From: Dmitry Safonov <dima@arista.com>
To: linux-kernel@vger.kernel.org
Cc: Dmitry Safonov <0x7f454c46@gmail.com>,
Andrei Vagin <avagin@openvz.org>,
Dmitry Safonov <dima@arista.com>, Adrian Reber <adrian@lisas.de>,
Andy Lutomirski <luto@kernel.org>,
Christian Brauner <christian.brauner@ubuntu.com>,
Cyrill Gorcunov <gorcunov@openvz.org>,
"Eric W. Biederman" <ebiederm@xmission.com>,
"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>,
Jeff Dike <jdike@addtoit.com>, Oleg Nesterov <oleg@redhat.com>,
Pavel Emelyanov <xemul@virtuozzo.com>,
Shuah Khan <shuah@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
containers@lists.linux-foundation.org, criu@openvz.org,
linux-api@vger.kernel.org, x86@kernel.org
Subject: [RFC 09/20] x86/vdso/timens: Add offsets page in vvar
Date: Wed, 19 Sep 2018 21:50:26 +0100 [thread overview]
Message-ID: <20180919205037.9574-10-dima@arista.com> (raw)
In-Reply-To: <20180919205037.9574-1-dima@arista.com>
From: Andrei Vagin <avagin@openvz.org>
As modern applications fetch time from vdso without entering the kernel,
it's needed to provide offsets for userspace code.
Allocate a page for timens offsets when constructing time namespace.
As vdso mappings are platform-specific, add Kconfig dependency for arch.
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Co-developed-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
---
arch/Kconfig | 5 +++++
arch/x86/Kconfig | 1 +
arch/x86/entry/vdso/vclock_gettime.c | 26 ++++++++++++++++++++++++++
arch/x86/entry/vdso/vdso-layout.lds.S | 9 ++++++++-
arch/x86/entry/vdso/vdso2c.c | 3 +++
arch/x86/entry/vdso/vma.c | 12 ++++++++++++
arch/x86/include/asm/vdso.h | 1 +
init/Kconfig | 1 +
8 files changed, 57 insertions(+), 1 deletion(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 6801123932a5..411df0227a1d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -681,6 +681,11 @@ config HAVE_ARCH_HASH
config ISA_BUS_API
def_bool ISA
+config ARCH_HAS_VDSO_TIME_NS
+ bool
+ help
+ VDSO can add time-ns offsets without entering kernel.
+
#
# ABI hall of shame
#
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..4bcbdd1f1200 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -70,6 +70,7 @@ config X86
select ARCH_HAS_STRICT_MODULE_RWX
select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
select ARCH_HAS_UBSAN_SANITIZE_ALL
+ select ARCH_HAS_VDSO_TIME_NS
select ARCH_HAS_ZONE_DEVICE if X86_64
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index f19856d95c60..0594266740b9 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -21,6 +21,7 @@
#include <linux/math64.h>
#include <linux/time.h>
#include <linux/kernel.h>
+#include <linux/timens_offsets.h>
#define gtod (&VVAR(vsyscall_gtod_data))
@@ -38,6 +39,11 @@ extern u8 hvclock_page
__attribute__((visibility("hidden")));
#endif
+#ifdef CONFIG_TIME_NS
+extern u8 timens_page
+ __attribute__((visibility("hidden")));
+#endif
+
#ifndef BUILD_VDSO32
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -225,6 +231,23 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
return mode;
}
+notrace static __always_inline void monotonic_to_ns(struct timespec *ts)
+{
+#ifdef CONFIG_TIME_NS
+ struct timens_offsets *timens = (struct timens_offsets *) &timens_page;
+
+ ts->tv_sec += timens->monotonic_time_offset.tv_sec;
+ ts->tv_nsec += timens->monotonic_time_offset.tv_nsec;
+ if (ts->tv_nsec > NSEC_PER_SEC) {
+ ts->tv_nsec -= NSEC_PER_SEC;
+ ts->tv_sec++;
+ } else if (ts->tv_nsec < 0) {
+ ts->tv_nsec += NSEC_PER_SEC;
+ ts->tv_sec--;
+ }
+#endif
+}
+
notrace static int __always_inline do_monotonic(struct timespec *ts)
{
unsigned long seq;
@@ -243,6 +266,8 @@ notrace static int __always_inline do_monotonic(struct timespec *ts)
ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
ts->tv_nsec = ns;
+ monotonic_to_ns(ts);
+
return mode;
}
@@ -264,6 +289,7 @@ notrace static void do_monotonic_coarse(struct timespec *ts)
ts->tv_sec = gtod->monotonic_time_coarse_sec;
ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
} while (unlikely(gtod_read_retry(gtod, seq)));
+ monotonic_to_ns(ts);
}
notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index acfd5ba7d943..e5c2e9deca03 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -17,6 +17,12 @@
#define NUM_FAKE_SHDRS 13
+#ifdef CONFIG_TIME_NS
+# define TIMENS_SZ PAGE_SIZE
+#else
+# define TIMENS_SZ 0
+#endif
+
SECTIONS
{
/*
@@ -26,7 +32,7 @@ SECTIONS
* segment.
*/
- vvar_start = . - 3 * PAGE_SIZE;
+ vvar_start = . - (3 * PAGE_SIZE + TIMENS_SZ);
vvar_page = vvar_start;
/* Place all vvars at the offsets in asm/vvar.h. */
@@ -38,6 +44,7 @@ SECTIONS
pvclock_page = vvar_start + PAGE_SIZE;
hvclock_page = vvar_start + 2 * PAGE_SIZE;
+ timens_page = vvar_start + 3 * PAGE_SIZE;
. = SIZEOF_HEADERS;
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 4674f58581a1..6c67cde7fe99 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -76,6 +76,7 @@ enum {
sym_hpet_page,
sym_pvclock_page,
sym_hvclock_page,
+ sym_timens_page,
sym_VDSO_FAKE_SECTION_TABLE_START,
sym_VDSO_FAKE_SECTION_TABLE_END,
};
@@ -85,6 +86,7 @@ const int special_pages[] = {
sym_hpet_page,
sym_pvclock_page,
sym_hvclock_page,
+ sym_timens_page,
};
struct vdso_sym {
@@ -98,6 +100,7 @@ struct vdso_sym required_syms[] = {
[sym_hpet_page] = {"hpet_page", true},
[sym_pvclock_page] = {"pvclock_page", true},
[sym_hvclock_page] = {"hvclock_page", true},
+ [sym_timens_page] = {"timens_page", true},
[sym_VDSO_FAKE_SECTION_TABLE_START] = {
"VDSO_FAKE_SECTION_TABLE_START", false
},
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 8cc0395687b0..0f92227a4a7e 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -14,6 +14,7 @@
#include <linux/elf.h>
#include <linux/cpu.h>
#include <linux/ptrace.h>
+#include <linux/time_namespace.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
@@ -23,6 +24,7 @@
#include <asm/desc.h>
#include <asm/cpufeature.h>
#include <asm/mshyperv.h>
+#include <asm/page.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
@@ -138,6 +140,16 @@ static int vvar_fault(const struct vm_special_mapping *sm,
if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
ret = vm_insert_pfn(vma, vmf->address,
vmalloc_to_pfn(tsc_pg));
+ } else if (sym_offset == image->sym_timens_page) {
+ struct time_namespace *ns = current->nsproxy->time_ns;
+ unsigned long pfn;
+
+ if (!ns->offsets)
+ pfn = page_to_pfn(ZERO_PAGE(0));
+ else
+ pfn = page_to_pfn(virt_to_page(ns->offsets));
+
+ ret = vm_insert_pfn(vma, vmf->address, pfn);
}
if (ret == 0 || ret == -EBUSY)
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 27566e57e87d..619322065b8e 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -22,6 +22,7 @@ struct vdso_image {
long sym_hpet_page;
long sym_pvclock_page;
long sym_hvclock_page;
+ long sym_timens_page;
long sym_VDSO32_NOTE_MASK;
long sym___kernel_sigreturn;
long sym___kernel_rt_sigreturn;
diff --git a/init/Kconfig b/init/Kconfig
index dc2b40f7d73f..c9b250475ddb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -929,6 +929,7 @@ config UTS_NS
config TIME_NS
bool "TIME namespace"
+ depends on ARCH_HAS_VDSO_TIME_NS
default y
help
In this namespace boottime and monotonic clocks can be set.
--
2.13.6
next prev parent reply other threads:[~2018-09-19 20:50 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-19 20:50 [RFC 00/20] ns: Introduce Time Namespace Dmitry Safonov
2018-09-19 20:50 ` [RFC 01/20] " Dmitry Safonov
2018-09-28 18:20 ` Laurent Vivier
2018-09-19 20:50 ` [RFC 02/20] timens: Add timens_offsets Dmitry Safonov
2018-09-20 18:45 ` Cyrill Gorcunov
2018-09-20 22:14 ` Cyrill Gorcunov
2018-09-19 20:50 ` [RFC 03/20] timens: Introduce CLOCK_MONOTONIC offsets Dmitry Safonov
2018-09-19 20:50 ` [RFC 04/20] timens: Introduce CLOCK_BOOTTIME offset Dmitry Safonov
2018-09-30 3:18 ` [LKP] [timens] 3cc8de9dcb: RIP:posix_get_boottime kernel test robot
2018-09-19 20:50 ` [RFC 05/20] timerfd/timens: Take into account ns clock offsets Dmitry Safonov
2018-09-19 20:50 ` [RFC 06/20] kernel: Take into account timens clock offsets in clock_nanosleep Dmitry Safonov
2018-09-19 20:50 ` [RFC 07/20] timens: Shift /proc/uptime Dmitry Safonov
2018-09-19 20:50 ` [RFC 08/20] x86/vdso: Restrict splitting vvar vma Dmitry Safonov
2018-09-19 20:50 ` Dmitry Safonov [this message]
2018-09-19 20:50 ` [RFC 10/20] x86/vdso: Use set_normalized_timespec() to avoid 32 bit overflow Dmitry Safonov
2018-09-19 20:50 ` [RFC 11/20] x86/vdso: Purge timens page on setns()/unshare()/clone() Dmitry Safonov
2018-09-19 20:50 ` [RFC 12/20] x86/vdso: Look for vvar vma to purge timens page Dmitry Safonov
2018-09-19 20:50 ` [RFC 13/20] posix-timers/timens: Take into account clock offsets Dmitry Safonov
2018-09-30 3:11 ` [LKP] [posix] 25217c6e39: BUG:KASAN:null-ptr-deref_in_c kernel test robot
2018-09-19 20:50 ` [RFC 14/20] timens: Add align for timens_offsets Dmitry Safonov
2018-09-19 20:50 ` [RFC 15/20] timens: Optimize zero-offsets Dmitry Safonov
2018-09-19 20:50 ` [RFC 16/20] selftest: Add Time Namespace test for supported clocks Dmitry Safonov
2018-09-24 21:36 ` Shuah Khan
2018-09-19 20:50 ` [RFC 17/20] selftest/timens: Add test for timerfd Dmitry Safonov
2018-09-19 20:50 ` [RFC 18/20] selftest/timens: Add test for clock_nanosleep Dmitry Safonov
2018-09-19 20:50 ` [RFC 19/20] timens/selftest: Add procfs selftest Dmitry Safonov
2018-09-19 20:50 ` [RFC 20/20] timens/selftest: Add timer offsets test Dmitry Safonov
2018-09-21 12:27 ` [RFC 00/20] ns: Introduce Time Namespace Eric W. Biederman
2018-09-24 20:51 ` Andrey Vagin
2018-09-24 22:02 ` Eric W. Biederman
2018-09-25 1:42 ` Andrey Vagin
2018-09-26 17:36 ` Eric W. Biederman
2018-09-26 17:59 ` Dmitry Safonov
2018-09-27 21:30 ` Thomas Gleixner
2018-09-27 21:41 ` Thomas Gleixner
2018-10-01 23:20 ` Andrey Vagin
2018-10-02 6:15 ` Thomas Gleixner
2018-10-02 21:05 ` Dmitry Safonov
2018-10-02 21:26 ` Thomas Gleixner
2018-09-28 17:03 ` Eric W. Biederman
2018-09-28 19:32 ` Thomas Gleixner
2018-10-01 9:05 ` Eric W. Biederman
2018-10-01 9:15 ` Setting monotonic time? Eric W. Biederman
2018-10-01 18:52 ` Thomas Gleixner
2018-10-02 20:00 ` Arnd Bergmann
2018-10-02 20:06 ` Thomas Gleixner
2018-10-03 4:50 ` Eric W. Biederman
2018-10-03 5:25 ` Thomas Gleixner
2018-10-03 6:14 ` Eric W. Biederman
2018-10-03 7:02 ` Arnd Bergmann
2018-10-03 6:14 ` Thomas Gleixner
2018-10-01 20:51 ` Andrey Vagin
2018-10-02 6:16 ` Thomas Gleixner
2018-10-21 1:41 ` [RFC 00/20] ns: Introduce Time Namespace Andrei Vagin
2018-10-21 3:54 ` Andrei Vagin
2018-10-29 20:33 ` Thomas Gleixner
2018-10-29 21:21 ` Eric W. Biederman
2018-10-29 21:36 ` Thomas Gleixner
2018-10-31 16:26 ` Andrei Vagin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180919205037.9574-10-dima@arista.com \
--to=dima@arista.com \
--cc=0x7f454c46@gmail.com \
--cc=adrian@lisas.de \
--cc=avagin@openvz.org \
--cc=christian.brauner@ubuntu.com \
--cc=containers@lists.linux-foundation.org \
--cc=criu@openvz.org \
--cc=ebiederm@xmission.com \
--cc=gorcunov@openvz.org \
--cc=hpa@zytor.com \
--cc=jdike@addtoit.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=shuah@kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=xemul@virtuozzo.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).