4 files changed, 210 insertions, 154 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5ab1849971b4..ddef482f1334 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -59,6 +59,7 @@
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/generic-radix-tree.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
 #include <linux/namei.h>
@@ -92,7 +93,6 @@
 #include <linux/sched/coredump.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/stat.h>
-#include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #include <trace/events/oom.h>
 #include "internal.h"
@@ -2142,11 +2142,12 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	struct task_struct *task;
 	struct mm_struct *mm;
 	unsigned long nr_files, pos, i;
-	struct flex_array *fa = NULL;
-	struct map_files_info info;
+	GENRADIX(struct map_files_info) fa;
 	struct map_files_info *p;
 	int ret;
 
+	genradix_init(&fa);
+
 	ret = -ENOENT;
 	task = get_proc_task(file_inode(file));
 	if (!task)
@@ -2178,35 +2179,22 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	 */
 
 	for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
-		if (vma->vm_file && ++pos > ctx->pos)
-			nr_files++;
-	}
+		if (!vma->vm_file)
+			continue;
+		if (++pos <= ctx->pos)
+			continue;
 
-	if (nr_files) {
-		fa = flex_array_alloc(sizeof(info), nr_files,
-					GFP_KERNEL);
-		if (!fa || flex_array_prealloc(fa, 0, nr_files,
-						GFP_KERNEL)) {
+		p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL);
+		if (!p) {
 			ret = -ENOMEM;
-			if (fa)
-				flex_array_free(fa);
 			up_read(&mm->mmap_sem);
 			mmput(mm);
 			goto out_put_task;
 		}
-		for (i = 0, vma = mm->mmap, pos = 2; vma;
-				vma = vma->vm_next) {
-			if (!vma->vm_file)
-				continue;
-			if (++pos <= ctx->pos)
-				continue;
 
-			info.start = vma->vm_start;
-			info.end = vma->vm_end;
-			info.mode = vma->vm_file->f_mode;
-			if (flex_array_put(fa, i++, &info, GFP_KERNEL))
-				BUG();
-		}
+		p->start = vma->vm_start;
+		p->end = vma->vm_end;
+		p->mode = vma->vm_file->f_mode;
 	}
 	up_read(&mm->mmap_sem);
 	mmput(mm);
@@ -2215,7 +2203,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		char buf[4 * sizeof(long) + 2];	/* max: %lx-%lx\0 */
 		unsigned int len;
 
-		p = flex_array_get(fa, i);
+		p = genradix_ptr(&fa, i);
 		len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end);
 		if (!proc_fill_cache(file, ctx,
 				      buf, len,
@@ -2225,12 +2213,11 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		ctx->pos++;
 	}
-	if (fa)
-		flex_array_free(fa);
 
 out_put_task:
 	put_task_struct(task);
 out:
+	genradix_free(&fa);
 	return ret;
 }
 
@@ -2459,11 +2446,10 @@ static struct dentry *proc_pident_instantiate(struct dentry *dentry,
 
 static struct dentry *proc_pident_lookup(struct inode *dir, 
 					 struct dentry *dentry,
-					 const struct pid_entry *ents,
-					 unsigned int nents)
+					 const struct pid_entry *p,
+					 const struct pid_entry *end)
 {
 	struct task_struct *task = get_proc_task(dir);
-	const struct pid_entry *p, *last;
 	struct dentry *res = ERR_PTR(-ENOENT);
 
 	if (!task)
@@ -2473,8 +2459,7 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 	 * Yes, it does not scale. And it should not. Don't add
 	 * new entries into /proc/<tgid>/ without very good reasons.
 	 */
-	last = &ents[nents];
-	for (p = ents; p < last; p++) {
+	for (; p < end; p++) {
 		if (p->len != dentry->d_name.len)
 			continue;
 		if (!memcmp(dentry->d_name.name, p->name, p->len)) {
@@ -2610,7 +2595,7 @@ static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \
 { \
 	return proc_pident_lookup(dir, dentry, \
 				  LSM##_attr_dir_stuff, \
-				  ARRAY_SIZE(LSM##_attr_dir_stuff)); \
+				  LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \
 } \
 \
 static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
@@ -2655,7 +2640,8 @@ static struct dentry *proc_attr_dir_lookup(struct inode *dir,
 				struct dentry *dentry, unsigned int flags)
 {
 	return proc_pident_lookup(dir, dentry,
-				  attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
+				  attr_dir_stuff,
+				  attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff));
 }
 
 static const struct inode_operations proc_attr_dir_inode_operations = {
@@ -3088,10 +3074,20 @@ static const struct file_operations proc_tgid_base_operations = {
 	.llseek		= generic_file_llseek,
 };
 
+struct pid *tgid_pidfd_to_pid(const struct file *file)
+{
+	if (!d_is_dir(file->f_path.dentry) ||
+	    (file->f_op != &proc_tgid_base_operations))
+		return ERR_PTR(-EBADF);
+
+	return proc_pid(file_inode(file));
+}
+
 static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	return proc_pident_lookup(dir, dentry,
-				  tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
+				  tgid_base_stuff,
+				  tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff));
 }
 
 static const struct inode_operations proc_tgid_base_inode_operations = {
@@ -3463,7 +3459,8 @@ static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
 static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	return proc_pident_lookup(dir, dentry,
-				  tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
+				  tid_base_stuff,
+				  tid_base_stuff + ARRAY_SIZE(tid_base_stuff));
 }
 
 static const struct file_operations proc_tid_base_operations = {
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index da649ccd6804..fc7e38def174 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
-#include <linux/magic.h>
 
 #include <linux/uaccess.h>
 
@@ -122,13 +121,12 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
-static const struct super_operations proc_sops = {
+const struct super_operations proc_sops = {
 	.alloc_inode	= proc_alloc_inode,
 	.destroy_inode	= proc_destroy_inode,
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= proc_evict_inode,
 	.statfs		= simple_statfs,
-	.remount_fs	= proc_remount,
 	.show_options	= proc_show_options,
 };
 
@@ -488,51 +486,3 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 	       pde_put(de);
 	return inode;
 }
-
-int proc_fill_super(struct super_block *s, void *data, int silent)
-{
-	struct pid_namespace *ns = get_pid_ns(s->s_fs_info);
-	struct inode *root_inode;
-	int ret;
-
-	if (!proc_parse_options(data, ns))
-		return -EINVAL;
-
-	/* User space would break if executables or devices appear on proc */
-	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
-	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
-	s->s_blocksize = 1024;
-	s->s_blocksize_bits = 10;
-	s->s_magic = PROC_SUPER_MAGIC;
-	s->s_op = &proc_sops;
-	s->s_time_gran = 1;
-
-	/*
-	 * procfs isn't actually a stacking filesystem; however, there is
-	 * too much magic going on inside it to permit stacking things on
-	 * top of it
-	 */
-	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
-	
-	/* procfs dentries and inodes don't require IO to create */
-	s->s_shrink.seeks = 0;
-
-	pde_get(&proc_root);
-	root_inode = proc_get_inode(s, &proc_root);
-	if (!root_inode) {
-		pr_err("proc_fill_super: get root inode failed\n");
-		return -ENOMEM;
-	}
-
-	s->s_root = d_make_root(root_inode);
-	if (!s->s_root) {
-		pr_err("proc_fill_super: allocate dentry failed\n");
-		return -ENOMEM;
-	}
-
-	ret = proc_setup_self(s);
-	if (ret) {
-		return ret;
-	}
-	return proc_setup_thread_self(s);
-}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index ea575375f210..d1671e97f7fe 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -207,13 +207,12 @@ struct pde_opener {
 	struct completion *c;
 } __randomize_layout;
 extern const struct inode_operations proc_link_inode_operations;
-
 extern const struct inode_operations proc_pid_link_inode_operations;
+extern const struct super_operations proc_sops;
 
 void proc_init_kmemcache(void);
 void set_proc_pid_nlink(void);
 extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
-extern int proc_fill_super(struct super_block *, void *data, int flags);
 extern void proc_entry_rundown(struct proc_dir_entry *);
 
 /*
@@ -271,10 +270,8 @@ static inline void proc_tty_init(void) {}
  * root.c
  */
 extern struct proc_dir_entry proc_root;
-extern int proc_parse_options(char *options, struct pid_namespace *pid);
 
 extern void proc_self_init(void);
-extern int proc_remount(struct super_block *, int *, char *);
 
 /*
  * task_[no]mmu.c
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 621e6ec322ca..8b145e7b9661 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -19,86 +19,178 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/user_namespace.h>
+#include <linux/fs_context.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
-#include <linux/parser.h>
+#include <linux/fs_parser.h>
 #include <linux/cred.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
 
 #include "internal.h"
 
-enum {
-	Opt_gid, Opt_hidepid, Opt_err,
+struct proc_fs_context {
+	struct pid_namespace	*pid_ns;
+	unsigned int		mask;
+	int			hidepid;
+	int			gid;
 };
 
-static const match_table_t tokens = {
-	{Opt_hidepid, "hidepid=%u"},
-	{Opt_gid, "gid=%u"},
-	{Opt_err, NULL},
+enum proc_param {
+	Opt_gid,
+	Opt_hidepid,
 };
 
-int proc_parse_options(char *options, struct pid_namespace *pid)
+static const struct fs_parameter_spec proc_param_specs[] = {
+	fsparam_u32("gid",	Opt_gid),
+	fsparam_u32("hidepid",	Opt_hidepid),
+	{}
+};
+
+static const struct fs_parameter_description proc_fs_parameters = {
+	.name		= "proc",
+	.specs		= proc_param_specs,
+};
+
+static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-	int option;
-
-	if (!options)
-		return 1;
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
-		if (!*p)
-			continue;
-
-		args[0].to = args[0].from = NULL;
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_gid:
-			if (match_int(&args[0], &option))
-				return 0;
-			pid->pid_gid = make_kgid(current_user_ns(), option);
-			break;
-		case Opt_hidepid:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < HIDEPID_OFF ||
-			    option > HIDEPID_INVISIBLE) {
-				pr_err("proc: hidepid value must be between 0 and 2.\n");
-				return 0;
-			}
-			pid->hide_pid = option;
-			break;
-		default:
-			pr_err("proc: unrecognized mount option \"%s\" "
-			       "or missing value\n", p);
-			return 0;
-		}
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, &proc_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_gid:
+		ctx->gid = result.uint_32;
+		break;
+
+	case Opt_hidepid:
+		ctx->hidepid = result.uint_32;
+		if (ctx->hidepid < HIDEPID_OFF ||
+		    ctx->hidepid > HIDEPID_INVISIBLE)
+			return invalf(fc, "proc: hidepid value must be between 0 and 2.\n");
+		break;
+
+	default:
+		return -EINVAL;
 	}
 
-	return 1;
+	ctx->mask |= 1 << opt;
+	return 0;
 }
 
-int proc_remount(struct super_block *sb, int *flags, char *data)
+static void proc_apply_options(struct super_block *s,
+			       struct fs_context *fc,
+			       struct pid_namespace *pid_ns,
+			       struct user_namespace *user_ns)
 {
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	if (ctx->mask & (1 << Opt_gid))
+		pid_ns->pid_gid = make_kgid(user_ns, ctx->gid);
+	if (ctx->mask & (1 << Opt_hidepid))
+		pid_ns->hide_pid = ctx->hidepid;
+}
+
+static int proc_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info);
+	struct inode *root_inode;
+	int ret;
+
+	proc_apply_options(s, fc, pid_ns, current_user_ns());
+
+	/* User space would break if executables or devices appear on proc */
+	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
+	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = PROC_SUPER_MAGIC;
+	s->s_op = &proc_sops;
+	s->s_time_gran = 1;
+
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+	
+	/* procfs dentries and inodes don't require IO to create */
+	s->s_shrink.seeks = 0;
+
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
+	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
+	}
+
+	ret = proc_setup_self(s);
+	if (ret) {
+		return ret;
+	}
+	return proc_setup_thread_self(s);
+}
+
+static int proc_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
 	struct pid_namespace *pid = sb->s_fs_info;
 
 	sync_filesystem(sb);
-	return !proc_parse_options(data, pid);
+
+	proc_apply_options(sb, fc, pid, current_user_ns());
+	return 0;
 }
 
-static struct dentry *proc_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int proc_get_tree(struct fs_context *fc)
 {
-	struct pid_namespace *ns;
+	struct proc_fs_context *ctx = fc->fs_private;
 
-	if (flags & SB_KERNMOUNT) {
-		ns = data;
-		data = NULL;
-	} else {
-		ns = task_active_pid_ns(current);
-	}
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	fc->s_fs_info = ctx->pid_ns;
+	return vfs_get_super(fc, vfs_get_keyed_super, proc_fill_super);
+}
 
-	return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
+static void proc_fs_context_free(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	if (ctx->pid_ns)
+		put_pid_ns(ctx->pid_ns);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations proc_fs_context_ops = {
+	.free		= proc_fs_context_free,
+	.parse_param	= proc_parse_param,
+	.get_tree	= proc_get_tree,
+	.reconfigure	= proc_reconfigure,
+};
+
+static int proc_init_fs_context(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	fc->fs_private = ctx;
+	fc->ops = &proc_fs_context_ops;
+	return 0;
 }
 
 static void proc_kill_sb(struct super_block *sb)
@@ -115,10 +207,11 @@ static void proc_kill_sb(struct super_block *sb)
 }
 
 static struct file_system_type proc_fs_type = {
-	.name		= "proc",
-	.mount		= proc_mount,
-	.kill_sb	= proc_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.name			= "proc",
+	.init_fs_context	= proc_init_fs_context,
+	.parameters		= &proc_fs_parameters,
+	.kill_sb		= proc_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT,
 };
 
 void __init proc_root_init(void)
@@ -156,7 +249,7 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr
 {
 	if (!proc_pid_lookup(dentry, flags))
 		return NULL;
-	
+
 	return proc_lookup(dir, dentry, flags);
 }
 
@@ -209,9 +302,28 @@ struct proc_dir_entry proc_root = {
 
 int pid_ns_prepare_proc(struct pid_namespace *ns)
 {
+	struct proc_fs_context *ctx;
+	struct fs_context *fc;
 	struct vfsmount *mnt;
 
-	mnt = kern_mount_data(&proc_fs_type, ns);
+	fc = fs_context_for_mount(&proc_fs_type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	if (fc->user_ns != ns->user_ns) {
+		put_user_ns(fc->user_ns);
+		fc->user_ns = get_user_ns(ns->user_ns);
+	}
+
+	ctx = fc->fs_private;
+	if (ctx->pid_ns != ns) {
+		put_pid_ns(ctx->pid_ns);
+		get_pid_ns(ns);
+		ctx->pid_ns = ns;
+	}
+
+	mnt = fc_mount(fc);
+	put_fs_context(fc);
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);