[PATCH] time: x86_64: re-enable vsyscall support for x86_64

Cleanup and re-enable vsyscall gettimeofday using the generic clocksource
infrastructure.

[akpm@osdl.org: cleanup]
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@muc.de>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 100 insertions, 72 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 286b4606fb1e..56eb14c98475 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -28,6 +28,10 @@ config GENERIC_TIME
         bool
         default y
 
+config GENERIC_TIME_VSYSCALL
+        bool
+        default y
+
 config ZONE_DMA32
         bool
         default y
diff --git a/arch/x86_64/kernel/hpet.c b/arch/x86_64/kernel/hpet.c
index c23738899ae9..65a0edd71a17 100644
--- a/arch/x86_64/kernel/hpet.c
+++ b/arch/x86_64/kernel/hpet.c
@@ -458,6 +458,11 @@ static cycle_t read_hpet(void)
         return (cycle_t)readl(hpet_ptr);
 }
 
+static cycle_t __vsyscall_fn vread_hpet(void)
+{
+        return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
+}
+
 struct clocksource clocksource_hpet = {
         .name           = "hpet",
         .rating         = 250,
@@ -466,6 +471,7 @@ struct clocksource clocksource_hpet = {
         .mult           = 0, /* set below */
         .shift          = HPET_SHIFT,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+        .vread          = vread_hpet,
 };
 
 static int __init init_hpet_clocksource(void)
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index d84208e3c618..a87c51705620 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -53,13 +53,7 @@ DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 DEFINE_SPINLOCK(i8253_lock);
 
-unsigned long vxtime_hz = PIT_TICK_RATE;
-
-struct vxtime_data __vxtime __section_vxtime;   /* for vsyscalls */
-
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
-struct timespec __xtime __section_xtime;
-struct timezone __sys_tz __section_sys_tz;
 
 unsigned long profile_pc(struct pt_regs *regs)
 {
diff --git a/arch/x86_64/kernel/tsc.c b/arch/x86_64/kernel/tsc.c
index 8c92f2fe7e2e..895831865019 100644
--- a/arch/x86_64/kernel/tsc.c
+++ b/arch/x86_64/kernel/tsc.c
@@ -180,6 +180,12 @@ static cycle_t read_tsc(void)
         return ret;
 }
 
+static cycle_t __vsyscall_fn vread_tsc(void)
+{
+        cycle_t ret = (cycle_t)get_cycles_sync();
+        return ret;
+}
+
 static struct clocksource clocksource_tsc = {
         .name                   = "tsc",
         .rating                 = 300,
@@ -188,6 +194,7 @@ static struct clocksource clocksource_tsc = {
         .shift                  = 22,
         .flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
                                   CLOCK_SOURCE_MUST_VERIFY,
+        .vread                  = vread_tsc,
 };
 
 void mark_tsc_unstable(void)
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index c360c4225244..b73212c0a550 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -88,31 +88,25 @@ SECTIONS
   __vsyscall_0 = VSYSCALL_VIRT_ADDR;
 
   . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .xtime_lock : AT(VLOAD(.xtime_lock)) { *(.xtime_lock) }
-  xtime_lock = VVIRT(.xtime_lock);
-
-  .vxtime : AT(VLOAD(.vxtime)) { *(.vxtime) }
-  vxtime = VVIRT(.vxtime);
+  .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
+  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+  .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
+                { *(.vsyscall_gtod_data) }
+  vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
 
   .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
   vgetcpu_mode = VVIRT(.vgetcpu_mode);
 
-  .sys_tz : AT(VLOAD(.sys_tz)) { *(.sys_tz) }
-  sys_tz = VVIRT(.sys_tz);
-
-  .sysctl_vsyscall : AT(VLOAD(.sysctl_vsyscall)) { *(.sysctl_vsyscall) }
-  sysctl_vsyscall = VVIRT(.sysctl_vsyscall);
-
-  .xtime : AT(VLOAD(.xtime)) { *(.xtime) }
-  xtime = VVIRT(.xtime);
-
   . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
   .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
   jiffies = VVIRT(.jiffies);
 
-  .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) { *(.vsyscall_1) }
-  .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) { *(.vsyscall_2) }
-  .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) { *(.vsyscall_3) }
+  .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
+                { *(.vsyscall_1) }
+  .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
+                { *(.vsyscall_2) }
+  .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
+                { *(.vsyscall_3) }
 
   . = VSYSCALL_VIRT_ADDR + 4096;
 
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index 313dc6ad780b..180ff919eaf9 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -26,6 +26,7 @@
 #include <linux/seqlock.h>
 #include <linux/jiffies.h>
 #include <linux/sysctl.h>
+#include <linux/clocksource.h>
 #include <linux/getcpu.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
@@ -34,6 +35,7 @@
 #include <asm/vsyscall.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/errno.h>
 #include <asm/io.h>
@@ -44,56 +46,41 @@
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","rcx","memory"
 
-int __sysctl_vsyscall __section_sysctl_vsyscall = 1;
-seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED;
+struct vsyscall_gtod_data_t {
+        seqlock_t lock;
+        int sysctl_enabled;
+        struct timeval wall_time_tv;
+        struct timezone sys_tz;
+        cycle_t offset_base;
+        struct clocksource clock;
+};
 int __vgetcpu_mode __section_vgetcpu_mode;
 
-#include <asm/unistd.h>
-
-static __always_inline void timeval_normalize(struct timeval * tv)
+struct vsyscall_gtod_data_t __vsyscall_gtod_data __section_vsyscall_gtod_data =
 {
-        time_t __sec;
-
-        __sec = tv->tv_usec / 1000000;
-        if (__sec) {
-                tv->tv_usec %= 1000000;
-                tv->tv_sec += __sec;
-        }
-}
+        .lock = SEQLOCK_UNLOCKED,
+        .sysctl_enabled = 1,
+};
 
-static __always_inline void do_vgettimeofday(struct timeval * tv)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 {
-        long sequence, t;
-        unsigned long sec, usec;
-
-        do {
-                sequence = read_seqbegin(&__xtime_lock);
-                
-                sec = __xtime.tv_sec;
-                usec = __xtime.tv_nsec / 1000;
-
-                if (__vxtime.mode != VXTIME_HPET) {
-                        t = get_cycles_sync();
-                        if (t < __vxtime.last_tsc)
-                                t = __vxtime.last_tsc;
-                        usec += ((t - __vxtime.last_tsc) *
-                                 __vxtime.tsc_quot) >> 32;
-                        /* See comment in x86_64 do_gettimeofday. */
-                } else {
-                        usec += ((readl((void __iomem *)
-                                   fix_to_virt(VSYSCALL_HPET) + 0xf0) -
-                                  __vxtime.last) * __vxtime.quot) >> 32;
-                }
-        } while (read_seqretry(&__xtime_lock, sequence));
-
-        tv->tv_sec = sec + usec / 1000000;
-        tv->tv_usec = usec % 1000000;
+        unsigned long flags;
+
+        write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+        /* copy vsyscall data */
+        vsyscall_gtod_data.clock = *clock;
+        vsyscall_gtod_data.wall_time_tv.tv_sec = wall_time->tv_sec;
+        vsyscall_gtod_data.wall_time_tv.tv_usec = wall_time->tv_nsec/1000;
+        vsyscall_gtod_data.sys_tz = sys_tz;
+        write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
-/* RED-PEN may want to readd seq locking, but then the variable should be write-once. */
+/* RED-PEN may want to readd seq locking, but then the variable should be
+ * write-once.
+ */
 static __always_inline void do_get_tz(struct timezone * tz)
 {
-        *tz = __sys_tz;
+        *tz = __vsyscall_gtod_data.sys_tz;
 }
 
 static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
@@ -101,7 +88,8 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
         int ret;
         asm volatile("vsysc2: syscall"
                 : "=a" (ret)
-                : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber );
+                : "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
+                : __syscall_clobber );
         return ret;
 }
 
@@ -114,10 +102,44 @@ static __always_inline long time_syscall(long *t)
         return secs;
 }
 
+static __always_inline void do_vgettimeofday(struct timeval * tv)
+{
+        cycle_t now, base, mask, cycle_delta;
+        unsigned long seq, mult, shift, nsec_delta;
+        cycle_t (*vread)(void);
+        do {
+                seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+
+                vread = __vsyscall_gtod_data.clock.vread;
+                if (unlikely(!__vsyscall_gtod_data.sysctl_enabled || !vread)) {
+                        gettimeofday(tv,0);
+                        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;
+
+                *tv = __vsyscall_gtod_data.wall_time_tv;
+
+        } while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+
+        /* calculate interval: */
+        cycle_delta = (now - base) & mask;
+        /* convert to nsecs: */
+        nsec_delta = (cycle_delta * mult) >> shift;
+
+        /* convert to usecs and add to timespec: */
+        tv->tv_usec += nsec_delta / NSEC_PER_USEC;
+        while (tv->tv_usec > USEC_PER_SEC) {
+                tv->tv_sec += 1;
+                tv->tv_usec -= USEC_PER_SEC;
+        }
+}
+
 int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
 {
-        if (!__sysctl_vsyscall)
-                return gettimeofday(tv,tz);
         if (tv)
                 do_vgettimeofday(tv);
         if (tz)
@@ -129,11 +151,11 @@ int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
  * unlikely */
 time_t __vsyscall(1) vtime(time_t *t)
 {
-        if (!__sysctl_vsyscall)
+        if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
                 return time_syscall(t);
         else if (t)
-                *t = __xtime.tv_sec;            
-        return __xtime.tv_sec;
+                *t = __vsyscall_gtod_data.wall_time_tv.tv_sec;
+        return __vsyscall_gtod_data.wall_time_tv.tv_sec;
 }
 
 /* Fast way to get current CPU and node.
@@ -210,7 +232,7 @@ static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
                 ret = -ENOMEM;
                 goto out;
         }
-        if (!sysctl_vsyscall) {
+        if (!vsyscall_gtod_data.sysctl_enabled) {
                 writew(SYSCALL, map1);
                 writew(SYSCALL, map2);
         } else {
@@ -232,7 +254,8 @@ static int vsyscall_sysctl_nostrat(ctl_table *t, int __user *name, int nlen,
 
 static ctl_table kernel_table2[] = {
         { .ctl_name = 99, .procname = "vsyscall64",
-          .data = &sysctl_vsyscall, .maxlen = sizeof(int), .mode = 0644,
+          .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int),
+          .mode = 0644,
           .strategy = vsyscall_sysctl_nostrat,
           .proc_handler = vsyscall_sysctl_change },
         {}