From: Michal Koutný mkoutny@suse.com
mainline inclusion from mainline-v5.12-rc1 commit da70862efe0065bada33d67a903270cdbbaf07d9 bugzilla: 186050 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4197
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
The functions cgroup_threads_write and cgroup_procs_write are almost identical. In order to reduce duplication, factor out the common code in similar fashion we already do for other threadgroup/task functions. No functional changes are intended.
Suggested-by: Hao Lee haolee.swjtu@gmail.com Signed-off-by: Michal Koutný mkoutny@suse.com Reviewed-by: Daniel Jordan daniel.m.jordan@oracle.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/cgroup/cgroup.c | 55 +++++++++++------------------------------- 1 file changed, 14 insertions(+), 41 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 353369a1bc6b..c76dbb03e887 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4835,8 +4835,8 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp, return ret; }
-static ssize_t cgroup_procs_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) +static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, + bool threadgroup) { struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; @@ -4847,7 +4847,7 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of, if (!dst_cgrp) return -ENODEV;
- task = cgroup_procs_write_start(buf, true, &locked); + task = cgroup_procs_write_start(buf, threadgroup, &locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; @@ -4857,19 +4857,26 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock);
+ /* process and thread migrations follow same delegation rule */ ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb, true); + of->file->f_path.dentry->d_sb, threadgroup); if (ret) goto out_finish;
- ret = cgroup_attach_task(dst_cgrp, task, true); + ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish: cgroup_procs_write_finish(task, locked); out_unlock: cgroup_kn_unlock(of->kn);
- return ret ?: nbytes; + return ret; +} + +static ssize_t cgroup_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, true) ?: nbytes; }
static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) @@ -4880,41 +4887,7 @@ static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct cgroup *src_cgrp, *dst_cgrp; - struct task_struct *task; - ssize_t ret; - bool locked; - - buf = strstrip(buf); - - dst_cgrp = cgroup_kn_lock_live(of->kn, false); - if (!dst_cgrp) - return -ENODEV; - - task = cgroup_procs_write_start(buf, false, &locked); - ret = PTR_ERR_OR_ZERO(task); - if (ret) - goto out_unlock; - - /* find the source cgroup */ - spin_lock_irq(&css_set_lock); - src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); - spin_unlock_irq(&css_set_lock); - - /* thread migrations follow the cgroup.procs delegation rule */ - ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb, false); - if (ret) - goto out_finish; - - ret = cgroup_attach_task(dst_cgrp, task, false); - -out_finish: - cgroup_procs_write_finish(task, locked); -out_unlock: - cgroup_kn_unlock(of->kn); - - return ret ?: nbytes; + return __cgroup_procs_write(of, buf, false) ?: nbytes; }
/* cgroup core interface files for the default hierarchy */
From: Hui Su sh_def@163.com
mainline inclusion from mainline-v5.11-rc2 commit 5a7b5f32c5aa628841502d19a813c633ff6ecbe4 bugzilla: 186050 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4197
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
we have supplied the inline function: of_cft() in cgroup.h.
So replace the direct use 'of->kn->priv' with inline func of_cft(), which is more readable.
Signed-off-by: Hui Su sh_def@163.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/cgroup/cgroup.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c76dbb03e887..f04097281669 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3763,7 +3763,7 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of,
static int cgroup_file_open(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of);
if (cft->open) return cft->open(of); @@ -3772,7 +3772,7 @@ static int cgroup_file_open(struct kernfs_open_file *of)
static void cgroup_file_release(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of);
if (cft->release) cft->release(of); @@ -3783,7 +3783,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, { struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *cgrp = of->kn->parent->priv; - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret;
@@ -3833,7 +3833,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of);
if (cft->poll) return cft->poll(of, pt);
From: Tejun Heo tj@kernel.org
mainline inclusion from mainline commit 1756d7994ad85c2479af6ae5a9750b92324685af bugzilla: 186050 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4197
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
cgroup process migration permission checks are performed at write time as whether a given operation is allowed or not is dependent on the content of the write - the PID. This currently uses current's credentials which is a potential security weakness as it may allow scenarios where a less privileged process tricks a more privileged one into writing into a fd that it created.
This patch makes both cgroup2 and cgroup1 process migration interfaces to use the credentials saved at the time of open (file->f_cred) instead of current's.
Reported-by: "Eric W. Biederman" ebiederm@xmission.com Suggested-by: Linus Torvalds torvalds@linuxfoundation.org Fixes: 187fe84067bd ("cgroup: require write perm on common ancestor when moving processes on the default hierarchy") Reviewed-by: Michal Koutný mkoutny@suse.com Signed-off-by: Tejun Heo tj@kernel.org Conflict: kernel/cgroup/cgroup-v1.c Signed-off-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/cgroup/cgroup-v1.c | 7 ++++--- kernel/cgroup/cgroup.c | 9 ++++++++- 2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 88b72815aa9d..2b0dc44e2447 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -503,10 +503,11 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, goto out_unlock;
/* - * Even if we're attaching all tasks in the thread group, we only - * need to check permissions on one of them. + * Even if we're attaching all tasks in the thread group, we only need + * to check permissions on one of them. Check permissions using the + * credentials from file open to protect against inherited fd attacks. */ - cred = current_cred(); + cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f04097281669..6e81fc9911ed 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4840,6 +4840,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, { struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; + const struct cred *saved_cred; ssize_t ret; bool locked;
@@ -4857,9 +4858,15 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock);
- /* process and thread migrations follow same delegation rule */ + /* + * Process and thread migrations follow same delegation rule. Check + * permissions using the credentials from file open to protect against + * inherited fd attacks. + */ + saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup); + revert_creds(saved_cred); if (ret) goto out_finish;
From: Tejun Heo tj@kernel.org
mainline inclusion from mainline commit 0d2b5955b36250a9428c832664f2079cbf723bec bugzilla: 186050 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4197
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
of->priv is currently used by each interface file implementation to store private information. This patch collects the current two private data usages into struct cgroup_file_ctx which is allocated and freed by the common path. This allows generic private data which applies to multiple files, which will be used to in the following patch.
Note that cgroup_procs iterator is now embedded as procs.iter in the new cgroup_file_ctx so that it doesn't need to be allocated and freed separately.
v2: union dropped from cgroup_file_ctx and the procs iterator is embedded in cgroup_file_ctx as suggested by Linus.
v3: Michal pointed out that cgroup1's procs pidlist uses of->priv too. Converted. Didn't change to embedded allocation as cgroup1 pidlists get stored for caching.
Signed-off-by: Tejun Heo tj@kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Reviewed-by: Michal Koutný mkoutny@suse.com Conflict: kernel/cgroup/cgroup.c Signed-off-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/cgroup/cgroup-internal.h | 17 +++++++++++ kernel/cgroup/cgroup-v1.c | 26 ++++++++-------- kernel/cgroup/cgroup.c | 53 +++++++++++++++++++++------------ 3 files changed, 65 insertions(+), 31 deletions(-)
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index bfbeabc17a9d..cf637bc4ab45 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -65,6 +65,23 @@ static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) return container_of(kfc, struct cgroup_fs_context, kfc); }
+struct cgroup_pidlist; + +struct cgroup_file_ctx { + struct { + void *trigger; + } psi; + + struct { + bool started; + struct css_task_iter iter; + } procs; + + struct { + struct cgroup_pidlist *pidlist; + } procs1; +}; + /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 2b0dc44e2447..1805c682ccc3 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -393,6 +393,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) * next pid to display, if any */ struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; @@ -402,25 +403,24 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) mutex_lock(&cgrp->pidlist_mutex);
/* - * !NULL @of->priv indicates that this isn't the first start() - * after open. If the matching pidlist is around, we can use that. - * Look for it. Note that @of->priv can't be used directly. It - * could already have been destroyed. + * !NULL @ctx->procs1.pidlist indicates that this isn't the first + * start() after open. If the matching pidlist is around, we can use + * that. Look for it. Note that @ctx->procs1.pidlist can't be used + * directly. It could already have been destroyed. */ - if (of->priv) - of->priv = cgroup_pidlist_find(cgrp, type); + if (ctx->procs1.pidlist) + ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type);
/* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ - if (!of->priv) { - ret = pidlist_array_load(cgrp, type, - (struct cgroup_pidlist **)&of->priv); + if (!ctx->procs1.pidlist) { + ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } - l = of->priv; + l = ctx->procs1.pidlist;
if (pid) { int end = l->length; @@ -448,7 +448,8 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist;
if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, @@ -459,7 +460,8 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v) static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6e81fc9911ed..ab489574e20a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3641,6 +3641,7 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { + struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; @@ -3659,7 +3660,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); }
- psi_trigger_replace(&of->priv, new); + psi_trigger_replace(&ctx->psi.trigger, new);
cgroup_put(cgrp);
@@ -3690,12 +3691,16 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { - return psi_trigger_poll(&of->priv, of->file, pt); + struct cgroup_file_ctx *ctx = of->priv; + + return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); }
static void cgroup_pressure_release(struct kernfs_open_file *of) { - psi_trigger_replace(&of->priv, NULL); + struct cgroup_file_ctx *ctx = of->priv; + + psi_trigger_replace(&ctx->psi.trigger, NULL); }
struct cftype cgroup_v1_psi_files[] = { @@ -3764,18 +3769,31 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx; + int ret;
- if (cft->open) - return cft->open(of); - return 0; + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + of->priv = ctx; + + if (!cft->open) + return 0; + + ret = cft->open(of); + if (ret) + kfree(ctx); + return ret; }
static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx = of->priv;
if (cft->release) cft->release(of); + kfree(ctx); }
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, @@ -4699,21 +4717,21 @@ void css_task_iter_end(struct css_task_iter *it)
static void cgroup_procs_release(struct kernfs_open_file *of) { - if (of->priv) { - css_task_iter_end(of->priv); - kfree(of->priv); - } + struct cgroup_file_ctx *ctx = of->priv; + + if (ctx->procs.started) + css_task_iter_end(&ctx->procs.iter); }
static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv;
if (pos) (*pos)++;
- return css_task_iter_next(it); + return css_task_iter_next(&ctx->procs.iter); }
static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, @@ -4721,21 +4739,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct css_task_iter *it = &ctx->procs.iter;
/* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ - if (!it) { + if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); - - it = kzalloc(sizeof(*it), GFP_KERNEL); - if (!it) - return ERR_PTR(-ENOMEM); - of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); + ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it);
From: Tejun Heo tj@kernel.org
mainline inclusion from mainline commit e57457641613fef0d147ede8bd6a3047df588b95 bugzilla: 186050 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2021-4197
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
cgroup process migration permission checks are performed at write time as whether a given operation is allowed or not is dependent on the content of the write - the PID. This currently uses current's cgroup namespace which is a potential security weakness as it may allow scenarios where a less privileged process tricks a more privileged one into writing into a fd that it created.
This patch makes cgroup remember the cgroup namespace at the time of open and uses it for migration permission checks instad of current's. Note that this only applies to cgroup2 as cgroup1 doesn't have namespace support.
This also fixes a use-after-free bug on cgroupns reported in
https://lore.kernel.org/r/00000000000048c15c05d0083397@google.com
Note that backporting this fix also requires the preceding patch.
Reported-by: "Eric W. Biederman" ebiederm@xmission.com Suggested-by: Linus Torvalds torvalds@linuxfoundation.org Cc: Michal Koutný mkoutny@suse.com Cc: Oleg Nesterov oleg@redhat.com Reviewed-by: Michal Koutný mkoutny@suse.com Reported-by: syzbot+50f5cf33a284ce738b62@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/00000000000048c15c05d0083397@google.com Fixes: 5136f6365ce3 ("cgroup: implement "nsdelegate" mount option") Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/cgroup/cgroup-internal.h | 2 ++ kernel/cgroup/cgroup.c | 28 +++++++++++++++++++--------- 2 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index cf637bc4ab45..6e36e854b512 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -68,6 +68,8 @@ static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) struct cgroup_pidlist;
struct cgroup_file_ctx { + struct cgroup_namespace *ns; + struct { void *trigger; } psi; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ab489574e20a..8ef51ddfb301 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3775,14 +3775,19 @@ static int cgroup_file_open(struct kernfs_open_file *of) ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); of->priv = ctx;
if (!cft->open) return 0;
ret = cft->open(of); - if (ret) + if (ret) { + put_cgroup_ns(ctx->ns); kfree(ctx); + } return ret; }
@@ -3793,13 +3798,14 @@ static void cgroup_file_release(struct kernfs_open_file *of)
if (cft->release) cft->release(of); + put_cgroup_ns(ctx->ns); kfree(ctx); }
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; @@ -3816,7 +3822,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && - ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp) + ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM;
if (cft->write) @@ -4801,9 +4807,9 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb) + struct super_block *sb, + struct cgroup_namespace *ns) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *com_cgrp = src_cgrp; int ret;
@@ -4832,11 +4838,12 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb, bool threadgroup) + struct super_block *sb, bool threadgroup, + struct cgroup_namespace *ns) { int ret = 0;
- ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb); + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret;
@@ -4853,6 +4860,7 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp, static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; @@ -4880,7 +4888,8 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb, threadgroup); + of->file->f_path.dentry->d_sb, + threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; @@ -6075,7 +6084,8 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) goto err;
ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, - !(kargs->flags & CLONE_THREAD)); + !(kargs->flags & CLONE_THREAD), + current->nsproxy->cgroup_ns); if (ret) goto err;
-
Zheng Zengkai