Re: [PATCH 6/6] sysctl: pass kernel pointers to ->proc_handler

From: Matthew Wilcox
Date: Fri Apr 17 2020 - 14:17:25 EST


On Fri, Apr 17, 2020 at 08:41:46AM +0200, Christoph Hellwig wrote:
> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index b6f5d459b087..d5c9a9bf4e90 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -539,13 +539,13 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
> return err;
> }
>
> -static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
> +static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
> size_t count, loff_t *ppos, int write)
> {
> struct inode *inode = file_inode(filp);
> struct ctl_table_header *head = grab_header(inode);
> struct ctl_table *table = PROC_I(inode)->sysctl_entry;
> - void *new_buf = NULL;
> + void *kbuf;
> ssize_t error;
>
> if (IS_ERR(head))
> @@ -564,27 +564,36 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
> if (!table->proc_handler)
> goto out;
>
> - error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
> - ppos, &new_buf);
> + if (write) {
> + kbuf = memdup_user_nul(ubuf, count);
> + if (IS_ERR(kbuf)) {
> + error = PTR_ERR(kbuf);
> + goto out;
> + }
> + } else {
> + error = -ENOMEM;
> + kbuf = kzalloc(count, GFP_KERNEL);
> + if (!kbuf)
> + goto out;
> + }
> +
> + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
> + ppos);
> if (error)
> - goto out;
> + goto out_free_buf;
>
> /* careful: calling conventions are nasty here */

I think this comment can go now ;-)

> - if (new_buf) {
> - mm_segment_t old_fs;
> -
> - old_fs = get_fs();
> - set_fs(KERNEL_DS);
> - error = table->proc_handler(table, write, (void __user *)new_buf,
> - &count, ppos);
> - set_fs(old_fs);
> - kfree(new_buf);
> - } else {
> - error = table->proc_handler(table, write, buf, &count, ppos);
> - }
> + error = table->proc_handler(table, write, kbuf, &count, ppos);
> + if (error)
> + goto out_free_buf;
> +
> + error = -EFAULT;
> + if (copy_to_user(ubuf, kbuf, count))
> + goto out_free_buf;

Can we skip this if !write? Indeed, don't we have to in case the user has
passed a pointer to a read-only memory page?