[PATCH v20 09/10] Add 32 bit VDSO time support for 64 bit kernel

From: Stefani Seibold
Date: Wed Feb 19 2014 - 04:13:03 EST

This patch add the VDSO time support for the IA32 Emulation Layer.

Due the nature of the kernel headers and the LP64 compiler where the
size of a long and a pointer differs against a 32 bit compiler, there
is some type hacking necessary for optimal performance.

The vsyscall_gtod_data struture must be a rearranged to serve 32- and
64-bit code access at the same time:

- The seqcount_t was replaced by an unsigned, this makes the
vsyscall_gtod_data intedepend of kernel configuration and internal functions.
- All kernel internal structures are replaced by fix size elements
which works for 32- and 64-bit access
- The inner struct clock was removed to pack the whole struct.

The "unsigned seq" would be handled by functions derivated from seqcount_t.

Signed-off-by: Stefani Seibold <stefani@xxxxxxxxxxx>
---
arch/x86/include/asm/vgtod.h | 71 +++++++++++++++++++++------
arch/x86/include/asm/vvar.h | 5 ++
arch/x86/kernel/vsyscall_gtod.c | 34 ++++++++-----
arch/x86/vdso/vclock_gettime.c | 91 +++++++++++++++++++----------------
arch/x86/vdso/vdso32/vclock_gettime.c | 21 ++++++++
5 files changed, 155 insertions(+), 67 deletions(-)

diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 46e24d3..3c3366c 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -1,30 +1,73 @@
#ifndef _ASM_X86_VGTOD_H
#define _ASM_X86_VGTOD_H

-#include <asm/vsyscall.h>
+#include <linux/compiler.h>
#include <linux/clocksource.h>

+#ifdef BUILD_VDSO32_64
+typedef u64 gtod_long_t;
+#else
+typedef unsigned long gtod_long_t;
+#endif
+/*
+ * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
+ * so be carefull by modifying this structure.
+ */
struct vsyscall_gtod_data {
- seqcount_t seq;
+ unsigned seq;

- struct { /* extract of a clocksource struct */
- int vclock_mode;
- cycle_t cycle_last;
- cycle_t mask;
- u32 mult;
- u32 shift;
- } clock;
+ int vclock_mode;
+ cycle_t cycle_last;
+ cycle_t mask;
+ u32 mult;
+ u32 shift;

/* open coded 'struct timespec' */
- time_t wall_time_sec;
u64 wall_time_snsec;
+ gtod_long_t wall_time_sec;
+ gtod_long_t monotonic_time_sec;
u64 monotonic_time_snsec;
- time_t monotonic_time_sec;
+ gtod_long_t wall_time_coarse_sec;
+ gtod_long_t wall_time_coarse_nsec;
+ gtod_long_t monotonic_time_coarse_sec;
+ gtod_long_t monotonic_time_coarse_nsec;

- struct timezone sys_tz;
- struct timespec wall_time_coarse;
- struct timespec monotonic_time_coarse;
+ int tz_minuteswest;
+ int tz_dsttime;
};
extern struct vsyscall_gtod_data vsyscall_gtod_data;

+static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
+{
+ unsigned ret;
+
+repeat:
+ ret = ACCESS_ONCE(s->seq);
+ if (unlikely(ret & 1)) {
+ cpu_relax();
+ goto repeat;
+ }
+ smp_rmb();
+ return ret;
+}
+
+static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
+ unsigned start)
+{
+ smp_rmb();
+ return unlikely(s->seq != start);
+}
+
+static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
+{
+ ++s->seq;
+ smp_wmb();
+}
+
+static inline void gtod_write_end(struct vsyscall_gtod_data *s)
+{
+ smp_wmb();
+ ++s->seq;
+}
+
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 52c79ff..081d909 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -16,6 +16,9 @@
* you mess up, the linker will catch it.)
*/

+#ifndef _ASM_X86_VVAR_H
+#define _ASM_X86_VVAR_H
+
#if defined(__VVAR_KERNEL_LDS)

/* The kernel linker script defines its own magic to put vvars in the
@@ -64,3 +67,5 @@ DECLARE_VVAR(16, int, vgetcpu_mode)
DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)

#undef DECLARE_VVAR
+
+#endif
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index 91862a4..eacd12f 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -4,6 +4,7 @@
*
* Modified for x86 32 bit architecture by
* Stefani Seibold <stefani@xxxxxxxxxxx>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
*
* Thanks to hpa@xxxxxxxxxxxxx for some useful hint.
* Special thanks to Ingo Molnar for his early experience with
@@ -13,26 +14,28 @@

#include <linux/timekeeper_internal.h>
#include <asm/vgtod.h>
+#include <asm/vvar.h>

DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);

void update_vsyscall_tz(void)
{
- vsyscall_gtod_data.sys_tz = sys_tz;
+ vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
+ vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
}

void update_vsyscall(struct timekeeper *tk)
{
struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;

- write_seqcount_begin(&vdata->seq);
+ gtod_write_begin(vdata);

/* copy vsyscall data */
- vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode;
- vdata->clock.cycle_last = tk->clock->cycle_last;
- vdata->clock.mask = tk->clock->mask;
- vdata->clock.mult = tk->mult;
- vdata->clock.shift = tk->shift;
+ vdata->vclock_mode = tk->clock->archdata.vclock_mode;
+ vdata->cycle_last = tk->clock->cycle_last;
+ vdata->mask = tk->clock->mask;
+ vdata->mult = tk->mult;
+ vdata->shift = tk->shift;

vdata->wall_time_sec = tk->xtime_sec;
vdata->wall_time_snsec = tk->xtime_nsec;
@@ -49,12 +52,19 @@ void update_vsyscall(struct timekeeper *tk)
vdata->monotonic_time_sec++;
}

- vdata->wall_time_coarse.tv_sec = tk->xtime_sec;
- vdata->wall_time_coarse.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
+ vdata->wall_time_coarse_sec = tk->xtime_sec;
+ vdata->wall_time_coarse_nsec = (long)(tk->xtime_nsec >> tk->shift);

- vdata->monotonic_time_coarse = timespec_add(vdata->wall_time_coarse,
- tk->wall_to_monotonic);
+ vdata->monotonic_time_coarse_sec =
+ vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_coarse_nsec =
+ vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;

- write_seqcount_end(&vdata->seq);
+ while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
+ vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
+ vdata->monotonic_time_coarse_sec++;
+ }
+
+ gtod_write_end(vdata);
}

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index fcbc974..828888e 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -14,16 +14,14 @@
/* Disable profiling for userspace code: */
#define DISABLE_BRANCH_PROFILING

-#include <linux/kernel.h>
#include <uapi/linux/time.h>
-#include <linux/string.h>
-#include <asm/vsyscall.h>
-#include <asm/fixmap.h>
#include <asm/vgtod.h>
#include <asm/hpet.h>
+#include <asm/vvar.h>
#include <asm/unistd.h>
-#include <asm/io.h>
-#include <asm/pvclock.h>
+#include <asm/msr.h>
+#include <linux/math64.h>
+#include <linux/time.h>

#define gtod (&VVAR(vsyscall_gtod_data))

@@ -31,11 +29,23 @@ extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
extern time_t __vdso_time(time_t *t);

+#ifdef CONFIG_HPET_TIMER
+static inline u32 read_hpet_counter(const volatile void *addr)
+{
+ return *(const volatile u32 *) (addr + HPET_COUNTER);
+}
+#endif
+
#ifndef BUILD_VDSO32

+#include <linux/kernel.h>
+#include <asm/vsyscall.h>
+#include <asm/fixmap.h>
+#include <asm/pvclock.h>
+
static notrace cycle_t vread_hpet(void)
{
- return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
+ return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET));
}

notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -116,7 +126,7 @@ static notrace cycle_t vread_pvclock(int *mode)
*mode = VCLOCK_NONE;

/* refer to tsc.c read_tsc() comment for rationale */
- last = gtod->clock.cycle_last;
+ last = gtod->cycle_last;

if (likely(ret >= last))
return ret;
@@ -133,7 +143,7 @@ extern u8 hpet_page
#ifdef CONFIG_HPET_TIMER
static notrace cycle_t vread_hpet(void)
{
- return readl((const void __iomem *)(&hpet_page + HPET_COUNTER));
+ return read_hpet_counter((const void *)(&hpet_page));
}
#endif

@@ -193,7 +203,7 @@ notrace static cycle_t vread_tsc(void)
rdtsc_barrier();
ret = (cycle_t)__native_read_tsc();

- last = gtod->clock.cycle_last;
+ last = gtod->cycle_last;

if (likely(ret >= last))
return ret;
@@ -214,20 +224,21 @@ notrace static inline u64 vgetsns(int *mode)
{
u64 v;
cycles_t cycles;
- if (gtod->clock.vclock_mode == VCLOCK_TSC)
+
+ if (gtod->vclock_mode == VCLOCK_TSC)
cycles = vread_tsc();
#ifdef CONFIG_HPET_TIMER
- else if (gtod->clock.vclock_mode == VCLOCK_HPET)
+ else if (gtod->vclock_mode == VCLOCK_HPET)
cycles = vread_hpet();
#endif
#ifdef CONFIG_PARAVIRT_CLOCK
- else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK)
+ else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
cycles = vread_pvclock(mode);
#endif
else
return 0;
- v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
- return v * gtod->clock.mult;
+ v = (cycles - gtod->cycle_last) & gtod->mask;
+ return v * gtod->mult;
}

/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
@@ -237,17 +248,18 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
u64 ns;
int mode;

- ts->tv_nsec = 0;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- mode = gtod->clock.vclock_mode;
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
ts->tv_sec = gtod->wall_time_sec;
ns = gtod->wall_time_snsec;
ns += vgetsns(&mode);
- ns >>= gtod->clock.shift;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;

- timespec_add_ns(ts, ns);
return mode;
}

@@ -257,16 +269,17 @@ notrace static int do_monotonic(struct timespec *ts)
u64 ns;
int mode;

- ts->tv_nsec = 0;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- mode = gtod->clock.vclock_mode;
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
ts->tv_sec = gtod->monotonic_time_sec;
ns = gtod->monotonic_time_snsec;
ns += vgetsns(&mode);
- ns >>= gtod->clock.shift;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
- timespec_add_ns(ts, ns);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;

return mode;
}
@@ -275,20 +288,20 @@ notrace static void do_realtime_coarse(struct timespec *ts)
{
unsigned long seq;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- ts->tv_sec = gtod->wall_time_coarse.tv_sec;
- ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->wall_time_coarse_sec;
+ ts->tv_nsec = gtod->wall_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
}

notrace static void do_monotonic_coarse(struct timespec *ts)
{
unsigned long seq;
do {
- seq = raw_read_seqcount_begin(&gtod->seq);
- ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
- ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->monotonic_time_coarse_sec;
+ ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
}

notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
@@ -322,17 +335,13 @@ int clock_gettime(clockid_t, struct timespec *)
notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
{
if (likely(tv != NULL)) {
- BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
- offsetof(struct timespec, tv_nsec) ||
- sizeof(*tv) != sizeof(struct timespec));
if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
return vdso_fallback_gtod(tv, tz);
tv->tv_usec /= 1000;
}
if (unlikely(tz != NULL)) {
- /* Avoid memcpy. Some old compilers fail to inline it */
- tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
- tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
+ tz->tz_minuteswest = gtod->tz_minuteswest;
+ tz->tz_dsttime = gtod->tz_dsttime;
}

return 0;
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/vdso/vdso32/vclock_gettime.c
index d9bb9fc..867c21d 100644
--- a/arch/x86/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/vdso/vdso32/vclock_gettime.c
@@ -1,4 +1,25 @@
#define BUILD_VDSO32

+#ifdef CONFIG_X86_64
+
+/*
+ * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration
+ */
+#undef CONFIG_64BIT
+#undef CONFIG_X86_64
+#undef CONFIG_ILLEGAL_POINTER_VALUE
+#undef CONFIG_SPARSEMEM_VMEMMAP
+#undef CONFIG_NR_CPUS
+
+#define CONFIG_X86_32 1
+#define CONFIG_PAGE_OFFSET 0
+#define CONFIG_ILLEGAL_POINTER_VALUE 0
+#define CONFIG_NR_CPUS 1
+
+#define BUILD_VDSO32_64
+
+#endif
+
#include "../vclock_gettime.c"

--
1.8.5.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/