From 2fd1d2c4ceb2248a727696962cf3370dc9f5a0a4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 6 Jul 2017 08:41:06 -0500 Subject: proc: Fix proc_sys_prune_dcache to hold a sb reference Andrei Vagin writes: FYI: This bug has been reproduced on 4.11.7 > BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo} still in use (1) [unmount of proc proc] > ------------[ cut here ]------------ > WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80 > CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1 > Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015 > Workqueue: events proc_cleanup_work > Call Trace: > dump_stack+0x63/0x86 > __warn+0xcb/0xf0 > warn_slowpath_null+0x1d/0x20 > umount_check+0x6e/0x80 > d_walk+0xc6/0x270 > ? dentry_free+0x80/0x80 > do_one_tree+0x26/0x40 > shrink_dcache_for_umount+0x2d/0x90 > generic_shutdown_super+0x1f/0xf0 > kill_anon_super+0x12/0x20 > proc_kill_sb+0x40/0x50 > deactivate_locked_super+0x43/0x70 > deactivate_super+0x5a/0x60 > cleanup_mnt+0x3f/0x90 > mntput_no_expire+0x13b/0x190 > kern_unmount+0x3e/0x50 > pid_ns_release_proc+0x15/0x20 > proc_cleanup_work+0x15/0x20 > process_one_work+0x197/0x450 > worker_thread+0x4e/0x4a0 > kthread+0x109/0x140 > ? process_one_work+0x450/0x450 > ? kthread_park+0x90/0x90 > ret_from_fork+0x2c/0x40 > ---[ end trace e1c109611e5d0b41 ]--- > VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds. Have a nice day... > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: _raw_spin_lock+0xc/0x30 > PGD 0 Fix this by taking a reference to the super block in proc_sys_prune_dcache. The superblock reference is the core of the fix however the sysctl_inodes list is converted to a hlist so that hlist_del_init_rcu may be used. This allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while not causing problems for proc_sys_evict_inode when if it later choses to remove the inode from the sysctl_inodes list. Removing inodes from the sysctl_inodes list allows proc_sys_prune_dcache to have a progress guarantee, while still being able to drop all locks. The fact that head->unregistering is set in start_unregistering ensures that no more inodes will be added to the the sysctl_inodes list. Previously the code did a dance where it delayed calling iput until the next entry in the list was being considered to ensure the inode remained on the sysctl_inodes list until the next entry was walked to. The structure of the loop in this patch does not need that so is much easier to understand and maintain. Cc: stable@vger.kernel.org Reported-by: Andrei Vagin Tested-by: Andrei Vagin Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.") Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering") Signed-off-by: "Eric W. Biederman" --- include/linux/sysctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sysctl.h') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..1c04a26bfd2f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -143,7 +143,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; - struct list_head inodes; /* head for proc_inode->sysctl_inodes */ + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ }; struct ctl_dir { -- cgit v1.2.3 From 61d9b56a89208d8cccd0b4cfec7e6959717e16e3 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:40 -0700 Subject: sysctl: add unsigned int range support To keep parity with regular int interfaces provide the an unsigned int proc_douintvec_minmax() which allows you to specify a range of allowed valid numbers. Adding proc_douintvec_minmax_sysadmin() is easy but we can wait for an actual user for that. Link: http://lkml.kernel.org/r/20170519033554.18592-6-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Acked-by: Kees Cook Cc: Subash Abhinov Kasiviswanathan Cc: Heinrich Schuchardt Cc: Kees Cook Cc: "David S. Miller" Cc: Ingo Molnar Cc: Al Viro Cc: "Eric W. Biederman" Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 4 ++- include/linux/sysctl.h | 3 +++ kernel/sysctl.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 72 insertions(+), 1 deletion(-) (limited to 'include/linux/sysctl.h') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index ee6feba8b6c0..8f9d564d0969 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1065,7 +1065,8 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) { int err = 0; - if (table->proc_handler == proc_douintvec) { + if ((table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax)) { if (table->maxlen != sizeof(unsigned int)) err |= sysctl_err(path, table, "array now allowed"); } @@ -1083,6 +1084,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..225001d437ae 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d12078fc215f..df9f2a367882 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2567,6 +2567,65 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, do_proc_dointvec_minmax_conv, ¶m); } +struct do_proc_douintvec_minmax_conv_param { + unsigned int *min; + unsigned int *max; +}; + +static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + struct do_proc_douintvec_minmax_conv_param *param = data; + + if (write) { + unsigned int val = *lvalp; + + if ((param->min && *param->min > val) || + (param->max && *param->max < val)) + return -ERANGE; + + if (*lvalp > UINT_MAX) + return -EINVAL; + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +/** + * proc_douintvec_minmax - read a vector of unsigned ints with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. Negative + * strings are not allowed. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). There is a final sanity + * check for UINT_MAX to avoid having to support wrap around uses from + * userspace. + * + * Returns 0 on success. + */ +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct do_proc_douintvec_minmax_conv_param param = { + .min = (unsigned int *) table->extra1, + .max = (unsigned int *) table->extra2, + }; + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_minmax_conv, ¶m); +} + static void validate_coredump_safety(void) { #ifdef CONFIG_COREDUMP @@ -3066,6 +3125,12 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3108,6 +3173,7 @@ EXPORT_SYMBOL(proc_dointvec); EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); +EXPORT_SYMBOL_GPL(proc_douintvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); -- cgit v1.2.3