From: Oren Laadan <orenl@librato.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@osdl.org>,
containers@lists.linux-foundation.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-api@vger.kernel.org, Serge Hallyn <serue@us.ibm.com>,
Ingo Molnar <mingo@elte.hu>, Pavel Emelyanov <xemul@openvz.org>,
Alexey Dobriyan <adobriyan@gmail.com>,
Oren Laadan <orenl@cs.columbia.edu>
Subject: [PATCH v18 01/80] c/r: extend arch_setup_additional_pages()
Date: Wed, 23 Sep 2009 19:50:41 -0400 [thread overview]
Message-ID: <1253749920-18673-2-git-send-email-orenl@librato.com> (raw)
In-Reply-To: <1253749920-18673-1-git-send-email-orenl@librato.com>
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[v2]:
- [ntl] powerpc: vdso build fix (ckpt-v17)
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 | 9 +++++++--
fs/binfmt_elf.c | 2 +-
10 files changed, 45 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 014a624..3cef9cf 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -271,6 +271,7 @@ 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 ad06d5c..679b394 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -184,7 +184,8 @@ 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;
@@ -211,6 +212,10 @@ 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
@@ -234,6 +239,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
goto fail_mmapsem;
}
+ /* for restart(2), double check that we got we asked for */
+ if (start && vdso_base != start) {
+ rc = -EBUSY;
+ goto fail_mmapsem;
+ }
+
/*
* our vma flags don't have VM_WRITE so by default, the process isn't
* allowed to write those pages.
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 74d0bbb..54235bc 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -205,6 +205,6 @@ 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 45e1708..c2ee689 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -193,7 +193,8 @@ 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;
@@ -224,6 +225,10 @@ 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
@@ -246,6 +251,12 @@ 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;
+ }
+
/*
* our vma flags don't have VM_WRITE so by default, the process
* isn't allowed to write those pages.
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index ccb1d93..6c27b1f 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -202,6 +202,7 @@ 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 3f7e415..64c70e5 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -59,7 +59,7 @@ 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 83c1bc8..a4398c8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -336,9 +336,10 @@ 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 58bc00f..5c914b0 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 21e1aeb..393b22a 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -99,7 +99,8 @@ 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;
@@ -109,13 +110,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
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 b7c1603..14a1b3c 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -945,7 +945,7 @@ 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;
--
1.6.0.4
--
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>
next prev parent reply other threads:[~2009-09-23 23:52 UTC|newest]
Thread overview: 101+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-23 23:50 [PATCH 00/80] Kernel based checkpoint/restart [v18] Oren Laadan
2009-09-23 23:50 ` Oren Laadan [this message]
2009-09-23 23:50 ` [PATCH v18 02/80] x86: ptrace debugreg checks rewrite Oren Laadan
2009-09-23 23:50 ` [PATCH v18 03/80] c/r: break out new_user_ns() Oren Laadan
2009-09-23 23:50 ` [PATCH v18 04/80] c/r: split core function out of some set*{u,g}id functions Oren Laadan
2009-09-23 23:50 ` [PATCH v18 05/80] cgroup freezer: Fix buggy resume test for tasks frozen with cgroup freezer Oren Laadan
2009-09-23 23:50 ` [PATCH v18 06/80] cgroup freezer: Update stale locking comments Oren Laadan
2009-09-23 23:50 ` [PATCH v18 07/80] cgroup freezer: Add CHECKPOINTING state to safeguard container checkpoint Oren Laadan
2009-09-23 23:50 ` [PATCH v18 08/80] cgroup freezer: interface to freeze a cgroup from within the kernel Oren Laadan
2009-09-23 23:50 ` [PATCH v18 09/80] Namespaces submenu Oren Laadan
2009-09-23 23:50 ` [PATCH v18 10/80] c/r: make file_pos_read/write() public Oren Laadan
2009-09-23 23:50 ` [PATCH v18 11/80] pids 1/7: Factor out code to allocate pidmap page Oren Laadan
2009-09-23 23:50 ` [PATCH v18 12/80] pids 2/7: Have alloc_pidmap() return actual error code Oren Laadan
2009-09-23 23:50 ` [PATCH v18 13/80] pids 3/7: Add target_pid parameter to alloc_pidmap() Oren Laadan
2009-09-23 23:50 ` [PATCH v18 14/80] pids 4/7: Add target_pids parameter to alloc_pid() Oren Laadan
2009-09-23 23:50 ` [PATCH v18 15/80] pids 5/7: Add target_pids parameter to copy_process() Oren Laadan
2009-09-23 23:50 ` [PATCH v18 16/80] pids 6/7: Define do_fork_with_pids() Oren Laadan
2009-09-23 23:50 ` [PATCH v18 17/80] pids 7/7: Define clone_with_pids syscall Oren Laadan
2009-09-23 23:50 ` [PATCH v18 18/80] c/r: create syscalls: sys_checkpoint, sys_restart Oren Laadan
2009-09-23 23:50 ` [PATCH v18 19/80] c/r: documentation Oren Laadan
2009-09-23 23:51 ` [PATCH v18 20/80] c/r: basic infrastructure for checkpoint/restart Oren Laadan
2009-09-24 16:03 ` Daniel Walker
2009-09-24 17:33 ` Oren Laadan
2009-09-23 23:51 ` [PATCH v18 21/80] c/r: x86_32 support " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 22/80] c/r: external checkpoint of a task other than ourself Oren Laadan
2009-09-23 23:51 ` [PATCH v18 23/80] c/r: export functionality used in next patch for restart-blocks Oren Laadan
2009-09-23 23:51 ` [PATCH v18 24/80] c/r: restart-blocks Oren Laadan
2009-09-23 23:51 ` [PATCH v18 25/80] c/r: checkpoint multiple processes Oren Laadan
2009-09-23 23:51 ` [PATCH v18 26/80] c/r: restart " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 27/80] c/r: introduce PF_RESTARTING, and skip notification on exit Oren Laadan
2009-09-23 23:51 ` [PATCH v18 28/80] c/r: support for zombie processes Oren Laadan
2009-09-23 23:51 ` [PATCH v18 29/80] c/r: Save and restore the [compat_]robust_list member of the task struct Oren Laadan
2009-09-23 23:51 ` [PATCH v18 30/80] c/r: infrastructure for shared objects Oren Laadan
2009-09-23 23:51 ` [PATCH v18 31/80] c/r: detect resource leaks for whole-container checkpoint Oren Laadan
2009-09-23 23:51 ` [PATCH v18 32/80] deferqueue: generic queue to defer work Oren Laadan
2009-09-23 23:51 ` [PATCH v18 33/80] c/r: introduce new 'file_operations': ->checkpoint, ->collect() Oren Laadan
2009-09-23 23:51 ` [PATCH v18 34/80] c/r: dump open file descriptors Oren Laadan
2009-09-23 23:51 ` [PATCH v18 35/80] c/r: restore " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 36/80] c/r: introduce method '->checkpoint()' in struct vm_operations_struct Oren Laadan
2009-09-23 23:51 ` [PATCH v18 37/80] c/r: dump memory address space (private memory) Oren Laadan
2009-09-23 23:51 ` [PATCH v18 38/80] c/r: restore " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 39/80] c/r: add generic '->checkpoint' f_op to ext fses Oren Laadan
2009-09-23 23:51 ` [PATCH v18 40/80] c/r: add generic '->checkpoint()' f_op to simple devices Oren Laadan
2009-09-23 23:51 ` [PATCH v18 41/80] Add the checkpoint operation for opened files of generic filesystems Oren Laadan
2009-09-23 23:51 ` [PATCH v18 42/80] c/r: export shmem_getpage() to support shared memory Oren Laadan
2009-09-23 23:51 ` [PATCH v18 43/80] c/r: dump anonymous- and file-mapped- " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 44/80] c/r: restore " Oren Laadan
2009-09-23 23:51 ` [PATCH v18 45/80] splice: export pipe/file-to-pipe/file functionality Oren Laadan
2009-09-23 23:51 ` [PATCH v18 46/80] c/r: support for open pipes Oren Laadan
2009-09-23 23:51 ` [PATCH v18 47/80] c/r: checkpoint and restore FIFOs Oren Laadan
2009-09-23 23:51 ` [PATCH v18 48/80] c/r: make ckpt_may_checkpoint_task() check each namespace individually Oren Laadan
2009-09-23 23:51 ` [PATCH v18 49/80] c/r: support for UTS namespace Oren Laadan
2009-09-29 18:13 ` Nikita V. Youshchenko
2009-09-29 18:51 ` Serge E. Hallyn
2009-09-29 23:01 ` Oren Laadan
2009-09-23 23:51 ` [PATCH v18 50/80] c/r (ipc): allow allocation of a desired ipc identifier Oren Laadan
2009-09-23 23:51 ` [PATCH v18 51/80] c/r: save and restore sysvipc namespace basics Oren Laadan
2009-09-23 23:51 ` [PATCH v18 52/80] c/r: support share-memory sysv-ipc Oren Laadan
2009-09-23 23:51 ` [PATCH v18 53/80] c/r: support message-queues sysv-ipc Oren Laadan
2009-09-23 23:51 ` [PATCH v18 54/80] c/r: support semaphore sysv-ipc Oren Laadan
2009-09-23 23:51 ` [PATCH v18 55/80] c/r: (s390): expose a constant for the number of words (CRs) Oren Laadan
2009-09-23 23:51 ` [PATCH v18 56/80] c/r: add CKPT_COPY() macro Oren Laadan
2009-09-23 23:51 ` [PATCH v18 57/80] c/r: define s390-specific checkpoint-restart code Oren Laadan
2009-09-23 23:51 ` [PATCH v18 58/80] c/r: clone_with_pids: define the s390 syscall Oren Laadan
2009-09-23 23:51 ` [PATCH v18 59/80] c/r: capabilities: define checkpoint and restore fns Oren Laadan
2009-09-23 23:51 ` [PATCH v18 60/80] c/r: checkpoint and restore task credentials Oren Laadan
2009-09-23 23:51 ` [PATCH v18 61/80] c/r: restore file->f_cred Oren Laadan
2009-09-23 23:51 ` [PATCH v18 62/80] c/r: checkpoint and restore (shared) task's sighand_struct Oren Laadan
2009-09-23 23:51 ` [PATCH v18 63/80] c/r: [signal 1/4] blocked and template for shared signals Oren Laadan
2009-09-23 23:51 ` [PATCH v18 64/80] c/r: [signal 2/4] checkpoint/restart of rlimit Oren Laadan
2009-09-23 23:51 ` [PATCH v18 65/80] c/r: [signal 3/4] pending signals (private, shared) Oren Laadan
2009-09-23 23:51 ` [PATCH v18 66/80] c/r: [signal 4/4] support for real/virt/prof itimers Oren Laadan
2009-09-23 23:51 ` [PATCH v18 67/80] Expose may_setuid() in user.h and add may_setgid() (v2) Oren Laadan
2009-09-23 23:51 ` [PATCH v18 68/80] Add common socket helpers to unify the security hooks Oren Laadan
2009-09-23 23:51 ` [PATCH v18 69/80] c/r: introduce checkpoint/restore methods to struct proto_ops Oren Laadan
2009-09-23 23:51 ` [PATCH v18 70/80] c/r: Add AF_UNIX support (v12) Oren Laadan
2009-09-23 23:51 ` [PATCH v18 71/80] c/r: [pty 1/2] allow allocation of desired pty slave Oren Laadan
2009-09-23 23:51 ` [PATCH v18 72/80] c/r: [pty 2/2] support for pseudo terminals Oren Laadan
2009-09-23 23:51 ` [PATCH v18 73/80] c/r: correctly restore pgid Oren Laadan
2009-09-23 23:51 ` [PATCH v18 74/80] c/r: support for controlling terminal and job control Oren Laadan
2009-09-23 23:51 ` [PATCH v18 75/80] powerpc: reserve checkpoint arch identifiers Oren Laadan
2009-09-23 23:51 ` [PATCH v18 76/80] powerpc: provide APIs for validating and updating DABR Oren Laadan
2009-09-23 23:51 ` [PATCH v18 77/80] powerpc: checkpoint/restart implementation Oren Laadan
2009-09-23 23:51 ` [PATCH v18 78/80] powerpc: wire up checkpoint and restart syscalls Oren Laadan
2009-09-23 23:51 ` [PATCH v18 79/80] powerpc: enable checkpoint support in Kconfig Oren Laadan
2009-09-23 23:52 ` [PATCH v18 80/80] powerpc: clone_with_pids implementation Oren Laadan
2009-09-24 13:05 ` [PATCH 00/80] Kernel based checkpoint/restart [v18] Rishikesh
2009-09-24 16:27 ` Dan Smith
2009-09-24 18:20 ` Rishikesh
2009-09-24 22:41 ` Andrew Morton
2009-09-25 13:59 ` Dan Smith
2009-09-26 14:56 ` Ingo Molnar
2009-09-28 16:37 ` Serge E. Hallyn
2009-09-29 13:29 ` Daniel Lezcano
2009-09-30 14:39 ` Dan Smith
2009-09-30 16:16 ` Daniel Lezcano
2009-09-30 16:29 ` Dan Smith
2009-09-30 18:01 ` Daniel Lezcano
2009-09-30 18:28 ` Dan Smith
2009-09-30 22:08 ` Daniel Lezcano
2009-09-29 18:31 ` Oren Laadan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1253749920-18673-2-git-send-email-orenl@librato.com \
--to=orenl@librato.com \
--cc=adobriyan@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=containers@lists.linux-foundation.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@elte.hu \
--cc=orenl@cs.columbia.edu \
--cc=serue@us.ibm.com \
--cc=torvalds@osdl.org \
--cc=xemul@openvz.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox