From: Ye Bin <yebin10@xxxxxxxxxx>
Fix race between rmmod and /proc/XXX's inode instantiation.
The bug is that pde->proc_ops don't belong to /proc, it belongs
to a module, therefore dereferencing it after /proc entry has been
registered is a bug unless use_pde/unuse_pde() pair has been used.
use_pde/unuse_pde can be avoided (2 atomic ops!) because pde->proc_ops
never changes so information necessary for inode instantiation can be
saved _before_ proc_register() in PDE itself and used later,
avoiding pde->proc_ops->... dereference.
rmmod lookup
sys_delete_module
proc_lookup_de
pde_get(de);
proc_get_inode(dir->i_sb, de);
mod->exit()
proc_remove
remove_proc_subtree
proc_entry_rundown(de);
free_module(mod);
if (S_ISREG(inode->i_mode))
if (de->proc_ops->proc_read_iter)
--> As module is already freed, will trigger UAF
BUG: unable to handle page fault for address: fffffbfff80a702b
PGD 817fc4067 P4D 817fc4067 PUD 817fc0067 PMD 102ef4067 PTE 0
Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI
CPU: 26 UID: 0 PID: 2667 Comm: ls Tainted: G
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
RIP: 0010:proc_get_inode+0x302/0x6e0
RSP: 0018:ffff88811c837998 EFLAGS: 00010a06
RAX: dffffc0000000000 RBX: ffffffffc0538140 RCX: 0000000000000007
RDX: 1ffffffff80a702b RSI: 0000000000000001 RDI: ffffffffc0538158
RBP: ffff8881299a6000 R08: 0000000067bbe1e5 R09: 1ffff11023906f20
R10: ffffffffb560ca07 R11: ffffffffb2b43a58 R12: ffff888105bb78f0
R13: ffff888100518048 R14: ffff8881299a6004 R15: 0000000000000001
FS: 00007f95b9686840(0000) GS:ffff8883af100000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffffbfff80a702b CR3: 0000000117dd2000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
proc_lookup_de+0x11f/0x2e0
__lookup_slow+0x188/0x350
walk_component+0x2ab/0x4f0
path_lookupat+0x120/0x660
filename_lookup+0x1ce/0x560
vfs_statx+0xac/0x150
__do_sys_newstat+0x96/0x110
do_syscall_64+0x5f/0x170
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Note:
don't do 2 atomic ops on the common path as original patch did
--adobriyan
Fixes: 778f3dd5a13c ("Fix procfs compat_ioctl regression")
Signed-off-by: Ye Bin <yebin10@xxxxxxxxxx>
Signed-off-by: Alexey Dobriyan <adobriyan@xxxxxxxxx>
---
fs/proc/generic.c | 10 +++++++++-
fs/proc/inode.c | 6 +++---
fs/proc/internal.h | 14 ++++++++++++++
include/linux/proc_fs.h | 7 +++++--
4 files changed, 31 insertions(+), 6 deletions(-)
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -559,10 +559,16 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
return p;
}
-static inline void pde_set_flags(struct proc_dir_entry *pde)
+static void pde_set_flags(struct proc_dir_entry *pde)
{
if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
pde->flags |= PROC_ENTRY_PERMANENT;
+ if (pde->proc_ops->proc_read_iter)
+ pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+ if (pde->proc_ops->proc_compat_ioctl)
+ pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
}
struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
@@ -626,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
p->proc_ops = &proc_seq_ops;
p->seq_ops = ops;
p->state_size = state_size;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_seq_private);
@@ -656,6 +663,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
return NULL;
p->proc_ops = &proc_single_ops;
p->single_show = show;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_single_data);
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
if (S_ISREG(inode->i_mode)) {
inode->i_op = de->proc_iops;
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops;
else
inode->i_fop = &proc_reg_file_ops;
#ifdef CONFIG_COMPAT
- if (de->proc_ops->proc_compat_ioctl) {
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_compat_ioctl(de)) {
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops_compat;
else
inode->i_fop = &proc_reg_file_ops_compat;
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -85,6 +85,20 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde)
pde->flags |= PROC_ENTRY_PERMANENT;
}
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+ return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+ return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+ return false;
+#endif
+}
+
extern struct kmem_cache *proc_dir_entry_cache;
void pde_free(struct proc_dir_entry *pde);
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -20,10 +20,13 @@ enum {
* If in doubt, ignore this flag.
*/
#ifdef MODULE
- PROC_ENTRY_PERMANENT = 0U,
+ PROC_ENTRY_PERMANENT = 0U,
#else
- PROC_ENTRY_PERMANENT = 1U << 0,
+ PROC_ENTRY_PERMANENT = 1U << 0,
#endif
+
+ PROC_ENTRY_proc_read_iter = 1U << 1,
+ PROC_ENTRY_proc_compat_ioctl = 1U << 2,
};
struct proc_ops {
