This patch adds the checkpointing and restart of signal handling
state - 'struct sighand_struct'. Since the contents of this state
only affect userspace, no input validation is required.
Add _NSIG to kernel constants saved/tested with image header.
Number of signals (_NSIG) is arch-dependent, but is within __KERNEL__
and not visibile to userspace compile. Therefore, define per arch
CKPT_ARCH_NSIG in <asm/checkpoint_hdr.h>.
Changelog[v21]:
- Do not include checkpoint_hdr.h explicitly
- [Matt Helsley] Move the signal handler c/r code into kernel/signal.c
Changelog[v19-rc1]:
- [Matt Helsley] Add cpp definitions for enums
Changelog[v1]:
- Rename headerless struct ckpt_hdr_* to struct ckpt_*
Cc: Oleg Nesterov <o...@redhat.com>
Cc: Roland McGrath <rol...@redhat.com>
Signed-off-by: Oren Laadan <or...@cs.columbia.edu>
Acked-by: Serge E. Hallyn <se...@us.ibm.com>
Tested-by: Serge E. Hallyn <se...@us.ibm.com>
---
arch/s390/include/asm/checkpoint_hdr.h | 8 ++
arch/x86/include/asm/checkpoint_hdr.h | 8 ++
include/linux/checkpoint.h | 6 +
include/linux/checkpoint_hdr.h | 24 +++++
kernel/checkpoint/checkpoint.c | 2 +
kernel/checkpoint/process.c | 19 ++++
kernel/checkpoint/restart.c | 3 +
kernel/signal.c | 179 ++++++++++++++++++++++++++++++++
8 files changed, 249 insertions(+), 0 deletions(-)
diff --git a/arch/s390/include/asm/checkpoint_hdr.h
b/arch/s390/include/asm/checkpoint_hdr.h
index e3312c0..7d30317 100644
--- a/arch/s390/include/asm/checkpoint_hdr.h
+++ b/arch/s390/include/asm/checkpoint_hdr.h
@@ -91,6 +91,14 @@ struct ckpt_hdr_mm_context {
unsigned long asce_limit;
};
+#define CKPT_ARCH_NSIG 64
+#ifdef __KERNEL__
+#include <asm/signal.h>
+#if CKPT_ARCH_NSIG != _SIGCONTEXT_NSIG
+#error CKPT_ARCH_NSIG size is wrong (asm/sigcontext.h and asm/checkpoint_hdr.h)
+#endif
+#endif
+
struct ckpt_hdr_header_arch {
struct ckpt_hdr h;
};
diff --git a/arch/x86/include/asm/checkpoint_hdr.h
b/arch/x86/include/asm/checkpoint_hdr.h
index 292bf50..44737b8 100644
--- a/arch/x86/include/asm/checkpoint_hdr.h
+++ b/arch/x86/include/asm/checkpoint_hdr.h
@@ -52,6 +52,14 @@ enum {
#define CKPT_HDR_MM_CONTEXT_LDT CKPT_HDR_MM_CONTEXT_LDT
};
+#define CKPT_ARCH_NSIG 64
+#ifdef __KERNEL__
+#include <asm/signal.h>
+#if CKPT_ARCH_NSIG != _NSIG
+#error CKPT_ARCH_NSIG size is wrong per asm/signal.h and asm/checkpoint_hdr.h
+#endif
+#endif
+
struct ckpt_hdr_header_arch {
struct ckpt_hdr h;
/* FIXME: add HAVE_HWFP */
diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h
index 776de99..8e8cf6e 100644
--- a/include/linux/checkpoint.h
+++ b/include/linux/checkpoint.h
@@ -242,6 +242,12 @@ extern int restore_memory_contents(struct ckpt_ctx *ctx,
struct inode *inode);
VM_RESERVED | VM_NORESERVE | VM_HUGETLB | VM_NONLINEAR | \
VM_MAPPED_COPY | VM_INSERTPAGE | VM_MIXEDMAP | VM_SAO)
+/* signals */
+extern int checkpoint_obj_sighand(struct ckpt_ctx *ctx, struct task_struct *t);
+extern int restore_obj_sighand(struct ckpt_ctx *ctx, int sighand_objref);
+
+extern int ckpt_collect_sighand(struct ckpt_ctx *ctx, struct task_struct *t);
+
static inline int ckpt_validate_errno(int errno)
{
return (errno >= 0) && (errno < MAX_ERRNO);
diff --git a/include/linux/checkpoint_hdr.h b/include/linux/checkpoint_hdr.h
index 261badb..2dea11e 100644
--- a/include/linux/checkpoint_hdr.h
+++ b/include/linux/checkpoint_hdr.h
@@ -136,6 +136,9 @@ enum {
CKPT_HDR_IPC_SEM,
#define CKPT_HDR_IPC_SEM CKPT_HDR_IPC_SEM
+ CKPT_HDR_SIGHAND = 601,
+#define CKPT_HDR_SIGHAND CKPT_HDR_SIGHAND
+
CKPT_HDR_TAIL = 9001,
#define CKPT_HDR_TAIL CKPT_HDR_TAIL
@@ -173,6 +176,8 @@ enum obj_type {
#define CKPT_OBJ_FILE CKPT_OBJ_FILE
CKPT_OBJ_MM,
#define CKPT_OBJ_MM CKPT_OBJ_MM
+ CKPT_OBJ_SIGHAND,
+#define CKPT_OBJ_SIGHAND CKPT_OBJ_SIGHAND
CKPT_OBJ_NS,
#define CKPT_OBJ_NS CKPT_OBJ_NS
CKPT_OBJ_UTS_NS,
@@ -197,6 +202,8 @@ struct ckpt_const {
__u16 task_comm_len;
/* mm */
__u16 at_vector_size;
+ /* signal */
+ __u16 signal_nsig;
/* uts */
__u16 uts_sysname_len;
__u16 uts_nodename_len;
@@ -370,6 +377,7 @@ struct ckpt_hdr_task_objs {
__s32 files_objref;
__s32 mm_objref;
+ __s32 sighand_objref;
} __attribute__((aligned(8)));
/* restart blocks */
@@ -511,6 +519,22 @@ struct ckpt_hdr_pgarr {
__u64 nr_pages; /* number of pages to saved */
} __attribute__((aligned(8)));
+/* signals */
+struct ckpt_sigset {
+ __u8 sigset[CKPT_ARCH_NSIG / 8];
+} __attribute__((aligned(8)));
+
+struct ckpt_sigaction {
+ __u64 _sa_handler;
+ __u64 sa_flags;
+ __u64 sa_restorer;
+ struct ckpt_sigset sa_mask;
+} __attribute__((aligned(8)));
+
+struct ckpt_hdr_sighand {
+ struct ckpt_hdr h;
+ struct ckpt_sigaction action[0];
+} __attribute__((aligned(8)));
/* ipc commons */
struct ckpt_hdr_ipcns {
diff --git a/kernel/checkpoint/checkpoint.c b/kernel/checkpoint/checkpoint.c
index 9743866..d75f753 100644
--- a/kernel/checkpoint/checkpoint.c
+++ b/kernel/checkpoint/checkpoint.c
@@ -114,6 +114,8 @@ static void fill_kernel_const(struct ckpt_const *h)
h->task_comm_len = sizeof(tsk->comm);
/* mm->saved_auxv size */
h->at_vector_size = AT_VECTOR_SIZE;
+ /* signal */
+ h->signal_nsig = _NSIG;
/* uts */
h->uts_sysname_len = sizeof(uts->sysname);
h->uts_nodename_len = sizeof(uts->nodename);
diff --git a/kernel/checkpoint/process.c b/kernel/checkpoint/process.c
index 4bc76e0..5927b7b 100644
--- a/kernel/checkpoint/process.c
+++ b/kernel/checkpoint/process.c
@@ -180,6 +180,7 @@ static int checkpoint_task_objs(struct ckpt_ctx *ctx,
struct task_struct *t)
struct ckpt_hdr_task_objs *h;
int files_objref;
int mm_objref;
+ int sighand_objref;
int ret;
/*
@@ -218,11 +219,19 @@ static int checkpoint_task_objs(struct ckpt_ctx *ctx,
struct task_struct *t)
return mm_objref;
}
+ sighand_objref = checkpoint_obj_sighand(ctx, t);
+ ckpt_debug("sighand: objref %d\n", sighand_objref);
+ if (sighand_objref < 0) {
+ ckpt_err(ctx, sighand_objref, "%(T)sighand_struct\n");
+ return sighand_objref;
+ }
+
h = ckpt_hdr_get_type(ctx, sizeof(*h), CKPT_HDR_TASK_OBJS);
if (!h)
return -ENOMEM;
h->files_objref = files_objref;
h->mm_objref = mm_objref;
+ h->sighand_objref = sighand_objref;
ret = ckpt_write_obj(ctx, &h->h);
ckpt_hdr_put(ctx, h);
@@ -385,6 +394,9 @@ int ckpt_collect_task(struct ckpt_ctx *ctx, struct
task_struct *t)
if (ret < 0)
return ret;
ret = ckpt_collect_mm(ctx, t);
+ if (ret < 0)
+ return ret;
+ ret = ckpt_collect_sighand(ctx, t);
return ret;
}
@@ -544,10 +556,17 @@ static int restore_task_objs(struct ckpt_ctx *ctx)
ret = restore_obj_file_table(ctx, h->files_objref);
ckpt_debug("file_table: ret %d (%p)\n", ret, current->files);
+ if (ret < 0)
+ goto out;
ret = restore_obj_mm(ctx, h->mm_objref);
ckpt_debug("mm: ret %d (%p)\n", ret, current->mm);
+ if (ret < 0)
+ goto out;
+ ret = restore_obj_sighand(ctx, h->sighand_objref);
+ ckpt_debug("sighand: ret %d (%p)\n", ret, current->sighand);
+ out:
ckpt_hdr_put(ctx, h);
return ret;
}
diff --git a/kernel/checkpoint/restart.c b/kernel/checkpoint/restart.c
index a511fda..c9a667d 100644
--- a/kernel/checkpoint/restart.c
+++ b/kernel/checkpoint/restart.c
@@ -569,6 +569,9 @@ static int check_kernel_const(struct ckpt_const *h)
/* mm->saved_auxv size */
if (h->at_vector_size != AT_VECTOR_SIZE)
return -EINVAL;
+ /* signal */
+ if (h->signal_nsig != _NSIG)
+ return -EINVAL;
/* uts */
if (h->uts_sysname_len != sizeof(uts->sysname))
return -EINVAL;
diff --git a/kernel/signal.c b/kernel/signal.c
index be447c8..fdd760a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -30,6 +30,9 @@
#include <linux/nsproxy.h>
#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
+#define CKPT_DFLAG CKPT_DSYS
+#include <linux/errno.h>
+#include <linux/checkpoint.h>
#include <asm/param.h>
#include <asm/uaccess.h>
@@ -2735,7 +2738,183 @@ __attribute__((weak)) const char *arch_vma_name(struct
vm_area_struct *vma)
return NULL;
}
+#ifdef CONFIG_CHECKPOINT
+static inline void fill_sigset(struct ckpt_sigset *h, sigset_t *sigset)
+{
+ memcpy(&h->sigset, sigset, sizeof(*sigset));
+}
+
+static inline void load_sigset(sigset_t *sigset, struct ckpt_sigset *h)
+{
+ memcpy(sigset, &h->sigset, sizeof(*sigset));
+}
+
+/***********************************************************************
+ * sighand checkpoint/collect/restart
+ */
+
+static int checkpoint_sighand(struct ckpt_ctx *ctx, void *ptr)
+{
+ struct sighand_struct *sighand = ptr;
+ struct ckpt_hdr_sighand *h;
+ struct ckpt_sigaction *hh;
+ struct sigaction *sa;
+ int i, ret;
+
+ h = ckpt_hdr_get_type(ctx, _NSIG * sizeof(*hh) + sizeof(*h),
+ CKPT_HDR_SIGHAND);
+ if (!h)
+ return -ENOMEM;
+
+ hh = h->action;
+ spin_lock_irq(&sighand->siglock);
+ for (i = 0; i < _NSIG; i++) {
+ sa = &sighand->action[i].sa;
+ hh[i]._sa_handler = (unsigned long) sa->sa_handler;
+ hh[i].sa_flags = sa->sa_flags;
+ hh[i].sa_restorer = (unsigned long) sa->sa_restorer;
+ fill_sigset(&hh[i].sa_mask, &sa->sa_mask);
+ }
+ spin_unlock_irq(&sighand->siglock);
+
+ ret = ckpt_write_obj(ctx, &h->h);
+ ckpt_hdr_put(ctx, h);
+
+ return ret;
+}
+
+int checkpoint_obj_sighand(struct ckpt_ctx *ctx, struct task_struct *t)
+{
+ struct sighand_struct *sighand;
+ int objref;
+
+ read_lock(&tasklist_lock);
+ sighand = rcu_dereference(t->sighand);
+ atomic_inc(&sighand->count);
+ read_unlock(&tasklist_lock);
+
+ objref = checkpoint_obj(ctx, sighand, CKPT_OBJ_SIGHAND);
+ __cleanup_sighand(sighand);
+
+ return objref;
+}
+
+int ckpt_collect_sighand(struct ckpt_ctx *ctx, struct task_struct *t)
+{
+ struct sighand_struct *sighand;
+ int ret;
+
+ read_lock(&tasklist_lock);
+ sighand = rcu_dereference(t->sighand);
+ atomic_inc(&sighand->count);
+ read_unlock(&tasklist_lock);
+
+ ret = ckpt_obj_collect(ctx, sighand, CKPT_OBJ_SIGHAND);
+ __cleanup_sighand(sighand);
+
+ return ret;
+}
+
+static void *restore_sighand(struct ckpt_ctx *ctx)
+{
+ struct ckpt_hdr_sighand *h;
+ struct ckpt_sigaction *hh;
+ struct sighand_struct *sighand;
+ struct sigaction *sa;
+ int i;
+
+ h = ckpt_read_obj_type(ctx, _NSIG * sizeof(*hh) + sizeof(*h),
+ CKPT_HDR_SIGHAND);
+ if (IS_ERR(h))
+ return ERR_PTR(PTR_ERR(h));
+
+ sighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
+ if (!sighand) {
+ sighand = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ atomic_set(&sighand->count, 1);
+
+ hh = h->action;
+ for (i = 0; i < _NSIG; i++) {
+ sa = &sighand->action[i].sa;
+ sa->sa_handler = (void *) (unsigned long) hh[i]._sa_handler;
+ sa->sa_flags = hh[i].sa_flags;
+ sa->sa_restorer = (void *) (unsigned long) hh[i].sa_restorer;
+ load_sigset(&sa->sa_mask, &hh[i].sa_mask);
+ }
+ out:
+ ckpt_hdr_put(ctx, h);
+ return (void *) sighand;
+}
+
+int restore_obj_sighand(struct ckpt_ctx *ctx, int sighand_objref)
+{
+ struct sighand_struct *sighand;
+ struct sighand_struct *old_sighand;
+
+ sighand = ckpt_obj_fetch(ctx, sighand_objref, CKPT_OBJ_SIGHAND);
+ if (IS_ERR(sighand))
+ return PTR_ERR(sighand);
+
+ if (sighand == current->sighand)
+ return 0;
+
+ atomic_inc(&sighand->count);
+
+ /* manipulate tsk->sighand with tasklist lock write-held */
+ write_lock_irq(&tasklist_lock);
+ old_sighand = rcu_dereference(current->sighand);
+ spin_lock(&old_sighand->siglock);
+ rcu_assign_pointer(current->sighand, sighand);
+ spin_unlock(&old_sighand->siglock);
+ write_unlock_irq(&tasklist_lock);
+ __cleanup_sighand(old_sighand);
+
+ return 0;
+}
+
+/*
+ * signal-related checkpoint objects
+ */
+
+static int obj_sighand_grab(void *ptr)
+{
+ atomic_inc(&((struct sighand_struct *) ptr)->count);
+ return 0;
+}
+
+static void obj_sighand_drop(void *ptr, int lastref)
+{
+ __cleanup_sighand((struct sighand_struct *) ptr);
+}
+
+static int obj_sighand_users(void *ptr)
+{
+ return atomic_read(&((struct sighand_struct *) ptr)->count);
+}
+
+/* sighand object */
+static const struct ckpt_obj_ops ckpt_obj_sighand_ops = {
+ .obj_name = "SIGHAND",
+ .obj_type = CKPT_OBJ_SIGHAND,
+ .ref_drop = obj_sighand_drop,
+ .ref_grab = obj_sighand_grab,
+ .ref_users = obj_sighand_users,
+ .checkpoint = checkpoint_sighand,
+ .restore = restore_sighand,
+};
+
+static int __init checkpoint_register_signal(void)
+{
+ return register_checkpoint_obj(&ckpt_obj_sighand_ops);
+}
+#endif /* CONFIG_CHECKPOINT */
+
void __init signals_init(void)
{
sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC);
+#ifdef CONFIG_CHECKPOINT
+ checkpoint_register_signal();
+#endif
}
--
1.6.3.3
_______________________________________________
Containers mailing list
contain...@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
_______________________________________________
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
