Architectures such as i386, sh, x86_64 have a flag /proc/sys/vm/vdso_enabled
to choose whether the kernel should setup a process to use vdso after execve().
Informing the user code via AT_SYSINFO* is controlled by macro ARCH_DLINFO in
fs/binfmt_elf.c and include/asm-$ARCH/elf.h, but the vdso page is established
always via arch_setup_additonal_pages() called from load_elf_binary().
If vdso_enabled is off, then current code wastes kernel time during execve()
and fragments the address space unnecessarily.
This patch changes arch_setup_additonal_pages() to honor vdso_enabled.
For i386 it also allows the option of a fixed addresss to avoid
fragmenting the address space. Compiles and runs on i386.
x86_64 [IA32 support] and sh maintainers also please comment.
For some related history, including interaction with exec-shield, see:
http://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=229304
and also 207020 and 162797.
Signed-off-by: John Reiser <[email protected]>
diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c
index 13ca54a..f8c4d76 100644
--- a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -22,6 +22,8 @@
#include <asm/msr.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>
+#include <asm/a.out.h>
+#include <asm/mman.h>
/*
* Should the kernel map a VDSO page into processes and pass its
@@ -105,10 +107,25 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
+ unsigned long flags;
int ret;
+ switch (vdso_enabled) {
+ case 0: /* none */
+ return 0;
+ default:
+ case 1: /* vdso in random available page */
+ addr = 0ul;
+ flags = 0ul;
+ break;
+ case 2: /* out of user's way */
+ addr = STACK_TOP;
+ flags = MAP_FIXED;
+ break;
+ }
+
down_write(&mm->mmap_sem);
- addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+ addr = get_unmapped_area(NULL, addr, PAGE_SIZE, 0, flags);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index 7b0f66f..2b789fb 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -64,6 +64,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
unsigned long addr;
int ret;
+ if (!vdso_enabled)
+ return 0;
+
down_write(&mm->mmap_sem);
addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
if (IS_ERR_VALUE(addr)) {
diff --git a/include/asm-i386/a.out.h b/include/asm-i386/a.out.h
index ab17bb8..9894f73 100644
--- a/include/asm-i386/a.out.h
+++ b/include/asm-i386/a.out.h
@@ -19,7 +19,7 @@ struct exec
#ifdef __KERNEL__
-#define STACK_TOP TASK_SIZE
+#define STACK_TOP (TASK_SIZE - PAGE_SIZE) /* 1 page optional for vdso */
#endif
--
On Thu, Feb 22, 2007 at 12:31:20PM -0800, John Reiser wrote:
> This patch changes arch_setup_additonal_pages() to honor vdso_enabled.
> For i386 it also allows the option of a fixed addresss to avoid
> fragmenting the address space. Compiles and runs on i386.
> x86_64 [IA32 support] and sh maintainers also please comment.
>
We didn't actually have the sysctl entry wired up on SH, but once that's
done, this patch works fine there too.
Andrew, do you want a separate patch for the vdso_enabled sysctl or
is it more convenient through my git tree?
Acked-by: Paul Mundt <[email protected]>
[adding Andi and Ingo]
John Reiser wrote:
> Architectures such as i386, sh, x86_64 have a flag /proc/sys/vm/vdso_enabled
> to choose whether the kernel should setup a process to use vdso after execve().
> Informing the user code via AT_SYSINFO* is controlled by macro ARCH_DLINFO in
> fs/binfmt_elf.c and include/asm-$ARCH/elf.h, but the vdso page is established
> always via arch_setup_additonal_pages() called from load_elf_binary().
> If vdso_enabled is off, then current code wastes kernel time during execve()
> and fragments the address space unnecessarily.
>
> This patch changes arch_setup_additonal_pages() to honor vdso_enabled.
> For i386 it also allows the option of a fixed addresss to avoid
> fragmenting the address space. Compiles and runs on i386.
> x86_64 [IA32 support] and sh maintainers also please comment.
>
> For some related history, including interaction with exec-shield, see:
> http://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=229304
> and also 207020 and 162797.
>
>
> Signed-off-by: John Reiser <[email protected]>
>
> diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c
> index 13ca54a..f8c4d76 100644
> --- a/arch/i386/kernel/sysenter.c
> +++ b/arch/i386/kernel/sysenter.c
> @@ -22,6 +22,8 @@
> #include <asm/msr.h>
> #include <asm/pgtable.h>
> #include <asm/unistd.h>
> +#include <asm/a.out.h>
> +#include <asm/mman.h>
>
> /*
> * Should the kernel map a VDSO page into processes and pass its
> @@ -105,10 +107,25 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
> {
> struct mm_struct *mm = current->mm;
> unsigned long addr;
> + unsigned long flags;
> int ret;
>
> + switch (vdso_enabled) {
> + case 0: /* none */
> + return 0;
> + default:
> + case 1: /* vdso in random available page */
> + addr = 0ul;
> + flags = 0ul;
> + break;
> + case 2: /* out of user's way */
> + addr = STACK_TOP;
> + flags = MAP_FIXED;
> + break;
> + }
> +
> down_write(&mm->mmap_sem);
> - addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
> + addr = get_unmapped_area(NULL, addr, PAGE_SIZE, 0, flags);
> if (IS_ERR_VALUE(addr)) {
> ret = addr;
> goto up_fail;
> diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
> index 7b0f66f..2b789fb 100644
> --- a/arch/sh/kernel/vsyscall/vsyscall.c
> +++ b/arch/sh/kernel/vsyscall/vsyscall.c
> @@ -64,6 +64,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
> unsigned long addr;
> int ret;
>
> + if (!vdso_enabled)
> + return 0;
> +
> down_write(&mm->mmap_sem);
> addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
> if (IS_ERR_VALUE(addr)) {
> diff --git a/include/asm-i386/a.out.h b/include/asm-i386/a.out.h
> index ab17bb8..9894f73 100644
> --- a/include/asm-i386/a.out.h
> +++ b/include/asm-i386/a.out.h
> @@ -19,7 +19,7 @@ struct exec
>
> #ifdef __KERNEL__
>
> -#define STACK_TOP TASK_SIZE
> +#define STACK_TOP (TASK_SIZE - PAGE_SIZE) /* 1 page optional for vdso */
>
> #endif
>
On Wed, 28 Feb 2007 18:11:11 +0900
Paul Mundt <[email protected]> wrote:
> On Thu, Feb 22, 2007 at 12:31:20PM -0800, John Reiser wrote:
> > This patch changes arch_setup_additonal_pages() to honor vdso_enabled.
> > For i386 it also allows the option of a fixed addresss to avoid
> > fragmenting the address space. Compiles and runs on i386.
> > x86_64 [IA32 support] and sh maintainers also please comment.
> >
> We didn't actually have the sysctl entry wired up on SH, but once that's
> done, this patch works fine there too.
>
> Andrew, do you want a separate patch for the vdso_enabled sysctl or
> is it more convenient through my git tree?
>
If it's an sh-only thing then through your tree is fine, thanks.