On Thu, Mar 30, 2017 at 8:22 AM, Djalal Harouni <tixxdz@xxxxxxxxx> wrote:
> This patch adds support for 'unshare' mount option to have multiple
> separated procfs inside the same pid namespace. This allows to solve lot
> of problem for containers and their specific use cases.
It would be nice if we could make this work without 'unshare'. How about:
hidepid still sets pid_ns->hidepid. "this_mount_hidepid" (or whatever
you want to call it), if set, overrides pid_ns->hidepid.
--Andy
>
> Signed-off-by: Djalal Harouni <tixxdz@xxxxxxxxx>
> ---
> fs/proc/generic.c | 10 +++++++++
> fs/proc/inode.c | 3 +++
> fs/proc/root.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++--
> include/linux/proc_fs.h | 12 ++++++++++
> 4 files changed, 82 insertions(+), 2 deletions(-)
>
> diff --git a/fs/proc/generic.c b/fs/proc/generic.c
> index 7e5e419..7ae5377 100644
> --- a/fs/proc/generic.c
> +++ b/fs/proc/generic.c
> @@ -52,6 +52,11 @@ void proc_fs_set_pid_gid(struct proc_fs_info *fs_info, kgid_t gid)
> fs_info->pid_gid = gid;
> }
>
> +void proc_fs_set_unshare(struct proc_fs_info *fs_info, int version)
> +{
> + fs_info->version = version;
> +}
> +
> int proc_fs_get_hide_pid(struct proc_fs_info *fs_info)
> {
> /* For backward compatibility */
> @@ -70,6 +75,11 @@ kgid_t proc_fs_get_pid_gid(struct proc_fs_info *fs_info)
> return fs_info->pid_gid;
> }
>
> +int proc_fs_get_unshare(struct proc_fs_info *fs_info)
> +{
> + return fs_info->version;
> +}
> +
> static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
> {
> if (len < de->namelen)
> diff --git a/fs/proc/inode.c b/fs/proc/inode.c
> index ca47a0a..5f7557d 100644
> --- a/fs/proc/inode.c
> +++ b/fs/proc/inode.c
> @@ -111,6 +111,9 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
> if (pid->hide_pid != HIDEPID_OFF)
> seq_printf(seq, ",hidepid=%u", pid->hide_pid);
>
> + if (proc_fs_get_unshare(fs_info) == PROC_FS_V2)
> + seq_printf(seq, ",unshare");
> +
> return 0;
> }
>
> diff --git a/fs/proc/root.c b/fs/proc/root.c
> index 6a96c02..7a8f425 100644
> --- a/fs/proc/root.c
> +++ b/fs/proc/root.c
> @@ -27,15 +27,52 @@
> #include "internal.h"
>
> enum {
> - Opt_gid, Opt_hidepid, Opt_err,
> + Opt_gid, Opt_hidepid, Opt_unshare, Opt_err,
> };
>
> static const match_table_t tokens = {
> {Opt_hidepid, "hidepid=%u"},
> {Opt_gid, "gid=%u"},
> + {Opt_unshare, "unshare"},
> {Opt_err, NULL},
> };
>
> +/* We only parse 'unshare' option here */
> +int proc_parse_early_options(char *options, struct proc_fs_info *fs_info)
> +{
> + char *p, *opts, *orig;
> + substring_t args[MAX_OPT_ARGS];
> +
> + if (!options)
> + return 0;
> +
> + opts = kstrdup(options, GFP_KERNEL);
> + if (!opts)
> + return -ENOMEM;
> +
> + orig = opts;
> +
> + while ((p = strsep(&opts, ",")) != NULL) {
> + int token;
> +
> + if (!*p)
> + continue;
> +
> + token = match_token(p, tokens, args);
> + switch (token) {
> + case Opt_unshare:
> + pr_info("proc: mounting a new procfs instance ");
> + proc_fs_set_unshare(fs_info, PROC_FS_V2);
> + break;
> + default:
> + break;
> + }
> + }
> +
> + kfree(orig);
> + return 0;
> +}
> +
> int proc_parse_options(char *options, struct proc_fs_info *fs_info)
> {
> char *p;
> @@ -70,6 +107,8 @@ int proc_parse_options(char *options, struct proc_fs_info *fs_info)
> }
> proc_fs_set_hide_pid(fs_info, option);
> break;
> + case Opt_unshare:
> + break;
> default:
> pr_err("proc: unrecognized mount option \"%s\" "
> "or missing value\n", p);
> @@ -82,9 +121,19 @@ int proc_parse_options(char *options, struct proc_fs_info *fs_info)
>
> int proc_remount(struct super_block *sb, int *flags, char *data)
> {
> + int error, version;
> struct proc_fs_info *fs_info = proc_sb(sb);
>
> + version = proc_fs_get_unshare(fs_info);
> +
> sync_filesystem(sb);
> +
> + if (version == PROC_FS_V2) {
> + error = proc_parse_early_options(data, fs_info);
> + if (error < 0)
> + return error;
> + }
> +
> return !proc_parse_options(data, fs_info);
> }
>
> @@ -122,15 +171,21 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
> if (!fs_info)
> return ERR_PTR(-ENOMEM);
>
> + /* Set it as early as possible */
> + proc_fs_set_unshare(fs_info, PROC_FS_V1);
> +
> if (flags & MS_KERNMOUNT) {
> ns = data;
> data = NULL;
> } else {
> + error = proc_parse_early_options(data, fs_info);
> + if (error < 0)
> + goto error_fs_info;
> +
> ns = task_active_pid_ns(current);
> }
>
> fs_info->pid_ns = ns;
> - fs_info->version = PROC_FS_V1;
> fs_info->hide_pid = HIDEPID_OFF;
> fs_info->pid_gid = GLOBAL_ROOT_GID;
> refcount_set(&fs_info->users, 1);
> diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
> index c23299d..e3a78a5 100644
> --- a/include/linux/proc_fs.h
> +++ b/include/linux/proc_fs.h
> @@ -31,8 +31,11 @@ extern void proc_fs_set_hide_pid(struct proc_fs_info *fs_info, int hide_pid);
>
> extern void proc_fs_set_pid_gid(struct proc_fs_info *fs_info, kgid_t gid);
>
> +extern void proc_fs_set_unshare(struct proc_fs_info *fs_info, int version);
> +
> extern int proc_fs_get_hide_pid(struct proc_fs_info *fs_info);
> extern kgid_t proc_fs_get_pid_gid(struct proc_fs_info *fs_info);
> +extern int proc_fs_get_unshare(struct proc_fs_info *fs_info);
>
> extern void proc_root_init(void);
> extern void proc_flush_task(struct task_struct *);
> @@ -84,6 +87,10 @@ static inline void proc_fs_set_hide_pid(struct proc_fs_info *fs_info, int hide_p
> {
> }
>
> +static inline void proc_fs_set_unshare(struct proc_fs_info *fs_info, int version)
> +{
> +}
> +
> static inline void proc_fs_set_pid_gid(struct proc_info_fs *fs_info, kgid_t gid)
> {
> }
> @@ -98,6 +105,11 @@ extern kgid_t proc_fs_get_pid_gid(struct proc_fs_info *fs_info)
> return GLOBAL_ROOT_GID;
> }
>
> +static inline int proc_fs_get_unshare(struct proc_fs_info *fs_info)
> +{
> + return PROC_FS_V1;
> +}
> +
> extern inline struct proc_fs_info *proc_sb(struct super_block *sb) { return NULL;}
> static inline struct proc_dir_entry *proc_symlink(const char *name,
> struct proc_dir_entry *parent,const char *dest) { return NULL;}
> --
> 2.10.2
>
--
Andy Lutomirski
AMA Capital Management, LLC
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
