* [PATCH v21 01/12] Make vsyscall_gtod_data handling x86 generic
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 02/12] Add new func _install_special_mapping() to mmap.c Stefani Seibold
` (10 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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 | 12 ++++++--
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 | 21 +++++++++++++
arch/x86/kernel/vsyscall_64.c | 45 ----------------------------
arch/x86/kernel/vsyscall_gtod.c | 60 ++++++++++++++++++++++++++++++++++++++
arch/x86/tools/relocs.c | 2 +-
13 files changed, 97 insertions(+), 67 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 0af5250..0da3b39 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..0a534ea 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -16,9 +16,6 @@
* you mess up, the linker will catch it.)
*/
-/* Base address of vvars. This is not ABI. */
-#define VVAR_ADDRESS (-10*1024*1024 - 4096)
-
#if defined(__VVAR_KERNEL_LDS)
/* The kernel linker script defines its own magic to put vvars in the
@@ -29,6 +26,15 @@
#else
+extern char __vvar_page;
+
+/* Base address of vvars. This is not ABI. */
+#ifdef CONFIG_X86_64
+#define VVAR_ADDRESS (-10*1024*1024 - 4096)
+#else
+#define VVAR_ADDRESS (&__vvar_page)
+#endif
+
#define DECLARE_VVAR(offset, type, name) \
static type const * const vvaraddr_ ## name = \
(void *)(VVAR_ADDRESS + (offset));
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 cfbe99f..227dcfc 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -985,9 +985,7 @@ 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..0b72db7
--- /dev/null
+++ b/arch/x86/kernel/vsyscall_32.c
@@ -0,0 +1,21 @@
+/*
+ * 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)
+{
+ __set_fixmap(VVAR_PAGE, __pa_symbol(&__vvar_page), PAGE_KERNEL_VVAR);
+}
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f93..9ea2876 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)
{
@@ -374,7 +330,6 @@ void __init map_vsyscall(void)
{
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- extern char __vvar_page;
unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
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);
+}
+
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index cfbdbdb..bbb1d22 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -69,8 +69,8 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
"__per_cpu_load|"
"init_per_cpu__.*|"
"__end_rodata_hpage_align|"
- "__vvar_page|"
#endif
+ "__vvar_page|"
"_end)$"
};
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 02/12] Add new func _install_special_mapping() to mmap.c
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 01/12] Make vsyscall_gtod_data handling x86 generic Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 03/12] revamp vclock_gettime.c Stefani Seibold
` (9 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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);
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 03/12] revamp vclock_gettime.c
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 01/12] Make vsyscall_gtod_data handling x86 generic Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 02/12] Add new func _install_special_mapping() to mmap.c Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 04/12] vclock_gettime.c __vdso_clock_gettime cleanup Stefani Seibold
` (8 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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)
{
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 04/12] vclock_gettime.c __vdso_clock_gettime cleanup
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (2 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 03/12] revamp vclock_gettime.c Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 05/12] replace VVAR(vsyscall_gtod_data) by gtod macro Stefani Seibold
` (7 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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(>od->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(>od->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")));
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 05/12] replace VVAR(vsyscall_gtod_data) by gtod macro
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (3 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 04/12] vclock_gettime.c __vdso_clock_gettime cleanup Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 06/12] cleanup __vdso_gettimeofday Stefani Seibold
` (6 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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;
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 06/12] cleanup __vdso_gettimeofday
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (4 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 05/12] replace VVAR(vsyscall_gtod_data) by gtod macro Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 07/12] introduce VVAR marco for vdso32 Stefani Seibold
` (5 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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..09dae4a 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 (unlikely(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 *)
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 07/12] introduce VVAR marco for vdso32
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (5 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 06/12] cleanup __vdso_gettimeofday Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 08/12] Patch alternatives in the 32-bit vDSO Stefani Seibold
` (4 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
This patch revamp the vvar.h for introduce the VVAR macro for vdso32.
Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
arch/x86/include/asm/vvar.h | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 0a534ea..52c79ff 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -26,6 +26,15 @@
#else
+#ifdef BUILD_VDSO32
+
+#define DECLARE_VVAR(offset, type, name) \
+ extern type vvar_ ## name __attribute__((visibility("hidden")));
+
+#define VVAR(name) (vvar_ ## name)
+
+#else
+
extern char __vvar_page;
/* Base address of vvars. This is not ABI. */
@@ -39,12 +48,13 @@ extern char __vvar_page;
static type const * const vvaraddr_ ## name = \
(void *)(VVAR_ADDRESS + (offset));
+#define VVAR(name) (*vvaraddr_ ## name)
+#endif
+
#define DEFINE_VVAR(type, name) \
type name \
__attribute__((section(".vvar_" #name), aligned(16))) __visible
-#define VVAR(name) (*vvaraddr_ ## name)
-
#endif
/* DECLARE_VVAR(offset, type, name) */
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 08/12] Patch alternatives in the 32-bit vDSO
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (6 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 07/12] introduce VVAR marco for vdso32 Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 09/12] Add 32 bit VDSO time support for 32 bit kernel Stefani Seibold
` (3 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
rdtsc_barrier() needs this.
Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
arch/x86/include/asm/vdso.h | 2 ++
arch/x86/vdso/Makefile | 3 ++-
arch/x86/vdso/vdso32-setup.c | 25 +++++++++++++------------
arch/x86/vdso/vma.c | 13 ++++++++++---
4 files changed, 27 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index fddb53d..6e39eb8 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -31,4 +31,6 @@ extern const char vdso32_int80_start, vdso32_int80_end;
extern const char vdso32_syscall_start, vdso32_syscall_end;
extern const char vdso32_sysenter_start, vdso32_sysenter_end;
+void __init patch_vdso32(void *vdso, size_t len);
+
#endif /* _ASM_X86_VDSO_H */
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index fd14be1..7a3d13e 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -21,7 +21,8 @@ vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
# files to link into kernel
-obj-$(VDSO64-y) += vma.o vdso.o
+obj-y += vma.o
+obj-$(VDSO64-y) += vdso.o
obj-$(VDSOX32-y) += vdsox32.o
obj-$(VDSO32-y) += vdso32.o vdso32-setup.o
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb87..bca2ffd 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -276,29 +276,30 @@ static void map_compat_vdso(int map)
int __init sysenter_setup(void)
{
- void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
- const void *vsyscall;
- size_t vsyscall_len;
+ void *vdso_page = (void *)get_zeroed_page(GFP_ATOMIC);
+ const void *vdso;
+ size_t vdso_len;
- vdso32_pages[0] = virt_to_page(syscall_page);
+ vdso32_pages[0] = virt_to_page(vdso_page);
#ifdef CONFIG_X86_32
gate_vma_init();
#endif
if (vdso32_syscall()) {
- vsyscall = &vdso32_syscall_start;
- vsyscall_len = &vdso32_syscall_end - &vdso32_syscall_start;
+ vdso = &vdso32_syscall_start;
+ vdso_len = &vdso32_syscall_end - &vdso32_syscall_start;
} else if (vdso32_sysenter()){
- vsyscall = &vdso32_sysenter_start;
- vsyscall_len = &vdso32_sysenter_end - &vdso32_sysenter_start;
+ vdso = &vdso32_sysenter_start;
+ vdso_len = &vdso32_sysenter_end - &vdso32_sysenter_start;
} else {
- vsyscall = &vdso32_int80_start;
- vsyscall_len = &vdso32_int80_end - &vdso32_int80_start;
+ vdso = &vdso32_int80_start;
+ vdso_len = &vdso32_int80_end - &vdso32_int80_start;
}
- memcpy(syscall_page, vsyscall, vsyscall_len);
- relocate_vdso(syscall_page);
+ memcpy(vdso_page, vdso, vdso_len);
+ patch_vdso32(vdso_page, vdso_len);
+ relocate_vdso(vdso_page);
return 0;
}
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e875..7345bc9 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -16,6 +16,7 @@
#include <asm/vdso.h>
#include <asm/page.h>
+#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso_enabled = 1;
extern char vdso_start[], vdso_end[];
@@ -28,8 +29,12 @@ static unsigned vdso_size;
extern char vdsox32_start[], vdsox32_end[];
extern struct page *vdsox32_pages[];
static unsigned vdsox32_size;
+#endif
+#endif
-static void __init patch_vdsox32(void *vdso, size_t len)
+#if defined(CONFIG_X86_32) || defined(CONFIG_X86_X32_ABI) || \
+ defined(CONFIG_COMPAT)
+void __init patch_vdso32(void *vdso, size_t len)
{
Elf32_Ehdr *hdr = vdso;
Elf32_Shdr *sechdrs, *alt_sec = 0;
@@ -52,7 +57,7 @@ static void __init patch_vdsox32(void *vdso, size_t len)
}
/* If we get here, it's probably a bug. */
- pr_warning("patch_vdsox32: .altinstructions not found\n");
+ pr_warning("patch_vdso32: .altinstructions not found\n");
return; /* nothing to patch */
found:
@@ -61,6 +66,7 @@ found:
}
#endif
+#if defined(CONFIG_X86_64)
static void __init patch_vdso64(void *vdso, size_t len)
{
Elf64_Ehdr *hdr = vdso;
@@ -104,7 +110,7 @@ static int __init init_vdso(void)
vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
#ifdef CONFIG_X86_X32_ABI
- patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
+ patch_vdso32(vdsox32_start, vdsox32_end - vdsox32_start);
npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
vdsox32_size = npages << PAGE_SHIFT;
for (i = 0; i < npages; i++)
@@ -204,3 +210,4 @@ static __init int vdso_setup(char *s)
return 0;
}
__setup("vdso=", vdso_setup);
+#endif
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 09/12] Add 32 bit VDSO time support for 32 bit kernel
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (7 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 08/12] Patch alternatives in the 32-bit vDSO Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 10/12] Add 32 bit VDSO time support for 64 " Stefani Seibold
` (2 subsequent siblings)
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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 | 8 ++++
arch/x86/vdso/vclock_gettime.c | 76 +++++++++++++++++++++++++++++++----
arch/x86/vdso/vdso-layout.lds.S | 22 ++++++++++
arch/x86/vdso/vdso32-setup.c | 53 +++++++++++++++++++++---
arch/x86/vdso/vdso32/vclock_gettime.c | 4 ++
arch/x86/vdso/vdso32/vdso32.lds.S | 9 +++++
8 files changed, 173 insertions(+), 13 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 6e39eb8..0f363c1 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..7efb701
--- /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 7a3d13e..6cef7a1 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -146,8 +146,16 @@ 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 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -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 09dae4a..90bb5e8 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.
*/
@@ -12,13 +15,11 @@
#define DISABLE_BRANCH_PROFILING
#include <linux/kernel.h>
-#include <linux/posix-timers.h>
-#include <linux/time.h>
+#include <uapi/linux/time.h>
#include <linux/string.h>
#include <asm/vsyscall.h>
#include <asm/fixmap.h>
#include <asm/vgtod.h>
-#include <asm/timex.h>
#include <asm/hpet.h>
#include <asm/unistd.h>
#include <asm/io.h>
@@ -26,6 +27,12 @@
#define gtod (&VVAR(vsyscall_gtod_data))
+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);
+
+#ifndef BUILD_VDSO32
+
static notrace cycle_t vread_hpet(void)
{
return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER);
@@ -118,6 +125,59 @@ static notrace cycle_t vread_pvclock(int *mode)
}
#endif
+#else
+
+extern u8 hpet_page
+ __attribute__((visibility("hidden")));
+
+#ifdef CONFIG_HPET_TIMER
+static notrace cycle_t vread_hpet(void)
+{
+ return readl((const void __iomem *)(&hpet_page + HPET_COUNTER));
+}
+#endif
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call VDSO32_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+ : "memory", "edx");
+ return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call VDSO32_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+ : "memory", "edx");
+ return ret;
+}
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+
+static notrace cycle_t vread_pvclock(int *mode)
+{
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif
+
+#endif
+
notrace static cycle_t vread_tsc(void)
{
cycle_t ret;
@@ -131,7 +191,7 @@ notrace static cycle_t vread_tsc(void)
* but no one has ever seen it happen.
*/
rdtsc_barrier();
- ret = (cycle_t)vget_cycles();
+ ret = (cycle_t)__native_read_tsc();
last = gtod->clock.cycle_last;
@@ -152,12 +212,14 @@ 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);
@@ -189,7 +251,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
return mode;
}
-notrace static int do_monotonic(struct timespec *ts)
+notrace static int __always_inline do_monotonic(struct timespec *ts)
{
unsigned long seq;
u64 ns;
@@ -284,7 +346,7 @@ 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 bca2ffd..54db7e4 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -25,6 +25,9 @@
#include <asm/tlbflush.h>
#include <asm/vdso.h>
#include <asm/proto.h>
+#include <asm/fixmap.h>
+#include <asm/hpet.h>
+#include <asm/vvar.h>
enum {
VDSO_DISABLED = 0,
@@ -193,7 +196,7 @@ 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
@@ -311,6 +314,7 @@ 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;
#ifdef CONFIG_X86_X32_ABI
if (test_thread_flag(TIF_X32))
@@ -331,11 +335,13 @@ 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;
@@ -344,13 +350,48 @@ 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..d9bb9fc
--- /dev/null
+++ b/arch/x86/vdso/vdso32/vclock_gettime.c
@@ -0,0 +1,4 @@
+#define BUILD_VDSO32
+
+#include "../vclock_gettime.c"
+
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S
index 976124b..bc8bf6d 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"
@@ -24,6 +27,9 @@ VERSION
__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;
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 10/12] Add 32 bit VDSO time support for 64 bit kernel
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (8 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 09/12] Add 32 bit VDSO time support for 32 bit kernel Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 9:20 ` [PATCH v21 12/12] x86: Zero-pad the VVAR page Stefani Seibold
2014-03-02 10:47 ` [PATCH v21 00/12] Add 32 bit VDSO time function support Ingo Molnar
11 siblings, 0 replies; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
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@seibold.net>
---
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@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
*
* Thanks to hpa@transmeta.com 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 90bb5e8..16d6861 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(>od->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(>od->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 __always_inline do_monotonic(struct timespec *ts)
u64 ns;
int mode;
- ts->tv_nsec = 0;
do {
- seq = raw_read_seqcount_begin(>od->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(>od->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(>od->seq);
- ts->tv_sec = gtod->wall_time_coarse.tv_sec;
- ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(>od->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(>od->seq);
- ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
- ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
- } while (unlikely(read_seqcount_retry(>od->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"
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v21 12/12] x86: Zero-pad the VVAR page
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (9 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 10/12] Add 32 bit VDSO time support for 64 " Stefani Seibold
@ 2014-03-02 9:20 ` Stefani Seibold
2014-03-02 10:46 ` Ingo Molnar
2014-03-02 10:47 ` [PATCH v21 00/12] Add 32 bit VDSO time function support Ingo Molnar
11 siblings, 1 reply; 16+ messages in thread
From: Stefani Seibold @ 2014-03-02 9:20 UTC (permalink / raw)
To: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko
Cc: Martin.Runge, Andreas.Brief, Stefani Seibold
By coincidence, the VVAR page is at the end of an ELF segment. As a
result, if it ends up being a partial page, the kernel loader will
leave garbage behind at the end of the vvar page. Zero-pad it to a
full page to fix this issue.
This has probably been broken since the VVAR page was introduced.
On QEMU, if you dump the run-time contents of the VVAR page, you can
find entertaining strings from seabios left behind.
It's remotely possible that this is a security bug -- conceivably
there's some BIOS out there that leaves something sensitive in the
few K of memory that is exposed to userspace.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
---
arch/x86/kernel/vmlinux.lds.S | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 1d4897b..49edf2d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -164,6 +164,11 @@ SECTIONS
#undef __VVAR_KERNEL_LDS
#undef EMIT_VVAR
+ /*
+ * Pad the rest of the page with zeros. Otherwise the loader
+ * can leave garbage here.
+ */
+ . = __vvar_beginning_hack + PAGE_SIZE;
} :data
. = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
--
1.9.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v21 12/12] x86: Zero-pad the VVAR page
2014-03-02 9:20 ` [PATCH v21 12/12] x86: Zero-pad the VVAR page Stefani Seibold
@ 2014-03-02 10:46 ` Ingo Molnar
0 siblings, 0 replies; 16+ messages in thread
From: Ingo Molnar @ 2014-03-02 10:46 UTC (permalink / raw)
To: Stefani Seibold
Cc: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko,
Martin.Runge, Andreas.Brief
* Stefani Seibold <stefani@seibold.net> wrote:
> By coincidence, the VVAR page is at the end of an ELF segment. As a
> result, if it ends up being a partial page, the kernel loader will
> leave garbage behind at the end of the vvar page. Zero-pad it to a
> full page to fix this issue.
>
> This has probably been broken since the VVAR page was introduced.
> On QEMU, if you dump the run-time contents of the VVAR page, you can
> find entertaining strings from seabios left behind.
>
> It's remotely possible that this is a security bug -- conceivably
> there's some BIOS out there that leaves something sensitive in the
> few K of memory that is exposed to userspace.
>
> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
> Signed-off-by: Stefani Seibold <stefani@seibold.net>
That's not a valid signoff sequence - if the patch came from Andy then
the patch needs to contain a From: Andy line as well. If Andy acked or
reviewed the patch then please add an Acked-by or Reviewed-by line.
Thanks,
Ingo
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v21 00/12] Add 32 bit VDSO time function support
2014-03-02 9:20 [PATCH v21 00/12] Add 32 bit VDSO time function support Stefani Seibold
` (10 preceding siblings ...)
2014-03-02 9:20 ` [PATCH v21 12/12] x86: Zero-pad the VVAR page Stefani Seibold
@ 2014-03-02 10:47 ` Ingo Molnar
2014-03-02 16:32 ` Andy Lutomirski
11 siblings, 1 reply; 16+ messages in thread
From: Ingo Molnar @ 2014-03-02 10:47 UTC (permalink / raw)
To: Stefani Seibold
Cc: gregkh, linux-kernel, x86, tglx, mingo, hpa, ak, aarcange,
john.stultz, luto, xemul, gorcunov, andriy.shevchenko,
Martin.Runge, Andreas.Brief
* Stefani Seibold <stefani@seibold.net> wrote:
> This patch add the functions vdso_gettimeofday(), vdso_clock_gettime()
> and vdso_time() to the 32 bit VDSO.
What I'm missing from all the series is any trace of the significant
review and debug work that Andy Lutomirski did for the series. Please
add Acked-by or Reviewed-by tags to credit his contributions, as
appropriate. (if Andy is fine with that.)
Thanks,
Ingo
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v21 00/12] Add 32 bit VDSO time function support
2014-03-02 10:47 ` [PATCH v21 00/12] Add 32 bit VDSO time function support Ingo Molnar
@ 2014-03-02 16:32 ` Andy Lutomirski
2014-03-02 21:02 ` H. Peter Anvin
0 siblings, 1 reply; 16+ messages in thread
From: Andy Lutomirski @ 2014-03-02 16:32 UTC (permalink / raw)
To: Ingo Molnar
Cc: Stefani Seibold, Greg KH, linux-kernel, X86 ML, Thomas Gleixner,
Ingo Molnar, H. Peter Anvin, Andi Kleen, Andrea Arcangeli,
John Stultz, Pavel Emelyanov, Cyrill Gorcunov, andriy.shevchenko,
Martin.Runge, Andreas.Brief
On Sun, Mar 2, 2014 at 2:47 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> * Stefani Seibold <stefani@seibold.net> wrote:
>
>> This patch add the functions vdso_gettimeofday(), vdso_clock_gettime()
>> and vdso_time() to the 32 bit VDSO.
>
> What I'm missing from all the series is any trace of the significant
> review and debug work that Andy Lutomirski did for the series. Please
> add Acked-by or Reviewed-by tags to credit his contributions, as
> appropriate. (if Andy is fine with that.)
>
I'm okay w/ Reviewed-by, except for the patch for 32-bit vdso on
64-bit, which I haven't really reviewed (nor do I feel fully qualified
to review it -- it's a bit of a core change, and I'd prefer for
someone involved in that code to comment on it).
For the patches I wrote, "From" would be nice :)
OTOH, hpa may prefer incremental patches, now that this lives in tip.
--Andy
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v21 00/12] Add 32 bit VDSO time function support
2014-03-02 16:32 ` Andy Lutomirski
@ 2014-03-02 21:02 ` H. Peter Anvin
0 siblings, 0 replies; 16+ messages in thread
From: H. Peter Anvin @ 2014-03-02 21:02 UTC (permalink / raw)
To: Andy Lutomirski, Ingo Molnar
Cc: Stefani Seibold, Greg KH, linux-kernel, X86 ML, Thomas Gleixner,
Ingo Molnar, Andi Kleen, Andrea Arcangeli, John Stultz,
Pavel Emelyanov, Cyrill Gorcunov, andriy.shevchenko,
Martin.Runge, Andreas.Brief
On 03/02/2014 08:32 AM, Andy Lutomirski wrote:
>
> OTOH, hpa may prefer incremental patches, now that this lives in tip.
>
The branch currently in -tip is dead, so it is not an issue either way.
-hpa
^ permalink raw reply [flat|nested] 16+ messages in thread