Merge branch 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs mount infrastructure updates from Al Viro:
 "The rest of core infrastructure; no new syscalls in that pile, but the
  old parts are switched to new infrastructure. At that point
  conversions of individual filesystems can happen independently; some
  are done here (afs, cgroup, procfs, etc.), there's also a large series
  outside of that pile dealing with NFS (quite a bit of option-parsing
  stuff is getting used there - it's one of the most convoluted
  filesystems in terms of mount-related logics), but NFS bits are the
  next cycle fodder.

  It got seriously simplified since the last cycle; documentation is
  probably the weakest bit at the moment - I considered dropping the
  commit introducing Documentation/filesystems/mount_api.txt (cutting
  the size increase by quarter ;-), but decided that it would be better
  to fix it up after -rc1 instead.

  That pile allows to do followup work in independent branches, which
  should make life much easier for the next cycle. fs/super.c size
  increase is unpleasant; there's a followup series that allows to
  shrink it considerably, but I decided to leave that until the next
  cycle"

* 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (41 commits)
  afs: Use fs_context to pass parameters over automount
  afs: Add fs_context support
  vfs: Add some logging to the core users of the fs_context log
  vfs: Implement logging through fs_context
  vfs: Provide documentation for new mount API
  vfs: Remove kern_mount_data()
  hugetlbfs: Convert to fs_context
  cpuset: Use fs_context
  kernfs, sysfs, cgroup, intel_rdt: Support fs_context
  cgroup: store a reference to cgroup_ns into cgroup_fs_context
  cgroup1_get_tree(): separate "get cgroup_root to use" into a separate helper
  cgroup_do_mount(): massage calling conventions
  cgroup: stash cgroup_root reference into cgroup_fs_context
  cgroup2: switch to option-by-option parsing
  cgroup1: switch to option-by-option parsing
  cgroup: take options parsing into ->parse_monolithic()
  cgroup: fold cgroup1_mount() into cgroup1_get_tree()
  cgroup: start switching to fs_context
  ipc: Convert mqueue fs to fs_context
  proc: Add fs_context support to procfs
  ...

1 files changed, 209 insertions, 185 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index f94a7229974e..c126b34fd4ff 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -13,9 +13,12 @@
 #include <linux/delayacct.h>
 #include <linux/pid_namespace.h>
 #include <linux/cgroupstats.h>
+#include <linux/fs_parser.h>
 
 #include <trace/events/cgroup.h>
 
+#define cg_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
+
 /*
  * pidlists linger the following amount before being destroyed.  The goal
  * is avoiding frequent destruction in the middle of consecutive read calls
@@ -906,172 +909,195 @@ static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_roo
 	return 0;
 }
 
-static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
-{
-	char *token, *o = data;
-	bool all_ss = false, one_ss = false;
-	u16 mask = U16_MAX;
-	struct cgroup_subsys *ss;
-	int nr_opts = 0;
-	int i;
-
-#ifdef CONFIG_CPUSETS
-	mask = ~((u16)1 << cpuset_cgrp_id);
-#endif
-
-	memset(opts, 0, sizeof(*opts));
+enum cgroup1_param {
+	Opt_all,
+	Opt_clone_children,
+	Opt_cpuset_v2_mode,
+	Opt_name,
+	Opt_none,
+	Opt_noprefix,
+	Opt_release_agent,
+	Opt_xattr,
+};
 
-	while ((token = strsep(&o, ",")) != NULL) {
-		nr_opts++;
+static const struct fs_parameter_spec cgroup1_param_specs[] = {
+	fsparam_flag  ("all",		Opt_all),
+	fsparam_flag  ("clone_children", Opt_clone_children),
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	fsparam_string("name",		Opt_name),
+	fsparam_flag  ("none",		Opt_none),
+	fsparam_flag  ("noprefix",	Opt_noprefix),
+	fsparam_string("release_agent",	Opt_release_agent),
+	fsparam_flag  ("xattr",		Opt_xattr),
+	{}
+};
 
-		if (!*token)
-			return -EINVAL;
-		if (!strcmp(token, "none")) {
-			/* Explicitly have no subsystems */
-			opts->none = true;
-			continue;
-		}
-		if (!strcmp(token, "all")) {
-			/* Mutually exclusive option 'all' + subsystem name */
-			if (one_ss)
-				return -EINVAL;
-			all_ss = true;
-			continue;
-		}
-		if (!strcmp(token, "noprefix")) {
-			opts->flags |= CGRP_ROOT_NOPREFIX;
-			continue;
-		}
-		if (!strcmp(token, "clone_children")) {
-			opts->cpuset_clone_children = true;
-			continue;
-		}
-		if (!strcmp(token, "cpuset_v2_mode")) {
-			opts->flags |= CGRP_ROOT_CPUSET_V2_MODE;
-			continue;
-		}
-		if (!strcmp(token, "xattr")) {
-			opts->flags |= CGRP_ROOT_XATTR;
-			continue;
-		}
-		if (!strncmp(token, "release_agent=", 14)) {
-			/* Specifying two release agents is forbidden */
-			if (opts->release_agent)
-				return -EINVAL;
-			opts->release_agent =
-				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
-			if (!opts->release_agent)
-				return -ENOMEM;
-			continue;
-		}
-		if (!strncmp(token, "name=", 5)) {
-			const char *name = token + 5;
-
-			/* blocked by boot param? */
-			if (cgroup_no_v1_named)
-				return -ENOENT;
-			/* Can't specify an empty name */
-			if (!strlen(name))
-				return -EINVAL;
-			/* Must match [\w.-]+ */
-			for (i = 0; i < strlen(name); i++) {
-				char c = name[i];
-				if (isalnum(c))
-					continue;
-				if ((c == '.') || (c == '-') || (c == '_'))
-					continue;
-				return -EINVAL;
-			}
-			/* Specifying two names is forbidden */
-			if (opts->name)
-				return -EINVAL;
-			opts->name = kstrndup(name,
-					      MAX_CGROUP_ROOT_NAMELEN - 1,
-					      GFP_KERNEL);
-			if (!opts->name)
-				return -ENOMEM;
+const struct fs_parameter_description cgroup1_fs_parameters = {
+	.name		= "cgroup1",
+	.specs		= cgroup1_param_specs,
+};
 
-			continue;
+int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct cgroup_subsys *ss;
+	struct fs_parse_result result;
+	int opt, i;
+
+	opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result);
+	if (opt == -ENOPARAM) {
+		if (strcmp(param->key, "source") == 0) {
+			fc->source = param->string;
+			param->string = NULL;
+			return 0;
 		}
-
 		for_each_subsys(ss, i) {
-			if (strcmp(token, ss->legacy_name))
+			if (strcmp(param->key, ss->legacy_name))
 				continue;
-			if (!cgroup_ssid_enabled(i))
+			ctx->subsys_mask |= (1 << i);
+			return 0;
+		}
+		return cg_invalf(fc, "cgroup1: Unknown subsys name '%s'", param->key);
+	}
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_none:
+		/* Explicitly have no subsystems */
+		ctx->none = true;
+		break;
+	case Opt_all:
+		ctx->all_ss = true;
+		break;
+	case Opt_noprefix:
+		ctx->flags |= CGRP_ROOT_NOPREFIX;
+		break;
+	case Opt_clone_children:
+		ctx->cpuset_clone_children = true;
+		break;
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		break;
+	case Opt_xattr:
+		ctx->flags |= CGRP_ROOT_XATTR;
+		break;
+	case Opt_release_agent:
+		/* Specifying two release agents is forbidden */
+		if (ctx->release_agent)
+			return cg_invalf(fc, "cgroup1: release_agent respecified");
+		ctx->release_agent = param->string;
+		param->string = NULL;
+		break;
+	case Opt_name:
+		/* blocked by boot param? */
+		if (cgroup_no_v1_named)
+			return -ENOENT;
+		/* Can't specify an empty name */
+		if (!param->size)
+			return cg_invalf(fc, "cgroup1: Empty name");
+		if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1)
+			return cg_invalf(fc, "cgroup1: Name too long");
+		/* Must match [\w.-]+ */
+		for (i = 0; i < param->size; i++) {
+			char c = param->string[i];
+			if (isalnum(c))
 				continue;
-			if (cgroup1_ssid_disabled(i))
+			if ((c == '.') || (c == '-') || (c == '_'))
 				continue;
-
-			/* Mutually exclusive option 'all' + subsystem name */
-			if (all_ss)
-				return -EINVAL;
-			opts->subsys_mask |= (1 << i);
-			one_ss = true;
-
-			break;
+			return cg_invalf(fc, "cgroup1: Invalid name");
 		}
-		if (i == CGROUP_SUBSYS_COUNT)
-			return -ENOENT;
+		/* Specifying two names is forbidden */
+		if (ctx->name)
+			return cg_invalf(fc, "cgroup1: name respecified");
+		ctx->name = param->string;
+		param->string = NULL;
+		break;
 	}
+	return 0;
+}
+
+static int check_cgroupfs_options(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	u16 mask = U16_MAX;
+	u16 enabled = 0;
+	struct cgroup_subsys *ss;
+	int i;
+
+#ifdef CONFIG_CPUSETS
+	mask = ~((u16)1 << cpuset_cgrp_id);
+#endif
+	for_each_subsys(ss, i)
+		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
+			enabled |= 1 << i;
+
+	ctx->subsys_mask &= enabled;
 
 	/*
-	 * If the 'all' option was specified select all the subsystems,
-	 * otherwise if 'none', 'name=' and a subsystem name options were
-	 * not specified, let's default to 'all'
+	 * In absense of 'none', 'name=' or subsystem name options,
+	 * let's default to 'all'.
 	 */
-	if (all_ss || (!one_ss && !opts->none && !opts->name))
-		for_each_subsys(ss, i)
-			if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
-				opts->subsys_mask |= (1 << i);
+	if (!ctx->subsys_mask && !ctx->none && !ctx->name)
+		ctx->all_ss = true;
+
+	if (ctx->all_ss) {
+		/* Mutually exclusive option 'all' + subsystem name */
+		if (ctx->subsys_mask)
+			return cg_invalf(fc, "cgroup1: subsys name conflicts with all");
+		/* 'all' => select all the subsystems */
+		ctx->subsys_mask = enabled;
+	}
 
 	/*
 	 * We either have to specify by name or by subsystems. (So all
 	 * empty hierarchies must have a name).
 	 */
-	if (!opts->subsys_mask && !opts->name)
-		return -EINVAL;
+	if (!ctx->subsys_mask && !ctx->name)
+		return cg_invalf(fc, "cgroup1: Need name or subsystem set");
 
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
 	 * the cpuset subsystem.
 	 */
-	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
-		return -EINVAL;
+	if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask))
+		return cg_invalf(fc, "cgroup1: noprefix used incorrectly");
 
 	/* Can't specify "none" and some subsystems */
-	if (opts->subsys_mask && opts->none)
-		return -EINVAL;
+	if (ctx->subsys_mask && ctx->none)
+		return cg_invalf(fc, "cgroup1: none used incorrectly");
 
 	return 0;
 }
 
-static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
+int cgroup1_reconfigure(struct fs_context *fc)
 {
-	int ret = 0;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb);
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
-	struct cgroup_sb_opts opts;
+	int ret = 0;
 	u16 added_mask, removed_mask;
 
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
 	/* See what subsystems are wanted */
-	ret = parse_cgroupfs_options(data, &opts);
+	ret = check_cgroupfs_options(fc);
 	if (ret)
 		goto out_unlock;
 
-	if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+	if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent)
 		pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n",
 			task_tgid_nr(current), current->comm);
 
-	added_mask = opts.subsys_mask & ~root->subsys_mask;
-	removed_mask = root->subsys_mask & ~opts.subsys_mask;
+	added_mask = ctx->subsys_mask & ~root->subsys_mask;
+	removed_mask = root->subsys_mask & ~ctx->subsys_mask;
 
 	/* Don't allow flags or name to change at remount */
-	if ((opts.flags ^ root->flags) ||
-	    (opts.name && strcmp(opts.name, root->name))) {
-		pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n",
-		       opts.flags, opts.name ?: "", root->flags, root->name);
+	if ((ctx->flags ^ root->flags) ||
+	    (ctx->name && strcmp(ctx->name, root->name))) {
+		cg_invalf(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"",
+		       ctx->flags, ctx->name ?: "", root->flags, root->name);
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -1088,17 +1114,15 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
 
 	WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask));
 
-	if (opts.release_agent) {
+	if (ctx->release_agent) {
 		spin_lock(&release_agent_path_lock);
-		strcpy(root->release_agent_path, opts.release_agent);
+		strcpy(root->release_agent_path, ctx->release_agent);
 		spin_unlock(&release_agent_path_lock);
 	}
 
 	trace_cgroup_remount(root);
 
  out_unlock:
-	kfree(opts.release_agent);
-	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
@@ -1106,28 +1130,30 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
 struct kernfs_syscall_ops cgroup1_kf_syscall_ops = {
 	.rename			= cgroup1_rename,
 	.show_options		= cgroup1_show_options,
-	.remount_fs		= cgroup1_remount,
 	.mkdir			= cgroup_mkdir,
 	.rmdir			= cgroup_rmdir,
 	.show_path		= cgroup_show_path,
 };
 
-struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
-			     void *data, unsigned long magic,
-			     struct cgroup_namespace *ns)
+/*
+ * The guts of cgroup1 mount - find or create cgroup_root to use.
+ * Called with cgroup_mutex held; returns 0 on success, -E... on
+ * error and positive - in case when the candidate is busy dying.
+ * On success it stashes a reference to cgroup_root into given
+ * cgroup_fs_context; that reference is *NOT* counting towards the
+ * cgroup_root refcount.
+ */
+static int cgroup1_root_to_use(struct fs_context *fc)
 {
-	struct cgroup_sb_opts opts;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 	struct cgroup_root *root;
 	struct cgroup_subsys *ss;
-	struct dentry *dentry;
 	int i, ret;
 
-	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
-
 	/* First find the desired set of subsystems */
-	ret = parse_cgroupfs_options(data, &opts);
+	ret = check_cgroupfs_options(fc);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/*
 	 * Destruction of cgroup root is asynchronous, so subsystems may
@@ -1137,16 +1163,12 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 	 * starting.  Testing ref liveliness is good enough.
 	 */
 	for_each_subsys(ss, i) {
-		if (!(opts.subsys_mask & (1 << i)) ||
+		if (!(ctx->subsys_mask & (1 << i)) ||
 		    ss->root == &cgrp_dfl_root)
 			continue;
 
-		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
-			mutex_unlock(&cgroup_mutex);
-			msleep(10);
-			ret = restart_syscall();
-			goto out_free;
-		}
+		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt))
+			return 1;	/* restart */
 		cgroup_put(&ss->root->cgrp);
 	}
 
@@ -1161,8 +1183,8 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		 * name matches but sybsys_mask doesn't, we should fail.
 		 * Remember whether name matched.
 		 */
-		if (opts.name) {
-			if (strcmp(opts.name, root->name))
+		if (ctx->name) {
+			if (strcmp(ctx->name, root->name))
 				continue;
 			name_match = true;
 		}
@@ -1171,19 +1193,18 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		 * If we asked for subsystems (or explicitly for no
 		 * subsystems) then they must match.
 		 */
-		if ((opts.subsys_mask || opts.none) &&
-		    (opts.subsys_mask != root->subsys_mask)) {
+		if ((ctx->subsys_mask || ctx->none) &&
+		    (ctx->subsys_mask != root->subsys_mask)) {
 			if (!name_match)
 				continue;
-			ret = -EBUSY;
-			goto out_unlock;
+			return -EBUSY;
 		}
 
-		if (root->flags ^ opts.flags)
+		if (root->flags ^ ctx->flags)
 			pr_warn("new mount options do not match the existing superblock, will be ignored\n");
 
-		ret = 0;
-		goto out_unlock;
+		ctx->root = root;
+		return 0;
 	}
 
 	/*
@@ -1191,55 +1212,58 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 	 * specification is allowed for already existing hierarchies but we
 	 * can't create new one without subsys specification.
 	 */
-	if (!opts.subsys_mask && !opts.none) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
+	if (!ctx->subsys_mask && !ctx->none)
+		return cg_invalf(fc, "cgroup1: No subsys list or none specified");
 
 	/* Hierarchies may only be created in the initial cgroup namespace. */
-	if (ns != &init_cgroup_ns) {
-		ret = -EPERM;
-		goto out_unlock;
-	}
+	if (ctx->ns != &init_cgroup_ns)
+		return -EPERM;
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
-	if (!root) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!root)
+		return -ENOMEM;
 
-	init_cgroup_root(root, &opts);
+	ctx->root = root;
+	init_cgroup_root(ctx);
 
-	ret = cgroup_setup_root(root, opts.subsys_mask);
+	ret = cgroup_setup_root(root, ctx->subsys_mask);
 	if (ret)
 		cgroup_free_root(root);
+	return ret;
+}
 
-out_unlock:
-	if (!ret && !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
-		mutex_unlock(&cgroup_mutex);
-		msleep(10);
-		ret = restart_syscall();
-		goto out_free;
-	}
-	mutex_unlock(&cgroup_mutex);
-out_free:
-	kfree(opts.release_agent);
-	kfree(opts.name);
+int cgroup1_get_tree(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	int ret;
 
-	if (ret)
-		return ERR_PTR(ret);
+	/* Check if the caller has permission to mount. */
+	if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
+
+	ret = cgroup1_root_to_use(fc);
+	if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt))
+		ret = 1;	/* restart */
 
-	dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
-				 CGROUP_SUPER_MAGIC, ns);
+	mutex_unlock(&cgroup_mutex);
 
-	if (!IS_ERR(dentry) && percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
-		struct super_block *sb = dentry->d_sb;
-		dput(dentry);
+	if (!ret)
+		ret = cgroup_do_get_tree(fc);
+
+	if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
+		struct super_block *sb = fc->root->d_sb;
+		dput(fc->root);
 		deactivate_locked_super(sb);
+		ret = 1;
+	}
+
+	if (unlikely(ret > 0)) {
 		msleep(10);
-		dentry = ERR_PTR(restart_syscall());
+		return restart_syscall();
 	}
-	return dentry;
+	return ret;
 }
 
 static int __init cgroup1_wq_init(void)