Now we can do "external" checkpoint, i.e. act on another task.
sys_checkpoint() now looks up the target pid (in our namespace) and
checkpoints that corresponding task. That task should be the root of
a container.
sys_restart() remains the same, as the restart is always done in the
context of the restarting task.
Changelog[v14]:
- Refuse non-self checkpoint if target task isn't frozen
Changelog[v12]:
- Replace obsolete cr_debug() with pr_debug()
Changelog[v11]:
- Copy contents of 'init->fs->root' instead of pointing to them
Changelog[v10]:
- Grab vfs root of container init, rather than current process
Signed-off-by: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
Acked-by: Serge Hallyn <serue@xxxxxxxxxx>
---
checkpoint/checkpoint.c | 73 ++++++++++++++++++++++++++++++++++++++++++-
checkpoint/restart.c | 4 +-
checkpoint/sys.c | 6 +++
include/linux/checkpoint.h | 2 +
4 files changed, 81 insertions(+), 4 deletions(-)
diff --git a/checkpoint/checkpoint.c b/checkpoint/checkpoint.c
index 248d594..a5db9be 100644
--- a/checkpoint/checkpoint.c
+++ b/checkpoint/checkpoint.c
@@ -10,6 +10,8 @@
#include <linux/version.h>
#include <linux/sched.h>
+#include <linux/freezer.h>
+#include <linux/ptrace.h>
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/file.h>
@@ -240,6 +242,11 @@ static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
{
int ret;
+ if (t->state == TASK_DEAD) {
+ pr_warning("c/r: task may not be in state TASK_DEAD\n");
+ return -EAGAIN;
+ }
+
ret = cr_write_task_struct(ctx, t);
cr_debug("task_struct: ret %d\n", ret);
if (ret < 0)
@@ -262,22 +269,84 @@ static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
return ret;
}
+static int cr_get_container(struct cr_ctx *ctx, pid_t pid)
+{
+ struct task_struct *task = NULL;
+ struct nsproxy *nsproxy = NULL;
+ int err = -ESRCH;
+
+ ctx->root_pid = pid;
+
+ read_lock(&tasklist_lock);
+ task = find_task_by_vpid(pid);
+ if (task)
+ get_task_struct(task);
+ read_unlock(&tasklist_lock);
+
+ if (!task)
+ goto out;
+
+#if 0 /* enable to use containers */
+ if (!is_container_init(task)) {
+ err = -EINVAL;
+ goto out;
+ }
+#endif
+
+ if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ /* verify that the task is frozen (unless self) */
+ if (task != current && !frozen(task))
+ return -EBUSY;
+
+ rcu_read_lock();
+ if (task_nsproxy(task)) {
+ nsproxy = task_nsproxy(task);
+ get_nsproxy(nsproxy);
+ }
+ rcu_read_unlock();
+
+ if (!nsproxy)
+ goto out;
+
+ ctx->root_task = task;
+ ctx->root_nsproxy = nsproxy;
+
+ return 0;
+
+ out:
+ if (task)
+ put_task_struct(task);
+ return err;
+}
+
+/* setup checkpoint-specific parts of ctx */
static int cr_ctx_checkpoint(struct cr_ctx *ctx, pid_t pid)
{
struct fs_struct *fs;
+ int ret;
ctx->root_pid = pid;
+ ret = cr_get_container(ctx, pid);
+ if (ret < 0)
+ return ret;
+
/*
* assume checkpointer is in container's root vfs
* FIXME: this works for now, but will change with real containers
*/
- fs = current->fs;
+ task_lock(ctx->root_task);
+ fs = ctx->root_task->fs;
read_lock(&fs->lock);
ctx->fs_mnt = fs->root;
path_get(&ctx->fs_mnt);
read_unlock(&fs->lock);
+ task_unlock(ctx->root_task);
return 0;
}
@@ -292,7 +361,7 @@ int do_checkpoint(struct cr_ctx *ctx, pid_t pid)
ret = cr_write_head(ctx);
if (ret < 0)
goto out;
- ret = cr_write_task(ctx, current);
+ ret = cr_write_task(ctx, ctx->root_task);
if (ret < 0)
goto out;
ret = cr_write_tail(ctx);
diff --git a/checkpoint/restart.c b/checkpoint/restart.c
index 2435f4c..9623cfb 100644
--- a/checkpoint/restart.c
+++ b/checkpoint/restart.c
@@ -291,7 +291,7 @@ static int cr_read_task(struct cr_ctx *ctx)
}
/* setup restart-specific parts of ctx */
-static int cr_ctx_restart(struct cr_ctx *ctx)
+static int cr_ctx_restart(struct cr_ctx *ctx, pid_t pid)
{
return 0;
}
@@ -300,7 +300,7 @@ int do_restart(struct cr_ctx *ctx, pid_t pid)
{
int ret;
- ret = cr_ctx_restart(ctx);
+ ret = cr_ctx_restart(ctx, pid);
if (ret < 0)
goto out;
ret = cr_read_head(ctx);
diff --git a/checkpoint/sys.c b/checkpoint/sys.c
index eef774e..b1c60b1 100644
--- a/checkpoint/sys.c
+++ b/checkpoint/sys.c
@@ -9,6 +9,7 @@
*/
#include <linux/sched.h>
+#include <linux/nsproxy.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/file.h>
@@ -163,6 +164,11 @@ static void cr_ctx_free(struct cr_ctx *ctx)
cr_pgarr_free(ctx);
cr_objhash_free(ctx);
+ if (ctx->root_nsproxy)
+ put_nsproxy(ctx->root_nsproxy);
+ if (ctx->root_task)
+ put_task_struct(ctx->root_task);
+
kfree(ctx);
}
diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h
index ad4322d..3a6cef9 100644
--- a/include/linux/checkpoint.h
+++ b/include/linux/checkpoint.h
@@ -19,6 +19,8 @@ struct cr_ctx {
int crid; /* unique checkpoint id */
pid_t root_pid; /* container identifier */
+ struct task_struct *root_task; /* container root task */
+ struct nsproxy *root_nsproxy; /* container root nsproxy */
unsigned long flags;
unsigned long oflags; /* restart: old flags */
--
1.5.4.3
_______________________________________________
Containers mailing list
Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/containers
