2aae950b21
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: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
51 lines
1.4 KiB
C
51 lines
1.4 KiB
C
/*
|
|
* Copyright 2006 Andi Kleen, SUSE Labs.
|
|
* Subject to the GNU Public License, v.2
|
|
*
|
|
* Fast user context implementation of getcpu()
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/getcpu.h>
|
|
#include <linux/jiffies.h>
|
|
#include <linux/time.h>
|
|
#include <asm/vsyscall.h>
|
|
#include <asm/vgtod.h>
|
|
#include "vextern.h"
|
|
|
|
long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
|
|
{
|
|
unsigned int dummy, p;
|
|
unsigned long j = 0;
|
|
|
|
/* Fast cache - only recompute value once per jiffies and avoid
|
|
relatively costly rdtscp/cpuid otherwise.
|
|
This works because the scheduler usually keeps the process
|
|
on the same CPU and this syscall doesn't guarantee its
|
|
results anyways.
|
|
We do this here because otherwise user space would do it on
|
|
its own in a likely inferior way (no access to jiffies).
|
|
If you don't like it pass NULL. */
|
|
if (tcache && tcache->blob[0] == (j = *vdso_jiffies)) {
|
|
p = tcache->blob[1];
|
|
} else if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
|
|
/* Load per CPU data from RDTSCP */
|
|
rdtscp(dummy, dummy, p);
|
|
} else {
|
|
/* Load per CPU data from GDT */
|
|
asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
|
|
}
|
|
if (tcache) {
|
|
tcache->blob[0] = j;
|
|
tcache->blob[1] = p;
|
|
}
|
|
if (cpu)
|
|
*cpu = p & 0xfff;
|
|
if (node)
|
|
*node = p >> 12;
|
|
return 0;
|
|
}
|
|
|
|
long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
|
|
__attribute__((weak, alias("__vdso_getcpu")));
|