[PATCH 01/19] c/r: extend arch_setup_additional_pages()

[PATCH 01/19] c/r: extend arch_setup_additional_pages()

[Dan Smith]

From: Alexey Dobriyan <adobriyan@gmail.com>

Add "start" argument, to request to map vDSO to a specific place,
and fail the operation if not.

This is useful for restart(2) to ensure that memory layout is restore
exactly as needed.

Changelog[v19]:
  - [serge hallyn] Fix potential use-before-set ret
Changelog[v2]:
  - [ntl] powerpc: vdso build fix (ckpt-v17)

Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Oren Laadan <orenl@cs.columbia.edu>
---
 arch/powerpc/include/asm/elf.h     |    1 +
 arch/powerpc/kernel/vdso.c         |   13 ++++++++++++-
 arch/s390/include/asm/elf.h        |    2 +-
 arch/s390/kernel/vdso.c            |   13 ++++++++++++-
 arch/sh/include/asm/elf.h          |    1 +
 arch/sh/kernel/vsyscall/vsyscall.c |    2 +-
 arch/x86/include/asm/elf.h         |    3 ++-
 arch/x86/vdso/vdso32-setup.c       |    9 +++++++--
 arch/x86/vdso/vma.c                |   11 ++++++++---
 fs/binfmt_elf.c                    |    2 +-
 10 files changed, 46 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 2b917c6..1c26833 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -266,6 +266,7 @@ extern int ucache_bsize;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       unsigned long start,
 				       int uses_interp);
 #define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b);
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index fd87287..c408960 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -188,7 +188,8 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
  */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+				unsigned long start, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	struct page **vdso_pagelist;
@@ -220,6 +221,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	vdso_base = VDSO32_MBASE;
 #endif
 
+	/* in case restart(2) mandates a specific location */
+	if (start)
+		vdso_base = start;
+
 	current->mm->context.vdso_base = 0;
 
 	/* vDSO has a problem and was disabled, just don't "enable" it for the
@@ -249,6 +254,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	/* Add required alignment. */
 	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
 
+	/* for restart(2), double check that we got we asked for */
+	if (start && vdso_base != start) {
+		rc = -EBUSY;
+		goto fail_mmapsem;
+	}
+
 	/*
 	 * Put vDSO base into mm struct. We need to do this before calling
 	 * install_special_mapping or the perf counter mmap tracking code
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 354d426..5081938 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -216,6 +216,6 @@ do {									    \
 struct linux_binprm;
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-int arch_setup_additional_pages(struct linux_binprm *, int);
+int arch_setup_additional_pages(struct linux_binprm *, unsigned long, int);
 
 #endif
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index e3150dd..199642b 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -187,7 +187,8 @@ static void vdso_init_cr5(void)
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
  */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+				unsigned long start, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	struct page **vdso_pagelist;
@@ -218,6 +219,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	vdso_pages = vdso32_pages;
 #endif
 
+	/* in case restart(2) mandates a specific location */
+	if (start)
+		vdso_base = start;
+
 	/*
 	 * vDSO has a problem and was disabled, just don't "enable" it for
 	 * the process
@@ -240,6 +245,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto out_up;
 	}
 
+	/* for restart(2), double check that we got we asked for */
+	if (start && vdso_base != start) {
+		rc = -EINVAL;
+		goto out_up;
+	}
+
 	/*
 	 * Put vDSO base into mm struct. We need to do this before calling
 	 * install_special_mapping or the perf counter mmap tracking code
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index f38112b..0f1dc2a 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -190,6 +190,7 @@ do {									\
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       unsigned long start,
 				       int uses_interp);
 
 extern unsigned int vdso_enabled;
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index 242117c..6dbdfe1 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -58,7 +58,7 @@ int __init vsyscall_init(void)
 }
 
 /* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm, unsigned long start, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f2ad216..3761be8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -312,9 +312,10 @@ struct linux_binprm;
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       unsigned long start,
 				       int uses_interp);
 
-extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
+extern int syscall32_setup_pages(struct linux_binprm *, unsigned long start, int exstack);
 #define compat_arch_setup_additional_pages	syscall32_setup_pages
 
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 36df991..8005f6f 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -310,7 +310,8 @@ int __init sysenter_setup(void)
 }
 
 /* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+				unsigned long start, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
@@ -331,13 +332,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (compat)
 		addr = VDSO_HIGH_BASE;
 	else {
-		addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+		addr = get_unmapped_area(NULL, start, PAGE_SIZE, 0, 0);
 		if (IS_ERR_VALUE(addr)) {
 			ret = addr;
 			goto up_fail;
 		}
 	}
 
+	/* for restart(2), double check that we got we asked for */
+	if (start && addr != start)
+		goto up_fail;
+
 	current->mm->context.vdso = (void *)addr;
 
 	if (compat_uses_vma || !compat) {
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 4b5d26f..5b32897 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -101,23 +101,28 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 
 /* Setup a VMA at program startup for the vsyscall page.
    Not called for compat tasks */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+				unsigned long start, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
-	int ret;
+	int ret = -EINVAL;
 
 	if (!vdso_enabled)
 		return 0;
 
 	down_write(&mm->mmap_sem);
-	addr = vdso_addr(mm->start_stack, vdso_size);
+	addr = start ? : vdso_addr(mm->start_stack, vdso_size);
 	addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
 	}
 
+	/* for restart(2), double check that we got we asked for */
+	if (start && addr != start)
+		goto up_fail;
+
 	current->mm->context.vdso = (void *)addr;
 
 	ret = install_special_mapping(mm, addr, vdso_size,
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 6884e19..fc53346 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -923,7 +923,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	set_binfmt(&elf_format);
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
-	retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
+	retval = arch_setup_additional_pages(bprm, 0, !!elf_interpreter);
 	if (retval < 0) {
 		send_sig(SIGKILL, current, 0);
 		goto out;
-- 
1.7.2.2

[PATCH 06/19] c/r: create syscalls: sys_checkpoint, sys_restart

[Dan Smith]

From: Oren Laadan <orenl@cs.columbia.edu>

Create trivial sys_checkpoint and sys_restore system calls. They will
enable to checkpoint and restart an entire container, to and from a
checkpoint image file descriptor.

The syscalls take a pid, a file descriptor (for the image file) and
flags as arguments. The pid identifies the top-most (root) task in the
process tree, e.g. the container init: for sys_checkpoint the first
argument identifies the pid of the target container/subtree; for
sys_restart it will identify the pid of restarting root task.

A checkpoint, much like a process coredump, dumps the state of multiple
processes at once, including the state of the container. The checkpoint
image is written to (and read from) the file descriptor directly from
the kernel. This way the data is generated and then pushed out naturally
as resources and tasks are scanned to save their state. This is the
approach taken by, e.g., Zap and OpenVZ.

By using a return value and not a file descriptor, we can distinguish
between a return from checkpoint, a return from restart (in case of a
checkpoint that includes self, i.e. a task checkpointing its own
container, or itself), and an error condition, in a manner analogous
to a fork() call.

We don't use copy_from_user()/copy_to_user() because it requires
holding the entire image in user space, and does not make sense for
restart.  Also, we don't use a pipe, pseudo-fs file and the like,
because they work by generating data on demand as the user pulls it
(unless the entire image is buffered in the kernel) and would require
more complex logic.  They also would significantly complicate
checkpoint that includes self.

Changelog[v21-rc3]:
  - Reorganize code:move checkpoint/* to kernel/checkpoint/*
Changelog[v19-rc1]:
  - Add 'int logfd' to prototype of sys_{checkpoint,restart}
Changelog[v18]:
  - [John Dykstra] Fix no-dot-config-targets pattern in linux/Makefile
Changelog[v17]:
  - Move checkpoint closer to namespaces (kconfig)
  - Kill "Enable" in c/r config option
Changelog[v16]:
  - Change sys_restart() first argument to be 'pid_t pid'
Changelog[v14]:
  - Change CONFIG_CHEKCPOINT_RESTART to CONFIG_CHECKPOINT (Ingo)
  - Remove line 'def_bool n' (default is already 'n')
  - Add CHECKPOINT_SUPPORT in Kconfig (Nathan Lynch)
Changelog[v5]:
  - Config is 'def_bool n' by default

Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Oren Laadan <orenl@cs.columbia.edu>
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
---
 Makefile                           |    2 +-
 arch/x86/Kconfig                   |    4 +++
 arch/x86/include/asm/unistd_32.h   |    4 ++-
 arch/x86/kernel/syscall_table_32.S |    2 +
 include/linux/syscalls.h           |    4 +++
 init/Kconfig                       |    2 +
 kernel/Makefile                    |    1 +
 kernel/checkpoint/Kconfig          |   14 +++++++++++
 kernel/checkpoint/Makefile         |    5 ++++
 kernel/checkpoint/sys.c            |   45 ++++++++++++++++++++++++++++++++++++
 kernel/sys_ni.c                    |    4 +++
 11 files changed, 85 insertions(+), 2 deletions(-)
 create mode 100644 kernel/checkpoint/Kconfig
 create mode 100644 kernel/checkpoint/Makefile
 create mode 100644 kernel/checkpoint/sys.c

diff --git a/Makefile b/Makefile
index ab5359d..38f5a25 100644
--- a/Makefile
+++ b/Makefile
@@ -421,7 +421,7 @@ endif
 
 no-dot-config-targets := clean mrproper distclean \
 			 cscope TAGS tags help %docs check% coccicheck \
-			 include/linux/version.h headers_% \
+			 checkstack include/linux/version.h headers_% \
 			 kernelversion %src-pkg
 
 config-targets := 0
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e832768..0e043fa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,6 +101,10 @@ config STACKTRACE_SUPPORT
 config HAVE_LATENCYTOP_SUPPORT
 	def_bool y
 
+config CHECKPOINT_SUPPORT
+	bool
+	default y if X86_32
+
 config MMU
 	def_bool y
 
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index b766a5e..a2d589f 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -346,10 +346,12 @@
 #define __NR_fanotify_init	338
 #define __NR_fanotify_mark	339
 #define __NR_prlimit64		340
+#define __NR_checkpoint		341
+#define __NR_restart		342
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 341
+#define NR_syscalls 343
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index b35786d..13fbe8a 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -340,3 +340,5 @@ ENTRY(sys_call_table)
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
 	.long sys_prlimit64		/* 340 */
+	.long ptregs_checkpoint
+	.long ptregs_restart
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index cacc27a..20be1a6 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -820,6 +820,10 @@ asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags
 asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags,
 				  u64 mask, int fd,
 				  const char  __user *pathname);
+asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags,
+			       int logfd);
+asmlinkage long sys_restart(pid_t pid, int fd, unsigned long flags,
+			    int logfd);
 
 int kernel_execve(const char *filename, const char *const argv[], const char *const envp[]);
 
diff --git a/init/Kconfig b/init/Kconfig
index 88c1046..75650df 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -780,6 +780,8 @@ config RELAY
 
 	  If unsure, say N.
 
+source "kernel/checkpoint/Kconfig"
+
 config BLK_DEV_INITRD
 	bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
 	depends on BROKEN || !FRV
diff --git a/kernel/Makefile b/kernel/Makefile
index 0b5ff08..3f6238c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -106,6 +106,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
+obj-$(CONFIG_CHECKPOINT) += checkpoint/
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/checkpoint/Kconfig b/kernel/checkpoint/Kconfig
new file mode 100644
index 0000000..ef7d406
--- /dev/null
+++ b/kernel/checkpoint/Kconfig
@@ -0,0 +1,14 @@
+# Architectures should define CHECKPOINT_SUPPORT when they have
+# implemented the hooks for processor state etc. needed by the
+# core checkpoint/restart code.
+
+config CHECKPOINT
+	bool "Checkpoint/restart (EXPERIMENTAL)"
+	depends on CHECKPOINT_SUPPORT && EXPERIMENTAL
+	help
+	  Application checkpoint/restart is the ability to save the
+	  state of a running application so that it can later resume
+	  its execution from the time at which it was checkpointed.
+
+	  Turning this option on will enable checkpoint and restart
+	  functionality in the kernel.
diff --git a/kernel/checkpoint/Makefile b/kernel/checkpoint/Makefile
new file mode 100644
index 0000000..8a32c6f
--- /dev/null
+++ b/kernel/checkpoint/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for linux checkpoint/restart.
+#
+
+obj-$(CONFIG_CHECKPOINT) += sys.o
diff --git a/kernel/checkpoint/sys.c b/kernel/checkpoint/sys.c
new file mode 100644
index 0000000..a81750a
--- /dev/null
+++ b/kernel/checkpoint/sys.c
@@ -0,0 +1,45 @@
+/*
+ *  Generic container checkpoint-restart
+ *
+ *  Copyright (C) 2008-2009 Oren Laadan
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of the Linux
+ *  distribution for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+
+/**
+ * sys_checkpoint - checkpoint a container
+ * @pid: pid of the container init(1) process
+ * @fd: file to which dump the checkpoint image
+ * @flags: checkpoint operation flags
+ * @logfd: fd to which to dump debug and error messages
+ *
+ * Returns positive identifier on success, 0 when returning from restart
+ * or negative value on error
+ */
+SYSCALL_DEFINE4(checkpoint, pid_t, pid, int, fd,
+		unsigned long, flags, int, logfd)
+{
+	return -ENOSYS;
+}
+
+/**
+ * sys_restart - restart a container
+ * @pid: pid of task root (in coordinator's namespace), or 0
+ * @fd: file from which read the checkpoint image
+ * @flags: restart operation flags
+ * @logfd: fd to which to dump debug and error messages
+ *
+ * Returns negative value on error, or otherwise returns in the realm
+ * of the original checkpoint
+ */
+SYSCALL_DEFINE4(restart, pid_t, pid, int, fd,
+		unsigned long, flags, int, logfd)
+{
+	return -ENOSYS;
+}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9..b73a106 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,7 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* checkpoint/restart */
+cond_syscall(sys_checkpoint);
+cond_syscall(sys_restart);
-- 
1.7.2.2

Re: [PATCH 01/19] c/r: extend arch_setup_additional_pages()

[Dan Smith]

DS> Cc: x86@kernel.org
DS> Cc: linux-s390@vger.kernel.org
DS> Cc: linuxppc-dev@ozlabs.org
DS> Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
DS> Signed-off-by: Oren Laadan <orenl@cs.columbia.edu>

My apologies to the above mentioned recipients.  I did not mean to
send this out.  Please ignore.

-- 
Dan Smith
IBM Linux Technology Center
email: danms@us.ibm.com