42c (diff) | |
download | linux-10c12851a022662bf6085bd4384b4ebed4c447ce.tar.bz2 |
libceph: avoid a __vmalloc() deadlock in ceph_kvmalloc()
The vmalloc allocator doesn't fully respect the specified gfp mask:
while the actual pages are allocated as requested, the page table pages
are always allocated with GFP_KERNEL. ceph_kvmalloc() may be called
with GFP_NOFS and GFP_NOIO (for ceph and rbd respectively), so this may
result in a deadlock.
There is no real reason for the current PAGE_ALLOC_COSTLY_ORDER logic,
it's just something that seemed sensible at the time (ceph_kvmalloc()
predates kvmalloc()). kvmalloc() is smarter: in an attempt to reduce
long term fragmentation, it first tries to kmalloc non-disruptively.
Switch to kvmalloc() and set the respective PF_MEMALLOC_* flag using
the scope API to avoid the deadlock. Note that kvmalloc() needs to be
passed GFP_KERNEL to enable the fallback.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Diffstat (limited to 'net/ceph')
-rw-r--r-- | net/ceph/ceph_common.c | 29 |
1 files changed, 23 insertions, 6 deletions
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index b412a3ccc4fc..2d568246803f 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -13,6 +13,7 @@ #include <linux/nsproxy.h> #include <linux/parser.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/statfs.h> @@ -185,18 +186,34 @@ int ceph_compare_options(struct ceph_options *new_opt, } EXPORT_SYMBOL(ceph_compare_options); +/* + * kvmalloc() doesn't fall back to the vmalloc allocator unless flags are + * compatible with (a superset of) GFP_KERNEL. This is because while the + * actual pages are allocated with the specified flags, the page table pages + * are always allocated with GFP_KERNEL. map_vm_area() doesn't even take + * flags because GFP_KERNEL is hard-coded in {p4d,pud,pmd,pte}_alloc(). + * + * ceph_kvmalloc() may be called with GFP_KERNEL, GFP_NOFS or GFP_NOIO. + */ void *ceph_kvmalloc(size_t size, gfp_t flags) { - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *ptr = kmalloc(size, flags | __GFP_NOWARN); - if (ptr) - return ptr; + void *p; + + if ((flags & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) { + p = kvmalloc(size, flags); + } else if ((flags & (__GFP_IO | __GFP_FS)) == __GFP_IO) { + unsigned int nofs_flag = memalloc_nofs_save(); + p = kvmalloc(size, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); + } else { + unsigned int noio_flag = memalloc_noio_save(); + p = kvmalloc(size, GFP_KERNEL); + memalloc_noio_restore(noio_flag); } - return __vmalloc(size, flags, PAGE_KERNEL); + return p; } - static int parse_fsid(const char *str, struct ceph_fsid *fsid) { int i = 0; |