x86-64: Clean up vdso/kernel shared variables
Variables that are shared between the vdso and the kernel are
currently a bit of a mess. They are each defined with their own
magic, they are accessed differently in the kernel, the vsyscall page,
and the vdso, and one of them (vsyscall_clock) doesn't even really
exist.
This changes them all to use a common mechanism. All of them are
delcared in vvar.h with a fixed address (validated by the linker
script). In the kernel (as before), they look like ordinary
read-write variables. In the vsyscall page and the vdso, they are
accessed through a new macro VVAR, which gives read-only access.
The vdso is now loaded verbatim into memory without any fixups. As a
side bonus, access from the vdso is faster because a level of
indirection is removed.
While we're at it, pack jiffies and vgetcpu_mode into the same
cacheline.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C7357882fbb51fa30491636a7b6528747301b7ee9.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 25a28a2..00cbb27 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
#include <asm/time.h>
#ifdef CONFIG_X86_64
-volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
#endif
unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 9335bf7..db697b8 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -777,8 +777,8 @@
ret = (cycle_t)vget_cycles();
rdtsc_barrier();
- return ret >= __vsyscall_gtod_data.clock.cycle_last ?
- ret : __vsyscall_gtod_data.clock.cycle_last;
+ return ret >= VVAR(vsyscall_gtod_data).clock.cycle_last ?
+ ret : VVAR(vsyscall_gtod_data).clock.cycle_last;
}
#endif
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49927a8..74b5ad4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -161,6 +161,12 @@
#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+#define EMIT_VVAR(x, offset) .vsyscall_var_ ## x \
+ ADDR(.vsyscall_0) + offset \
+ : AT(VLOAD(.vsyscall_var_ ## x)) { \
+ *(.vsyscall_var_ ## x) \
+ } \
+ x = VVIRT(.vsyscall_var_ ## x);
. = ALIGN(4096);
__vsyscall_0 = .;
@@ -175,18 +181,6 @@
*(.vsyscall_fn)
}
- . = ALIGN(L1_CACHE_BYTES);
- .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)) {
*(.vsyscall_1)
}
@@ -194,21 +188,14 @@
*(.vsyscall_2)
}
- .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
- *(.vgetcpu_mode)
- }
- vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
- . = ALIGN(L1_CACHE_BYTES);
- .jiffies : AT(VLOAD(.jiffies)) {
- *(.jiffies)
- }
- jiffies = VVIRT(.jiffies);
-
.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
*(.vsyscall_3)
}
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+
. = __vsyscall_0 + PAGE_SIZE;
#undef VSYSCALL_ADDR
@@ -216,6 +203,7 @@
#undef VLOAD
#undef VVIRT_OFFSET
#undef VVIRT
+#undef EMIT_VVAR
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index dcbb28c..5f6ad03 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -49,15 +49,8 @@
__attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
#define __syscall_clobber "r11","cx","memory"
-/*
- * vsyscall_gtod_data contains data that is :
- * - readonly from vsyscalls
- * - written by timer interrupt or systcl (/proc/sys/kernel/vsyscall64)
- * Try to keep this structure as small as possible to avoid cache line ping pongs
- */
-int __vgetcpu_mode __section_vgetcpu_mode;
-
-struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data =
+DEFINE_VVAR(int, vgetcpu_mode);
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
{
.lock = SEQLOCK_UNLOCKED,
.sysctl_enabled = 1,
@@ -97,7 +90,7 @@
*/
static __always_inline void do_get_tz(struct timezone * tz)
{
- *tz = __vsyscall_gtod_data.sys_tz;
+ *tz = VVAR(vsyscall_gtod_data).sys_tz;
}
static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
@@ -126,23 +119,24 @@
unsigned long mult, shift, nsec;
cycle_t (*vread)(void);
do {
- seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+ seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
- vread = __vsyscall_gtod_data.clock.vread;
- if (unlikely(!__vsyscall_gtod_data.sysctl_enabled || !vread)) {
+ vread = VVAR(vsyscall_gtod_data).clock.vread;
+ if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled ||
+ !vread)) {
gettimeofday(tv,NULL);
return;
}
now = vread();
- base = __vsyscall_gtod_data.clock.cycle_last;
- mask = __vsyscall_gtod_data.clock.mask;
- mult = __vsyscall_gtod_data.clock.mult;
- shift = __vsyscall_gtod_data.clock.shift;
+ base = VVAR(vsyscall_gtod_data).clock.cycle_last;
+ mask = VVAR(vsyscall_gtod_data).clock.mask;
+ mult = VVAR(vsyscall_gtod_data).clock.mult;
+ shift = VVAR(vsyscall_gtod_data).clock.shift;
- tv->tv_sec = __vsyscall_gtod_data.wall_time_sec;
- nsec = __vsyscall_gtod_data.wall_time_nsec;
- } while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+ tv->tv_sec = VVAR(vsyscall_gtod_data).wall_time_sec;
+ nsec = VVAR(vsyscall_gtod_data).wall_time_nsec;
+ } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
/* calculate interval: */
cycle_delta = (now - base) & mask;
@@ -171,15 +165,15 @@
{
unsigned seq;
time_t result;
- if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
+ if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled))
return time_syscall(t);
do {
- seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+ seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
- result = __vsyscall_gtod_data.wall_time_sec;
+ result = VVAR(vsyscall_gtod_data).wall_time_sec;
- } while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+ } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
if (t)
*t = result;
@@ -208,9 +202,9 @@
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 = __jiffies)) {
+ if (tcache && tcache->blob[0] == (j = VVAR(jiffies))) {
p = tcache->blob[1];
- } else if (__vgetcpu_mode == VGETCPU_RDTSCP) {
+ } else if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
/* Load per CPU data from RDTSCP */
native_read_tscp(&p);
} else {