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>

4 files changed, 34 insertions, 52 deletions

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 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	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 @@ SECTIONS
 
 #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 @@ SECTIONS
 		*(.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 @@ SECTIONS
 		*(.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 @@ SECTIONS
 #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 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
  */
 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 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 	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 @@ time_t __vsyscall(1) vtime(time_t *t)
 {
 	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 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 	   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 {