* [PATCH 5/5] cgroup: introduce cgroup namespaces
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA
In-Reply-To: <1405626731-12220-1-git-send-email-adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Introduce the ability to create new cgroup namespace. The newly created
cgroup namespace remembers the 'struct cgroup *root_cgrp' at the point
of creation of the cgroup namespace. The task that creates the new
cgroup namespace and all its future children will now be restricted only
to the cgroup hierarchy under this root_cgrp. In the first version,
setns() is not supported for cgroup namespaces.
The main purpose of cgroup namespace is to virtualize the contents
of /proc/self/cgroup file. Processes inside a cgroup namespace
are only able to see paths relative to their namespace root.
This allows container-tools (like libcontainer, lxc, lmctfy, etc.)
to create completely virtualized containers without leaking system
level cgroup hierarchy to the task.
Signed-off-by: Aditya Kali <adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
fs/proc/namespaces.c | 3 +
include/linux/cgroup.h | 18 +++++-
include/linux/cgroup_namespace.h | 62 +++++++++++++++++++
include/linux/nsproxy.h | 2 +
include/linux/proc_ns.h | 4 ++
init/Kconfig | 9 +++
kernel/Makefile | 1 +
kernel/cgroup.c | 32 ++++++++++
kernel/cgroup_namespace.c | 128 +++++++++++++++++++++++++++++++++++++++
kernel/fork.c | 2 +-
kernel/nsproxy.c | 19 +++++-
11 files changed, 276 insertions(+), 4 deletions(-)
create mode 100644 include/linux/cgroup_namespace.h
create mode 100644 kernel/cgroup_namespace.c
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 8902609..e04ed4b 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -32,6 +32,9 @@ static const struct proc_ns_operations *ns_entries[] = {
&userns_operations,
#endif
&mntns_operations,
+#ifdef CONFIG_CGROUP_NS
+ &cgroupns_operations,
+#endif
};
static const struct file_operations ns_file_operations = {
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4ea477f..d3c6070 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -22,6 +22,8 @@
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#include <linux/wait.h>
+#include <linux/nsproxy.h>
+#include <linux/types.h>
#ifdef CONFIG_CGROUPS
@@ -469,6 +471,13 @@ struct cftype {
#endif
};
+struct cgroup_namespace {
+ atomic_t count;
+ unsigned int proc_inum;
+ struct user_namespace *user_ns;
+ struct cgroup *root_cgrp;
+};
+
extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;
@@ -591,10 +600,17 @@ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
return kernfs_name(cgrp->kn, buf, buflen);
}
+static inline char * __must_check cgroup_path_ns(struct cgroup_namespace *ns,
+ struct cgroup *cgrp, char *buf,
+ size_t buflen)
+{
+ return kernfs_path_from_node(ns->root_cgrp->kn, cgrp->kn, buf, buflen);
+}
+
static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
size_t buflen)
{
- return kernfs_path(cgrp->kn, buf, buflen);
+ return cgroup_path_ns(current->nsproxy->cgroup_ns, cgrp, buf, buflen);
}
static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
diff --git a/include/linux/cgroup_namespace.h b/include/linux/cgroup_namespace.h
new file mode 100644
index 0000000..9f637fe
--- /dev/null
+++ b/include/linux/cgroup_namespace.h
@@ -0,0 +1,62 @@
+#ifndef _LINUX_CGROUP_NAMESPACE_H
+#define _LINUX_CGROUP_NAMESPACE_H
+
+#include <linux/nsproxy.h>
+#include <linux/cgroup.h>
+#include <linux/types.h>
+#include <linux/user_namespace.h>
+
+extern struct cgroup_namespace init_cgroup_ns;
+
+static inline struct cgroup *task_cgroupns_root(struct task_struct *tsk)
+{
+ return tsk->nsproxy->cgroup_ns->root_cgrp;
+}
+
+#ifdef CONFIG_CGROUP_NS
+
+extern void free_cgroup_ns(struct cgroup_namespace *ns);
+
+static inline struct cgroup_namespace *get_cgroup_ns(
+ struct cgroup_namespace *ns)
+{
+ if (ns)
+ atomic_inc(&ns->count);
+ return ns;
+}
+
+static inline void put_cgroup_ns(struct cgroup_namespace *ns)
+{
+ if (ns && atomic_dec_and_test(&ns->count))
+ free_cgroup_ns(ns);
+}
+
+extern struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+ struct user_namespace *user_ns,
+ struct cgroup_namespace *old_ns);
+
+#else /* CONFIG_CGROUP_NS */
+
+static inline struct cgroup_namespace *get_cgroup_ns(
+ struct cgroup_namespace *ns)
+{
+ return &init_cgroup_ns;
+}
+
+static inline void put_cgroup_ns(struct cgroup_namespace *ns)
+{
+}
+
+static inline struct cgroup_namespace *copy_cgroup_ns(
+ unsigned long flags,
+ struct user_namespace *user_ns,
+ struct cgroup_namespace *old_ns) {
+ if (flags & CLONE_NEWCGROUP)
+ return ERR_PTR(-EINVAL);
+
+ return old_ns;
+}
+
+#endif /* CONFIG_CGROUP_NS */
+
+#endif /* _LINUX_CGROUP_NAMESPACE_H */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index b4ec59d..44f388c 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -8,6 +8,7 @@ struct mnt_namespace;
struct uts_namespace;
struct ipc_namespace;
struct pid_namespace;
+struct cgroup_namespace;
struct fs_struct;
/*
@@ -33,6 +34,7 @@ struct nsproxy {
struct mnt_namespace *mnt_ns;
struct pid_namespace *pid_ns_for_children;
struct net *net_ns;
+ struct cgroup_namespace *cgroup_ns;
};
extern struct nsproxy init_nsproxy;
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 34a1e10..e56dd73 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -6,6 +6,8 @@
struct pid_namespace;
struct nsproxy;
+struct task_struct;
+struct inode;
struct proc_ns_operations {
const char *name;
@@ -27,6 +29,7 @@ extern const struct proc_ns_operations ipcns_operations;
extern const struct proc_ns_operations pidns_operations;
extern const struct proc_ns_operations userns_operations;
extern const struct proc_ns_operations mntns_operations;
+extern const struct proc_ns_operations cgroupns_operations;
/*
* We always define these enumerators
@@ -37,6 +40,7 @@ enum {
PROC_UTS_INIT_INO = 0xEFFFFFFEU,
PROC_USER_INIT_INO = 0xEFFFFFFDU,
PROC_PID_INIT_INO = 0xEFFFFFFCU,
+ PROC_CGROUP_INIT_INO = 0xEFFFFFFBU,
};
#ifdef CONFIG_PROC_FS
diff --git a/init/Kconfig b/init/Kconfig
index 9d76b99..2f43ec9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1101,6 +1101,15 @@ config DEBUG_BLK_CGROUP
Enable some debugging help. Currently it exports additional stat
files in a cgroup which can be useful for debugging.
+config CGROUP_NS
+ bool "CGroup Namespaces"
+ default n
+ help
+ This options enables CGroup Namespaces which can be used to isolate
+ cgroup paths. This feature is only useful when unified cgroup
+ hierarchy is in use (i.e. cgroups are mounted with sane_behavior
+ option).
+
endif # CGROUPS
config CHECKPOINT_RESTORE
diff --git a/kernel/Makefile b/kernel/Makefile
index f2a8b62..61c5791 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_CGROUPS) += cgroup.o
+obj-$(CONFIG_CGROUP_NS) += cgroup_namespace.o
obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
obj-$(CONFIG_CPUSETS) += cpuset.o
obj-$(CONFIG_UTS_NS) += utsname.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8552513..c04e971 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,6 +57,8 @@
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/kthread.h>
#include <linux/delay.h>
+#include <linux/proc_ns.h>
+#include <linux/cgroup_namespace.h>
#include <linux/atomic.h>
@@ -196,6 +198,15 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
+struct cgroup_namespace init_cgroup_ns = {
+ .count = {
+ .counter = 1,
+ },
+ .proc_inum = PROC_CGROUP_INIT_INO,
+ .user_ns = &init_user_ns,
+ .root_cgrp = &cgrp_dfl_root.cgrp,
+};
+
/* IDR wrappers which synchronize using cgroup_idr_lock */
static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
gfp_t gfp_mask)
@@ -2333,6 +2344,12 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
struct task_struct *task;
int ret;
+ /* Only allow changing cgroups accessible within task's cgroup
+ * namespace. i.e. 'dst_cgrp' should be a descendant of task's
+ * cgroupns->root_cgrp. */
+ if (!cgroup_is_descendant(dst_cgrp, task_cgroupns_root(leader)))
+ return -EPERM;
+
/* look up all src csets */
down_read(&css_set_rwsem);
rcu_read_lock();
@@ -4551,6 +4568,13 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
parent = cgroup_kn_lock_live(parent_kn);
if (!parent)
return -ENODEV;
+
+ /* Allow mkdir only within process's cgroup namespace root. */
+ if (!cgroup_is_descendant(parent, task_cgroupns_root(current))) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
root = parent->root;
/* allocate the cgroup and its ID, 0 is reserved for the root */
@@ -4819,6 +4843,14 @@ static int cgroup_rmdir(struct kernfs_node *kn)
cgrp = cgroup_kn_lock_live(kn);
if (!cgrp)
return 0;
+
+ /* Allow rmdir only within process's cgroup namespace root.
+ * The process can't delete its own root anyways. */
+ if (!cgroup_is_descendant(cgrp, task_cgroupns_root(current))) {
+ cgroup_kn_unlock(kn);
+ return -EPERM;
+ }
+
cgroup_get(cgrp); /* for @kn->priv clearing */
ret = cgroup_destroy_locked(cgrp);
diff --git a/kernel/cgroup_namespace.c b/kernel/cgroup_namespace.c
new file mode 100644
index 0000000..a2e6804
--- /dev/null
+++ b/kernel/cgroup_namespace.c
@@ -0,0 +1,128 @@
+
+#include <linux/cgroup.h>
+#include <linux/cgroup_namespace.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
+
+static struct cgroup_namespace *alloc_cgroup_ns(void)
+{
+ struct cgroup_namespace *new_ns;
+
+ new_ns = kmalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
+ if (new_ns)
+ atomic_set(&new_ns->count, 1);
+ return new_ns;
+}
+
+void free_cgroup_ns(struct cgroup_namespace *ns)
+{
+ cgroup_put(ns->root_cgrp);
+ put_user_ns(ns->user_ns);
+ proc_free_inum(ns->proc_inum);
+}
+EXPORT_SYMBOL(free_cgroup_ns);
+
+struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+ struct user_namespace *user_ns,
+ struct cgroup_namespace *old_ns)
+{
+ struct cgroup_namespace *new_ns = NULL;
+ struct cgroup *cgrp = NULL;
+ int err;
+
+ BUG_ON(!old_ns);
+
+ if (!(flags & CLONE_NEWCGROUP))
+ return get_cgroup_ns(old_ns);
+
+ /* Allow only sysadmin to create cgroup namespace. */
+ err = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto err_out;
+
+ /* Prevent cgroup changes for this task. */
+ threadgroup_lock(current);
+
+ cgrp = get_task_cgroup(current);
+
+ /* Creating new CGROUPNS is supported only when unified hierarchy is in
+ * use. */
+ err = -EINVAL;
+ if (!cgroup_on_dfl(cgrp))
+ goto err_out_unlock;
+
+ err = -ENOMEM;
+ new_ns = alloc_cgroup_ns();
+ if (!new_ns)
+ goto err_out_unlock;
+
+ err = proc_alloc_inum(&new_ns->proc_inum);
+ if (err)
+ goto err_out_unlock;
+
+ new_ns->user_ns = get_user_ns(user_ns);
+ new_ns->root_cgrp = cgrp;
+
+ threadgroup_unlock(current);
+
+ return new_ns;
+
+err_out_unlock:
+ threadgroup_unlock(current);
+err_out:
+ if (cgrp)
+ cgroup_put(cgrp);
+ kfree(new_ns);
+ return ERR_PTR(err);
+}
+
+static int cgroupns_install(struct nsproxy *nsproxy, void *ns)
+{
+ pr_info("setns not supported for cgroup namespace");
+ return -EINVAL;
+}
+
+static void *cgroupns_get(struct task_struct *task)
+{
+ struct cgroup_namespace *ns = NULL;
+ struct nsproxy *nsproxy;
+
+ rcu_read_lock();
+ nsproxy = task_nsproxy(task);
+ if (nsproxy) {
+ ns = nsproxy->cgroup_ns;
+ get_cgroup_ns(ns);
+ }
+ rcu_read_unlock();
+
+ return ns;
+}
+
+static void cgroupns_put(void *ns)
+{
+ put_cgroup_ns(ns);
+}
+
+static unsigned int cgroupns_inum(void *ns)
+{
+ struct cgroup_namespace *cgroup_ns = ns;
+
+ return cgroup_ns->proc_inum;
+}
+
+const struct proc_ns_operations cgroupns_operations = {
+ .name = "cgroup",
+ .type = CLONE_NEWCGROUP,
+ .get = cgroupns_get,
+ .put = cgroupns_put,
+ .install = cgroupns_install,
+ .inum = cgroupns_inum,
+};
+
+static __init int cgroup_namespaces_init(void)
+{
+ return 0;
+}
+subsys_initcall(cgroup_namespaces_init);
diff --git a/kernel/fork.c b/kernel/fork.c
index d2799d1..95981a1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1747,7 +1747,7 @@ static int check_unshare_flags(unsigned long unshare_flags)
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
- CLONE_NEWUSER|CLONE_NEWPID))
+ CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP))
return -EINVAL;
/*
* Not implemented, but pretend it works if there is nothing to
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 8e78110..e20298c 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -25,6 +25,7 @@
#include <linux/proc_ns.h>
#include <linux/file.h>
#include <linux/syscalls.h>
+#include <linux/cgroup_namespace.h>
static struct kmem_cache *nsproxy_cachep;
@@ -39,6 +40,7 @@ struct nsproxy init_nsproxy = {
#ifdef CONFIG_NET
.net_ns = &init_net,
#endif
+ .cgroup_ns = &init_cgroup_ns,
};
static inline struct nsproxy *create_nsproxy(void)
@@ -92,6 +94,13 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
goto out_pid;
}
+ new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
+ tsk->nsproxy->cgroup_ns);
+ if (IS_ERR(new_nsp->cgroup_ns)) {
+ err = PTR_ERR(new_nsp->cgroup_ns);
+ goto out_cgroup;
+ }
+
new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
@@ -101,6 +110,9 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
return new_nsp;
out_net:
+ if (new_nsp->cgroup_ns)
+ put_cgroup_ns(new_nsp->cgroup_ns);
+out_cgroup:
if (new_nsp->pid_ns_for_children)
put_pid_ns(new_nsp->pid_ns_for_children);
out_pid:
@@ -128,7 +140,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
struct nsproxy *new_ns;
if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
- CLONE_NEWPID | CLONE_NEWNET)))) {
+ CLONE_NEWPID | CLONE_NEWNET |
+ CLONE_NEWCGROUP)))) {
get_nsproxy(old_ns);
return 0;
}
@@ -165,6 +178,8 @@ void free_nsproxy(struct nsproxy *ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns_for_children)
put_pid_ns(ns->pid_ns_for_children);
+ if (ns->cgroup_ns)
+ put_cgroup_ns(ns->cgroup_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
@@ -180,7 +195,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
- CLONE_NEWNET | CLONE_NEWPID)))
+ CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP)))
return 0;
user_ns = new_cred ? new_cred->user_ns : current_user_ns();
--
2.0.0.526.g5318336
^ permalink raw reply related
* [PATCH 4/5] cgroup: export cgroup_get() and cgroup_put()
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA
In-Reply-To: <1405626731-12220-1-git-send-email-adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
move cgroup_get() and cgroup_put() into cgroup.h so that
they can be called from other places.
Signed-off-by: Aditya Kali <adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
include/linux/cgroup.h | 17 +++++++++++++++++
kernel/cgroup.c | 18 ------------------
2 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 707c302..4ea477f 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -530,6 +530,23 @@ static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
return cgrp->root == &cgrp_dfl_root;
}
+/* convenient tests for these bits */
+static inline bool cgroup_is_dead(const struct cgroup *cgrp)
+{
+ return !(cgrp->self.flags & CSS_ONLINE);
+}
+
+static inline void cgroup_get(struct cgroup *cgrp)
+{
+ WARN_ON_ONCE(cgroup_is_dead(cgrp));
+ css_get(&cgrp->self);
+}
+
+static inline void cgroup_put(struct cgroup *cgrp)
+{
+ css_put(&cgrp->self);
+}
+
/* no synchronization, the result can only be used as a hint */
static inline bool cgroup_has_tasks(struct cgroup *cgrp)
{
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1671345..8552513 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -185,7 +185,6 @@ static int need_forkexit_callback __read_mostly;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
-static void cgroup_put(struct cgroup *cgrp);
static int rebind_subsystems(struct cgroup_root *dst_root,
unsigned int ss_mask);
static int cgroup_destroy_locked(struct cgroup *cgrp);
@@ -286,12 +285,6 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
return cgroup_css(cgrp, ss);
}
-/* convenient tests for these bits */
-static inline bool cgroup_is_dead(const struct cgroup *cgrp)
-{
- return !(cgrp->self.flags & CSS_ONLINE);
-}
-
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
{
struct cgroup *cgrp = of->kn->parent->priv;
@@ -1029,17 +1022,6 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
return mode;
}
-static void cgroup_get(struct cgroup *cgrp)
-{
- WARN_ON_ONCE(cgroup_is_dead(cgrp));
- css_get(&cgrp->self);
-}
-
-static void cgroup_put(struct cgroup *cgrp)
-{
- css_put(&cgrp->self);
-}
-
/**
* cgroup_refresh_child_subsys_mask - update child_subsys_mask
* @cgrp: the target cgroup
--
2.0.0.526.g5318336
^ permalink raw reply related
* [PATCH 3/5] cgroup: add function to get task's cgroup on default hierarchy
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA
In-Reply-To: <1405626731-12220-1-git-send-email-adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
get_task_cgroup() returns the (reference counted) cgroup of the
given task on the default hierarchy.
Signed-off-by: Aditya Kali <adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
include/linux/cgroup.h | 1 +
kernel/cgroup.c | 25 +++++++++++++++++++++++++
2 files changed, 26 insertions(+)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b5223c5..707c302 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -591,6 +591,7 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
}
char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
+struct cgroup *get_task_cgroup(struct task_struct *task);
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1e94b71..1671345 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1937,6 +1937,31 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
+/*
+ * get_task_cgroup - returns the cgroup of the task in the default cgroup
+ * hierarchy.
+ *
+ * @task: target task
+ * This function returns the @task's cgroup on the default cgroup hierarchy. The
+ * returned cgroup has its reference incremented (by calling cgroup_get()). So
+ * the caller must cgroup_put() the obtained reference once it is done with it.
+ */
+struct cgroup *get_task_cgroup(struct task_struct *task)
+{
+ struct cgroup *cgrp;
+
+ mutex_lock(&cgroup_mutex);
+ down_read(&css_set_rwsem);
+
+ cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
+ cgroup_get(cgrp);
+
+ up_read(&css_set_rwsem);
+ mutex_unlock(&cgroup_mutex);
+ return cgrp;
+}
+EXPORT_SYMBOL_GPL(get_task_cgroup);
+
/* used to track tasks and other necessary states during migration */
struct cgroup_taskset {
/* the src and dst cset list running through cset->mg_node */
--
2.0.0.526.g5318336
^ permalink raw reply related
* [PATCH 2/5] sched: new clone flag CLONE_NEWCGROUP for cgroup namespace
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA,
Aditya Kali
In-Reply-To: <1405626731-12220-1-git-send-email-adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
CLONE_NEWCGROUP will be used to create new cgroup namespace.
Signed-off-by: Aditya Kali <adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
include/uapi/linux/sched.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 34f9d73..2f90d00 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -21,8 +21,7 @@
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
-/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
- and is now available for re-use. */
+#define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */
#define CLONE_NEWUTS 0x04000000 /* New utsname group? */
#define CLONE_NEWIPC 0x08000000 /* New ipcs */
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
--
2.0.0.526.g5318336
^ permalink raw reply related
* [PATCH 1/5] kernfs: Add API to get generate relative kernfs path
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA
In-Reply-To: <1405626731-12220-1-git-send-email-adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
The new function kernfs_path_from_node() generates and returns
kernfs path of a given kernfs_node relative to a given parent
kernfs_node.
Signed-off-by: Aditya Kali <adityakali-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
fs/kernfs/dir.c | 51 ++++++++++++++++++++++++++++++++++++++++----------
include/linux/kernfs.h | 3 +++
2 files changed, 44 insertions(+), 10 deletions(-)
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a693f5b..2224f08 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -44,14 +44,22 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
}
-static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
- size_t buflen)
+static char * __must_check kernfs_path_from_node_locked(
+ struct kernfs_node *kn_root,
+ struct kernfs_node *kn,
+ char *buf,
+ size_t buflen)
{
char *p = buf + buflen;
int len;
*--p = '\0';
+ if (kn == kn_root) {
+ *--p = '/';
+ return p;
+ }
+
do {
len = strlen(kn->name);
if (p - buf < len + 1) {
@@ -63,6 +71,8 @@ static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
memcpy(p, kn->name, len);
*--p = '/';
kn = kn->parent;
+ if (kn == kn_root)
+ break;
} while (kn && kn->parent);
return p;
@@ -92,26 +102,47 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
}
/**
- * kernfs_path - build full path of a given node
+ * kernfs_path_from_node - build path of node @kn relative to @kn_root.
+ * @kn_root: parent kernfs_node relative to which we need to build the path
* @kn: kernfs_node of interest
- * @buf: buffer to copy @kn's name into
+ * @buf: buffer to copy @kn's path into
* @buflen: size of @buf
*
- * Builds and returns the full path of @kn in @buf of @buflen bytes. The
- * path is built from the end of @buf so the returned pointer usually
+ * Builds and returns @kn's path relative to @kn_root. @kn_root is expected to
+ * be parent of @kn at some level. If this is not true or if @kn_root is NULL,
+ * then full path of @kn is returned.
+ * The path is built from the end of @buf so the returned pointer usually
* doesn't match @buf. If @buf isn't long enough, @buf is nul terminated
* and %NULL is returned.
*/
-char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+char *kernfs_path_from_node(struct kernfs_node *kn_root, struct kernfs_node *kn,
+ char *buf, size_t buflen)
{
unsigned long flags;
char *p;
spin_lock_irqsave(&kernfs_rename_lock, flags);
- p = kernfs_path_locked(kn, buf, buflen);
+ p = kernfs_path_from_node_locked(kn_root, kn, buf, buflen);
spin_unlock_irqrestore(&kernfs_rename_lock, flags);
return p;
}
+EXPORT_SYMBOL_GPL(kernfs_path_from_node);
+
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes. The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+ return kernfs_path_from_node(NULL, kn, buf, buflen);
+}
EXPORT_SYMBOL_GPL(kernfs_path);
/**
@@ -145,8 +176,8 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
spin_lock_irqsave(&kernfs_rename_lock, flags);
- p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
- sizeof(kernfs_pr_cont_buf));
+ p = kernfs_path_from_node_locked(NULL, kn, kernfs_pr_cont_buf,
+ sizeof(kernfs_pr_cont_buf));
if (p)
pr_cont("%s", p);
else
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 20f4935..1627341 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -257,6 +257,9 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
}
int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
+char * __must_check kernfs_path_from_node(struct kernfs_node *root_kn,
+ struct kernfs_node *kn, char *buf,
+ size_t buflen);
char * __must_check kernfs_path(struct kernfs_node *kn, char *buf,
size_t buflen);
void pr_cont_kernfs_name(struct kernfs_node *kn);
--
2.0.0.526.g5318336
^ permalink raw reply related
* [PATCH 0/5] RFC: CGroup Namespaces
From: Aditya Kali @ 2014-07-17 19:52 UTC (permalink / raw)
To: tj-DgEjT+Ai2ygdnm+yROfE0A, lizefan-hv44wF8Li93QT0dZR+AlfA,
cgroups-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, mingo-H+wXaHxf7aLQT0dZR+AlfA
Cc: containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA
In-Reply-To: <adityakali-cgroupns>
Background
Cgroups and Namespaces are used together to create “virtual”
containers that isolates the host environment from the processes
running in container. But since cgroups themselves are not
“virtualized”, the task is always able to see global cgroups view
through cgroupfs mount and via /proc/self/cgroup file.
$ cat /proc/self/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1
This exposure of cgroup names to the processes running inside a
container results in some problems:
(1) The container names are typically host-container-management-agent
(systemd, docker/libcontainer, etc.) data and leaking its name (or
leaking the hierarchy) reveals too much information about the host
system.
(2) It makes the container migration across machines (CRIU) more
difficult as the container names need to be unique across the
machines in the migration domain.
(3) It makes it difficult to run container management tools (like
docker/libcontainer, lmctfy, etc.) within virtual containers
without adding dependency on some state/agent present outside the
container.
Note that the feature proposed here is completely different than the
“ns cgroup” feature which existed in the linux kernel until recently.
The ns cgroup also attempted to connect cgroups and namespaces by
creating a new cgroup every time a new namespace was created. It did
not solve any of the above mentioned problems and was later dropped
from the kernel.
Introducing CGroup Namespaces
With unified cgroup hierarchy
(Documentation/cgroups/unified-hierarchy.txt), the containers can now
have a much more coherent cgroup view and its easy to associate a
container with a single cgroup. This also allows us to virtualize the
cgroup view for tasks inside the container.
The new CGroup Namespace allows a process to “unshare” its cgroup
hierarchy starting from the cgroup its currently in.
For Ex:
$ cat /proc/self/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1
$ ls -l /proc/self/ns/cgroup
lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835]
$ ~/unshare -c # calls unshare(CLONE_NEWCGROUP) and exec’s /bin/bash
[ns]$ ls -l /proc/self/ns/cgroup
lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183]
# From within new cgroupns, process sees that its in the root cgroup
[ns]$ cat /proc/self/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/
# From global cgroupns:
$ cat /proc/<pid>/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1
The virtualization of /proc/self/cgroup file combined with restricting
the view of cgroup hierarchy by bind-mounting for the
$CGROUP_MOUNT/batchjobs/c_job_id1/ directory to
$CONTAINER_CHROOT/sys/fs/cgroup/) should provide a completely isolated
cgroup view inside the container.
In its current simplistic form, the cgroup namespaces provide
following behavior:
(1) The “root” cgroup for a cgroup namespace is the cgroup in which
the process calling unshare is running.
For ex. if a process in /batchjobs/c_job_id1 cgroup calls unshare,
cgroup /batchjobs/c_job_id1 becomes the cgroupns-root.
For the init_cgroup_ns, this is the real root (“/”) cgroup
(identified in code as cgrp_dfl_root.cgrp).
(2) The cgroupns-root cgroup does not change even if the namespace
creator process later moves to a different cgroup.
$ ~/unshare -c # unshare cgroupns in some cgroup
[ns]$ cat /proc/self/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/
[ns]$ mkdir sub_cgrp_1
[ns]$ echo 0 > sub_cgrp_1/cgroup.procs
[ns]$ cat /proc/self/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1
(3) Each process gets its CGROUPNS specific view of
/proc/<pid>/cgroup.
(a) Processes running inside the cgroup namespace will be able to see
cgroup paths (in /proc/self/cgroup) only inside their root cgroup
[ns]$ sleep 100000 & # From within unshared cgroupns
[1] 7353
[ns]$ echo 7353 > sub_cgrp_1/cgroup.procs
[ns]$ cat /proc/7353/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1
(b) From global cgroupns, the real cgroup path will be visible:
$ cat /proc/7353/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1/sub_cgrp_1
(c) From a sibling cgroupns, the real path will be visible:
[ns2]$ cat /proc/7353/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1/sub_cgrp_1
(In correct container setup though, it should not be possible to
access PIDs in another container in the first place. This can be
detected changed if desired.)
(4) Processes inside a cgroupns are not allowed to move out of the
cgroupns-root. This is true even if a privileged process in global
cgroupns tries to move the process out of its cgroupns-root.
# From global cgroupns
$ cat /proc/7353/cgroup
0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/c_job_id1/sub_cgrp_1
# cgroupns-root for 7353 is /batchjobs/c_job_id1
$ echo 7353 > batchjobs/c_job_id2/cgroup.procs
-bash: echo: write error: Operation not permitted
(5) setns() is not supported for cgroup namespace in the initial
version.
(6) When some thread from a multi-threaded process unshares its
cgroup-namespace, the new cgroupns gets applied to the entire
process (all the threads). This should be OK since
unified-hierarchy only allows process-level containerization. So
all the threads in the process will have the same cgroup. And both
- changing cgroups and unsharing namespaces - are protected under
threadgroup_lock(task).
(7) The cgroup namespace is alive as long as there is atleast 1
process inside it. When the last process exits, the cgroup
namespace is destroyed. The cgroupns-root and the actual cgroups
remain though.
Implementation
The current patch-set is based on top of Tejun's cgroup tree (for-next
branch). Its fairly non-intrusive and provides above mentioned
features.
Possible extensions of CGROUPNS:
(1) The Documentation/cgroups/unified-hierarchy.txt mentions use of
capabilities to restrict cgroups to administrative users. CGroup
namespaces could be of help here. With cgroup namespaces, it might
be possible to delegate administration of sub-cgroups under a
cgroupns-root to the cgroupns owner.
(2) Provide a cgroupns specific cgroupfs mount. i.e., the following
command when ran from inside a cgroupns should only mount the
hierarchy from cgroupns-root cgroup:
$ mount -t cgroup cgroup <cgroup-mountpoint>
# -o __DEVEL__sane_behavior should be implicit
This is similar to how procfs can be mounted for every PIDNS. This
may have some usecases.
---
fs/kernfs/dir.c | 51 +++++++++++++---
fs/proc/namespaces.c | 3 +
include/linux/cgroup.h | 36 ++++++++++-
include/linux/cgroup_namespace.h | 62 +++++++++++++++++++
include/linux/kernfs.h | 3 +
include/linux/nsproxy.h | 2 +
include/linux/proc_ns.h | 4 ++
include/uapi/linux/sched.h | 3 +-
init/Kconfig | 9 +++
kernel/Makefile | 1 +
kernel/cgroup.c | 75 +++++++++++++++++------
kernel/cgroup_namespace.c | 128 +++++++++++++++++++++++++++++++++++++++
kernel/fork.c | 2 +-
kernel/nsproxy.c | 19 +++++-
14 files changed, 364 insertions(+), 34 deletions(-)
create mode 100644 include/linux/cgroup_namespace.h
create mode 100644 kernel/cgroup_namespace.c
[PATCH 1/5] kernfs: Add API to get generate relative kernfs path
[PATCH 2/5] sched: new clone flag CLONE_NEWCGROUP for cgroup
[PATCH 3/5] cgroup: add function to get task's cgroup on default
[PATCH 4/5] cgroup: export cgroup_get() and cgroup_put()
[PATCH 5/5] cgroup: introduce cgroup namespaces
^ permalink raw reply
* [PATCH v12 11/11] seccomp: implement SECCOMP_FILTER_FLAG_TSYNC
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
Applying restrictive seccomp filter programs to large or diverse
codebases often requires handling threads which may be started early in
the process lifetime (e.g., by code that is linked in). While it is
possible to apply permissive programs prior to process start up, it is
difficult to further restrict the kernel ABI to those threads after that
point.
This change adds a new seccomp syscall flag to SECCOMP_SET_MODE_FILTER for
synchronizing thread group seccomp filters at filter installation time.
When calling seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
filter) an attempt will be made to synchronize all threads in current's
threadgroup to its new seccomp filter program. This is possible iff all
threads are using a filter that is an ancestor to the filter current is
attempting to synchronize to. NULL filters (where the task is running as
SECCOMP_MODE_NONE) are also treated as ancestors allowing threads to be
transitioned into SECCOMP_MODE_FILTER. If prctrl(PR_SET_NO_NEW_PRIVS,
...) has been set on the calling thread, no_new_privs will be set for
all synchronized threads too. On success, 0 is returned. On failure,
the pid of one of the failing threads will be returned and no filters
will have been applied.
The race conditions against another thread are:
- requesting TSYNC (already handled by sighand lock)
- performing a clone (already handled by sighand lock)
- changing its filter (already handled by sighand lock)
- calling exec (handled by cred_guard_mutex)
The clone case is assisted by the fact that new threads will have their
seccomp state duplicated from their parent before appearing on the tasklist.
Holding cred_guard_mutex means that seccomp filters cannot be assigned
while in the middle of another thread's exec (potentially bypassing
no_new_privs or similar). The call to de_thread() may kill threads waiting
for the mutex.
Changes across threads to the filter pointer includes a barrier.
Based on patches by Will Drewry.
Suggested-by: Julien Tinnes <jln@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
fs/exec.c | 2 +-
include/linux/seccomp.h | 2 +
include/uapi/linux/seccomp.h | 3 +
kernel/seccomp.c | 135 +++++++++++++++++++++++++++++++++++++++++-
4 files changed, 140 insertions(+), 2 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index 0f5c272410f6..ab1f1200ce5d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1216,7 +1216,7 @@ EXPORT_SYMBOL(install_exec_creds);
/*
* determine how safe it is to execute the proposed program
* - the caller must hold ->cred_guard_mutex to protect against
- * PTRACE_ATTACH
+ * PTRACE_ATTACH or seccomp thread-sync
*/
static void check_unsafe_exec(struct linux_binprm *bprm)
{
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 9ff98b4bfe2e..5d586a45a319 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,6 +3,8 @@
#include <uapi/linux/seccomp.h>
+#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC)
+
#ifdef CONFIG_SECCOMP
#include <linux/thread_info.h>
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index b258878ba754..0f238a43ff1e 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -14,6 +14,9 @@
#define SECCOMP_SET_MODE_STRICT 0
#define SECCOMP_SET_MODE_FILTER 1
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+
/*
* All BPF programs must return a 32-bit value.
* The bottom 16-bits are for optional return data.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9065d2c79c56..74f460179171 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -26,6 +26,7 @@
#ifdef CONFIG_SECCOMP_FILTER
#include <asm/syscall.h>
#include <linux/filter.h>
+#include <linux/pid.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/tracehook.h>
@@ -225,6 +226,114 @@ static inline void seccomp_assign_mode(struct task_struct *task,
}
#ifdef CONFIG_SECCOMP_FILTER
+/* Returns 1 if the parent is an ancestor of the child. */
+static int is_ancestor(struct seccomp_filter *parent,
+ struct seccomp_filter *child)
+{
+ /* NULL is the root ancestor. */
+ if (parent == NULL)
+ return 1;
+ for (; child; child = child->prev)
+ if (child == parent)
+ return 1;
+ return 0;
+}
+
+/**
+ * seccomp_can_sync_threads: checks if all threads can be synchronized
+ *
+ * Expects sighand and cred_guard_mutex locks to be held.
+ *
+ * Returns 0 on success, -ve on error, or the pid of a thread which was
+ * either not in the correct seccomp mode or it did not have an ancestral
+ * seccomp filter.
+ */
+static inline pid_t seccomp_can_sync_threads(void)
+{
+ struct task_struct *thread, *caller;
+
+ BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
+ /* Validate all threads being eligible for synchronization. */
+ caller = current;
+ for_each_thread(caller, thread) {
+ pid_t failed;
+
+ /* Skip current, since it is initiating the sync. */
+ if (thread == caller)
+ continue;
+
+ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
+ (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
+ is_ancestor(thread->seccomp.filter,
+ caller->seccomp.filter)))
+ continue;
+
+ /* Return the first thread that cannot be synchronized. */
+ failed = task_pid_vnr(thread);
+ /* If the pid cannot be resolved, then return -ESRCH */
+ if (unlikely(WARN_ON(failed == 0)))
+ failed = -ESRCH;
+ return failed;
+ }
+
+ return 0;
+}
+
+/**
+ * seccomp_sync_threads: sets all threads to use current's filter
+ *
+ * Expects sighand and cred_guard_mutex locks to be held, and for
+ * seccomp_can_sync_threads() to have returned success already
+ * without dropping the locks.
+ *
+ */
+static inline void seccomp_sync_threads(void)
+{
+ struct task_struct *thread, *caller;
+
+ BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
+ /* Synchronize all threads. */
+ caller = current;
+ for_each_thread(caller, thread) {
+ /* Skip current, since it needs no changes. */
+ if (thread == caller)
+ continue;
+
+ /* Get a task reference for the new leaf node. */
+ get_seccomp_filter(caller);
+ /*
+ * Drop the task reference to the shared ancestor since
+ * current's path will hold a reference. (This also
+ * allows a put before the assignment.)
+ */
+ put_seccomp_filter(thread);
+ smp_store_release(&thread->seccomp.filter,
+ caller->seccomp.filter);
+ /*
+ * Opt the other thread into seccomp if needed.
+ * As threads are considered to be trust-realm
+ * equivalent (see ptrace_may_access), it is safe to
+ * allow one thread to transition the other.
+ */
+ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) {
+ /*
+ * Don't let an unprivileged task work around
+ * the no_new_privs restriction by creating
+ * a thread that sets it up, enters seccomp,
+ * then dies.
+ */
+ if (task_no_new_privs(caller))
+ task_set_no_new_privs(thread);
+
+ seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+ }
+ }
+}
+
/**
* seccomp_prepare_filter: Prepares a seccomp filter for use.
* @fprog: BPF program to install
@@ -364,6 +473,15 @@ static long seccomp_attach_filter(unsigned int flags,
if (total_insns > MAX_INSNS_PER_PATH)
return -ENOMEM;
+ /* If thread sync has been requested, check that it is possible. */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
+ int ret;
+
+ ret = seccomp_can_sync_threads();
+ if (ret)
+ return ret;
+ }
+
/*
* If there is an existing filter, make it the prev and don't drop its
* task reference.
@@ -371,6 +489,10 @@ static long seccomp_attach_filter(unsigned int flags,
filter->prev = current->seccomp.filter;
current->seccomp.filter = filter;
+ /* Now that the new filter is in place, synchronize to all threads. */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+ seccomp_sync_threads();
+
return 0;
}
@@ -590,7 +712,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
long ret = -EINVAL;
/* Validate flags. */
- if (flags != 0)
+ if (flags & ~SECCOMP_FILTER_FLAG_MASK)
return -EINVAL;
/* Prepare the new filter before holding any locks. */
@@ -598,6 +720,14 @@ static long seccomp_set_mode_filter(unsigned int flags,
if (IS_ERR(prepared))
return PTR_ERR(prepared);
+ /*
+ * Make sure we cannot change seccomp or nnp state via TSYNC
+ * while another thread is in the middle of calling exec.
+ */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
+ mutex_lock_killable(¤t->signal->cred_guard_mutex))
+ goto out_free;
+
spin_lock_irq(¤t->sighand->siglock);
if (!seccomp_may_assign_mode(seccomp_mode))
@@ -612,6 +742,9 @@ static long seccomp_set_mode_filter(unsigned int flags,
seccomp_assign_mode(current, seccomp_mode);
out:
spin_unlock_irq(¤t->sighand->siglock);
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+out_free:
seccomp_filter_free(prepared);
return ret;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 10/11] seccomp: allow mode setting across threads
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
This changes the mode setting helper to allow threads to change the
seccomp mode from another thread. We must maintain barriers to keep
TIF_SECCOMP synchronized with the rest of the seccomp state.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
kernel/seccomp.c | 36 +++++++++++++++++++++++++-----------
1 file changed, 25 insertions(+), 11 deletions(-)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d5543e787e4e..9065d2c79c56 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -173,21 +173,24 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
*/
static u32 seccomp_run_filters(int syscall)
{
- struct seccomp_filter *f;
+ struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
struct seccomp_data sd;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
- if (WARN_ON(current->seccomp.filter == NULL))
+ if (unlikely(WARN_ON(f == NULL)))
return SECCOMP_RET_KILL;
+ /* Make sure cross-thread synced filter points somewhere sane. */
+ smp_read_barrier_depends();
+
populate_seccomp_data(&sd);
/*
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
- for (f = current->seccomp.filter; f; f = f->prev) {
+ for (; f; f = f->prev) {
u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
@@ -207,12 +210,18 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
return true;
}
-static inline void seccomp_assign_mode(unsigned long seccomp_mode)
+static inline void seccomp_assign_mode(struct task_struct *task,
+ unsigned long seccomp_mode)
{
- BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+ BUG_ON(!spin_is_locked(&task->sighand->siglock));
- current->seccomp.mode = seccomp_mode;
- set_tsk_thread_flag(current, TIF_SECCOMP);
+ task->seccomp.mode = seccomp_mode;
+ /*
+ * Make sure TIF_SECCOMP cannot be set before the mode (and
+ * filter) is set.
+ */
+ smp_mb__before_atomic();
+ set_tsk_thread_flag(task, TIF_SECCOMP);
}
#ifdef CONFIG_SECCOMP_FILTER
@@ -435,12 +444,17 @@ static int mode1_syscalls_32[] = {
int __secure_computing(int this_syscall)
{
- int mode = current->seccomp.mode;
int exit_sig = 0;
int *syscall;
u32 ret;
- switch (mode) {
+ /*
+ * Make sure that any changes to mode from another thread have
+ * been seen after TIF_SECCOMP was seen.
+ */
+ rmb();
+
+ switch (current->seccomp.mode) {
case SECCOMP_MODE_STRICT:
syscall = mode1_syscalls;
#ifdef CONFIG_COMPAT
@@ -545,7 +559,7 @@ static long seccomp_set_mode_strict(void)
#ifdef TIF_NOTSC
disable_TSC();
#endif
- seccomp_assign_mode(seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode);
ret = 0;
out:
@@ -595,7 +609,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
/* Do not free the successfully attached filter. */
prepared = NULL;
- seccomp_assign_mode(seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode);
out:
spin_unlock_irq(¤t->sighand->siglock);
seccomp_filter_free(prepared);
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 09/11] seccomp: introduce writer locking
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api-u79uwXL29TY76Z2rM5mHXA,
x86-DgEjT+Ai2ygdnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
linux-mips-6z/3iImG2C8G8FEW9MqTrA,
linux-arch-u79uwXL29TY76Z2rM5mHXA,
linux-security-module-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1405620518-18495-1-git-send-email-keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Normally, task_struct.seccomp.filter is only ever read or modified by
the task that owns it (current). This property aids in fast access
during system call filtering as read access is lockless.
Updating the pointer from another task, however, opens up race
conditions. To allow cross-thread filter pointer updates, writes to the
seccomp fields are now protected by the sighand spinlock (which is shared
by all threads in the thread group). Read access remains lockless because
pointer updates themselves are atomic. However, writes (or cloning)
often entail additional checking (like maximum instruction counts)
which require locking to perform safely.
In the case of cloning threads, the child is invisible to the system
until it enters the task list. To make sure a child can't be cloned from
a thread and left in a prior state, seccomp duplication is additionally
moved under the sighand lock. Then parent and child are certain have
the same seccomp state when they exit the lock.
Based on patches by Will Drewry and David Drysdale.
Signed-off-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Reviewed-by: Oleg Nesterov <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Reviewed-by: Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org>
---
include/linux/seccomp.h | 6 +++---
kernel/fork.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++-
kernel/seccomp.c | 16 +++++++++++++++-
3 files changed, 66 insertions(+), 5 deletions(-)
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 4054b0994071..9ff98b4bfe2e 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -14,11 +14,11 @@ struct seccomp_filter;
*
* @mode: indicates one of the valid values above for controlled
* system calls available to a process.
- * @filter: The metadata and ruleset for determining what system calls
- * are allowed for a task.
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ * accessed without locking during system call entry.
*
* @filter must only be accessed from the context of current as there
- * is no locking.
+ * is no read locking.
*/
struct seccomp {
int mode;
diff --git a/kernel/fork.c b/kernel/fork.c
index 6a13c46cd87d..ed4bc339c9dc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,6 +315,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
goto free_ti;
tsk->stack = ti;
+#ifdef CONFIG_SECCOMP
+ /*
+ * We must handle setting up seccomp filters once we're under
+ * the sighand lock in case orig has changed between now and
+ * then. Until then, filter must be NULL to avoid messing up
+ * the usage counts on the error path calling free_task.
+ */
+ tsk->seccomp.filter = NULL;
+#endif
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
@@ -1081,6 +1090,39 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
+static void copy_seccomp(struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+ /*
+ * Must be called with sighand->lock held, which is common to
+ * all threads in the group. Holding cred_guard_mutex is not
+ * needed because this new task is not yet running and cannot
+ * be racing exec.
+ */
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
+ /* Ref-count the new filter user, and assign it. */
+ get_seccomp_filter(current);
+ p->seccomp = current->seccomp;
+
+ /*
+ * Explicitly enable no_new_privs here in case it got set
+ * between the task_struct being duplicated and holding the
+ * sighand lock. The seccomp state and nnp must be in sync.
+ */
+ if (task_no_new_privs(current))
+ task_set_no_new_privs(p);
+
+ /*
+ * If the parent gained a seccomp mode after copying thread
+ * flags and between before we held the sighand lock, we have
+ * to manually enable the seccomp thread flag here.
+ */
+ if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
+ set_tsk_thread_flag(p, TIF_SECCOMP);
+#endif
+}
+
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
@@ -1196,7 +1238,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
ftrace_graph_init_task(p);
- get_seccomp_filter(p);
rt_mutex_init_task(p);
@@ -1437,6 +1478,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
spin_lock(¤t->sighand->siglock);
/*
+ * Copy seccomp details explicitly here, in case they were changed
+ * before holding sighand lock.
+ */
+ copy_seccomp(p);
+
+ /*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 58125160417c..d5543e787e4e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -199,6 +199,8 @@ static u32 seccomp_run_filters(int syscall)
static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
{
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
return false;
@@ -207,6 +209,8 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
static inline void seccomp_assign_mode(unsigned long seccomp_mode)
{
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
current->seccomp.mode = seccomp_mode;
set_tsk_thread_flag(current, TIF_SECCOMP);
}
@@ -332,6 +336,8 @@ out:
* @flags: flags to change filter behavior
* @filter: seccomp filter to add to the current process
*
+ * Caller must be holding current->sighand->siglock lock.
+ *
* Returns 0 on success, -ve on error.
*/
static long seccomp_attach_filter(unsigned int flags,
@@ -340,6 +346,8 @@ static long seccomp_attach_filter(unsigned int flags,
unsigned long total_insns;
struct seccomp_filter *walker;
+ BUG_ON(!spin_is_locked(¤t->sighand->siglock));
+
/* Validate resulting filter length. */
total_insns = filter->prog->len;
for (walker = current->seccomp.filter; walker; walker = walker->prev)
@@ -529,6 +537,8 @@ static long seccomp_set_mode_strict(void)
const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
long ret = -EINVAL;
+ spin_lock_irq(¤t->sighand->siglock);
+
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
@@ -539,6 +549,7 @@ static long seccomp_set_mode_strict(void)
ret = 0;
out:
+ spin_unlock_irq(¤t->sighand->siglock);
return ret;
}
@@ -566,13 +577,15 @@ static long seccomp_set_mode_filter(unsigned int flags,
/* Validate flags. */
if (flags != 0)
- goto out;
+ return -EINVAL;
/* Prepare the new filter before holding any locks. */
prepared = seccomp_prepare_user_filter(filter);
if (IS_ERR(prepared))
return PTR_ERR(prepared);
+ spin_lock_irq(¤t->sighand->siglock);
+
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
@@ -584,6 +597,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
seccomp_assign_mode(seccomp_mode);
out:
+ spin_unlock_irq(¤t->sighand->siglock);
seccomp_filter_free(prepared);
return ret;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 08/11] seccomp: split filter prep from check and apply
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
In preparation for adding seccomp locking, move filter creation away
from where it is checked and applied. This will allow for locking where
no memory allocation is happening. The validation, filter attachment,
and seccomp mode setting can all happen under the future locks.
For extreme defensiveness, I've added a BUG_ON check for the calculated
size of the buffer allocation in case BPF_MAXINSN ever changes, which
shouldn't ever happen. The compiler should actually optimize out this
check since the test above it makes it impossible.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
kernel/seccomp.c | 97 +++++++++++++++++++++++++++++++++++++-----------------
1 file changed, 67 insertions(+), 30 deletions(-)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d2596136b0d1..58125160417c 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -18,6 +18,7 @@
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
+#include <linux/slab.h>
#include <linux/syscalls.h>
/* #define SECCOMP_DEBUG 1 */
@@ -27,7 +28,6 @@
#include <linux/filter.h>
#include <linux/ptrace.h>
#include <linux/security.h>
-#include <linux/slab.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>
@@ -213,27 +213,23 @@ static inline void seccomp_assign_mode(unsigned long seccomp_mode)
#ifdef CONFIG_SECCOMP_FILTER
/**
- * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * seccomp_prepare_filter: Prepares a seccomp filter for use.
* @fprog: BPF program to install
*
- * Returns 0 on success or an errno on failure.
+ * Returns filter on success or an ERR_PTR on failure.
*/
-static long seccomp_attach_filter(struct sock_fprog *fprog)
+static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
struct seccomp_filter *filter;
- unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
- unsigned long total_insns = fprog->len;
+ unsigned long fp_size;
struct sock_filter *fp;
int new_len;
long ret;
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
- return -EINVAL;
-
- for (filter = current->seccomp.filter; filter; filter = filter->prev)
- total_insns += filter->prog->len + 4; /* include a 4 instr penalty */
- if (total_insns > MAX_INSNS_PER_PATH)
- return -ENOMEM;
+ return ERR_PTR(-EINVAL);
+ BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));
+ fp_size = fprog->len * sizeof(struct sock_filter);
/*
* Installing a seccomp filter requires that the task has
@@ -244,11 +240,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
if (!task_no_new_privs(current) &&
security_capable_noaudit(current_cred(), current_user_ns(),
CAP_SYS_ADMIN) != 0)
- return -EACCES;
+ return ERR_PTR(-EACCES);
fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
if (!fp)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
/* Copy the instructions from fprog. */
ret = -EFAULT;
@@ -292,13 +288,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
sk_filter_select_runtime(filter->prog);
- /*
- * If there is an existing filter, make it the prev and don't drop its
- * task reference.
- */
- filter->prev = current->seccomp.filter;
- current->seccomp.filter = filter;
- return 0;
+ return filter;
free_filter_prog:
kfree(filter->prog);
@@ -306,19 +296,20 @@ free_filter:
kfree(filter);
free_prog:
kfree(fp);
- return ret;
+ return ERR_PTR(ret);
}
/**
- * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog
* @user_filter: pointer to the user data containing a sock_fprog.
*
* Returns 0 on success and non-zero otherwise.
*/
-static long seccomp_attach_user_filter(const char __user *user_filter)
+static struct seccomp_filter *
+seccomp_prepare_user_filter(const char __user *user_filter)
{
struct sock_fprog fprog;
- long ret = -EFAULT;
+ struct seccomp_filter *filter = ERR_PTR(-EFAULT);
#ifdef CONFIG_COMPAT
if (is_compat_task()) {
@@ -331,9 +322,39 @@ static long seccomp_attach_user_filter(const char __user *user_filter)
#endif
if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
goto out;
- ret = seccomp_attach_filter(&fprog);
+ filter = seccomp_prepare_filter(&fprog);
out:
- return ret;
+ return filter;
+}
+
+/**
+ * seccomp_attach_filter: validate and attach filter
+ * @flags: flags to change filter behavior
+ * @filter: seccomp filter to add to the current process
+ *
+ * Returns 0 on success, -ve on error.
+ */
+static long seccomp_attach_filter(unsigned int flags,
+ struct seccomp_filter *filter)
+{
+ unsigned long total_insns;
+ struct seccomp_filter *walker;
+
+ /* Validate resulting filter length. */
+ total_insns = filter->prog->len;
+ for (walker = current->seccomp.filter; walker; walker = walker->prev)
+ total_insns += walker->prog->len + 4; /* 4 instr penalty */
+ if (total_insns > MAX_INSNS_PER_PATH)
+ return -ENOMEM;
+
+ /*
+ * If there is an existing filter, make it the prev and don't drop its
+ * task reference.
+ */
+ filter->prev = current->seccomp.filter;
+ current->seccomp.filter = filter;
+
+ return 0;
}
/* get_seccomp_filter - increments the reference count of the filter on @tsk */
@@ -346,6 +367,14 @@ void get_seccomp_filter(struct task_struct *tsk)
atomic_inc(&orig->usage);
}
+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+ if (filter) {
+ sk_filter_free(filter->prog);
+ kfree(filter);
+ }
+}
+
/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
void put_seccomp_filter(struct task_struct *tsk)
{
@@ -354,8 +383,7 @@ void put_seccomp_filter(struct task_struct *tsk)
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
orig = orig->prev;
- sk_filter_free(freeme->prog);
- kfree(freeme);
+ seccomp_filter_free(freeme);
}
}
@@ -533,21 +561,30 @@ static long seccomp_set_mode_filter(unsigned int flags,
const char __user *filter)
{
const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
+ struct seccomp_filter *prepared = NULL;
long ret = -EINVAL;
/* Validate flags. */
if (flags != 0)
goto out;
+ /* Prepare the new filter before holding any locks. */
+ prepared = seccomp_prepare_user_filter(filter);
+ if (IS_ERR(prepared))
+ return PTR_ERR(prepared);
+
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
- ret = seccomp_attach_user_filter(filter);
+ ret = seccomp_attach_filter(flags, prepared);
if (ret)
goto out;
+ /* Do not free the successfully attached filter. */
+ prepared = NULL;
seccomp_assign_mode(seccomp_mode);
out:
+ seccomp_filter_free(prepared);
return ret;
}
#else
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 07/11] sched: move no_new_privs into new atomic flags
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
Since seccomp transitions between threads requires updates to the
no_new_privs flag to be atomic, the flag must be part of an atomic flag
set. This moves the nnp flag into a separate task field, and introduces
accessors.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
fs/exec.c | 4 ++--
include/linux/sched.h | 18 +++++++++++++++---
kernel/seccomp.c | 2 +-
kernel/sys.c | 4 ++--
security/apparmor/domain.c | 4 ++--
5 files changed, 22 insertions(+), 10 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index a3d33fe592d6..0f5c272410f6 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1234,7 +1234,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
* This isn't strictly necessary, but it makes it harder for LSMs to
* mess up.
*/
- if (current->no_new_privs)
+ if (task_no_new_privs(current))
bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
t = p;
@@ -1272,7 +1272,7 @@ int prepare_binprm(struct linux_binprm *bprm)
bprm->cred->egid = current_egid();
if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
- !current->no_new_privs &&
+ !task_no_new_privs(current) &&
kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
/* Set-uid? */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0376b054a0d0..45cec6b70eaf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1307,13 +1307,12 @@ struct task_struct {
* execve */
unsigned in_iowait:1;
- /* task may not gain privileges */
- unsigned no_new_privs:1;
-
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+ unsigned long atomic_flags; /* Flags needing atomic access. */
+
pid_t pid;
pid_t tgid;
@@ -1967,6 +1966,19 @@ static inline void memalloc_noio_restore(unsigned int flags)
current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}
+/* Per-process atomic flags. */
+#define PFA_NO_NEW_PRIVS 0x00000001 /* May not gain new privileges. */
+
+static inline bool task_no_new_privs(struct task_struct *p)
+{
+ return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
+static inline void task_set_no_new_privs(struct task_struct *p)
+{
+ set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
/*
* task->jobctl flags
*/
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f0652578af75..d2596136b0d1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -241,7 +241,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
* This avoids scenarios where unprivileged tasks can affect the
* behavior of privileged children.
*/
- if (!current->no_new_privs &&
+ if (!task_no_new_privs(current) &&
security_capable_noaudit(current_cred(), current_user_ns(),
CAP_SYS_ADMIN) != 0)
return -EACCES;
diff --git a/kernel/sys.c b/kernel/sys.c
index 66a751ebf9d9..ce8129192a26 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1990,12 +1990,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
if (arg2 != 1 || arg3 || arg4 || arg5)
return -EINVAL;
- current->no_new_privs = 1;
+ task_set_no_new_privs(current);
break;
case PR_GET_NO_NEW_PRIVS:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- return current->no_new_privs ? 1 : 0;
+ return task_no_new_privs(current) ? 1 : 0;
case PR_GET_THP_DISABLE:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 452567d3a08e..d97cba3e3849 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -621,7 +621,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
* There is no exception for unconfined as change_hat is not
* available.
*/
- if (current->no_new_privs)
+ if (task_no_new_privs(current))
return -EPERM;
/* released below */
@@ -776,7 +776,7 @@ int aa_change_profile(const char *ns_name, const char *hname, bool onexec,
* no_new_privs is set because this aways results in a reduction
* of permissions.
*/
- if (current->no_new_privs && !unconfined(profile)) {
+ if (task_no_new_privs(current) && !unconfined(profile)) {
put_cred(cred);
return -EPERM;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 06/11] MIPS: add seccomp syscall
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, linux-mips, Will Drewry, Kees Cook, linux-api, x86,
Oleg Nesterov, Andy Lutomirski, linux-security-module,
Julien Tinnes, Michael Kerrisk (man-pages), James Morris,
David Drysdale, linux-arm-kernel
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
Wires up the new seccomp syscall.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
---
arch/mips/include/uapi/asm/unistd.h | 15 +++++++++------
arch/mips/kernel/scall32-o32.S | 1 +
arch/mips/kernel/scall64-64.S | 1 +
arch/mips/kernel/scall64-n32.S | 1 +
arch/mips/kernel/scall64-o32.S | 1 +
5 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 5805414777e0..9bc13eaf9d67 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -372,16 +372,17 @@
#define __NR_sched_setattr (__NR_Linux + 349)
#define __NR_sched_getattr (__NR_Linux + 350)
#define __NR_renameat2 (__NR_Linux + 351)
+#define __NR_seccomp (__NR_Linux + 352)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 351
+#define __NR_Linux_syscalls 352
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 351
+#define __NR_O32_Linux_syscalls 352
#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -701,16 +702,17 @@
#define __NR_sched_setattr (__NR_Linux + 309)
#define __NR_sched_getattr (__NR_Linux + 310)
#define __NR_renameat2 (__NR_Linux + 311)
+#define __NR_seccomp (__NR_Linux + 312)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 311
+#define __NR_Linux_syscalls 312
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 311
+#define __NR_64_Linux_syscalls 312
#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -1034,15 +1036,16 @@
#define __NR_sched_setattr (__NR_Linux + 313)
#define __NR_sched_getattr (__NR_Linux + 314)
#define __NR_renameat2 (__NR_Linux + 315)
+#define __NR_seccomp (__NR_Linux + 316)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 315
+#define __NR_Linux_syscalls 316
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 315
+#define __NR_N32_Linux_syscalls 316
#endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 3245474f19d5..ab02d14f1b5c 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -578,3 +578,4 @@ EXPORT(sys_call_table)
PTR sys_sched_setattr
PTR sys_sched_getattr /* 4350 */
PTR sys_renameat2
+ PTR sys_seccomp
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index be2fedd4ae33..010dccf128ec 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -431,4 +431,5 @@ EXPORT(sys_call_table)
PTR sys_sched_setattr
PTR sys_sched_getattr /* 5310 */
PTR sys_renameat2
+ PTR sys_seccomp
.size sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index c1dbcda4b816..c3b3b6525df5 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -424,4 +424,5 @@ EXPORT(sysn32_call_table)
PTR sys_sched_setattr
PTR sys_sched_getattr
PTR sys_renameat2 /* 6315 */
+ PTR sys_seccomp
.size sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f1343ccd7ed7..bb1550b1f501 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -557,4 +557,5 @@ EXPORT(sys32_call_table)
PTR sys_sched_setattr
PTR sys_sched_getattr /* 4350 */
PTR sys_renameat2
+ PTR sys_seccomp
.size sys32_call_table,.-sys32_call_table
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 05/11] ARM: add seccomp syscall
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
Wires up the new seccomp syscall.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
---
arch/arm/include/uapi/asm/unistd.h | 1 +
arch/arm/kernel/calls.S | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index ba94446c72d9..e21b4a069701 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -409,6 +409,7 @@
#define __NR_sched_setattr (__NR_SYSCALL_BASE+380)
#define __NR_sched_getattr (__NR_SYSCALL_BASE+381)
#define __NR_renameat2 (__NR_SYSCALL_BASE+382)
+#define __NR_seccomp (__NR_SYSCALL_BASE+383)
/*
* This may need to be greater than __NR_last_syscall+1 in order to
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 8f51bdcdacbb..bea85f97f363 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -392,6 +392,7 @@
/* 380 */ CALL(sys_sched_setattr)
CALL(sys_sched_getattr)
CALL(sys_renameat2)
+ CALL(sys_seccomp)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 04/11] seccomp: add "seccomp" syscall
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
This adds the new "seccomp" syscall with both an "operation" and "flags"
parameter for future expansion. The third argument is a pointer value,
used with the SECCOMP_SET_MODE_FILTER operation. Currently, flags must
be 0. This is functionally equivalent to prctl(PR_SET_SECCOMP, ...).
In addition to the TSYNC flag later in this patch series, there is a
non-zero chance that this syscall could be used for configuring a fixed
argument area for seccomp-tracer-aware processes to pass syscall arguments
in the future. Hence, the use of "seccomp" not simply "seccomp_add_filter"
for this syscall. Additionally, this syscall uses operation, flags,
and user pointer for arguments because strictly passing arguments via
a user pointer would mean seccomp itself would be unable to trivially
filter the seccomp syscall itself.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
arch/Kconfig | 1 +
arch/x86/syscalls/syscall_32.tbl | 1 +
arch/x86/syscalls/syscall_64.tbl | 1 +
include/linux/syscalls.h | 2 ++
include/uapi/asm-generic/unistd.h | 4 ++-
include/uapi/linux/seccomp.h | 4 +++
kernel/seccomp.c | 55 +++++++++++++++++++++++++++++++++----
kernel/sys_ni.c | 3 ++
8 files changed, 65 insertions(+), 6 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 97ff872c7acc..0eae9df35b88 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -321,6 +321,7 @@ config HAVE_ARCH_SECCOMP_FILTER
- secure_computing is called from a ptrace_event()-safe context
- secure_computing return value is checked and a return value of -1
results in the system call being skipped immediately.
+ - seccomp syscall wired up
config SECCOMP_FILTER
def_bool y
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index d6b867921612..7527eac24122 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -360,3 +360,4 @@
351 i386 sched_setattr sys_sched_setattr
352 i386 sched_getattr sys_sched_getattr
353 i386 renameat2 sys_renameat2
+354 i386 seccomp sys_seccomp
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index ec255a1646d2..16272a6c12b7 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -323,6 +323,7 @@
314 common sched_setattr sys_sched_setattr
315 common sched_getattr sys_sched_getattr
316 common renameat2 sys_renameat2
+317 common seccomp sys_seccomp
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b0881a0ed322..1713977ee26f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -866,4 +866,6 @@ asmlinkage long sys_process_vm_writev(pid_t pid,
asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
unsigned long idx1, unsigned long idx2);
asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
+asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs);
#endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 333640608087..65acbf0e2867 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -699,9 +699,11 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
#define __NR_renameat2 276
__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
#undef __NR_syscalls
-#define __NR_syscalls 277
+#define __NR_syscalls 278
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index ac2dc9f72973..b258878ba754 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -10,6 +10,10 @@
#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+
/*
* All BPF programs must return a 32-bit value.
* The bottom 16-bits are for optional return data.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 05cac2c2eca1..f0652578af75 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -18,6 +18,7 @@
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
+#include <linux/syscalls.h>
/* #define SECCOMP_DEBUG 1 */
@@ -314,7 +315,7 @@ free_prog:
*
* Returns 0 on success and non-zero otherwise.
*/
-static long seccomp_attach_user_filter(char __user *user_filter)
+static long seccomp_attach_user_filter(const char __user *user_filter)
{
struct sock_fprog fprog;
long ret = -EFAULT;
@@ -517,6 +518,7 @@ out:
#ifdef CONFIG_SECCOMP_FILTER
/**
* seccomp_set_mode_filter: internal function for setting seccomp filter
+ * @flags: flags to change filter behavior
* @filter: struct sock_fprog containing filter
*
* This function may be called repeatedly to install additional filters.
@@ -527,11 +529,16 @@ out:
*
* Returns 0 on success or -EINVAL on failure.
*/
-static long seccomp_set_mode_filter(char __user *filter)
+static long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
{
const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
long ret = -EINVAL;
+ /* Validate flags. */
+ if (flags != 0)
+ goto out;
+
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
@@ -544,12 +551,35 @@ out:
return ret;
}
#else
-static inline long seccomp_set_mode_filter(char __user *filter)
+static inline long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
{
return -EINVAL;
}
#endif
+/* Common entry point for both prctl and syscall. */
+static long do_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs)
+{
+ switch (op) {
+ case SECCOMP_SET_MODE_STRICT:
+ if (flags != 0 || uargs != NULL)
+ return -EINVAL;
+ return seccomp_set_mode_strict();
+ case SECCOMP_SET_MODE_FILTER:
+ return seccomp_set_mode_filter(flags, uargs);
+ default:
+ return -EINVAL;
+ }
+}
+
+SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
+ const char __user *, uargs)
+{
+ return do_seccomp(op, flags, uargs);
+}
+
/**
* prctl_set_seccomp: configures current->seccomp.mode
* @seccomp_mode: requested mode to use
@@ -559,12 +589,27 @@ static inline long seccomp_set_mode_filter(char __user *filter)
*/
long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
+ unsigned int op;
+ char __user *uargs;
+
switch (seccomp_mode) {
case SECCOMP_MODE_STRICT:
- return seccomp_set_mode_strict();
+ op = SECCOMP_SET_MODE_STRICT;
+ /*
+ * Setting strict mode through prctl always ignored filter,
+ * so make sure it is always NULL here to pass the internal
+ * check in do_seccomp().
+ */
+ uargs = NULL;
+ break;
case SECCOMP_MODE_FILTER:
- return seccomp_set_mode_filter(filter);
+ op = SECCOMP_SET_MODE_FILTER;
+ uargs = filter;
+ break;
default:
return -EINVAL;
}
+
+ /* prctl interface doesn't have flags, so they are always zero. */
+ return do_seccomp(op, 0, uargs);
}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 36441b51b5df..2904a2105914 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -213,3 +213,6 @@ cond_syscall(compat_sys_open_by_handle_at);
/* compare kernel pointers */
cond_syscall(sys_kcmp);
+
+/* operate on Secure Computing state */
+cond_syscall(sys_seccomp);
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 03/11] seccomp: split mode setting routines
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api-u79uwXL29TY76Z2rM5mHXA,
x86-DgEjT+Ai2ygdnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
linux-mips-6z/3iImG2C8G8FEW9MqTrA,
linux-arch-u79uwXL29TY76Z2rM5mHXA,
linux-security-module-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1405620518-18495-1-git-send-email-keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Separates the two mode setting paths to make things more readable with
fewer #ifdefs within function bodies.
Signed-off-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Reviewed-by: Oleg Nesterov <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Reviewed-by: Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org>
---
kernel/seccomp.c | 71 ++++++++++++++++++++++++++++++++++++------------------
1 file changed, 48 insertions(+), 23 deletions(-)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9df7def86c3b..05cac2c2eca1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -489,48 +489,66 @@ long prctl_get_seccomp(void)
}
/**
- * seccomp_set_mode: internal function for setting seccomp mode
- * @seccomp_mode: requested mode to use
- * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
- *
- * This function may be called repeatedly with a @seccomp_mode of
- * SECCOMP_MODE_FILTER to install additional filters. Every filter
- * successfully installed will be evaluated (in reverse order) for each system
- * call the task makes.
+ * seccomp_set_mode_strict: internal function for setting strict seccomp
*
* Once current->seccomp.mode is non-zero, it may not be changed.
*
* Returns 0 on success or -EINVAL on failure.
*/
-static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
+static long seccomp_set_mode_strict(void)
{
+ const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
long ret = -EINVAL;
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
- switch (seccomp_mode) {
- case SECCOMP_MODE_STRICT:
- ret = 0;
#ifdef TIF_NOTSC
- disable_TSC();
+ disable_TSC();
#endif
- break;
+ seccomp_assign_mode(seccomp_mode);
+ ret = 0;
+
+out:
+
+ return ret;
+}
+
#ifdef CONFIG_SECCOMP_FILTER
- case SECCOMP_MODE_FILTER:
- ret = seccomp_attach_user_filter(filter);
- if (ret)
- goto out;
- break;
-#endif
- default:
+/**
+ * seccomp_set_mode_filter: internal function for setting seccomp filter
+ * @filter: struct sock_fprog containing filter
+ *
+ * This function may be called repeatedly to install additional filters.
+ * Every filter successfully installed will be evaluated (in reverse order)
+ * for each system call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+static long seccomp_set_mode_filter(char __user *filter)
+{
+ const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
+ long ret = -EINVAL;
+
+ if (!seccomp_may_assign_mode(seccomp_mode))
+ goto out;
+
+ ret = seccomp_attach_user_filter(filter);
+ if (ret)
goto out;
- }
seccomp_assign_mode(seccomp_mode);
out:
return ret;
}
+#else
+static inline long seccomp_set_mode_filter(char __user *filter)
+{
+ return -EINVAL;
+}
+#endif
/**
* prctl_set_seccomp: configures current->seccomp.mode
@@ -541,5 +559,12 @@ out:
*/
long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
- return seccomp_set_mode(seccomp_mode, filter);
+ switch (seccomp_mode) {
+ case SECCOMP_MODE_STRICT:
+ return seccomp_set_mode_strict();
+ case SECCOMP_MODE_FILTER:
+ return seccomp_set_mode_filter(filter);
+ default:
+ return -EINVAL;
+ }
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 02/11] seccomp: extract check/assign mode helpers
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, linux-mips, Will Drewry, Kees Cook, linux-api, x86,
Oleg Nesterov, Andy Lutomirski, linux-security-module,
Julien Tinnes, Michael Kerrisk (man-pages), James Morris,
David Drysdale, linux-arm-kernel
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
To support splitting mode 1 from mode 2, extract the mode checking and
assignment logic into common functions.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
kernel/seccomp.c | 22 ++++++++++++++++++----
1 file changed, 18 insertions(+), 4 deletions(-)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index afb916c7e890..9df7def86c3b 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -194,7 +194,23 @@ static u32 seccomp_run_filters(int syscall)
}
return ret;
}
+#endif /* CONFIG_SECCOMP_FILTER */
+static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
+{
+ if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
+ return false;
+
+ return true;
+}
+
+static inline void seccomp_assign_mode(unsigned long seccomp_mode)
+{
+ current->seccomp.mode = seccomp_mode;
+ set_tsk_thread_flag(current, TIF_SECCOMP);
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
/**
* seccomp_attach_filter: Attaches a seccomp filter to current.
* @fprog: BPF program to install
@@ -490,8 +506,7 @@ static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
{
long ret = -EINVAL;
- if (current->seccomp.mode &&
- current->seccomp.mode != seccomp_mode)
+ if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
switch (seccomp_mode) {
@@ -512,8 +527,7 @@ static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
goto out;
}
- current->seccomp.mode = seccomp_mode;
- set_thread_flag(TIF_SECCOMP);
+ seccomp_assign_mode(seccomp_mode);
out:
return ret;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 01/11] seccomp: create internal mode-setting function
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
In-Reply-To: <1405620518-18495-1-git-send-email-keescook@chromium.org>
In preparation for having other callers of the seccomp mode setting
logic, split the prctl entry point away from the core logic that performs
seccomp mode setting.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
---
kernel/seccomp.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 301bbc24739c..afb916c7e890 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -473,7 +473,7 @@ long prctl_get_seccomp(void)
}
/**
- * prctl_set_seccomp: configures current->seccomp.mode
+ * seccomp_set_mode: internal function for setting seccomp mode
* @seccomp_mode: requested mode to use
* @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
*
@@ -486,7 +486,7 @@ long prctl_get_seccomp(void)
*
* Returns 0 on success or -EINVAL on failure.
*/
-long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+static long seccomp_set_mode(unsigned long seccomp_mode, char __user *filter)
{
long ret = -EINVAL;
@@ -517,3 +517,15 @@ long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
out:
return ret;
}
+
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+{
+ return seccomp_set_mode(seccomp_mode, filter);
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH v12 11/11] seccomp: add thread sync ability
From: Kees Cook @ 2014-07-17 18:08 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, James Morris, Oleg Nesterov, Andy Lutomirski,
David Drysdale, Michael Kerrisk (man-pages), Will Drewry,
Julien Tinnes, linux-api, x86, linux-arm-kernel, linux-mips,
linux-arch, linux-security-module
Twelfth time's the charm! :)
This adds the ability for threads to request seccomp filter
synchronization across their thread group (at filter attach time).
For example, for Chrome to make sure graphic driver threads are fully
confined after seccomp filters have been attached.
To support this, locking on seccomp changes via thread-group-shared
sighand lock is introduced, along with refactoring of no_new_privs. Races
with thread creation are handled via delayed duplication of the seccomp
task struct field and cred_guard_mutex.
This includes a new syscall (instead of adding a new prctl option),
as suggested by Andy Lutomirski and Michael Kerrisk.
Thanks!
-Kees
v12:
- fixed bug where initial filter wouldn't allow TSYNC flag (drysdale)
- optimized thread loops (drysdale)
v11:
- updated writer locking commit log for clarity (luto)
- clarified writer lock thread flag setting comment (luto)
- inverted SECCOMP_FILTER_FLAG_MASK (luto)
- renamed is_acestor parameter (luto)
- added BUG_ON to catch currently impossible integer overflow (luto)
v10:
- dropped pending-kill checks (oleg)
- tweaked memory barriers (oleg)
v9:
- rearranged/split patches to make things more reviewable
- added use of cred_guard_mutex to solve exec race (oleg, luto)
- added barriers for TIF_SECCOMP vs seccomp.mode race (oleg, luto)
- fixed missed copying of nnp state after v8 refactor (oleg)
v8:
- drop use of tasklist_lock, appears redundant against sighand (oleg)
- reduced use of smp_load_acquire to logical minimum (oleg)
- change nnp to a task struct held atomic flags field (oleg, luto)
- drop needless irqflags changes in fork.c for holding sighand lock (oleg)
- cleaned up use of thread for-each loop (oleg)
- rearranged patch order to keep syscall changes adjacent
- added example code to manpage (mtk)
v7:
- rebase on Linus's tree (merged with network bpf changes)
- wrote manpage text documenting API (follows this series)
v6:
- switch from seccomp-specific lock to thread-group lock to gain atomicity
- implement seccomp syscall across all architectures with seccomp filter
- clean up sparse warnings around locking
v5:
- move includes around (drysdale)
- drop set_nnp return value (luto)
- use smp_load_acquire/store_release (luto)
- merge nnp changes to seccomp always, fewer ifdef (luto)
v4:
- cleaned up locking further, as noticed by David Drysdale
v3:
- added SECCOMP_EXT_ACT_FILTER for new filter install options
v2:
- reworked to avoid clone races
^ permalink raw reply
* Re: [PATCH v11 11/11] seccomp: implement SECCOMP_FILTER_FLAG_TSYNC
From: Kees Cook @ 2014-07-17 17:52 UTC (permalink / raw)
To: David Drysdale
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Andy Lutomirski, Oleg Nesterov, James Morris,
Michael Kerrisk (man-pages), Alexei Starovoitov, Andrew Morton,
Daniel Borkmann, Will Drewry, Julien Tinnes, Linux API,
x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
Linux MIPS Mailing List, linux-arch, LSM List
In-Reply-To: <CAGXu5j+dFZdnnK8f-HRrUs2vLeyhWyHh_AY-OynDcp-Ye+dy7Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Thu, Jul 17, 2014 at 8:45 AM, Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org> wrote:
> On Thu, Jul 17, 2014 at 8:04 AM, David Drysdale <drysdale-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org> wrote:
>> On Wed, Jul 16, 2014 at 10:50 PM, Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org> wrote:
>>> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
>>> index 9065d2c79c56..2125b83ccfd4 100644
>>> +/**
>>> + * seccomp_can_sync_threads: checks if all threads can be synchronized
>>> + *
>>> + * Expects sighand and cred_guard_mutex locks to be held.
>>> + *
>>> + * Returns 0 on success, -ve on error, or the pid of a thread which was
>>> + * either not in the correct seccomp mode or it did not have an ancestral
>>> + * seccomp filter.
>>> + */
>>> +static inline pid_t seccomp_can_sync_threads(void)
>>> +{
>>> + struct task_struct *thread, *caller;
>>> +
>>> + BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
>>> + BUG_ON(!spin_is_locked(¤t->sighand->siglock));
>>> +
>>> + if (current->seccomp.mode != SECCOMP_MODE_FILTER)
>>> + return -EACCES;
>>
>> Quick question -- is it possible to apply the first filter and also synchronize
>> it across threads in the same operation? If so, does this arm also need to
>> cope with seccomp.mode being SECCOMP_MODE_DISABLED?
>>
>> [seccomp_set_mode_filter() looks to call this via seccomp_attach_filter()
>> before it does seccomp_assign_mode()]
>
> I don't entirely understand what you're asking. The threads gain the
> filter and the mode before the current thread may gain the mode (if
> it's the first time this has been called). Due to all the locks,
> though, this isn't a problem. Is there a situation you see where there
> might be a problem?
Just to follow up for posterity on lkml: the problem was that mode was
being set in "current" _after_ sync, so the mode check in can_sync
would fail if "current" was not yet in filter mode. (i.e. the first
attached filter could not have the TSYNC flag.) This check was
redundant with the attach_filter entry point checks, and protected
nothing, so it has been removed and a new test added to the seccomp
regression test suite. :)
I sent it as a new patch on top of v11, instead of respinning
everything as v12. If that's not preferred, I can send v12 with this
fix incorporated.
Thanks!
-Kees
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v11 11/11] seccomp: implement SECCOMP_FILTER_FLAG_TSYNC
From: Kees Cook @ 2014-07-17 15:45 UTC (permalink / raw)
To: David Drysdale
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Andy Lutomirski, Oleg Nesterov, James Morris,
Michael Kerrisk (man-pages), Alexei Starovoitov, Andrew Morton,
Daniel Borkmann, Will Drewry, Julien Tinnes, Linux API,
x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
Linux MIPS Mailing List, linux-arch, LSM List
In-Reply-To: <CAHse=S_32tmusk4ceY4U6GbNpX4PkX12iPPDZFVZ7qgv-RAooA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Thu, Jul 17, 2014 at 8:04 AM, David Drysdale <drysdale-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org> wrote:
> On Wed, Jul 16, 2014 at 10:50 PM, Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org> wrote:
>> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
>> index 9065d2c79c56..2125b83ccfd4 100644
>> +/**
>> + * seccomp_can_sync_threads: checks if all threads can be synchronized
>> + *
>> + * Expects sighand and cred_guard_mutex locks to be held.
>> + *
>> + * Returns 0 on success, -ve on error, or the pid of a thread which was
>> + * either not in the correct seccomp mode or it did not have an ancestral
>> + * seccomp filter.
>> + */
>> +static inline pid_t seccomp_can_sync_threads(void)
>> +{
>> + struct task_struct *thread, *caller;
>> +
>> + BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
>> + BUG_ON(!spin_is_locked(¤t->sighand->siglock));
>> +
>> + if (current->seccomp.mode != SECCOMP_MODE_FILTER)
>> + return -EACCES;
>
> Quick question -- is it possible to apply the first filter and also synchronize
> it across threads in the same operation? If so, does this arm also need to
> cope with seccomp.mode being SECCOMP_MODE_DISABLED?
>
> [seccomp_set_mode_filter() looks to call this via seccomp_attach_filter()
> before it does seccomp_assign_mode()]
I don't entirely understand what you're asking. The threads gain the
filter and the mode before the current thread may gain the mode (if
it's the first time this has been called). Due to all the locks,
though, this isn't a problem. Is there a situation you see where there
might be a problem?
-Kees
--
Kees Cook
Chrome OS Security
^ permalink raw reply
* Re: [PATCH v11 11/11] seccomp: implement SECCOMP_FILTER_FLAG_TSYNC
From: David Drysdale @ 2014-07-17 15:04 UTC (permalink / raw)
To: Kees Cook
Cc: linux-kernel@vger.kernel.org, Andy Lutomirski, Oleg Nesterov,
James Morris, Michael Kerrisk (man-pages), Alexei Starovoitov,
Andrew Morton, Daniel Borkmann, Will Drewry, Julien Tinnes,
Linux API, x86, linux-arm-kernel, linux-mips, linux-arch,
LSM List
In-Reply-To: <1405547442-26641-12-git-send-email-keescook@chromium.org>
On Wed, Jul 16, 2014 at 10:50 PM, Kees Cook <keescook@chromium.org> wrote:
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 9065d2c79c56..2125b83ccfd4 100644
> +/**
> + * seccomp_can_sync_threads: checks if all threads can be synchronized
> + *
> + * Expects sighand and cred_guard_mutex locks to be held.
> + *
> + * Returns 0 on success, -ve on error, or the pid of a thread which was
> + * either not in the correct seccomp mode or it did not have an ancestral
> + * seccomp filter.
> + */
> +static inline pid_t seccomp_can_sync_threads(void)
> +{
> + struct task_struct *thread, *caller;
> +
> + BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
> + BUG_ON(!spin_is_locked(¤t->sighand->siglock));
> +
> + if (current->seccomp.mode != SECCOMP_MODE_FILTER)
> + return -EACCES;
Quick question -- is it possible to apply the first filter and also synchronize
it across threads in the same operation? If so, does this arm also need to
cope with seccomp.mode being SECCOMP_MODE_DISABLED?
[seccomp_set_mode_filter() looks to call this via seccomp_attach_filter()
before it does seccomp_assign_mode()]
> +
> + /* Validate all threads being eligible for synchronization. */
> + caller = current;
> + for_each_thread(caller, thread) {
> + pid_t failed;
> +
> + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
> + (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
> + is_ancestor(thread->seccomp.filter,
> + caller->seccomp.filter)))
> + continue;
> +
> + /* Return the first thread that cannot be synchronized. */
> + failed = task_pid_vnr(thread);
> + /* If the pid cannot be resolved, then return -ESRCH */
> + if (unlikely(WARN_ON(failed == 0)))
> + failed = -ESRCH;
> + return failed;
> + }
> +
> + return 0;
> +}
^ permalink raw reply
* [PATCH v2 08/25] amdkfd: Add IOCTL set definitions of amdkfd
From: Oded Gabbay @ 2014-07-17 13:29 UTC (permalink / raw)
To: David Airlie, Jerome Glisse, Alex Deucher, Andrew Morton
Cc: John Bridgman, Joerg Roedel, Andrew Lewycky, Christian König,
Michel Dänzer, Ben Goz, Alexey Skidanov, Evgeny Pinchuk,
Oded Gabbay, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1405603773-32688-1-git-send-email-oded.gabbay-5C7GfCeVMHo@public.gmane.org>
- KFD_IOC_GET_VERSION:
Retrieves the interface version of amdkfd
- KFD_IOC_CREATE_QUEUE:
Creates a usermode queue that runs on a specific GPU device
- KFD_IOC_DESTROY_QUEUE:
Destroys an existing usermode queue
- KFD_IOC_SET_MEMORY_POLICY:
Sets the memory policy of the default and alternate aperture of the calling process
- KFD_IOC_GET_CLOCK_COUNTERS:
Retrieves counters (timestamps) of CPU and GPU
- KFD_IOC_GET_PROCESS_APERTURES:
Retrieves information about process apertures that were initialized
during the open() call of the amdkfd device
- KFD_IOC_UPDATE_QUEUE:
Updates configuration of an existing usermode queue
- KFD_IOC_PMC_ACQUIRE_ACCESS:
Acquires exclusive access (from other HSA processes) to the performance
counters of the GPU
- KFD_IOC_PMC_RELEASE_ACCESS:
Releases exclusive access of the GPU's performance counters
Signed-off-by: Oded Gabbay <oded.gabbay-5C7GfCeVMHo@public.gmane.org>
---
include/uapi/linux/kfd_ioctl.h | 133 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 133 insertions(+)
create mode 100644 include/uapi/linux/kfd_ioctl.h
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
new file mode 100644
index 0000000..3cedd1a
--- /dev/null
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -0,0 +1,133 @@
+/*
+ * Copyright 2014 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef KFD_IOCTL_H_INCLUDED
+#define KFD_IOCTL_H_INCLUDED
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define KFD_IOCTL_CURRENT_VERSION 1
+
+/* The 64-bit ABI is the authoritative version. */
+#pragma pack(push, 1)
+
+struct kfd_ioctl_get_version_args {
+ uint32_t min_supported_version; /* from KFD */
+ uint32_t max_supported_version; /* from KFD */
+};
+
+/* For kfd_ioctl_create_queue_args.queue_type. */
+#define KFD_IOC_QUEUE_TYPE_COMPUTE 0
+#define KFD_IOC_QUEUE_TYPE_SDMA 1
+
+struct kfd_ioctl_create_queue_args {
+ uint64_t ring_base_address; /* to KFD */
+ uint64_t write_pointer_address; /* from KFD */
+ uint64_t read_pointer_address; /* from KFD */
+ uint64_t doorbell_address; /* from KFD */
+
+ uint32_t ring_size; /* to KFD */
+ uint32_t gpu_id; /* to KFD */
+ uint32_t queue_type; /* to KFD */
+ uint32_t queue_percentage; /* to KFD */
+ uint32_t queue_priority; /* to KFD */
+ uint32_t queue_id; /* from KFD */
+};
+
+struct kfd_ioctl_destroy_queue_args {
+ uint32_t queue_id; /* to KFD */
+};
+
+struct kfd_ioctl_update_queue_args {
+ uint64_t ring_base_address; /* to KFD */
+
+ uint32_t queue_id; /* to KFD */
+ uint32_t ring_size; /* to KFD */
+ uint32_t queue_percentage; /* to KFD */
+ uint32_t queue_priority; /* to KFD */
+};
+
+/* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
+#define KFD_IOC_CACHE_POLICY_COHERENT 0
+#define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
+
+struct kfd_ioctl_set_memory_policy_args {
+ uint64_t alternate_aperture_base; /* to KFD */
+ uint64_t alternate_aperture_size; /* to KFD */
+
+ uint32_t gpu_id; /* to KFD */
+ uint32_t default_policy; /* to KFD */
+ uint32_t alternate_policy; /* to KFD */
+};
+
+struct kfd_ioctl_get_clock_counters_args {
+ uint64_t gpu_clock_counter; /* from KFD */
+ uint64_t cpu_clock_counter; /* from KFD */
+ uint64_t system_clock_counter; /* from KFD */
+ uint64_t system_clock_freq; /* from KFD */
+
+ uint32_t gpu_id; /* to KFD */
+};
+
+#define NUM_OF_SUPPORTED_GPUS 7
+
+struct kfd_process_device_apertures {
+ uint64_t lds_base; /* from KFD */
+ uint64_t lds_limit; /* from KFD */
+ uint64_t scratch_base; /* from KFD */
+ uint64_t scratch_limit; /* from KFD */
+ uint64_t gpuvm_base; /* from KFD */
+ uint64_t gpuvm_limit; /* from KFD */
+ uint32_t gpu_id; /* from KFD */
+};
+
+struct kfd_ioctl_get_process_apertures_args {
+ struct kfd_process_device_apertures process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */
+ uint8_t num_of_nodes; /* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS]*/
+};
+
+struct kfd_ioctl_pmc_acquire_access_args {
+ uint64_t trace_id; /* to KFD */
+ uint32_t gpu_id; /* to KFD */
+};
+
+struct kfd_ioctl_pmc_release_access_args {
+ uint64_t trace_id; /* to KFD */
+ uint32_t gpu_id; /* to KFD */
+};
+
+#define KFD_IOC_MAGIC 'K'
+
+#define KFD_IOC_GET_VERSION _IOR(KFD_IOC_MAGIC, 1, struct kfd_ioctl_get_version_args)
+#define KFD_IOC_CREATE_QUEUE _IOWR(KFD_IOC_MAGIC, 2, struct kfd_ioctl_create_queue_args)
+#define KFD_IOC_DESTROY_QUEUE _IOWR(KFD_IOC_MAGIC, 3, struct kfd_ioctl_destroy_queue_args)
+#define KFD_IOC_SET_MEMORY_POLICY _IOW(KFD_IOC_MAGIC, 4, struct kfd_ioctl_set_memory_policy_args)
+#define KFD_IOC_GET_CLOCK_COUNTERS _IOWR(KFD_IOC_MAGIC, 5, struct kfd_ioctl_get_clock_counters_args)
+#define KFD_IOC_GET_PROCESS_APERTURES _IOR(KFD_IOC_MAGIC, 6, struct kfd_ioctl_get_process_apertures_args)
+#define KFD_IOC_UPDATE_QUEUE _IOW(KFD_IOC_MAGIC, 7, struct kfd_ioctl_update_queue_args)
+#define KFD_IOC_PMC_ACQUIRE_ACCESS _IOW(KFD_IOC_MAGIC, 12, struct kfd_ioctl_pmc_acquire_access_args)
+#define KFD_IOC_PMC_RELEASE_ACCESS _IOW(KFD_IOC_MAGIC, 13, struct kfd_ioctl_pmc_release_access_args)
+
+#pragma pack(pop)
+
+#endif
--
1.9.1
^ permalink raw reply related
* RE: [net-next PATCH v2 0/3] Broadcast/Multicast rate limit via Ethtool Coalesce
From: David Laight @ 2014-07-17 12:53 UTC (permalink / raw)
To: 'Mugunthan V N', David Miller
Cc: netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <53C76990.3000304-l0cyMroinI0@public.gmane.org>
> From: Mugunthan V N
> On Thursday 10 July 2014 05:14 AM, David Miller wrote:
> > From: Mugunthan V N <mugunthanvnm-l0cyMroinI0@public.gmane.org>
> > Date: Wed, 9 Jul 2014 12:44:07 +0530
> >
> >> A system/cpu can be loaded by a hacker with flooding of broadcast or
> >> multicast packets, to prevent this some Ethernet controllers like CPSW
> >> provide a mechanism to limit the broadcast/multicast packet rate via
> >> hardware limiters. This patch series enables this feature via
> >> Ethtool Coalesce.
> > This is pretty bogus if you ask me.
> >
> > What is the difference from accepting a high rate of unicast packets?
> > I say it is no different.
> >
> > Therefore, this feature makes no sense to me at all.
>
> Any packet storm can cause an endpoint some issues. Typically packet
> storms will cause the system CPU to thrash resulting is very low system
> performance.
>
> Unicast storms only target a single destination end station, it can be
> easily mitigated by the host adding a blocking entry in the LUT for each
> aggressor.
>
> Broadcast and multicast target multiple end stations, or an entire
> network, not only can it cause CPU thrashing, it can result in loss of
> other broadcast and multicast services. The rate limiting feature allow
> the broadcast and or multicast traffic to be dropped if the rates are
> too high. This eliminates the CPU thrashing issue. It also allows the
> system to analyze the aggressors and block them for future transgressions.
Rate limiting multicast traffic will definitely cause the loss of multicast
services.
My experience of broadcast storms is that many of the ethernet switches
(probably especially the cheap ones) end up using a much slower software?
path for broadcasts. In a broadcast storm they start discarding normal
traffic - to point where a single ssh session becomes unusable.
This is true even when isolated from the storm by a 10M hub.
Broadcast storms are probably mostly caused by network topology issues.
Especially is switches are sending traffic to 'all ports' while resetting
the spanning tree tables.
David
^ permalink raw reply
* Re: [PATCH v12 8/8] mm: Don't split THP page when syscall is called
From: Kirill A. Shutemov @ 2014-07-17 11:30 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-kernel, linux-mm, Michael Kerrisk, Linux API,
Hugh Dickins, Johannes Weiner, Rik van Riel, KOSAKI Motohiro,
Mel Gorman, Jason Evans, Zhang Yanfei, Andrea Arcangeli
In-Reply-To: <1404886949-17695-9-git-send-email-minchan@kernel.org>
On Wed, Jul 09, 2014 at 03:22:29PM +0900, Minchan Kim wrote:
> We don't need to split THP page when MADV_FREE syscall is
> called. It could be done when VM decide really frees it so
> we could avoid unnecessary THP split.
>
> Cc: Andrea Arcangeli <aarcange@redhat.com>
> Signed-off-by: Minchan Kim <minchan@kernel.org>
I would like to free THP without splitting. But good enough for now.
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
--
Kirill A. Shutemov
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [PATCH v12 1/8] mm: support madvise(MADV_FREE)
From: Kirill A. Shutemov @ 2014-07-17 11:28 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-kernel, linux-mm, Michael Kerrisk, Linux API,
Hugh Dickins, Johannes Weiner, Rik van Riel, KOSAKI Motohiro,
Mel Gorman, Jason Evans, Zhang Yanfei
In-Reply-To: <1404886949-17695-2-git-send-email-minchan@kernel.org>
On Wed, Jul 09, 2014 at 03:22:22PM +0900, Minchan Kim wrote:
> Linux doesn't have an ability to free pages lazy while other OS
> already have been supported that named by madvise(MADV_FREE).
>
> The gain is clear that kernel can discard freed pages rather than
> swapping out or OOM if memory pressure happens.
>
> Without memory pressure, freed pages would be reused by userspace
> without another additional overhead(ex, page fault + allocation
> + zeroing).
>
> How to work is following as.
>
> When madvise syscall is called, VM clears dirty bit of ptes of
> the range. If memory pressure happens, VM checks dirty bit of
> page table and if it found still "clean", it means it's a
> "lazyfree pages" so VM could discard the page instead of swapping out.
> Once there was store operation for the page before VM peek a page
> to reclaim, dirty bit is set so VM can swap out the page instead of
> discarding.
>
> Firstly, heavy users would be general allocators(ex, jemalloc,
> tcmalloc and hope glibc supports it) and jemalloc/tcmalloc already
> have supported the feature for other OS(ex, FreeBSD)
>
> barrios@blaptop:~/benchmark/ebizzy$ lscpu
> Architecture: x86_64
> CPU op-mode(s): 32-bit, 64-bit
> Byte Order: Little Endian
> CPU(s): 4
> On-line CPU(s) list: 0-3
> Thread(s) per core: 2
> Core(s) per socket: 2
> Socket(s): 1
> NUMA node(s): 1
> Vendor ID: GenuineIntel
> CPU family: 6
> Model: 42
> Stepping: 7
> CPU MHz: 2801.000
> BogoMIPS: 5581.64
> Virtualization: VT-x
> L1d cache: 32K
> L1i cache: 32K
> L2 cache: 256K
> L3 cache: 4096K
> NUMA node0 CPU(s): 0-3
>
> ebizzy benchmark(./ebizzy -S 10 -n 512)
>
> vanilla-jemalloc MADV_free-jemalloc
>
> 1 thread
> records: 10 records: 10
> avg: 7682.10 avg: 15306.10
> std: 62.35(0.81%) std: 347.99(2.27%)
> max: 7770.00 max: 15622.00
> min: 7598.00 min: 14772.00
>
> 2 thread
> records: 10 records: 10
> avg: 12747.50 avg: 24171.00
> std: 792.06(6.21%) std: 895.18(3.70%)
> max: 13337.00 max: 26023.00
> min: 10535.00 min: 23152.00
>
> 4 thread
> records: 10 records: 10
> avg: 16474.60 avg: 33717.90
> std: 1496.45(9.08%) std: 2008.97(5.96%)
> max: 17877.00 max: 35958.00
> min: 12224.00 min: 29565.00
>
> 8 thread
> records: 10 records: 10
> avg: 16778.50 avg: 33308.10
> std: 825.53(4.92%) std: 1668.30(5.01%)
> max: 17543.00 max: 36010.00
> min: 14576.00 min: 29577.00
>
> 16 thread
> records: 10 records: 10
> avg: 20614.40 avg: 35516.30
> std: 602.95(2.92%) std: 1283.65(3.61%)
> max: 21753.00 max: 37178.00
> min: 19605.00 min: 33217.00
>
> 32 thread
> records: 10 records: 10
> avg: 22771.70 avg: 36018.50
> std: 598.94(2.63%) std: 1046.76(2.91%)
> max: 24035.00 max: 37266.00
> min: 22108.00 min: 34149.00
>
> In summary, MADV_FREE is about 2 time faster than MADV_DONTNEED.
>
> Cc: Michael Kerrisk <mtk.manpages@gmail.com>
> Cc: Linux API <linux-api@vger.kernel.org>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> Cc: Mel Gorman <mgorman@suse.de>
> Cc: Jason Evans <je@fb.com>
> Acked-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
> Acked-by: Rik van Riel <riel@redhat.com>
> Signed-off-by: Minchan Kim <minchan@kernel.org>
> ---
> include/linux/rmap.h | 9 ++-
> include/linux/vm_event_item.h | 1 +
> include/uapi/asm-generic/mman-common.h | 1 +
> mm/madvise.c | 136 +++++++++++++++++++++++++++++++++
> mm/rmap.c | 42 +++++++++-
> mm/vmscan.c | 40 ++++++++--
> mm/vmstat.c | 1 +
> 7 files changed, 218 insertions(+), 12 deletions(-)
>
> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
> index be574506e6a9..0ba377b97a38 100644
> --- a/include/linux/rmap.h
> +++ b/include/linux/rmap.h
> @@ -75,6 +75,7 @@ enum ttu_flags {
> TTU_UNMAP = 1, /* unmap mode */
> TTU_MIGRATION = 2, /* migration mode */
> TTU_MUNLOCK = 4, /* munlock mode */
> + TTU_FREE = 8, /* free mode */
>
> TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
> TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
> @@ -181,7 +182,8 @@ static inline void page_dup_rmap(struct page *page)
> * Called from mm/vmscan.c to handle paging out
> */
> int page_referenced(struct page *, int is_locked,
> - struct mem_cgroup *memcg, unsigned long *vm_flags);
> + struct mem_cgroup *memcg, unsigned long *vm_flags,
> + int *is_dirty);
>
> #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
>
> @@ -260,9 +262,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
>
> static inline int page_referenced(struct page *page, int is_locked,
> struct mem_cgroup *memcg,
> - unsigned long *vm_flags)
> + unsigned long *vm_flags,
> + int *is_pte_dirty)
> {
> *vm_flags = 0;
> + if (is_pte_dirty)
> + *is_pte_dirty = 0;
> return 0;
> }
>
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> index ced92345c963..e2d3fb1e9814 100644
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
> FOR_ALL_ZONES(PGALLOC),
> PGFREE, PGACTIVATE, PGDEACTIVATE,
> PGFAULT, PGMAJFAULT,
> + PGLAZYFREED,
> FOR_ALL_ZONES(PGREFILL),
> FOR_ALL_ZONES(PGSTEAL_KSWAPD),
> FOR_ALL_ZONES(PGSTEAL_DIRECT),
> diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
> index ddc3b36f1046..7a94102b7a02 100644
> --- a/include/uapi/asm-generic/mman-common.h
> +++ b/include/uapi/asm-generic/mman-common.h
> @@ -34,6 +34,7 @@
> #define MADV_SEQUENTIAL 2 /* expect sequential page references */
> #define MADV_WILLNEED 3 /* will need these pages */
> #define MADV_DONTNEED 4 /* don't need these pages */
> +#define MADV_FREE 5 /* free pages only if memory pressure */
>
> /* common parameters: try to keep these consistent across architectures */
> #define MADV_REMOVE 9 /* remove these pages & resources */
> diff --git a/mm/madvise.c b/mm/madvise.c
> index 0938b30da4ab..55b42e5e32a3 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -19,6 +19,14 @@
> #include <linux/blkdev.h>
> #include <linux/swap.h>
> #include <linux/swapops.h>
> +#include <linux/mmu_notifier.h>
> +
> +#include <asm/tlb.h>
> +
> +struct madvise_free_private {
> + struct vm_area_struct *vma;
> + struct mmu_gather *tlb;
> +};
>
> /*
> * Any behaviour which results in changes to the vma->vm_flags needs to
> @@ -31,6 +39,7 @@ static int madvise_need_mmap_write(int behavior)
> case MADV_REMOVE:
> case MADV_WILLNEED:
> case MADV_DONTNEED:
> + case MADV_FREE:
> return 0;
> default:
> /* be safe, default to 1. list exceptions explicitly */
> @@ -251,6 +260,124 @@ static long madvise_willneed(struct vm_area_struct *vma,
> return 0;
> }
>
> +static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
> + unsigned long end, struct mm_walk *walk)
> +
> +{
> + struct madvise_free_private *fp = walk->private;
> + struct mmu_gather *tlb = fp->tlb;
> + struct mm_struct *mm = tlb->mm;
> + struct vm_area_struct *vma = fp->vma;
> + spinlock_t *ptl;
> + pte_t *pte, ptent;
> + struct page *page;
> +
> + split_huge_page_pmd(vma, addr, pmd);
> + if (pmd_trans_unstable(pmd))
> + return 0;
> +
> + pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
> + arch_enter_lazy_mmu_mode();
> + for (; addr != end; pte++, addr += PAGE_SIZE) {
> + ptent = *pte;
> +
> + if (!pte_present(ptent))
> + continue;
> +
> + page = vm_normal_page(vma, addr, ptent);
> + if (!page)
> + continue;
> +
> + if (PageSwapCache(page)) {
> + if (trylock_page(page)) {
> + if (try_to_free_swap(page))
> + ClearPageDirty(page);
> + unlock_page(page);
'continue' for !try_to_free_swap(page) case?
> + } else
> + continue;
> + }
> +
> + /*
> + * Some of architecture(ex, PPC) don't update TLB
> + * with set_pte_at and tlb_remove_tlb_entry so for
> + * the portability, remap the pte with old|clean
> + * after pte clearing.
> + */
> + ptent = ptep_get_and_clear_full(mm, addr, pte,
> + tlb->fullmm);
> + ptent = pte_mkold(ptent);
> + ptent = pte_mkclean(ptent);
> + set_pte_at(mm, addr, pte, ptent);
> + tlb_remove_tlb_entry(tlb, pte, addr);
> + }
> + arch_leave_lazy_mmu_mode();
> + pte_unmap_unlock(pte - 1, ptl);
> + cond_resched();
> + return 0;
> +}
> +
> +static void madvise_free_page_range(struct mmu_gather *tlb,
> + struct vm_area_struct *vma,
> + unsigned long addr, unsigned long end)
> +{
> + struct madvise_free_private fp = {
> + .vma = vma,
> + .tlb = tlb,
> + };
> +
> + struct mm_walk free_walk = {
> + .pmd_entry = madvise_free_pte_range,
> + .mm = vma->vm_mm,
> + .private = &fp,
> + };
> +
> + BUG_ON(addr >= end);
> + tlb_start_vma(tlb, vma);
> + walk_page_range(addr, end, &free_walk);
> + tlb_end_vma(tlb, vma);
> +}
> +
> +static int madvise_free_single_vma(struct vm_area_struct *vma,
> + unsigned long start_addr, unsigned long end_addr)
> +{
> + unsigned long start, end;
> + struct mm_struct *mm = vma->vm_mm;
> + struct mmu_gather tlb;
> +
> + if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
THP uses VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE to filter out
'special' VMAs. Looks reasonable here too.
Otherwise:
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
--
Kirill A. Shutemov
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox