Commit 2aae950b authored by Andi Kleen's avatar Andi Kleen Committed by Linus Torvalds
Browse files

x86_64: Add vDSO for x86-64 with gettimeofday/clock_gettime/getcpu 



This implements new vDSO for x86-64.  The concept is similar
to the existing vDSOs on i386 and PPC.  x86-64 has had static
vsyscalls before,  but these are not flexible enough anymore.

A vDSO is a ELF shared library supplied by the kernel that is mapped into
user address space.  The vDSO mapping is randomized for each process
for security reasons.

Doing this was needed for clock_gettime, because clock_gettime
always needs a syscall fallback and having one at a fixed
address would have made buffer overflow exploits too easy to write.

The vdso can be disabled with vdso=0

It currently includes a new gettimeofday implemention and optimized
clock_gettime(). The gettimeofday implementation is slightly faster
than the one in the old vsyscall.  clock_gettime is significantly faster
than the syscall for CLOCK_MONOTONIC and CLOCK_REALTIME.

The new calls are generally faster than the old vsyscall.

Advantages over the old x86-64 vsyscalls:
- Extensible
- Randomized
- Cleaner
- Easier to virtualize (the old static address range previously causes
overhead e.g. for Xen because it has to create special page tables for it)

Weak points:
- glibc support still to be written

The VM interface is partly based on Ingo Molnar's i386 version.

Includes compile fix from Joachim Deguara

Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent a586df06

Documentation/kernel-parameters.txt

+1 −1
Original line number Diff line number Diff line
@@ -1882,7 +1882,7 @@ and is between 256 and 4096 characters. It is defined in the file 
	usbhid.mousepoll=

			[USBHID] The interval which mice are to be polled at.



	vdso=		[IA-32,SH]

	vdso=		[IA-32,SH,x86-64]

			vdso=2: enable compat VDSO (default with COMPAT_VDSO)

			vdso=1: enable VDSO (default)

			vdso=0: disable VDSO mapping

arch/x86_64/Makefile

+2 −1
Original line number Diff line number Diff line
@@ -76,7 +76,8 @@ head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kern 
libs-y 					+= arch/x86_64/lib/

core-y					+= arch/x86_64/kernel/ \

					   arch/x86_64/mm/ \

					   arch/x86_64/crypto/

					   arch/x86_64/crypto/ \

					   arch/x86_64/vdso/

core-$(CONFIG_IA32_EMULATION)		+= arch/x86_64/ia32/

drivers-$(CONFIG_PCI)			+= arch/x86_64/pci/

drivers-$(CONFIG_OPROFILE)		+= arch/x86_64/oprofile/

arch/x86_64/ia32/ia32_binfmt.c

+1 −0
Original line number Diff line number Diff line
@@ -38,6 +38,7 @@ 


int sysctl_vsyscall32 = 1;



#undef ARCH_DLINFO

#define ARCH_DLINFO do {  \

	if (sysctl_vsyscall32) { \

	NEW_AUX_ENT(AT_SYSINFO, (u32)(u64)VSYSCALL32_VSYSCALL); \

arch/x86_64/kernel/time.c

+1 −0
Original line number Diff line number Diff line
@@ -44,6 +44,7 @@ 
#include <asm/hpet.h>

#include <asm/mpspec.h>

#include <asm/nmi.h>

#include <asm/vgtod.h>



static char *timename = NULL;

arch/x86_64/kernel/vmlinux.lds.S

+9 −0
Original line number Diff line number Diff line
@@ -93,6 +93,9 @@ SECTIONS 
  .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))

		{ *(.vsyscall_gtod_data) }

  vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);

  .vsyscall_clock : AT(VLOAD(.vsyscall_clock))

		{ *(.vsyscall_clock) }

  vsyscall_clock = VVIRT(.vsyscall_clock);





  .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
@@ -189,6 +192,12 @@ SECTIONS 
  .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { *(.exit.text) }

  .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) { *(.exit.data) }



/* vdso blob that is mapped into user space */

  vdso_start = . ;

  .vdso  : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) }

  . = ALIGN(4096);

  vdso_end = .;



#ifdef CONFIG_BLK_DEV_INITRD

  . = ALIGN(4096);

  __initramfs_start = .;

CRA Git | Maintained and supported by SUSTech CRA and CCSE