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 ...
This commit is contained in:
Linus Torvalds
@@ -54,6 +54,7 @@
|
||||
#include <linux/proc_ns.h>
|
||||
#include <linux/nsproxy.h>
|
||||
#include <linux/file.h>
|
||||
#include <linux/fs_parser.h>
|
||||
#include <linux/sched/cputime.h>
|
||||
#include <linux/psi.h>
|
||||
#include <net/sock.h>
|
||||
@@ -1772,26 +1773,37 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
|
||||
return len;
|
||||
}
|
||||
|
||||
static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
|
||||
enum cgroup2_param {
|
||||
Opt_nsdelegate,
|
||||
nr__cgroup2_params
|
||||
};
|
||||
|
||||
static const struct fs_parameter_spec cgroup2_param_specs[] = {
|
||||
fsparam_flag ("nsdelegate", Opt_nsdelegate),
|
||||
{}
|
||||
};
|
||||
|
||||
static const struct fs_parameter_description cgroup2_fs_parameters = {
|
||||
.name = "cgroup2",
|
||||
.specs = cgroup2_param_specs,
|
||||
};
|
||||
|
||||
static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param)
|
||||
{
|
||||
char *token;
|
||||
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
|
||||
struct fs_parse_result result;
|
||||
int opt;
|
||||
|
||||
*root_flags = 0;
|
||||
opt = fs_parse(fc, &cgroup2_fs_parameters, param, &result);
|
||||
if (opt < 0)
|
||||
return opt;
|
||||
|
||||
if (!data || *data == '\0')
|
||||
switch (opt) {
|
||||
case Opt_nsdelegate:
|
||||
ctx->flags |= CGRP_ROOT_NS_DELEGATE;
|
||||
return 0;
|
||||
|
||||
while ((token = strsep(&data, ",")) != NULL) {
|
||||
if (!strcmp(token, "nsdelegate")) {
|
||||
*root_flags |= CGRP_ROOT_NS_DELEGATE;
|
||||
continue;
|
||||
}
|
||||
|
||||
pr_err("cgroup2: unknown option \"%s\"\n", token);
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
return 0;
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
static void apply_cgroup_root_flags(unsigned int root_flags)
|
||||
@@ -1811,16 +1823,11 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
|
||||
static int cgroup_reconfigure(struct fs_context *fc)
|
||||
{
|
||||
unsigned int root_flags;
|
||||
int ret;
|
||||
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
|
||||
|
||||
ret = parse_cgroup_root_flags(data, &root_flags);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
apply_cgroup_root_flags(root_flags);
|
||||
apply_cgroup_root_flags(ctx->flags);
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -1908,8 +1915,9 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
|
||||
INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
|
||||
}
|
||||
|
||||
void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
|
||||
void init_cgroup_root(struct cgroup_fs_context *ctx)
|
||||
{
|
||||
struct cgroup_root *root = ctx->root;
|
||||
struct cgroup *cgrp = &root->cgrp;
|
||||
|
||||
INIT_LIST_HEAD(&root->root_list);
|
||||
@@ -1918,12 +1926,12 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
|
||||
init_cgroup_housekeeping(cgrp);
|
||||
idr_init(&root->cgroup_idr);
|
||||
|
||||
root->flags = opts->flags;
|
||||
if (opts->release_agent)
|
||||
strscpy(root->release_agent_path, opts->release_agent, PATH_MAX);
|
||||
if (opts->name)
|
||||
strscpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN);
|
||||
if (opts->cpuset_clone_children)
|
||||
root->flags = ctx->flags;
|
||||
if (ctx->release_agent)
|
||||
strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX);
|
||||
if (ctx->name)
|
||||
strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN);
|
||||
if (ctx->cpuset_clone_children)
|
||||
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
|
||||
}
|
||||
|
||||
@@ -2028,60 +2036,104 @@ out:
|
||||
return ret;
|
||||
}
|
||||
|
||||
struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
|
||||
struct cgroup_root *root, unsigned long magic,
|
||||
struct cgroup_namespace *ns)
|
||||
int cgroup_do_get_tree(struct fs_context *fc)
|
||||
{
|
||||
struct dentry *dentry;
|
||||
bool new_sb = false;
|
||||
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
|
||||
int ret;
|
||||
|
||||
dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
|
||||
ctx->kfc.root = ctx->root->kf_root;
|
||||
if (fc->fs_type == &cgroup2_fs_type)
|
||||
ctx->kfc.magic = CGROUP2_SUPER_MAGIC;
|
||||
else
|
||||
ctx->kfc.magic = CGROUP_SUPER_MAGIC;
|
||||
ret = kernfs_get_tree(fc);
|
||||
|
||||
/*
|
||||
* In non-init cgroup namespace, instead of root cgroup's dentry,
|
||||
* we return the dentry corresponding to the cgroupns->root_cgrp.
|
||||
*/
|
||||
if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
|
||||
if (!ret && ctx->ns != &init_cgroup_ns) {
|
||||
struct dentry *nsdentry;
|
||||
struct super_block *sb = dentry->d_sb;
|
||||
struct super_block *sb = fc->root->d_sb;
|
||||
struct cgroup *cgrp;
|
||||
|
||||
mutex_lock(&cgroup_mutex);
|
||||
spin_lock_irq(&css_set_lock);
|
||||
|
||||
cgrp = cset_cgroup_from_root(ns->root_cset, root);
|
||||
cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root);
|
||||
|
||||
spin_unlock_irq(&css_set_lock);
|
||||
mutex_unlock(&cgroup_mutex);
|
||||
|
||||
nsdentry = kernfs_node_dentry(cgrp->kn, sb);
|
||||
dput(dentry);
|
||||
if (IS_ERR(nsdentry))
|
||||
dput(fc->root);
|
||||
fc->root = nsdentry;
|
||||
if (IS_ERR(nsdentry)) {
|
||||
ret = PTR_ERR(nsdentry);
|
||||
deactivate_locked_super(sb);
|
||||
dentry = nsdentry;
|
||||
}
|
||||
}
|
||||
|
||||
if (!new_sb)
|
||||
cgroup_put(&root->cgrp);
|
||||
if (!ctx->kfc.new_sb_created)
|
||||
cgroup_put(&ctx->root->cgrp);
|
||||
|
||||
return dentry;
|
||||
return ret;
|
||||
}
|
||||
|
||||
static struct dentry *cgroup_mount(struct file_system_type *fs_type,
|
||||
int flags, const char *unused_dev_name,
|
||||
void *data)
|
||||
/*
|
||||
* Destroy a cgroup filesystem context.
|
||||
*/
|
||||
static void cgroup_fs_context_free(struct fs_context *fc)
|
||||
{
|
||||
struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
|
||||
struct dentry *dentry;
|
||||
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
|
||||
|
||||
kfree(ctx->name);
|
||||
kfree(ctx->release_agent);
|
||||
put_cgroup_ns(ctx->ns);
|
||||
kernfs_free_fs_context(fc);
|
||||
kfree(ctx);
|
||||
}
|
||||
|
||||
static int cgroup_get_tree(struct fs_context *fc)
|
||||
{
|
||||
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
|
||||
int ret;
|
||||
|
||||
get_cgroup_ns(ns);
|
||||
cgrp_dfl_visible = true;
|
||||
cgroup_get_live(&cgrp_dfl_root.cgrp);
|
||||
ctx->root = &cgrp_dfl_root;
|
||||
|
||||
/* Check if the caller has permission to mount. */
|
||||
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
|
||||
put_cgroup_ns(ns);
|
||||
return ERR_PTR(-EPERM);
|
||||
}
|
||||
ret = cgroup_do_get_tree(fc);
|
||||
if (!ret)
|
||||
apply_cgroup_root_flags(ctx->flags);
|
||||
return ret;
|
||||
}
|
||||
|
||||
static const struct fs_context_operations cgroup_fs_context_ops = {
|
||||
.free = cgroup_fs_context_free,
|
||||
.parse_param = cgroup2_parse_param,
|
||||
.get_tree = cgroup_get_tree,
|
||||
.reconfigure = cgroup_reconfigure,
|
||||
};
|
||||
|
||||
static const struct fs_context_operations cgroup1_fs_context_ops = {
|
||||
.free = cgroup_fs_context_free,
|
||||
.parse_param = cgroup1_parse_param,
|
||||
.get_tree = cgroup1_get_tree,
|
||||
.reconfigure = cgroup1_reconfigure,
|
||||
};
|
||||
|
||||
/*
|
||||
* Initialise the cgroup filesystem creation/reconfiguration context. Notably,
|
||||
* we select the namespace we're going to use.
|
||||
*/
|
||||
static int cgroup_init_fs_context(struct fs_context *fc)
|
||||
{
|
||||
struct cgroup_fs_context *ctx;
|
||||
|
||||
ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL);
|
||||
if (!ctx)
|
||||
return -ENOMEM;
|
||||
|
||||
/*
|
||||
* The first time anyone tries to mount a cgroup, enable the list
|
||||
@@ -2090,29 +2142,18 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
|
||||
if (!use_task_css_set_links)
|
||||
cgroup_enable_task_cg_lists();
|
||||
|
||||
if (fs_type == &cgroup2_fs_type) {
|
||||
unsigned int root_flags;
|
||||
|
||||
ret = parse_cgroup_root_flags(data, &root_flags);
|
||||
if (ret) {
|
||||
put_cgroup_ns(ns);
|
||||
return ERR_PTR(ret);
|
||||
}
|
||||
|
||||
cgrp_dfl_visible = true;
|
||||
cgroup_get_live(&cgrp_dfl_root.cgrp);
|
||||
|
||||
dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
|
||||
CGROUP2_SUPER_MAGIC, ns);
|
||||
if (!IS_ERR(dentry))
|
||||
apply_cgroup_root_flags(root_flags);
|
||||
} else {
|
||||
dentry = cgroup1_mount(&cgroup_fs_type, flags, data,
|
||||
CGROUP_SUPER_MAGIC, ns);
|
||||
}
|
||||
|
||||
put_cgroup_ns(ns);
|
||||
return dentry;
|
||||
ctx->ns = current->nsproxy->cgroup_ns;
|
||||
get_cgroup_ns(ctx->ns);
|
||||
fc->fs_private = &ctx->kfc;
|
||||
if (fc->fs_type == &cgroup2_fs_type)
|
||||
fc->ops = &cgroup_fs_context_ops;
|
||||
else
|
||||
fc->ops = &cgroup1_fs_context_ops;
|
||||
if (fc->user_ns)
|
||||
put_user_ns(fc->user_ns);
|
||||
fc->user_ns = get_user_ns(ctx->ns->user_ns);
|
||||
fc->global = true;
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void cgroup_kill_sb(struct super_block *sb)
|
||||
@@ -2135,17 +2176,19 @@ static void cgroup_kill_sb(struct super_block *sb)
|
||||
}
|
||||
|
||||
struct file_system_type cgroup_fs_type = {
|
||||
.name = "cgroup",
|
||||
.mount = cgroup_mount,
|
||||
.kill_sb = cgroup_kill_sb,
|
||||
.fs_flags = FS_USERNS_MOUNT,
|
||||
.name = "cgroup",
|
||||
.init_fs_context = cgroup_init_fs_context,
|
||||
.parameters = &cgroup1_fs_parameters,
|
||||
.kill_sb = cgroup_kill_sb,
|
||||
.fs_flags = FS_USERNS_MOUNT,
|
||||
};
|
||||
|
||||
static struct file_system_type cgroup2_fs_type = {
|
||||
.name = "cgroup2",
|
||||
.mount = cgroup_mount,
|
||||
.kill_sb = cgroup_kill_sb,
|
||||
.fs_flags = FS_USERNS_MOUNT,
|
||||
.name = "cgroup2",
|
||||
.init_fs_context = cgroup_init_fs_context,
|
||||
.parameters = &cgroup2_fs_parameters,
|
||||
.kill_sb = cgroup_kill_sb,
|
||||
.fs_flags = FS_USERNS_MOUNT,
|
||||
};
|
||||
|
||||
int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
|
||||
@@ -5280,7 +5323,6 @@ int cgroup_rmdir(struct kernfs_node *kn)
|
||||
|
||||
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
|
||||
.show_options = cgroup_show_options,
|
||||
.remount_fs = cgroup_remount,
|
||||
.mkdir = cgroup_mkdir,
|
||||
.rmdir = cgroup_rmdir,
|
||||
.show_path = cgroup_show_path,
|
||||
@@ -5347,11 +5389,12 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
|
||||
*/
|
||||
int __init cgroup_init_early(void)
|
||||
{
|
||||
static struct cgroup_sb_opts __initdata opts;
|
||||
static struct cgroup_fs_context __initdata ctx;
|
||||
struct cgroup_subsys *ss;
|
||||
int i;
|
||||
|
||||
init_cgroup_root(&cgrp_dfl_root, &opts);
|
||||
ctx.root = &cgrp_dfl_root;
|
||||
init_cgroup_root(&ctx);
|
||||
cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
|
||||
|
||||
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
|
||||
|
||||
Reference in New Issue
Block a user