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: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 47 insertions, 1 deletions

diff --git a/include/asm-x86_64/auxvec.h b/include/asm-x86_64/auxvec.h
index 2403c4cfced..1d5ab0d0395 100644
--- a/include/asm-x86_64/auxvec.h
+++ b/include/asm-x86_64/auxvec.h
@@ -1,4 +1,6 @@
 #ifndef __ASM_X86_64_AUXVEC_H
 #define __ASM_X86_64_AUXVEC_H
 
+#define AT_SYSINFO_EHDR		33
+
 #endif
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
index 6d24ea7c4d9..b4fbe47f6cc 100644
--- a/include/asm-x86_64/elf.h
+++ b/include/asm-x86_64/elf.h
@@ -162,6 +162,19 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
 /* 1GB for 64bit, 8MB for 32bit */
 #define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
 
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+                                       int executable_stack);
+
+extern int vdso_enabled;
+
+#define ARCH_DLINFO						\
+do if (vdso_enabled) {						\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,(unsigned long)current->mm->context.vdso);\
+} while (0)
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/mmu.h b/include/asm-x86_64/mmu.h
index 5dc6ed79859..d2cd4a9d984 100644
--- a/include/asm-x86_64/mmu.h
+++ b/include/asm-x86_64/mmu.h
@@ -15,6 +15,7 @@ typedef struct {
 	rwlock_t ldtlock; 
 	int size;
 	struct semaphore sem; 
+	void *vdso;
 } mm_context_t;
 
 #endif
diff --git a/include/asm-x86_64/vgtod.h b/include/asm-x86_64/vgtod.h
new file mode 100644
index 00000000000..3301f092934
--- /dev/null
+++ b/include/asm-x86_64/vgtod.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_VGTOD_H
+#define _ASM_VGTOD_H 1
+
+#include <asm/vsyscall.h>
+#include <linux/clocksource.h>
+
+struct vsyscall_gtod_data {
+	seqlock_t	lock;
+
+	/* open coded 'struct timespec' */
+	time_t		wall_time_sec;
+	u32		wall_time_nsec;
+
+	int		sysctl_enabled;
+	struct timezone sys_tz;
+	struct { /* extract of a clocksource struct */
+		cycle_t (*vread)(void);
+		cycle_t	cycle_last;
+		cycle_t	mask;
+		u32	mult;
+		u32	shift;
+	} clock;
+	struct timespec wall_to_monotonic;
+};
+extern struct vsyscall_gtod_data __vsyscall_gtod_data
+__section_vsyscall_gtod_data;
+extern struct vsyscall_gtod_data vsyscall_gtod_data;
+
+#endif
diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h
index 82b4afe65c9..3b8ceb4af2c 100644
--- a/include/asm-x86_64/vsyscall.h
+++ b/include/asm-x86_64/vsyscall.h
@@ -22,6 +22,8 @@ enum vsyscall_num {
 /* Definitions for CONFIG_GENERIC_TIME definitions */
 #define __section_vsyscall_gtod_data __attribute__ \
 	((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
+#define __section_vsyscall_clock __attribute__ \
+	((unused, __section__ (".vsyscall_clock"),aligned(16)))
 #define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn")))
 
 #define VGETCPU_RDTSCP	1
@@ -36,7 +38,6 @@ extern volatile unsigned long __jiffies;
 /* kernel space (writeable) */
 extern int vgetcpu_mode;
 extern struct timezone sys_tz;
-extern struct vsyscall_gtod_data_t vsyscall_gtod_data;
 
 #endif /* __KERNEL__ */