[PATCH v9 0/8] Add 32 bit VDSO time function support

[PATCH v9 0/8] Add 32 bit VDSO time function support

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This patch add the functions vdso_gettimeofday(), vdso_clock_gettime()
and vdso_time() to the 32 bit VDSO.

The reason to do this was to get a fast reliable time stamp. Many developers
uses TSC to get a fast time stamp, without knowing the pitfalls. VDSO
time functions a fast and a reliable way, because the kernel knows the
best time source and the P- and C-state of the CPU.

The helper library to use the VDSO functions can be download at
http://http://seibold.net/vdso.c
The libary is very small, only 228 lines of code. Compile it with
gcc -Wall -O3 -fpic vdso.c -lrt -shared -o libvdso.so
and use it with LD_PRELOAD=<path>/libvdso.so

This kind of helper must be integrated into glibc, for x86 64 bit and
PowerPC it is already there.

Some linux 32 bit kernel benchmark results (all measurements are in nano
seconds):

Intel(R) Celeron(TM) CPU 400MHz

Average time kernel call:
 gettimeofday(): 1039
 clock_gettime(): 1578
 time(): 526
Average time VDSO call:
 gettimeofday(): 378
 clock_gettime(): 303
 time(): 60

Celeron(R) Dual-Core CPU T3100 1.90GHz

Average time kernel call:
 gettimeofday(): 209
 clock_gettime(): 406
 time(): 135
Average time VDSO call:
 gettimeofday(): 51
 clock_gettime(): 43
 time(): 10

So you can see a performance increase between 4 and 13, depending on the
CPU and the function.

The address layout of the VDSO has changed, because there is no fixed
address space available on a x86 32 bit kernel, despite the name. Because
someone decided to add an offset to the __FIXADDR_TOP for virtualization.

Also the IA32 Emulation uses the whole 4 GB address space, so there is no
fixed address available.

This was the reason not depend on this kind of address and change the layout
of the VDSO. The VDSO for a 32 bit application has now three pages:

^ Higher Address
|
+----------------------------------------+
+ VDSO page (includes code) ro+x         +
+----------------------------------------+
+ VVAR page (export kernel variables) ro +
+----------------------------------------+
+ HPET page (mapped registers) ro 
+----------------------------------------+
|
^ Lower Address

The VDSO page for a 32 bit resided still on 0xffffe000, the the VVAR and
HPET page are mapped before.

In the non compat mode the VMA of the VDSO is now 3 pages for a 32 bit kernel.
So this decrease the available logical address room by 2 pages.

The patch is against kernel 3.14 (e7651b819e90da924991d727d3c007200a18670d)

Changelog:
25.11.2012 - first release and proof of concept for linux 3.4
11.12.2012 - Port to linux 3.7 and code cleanup
12.12.2012 - fixes suggested by Andy Lutomirski
           - fixes suggested by John Stultz
           - use call VDSO32_vsyscall instead of int 80
           - code cleanup
17.12.2012 - support for IA32_EMULATION, this includes
             - code cleanup
             - include cleanup to fix compile warnings and errors
	     - move out seqcount from seqlock, enable use in VDSO
	     - map FIXMAP and HPET into the 32 bit address space
18.12.2012 - split into separate patches
30.01.2014 - revamp the code
             - code clean up
	     - VDSO layout changed
	     - no fixed addresses
	     - port to 3.14
01.02.2014 - code cleanup
02.02.2014 - code cleanup
             - split into more patches
	     - use HPET_COUNTER instead of hard coded value
	     - fix changelog to the right year ;-)
02.02.2014 - reverse the mapping, this make the new VDSO 32 bit support
             full compatible.

[PATCH v9 1/8] Make vsyscall_gtod_data handling x86 generic

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This patch move the vsyscall_gtod_data handling out of vsyscall_64.c
into an additonal file vsyscall_gtod.c to make the functionality
available for x86 32 bit kernel.

It also adds a new vsyscall_32.c which setup the VVAR page.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/Kconfig                   |  4 +--
 arch/x86/include/asm/clocksource.h |  4 ---
 arch/x86/include/asm/fixmap.h      |  2 ++
 arch/x86/include/asm/vvar.h        |  4 +++
 arch/x86/kernel/Makefile           |  3 +-
 arch/x86/kernel/hpet.c             |  4 ---
 arch/x86/kernel/setup.c            |  2 --
 arch/x86/kernel/tsc.c              |  2 --
 arch/x86/kernel/vmlinux.lds.S      |  3 --
 arch/x86/kernel/vsyscall_32.c      | 24 +++++++++++++++
 arch/x86/kernel/vsyscall_64.c      | 44 ----------------------------
 arch/x86/kernel/vsyscall_gtod.c    | 60 ++++++++++++++++++++++++++++++++++++++
 12 files changed, 94 insertions(+), 62 deletions(-)
 create mode 100644 arch/x86/kernel/vsyscall_32.c
 create mode 100644 arch/x86/kernel/vsyscall_gtod.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 940e50e..b556f00 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -107,9 +107,9 @@ config X86
 	select HAVE_ARCH_SOFT_DIRTY
 	select CLOCKSOURCE_WATCHDOG
 	select GENERIC_CLOCKEVENTS
-	select ARCH_CLOCKSOURCE_DATA if X86_64
+	select ARCH_CLOCKSOURCE_DATA
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
-	select GENERIC_TIME_VSYSCALL if X86_64
+	select GENERIC_TIME_VSYSCALL
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index 16a57f4..eda81dc 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -3,8 +3,6 @@
 #ifndef _ASM_X86_CLOCKSOURCE_H
 #define _ASM_X86_CLOCKSOURCE_H
 
-#ifdef CONFIG_X86_64
-
 #define VCLOCK_NONE 0  /* No vDSO clock available.	*/
 #define VCLOCK_TSC  1  /* vDSO should use vread_tsc.	*/
 #define VCLOCK_HPET 2  /* vDSO should use vread_hpet.	*/
@@ -14,6 +12,4 @@ struct arch_clocksource_data {
 	int vclock_mode;
 };
 
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_CLOCKSOURCE_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7252cd3..094d0cc 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -75,6 +75,8 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_32
 	FIX_HOLE,
 	FIX_VDSO,
+	VVAR_PAGE,
+	VSYSCALL_HPET,
 #else
 	VSYSCALL_LAST_PAGE,
 	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index d76ac40..c442782 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -17,7 +17,11 @@
  */
 
 /* Base address of vvars.  This is not ABI. */
+#ifdef CONFIG_X86_64
 #define VVAR_ADDRESS (-10*1024*1024 - 4096)
+#else
+#define VVAR_ADDRESS 0xffffd000
+#endif
 
 #if defined(__VVAR_KERNEL_LDS)
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cb648c8..3282eda 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,7 +26,8 @@ obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
-obj-y			+= syscall_$(BITS).o
+obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
+obj-$(CONFIG_X86_32)	+= vsyscall_32.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index da85a8e..54263f0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -74,9 +74,7 @@ static inline void hpet_writel(unsigned int d, unsigned int a)
 static inline void hpet_set_mapping(void)
 {
 	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-#ifdef CONFIG_X86_64
 	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
-#endif
 }
 
 static inline void hpet_clear_mapping(void)
@@ -752,9 +750,7 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	.resume		= hpet_resume_counter,
-#ifdef CONFIG_X86_64
 	.archdata	= { .vclock_mode = VCLOCK_HPET },
-#endif
 };
 
 static int hpet_clocksource_register(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e6..56ff330 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1182,9 +1182,7 @@ void __init setup_arch(char **cmdline_p)
 
 	tboot_probe();
 
-#ifdef CONFIG_X86_64
 	map_vsyscall();
-#endif
 
 	generic_apic_probe();
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb..f49d1a2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -988,9 +988,7 @@ static struct clocksource clocksource_tsc = {
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_MUST_VERIFY,
-#ifdef CONFIG_X86_64
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
-#endif
 };
 
 void mark_tsc_unstable(char *reason)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index da6b35a..1d4897b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -147,7 +147,6 @@ SECTIONS
 		_edata = .;
 	} :data
 
-#ifdef CONFIG_X86_64
 
 	. = ALIGN(PAGE_SIZE);
 	__vvar_page = .;
@@ -169,8 +168,6 @@ SECTIONS
 
        . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
 
-#endif /* CONFIG_X86_64 */
-
 	/* Init code and data - will be freed after init */
 	. = ALIGN(PAGE_SIZE);
 	.init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/vsyscall_32.c b/arch/x86/kernel/vsyscall_32.c
new file mode 100644
index 0000000..f541dfa
--- /dev/null
+++ b/arch/x86/kernel/vsyscall_32.c
@@ -0,0 +1,24 @@
+/*
+ *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ *  Modified for x86 32 bit arch by Stefani Seibold <stefani@seibold.net>
+ *
+ *  Thanks to hpa@transmeta.com for some useful hint.
+ *  Special thanks to Ingo Molnar for his early experience with
+ *  a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ */
+
+#include <asm/vsyscall.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+
+void __init map_vsyscall(void)
+{
+	extern char __vvar_page;
+	unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
+
+	__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
+}
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f93..50622ed 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -47,14 +47,12 @@
 #include <asm/segment.h>
 #include <asm/desc.h>
 #include <asm/topology.h>
-#include <asm/vgtod.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
 DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
 
@@ -77,48 +75,6 @@ static int __init vsyscall_setup(char *str)
 }
 early_param("vsyscall", vsyscall_setup);
 
-void update_vsyscall_tz(void)
-{
-	vsyscall_gtod_data.sys_tz = sys_tz;
-}
-
-void update_vsyscall(struct timekeeper *tk)
-{
-	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
-
-	write_seqcount_begin(&vdata->seq);
-
-	/* 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->wall_time_sec		= tk->xtime_sec;
-	vdata->wall_time_snsec		= tk->xtime_nsec;
-
-	vdata->monotonic_time_sec	= tk->xtime_sec
-					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->xtime_nsec
-					+ (tk->wall_to_monotonic.tv_nsec
-						<< tk->shift);
-	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->shift)) {
-		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->shift;
-		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->monotonic_time_coarse	= timespec_add(vdata->wall_time_coarse,
-							tk->wall_to_monotonic);
-
-	write_seqcount_end(&vdata->seq);
-}
-
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 			      const char *message)
 {
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
new file mode 100644
index 0000000..91862a4
--- /dev/null
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -0,0 +1,60 @@
+/*
+ *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ *  Modified for x86 32 bit architecture by
+ *  Stefani Seibold <stefani@seibold.net>
+ *
+ *  Thanks to hpa@transmeta.com for some useful hint.
+ *  Special thanks to Ingo Molnar for his early experience with
+ *  a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ */
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vgtod.h>
+
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
+
+void update_vsyscall_tz(void)
+{
+	vsyscall_gtod_data.sys_tz = sys_tz;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+
+	write_seqcount_begin(&vdata->seq);
+
+	/* 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->wall_time_sec		= tk->xtime_sec;
+	vdata->wall_time_snsec		= tk->xtime_nsec;
+
+	vdata->monotonic_time_sec	= tk->xtime_sec
+					+ tk->wall_to_monotonic.tv_sec;
+	vdata->monotonic_time_snsec	= tk->xtime_nsec
+					+ (tk->wall_to_monotonic.tv_nsec
+						<< tk->shift);
+	while (vdata->monotonic_time_snsec >=
+					(((u64)NSEC_PER_SEC) << tk->shift)) {
+		vdata->monotonic_time_snsec -=
+					((u64)NSEC_PER_SEC) << tk->shift;
+		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->monotonic_time_coarse	= timespec_add(vdata->wall_time_coarse,
+							tk->wall_to_monotonic);
+
+	write_seqcount_end(&vdata->seq);
+}
+
-- 
1.8.5.3

[PATCH v9 2/8] Add new func _install_special_mapping() to mmap.c

[stefani]

From: Stefani Seibold <stefani@seibold.net>

The _install_special_mapping() is the new base function for
install_special_mapping(). This function will return a pointer of the
created VMA or a error code in an ERR_PTR()

This new function will be needed by the for the vdso 32 bit support to map the
additonal vvar and hpet pages into the 32 bit address space. This will be done
with io_remap_pfn_range() and remap_pfn_range, which requieres a vm_area_struct.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 include/linux/mm.h |  3 +++
 mm/mmap.c          | 20 ++++++++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46e..55342aa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1740,6 +1740,9 @@ extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
+extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
+				   unsigned long addr, unsigned long len,
+				   unsigned long flags, struct page **pages);
 extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags, struct page **pages);
diff --git a/mm/mmap.c b/mm/mmap.c
index 20ff0c3..81ba54f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2918,7 +2918,7 @@ static const struct vm_operations_struct special_mapping_vmops = {
  * The array pointer and the pages it points to are assumed to stay alive
  * for as long as this mapping might exist.
  */
-int install_special_mapping(struct mm_struct *mm,
+struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 			    unsigned long addr, unsigned long len,
 			    unsigned long vm_flags, struct page **pages)
 {
@@ -2927,7 +2927,7 @@ int install_special_mapping(struct mm_struct *mm,
 
 	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 	if (unlikely(vma == NULL))
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_mm = mm;
@@ -2948,11 +2948,23 @@ int install_special_mapping(struct mm_struct *mm,
 
 	perf_event_mmap(vma);
 
-	return 0;
+	return vma;
 
 out:
 	kmem_cache_free(vm_area_cachep, vma);
-	return ret;
+	return ERR_PTR(ret);
+}
+
+int install_special_mapping(struct mm_struct *mm,
+			    unsigned long addr, unsigned long len,
+			    unsigned long vm_flags, struct page **pages)
+{
+	struct vm_area_struct *vma = _install_special_mapping(mm,
+			    addr, len, vm_flags, pages);
+
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+	return 0;
 }
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
-- 
1.8.5.3

[PATCH v9 3/8] revamp vclock_gettime.c

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This intermediate patch revamps the vclock_gettime.c by moving some functions
around. It is only for spliting purpose, to make whole the 32 bit vdso timer
patch easier to review.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/vdso/vclock_gettime.c | 85 +++++++++++++++++++++---------------------
 1 file changed, 42 insertions(+), 43 deletions(-)

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index eb5d7a5..bbc8065 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -26,41 +26,26 @@
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
-notrace static cycle_t vread_tsc(void)
+static notrace cycle_t vread_hpet(void)
 {
-	cycle_t ret;
-	u64 last;
-
-	/*
-	 * Empirically, a fence (of type that depends on the CPU)
-	 * before rdtsc is enough to ensure that rdtsc is ordered
-	 * with respect to loads.  The various CPU manuals are unclear
-	 * as to whether rdtsc can be reordered with later loads,
-	 * but no one has ever seen it happen.
-	 */
-	rdtsc_barrier();
-	ret = (cycle_t)vget_cycles();
-
-	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
+	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
+}
 
-	/*
-	 * GCC likes to generate cmov here, but this branch is extremely
-	 * predictable (it's just a funciton of time and the likely is
-	 * very likely) and there's a data dependence, so force GCC
-	 * to generate a branch instead.  I don't barrier() because
-	 * we don't actually need a barrier, and if this function
-	 * ever gets inlined it will generate worse code.
-	 */
-	asm volatile ("");
-	return last;
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+	long ret;
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	return ret;
 }
 
-static notrace cycle_t vread_hpet(void)
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 {
-	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
+	long ret;
+
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	return ret;
 }
 
 #ifdef CONFIG_PARAVIRT_CLOCK
@@ -133,23 +118,37 @@ static notrace cycle_t vread_pvclock(int *mode)
 }
 #endif
 
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+notrace static cycle_t vread_tsc(void)
 {
-	long ret;
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory");
-	return ret;
-}
+	cycle_t ret;
+	u64 last;
 
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
-	long ret;
+	/*
+	 * Empirically, a fence (of type that depends on the CPU)
+	 * before rdtsc is enough to ensure that rdtsc is ordered
+	 * with respect to loads.  The various CPU manuals are unclear
+	 * as to whether rdtsc can be reordered with later loads,
+	 * but no one has ever seen it happen.
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
 
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
-	return ret;
-}
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
 
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * GCC likes to generate cmov here, but this branch is extremely
+	 * predictable (it's just a funciton of time and the likely is
+	 * very likely) and there's a data dependence, so force GCC
+	 * to generate a branch instead.  I don't barrier() because
+	 * we don't actually need a barrier, and if this function
+	 * ever gets inlined it will generate worse code.
+	 */
+	asm volatile ("");
+	return last;
+}
 
 notrace static inline u64 vgetsns(int *mode)
 {
-- 
1.8.5.3

[PATCH v9 4/8] vclock_gettime.c __vdso_clock_gettime cleanup

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This patch is a small code cleanup for the __vdso_clock_gettime() function.

It removes the unneeded return values from do_monotonic_coarse() and
do_realtime_coarse() and add a fallback label for doing the kernel
gettimeofday() system call.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/vdso/vclock_gettime.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index bbc8065..fd074dd 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -209,7 +209,7 @@ notrace static int do_monotonic(struct timespec *ts)
 	return mode;
 }
 
-notrace static int do_realtime_coarse(struct timespec *ts)
+notrace static void do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
@@ -217,10 +217,9 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 		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)));
-	return 0;
 }
 
-notrace static int do_monotonic_coarse(struct timespec *ts)
+notrace static void do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
@@ -228,30 +227,32 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 		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)));
-
-	return 0;
 }
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
-	int ret = VCLOCK_NONE;
-
 	switch (clock) {
 	case CLOCK_REALTIME:
-		ret = do_realtime(ts);
+		if (do_realtime(ts) == VCLOCK_NONE)
+			goto fallback;
 		break;
 	case CLOCK_MONOTONIC:
-		ret = do_monotonic(ts);
+		if (do_monotonic(ts) == VCLOCK_NONE)
+			goto fallback;
 		break;
 	case CLOCK_REALTIME_COARSE:
-		return do_realtime_coarse(ts);
+		do_realtime_coarse(ts);
+		break;
 	case CLOCK_MONOTONIC_COARSE:
-		return do_monotonic_coarse(ts);
+		do_monotonic_coarse(ts);
+		break;
+	default:
+		goto fallback;
 	}
 
-	if (ret == VCLOCK_NONE)
-		return vdso_fallback_gettime(clock, ts);
 	return 0;
+fallback:
+	return vdso_fallback_gettime(clock, ts);
 }
 int clock_gettime(clockid_t, struct timespec *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
-- 
1.8.5.3

[PATCH v9 5/8] replace VVAR(vsyscall_gtod_data) by gtod macro

[stefani]

From: Stefani Seibold <stefani@seibold.net>

There a currently more than 30 users of the gtod macro, so replace the
last VVAR(vsyscall_gtod_data) by gtod macro.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/vdso/vclock_gettime.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index fd074dd..743f277 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -109,7 +109,7 @@ static notrace cycle_t vread_pvclock(int *mode)
 		*mode = VCLOCK_NONE;
 
 	/* refer to tsc.c read_tsc() comment for rationale */
-	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+	last = gtod->clock.cycle_last;
 
 	if (likely(ret >= last))
 		return ret;
@@ -133,7 +133,7 @@ notrace static cycle_t vread_tsc(void)
 	rdtsc_barrier();
 	ret = (cycle_t)vget_cycles();
 
-	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+	last = gtod->clock.cycle_last;
 
 	if (likely(ret >= last))
 		return ret;
@@ -288,7 +288,7 @@ int gettimeofday(struct timeval *, struct timezone *)
 notrace time_t __vdso_time(time_t *t)
 {
 	/* This is atomic on x86_64 so we don't need any locks. */
-	time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
+	time_t result = ACCESS_ONCE(gtod->wall_time_sec);
 
 	if (t)
 		*t = result;
-- 
1.8.5.3

[PATCH v9 6/8] cleanup __vdso_gettimeofday

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This patch do a little cleanup for the __vdso_gettimeofday() function.

It kick out an unneeded ret local variable and makes the code faster if
only the timezone is needed.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/vdso/vclock_gettime.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 743f277..bf969a0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -259,13 +259,12 @@ int clock_gettime(clockid_t, struct timespec *)
 
 notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
-	long ret = VCLOCK_NONE;
-
 	if (likely(tv != NULL)) {
 		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
 			     offsetof(struct timespec, tv_nsec) ||
 			     sizeof(*tv) != sizeof(struct timespec));
-		ret = do_realtime((struct timespec *)tv);
+		if (do_realtime((struct timespec *)tv) == VCLOCK_NONE)
+			return vdso_fallback_gtod(tv, tz);
 		tv->tv_usec /= 1000;
 	}
 	if (unlikely(tz != NULL)) {
@@ -274,8 +273,6 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 		tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
 	}
 
-	if (ret == VCLOCK_NONE)
-		return vdso_fallback_gtod(tv, tz);
 	return 0;
 }
 int gettimeofday(struct timeval *, struct timezone *)
-- 
1.8.5.3

[PATCH v9 7/8] Add 32 bit VDSO time support for 32 bit kernel

[stefani]

From: Stefani Seibold <stefani@seibold.net>

This patch add the time support for 32 bit a VDSO to a 32 bit kernel.

For 32 bit programs running on a 32 bit kernel, the same mechanism is
used as for 64 bit programs running on a 64 bit kernel.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/include/asm/vdso.h           |  3 ++
 arch/x86/include/asm/vdso32.h         | 11 +++++++
 arch/x86/vdso/Makefile                |  7 +++++
 arch/x86/vdso/vclock_gettime.c        | 59 +++++++++++++++++++++++++++++++++--
 arch/x86/vdso/vdso-layout.lds.S       | 22 +++++++++++++
 arch/x86/vdso/vdso32-setup.c          | 55 ++++++++++++++++++++++++++++----
 arch/x86/vdso/vdso32/vclock_gettime.c | 16 ++++++++++
 arch/x86/vdso/vdso32/vdso32.lds.S     | 11 ++++++-
 8 files changed, 175 insertions(+), 9 deletions(-)
 create mode 100644 arch/x86/include/asm/vdso32.h
 create mode 100644 arch/x86/vdso/vdso32/vclock_gettime.c

diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index fddb53d..fe3cef9 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -2,6 +2,9 @@
 #define _ASM_X86_VDSO_H
 
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
+
+#include <asm/vdso32.h>
+
 extern const char VDSO32_PRELINK[];
 
 /*
diff --git a/arch/x86/include/asm/vdso32.h b/arch/x86/include/asm/vdso32.h
new file mode 100644
index 0000000..37e1a75
--- /dev/null
+++ b/arch/x86/include/asm/vdso32.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_X86_VDSO32_H
+#define _ASM_X86_VDSO32_H
+
+#define VDSO_BASE_PAGE	0
+#define VDSO_VVAR_PAGE	1
+#define VDSO_HPET_PAGE	2
+#define	VDSO_PAGES	3
+#define VDSO_PREV_PAGES	2
+#define	VDSO_OFFSET(x)	((x) * PAGE_SIZE)
+
+#endif
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index fd14be1..1ff5b0a 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -145,8 +145,15 @@ KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
 $(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
 $(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
 
+KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=3 -freg-struct-return -fpic
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+
 $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
 				 $(obj)/vdso32/vdso32.lds \
+				 $(obj)/vdso32/vclock_gettime.o \
 				 $(obj)/vdso32/note.o \
 				 $(obj)/vdso32/%.o
 	$(call if_changed,vdso)
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index bf969a0..42f641c 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -4,6 +4,9 @@
  *
  * Fast user context implementation of clock_gettime, gettimeofday, and time.
  *
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
  * The code should have no internal unresolved relocations.
  * Check with readelf after changing.
  */
@@ -24,6 +27,8 @@
 #include <asm/io.h>
 #include <asm/pvclock.h>
 
+#ifndef BUILD_VDSO32
+
 #define gtod (&VVAR(vsyscall_gtod_data))
 
 static notrace cycle_t vread_hpet(void)
@@ -47,6 +52,54 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
 	return ret;
 }
+#else
+
+struct vsyscall_gtod_data vvar_vsyscall_gtod_data
+	__attribute__((visibility("hidden")));
+
+u8 hpet_page
+	__attribute__((visibility("hidden")));
+
+#define gtod (&vvar_vsyscall_gtod_data)
+
+#ifdef CONFIG_HPET_TIMER
+static notrace cycle_t vread_hpet(void)
+{
+	return readl(&hpet_page + HPET_COUNTER);
+}
+#endif
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+	long ret;
+
+	asm(
+		"push %%ebx \n"
+		"mov %2,%%ebx \n"
+		"call VDSO32_vsyscall \n"
+		"pop %%ebx \n"
+		: "=a" (ret)
+		: "0" (__NR_clock_gettime), "d" (clock), "c" (ts)
+		: "memory");
+	return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv,
+		struct timezone *tz)
+{
+	long ret;
+
+	asm(
+		"push %%ebx \n"
+		"mov %2,%%ebx \n"
+		"call VDSO32_vsyscall \n"
+		"pop %%ebx \n"
+		: "=a" (ret)
+		: "0" (__NR_gettimeofday), "d" (tv), "c" (tz)
+		: "memory");
+	return ret;
+}
+#endif
 
 #ifdef CONFIG_PARAVIRT_CLOCK
 
@@ -152,12 +205,14 @@ notrace static cycle_t vread_tsc(void)
 
 notrace static inline u64 vgetsns(int *mode)
 {
-	long v;
+	u64 v;
 	cycles_t cycles;
 	if (gtod->clock.vclock_mode == VCLOCK_TSC)
 		cycles = vread_tsc();
+#ifdef CONFIG_HPET_TIMER
 	else if (gtod->clock.vclock_mode == VCLOCK_HPET)
 		cycles = vread_hpet();
+#endif
 #ifdef CONFIG_PARAVIRT_CLOCK
 	else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK)
 		cycles = vread_pvclock(mode);
@@ -284,7 +339,7 @@ int gettimeofday(struct timeval *, struct timezone *)
  */
 notrace time_t __vdso_time(time_t *t)
 {
-	/* This is atomic on x86_64 so we don't need any locks. */
+	/* This is atomic on x86 so we don't need any locks. */
 	time_t result = ACCESS_ONCE(gtod->wall_time_sec);
 
 	if (t)
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 634a2cf..1261437 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -6,6 +6,24 @@
 
 SECTIONS
 {
+#ifdef BUILD_VDSO32
+#include <asm/vdso32.h>
+
+	.hpet_sect : {
+		hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
+	} :text :hpet_sect
+
+	.vvar_sect : {
+		vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
+
+	/* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset;
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+	} :text :vvar_sect
+#endif
 	. = VDSO_PRELINK + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
@@ -61,4 +79,8 @@ PHDRS
 	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
 	note		PT_NOTE		FLAGS(4);		/* PF_R */
 	eh_frame_hdr	PT_GNU_EH_FRAME;
+#ifdef BUILD_VDSO32
+	vvar_sect	PT_NULL		FLAGS(4);		/* PF_R */
+	hpet_sect	PT_NULL		FLAGS(4);		/* PF_R */
+#endif
 }
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb87..65ccebc 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -25,6 +25,7 @@
 #include <asm/tlbflush.h>
 #include <asm/vdso.h>
 #include <asm/proto.h>
+#include <asm/fixmap.h>
 
 enum {
 	VDSO_DISABLED = 0,
@@ -193,7 +194,7 @@ static __init void relocate_vdso(Elf32_Ehdr *ehdr)
 	}
 }
 
-static struct page *vdso32_pages[1];
+static struct page *vdso32_pages[VDSO_PAGES];
 
 #ifdef CONFIG_X86_64
 
@@ -310,6 +311,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	unsigned long addr;
 	int ret = 0;
 	bool compat;
+	struct vm_area_struct *vma;
+	extern char __vvar_page;
+#ifdef CONFIG_HPET_TIMER
+	extern unsigned long hpet_address;
+#endif
 
 #ifdef CONFIG_X86_X32_ABI
 	if (test_thread_flag(TIF_X32))
@@ -330,11 +336,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (compat)
 		addr = VDSO_HIGH_BASE;
 	else {
-		addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+		addr = get_unmapped_area(NULL, 0, VDSO_OFFSET(VDSO_PAGES), 0, 0);
 		if (IS_ERR_VALUE(addr)) {
 			ret = addr;
 			goto up_fail;
 		}
+
+		addr += VDSO_OFFSET(VDSO_PREV_PAGES);
 	}
 
 	current->mm->context.vdso = (void *)addr;
@@ -343,13 +351,48 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		/*
 		 * MAYWRITE to allow gdb to COW and set breakpoints
 		 */
-		ret = install_special_mapping(mm, addr, PAGE_SIZE,
-					      VM_READ|VM_EXEC|
-					      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-					      vdso32_pages);
+		ret = install_special_mapping(mm,
+				addr,
+				VDSO_OFFSET(VDSO_PAGES - VDSO_PREV_PAGES),
+				VM_READ|VM_EXEC|
+				VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				vdso32_pages);
+
+		if (ret)
+			goto up_fail;
+
+		vma = _install_special_mapping(mm,
+				addr -  VDSO_OFFSET(VDSO_PREV_PAGES),
+				VDSO_OFFSET(VDSO_PREV_PAGES),
+				VM_READ,
+				NULL);
+
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto up_fail;
+		}
+
+		ret = remap_pfn_range(vma,
+			addr - VDSO_OFFSET(VDSO_VVAR_PAGE),
+			__pa_symbol(&__vvar_page) >> PAGE_SHIFT,
+			PAGE_SIZE,
+			PAGE_READONLY);
 
 		if (ret)
 			goto up_fail;
+
+#ifdef CONFIG_HPET_TIMER
+		if (hpet_address) {
+			ret = io_remap_pfn_range(vma,
+				addr - VDSO_OFFSET(VDSO_HPET_PAGE),
+				hpet_address >> PAGE_SHIFT,
+				PAGE_SIZE,
+				pgprot_noncached(PAGE_READONLY));
+
+			if (ret)
+				goto up_fail;
+		}
+#endif
 	}
 
 	current_thread_info()->sysenter_return =
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/vdso/vdso32/vclock_gettime.c
new file mode 100644
index 0000000..fab4ec6
--- /dev/null
+++ b/arch/x86/vdso/vdso32/vclock_gettime.c
@@ -0,0 +1,16 @@
+#define BUILD_VDSO32
+
+#ifdef CONFIG_X86_64
+
+#define _ASM_X86_PAGE_H
+
+#define __pa(x)                0
+#define __va(x)                0
+
+#undef CONFIG_ILLEGAL_POINTER_VALUE
+#define CONFIG_ILLEGAL_POINTER_VALUE   0
+
+#endif
+
+#include "../vclock_gettime.c"
+
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S
index 976124b..66e73b2 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/vdso/vdso32/vdso32.lds.S
@@ -8,6 +8,9 @@
  * values visible using the asm-x86/vdso.h macros from the kernel proper.
  */
 
+#include <asm/page.h>
+
+#define BUILD_VDSO32
 #define VDSO_PRELINK 0
 #include "../vdso-layout.lds.S"
 
@@ -19,11 +22,14 @@ ENTRY(__kernel_vsyscall);
  */
 VERSION
 {
-	LINUX_2.5 {
+	LINUX_2.6 {
 	global:
 		__kernel_vsyscall;
 		__kernel_sigreturn;
 		__kernel_rt_sigreturn;
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_time;
 	local: *;
 	};
 }
@@ -35,3 +41,6 @@ VDSO32_PRELINK		= VDSO_PRELINK;
 VDSO32_vsyscall		= __kernel_vsyscall;
 VDSO32_sigreturn	= __kernel_sigreturn;
 VDSO32_rt_sigreturn	= __kernel_rt_sigreturn;
+VDSO32_clock_gettime	= clock_gettime;
+VDSO32_gettimeofday	= gettimeofday;
+VDSO32_time		= time;
-- 
1.8.5.3

[PATCH v9 8/8] Add 32 bit VDSO time support for 64 bit kernel

[stefani]

From: Stefani Seibold <stefani@seibold.net>

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 a lot of type hacking necessary.

Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
 arch/x86/vdso/vclock_gettime.c        | 109 +++++++++++++++++++++++++++-------
 arch/x86/vdso/vdso32/vclock_gettime.c |   7 +++
 2 files changed, 95 insertions(+), 21 deletions(-)

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 42f641c..cd33f05 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -31,12 +31,24 @@
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
+struct api_timeval {
+	long	tv_sec;		/* seconds */
+	long	tv_usec;	/* microseconds */
+};
+
+struct api_timespec {
+	long	tv_sec;		/* seconds */
+	long	tv_nsec;	/* microseconds */
+};
+
+typedef long api_time_t;
+
 static notrace cycle_t vread_hpet(void)
 {
 	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
 }
 
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+notrace static long vdso_fallback_gettime(long clock, struct api_timespec *ts)
 {
 	long ret;
 	asm("syscall" : "=a" (ret) :
@@ -44,7 +56,8 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 	return ret;
 }
 
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+notrace static long vdso_fallback_gtod(struct api_timeval *tv,
+		struct timezone *tz)
 {
 	long ret;
 
@@ -54,14 +67,62 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 }
 #else
 
+#ifdef CONFIG_IA32_EMULATION
+typedef s64	arch_time_t;
+
+struct arch_timespec {
+	s64	tv_sec;
+	s64	tv_nsec;
+};
+
+#define ALIGN8 __attribute__ ((aligned (8)))
+
+struct arch_vsyscall_gtod_data {
+	seqcount_t	seq ALIGN8;
+
+	struct { /* extract of a clocksource struct */
+		int vclock_mode ALIGN8;
+		cycle_t	cycle_last ALIGN8;
+		cycle_t	mask ALIGN8;
+		u32	mult;
+		u32	shift;
+	} clock;
+
+	/* open coded 'struct timespec' */
+	arch_time_t	wall_time_sec;
+	u64		wall_time_snsec;
+	u64		monotonic_time_snsec;
+	arch_time_t	monotonic_time_sec;
+
+	struct timezone sys_tz;
+	struct arch_timespec wall_time_coarse;
+	struct arch_timespec monotonic_time_coarse;
+};
+
+struct arch_vsyscall_gtod_data vvar_vsyscall_gtod_data
+	__attribute__((visibility("hidden")));
+#else
 struct vsyscall_gtod_data vvar_vsyscall_gtod_data
 	__attribute__((visibility("hidden")));
+#endif
 
 u8 hpet_page
 	__attribute__((visibility("hidden")));
 
 #define gtod (&vvar_vsyscall_gtod_data)
 
+struct api_timeval {
+	s32	tv_sec;		/* seconds */
+	s32	tv_usec;	/* microseconds */
+};
+
+struct api_timespec {
+	s32	tv_sec;		/* seconds */
+	s32	tv_nsec;	/* microseconds */
+};
+
+typedef s32 api_time_t;
+
 #ifdef CONFIG_HPET_TIMER
 static notrace cycle_t vread_hpet(void)
 {
@@ -69,7 +130,7 @@ static notrace cycle_t vread_hpet(void)
 }
 #endif
 
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+notrace static long vdso_fallback_gettime(long clock, struct api_timespec *ts)
 {
 	long ret;
 
@@ -79,12 +140,12 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 		"call VDSO32_vsyscall \n"
 		"pop %%ebx \n"
 		: "=a" (ret)
-		: "0" (__NR_clock_gettime), "d" (clock), "c" (ts)
+		: "0" (__NR_ia32_clock_gettime), "d" (clock), "c" (ts)
 		: "memory");
 	return ret;
 }
 
-notrace static long vdso_fallback_gtod(struct timeval *tv,
+notrace static long vdso_fallback_gtod(struct api_timeval *tv,
 		struct timezone *tz)
 {
 	long ret;
@@ -95,7 +156,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv,
 		"call VDSO32_vsyscall \n"
 		"pop %%ebx \n"
 		: "=a" (ret)
-		: "0" (__NR_gettimeofday), "d" (tv), "c" (tz)
+		: "0" (__NR_ia32_gettimeofday), "d" (tv), "c" (tz)
 		: "memory");
 	return ret;
 }
@@ -284,42 +345,48 @@ notrace static void do_monotonic_coarse(struct timespec *ts)
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 }
 
-notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+notrace int __vdso_clock_gettime(clockid_t clock, struct api_timespec *ts)
 {
+	struct timespec tmp;
+
 	switch (clock) {
 	case CLOCK_REALTIME:
-		if (do_realtime(ts) == VCLOCK_NONE)
+		if (do_realtime(&tmp) == VCLOCK_NONE)
 			goto fallback;
 		break;
 	case CLOCK_MONOTONIC:
-		if (do_monotonic(ts) == VCLOCK_NONE)
+		if (do_monotonic(&tmp) == VCLOCK_NONE)
 			goto fallback;
 		break;
 	case CLOCK_REALTIME_COARSE:
-		do_realtime_coarse(ts);
+		do_realtime_coarse(&tmp);
 		break;
 	case CLOCK_MONOTONIC_COARSE:
-		do_monotonic_coarse(ts);
+		do_monotonic_coarse(&tmp);
 		break;
 	default:
 		goto fallback;
 	}
 
+	ts->tv_sec = tmp.tv_sec;
+	ts->tv_nsec = tmp.tv_nsec;
+
 	return 0;
 fallback:
 	return vdso_fallback_gettime(clock, ts);
 }
-int clock_gettime(clockid_t, struct timespec *)
+int clock_gettime(clockid_t, struct api_timespec *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
 
-notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+notrace int __vdso_gettimeofday(struct api_timeval *tv, struct timezone *tz)
 {
+	struct timespec tmp;
+
 	if (likely(tv != NULL)) {
-		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
-			     offsetof(struct timespec, tv_nsec) ||
-			     sizeof(*tv) != sizeof(struct timespec));
-		if (do_realtime((struct timespec *)tv) == VCLOCK_NONE)
+		if (do_realtime(&tmp) == VCLOCK_NONE)
 			return vdso_fallback_gtod(tv, tz);
+		tv->tv_sec = tmp.tv_sec;
+		tv->tv_usec = tmp.tv_nsec;
 		tv->tv_usec /= 1000;
 	}
 	if (unlikely(tz != NULL)) {
@@ -330,21 +397,21 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 
 	return 0;
 }
-int gettimeofday(struct timeval *, struct timezone *)
+int gettimeofday(struct api_timeval *, struct timezone *)
 	__attribute__((weak, alias("__vdso_gettimeofday")));
 
 /*
  * This will break when the xtime seconds get inaccurate, but that is
  * unlikely
  */
-notrace time_t __vdso_time(time_t *t)
+notrace api_time_t __vdso_time(api_time_t *t)
 {
 	/* This is atomic on x86 so we don't need any locks. */
-	time_t result = ACCESS_ONCE(gtod->wall_time_sec);
+	api_time_t result = ACCESS_ONCE(gtod->wall_time_sec);
 
 	if (t)
 		*t = result;
 	return result;
 }
-int time(time_t *t)
+int time(api_time_t *t)
 	__attribute__((weak, alias("__vdso_time")));
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/vdso/vdso32/vclock_gettime.c
index fab4ec6..b6df952 100644
--- a/arch/x86/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/vdso/vdso32/vclock_gettime.c
@@ -2,6 +2,8 @@
 
 #ifdef CONFIG_X86_64
 
+#include <generated/asm/unistd_32_ia32.h>
+
 #define _ASM_X86_PAGE_H
 
 #define __pa(x)                0
@@ -10,6 +12,11 @@
 #undef CONFIG_ILLEGAL_POINTER_VALUE
 #define CONFIG_ILLEGAL_POINTER_VALUE   0
 
+#else
+
+#define __NR_ia32_clock_gettime	__NR_clock_gettime
+#define __NR_ia32_gettimeofday	__NR_gettimeofday
+
 #endif
 
 #include "../vclock_gettime.c"
-- 
1.8.5.3

Re: [PATCH v9 7/8] Add 32 bit VDSO time support for 32 bit kernel

[H. Peter Anvin]

On 02/02/2014 01:41 PM, stefani@seibold.net wrote:
> @@ -19,11 +22,14 @@ ENTRY(__kernel_vsyscall);
>   */
>  VERSION
>  {
> -	LINUX_2.5 {
> +	LINUX_2.6 {
>  	global:

Why are you changing the version number?  This will, at least in theory,
break libcs from a certain time period.  The version number should only
be changed when there is an ABI-level incompatible change.

	-hpa

Re: [PATCH v9 8/8] Add 32 bit VDSO time support for 64 bit kernel

[H. Peter Anvin]

On 02/02/2014 01:41 PM, stefani@seibold.net wrote:
> +
> +struct api_timespec {
> +	long	tv_sec;		/* seconds */
> +	long	tv_nsec;	/* microseconds */
> +};
> +

/* nanoseconds */  ;)

	-hpa