Linux-api Archive on lore.kernel.org
 help / color / Atom feed
From: Dmitry Safonov <dima@arista.com>
To: linux-kernel@vger.kernel.org
Cc: Dmitry Safonov <0x7f454c46@gmail.com>,
	Dmitry Safonov <dima@arista.com>, Adrian Reber <adrian@lisas.de>,
	Andrei Vagin <avagin@openvz.org>,
	Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	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>,
	Jann Horn <jannh@google.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>,
	Vincenzo Frascino <vincenzo.frascino@arm.com>,
	containers@lists.linux-foundation.org, criu@openvz.org,
	linux-api@vger.kernel.org, x86@kernel.org
Subject: [PATCHv8 23/34] time: Allocate per-timens vvar page
Date: Tue, 12 Nov 2019 01:27:12 +0000
Message-ID: <20191112012724.250792-24-dima@arista.com> (raw)
In-Reply-To: <20191112012724.250792-1-dima@arista.com>

VDSO support for Time namespace needs to set up a page with the same
layout as VVAR. That timens page will be placed on position of VVAR page
inside namespace. That page contains time namespace clock offsets and it
has vdso_data->seq set to 1 to enforce the slow path and
vdso_data->clock_mode set to VCLOCK_TIMENS to enforce the time namespace
handling path.

Allocate the timens page during namespace creation. Setup the offsets
when the first task enters the ns and freeze them to guarantee the pace
of monotonic/boottime clocks and to avoid breakage of applications.

The design decision is to have a global offset_lock which is used
during namespace offsets set up and to freeze offsets when first task
joins the new ns. That is better in terms of memory usage comparing
to having per-ns mutex that's used only during the set up period.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Based-on-work-by: Thomas Gleixner <tglx@linutronix.de>
Co-developed-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
---
 include/linux/time_namespace.h |   3 +
 kernel/time/namespace.c        | 103 ++++++++++++++++++++++++++++++++-
 2 files changed, 105 insertions(+), 1 deletion(-)

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 90e82654b4ce..cdb438ba0037 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -23,6 +23,9 @@ struct time_namespace {
 	struct ucounts *ucounts;
 	struct ns_common ns;
 	struct timens_offsets offsets;
+	struct page *vvar_page;
+	/* Disallow changing offsets after any task joined namespace. */
+	bool frozen_offsets;
 } __randomize_layout;
 extern struct time_namespace init_time_ns;
 
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 1a0fbaa5d2d4..e14cd1ca387d 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -15,6 +15,7 @@
 #include <linux/cred.h>
 #include <linux/err.h>
 #include <linux/mm.h>
+#include <vdso/datapage.h>
 
 ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
 				struct timens_offsets *ns_offsets)
@@ -90,16 +91,23 @@ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
 
 	kref_init(&ns->kref);
 
+	ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!ns->vvar_page)
+		goto fail_free;
+
 	err = ns_alloc_inum(&ns->ns);
 	if (err)
-		goto fail_free;
+		goto fail_free_page;
 
 	ns->ucounts = ucounts;
 	ns->ns.ops = &timens_operations;
 	ns->user_ns = get_user_ns(user_ns);
 	ns->offsets = old_ns->offsets;
+	ns->frozen_offsets = false;
 	return ns;
 
+fail_free_page:
+	__free_page(ns->vvar_page);
 fail_free:
 	kfree(ns);
 fail_dec:
@@ -128,6 +136,93 @@ struct time_namespace *copy_time_ns(unsigned long flags,
 	return clone_time_ns(user_ns, old_ns);
 }
 
+static struct timens_offset offset_from_ts(struct timespec64 off)
+{
+	struct timens_offset ret;
+
+	ret.sec = off.tv_sec;
+	ret.nsec = off.tv_nsec;
+
+	return ret;
+}
+
+/*
+ * A time namespace VVAR page has the same layout as the VVAR page which
+ * contains the system wide VDSO data.
+ *
+ * For a normal task the VVAR pages are installed in the normal ordering:
+ *     VVAR
+ *     PVCLOCK
+ *     HVCLOCK
+ *     TIMENS   <- Not really required
+ *
+ * Now for a timens task the pages are installed in the following order:
+ *     TIMENS
+ *     PVCLOCK
+ *     HVCLOCK
+ *     VVAR
+ *
+ * The check for vdso_data->clock_mode is in the unlikely path of
+ * the seq begin magic. So for the non-timens case most of the time
+ * 'seq' is even, so the branch is not taken.
+ *
+ * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
+ * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the
+ * update to finish and for 'seq' to become even anyway.
+ *
+ * Timens page has vdso_data->clock_mode set to VCLOCK_TIMENS which enforces
+ * the time namespace handling path.
+ */
+static void timens_setup_vdso_data(struct vdso_data *vdata,
+				   struct time_namespace *ns)
+{
+	struct timens_offset *offset = vdata->offset;
+	struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
+	struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
+
+	vdata->seq			= 1;
+	vdata->clock_mode		= VCLOCK_TIMENS;
+	offset[CLOCK_MONOTONIC]		= monotonic;
+	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
+	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
+	offset[CLOCK_BOOTTIME]		= boottime;
+	offset[CLOCK_BOOTTIME_ALARM]	= boottime;
+}
+
+/*
+ * Protects possibly multiple offsets writers racing each other
+ * and tasks entering the namespace.
+ */
+static DEFINE_MUTEX(offset_lock);
+
+static void timens_set_vvar_page(struct task_struct *task,
+				struct time_namespace *ns)
+{
+	struct vdso_data *vdata;
+	unsigned int i;
+
+	if (ns == &init_time_ns)
+		return;
+
+	/* Fast-path, taken by every task in namespace except the first. */
+	if (likely(ns->frozen_offsets))
+		return;
+
+	mutex_lock(&offset_lock);
+	/* Nothing to-do: vvar_page has been already initialized. */
+	if (ns->frozen_offsets)
+		goto out;
+
+	ns->frozen_offsets = true;
+	vdata = arch_get_vdso_data(page_address(ns->vvar_page));
+
+	for (i = 0; i < CS_BASES; i++)
+		timens_setup_vdso_data(&vdata[i], ns);
+
+out:
+	mutex_unlock(&offset_lock);
+}
+
 void free_time_ns(struct kref *kref)
 {
 	struct time_namespace *ns;
@@ -136,6 +231,7 @@ void free_time_ns(struct kref *kref)
 	dec_time_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
+	__free_page(ns->vvar_page);
 	kfree(ns);
 }
 
@@ -192,6 +288,8 @@ static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
 	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
+	timens_set_vvar_page(current, ns);
+
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
@@ -211,6 +309,8 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
 	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
 		return 0;
 
+	timens_set_vvar_page(tsk, ns);
+
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
@@ -246,6 +346,7 @@ struct time_namespace init_time_ns = {
 	.user_ns	= &init_user_ns,
 	.ns.inum	= PROC_TIME_INIT_INO,
 	.ns.ops		= &timens_operations,
+	.frozen_offsets	= true,
 };
 
 static int __init time_ns_init(void)
-- 
2.24.0

  parent reply index

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-12  1:26 [PATCHv8 00/34] kernel: Introduce Time Namespace Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 01/34] lib/vdso: Add unlikely() hint into vdso_read_begin() Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 02/34] lib/vdso: make do_hres and do_coarse as __always_inline Dmitry Safonov
     [not found]   ` <20191112012724.250792-3-dima-nzgTgzXrdUbQT0dZR+AlfA@public.gmane.org>
2020-01-10  9:45     ` Vincenzo Frascino
2020-01-10 11:42       ` Thomas Gleixner
     [not found]         ` <878smfa66i.fsf-ecDvlHI5BZPZikZi3RtOZ1XZhhPuCNm+@public.gmane.org>
2020-01-10 11:47           ` Vincenzo Frascino
2020-01-10 12:02             ` Thomas Gleixner
     [not found]               ` <875zhja59q.fsf-ecDvlHI5BZPZikZi3RtOZ1XZhhPuCNm+@public.gmane.org>
2020-01-10 12:18                 ` Vincenzo Frascino
2020-01-13  5:27               ` Andrei Vagin
2019-11-12  1:26 ` [PATCHv8 03/34] ns: Introduce Time Namespace Dmitry Safonov
     [not found]   ` <20191112012724.250792-4-dima-nzgTgzXrdUbQT0dZR+AlfA@public.gmane.org>
2020-01-27 14:12     ` Dmitry Vyukov
     [not found]       ` <CACT4Y+b70bRRS2XD3yxhBoy4E-LFy_K3wMrjeuPmiEvaPe_c2Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2020-01-27 14:19         ` Dmitry Safonov
2020-02-17 14:20   ` Time Namespaces: CLONE_NEWTIME and clone3()? Michael Kerrisk
2020-02-17 14:59     ` Christian Brauner
2020-02-17 21:47       ` Michael Kerrisk (man-pages)
2020-02-17 23:03         ` Christian Brauner
2020-02-17 23:29           ` Thomas Gleixner
2020-02-18  2:37             ` Eric W. Biederman
2020-02-18 17:11           ` Adrian Reber
2020-02-18 17:26             ` Christian Brauner
2019-11-12  1:26 ` [PATCHv8 04/34] time: Add timens_offsets to be used for tasks in timens Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 05/34] posix-clocks: Rename the clock_get() callback to clock_get_timespec() Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 06/34] posix-clocks: Rename .clock_get_timespec() callbacks accordingly Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 07/34] alarmtimer: Rename gettime() callback to get_ktime() Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 08/34] alarmtimer: Provide get_timespec() callback Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 09/34] posix-clocks: Introduce clock_get_ktime() callback Dmitry Safonov
2019-11-12  1:26 ` [PATCHv8 10/34] posix-timers: Use clock_get_ktime() in common_timer_get() Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 11/34] posix-clocks: Wire up clock_gettime() with timens offsets Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 12/34] kernel: Add do_timens_ktime_to_host() helper Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 13/34] timerfd: Make timerfd_settime() time namespace aware Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 14/34] posix-timers: Make timer_settime() " Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 15/34] alarmtimer: Make nanosleep " Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 16/34] hrtimers: Prepare hrtimer_nanosleep() for time namespaces Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 17/34] posix-timers: Make clock_nanosleep() time namespace aware Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 18/34] fs/proc: Respect boottime inside time namespace for /proc/uptime Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 19/34] x86/vdso: Restrict splitting VVAR VMA Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 20/34] lib/vdso: Prepare for time namespace support Dmitry Safonov
     [not found]   ` <20191112012724.250792-21-dima-nzgTgzXrdUbQT0dZR+AlfA@public.gmane.org>
2020-01-12 10:32     ` Thomas Gleixner
2019-11-12  1:27 ` [PATCHv8 21/34] x86/vdso: Provide vdso_data offset on vvar_page Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 22/34] x86/vdso: Add timens page Dmitry Safonov
2019-11-12  1:27 ` Dmitry Safonov [this message]
2019-11-12  1:27 ` [PATCHv8 24/34] x86/vdso: Handle faults on " Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 25/34] x86/vdso: On timens page fault prefault also VVAR page Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 26/34] x86/vdso: Zap vvar pages on switch a time namspace Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 27/34] fs/proc: Introduce /proc/pid/timens_offsets Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 28/34] selftests/timens: Add Time Namespace test for supported clocks Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 29/34] selftests/timens: Add a test for timerfd Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 30/34] selftests/timens: Add a test for clock_nanosleep() Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 31/34] selftests/timens: Add procfs selftest Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 32/34] selftests/timens: Add timer offsets test Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 33/34] selftests/timens: Add a simple perf test for clock_gettime() Dmitry Safonov
2019-11-12  1:27 ` [PATCHv8 34/34] selftests/timens: Check for right timens offsets after fork and exec Dmitry Safonov
2019-11-21 18:05 ` [PATCHv8 00/34] kernel: Introduce Time Namespace Andrei Vagin
2019-12-11 20:38   ` Dmitry Safonov
2020-01-09 21:09     ` Thomas Gleixner
2020-01-10  9:52       ` Vincenzo Frascino

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=20191112012724.250792-24-dima@arista.com \
    --to=dima@arista.com \
    --cc=0x7f454c46@gmail.com \
    --cc=adrian@lisas.de \
    --cc=arnd@arndb.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=jannh@google.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=vincenzo.frascino@arm.com \
    --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

Linux-api Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-api/0 linux-api/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-api linux-api/ https://lore.kernel.org/linux-api \
		linux-api@vger.kernel.org
	public-inbox-index linux-api

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-api


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git