proc_sys_lookup can fail with ENOMEM instead of ENOENT when the
corresponding sysctl table is being unregistered. In our case we see
this upon opening /proc/sys/net/*/conf files while network interfaces
are being removed, which confuses our configuration daemon.
The problem was successfully reproduced and this fix tested on v4.9.122
and v4.20-rc6.
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Cc: [email protected]
Signed-off-by: Ivan Delalande <[email protected]>
---
fs/proc/proc_sysctl.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 89921a0d2ebb..834be5bc3d07 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -474,7 +474,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
if (unlikely(head->unregistering)) {
spin_unlock(&sysctl_lock);
iput(inode);
- inode = NULL;
+ inode = ERR_PTR(-ENOENT);
goto out;
}
ei->sysctl = head;
@@ -549,10 +549,11 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- if (!inode)
+ if (IS_ERR_OR_NULL(inode)) {
+ err = inode ? ERR_CAST(inode) : ERR_PTR(-ENOMEM);
goto out;
+ }
d_set_d_op(dentry, &proc_sys_dentry_operations);
err = d_splice_alias(inode, dentry);
@@ -685,7 +686,7 @@ static bool proc_sys_fill_cache(struct file *file,
if (d_in_lookup(child)) {
struct dentry *res;
inode = proc_sys_make_inode(dir->d_sb, head, table);
- if (!inode) {
+ if (IS_ERR_OR_NULL(inode)) {
d_lookup_done(child);
dput(child);
return false;
--
2.20.0
On Wed, Dec 12, 2018 at 05:57:43PM -0800, Ivan Delalande wrote:
> proc_sys_lookup can fail with ENOMEM instead of ENOENT when the
> corresponding sysctl table is being unregistered. In our case we see
> this upon opening /proc/sys/net/*/conf files while network interfaces
> are being removed, which confuses our configuration daemon.
>
> The problem was successfully reproduced and this fix tested on v4.9.122
> and v4.20-rc6.
>
> Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
> Cc: [email protected]
> Signed-off-by: Ivan Delalande <[email protected]>
> ---
> fs/proc/proc_sysctl.c | 9 +++++----
> 1 file changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index 89921a0d2ebb..834be5bc3d07 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -474,7 +474,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
> if (unlikely(head->unregistering)) {
> spin_unlock(&sysctl_lock);
> iput(inode);
> - inode = NULL;
> + inode = ERR_PTR(-ENOENT);
> goto out;
> }
> ei->sysctl = head;
> @@ -549,10 +549,11 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
> goto out;
> }
>
> - err = ERR_PTR(-ENOMEM);
> inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
> - if (!inode)
> + if (IS_ERR_OR_NULL(inode)) {
> + err = inode ? ERR_CAST(inode) : ERR_PTR(-ENOMEM);
*gags*
If you want to return specific errors, do just that and for pity sake,
do *NOT* invent such hybrids. "Pointer to object on success,
ERR_PTR(-E...) on failure, NULL means ERR_PTR(-ENOMEM)" is a bitch to
reason about and prone to breakage.
"Return NULL on error" and "return ERR_PTR() on error" do not mix.
Just make proc_sys_make_inode() return ERR_PTR(-ENOMEM) on allocation
failures and update the callers (as you have to, anyway).
IS_ERR_OR_NULL() is usually a sign of bad calling conventions and it
certainly is just that in this case.
Just do
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
in there, in addition to your return of ERR_PTR(-ENOENT), and lose those
IS_ERR_OR_NULL() things. Make those IS_ERR() and turn the assignment
to err into straight ERR_CAST(). All there is to it...
proc_sys_lookup can fail with ENOMEM instead of ENOENT when the
corresponding sysctl table is being unregistered. In our case we see
this upon opening /proc/sys/net/*/conf files while network interfaces
are being deleted, which confuses our configuration daemon.
The problem was successfully reproduced and this fix tested on v4.9.122
and v4.20-rc6.
v2: return ERR_PTRs in all cases when proc_sys_make_inode fails instead
of mixing them with NULL. Thanks Al Viro for the feedback.
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Cc: [email protected]
Signed-off-by: Ivan Delalande <[email protected]>
---
fs/proc/proc_sysctl.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 89921a0d2ebb..e9d4fc40d832 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -464,7 +464,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
inode = new_inode(sb);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOMEM);
inode->i_ino = get_next_ino();
@@ -474,7 +474,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
if (unlikely(head->unregistering)) {
spin_unlock(&sysctl_lock);
iput(inode);
- inode = NULL;
+ inode = ERR_PTR(-ENOENT);
goto out;
}
ei->sysctl = head;
@@ -549,10 +549,11 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- if (!inode)
+ if (IS_ERR(inode)) {
+ err = ERR_CAST(inode);
goto out;
+ }
d_set_d_op(dentry, &proc_sys_dentry_operations);
err = d_splice_alias(inode, dentry);
@@ -685,7 +686,7 @@ static bool proc_sys_fill_cache(struct file *file,
if (d_in_lookup(child)) {
struct dentry *res;
inode = proc_sys_make_inode(dir->d_sb, head, table);
- if (!inode) {
+ if (IS_ERR(inode)) {
d_lookup_done(child);
dput(child);
return false;
--
2.20.0
On Thu, Dec 13, 2018 at 03:20:52PM -0800, Ivan Delalande wrote:
> @@ -474,7 +474,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
> if (unlikely(head->unregistering)) {
> spin_unlock(&sysctl_lock);
> iput(inode);
> - inode = NULL;
> + inode = ERR_PTR(-ENOENT);
> goto out;
> }
Applied, with one modification: if you look at the target of that goto,
you'll see
out:
return inode;
so this place should be simply
spin_unlock(&sysctl_lock);
iput(inode);
return ERR_PTR(-ENOENT);
}
That way the label becomes unused and goes away.