[GIT pull 0/7] Various tip branches

[GIT pull 0/7] Various tip branches

[Thomas Gleixner]

Linus,

the following pull request are my first attempt of using signed
tags. Please double check and yell if something went wrong.

Thanks,

	tglx

[GIT pull] core/core for

[Thomas Gleixner]

Linus,

please pull the latest core/core branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-core-2020-01-28

up to:  11e31f608b49: watchdog/softlockup: Enforce that timestamp is valid on boot

A set of watchdog/softlockup related improvements:

 - Enforce that the watchdog timestamp is always valid on boot. The
   original implementation caused a watchdog disabled gap of one second in
   the boot process due to truncation of the underlying sched clock. The
   sched clock is divided by 1e9 to convert nanoseconds to seconds. So for
   the first second of the boot process the result is 0 which is at the
   same time the indicator to disable the watchdog. The trivial fix is to
   change the disabled indicator to ULONG_MAX.

 - Two cleanup patches removing unused and redundant code which got
   forgotten to be cleaned up in previous changes.

Thanks,

	tglx

------------------>
Jisheng Zhang (1):
      watchdog: Remove soft_lockup_hrtimer_cnt and related code

Petr Mladek (1):
      watchdog/softlockup: Remove obsolete check of last reported task

Thomas Gleixner (1):
      watchdog/softlockup: Enforce that timestamp is valid on boot


 kernel/watchdog.c | 31 +++++++------------------------
 1 file changed, 7 insertions(+), 24 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f41334ef0971..b6b1f54a7837 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void)
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
+#define SOFTLOCKUP_RESET	ULONG_MAX
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -173,8 +175,6 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
-static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
@@ -274,7 +274,7 @@ notrace void touch_softlockup_watchdog_sched(void)
 	 * Preemption can be enabled.  It doesn't matter which CPU's timestamp
 	 * gets zeroed here, so use the raw_ operation.
 	 */
-	raw_cpu_write(watchdog_touch_ts, 0);
+	raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
 }
 
 notrace void touch_softlockup_watchdog(void)
@@ -298,14 +298,14 @@ void touch_all_softlockup_watchdogs(void)
 	 * the softlockup check.
 	 */
 	for_each_cpu(cpu, &watchdog_allowed_mask)
-		per_cpu(watchdog_touch_ts, cpu) = 0;
+		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
 	wq_watchdog_touch(-1);
 }
 
 void touch_softlockup_watchdog_sync(void)
 {
 	__this_cpu_write(softlockup_touch_sync, true);
-	__this_cpu_write(watchdog_touch_ts, 0);
+	__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
 }
 
 static int is_softlockup(unsigned long touch_ts)
@@ -350,8 +350,6 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
  */
 static int softlockup_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
 	complete(this_cpu_ptr(&softlockup_completion));
 
@@ -383,7 +381,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
 
-	if (touch_ts == 0) {
+	if (touch_ts == SOFTLOCKUP_RESET) {
 		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
 			/*
 			 * If the time stamp was touched atomically
@@ -416,22 +414,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			return HRTIMER_RESTART;
 
 		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true) {
-			/*
-			 * When multiple processes are causing softlockups the
-			 * softlockup detector only warns on the first one
-			 * because the code relies on a full quiet cycle to
-			 * re-arm.  The second process prevents the quiet cycle
-			 * and never gets reported.  Use task pointers to detect
-			 * this.
-			 */
-			if (__this_cpu_read(softlockup_task_ptr_saved) !=
-			    current) {
-				__this_cpu_write(soft_watchdog_warn, false);
-				__touch_watchdog();
-			}
+		if (__this_cpu_read(soft_watchdog_warn) == true)
 			return HRTIMER_RESTART;
-		}
 
 		if (softlockup_all_cpu_backtrace) {
 			/* Prevent multiple soft-lockup reports if one cpu is already
@@ -447,7 +431,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
-		__this_cpu_write(softlockup_task_ptr_saved, current);
 		print_modules();
 		print_irqtrace_events(current);
 		if (regs)

Re: [GIT pull] core/core for

[Linus Torvalds]

On Mon, Jan 27, 2020 at 4:06 PM Thomas Gleixner <tglx@linutronix.de> wrote:
>
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-core-2020-01-28

Hmm. Maybe this is related to the subject line after all.

I think that your tag naming has some bug in it, and then that bug
causes problems for the subject line?

"core-core" doesn't make much sense as a name, since it is about
watchdog logic.

My guess is that you automated this and something escaped through the cracks.

Again, not a big deal - everything _works_, it just has some oddities there.

            Linus

Re: [GIT pull] core/core for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-core-2020-01-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b11c89a158f29a9b9d740f8f60b74f261ce6557f

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] timers/urgent for 5.6-rc1

[Thomas Gleixner]

Linus,

please pull the latest timers/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2020-01-27

up to:  9f24c540f7f8: lib/vdso: Update coarse timekeeper unconditionally


Two fixes for the generic VDSO code which missed 5.5:

 - Make the update to the coarse timekeeper unconditional. This is required
   because the coarse timekeeper interfaces in the VDSO do not depend on a
   VDSO capable clocksource. If the system does not have a VDSO capable
   clocksource and the update is depending on the VDSO capable clocksource,
   the coarse VDSO interfaces would operate on stale data forever.

 - Invert the logic of __arch_update_vdso_data() to avoid further head
   scratching. Tripped over this several times while analyzing the update
   problem above.

Thanks,

	tglx

------------------>
Thomas Gleixner (2):
      lib/vdso: Make __arch_update_vdso_data() logic understandable
      lib/vdso: Update coarse timekeeper unconditionally


 arch/arm/include/asm/vdso/vsyscall.h |  4 ++--
 include/asm-generic/vdso/vsyscall.h  |  4 ++--
 kernel/time/vsyscall.c               | 37 +++++++++++++++++-------------------
 3 files changed, 21 insertions(+), 24 deletions(-)

diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h
index c4166f317071..cff87d8d30da 100644
--- a/arch/arm/include/asm/vdso/vsyscall.h
+++ b/arch/arm/include/asm/vdso/vsyscall.h
@@ -34,9 +34,9 @@ struct vdso_data *__arm_get_k_vdso_data(void)
 #define __arch_get_k_vdso_data __arm_get_k_vdso_data
 
 static __always_inline
-int __arm_update_vdso_data(void)
+bool __arm_update_vdso_data(void)
 {
-	return !cntvct_ok;
+	return cntvct_ok;
 }
 #define __arch_update_vdso_data __arm_update_vdso_data
 
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index ce4103208619..cec543d9e87b 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -12,9 +12,9 @@ static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
 #endif /* __arch_get_k_vdso_data */
 
 #ifndef __arch_update_vdso_data
-static __always_inline int __arch_update_vdso_data(void)
+static __always_inline bool __arch_update_vdso_data(void)
 {
-	return 0;
+	return true;
 }
 #endif /* __arch_update_vdso_data */
 
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 5ee0f7709410..9577c89179cd 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -28,11 +28,6 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 	vdata[CS_RAW].mult			= tk->tkr_raw.mult;
 	vdata[CS_RAW].shift			= tk->tkr_raw.shift;
 
-	/* CLOCK_REALTIME */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
-	vdso_ts->sec	= tk->xtime_sec;
-	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
-
 	/* CLOCK_MONOTONIC */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
@@ -70,12 +65,6 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
 	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
-
-	/*
-	 * Read without the seqlock held by clock_getres().
-	 * Note: No need to have a second copy.
-	 */
-	WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
 }
 
 void update_vsyscall(struct timekeeper *tk)
@@ -84,20 +73,17 @@ void update_vsyscall(struct timekeeper *tk)
 	struct vdso_timestamp *vdso_ts;
 	u64 nsec;
 
-	if (__arch_update_vdso_data()) {
-		/*
-		 * Some architectures might want to skip the update of the
-		 * data page.
-		 */
-		return;
-	}
-
 	/* copy vsyscall data */
 	vdso_write_begin(vdata);
 
 	vdata[CS_HRES_COARSE].clock_mode	= __arch_get_clock_mode(tk);
 	vdata[CS_RAW].clock_mode		= __arch_get_clock_mode(tk);
 
+	/* CLOCK_REALTIME also required for time() */
+	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
+	vdso_ts->sec	= tk->xtime_sec;
+	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
+
 	/* CLOCK_REALTIME_COARSE */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
 	vdso_ts->sec	= tk->xtime_sec;
@@ -110,7 +96,18 @@ void update_vsyscall(struct timekeeper *tk)
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
 	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
 
-	update_vdso_data(vdata, tk);
+	/*
+	 * Read without the seqlock held by clock_getres().
+	 * Note: No need to have a second copy.
+	 */
+	WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
+
+	/*
+	 * Architectures can opt out of updating the high resolution part
+	 * of the VDSO.
+	 */
+	if (__arch_update_vdso_data())
+		update_vdso_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata, tk);
 

Re: [GIT pull] timers/urgent for 5.6-rc1

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2020-01-27

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a56c41e5d766871231828046f477611d6ee7d2db

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] x86/pti for

[Thomas Gleixner]

Linus,

please pull the latest x86/pti branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-pti-2020-01-28

up to:  a84de2fa962c: x86/speculation/swapgs: Exclude Zhaoxin CPUs from SWAPGS vulnerability


The performance deterioration departement provides a few non-scary fixes
and improvements:

 - Update the cached HLE state when the TSX state is changed via the new
   control register. This ensures feature bit consistency.

 - Exclude the new Zhaoxin CPUs from Spectre V2 and SWAPGS vulnerabilities.


Thanks,

	tglx

------------------>
Pawan Gupta (1):
      x86/cpu: Update cached HLE state on write to TSX_CTRL_CPUID_CLEAR

Tony W Wang-oc (2):
      x86/speculation/spectre_v2: Exclude Zhaoxin CPUs from SPECTRE_V2
      x86/speculation/swapgs: Exclude Zhaoxin CPUs from SWAPGS vulnerability


 arch/x86/kernel/cpu/common.c |  9 ++++++++-
 arch/x86/kernel/cpu/tsx.c    | 13 +++++++------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2e4d90294fe6..ca4a0d2cc88f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1023,6 +1023,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define MSBDS_ONLY		BIT(5)
 #define NO_SWAPGS		BIT(6)
 #define NO_ITLB_MULTIHIT	BIT(7)
+#define NO_SPECTRE_V2		BIT(8)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1084,6 +1085,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
 	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+
+	/* Zhaoxin Family 7 */
+	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
+	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
 	{}
 };
 
@@ -1116,7 +1121,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
-	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+
+	if (!cpu_matches(NO_SPECTRE_V2))
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
 	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index 3e20d322bc98..032509adf9de 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -115,11 +115,12 @@ void __init tsx_init(void)
 		tsx_disable();
 
 		/*
-		 * tsx_disable() will change the state of the
-		 * RTM CPUID bit.  Clear it here since it is now
-		 * expected to be not set.
+		 * tsx_disable() will change the state of the RTM and HLE CPUID
+		 * bits. Clear them here since they are now expected to be not
+		 * set.
 		 */
 		setup_clear_cpu_cap(X86_FEATURE_RTM);
+		setup_clear_cpu_cap(X86_FEATURE_HLE);
 	} else if (tsx_ctrl_state == TSX_CTRL_ENABLE) {
 
 		/*
@@ -131,10 +132,10 @@ void __init tsx_init(void)
 		tsx_enable();
 
 		/*
-		 * tsx_enable() will change the state of the
-		 * RTM CPUID bit.  Force it here since it is now
-		 * expected to be set.
+		 * tsx_enable() will change the state of the RTM and HLE CPUID
+		 * bits. Force them here since they are now expected to be set.
 		 */
 		setup_force_cpu_cap(X86_FEATURE_RTM);
+		setup_force_cpu_cap(X86_FEATURE_HLE);
 	}
 }

Re: [GIT pull] x86/pti for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-pti-2020-01-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b0be0eff1a5ab77d588b76bd8b1c92d5d17b3f73

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] timers/core for

[Thomas Gleixner]

Linus,

please pull the latest timers/core branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-core-2020-01-27

up to:  fd928f3e32ba: alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n


The timekeeping and timers departement provides:

  - Time namespace support:

    If a container migrates from one host to another then it expects that
    clocks based on MONOTONIC and BOOTTIME are not subject to
    disruption. Due to different boot time and non-suspended runtime these
    clocks can differ significantly on two hosts, in the worst case time
    goes backwards which is a violation of the POSIX requirements.

    The time namespace addresses this problem. It allows to set offsets for
    clock MONOTONIC and BOOTTIME once after creation and before tasks are
    associated with the namespace. These offsets are taken into account by
    timers and timekeeping including the VDSO.

    Offsets for wall clock based clocks (REALTIME/TAI) are not provided by
    this mechanism. While in theory possible, the overhead and code
    complexity would be immense and not justified by the esoteric potential
    use cases which were discussed at Plumbers '18.

    The overhead for tasks in the root namespace (host time offsets = 0) is
    in the noise and great effort was made to ensure that especially in the
    VDSO. If time namespace is disabled in the kernel configuration the
    code is compiled out.

    Kudos to Andrei Vagin and Dmitry Sofanov who implemented this feature
    and kept on for more than a year addressing review comments, finding
    better solutions. A pleasant experience.

  - Overhaul of the alarmtimer device dependency handling to ensure that
    the init/suspend/resume ordering is correct.

  - A new clocksource/event driver for Microchip PIT64

  - Suspend/resume support for the Hyper-V clocksource

  - The usual pile of fixes, updates and improvements mostly in the
    driver code.


Thanks,

	tglx

------------------>
Andrea Parri (2):
      clocksource/drivers/hyper-v: Untangle stimers and timesync from clocksources
      clocksource/drivers/hyper-v: Set TSC clocksource as default w/ InvariantTSC

Andrei Vagin (23):
      lib/vdso: Add unlikely() hint into vdso_read_begin()
      lib/vdso: Mark do_hres() and do_coarse() as __always_inline
      ns: Introduce Time Namespace
      time: Add timens_offsets to be used for tasks in time namespace
      posix-clocks: Rename the clock_get() callback to clock_get_timespec()
      posix-clocks: Rename .clock_get_timespec() callbacks accordingly
      alarmtimer: Rename gettime() callback to get_ktime()
      alarmtimer: Provide get_timespec() callback
      posix-clocks: Introduce clock_get_ktime() callback
      posix-timers: Use clock_get_ktime() in common_timer_get()
      posix-clocks: Wire up clock_gettime() with timens offsets
      time: Add do_timens_ktime_to_host() helper
      timerfd: Make timerfd_settime() time namespace aware
      posix-timers: Make timer_settime() time namespace aware
      alarmtimer: Make nanosleep() time namespace aware
      hrtimers: Prepare hrtimer_nanosleep() for time namespaces
      posix-timers: Make clock_nanosleep() time namespace aware
      fs/proc: Introduce /proc/pid/timens_offsets
      selftests/timens: Add a test for timerfd
      selftests/timens: Add a test for clock_nanosleep()
      selftests/timens: Add timer offsets test
      selftests/timens: Add a simple perf test for clock_gettime()
      selftests/timens: Check for right timens offsets after fork and exec

Biju Das (1):
      dt-bindings: timer: renesas, cmt: Document r8a774b1 CMT support

Boqun Feng (1):
      clocksource/drivers/hyper-v: Reserve PAGE_SIZE space for tsc page

Christophe Leroy (3):
      lib/vdso: Let do_coarse() return 0 to simplify the callsite
      lib/vdso: Avoid duplication in __cvdso_clock_getres()
      lib/vdso: Only read hrtimer_res when needed in __cvdso_clock_getres()

Chunyan Zhang (1):
      tick/common: Touch watchdog in tick_unfreeze() on all CPUs

Claudiu Beznea (2):
      clocksource/drivers/timer-microchip-pit64b: Add Microchip PIT64B support
      clocksource/drivers/timer-microchip-pit64b: Fix sparse warning

Colin Ian King (1):
      clocksource/drivers/bcm2835_timer: Fix memory leak of timer

Dexuan Cui (1):
      clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation

Dmitry Safonov (10):
      fs/proc: Respect boottime inside time namespace for /proc/uptime
      x86/vdso: Restrict splitting VVAR VMA
      x86/vdso: Provide vdso_data offset on vvar_page
      x86/vdso: Add time napespace page
      time: Allocate per-timens vvar page
      x86/vdso: Handle faults on timens page
      x86/vdso: On timens page fault prefault also VVAR page
      x86/vdso: Zap vvar pages when switching to a time namespace
      selftests/timens: Add Time Namespace test for supported clocks
      selftests/timens: Add procfs selftest

Jules Irenge (1):
      hrtimer: Add missing sparse annotation for __run_timer()

Krzysztof Kozlowski (2):
      clocksource: Fix Kconfig indentation
      clocksource/drivers/exynos_mct: Rename Exynos to lowercase

Paul Cercueil (1):
      time/sched_clock: Disable interrupts in sched_clock_register()

Rajan Vaja (1):
      clocksource/drivers/cadence-ttc: Use ttc driver as platform driver

Randy Dunlap (1):
      clocksource: Fix Kconfig miscues

Stephen Boyd (5):
      alarmtimer: Unregister wakeup source when module get fails
      alarmtimer: Update alarmtimer_get_rtcdev() docs to reflect reality
      alarmtimer: Make alarmtimer platform device child of RTC device
      alarmtimer: Use wakeup source from alarmtimer platform device
      alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n

Thomas Gleixner (3):
      ARM: vdso: Set BUILD_VDSO32 and provide 32bit fallbacks
      lib/vdso: Prepare for time namespace support
      MIPS: vdso: Define BUILD_VDSO32 when building a 32bit kernel

Tony Lindgren (1):
      clocksource/drivers/timer-ti-dm: Fix uninitialized pointer access

Vincenzo Frascino (7):
      arm64: compat: vdso: Expose BUILD_VDSO32
      lib/vdso: Build 32 bit specific functions in the right context
      lib/vdso: Remove VDSO_HAS_32BIT_FALLBACK
      lib/vdso: Remove checks on return value for 32 bit vDSO
      arm64: compat: vdso: Remove unused VDSO_HAS_32BIT_FALLBACK
      mips: vdso: Remove unused VDSO_HAS_32BIT_FALLBACK
      x86/vdso: Remove unused VDSO_HAS_32BIT_FALLBACK

Yangtao Li (4):
      clocksource/drivers/em_sti: Convert to devm_platform_ioremap_resource
      clocksource/drivers/em_sti: Fix variable declaration in em_sti_probe
      clocksource/drivers/timer-ti-dm: Convert to devm_platform_ioremap_resource
      clocksource/drivers/timer-ti-dm: Switch to platform_get_irq


 .../devicetree/bindings/arm/atmel-sysregs.txt      |   6 +
 .../devicetree/bindings/timer/renesas,cmt.txt      |   2 +
 MAINTAINERS                                        |   2 +
 arch/arm/include/asm/vdso/gettimeofday.h           |  36 ++
 arch/arm/vdso/Makefile                             |   2 +-
 arch/arm64/include/asm/vdso/compat_gettimeofday.h  |   2 +-
 arch/mips/include/asm/vdso/gettimeofday.h          |   2 -
 arch/mips/vdso/Makefile                            |   4 +
 arch/x86/Kconfig                                   |   1 +
 arch/x86/entry/vdso/vdso-layout.lds.S              |  13 +-
 arch/x86/entry/vdso/vdso2c.c                       |   3 +
 arch/x86/entry/vdso/vma.c                          | 120 +++++-
 arch/x86/include/asm/vdso.h                        |   1 +
 arch/x86/include/asm/vdso/gettimeofday.h           |  10 +-
 arch/x86/include/asm/vvar.h                        |  13 +-
 arch/x86/kernel/vmlinux.lds.S                      |   4 +-
 drivers/clocksource/Kconfig                        |  76 ++--
 drivers/clocksource/Makefile                       |   1 +
 drivers/clocksource/bcm2835_timer.c                |   5 +-
 drivers/clocksource/em_sti.c                       |   7 +-
 drivers/clocksource/exynos_mct.c                   |   2 +-
 drivers/clocksource/hyperv_timer.c                 |  84 +++-
 drivers/clocksource/timer-cadence-ttc.c            |  26 +-
 drivers/clocksource/timer-microchip-pit64b.c       | 451 ++++++++++++++++++++
 drivers/clocksource/timer-ti-dm.c                  |  20 +-
 drivers/hv/hv_util.c                               |   8 +-
 fs/proc/base.c                                     |  94 +++++
 fs/proc/namespaces.c                               |   4 +
 fs/proc/uptime.c                                   |   3 +
 fs/timerfd.c                                       |   3 +
 include/clocksource/hyperv_timer.h                 |   2 +-
 include/linux/alarmtimer.h                         |   4 +
 include/linux/hrtimer.h                            |   3 +-
 include/linux/nsproxy.h                            |   2 +
 include/linux/proc_ns.h                            |   3 +
 include/linux/time.h                               |   6 +
 include/linux/time_namespace.h                     | 133 ++++++
 include/linux/user_namespace.h                     |   1 +
 include/uapi/linux/sched.h                         |   6 +
 include/vdso/datapage.h                            |  19 +-
 include/vdso/helpers.h                             |   2 +-
 init/Kconfig                                       |   8 +
 kernel/fork.c                                      |  16 +-
 kernel/nsproxy.c                                   |  41 +-
 kernel/time/Makefile                               |   1 +
 kernel/time/alarmtimer.c                           | 121 +++---
 kernel/time/hrtimer.c                              |  14 +-
 kernel/time/namespace.c                            | 468 +++++++++++++++++++++
 kernel/time/posix-clock.c                          |   8 +-
 kernel/time/posix-cpu-timers.c                     |  32 +-
 kernel/time/posix-stubs.c                          |  15 +-
 kernel/time/posix-timers.c                         |  88 ++--
 kernel/time/posix-timers.h                         |   7 +-
 kernel/time/sched_clock.c                          |   7 +-
 kernel/time/tick-common.c                          |   2 +
 lib/vdso/Kconfig                                   |   6 +
 lib/vdso/gettimeofday.c                            | 204 +++++++--
 mm/mmap.c                                          |   2 +
 tools/perf/examples/bpf/5sec.c                     |   6 +-
 tools/testing/selftests/Makefile                   |   1 +
 tools/testing/selftests/timens/.gitignore          |   8 +
 tools/testing/selftests/timens/Makefile            |   7 +
 tools/testing/selftests/timens/clock_nanosleep.c   | 149 +++++++
 tools/testing/selftests/timens/config              |   1 +
 tools/testing/selftests/timens/exec.c              |  94 +++++
 tools/testing/selftests/timens/gettime_perf.c      |  95 +++++
 tools/testing/selftests/timens/log.h               |  26 ++
 tools/testing/selftests/timens/procfs.c            | 144 +++++++
 tools/testing/selftests/timens/timens.c            | 190 +++++++++
 tools/testing/selftests/timens/timens.h            | 100 +++++
 tools/testing/selftests/timens/timer.c             | 122 ++++++
 tools/testing/selftests/timens/timerfd.c           | 128 ++++++
 72 files changed, 3027 insertions(+), 270 deletions(-)
 create mode 100644 drivers/clocksource/timer-microchip-pit64b.c
 create mode 100644 include/linux/time_namespace.h
 create mode 100644 kernel/time/namespace.c
 create mode 100644 tools/testing/selftests/timens/.gitignore
 create mode 100644 tools/testing/selftests/timens/Makefile
 create mode 100644 tools/testing/selftests/timens/clock_nanosleep.c
 create mode 100644 tools/testing/selftests/timens/config
 create mode 100644 tools/testing/selftests/timens/exec.c
 create mode 100644 tools/testing/selftests/timens/gettime_perf.c
 create mode 100644 tools/testing/selftests/timens/log.h
 create mode 100644 tools/testing/selftests/timens/procfs.c
 create mode 100644 tools/testing/selftests/timens/timens.c
 create mode 100644 tools/testing/selftests/timens/timens.h
 create mode 100644 tools/testing/selftests/timens/timer.c
 create mode 100644 tools/testing/selftests/timens/timerfd.c

diff --git a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
index 9fbde401a090..e003a553b986 100644
--- a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
@@ -10,6 +10,12 @@ PIT Timer required properties:
 - interrupts: Should contain interrupt for the PIT which is the IRQ line
   shared across all System Controller members.
 
+PIT64B Timer required properties:
+- compatible: Should be "microchip,sam9x60-pit64b"
+- reg: Should contain registers location and length
+- interrupts: Should contain interrupt for PIT64B timer
+- clocks: Should contain the available clock sources for PIT64B timer.
+
 System Timer (ST) required properties:
 - compatible: Should be "atmel,at91rm9200-st", "syscon", "simple-mfd"
 - reg: Should contain registers location and length
diff --git a/Documentation/devicetree/bindings/timer/renesas,cmt.txt b/Documentation/devicetree/bindings/timer/renesas,cmt.txt
index a444cfc5852a..a747fabab7d3 100644
--- a/Documentation/devicetree/bindings/timer/renesas,cmt.txt
+++ b/Documentation/devicetree/bindings/timer/renesas,cmt.txt
@@ -29,6 +29,8 @@ Required Properties:
     - "renesas,r8a77470-cmt1" for the 48-bit CMT1 device included in r8a77470.
     - "renesas,r8a774a1-cmt0" for the 32-bit CMT0 device included in r8a774a1.
     - "renesas,r8a774a1-cmt1" for the 48-bit CMT devices included in r8a774a1.
+    - "renesas,r8a774b1-cmt0" for the 32-bit CMT0 device included in r8a774b1.
+    - "renesas,r8a774b1-cmt1" for the 48-bit CMT devices included in r8a774b1.
     - "renesas,r8a774c0-cmt0" for the 32-bit CMT0 device included in r8a774c0.
     - "renesas,r8a774c0-cmt1" for the 48-bit CMT devices included in r8a774c0.
     - "renesas,r8a7790-cmt0" for the 32-bit CMT0 device included in r8a7790.
diff --git a/MAINTAINERS b/MAINTAINERS
index 8982c6e013b3..f6d00023e56f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13214,6 +13214,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 S:	Maintained
 F:	fs/timerfd.c
 F:	include/linux/timer*
+F:	include/linux/time_namespace.h
+F:	kernel/time_namespace.c
 F:	kernel/time/*timer*
 
 POWER MANAGEMENT CORE
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 0ad2429c324f..fe6e1f65932d 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -52,6 +52,24 @@ static __always_inline long clock_gettime_fallback(
 	return ret;
 }
 
+static __always_inline long clock_gettime32_fallback(
+					clockid_t _clkid,
+					struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_gettime;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
 static __always_inline int clock_getres_fallback(
 					clockid_t _clkid,
 					struct __kernel_timespec *_ts)
@@ -70,6 +88,24 @@ static __always_inline int clock_getres_fallback(
 	return ret;
 }
 
+static __always_inline int clock_getres32_fallback(
+					clockid_t _clkid,
+					struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_getres;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
 static __always_inline u64 __arch_get_hw_counter(int clock_mode)
 {
 #ifdef CONFIG_ARM_ARCH_TIMER
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 0fda344beb0b..1babb392e70a 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -14,7 +14,7 @@ targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.so.raw vdso.lds
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
 ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
-ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
 
 ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
 ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index c50ee1b7d5cd..537b1e695365 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -16,7 +16,7 @@
 
 #define VDSO_HAS_CLOCK_GETRES		1
 
-#define VDSO_HAS_32BIT_FALLBACK		1
+#define BUILD_VDSO32			1
 
 static __always_inline
 int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index 0ae9b4cbc153..a58687e26c5d 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -96,8 +96,6 @@ static __always_inline int clock_getres_fallback(
 
 #if _MIPS_SIM != _MIPS_SIM_ABI64
 
-#define VDSO_HAS_32BIT_FALLBACK	1
-
 static __always_inline long clock_gettime32_fallback(
 					clockid_t _clkid,
 					struct old_timespec32 *_ts)
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index e05938997e69..b2a2e032dc99 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -18,6 +18,10 @@ ccflags-vdso := \
 	$(filter -mno-loongson-%,$(KBUILD_CFLAGS)) \
 	-D__VDSO__
 
+ifndef CONFIG_64BIT
+ccflags-vdso += -DBUILD_VDSO32
+endif
+
 ifdef CONFIG_CC_IS_CLANG
 ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS))
 endif
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e8949953660..a2488c372fa1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -124,6 +124,7 @@ config X86
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_TIME_NS
 	select GUP_GET_PTE_LOW_HIGH		if X86_PAE
 	select HARDLOCKUP_CHECK_TIMESTAMP	if X86_64
 	select HAVE_ACPI_APEI			if ACPI
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 93c6dc7812d0..ea7e0155c604 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -16,18 +16,23 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 3 * PAGE_SIZE;
-	vvar_page = vvar_start;
+	vvar_start = . - 4 * PAGE_SIZE;
+	vvar_page  = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
 #define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
-#define __VVAR_KERNEL_LDS
 #include <asm/vvar.h>
-#undef __VVAR_KERNEL_LDS
 #undef EMIT_VVAR
 
 	pvclock_page = vvar_start + PAGE_SIZE;
 	hvclock_page = vvar_start + 2 * PAGE_SIZE;
+	timens_page  = vvar_start + 3 * PAGE_SIZE;
+
+#undef _ASM_X86_VVAR_H
+	/* Place all vvars in timens too at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) timens_ ## name = timens_page + offset;
+#include <asm/vvar.h>
+#undef EMIT_VVAR
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 3a4d8d4d39f8..3842873b3ae3 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -75,12 +75,14 @@ enum {
 	sym_vvar_page,
 	sym_pvclock_page,
 	sym_hvclock_page,
+	sym_timens_page,
 };
 
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_pvclock_page,
 	sym_hvclock_page,
+	sym_timens_page,
 };
 
 struct vdso_sym {
@@ -93,6 +95,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_hvclock_page] = {"hvclock_page", true},
+	[sym_timens_page] = {"timens_page", true},
 	{"VDSO32_NOTE_MASK", true},
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index f5937742b290..c1b8496b5606 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -14,16 +14,30 @@
 #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>
 #include <asm/vdso.h>
 #include <asm/vvar.h>
+#include <asm/tlb.h>
 #include <asm/page.h>
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
 #include <clocksource/hyperv_timer.h>
 
+#undef _ASM_X86_VVAR_H
+#define EMIT_VVAR(name, offset)	\
+	const size_t name ## _offset = offset;
+#include <asm/vvar.h>
+
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page + _vdso_data_offset);
+}
+#undef EMIT_VVAR
+
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
 #endif
@@ -37,6 +51,7 @@ void __init init_vdso_image(const struct vdso_image *image)
 						image->alt_len));
 }
 
+static const struct vm_special_mapping vvar_mapping;
 struct linux_binprm;
 
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
@@ -84,10 +99,74 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
+static int vvar_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	const struct vdso_image *image = new_vma->vm_mm->context.vdso_image;
+	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+
+	if (new_size != -image->sym_vvar_start)
+		return -EINVAL;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops().
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+
+/*
+ * The vvar page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_data() for details.
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, &vvar_mapping))
+			zap_page_range(vma, vma->vm_start, size);
+	}
+
+	up_write(&mm->mmap_sem);
+	return 0;
+}
+#else
+static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
 static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	unsigned long pfn;
 	long sym_offset;
 
 	if (!image)
@@ -107,8 +186,36 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 		return VM_FAULT_SIGBUS;
 
 	if (sym_offset == image->sym_vvar_page) {
-		return vmf_insert_pfn(vma, vmf->address,
-				__pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+		struct page *timens_page = find_timens_vvar_page(vma);
+
+		pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT;
+
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the sym_vvar_page offset and
+		 * the real VVAR page is mapped with the sym_timens_page
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (timens_page) {
+			unsigned long addr;
+			vm_fault_t err;
+
+			/*
+			 * Optimization: inside time namespace pre-fault
+			 * VVAR page too. As on timens page there are only
+			 * offsets for clocks on VVAR, it'll be faulted
+			 * shortly by VDSO code.
+			 */
+			addr = vmf->address + (image->sym_timens_page - sym_offset);
+			err = vmf_insert_pfn(vma, addr, pfn);
+			if (unlikely(err & VM_FAULT_ERROR))
+				return err;
+
+			pfn = page_to_pfn(timens_page);
+		}
+
+		return vmf_insert_pfn(vma, vmf->address, pfn);
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_get_pvti_cpu0_va();
@@ -123,6 +230,14 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 		if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
 			return vmf_insert_pfn(vma, vmf->address,
 					virt_to_phys(tsc_pg) >> PAGE_SHIFT);
+	} else if (sym_offset == image->sym_timens_page) {
+		struct page *timens_page = find_timens_vvar_page(vma);
+
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+
+		pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT;
+		return vmf_insert_pfn(vma, vmf->address, pfn);
 	}
 
 	return VM_FAULT_SIGBUS;
@@ -136,6 +251,7 @@ static const struct vm_special_mapping vdso_mapping = {
 static const struct vm_special_mapping vvar_mapping = {
 	.name = "[vvar]",
 	.fault = vvar_fault,
+	.mremap = vvar_mremap,
 };
 
 /*
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 230474e2ddb5..bbcdc7b8f963 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -21,6 +21,7 @@ struct vdso_image {
 	long sym_vvar_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/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index e9ee139cf29e..6ee1f7dba34b 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -21,6 +21,7 @@
 #include <clocksource/hyperv_timer.h>
 
 #define __vdso_data (VVAR(_vdso_data))
+#define __timens_vdso_data (TIMENS(_vdso_data))
 
 #define VDSO_HAS_TIME 1
 
@@ -56,6 +57,13 @@ extern struct ms_hyperv_tsc_page hvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
+#ifdef CONFIG_TIME_NS
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return __timens_vdso_data;
+}
+#endif
+
 #ifndef BUILD_VDSO32
 
 static __always_inline
@@ -96,8 +104,6 @@ long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 
 #else
 
-#define VDSO_HAS_32BIT_FALLBACK	1
-
 static __always_inline
 long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 {
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 32f5d9a0b90e..183e98e49ab9 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -19,10 +19,10 @@
 #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
- * right place.
+#ifdef EMIT_VVAR
+/*
+ * EMIT_VVAR() is used by the kernel linker script to put vvars in the
+ * right place. Also, it's used by kernel code to import offsets values.
  */
 #define DECLARE_VVAR(offset, type, name) \
 	EMIT_VVAR(name, offset)
@@ -33,9 +33,12 @@ extern char __vvar_page;
 
 #define DECLARE_VVAR(offset, type, name)				\
 	extern type vvar_ ## name[CS_BASES]				\
-	__attribute__((visibility("hidden")));
+	__attribute__((visibility("hidden")));				\
+	extern type timens_ ## name[CS_BASES]				\
+	__attribute__((visibility("hidden")));				\
 
 #define VVAR(name) (vvar_ ## name)
+#define TIMENS(name) (timens_ ## name)
 
 #define DEFINE_VVAR(type, name)						\
 	type name[CS_BASES]						\
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3a1a819da137..e3296aa028fe 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -193,12 +193,10 @@ SECTIONS
 		__vvar_beginning_hack = .;
 
 		/* Place all vvars at the offsets in asm/vvar.h. */
-#define EMIT_VVAR(name, offset) 			\
+#define EMIT_VVAR(name, offset)				\
 		. = __vvar_beginning_hack + offset;	\
 		*(.vvar_ ## name)
-#define __VVAR_KERNEL_LDS
 #include <asm/vvar.h>
-#undef __VVAR_KERNEL_LDS
 #undef EMIT_VVAR
 
 		/*
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 5fdd76cb1768..cc909e465823 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -88,7 +88,7 @@ config ROCKCHIP_TIMER
 	select TIMER_OF
 	select CLKSRC_MMIO
 	help
-	  Enables the support for the rockchip timer driver.
+	  Enables the support for the Rockchip timer driver.
 
 config ARMADA_370_XP_TIMER
 	bool "Armada 370 and XP timer driver" if COMPILE_TEST
@@ -162,13 +162,13 @@ config NPCM7XX_TIMER
 	select CLKSRC_MMIO
 	help
 	  Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
-	  While TIMER0 serves as clockevent and TIMER1 serves as clocksource.
+	  where TIMER0 serves as clockevent and TIMER1 serves as clocksource.
 
 config CADENCE_TTC_TIMER
 	bool "Cadence TTC timer driver" if COMPILE_TEST
 	depends on COMMON_CLK
 	help
-	  Enables support for the cadence ttc driver.
+	  Enables support for the Cadence TTC driver.
 
 config ASM9260_TIMER
 	bool "ASM9260 timer driver" if COMPILE_TEST
@@ -190,10 +190,10 @@ config CLKSRC_DBX500_PRCMU
 	bool "Clocksource PRCMU Timer" if COMPILE_TEST
 	depends on HAS_IOMEM
 	help
-	  Use the always on PRCMU Timer as clocksource
+	  Use the always on PRCMU Timer as clocksource.
 
 config CLPS711X_TIMER
-	bool "Cirrus logic timer driver" if COMPILE_TEST
+	bool "Cirrus Logic timer driver" if COMPILE_TEST
 	select CLKSRC_MMIO
 	help
 	  Enables support for the Cirrus Logic PS711 timer.
@@ -205,11 +205,11 @@ config ATLAS7_TIMER
 	  Enables support for the Atlas7 timer.
 
 config MXS_TIMER
-	bool "Mxs timer driver" if COMPILE_TEST
+	bool "MXS timer driver" if COMPILE_TEST
 	select CLKSRC_MMIO
 	select STMP_DEVICE
 	help
-	  Enables support for the Mxs timer.
+	  Enables support for the MXS timer.
 
 config PRIMA2_TIMER
 	bool "Prima2 timer driver" if COMPILE_TEST
@@ -238,10 +238,10 @@ config KEYSTONE_TIMER
 	  Enables support for the Keystone timer.
 
 config INTEGRATOR_AP_TIMER
-	bool "Integrator-ap timer driver" if COMPILE_TEST
+	bool "Integrator-AP timer driver" if COMPILE_TEST
 	select CLKSRC_MMIO
 	help
-	  Enables support for the Integrator-ap timer.
+	  Enables support for the Integrator-AP timer.
 
 config CLKSRC_EFM32
 	bool "Clocksource for Energy Micro's EFM32 SoCs" if !ARCH_EFM32
@@ -283,8 +283,8 @@ config CLKSRC_NPS
 	select TIMER_OF if OF
 	help
 	  NPS400 clocksource support.
-	  Got 64 bit counter with update rate up to 1000MHz.
-	  This counter is accessed via couple of 32 bit memory mapped registers.
+	  It has a 64-bit counter with update rate up to 1000MHz.
+	  This counter is accessed via couple of 32-bit memory-mapped registers.
 
 config CLKSRC_STM32
 	bool "Clocksource for STM32 SoCs" if !ARCH_STM32
@@ -305,14 +305,14 @@ config ARC_TIMERS
 	help
 	  These are legacy 32-bit TIMER0 and TIMER1 counters found on all ARC cores
 	  (ARC700 as well as ARC HS38).
-	  TIMER0 serves as clockevent while TIMER1 provides clocksource
+	  TIMER0 serves as clockevent while TIMER1 provides clocksource.
 
 config ARC_TIMERS_64BIT
 	bool "Support for 64-bit counters in ARC HS38 cores" if COMPILE_TEST
 	depends on ARC_TIMERS
 	select TIMER_OF
 	help
-	  This enables 2 different 64-bit timers: RTC (for UP) and GFRC (for SMP)
+	  This enables 2 different 64-bit timers: RTC (for UP) and GFRC (for SMP).
 	  RTC is implemented inside the core, while GFRC sits outside the core in
 	  ARConnect IP block. Driver automatically picks one of them for clocksource
 	  as appropriate.
@@ -390,7 +390,7 @@ config ARM_GLOBAL_TIMER
 	select TIMER_OF if OF
 	depends on ARM
 	help
-	  This options enables support for the ARM global timer unit
+	  This option enables support for the ARM global timer unit.
 
 config ARM_TIMER_SP804
 	bool "Support for Dual Timer SP804 module" if COMPILE_TEST
@@ -403,14 +403,14 @@ config CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
 	depends on ARM_GLOBAL_TIMER
 	default y
 	help
-	 Use ARM global timer clock source as sched_clock
+	  Use ARM global timer clock source as sched_clock.
 
 config ARMV7M_SYSTICK
 	bool "Support for the ARMv7M system time" if COMPILE_TEST
 	select TIMER_OF if OF
 	select CLKSRC_MMIO
 	help
-	  This options enables support for the ARMv7M system timer unit
+	  This option enables support for the ARMv7M system timer unit.
 
 config ATMEL_PIT
 	bool "Atmel PIT support" if COMPILE_TEST
@@ -460,7 +460,7 @@ config VF_PIT_TIMER
 	bool
 	select CLKSRC_MMIO
 	help
-	  Support for Period Interrupt Timer on Freescale Vybrid Family SoCs.
+	  Support for Periodic Interrupt Timer on Freescale Vybrid Family SoCs.
 
 config OXNAS_RPS_TIMER
 	bool "Oxford Semiconductor OXNAS RPS Timers driver" if COMPILE_TEST
@@ -470,7 +470,7 @@ config OXNAS_RPS_TIMER
 	  This enables support for the Oxford Semiconductor OXNAS RPS timers.
 
 config SYS_SUPPORTS_SH_CMT
-        bool
+	bool
 
 config MTK_TIMER
 	bool "Mediatek timer driver" if COMPILE_TEST
@@ -490,13 +490,13 @@ config SPRD_TIMER
 	  Enables support for the Spreadtrum timer driver.
 
 config SYS_SUPPORTS_SH_MTU2
-        bool
+	bool
 
 config SYS_SUPPORTS_SH_TMU
-        bool
+	bool
 
 config SYS_SUPPORTS_EM_STI
-        bool
+	bool
 
 config CLKSRC_JCORE_PIT
 	bool "J-Core PIT timer driver" if COMPILE_TEST
@@ -523,7 +523,7 @@ config SH_TIMER_MTU2
 	help
 	  This enables build of a clockevent driver for the Multi-Function
 	  Timer Pulse Unit 2 (MTU2) hardware available on SoCs from Renesas.
-	  This hardware comes with 16 bit-timer registers.
+	  This hardware comes with 16-bit timer registers.
 
 config RENESAS_OSTM
 	bool "Renesas OSTM timer driver" if COMPILE_TEST
@@ -580,7 +580,7 @@ config CLKSRC_TANGO_XTAL
 	select TIMER_OF
 	select CLKSRC_MMIO
 	help
-	  This enables the clocksource for Tango SoC
+	  This enables the clocksource for Tango SoC.
 
 config CLKSRC_PXA
 	bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST
@@ -591,24 +591,24 @@ config CLKSRC_PXA
 	  platforms.
 
 config H8300_TMR8
-        bool "Clockevent timer for the H8300 platform" if COMPILE_TEST
-        depends on HAS_IOMEM
+	bool "Clockevent timer for the H8300 platform" if COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the 8 bits timer for the H8300 platform.
 
 config H8300_TMR16
-        bool "Clockevent timer for the H83069 platform" if COMPILE_TEST
-        depends on HAS_IOMEM
+	bool "Clockevent timer for the H83069 platform" if COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the 16 bits timer for the H8300 platform with the
-	  H83069 cpu.
+	  H83069 CPU.
 
 config H8300_TPU
-        bool "Clocksource for the H8300 platform" if COMPILE_TEST
-        depends on HAS_IOMEM
+	bool "Clocksource for the H8300 platform" if COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the clocksource for the H8300 platform with the
-	  H8S2678 cpu.
+	  H8S2678 CPU.
 
 config CLKSRC_IMX_GPT
 	bool "Clocksource using i.MX GPT" if COMPILE_TEST
@@ -666,8 +666,8 @@ config CSKY_MP_TIMER
 	help
 	  Say yes here to enable C-SKY SMP timer driver used for C-SKY SMP
 	  system.
-	  csky,mptimer is not only used in SMP system, it also could be used
-	  single core system. It's not a mmio reg and it use mtcr/mfcr instruction.
+	  csky,mptimer is not only used in SMP system, it also could be used in
+	  single core system. It's not a mmio reg and it uses mtcr/mfcr instruction.
 
 config GX6605S_TIMER
 	bool "Gx6605s SOC system timer driver" if COMPILE_TEST
@@ -697,4 +697,14 @@ config INGENIC_TIMER
 	help
 	  Support for the timer/counter unit of the Ingenic JZ SoCs.
 
+config MICROCHIP_PIT64B
+	bool "Microchip PIT64B support"
+	depends on OF || COMPILE_TEST
+	select CLKSRC_MMIO
+	help
+	  This option enables Microchip PIT64B timer for Atmel
+	  based system. It supports the oneshot, the periodic
+	  modes and high resolution. It is used as a clocksource
+	  and a clockevent.
+
 endmenu
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 4dfe4225ece7..713686faa549 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -88,3 +88,4 @@ obj-$(CONFIG_RISCV_TIMER)		+= timer-riscv.o
 obj-$(CONFIG_CSKY_MP_TIMER)		+= timer-mp-csky.o
 obj-$(CONFIG_GX6605S_TIMER)		+= timer-gx6605s.o
 obj-$(CONFIG_HYPERV_TIMER)		+= hyperv_timer.o
+obj-$(CONFIG_MICROCHIP_PIT64B)		+= timer-microchip-pit64b.o
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 2b196cbfadb6..b235f446ee50 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -121,7 +121,7 @@ static int __init bcm2835_timer_init(struct device_node *node)
 	ret = setup_irq(irq, &timer->act);
 	if (ret) {
 		pr_err("Can't set up timer IRQ\n");
-		goto err_iounmap;
+		goto err_timer_free;
 	}
 
 	clockevents_config_and_register(&timer->evt, freq, 0xf, 0xffffffff);
@@ -130,6 +130,9 @@ static int __init bcm2835_timer_init(struct device_node *node)
 
 	return 0;
 
+err_timer_free:
+	kfree(timer);
+
 err_iounmap:
 	iounmap(base);
 	return ret;
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 9039df4f90e2..ab190dffb1ed 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -279,9 +279,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 static int em_sti_probe(struct platform_device *pdev)
 {
 	struct em_sti_priv *p;
-	struct resource *res;
-	int irq;
-	int ret;
+	int irq, ret;
 
 	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
@@ -295,8 +293,7 @@ static int em_sti_probe(struct platform_device *pdev)
 		return irq;
 
 	/* map memory, let base point to the STI instance */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	p->base = devm_ioremap_resource(&pdev->dev, res);
+	p->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(p->base))
 		return PTR_ERR(p->base);
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 74cb299f5089..a267fe31ef13 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
- * EXYNOS4 MCT(Multi-Core Timer) support
+ * Exynos4 MCT(Multi-Core Timer) support
 */
 
 #include <linux/interrupt.h>
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 287d8d58c21a..9d808d595ca8 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -66,7 +66,7 @@ static int hv_ce_set_next_event(unsigned long delta,
 {
 	u64 current_tick;
 
-	current_tick = hyperv_cs->read(NULL);
+	current_tick = hv_read_reference_counter();
 	current_tick += delta;
 	hv_init_timer(0, current_tick);
 	return 0;
@@ -302,22 +302,33 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
  * the other that uses the TSC reference page feature as defined in the
  * TLFS.  The MSR version is for compatibility with old versions of
  * Hyper-V and 32-bit x86.  The TSC reference page version is preferred.
+ *
+ * The Hyper-V clocksource ratings of 250 are chosen to be below the
+ * TSC clocksource rating of 300.  In configurations where Hyper-V offers
+ * an InvariantTSC, the TSC is not marked "unstable", so the TSC clocksource
+ * is available and preferred.  With the higher rating, it will be the
+ * default.  On older hardware and Hyper-V versions, the TSC is marked
+ * "unstable", so no TSC clocksource is created and the selected Hyper-V
+ * clocksource will be the default.
  */
 
-struct clocksource *hyperv_cs;
-EXPORT_SYMBOL_GPL(hyperv_cs);
+u64 (*hv_read_reference_counter)(void);
+EXPORT_SYMBOL_GPL(hv_read_reference_counter);
 
-static struct ms_hyperv_tsc_page tsc_pg __aligned(PAGE_SIZE);
+static union {
+	struct ms_hyperv_tsc_page page;
+	u8 reserved[PAGE_SIZE];
+} tsc_pg __aligned(PAGE_SIZE);
 
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
-	return &tsc_pg;
+	return &tsc_pg.page;
 }
 EXPORT_SYMBOL_GPL(hv_get_tsc_page);
 
-static u64 notrace read_hv_clock_tsc(struct clocksource *arg)
+static u64 notrace read_hv_clock_tsc(void)
 {
-	u64 current_tick = hv_read_tsc_page(&tsc_pg);
+	u64 current_tick = hv_read_tsc_page(hv_get_tsc_page());
 
 	if (current_tick == U64_MAX)
 		hv_get_time_ref_count(current_tick);
@@ -325,20 +336,50 @@ static u64 notrace read_hv_clock_tsc(struct clocksource *arg)
 	return current_tick;
 }
 
+static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg)
+{
+	return read_hv_clock_tsc();
+}
+
 static u64 read_hv_sched_clock_tsc(void)
 {
-	return read_hv_clock_tsc(NULL) - hv_sched_clock_offset;
+	return read_hv_clock_tsc() - hv_sched_clock_offset;
+}
+
+static void suspend_hv_clock_tsc(struct clocksource *arg)
+{
+	u64 tsc_msr;
+
+	/* Disable the TSC page */
+	hv_get_reference_tsc(tsc_msr);
+	tsc_msr &= ~BIT_ULL(0);
+	hv_set_reference_tsc(tsc_msr);
+}
+
+
+static void resume_hv_clock_tsc(struct clocksource *arg)
+{
+	phys_addr_t phys_addr = virt_to_phys(&tsc_pg);
+	u64 tsc_msr;
+
+	/* Re-enable the TSC page */
+	hv_get_reference_tsc(tsc_msr);
+	tsc_msr &= GENMASK_ULL(11, 0);
+	tsc_msr |= BIT_ULL(0) | (u64)phys_addr;
+	hv_set_reference_tsc(tsc_msr);
 }
 
 static struct clocksource hyperv_cs_tsc = {
 	.name	= "hyperv_clocksource_tsc_page",
-	.rating	= 400,
-	.read	= read_hv_clock_tsc,
+	.rating	= 250,
+	.read	= read_hv_clock_tsc_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+	.suspend= suspend_hv_clock_tsc,
+	.resume	= resume_hv_clock_tsc,
 };
 
-static u64 notrace read_hv_clock_msr(struct clocksource *arg)
+static u64 notrace read_hv_clock_msr(void)
 {
 	u64 current_tick;
 	/*
@@ -350,15 +391,20 @@ static u64 notrace read_hv_clock_msr(struct clocksource *arg)
 	return current_tick;
 }
 
+static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
+{
+	return read_hv_clock_msr();
+}
+
 static u64 read_hv_sched_clock_msr(void)
 {
-	return read_hv_clock_msr(NULL) - hv_sched_clock_offset;
+	return read_hv_clock_msr() - hv_sched_clock_offset;
 }
 
 static struct clocksource hyperv_cs_msr = {
 	.name	= "hyperv_clocksource_msr",
-	.rating	= 400,
-	.read	= read_hv_clock_msr,
+	.rating	= 250,
+	.read	= read_hv_clock_msr_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -371,8 +417,8 @@ static bool __init hv_init_tsc_clocksource(void)
 	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
 		return false;
 
-	hyperv_cs = &hyperv_cs_tsc;
-	phys_addr = virt_to_phys(&tsc_pg);
+	hv_read_reference_counter = read_hv_clock_tsc;
+	phys_addr = virt_to_phys(hv_get_tsc_page());
 
 	/*
 	 * The Hyper-V TLFS specifies to preserve the value of reserved
@@ -389,7 +435,7 @@ static bool __init hv_init_tsc_clocksource(void)
 	hv_set_clocksource_vdso(hyperv_cs_tsc);
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
-	hv_sched_clock_offset = hyperv_cs->read(hyperv_cs);
+	hv_sched_clock_offset = hv_read_reference_counter();
 	hv_setup_sched_clock(read_hv_sched_clock_tsc);
 
 	return true;
@@ -411,10 +457,10 @@ void __init hv_init_clocksource(void)
 	if (!(ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE))
 		return;
 
-	hyperv_cs = &hyperv_cs_msr;
+	hv_read_reference_counter = read_hv_clock_msr;
 	clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
 
-	hv_sched_clock_offset = hyperv_cs->read(hyperv_cs);
+	hv_sched_clock_offset = hv_read_reference_counter();
 	hv_setup_sched_clock(read_hv_sched_clock_msr);
 }
 EXPORT_SYMBOL_GPL(hv_init_clocksource);
diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c
index 88fe2e9ba9a3..38858e141731 100644
--- a/drivers/clocksource/timer-cadence-ttc.c
+++ b/drivers/clocksource/timer-cadence-ttc.c
@@ -15,6 +15,8 @@
 #include <linux/of_irq.h>
 #include <linux/slab.h>
 #include <linux/sched_clock.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
 
 /*
  * This driver configures the 2 16/32-bit count-up timers as follows:
@@ -464,13 +466,7 @@ static int __init ttc_setup_clockevent(struct clk *clk,
 	return 0;
 }
 
-/**
- * ttc_timer_init - Initialize the timer
- *
- * Initializes the timer hardware and register the clock source and clock event
- * timers with Linux kernal timer framework
- */
-static int __init ttc_timer_init(struct device_node *timer)
+static int __init ttc_timer_probe(struct platform_device *pdev)
 {
 	unsigned int irq;
 	void __iomem *timer_baseaddr;
@@ -478,6 +474,7 @@ static int __init ttc_timer_init(struct device_node *timer)
 	static int initialized;
 	int clksel, ret;
 	u32 timer_width = 16;
+	struct device_node *timer = pdev->dev.of_node;
 
 	if (initialized)
 		return 0;
@@ -532,4 +529,17 @@ static int __init ttc_timer_init(struct device_node *timer)
 	return 0;
 }
 
-TIMER_OF_DECLARE(ttc, "cdns,ttc", ttc_timer_init);
+static const struct of_device_id ttc_timer_of_match[] = {
+	{.compatible = "cdns,ttc"},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, ttc_timer_of_match);
+
+static struct platform_driver ttc_timer_driver = {
+	.driver = {
+		.name	= "cdns_ttc_timer",
+		.of_match_table = ttc_timer_of_match,
+	},
+};
+builtin_platform_driver_probe(ttc_timer_driver, ttc_timer_probe);
diff --git a/drivers/clocksource/timer-microchip-pit64b.c b/drivers/clocksource/timer-microchip-pit64b.c
new file mode 100644
index 000000000000..bd63d3484838
--- /dev/null
+++ b/drivers/clocksource/timer-microchip-pit64b.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * 64-bit Periodic Interval Timer driver
+ *
+ * Copyright (C) 2019 Microchip Technology Inc. and its subsidiaries
+ *
+ * Author: Claudiu Beznea <claudiu.beznea@microchip.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+#define MCHP_PIT64B_CR			0x00	/* Control Register */
+#define MCHP_PIT64B_CR_START		BIT(0)
+#define MCHP_PIT64B_CR_SWRST		BIT(8)
+
+#define MCHP_PIT64B_MR			0x04	/* Mode Register */
+#define MCHP_PIT64B_MR_CONT		BIT(0)
+#define MCHP_PIT64B_MR_ONE_SHOT		(0)
+#define MCHP_PIT64B_MR_SGCLK		BIT(3)
+#define MCHP_PIT64B_MR_PRES		GENMASK(11, 8)
+
+#define MCHP_PIT64B_LSB_PR		0x08	/* LSB Period Register */
+
+#define MCHP_PIT64B_MSB_PR		0x0C	/* MSB Period Register */
+
+#define MCHP_PIT64B_IER			0x10	/* Interrupt Enable Register */
+#define MCHP_PIT64B_IER_PERIOD		BIT(0)
+
+#define MCHP_PIT64B_ISR			0x1C	/* Interrupt Status Register */
+
+#define MCHP_PIT64B_TLSBR		0x20	/* Timer LSB Register */
+
+#define MCHP_PIT64B_TMSBR		0x24	/* Timer MSB Register */
+
+#define MCHP_PIT64B_PRES_MAX		0x10
+#define MCHP_PIT64B_LSBMASK		GENMASK_ULL(31, 0)
+#define MCHP_PIT64B_PRES_TO_MODE(p)	(MCHP_PIT64B_MR_PRES & ((p) << 8))
+#define MCHP_PIT64B_MODE_TO_PRES(m)	((MCHP_PIT64B_MR_PRES & (m)) >> 8)
+#define MCHP_PIT64B_DEF_CS_FREQ		5000000UL	/* 5 MHz */
+#define MCHP_PIT64B_DEF_CE_FREQ		32768		/* 32 KHz */
+
+#define MCHP_PIT64B_NAME		"pit64b"
+
+/**
+ * struct mchp_pit64b_timer - PIT64B timer data structure
+ * @base: base address of PIT64B hardware block
+ * @pclk: PIT64B's peripheral clock
+ * @gclk: PIT64B's generic clock
+ * @mode: precomputed value for mode register
+ */
+struct mchp_pit64b_timer {
+	void __iomem	*base;
+	struct clk	*pclk;
+	struct clk	*gclk;
+	u32		mode;
+};
+
+/**
+ * mchp_pit64b_clkevt - PIT64B clockevent data structure
+ * @timer: PIT64B timer
+ * @clkevt: clockevent
+ */
+struct mchp_pit64b_clkevt {
+	struct mchp_pit64b_timer	timer;
+	struct clock_event_device	clkevt;
+};
+
+#define to_mchp_pit64b_timer(x) \
+	((struct mchp_pit64b_timer *)container_of(x,\
+		struct mchp_pit64b_clkevt, clkevt))
+
+/* Base address for clocksource timer. */
+static void __iomem *mchp_pit64b_cs_base;
+/* Default cycles for clockevent timer. */
+static u64 mchp_pit64b_ce_cycles;
+
+static inline u64 mchp_pit64b_cnt_read(void __iomem *base)
+{
+	unsigned long	flags;
+	u32		low, high;
+
+	raw_local_irq_save(flags);
+
+	/*
+	 * When using a 64 bit period TLSB must be read first, followed by the
+	 * read of TMSB. This sequence generates an atomic read of the 64 bit
+	 * timer value whatever the lapse of time between the accesses.
+	 */
+	low = readl_relaxed(base + MCHP_PIT64B_TLSBR);
+	high = readl_relaxed(base + MCHP_PIT64B_TMSBR);
+
+	raw_local_irq_restore(flags);
+
+	return (((u64)high << 32) | low);
+}
+
+static inline void mchp_pit64b_reset(struct mchp_pit64b_timer *timer,
+				     u64 cycles, u32 mode, u32 irqs)
+{
+	u32 low, high;
+
+	low = cycles & MCHP_PIT64B_LSBMASK;
+	high = cycles >> 32;
+
+	writel_relaxed(MCHP_PIT64B_CR_SWRST, timer->base + MCHP_PIT64B_CR);
+	writel_relaxed(mode | timer->mode, timer->base + MCHP_PIT64B_MR);
+	writel_relaxed(high, timer->base + MCHP_PIT64B_MSB_PR);
+	writel_relaxed(low, timer->base + MCHP_PIT64B_LSB_PR);
+	writel_relaxed(irqs, timer->base + MCHP_PIT64B_IER);
+	writel_relaxed(MCHP_PIT64B_CR_START, timer->base + MCHP_PIT64B_CR);
+}
+
+static u64 mchp_pit64b_clksrc_read(struct clocksource *cs)
+{
+	return mchp_pit64b_cnt_read(mchp_pit64b_cs_base);
+}
+
+static u64 mchp_pit64b_sched_read_clk(void)
+{
+	return mchp_pit64b_cnt_read(mchp_pit64b_cs_base);
+}
+
+static int mchp_pit64b_clkevt_shutdown(struct clock_event_device *cedev)
+{
+	struct mchp_pit64b_timer *timer = to_mchp_pit64b_timer(cedev);
+
+	writel_relaxed(MCHP_PIT64B_CR_SWRST, timer->base + MCHP_PIT64B_CR);
+
+	return 0;
+}
+
+static int mchp_pit64b_clkevt_set_periodic(struct clock_event_device *cedev)
+{
+	struct mchp_pit64b_timer *timer = to_mchp_pit64b_timer(cedev);
+
+	mchp_pit64b_reset(timer, mchp_pit64b_ce_cycles, MCHP_PIT64B_MR_CONT,
+			  MCHP_PIT64B_IER_PERIOD);
+
+	return 0;
+}
+
+static int mchp_pit64b_clkevt_set_next_event(unsigned long evt,
+					     struct clock_event_device *cedev)
+{
+	struct mchp_pit64b_timer *timer = to_mchp_pit64b_timer(cedev);
+
+	mchp_pit64b_reset(timer, evt, MCHP_PIT64B_MR_ONE_SHOT,
+			  MCHP_PIT64B_IER_PERIOD);
+
+	return 0;
+}
+
+static void mchp_pit64b_clkevt_suspend(struct clock_event_device *cedev)
+{
+	struct mchp_pit64b_timer *timer = to_mchp_pit64b_timer(cedev);
+
+	writel_relaxed(MCHP_PIT64B_CR_SWRST, timer->base + MCHP_PIT64B_CR);
+	if (timer->mode & MCHP_PIT64B_MR_SGCLK)
+		clk_disable_unprepare(timer->gclk);
+	clk_disable_unprepare(timer->pclk);
+}
+
+static void mchp_pit64b_clkevt_resume(struct clock_event_device *cedev)
+{
+	struct mchp_pit64b_timer *timer = to_mchp_pit64b_timer(cedev);
+
+	clk_prepare_enable(timer->pclk);
+	if (timer->mode & MCHP_PIT64B_MR_SGCLK)
+		clk_prepare_enable(timer->gclk);
+}
+
+static irqreturn_t mchp_pit64b_interrupt(int irq, void *dev_id)
+{
+	struct mchp_pit64b_clkevt *irq_data = dev_id;
+
+	/* Need to clear the interrupt. */
+	readl_relaxed(irq_data->timer.base + MCHP_PIT64B_ISR);
+
+	irq_data->clkevt.event_handler(&irq_data->clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void __init mchp_pit64b_pres_compute(u32 *pres, u32 clk_rate,
+					    u32 max_rate)
+{
+	u32 tmp;
+
+	for (*pres = 0; *pres < MCHP_PIT64B_PRES_MAX; (*pres)++) {
+		tmp = clk_rate / (*pres + 1);
+		if (tmp <= max_rate)
+			break;
+	}
+
+	/* Use the bigest prescaler if we didn't match one. */
+	if (*pres == MCHP_PIT64B_PRES_MAX)
+		*pres = MCHP_PIT64B_PRES_MAX - 1;
+}
+
+/**
+ * mchp_pit64b_init_mode - prepare PIT64B mode register value to be used at
+ *			   runtime; this includes prescaler and SGCLK bit
+ *
+ * PIT64B timer may be fed by gclk or pclk. When gclk is used its rate has to
+ * be at least 3 times lower that pclk's rate. pclk rate is fixed, gclk rate
+ * could be changed via clock APIs. The chosen clock (pclk or gclk) could be
+ * divided by the internal PIT64B's divider.
+ *
+ * This function, first tries to use GCLK by requesting the desired rate from
+ * PMC and then using the internal PIT64B prescaler, if any, to reach the
+ * requested rate. If PCLK/GCLK < 3 (condition requested by PIT64B hardware)
+ * then the function falls back on using PCLK as clock source for PIT64B timer
+ * choosing the highest prescaler in case it doesn't locate one to match the
+ * requested frequency.
+ *
+ * Below is presented the PIT64B block in relation with PMC:
+ *
+ *                                PIT64B
+ *  PMC             +------------------------------------+
+ * +----+           |   +-----+                          |
+ * |    |-->gclk -->|-->|     |    +---------+  +-----+  |
+ * |    |           |   | MUX |--->| Divider |->|timer|  |
+ * |    |-->pclk -->|-->|     |    +---------+  +-----+  |
+ * +----+           |   +-----+                          |
+ *                  |      ^                             |
+ *                  |     sel                            |
+ *                  +------------------------------------+
+ *
+ * Where:
+ *	- gclk rate <= pclk rate/3
+ *	- gclk rate could be requested from PMC
+ *	- pclk rate is fixed (cannot be requested from PMC)
+ */
+static int __init mchp_pit64b_init_mode(struct mchp_pit64b_timer *timer,
+					unsigned long max_rate)
+{
+	unsigned long pclk_rate, diff = 0, best_diff = ULONG_MAX;
+	long gclk_round = 0;
+	u32 pres, best_pres = 0;
+
+	pclk_rate = clk_get_rate(timer->pclk);
+	if (!pclk_rate)
+		return -EINVAL;
+
+	timer->mode = 0;
+
+	/* Try using GCLK. */
+	gclk_round = clk_round_rate(timer->gclk, max_rate);
+	if (gclk_round < 0)
+		goto pclk;
+
+	if (pclk_rate / gclk_round < 3)
+		goto pclk;
+
+	mchp_pit64b_pres_compute(&pres, gclk_round, max_rate);
+	best_diff = abs(gclk_round / (pres + 1) - max_rate);
+	best_pres = pres;
+
+	if (!best_diff) {
+		timer->mode |= MCHP_PIT64B_MR_SGCLK;
+		goto done;
+	}
+
+pclk:
+	/* Check if requested rate could be obtained using PCLK. */
+	mchp_pit64b_pres_compute(&pres, pclk_rate, max_rate);
+	diff = abs(pclk_rate / (pres + 1) - max_rate);
+
+	if (best_diff > diff) {
+		/* Use PCLK. */
+		best_pres = pres;
+	} else {
+		/* Use GCLK. */
+		timer->mode |= MCHP_PIT64B_MR_SGCLK;
+		clk_set_rate(timer->gclk, gclk_round);
+	}
+
+done:
+	timer->mode |= MCHP_PIT64B_PRES_TO_MODE(best_pres);
+
+	pr_info("PIT64B: using clk=%s with prescaler %u, freq=%lu [Hz]\n",
+		timer->mode & MCHP_PIT64B_MR_SGCLK ? "gclk" : "pclk", best_pres,
+		timer->mode & MCHP_PIT64B_MR_SGCLK ?
+		gclk_round / (best_pres + 1) : pclk_rate / (best_pres + 1));
+
+	return 0;
+}
+
+static int __init mchp_pit64b_init_clksrc(struct mchp_pit64b_timer *timer,
+					  u32 clk_rate)
+{
+	int ret;
+
+	mchp_pit64b_reset(timer, ULLONG_MAX, MCHP_PIT64B_MR_CONT, 0);
+
+	mchp_pit64b_cs_base = timer->base;
+
+	ret = clocksource_mmio_init(timer->base, MCHP_PIT64B_NAME, clk_rate,
+				    210, 64, mchp_pit64b_clksrc_read);
+	if (ret) {
+		pr_debug("clksrc: Failed to register PIT64B clocksource!\n");
+
+		/* Stop timer. */
+		writel_relaxed(MCHP_PIT64B_CR_SWRST,
+			       timer->base + MCHP_PIT64B_CR);
+
+		return ret;
+	}
+
+	sched_clock_register(mchp_pit64b_sched_read_clk, 64, clk_rate);
+
+	return 0;
+}
+
+static int __init mchp_pit64b_init_clkevt(struct mchp_pit64b_timer *timer,
+					  u32 clk_rate, u32 irq)
+{
+	struct mchp_pit64b_clkevt *ce;
+	int ret;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce)
+		return -ENOMEM;
+
+	mchp_pit64b_ce_cycles = DIV_ROUND_CLOSEST(clk_rate, HZ);
+
+	ce->timer.base = timer->base;
+	ce->timer.pclk = timer->pclk;
+	ce->timer.gclk = timer->gclk;
+	ce->timer.mode = timer->mode;
+	ce->clkevt.name = MCHP_PIT64B_NAME;
+	ce->clkevt.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC;
+	ce->clkevt.rating = 150;
+	ce->clkevt.set_state_shutdown = mchp_pit64b_clkevt_shutdown;
+	ce->clkevt.set_state_periodic = mchp_pit64b_clkevt_set_periodic;
+	ce->clkevt.set_next_event = mchp_pit64b_clkevt_set_next_event;
+	ce->clkevt.suspend = mchp_pit64b_clkevt_suspend;
+	ce->clkevt.resume = mchp_pit64b_clkevt_resume;
+	ce->clkevt.cpumask = cpumask_of(0);
+	ce->clkevt.irq = irq;
+
+	ret = request_irq(irq, mchp_pit64b_interrupt, IRQF_TIMER,
+			  "pit64b_tick", ce);
+	if (ret) {
+		pr_debug("clkevt: Failed to setup PIT64B IRQ\n");
+		kfree(ce);
+		return ret;
+	}
+
+	clockevents_config_and_register(&ce->clkevt, clk_rate, 1, ULONG_MAX);
+
+	return 0;
+}
+
+static int __init mchp_pit64b_dt_init_timer(struct device_node *node,
+					    bool clkevt)
+{
+	u32 freq = clkevt ? MCHP_PIT64B_DEF_CE_FREQ : MCHP_PIT64B_DEF_CS_FREQ;
+	struct mchp_pit64b_timer timer;
+	unsigned long clk_rate;
+	u32 irq = 0;
+	int ret;
+
+	/* Parse DT node. */
+	timer.pclk = of_clk_get_by_name(node, "pclk");
+	if (IS_ERR(timer.pclk))
+		return PTR_ERR(timer.pclk);
+
+	timer.gclk = of_clk_get_by_name(node, "gclk");
+	if (IS_ERR(timer.gclk))
+		return PTR_ERR(timer.gclk);
+
+	timer.base = of_iomap(node, 0);
+	if (!timer.base)
+		return -ENXIO;
+
+	if (clkevt) {
+		irq = irq_of_parse_and_map(node, 0);
+		if (!irq) {
+			ret = -ENODEV;
+			goto io_unmap;
+		}
+	}
+
+	/* Initialize mode (prescaler + SGCK bit). To be used at runtime. */
+	ret = mchp_pit64b_init_mode(&timer, freq);
+	if (ret)
+		goto irq_unmap;
+
+	ret = clk_prepare_enable(timer.pclk);
+	if (ret)
+		goto irq_unmap;
+
+	if (timer.mode & MCHP_PIT64B_MR_SGCLK) {
+		ret = clk_prepare_enable(timer.gclk);
+		if (ret)
+			goto pclk_unprepare;
+
+		clk_rate = clk_get_rate(timer.gclk);
+	} else {
+		clk_rate = clk_get_rate(timer.pclk);
+	}
+	clk_rate = clk_rate / (MCHP_PIT64B_MODE_TO_PRES(timer.mode) + 1);
+
+	if (clkevt)
+		ret = mchp_pit64b_init_clkevt(&timer, clk_rate, irq);
+	else
+		ret = mchp_pit64b_init_clksrc(&timer, clk_rate);
+
+	if (ret)
+		goto gclk_unprepare;
+
+	return 0;
+
+gclk_unprepare:
+	if (timer.mode & MCHP_PIT64B_MR_SGCLK)
+		clk_disable_unprepare(timer.gclk);
+pclk_unprepare:
+	clk_disable_unprepare(timer.pclk);
+irq_unmap:
+	irq_dispose_mapping(irq);
+io_unmap:
+	iounmap(timer.base);
+
+	return ret;
+}
+
+static int __init mchp_pit64b_dt_init(struct device_node *node)
+{
+	static int inits;
+
+	switch (inits++) {
+	case 0:
+		/* 1st request, register clockevent. */
+		return mchp_pit64b_dt_init_timer(node, true);
+	case 1:
+		/* 2nd request, register clocksource. */
+		return mchp_pit64b_dt_init_timer(node, false);
+	}
+
+	/* The rest, don't care. */
+	return -EINVAL;
+}
+
+TIMER_OF_DECLARE(mchp_pit64b, "microchip,sam9x60-pit64b", mchp_pit64b_dt_init);
diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index 5394d9dbdfbc..269a994d6a99 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -780,7 +780,6 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 {
 	unsigned long flags;
 	struct omap_dm_timer *timer;
-	struct resource *mem, *irq;
 	struct device *dev = &pdev->dev;
 	const struct dmtimer_platform_data *pdata;
 	int ret;
@@ -796,24 +795,16 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (unlikely(!irq)) {
-		dev_err(dev, "%s: no IRQ resource.\n", __func__);
-		return -ENODEV;
-	}
-
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (unlikely(!mem)) {
-		dev_err(dev, "%s: no memory resource.\n", __func__);
-		return -ENODEV;
-	}
-
 	timer = devm_kzalloc(dev, sizeof(*timer), GFP_KERNEL);
 	if (!timer)
 		return  -ENOMEM;
 
+	timer->irq = platform_get_irq(pdev, 0);
+	if (timer->irq < 0)
+		return timer->irq;
+
 	timer->fclk = ERR_PTR(-ENODEV);
-	timer->io_base = devm_ioremap_resource(dev, mem);
+	timer->io_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(timer->io_base))
 		return PTR_ERR(timer->io_base);
 
@@ -836,7 +827,6 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 	if (pdata)
 		timer->errata = pdata->timer_errata;
 
-	timer->irq = irq->start;
 	timer->pdev = pdev;
 
 	pm_runtime_enable(dev);
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 766bd8457346..296f9098c9e4 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -211,7 +211,7 @@ static struct timespec64 hv_get_adj_host_time(void)
 	unsigned long flags;
 
 	spin_lock_irqsave(&host_ts.lock, flags);
-	reftime = hyperv_cs->read(hyperv_cs);
+	reftime = hv_read_reference_counter();
 	newtime = host_ts.host_time + (reftime - host_ts.ref_time);
 	ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
 	spin_unlock_irqrestore(&host_ts.lock, flags);
@@ -250,7 +250,7 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
 	 */
 	spin_lock_irqsave(&host_ts.lock, flags);
 
-	cur_reftime = hyperv_cs->read(hyperv_cs);
+	cur_reftime = hv_read_reference_counter();
 	host_ts.host_time = hosttime;
 	host_ts.ref_time = cur_reftime;
 
@@ -315,7 +315,7 @@ static void timesync_onchannelcallback(void *context)
 					sizeof(struct vmbuspipe_hdr) +
 					sizeof(struct icmsg_hdr)];
 				adj_guesttime(timedatap->parenttime,
-					      hyperv_cs->read(hyperv_cs),
+					      hv_read_reference_counter(),
 					      timedatap->flags);
 			}
 		}
@@ -524,7 +524,7 @@ static struct ptp_clock *hv_ptp_clock;
 static int hv_timesync_init(struct hv_util_service *srv)
 {
 	/* TimeSync requires Hyper-V clocksource. */
-	if (!hyperv_cs)
+	if (!hv_read_reference_counter)
 		return -ENODEV;
 
 	spin_lock_init(&host_ts.lock);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb8..5adc6390ac3a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -94,6 +94,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/stat.h>
 #include <linux/posix-timers.h>
+#include <linux/time_namespace.h>
 #include <trace/events/oom.h>
 #include "internal.h"
 #include "fd.h"
@@ -1533,6 +1534,96 @@ static const struct file_operations proc_pid_sched_autogroup_operations = {
 
 #endif /* CONFIG_SCHED_AUTOGROUP */
 
+#ifdef CONFIG_TIME_NS
+static int timens_offsets_show(struct seq_file *m, void *v)
+{
+	struct task_struct *p;
+
+	p = get_proc_task(file_inode(m->file));
+	if (!p)
+		return -ESRCH;
+	proc_timens_show_offsets(p, m);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	struct inode *inode = file_inode(file);
+	struct proc_timens_offset offsets[2];
+	char *kbuf = NULL, *pos, *next_line;
+	struct task_struct *p;
+	int ret, noffsets;
+
+	/* Only allow < page size writes at the beginning of the file */
+	if ((*ppos != 0) || (count >= PAGE_SIZE))
+		return -EINVAL;
+
+	/* Slurp in the user data */
+	kbuf = memdup_user_nul(buf, count);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
+
+	/* Parse the user data */
+	ret = -EINVAL;
+	noffsets = 0;
+	for (pos = kbuf; pos; pos = next_line) {
+		struct proc_timens_offset *off = &offsets[noffsets];
+		int err;
+
+		/* Find the end of line and ensure we don't look past it */
+		next_line = strchr(pos, '\n');
+		if (next_line) {
+			*next_line = '\0';
+			next_line++;
+			if (*next_line == '\0')
+				next_line = NULL;
+		}
+
+		err = sscanf(pos, "%u %lld %lu", &off->clockid,
+				&off->val.tv_sec, &off->val.tv_nsec);
+		if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC)
+			goto out;
+		noffsets++;
+		if (noffsets == ARRAY_SIZE(offsets)) {
+			if (next_line)
+				count = next_line - kbuf;
+			break;
+		}
+	}
+
+	ret = -ESRCH;
+	p = get_proc_task(inode);
+	if (!p)
+		goto out;
+	ret = proc_timens_set_offset(file, p, offsets, noffsets);
+	put_task_struct(p);
+	if (ret)
+		goto out;
+
+	ret = count;
+out:
+	kfree(kbuf);
+	return ret;
+}
+
+static int timens_offsets_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, timens_offsets_show, inode);
+}
+
+static const struct file_operations proc_timens_offsets_operations = {
+	.open		= timens_offsets_open,
+	.read		= seq_read,
+	.write		= timens_offsets_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif /* CONFIG_TIME_NS */
+
 static ssize_t comm_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *offset)
 {
@@ -3015,6 +3106,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
+#endif
+#ifdef CONFIG_TIME_NS
+	REG("timens_offsets",  S_IRUGO|S_IWUSR, proc_timens_offsets_operations),
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index dd2b35f78b09..8b5c720fe5d7 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -33,6 +33,10 @@ static const struct proc_ns_operations *ns_entries[] = {
 #ifdef CONFIG_CGROUPS
 	&cgroupns_operations,
 #endif
+#ifdef CONFIG_TIME_NS
+	&timens_operations,
+	&timens_for_children_operations,
+#endif
 };
 
 static const char *proc_ns_get_link(struct dentry *dentry,
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index a4c2791ab70b..5a1b228964fb 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/time.h>
+#include <linux/time_namespace.h>
 #include <linux/kernel_stat.h>
 
 static int uptime_proc_show(struct seq_file *m, void *v)
@@ -20,6 +21,8 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 		nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
 	ktime_get_boottime_ts64(&uptime);
+	timens_add_boottime(&uptime);
+
 	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
diff --git a/fs/timerfd.c b/fs/timerfd.c
index ac7f59a58f94..c5509d2448e3 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/compat.h>
 #include <linux/rcupdate.h>
+#include <linux/time_namespace.h>
 
 struct timerfd_ctx {
 	union {
@@ -196,6 +197,8 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
 	}
 
 	if (texp != 0) {
+		if (flags & TFD_TIMER_ABSTIME)
+			texp = timens_ktime_to_host(clockid, texp);
 		if (isalarm(ctx)) {
 			if (flags & TFD_TIMER_ABSTIME)
 				alarm_start(&ctx->t.alarm, texp);
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 553e539469f0..34eef083c988 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -30,7 +30,7 @@ extern void hv_stimer_global_cleanup(void);
 extern void hv_stimer0_isr(void);
 
 #ifdef CONFIG_HYPERV_TIMER
-extern struct clocksource *hyperv_cs;
+extern u64 (*hv_read_reference_counter)(void);
 extern void hv_init_clocksource(void);
 
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 74748e306f4b..05e758b8b894 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -60,7 +60,11 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval);
 u64 alarm_forward_now(struct alarm *alarm, ktime_t interval);
 ktime_t alarm_expires_remaining(const struct alarm *alarm);
 
+#ifdef CONFIG_RTC_CLASS
 /* Provide way to access the rtc device being used by alarmtimers */
 struct rtc_device *alarmtimer_get_rtcdev(void);
+#else
+static inline struct rtc_device *alarmtimer_get_rtcdev(void) { return NULL; }
+#endif
 
 #endif
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 1f98b52118f0..15c8ac313678 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -508,8 +508,7 @@ static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 /* Precise sleep: */
 
 extern int nanosleep_copyout(struct restart_block *, struct timespec64 *);
-extern long hrtimer_nanosleep(const struct timespec64 *rqtp,
-			      const enum hrtimer_mode mode,
+extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 			      const clockid_t clockid);
 
 extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 2ae1b1a4d84d..074f395b9ad2 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -35,6 +35,8 @@ struct nsproxy {
 	struct mnt_namespace *mnt_ns;
 	struct pid_namespace *pid_ns_for_children;
 	struct net 	     *net_ns;
+	struct time_namespace *time_ns;
+	struct time_namespace *time_ns_for_children;
 	struct cgroup_namespace *cgroup_ns;
 };
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index d31cb6215905..d312e6281e69 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -32,6 +32,8 @@ extern const struct proc_ns_operations pidns_for_children_operations;
 extern const struct proc_ns_operations userns_operations;
 extern const struct proc_ns_operations mntns_operations;
 extern const struct proc_ns_operations cgroupns_operations;
+extern const struct proc_ns_operations timens_operations;
+extern const struct proc_ns_operations timens_for_children_operations;
 
 /*
  * We always define these enumerators
@@ -43,6 +45,7 @@ enum {
 	PROC_USER_INIT_INO	= 0xEFFFFFFDU,
 	PROC_PID_INIT_INO	= 0xEFFFFFFCU,
 	PROC_CGROUP_INIT_INO	= 0xEFFFFFFBU,
+	PROC_TIME_INIT_INO	= 0xEFFFFFFAU,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/linux/time.h b/include/linux/time.h
index 8e10b9dbd8c2..8ef5e5cc9f57 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -110,4 +110,10 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its)
  * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)).
  */
 #define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l))
+
+struct timens_offset {
+	s64	sec;
+	u64	nsec;
+};
+
 #endif
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
new file mode 100644
index 000000000000..824d54e057eb
--- /dev/null
+++ b/include/linux/time_namespace.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TIMENS_H
+#define _LINUX_TIMENS_H
+
+
+#include <linux/sched.h>
+#include <linux/kref.h>
+#include <linux/nsproxy.h>
+#include <linux/ns_common.h>
+#include <linux/err.h>
+
+struct user_namespace;
+extern struct user_namespace init_user_ns;
+
+struct timens_offsets {
+	struct timespec64 monotonic;
+	struct timespec64 boottime;
+};
+
+struct time_namespace {
+	struct kref		kref;
+	struct user_namespace	*user_ns;
+	struct ucounts		*ucounts;
+	struct ns_common	ns;
+	struct timens_offsets	offsets;
+	struct page		*vvar_page;
+	/* If set prevents changing offsets after any task joined namespace. */
+	bool			frozen_offsets;
+} __randomize_layout;
+
+extern struct time_namespace init_time_ns;
+
+#ifdef CONFIG_TIME_NS
+extern int vdso_join_timens(struct task_struct *task,
+			    struct time_namespace *ns);
+
+static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
+{
+	kref_get(&ns->kref);
+	return ns;
+}
+
+struct time_namespace *copy_time_ns(unsigned long flags,
+				    struct user_namespace *user_ns,
+				    struct time_namespace *old_ns);
+void free_time_ns(struct kref *kref);
+int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
+struct vdso_data *arch_get_vdso_data(void *vvar_page);
+
+static inline void put_time_ns(struct time_namespace *ns)
+{
+	kref_put(&ns->kref, free_time_ns);
+}
+
+void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m);
+
+struct proc_timens_offset {
+	int			clockid;
+	struct timespec64	val;
+};
+
+int proc_timens_set_offset(struct file *file, struct task_struct *p,
+			   struct proc_timens_offset *offsets, int n);
+
+static inline void timens_add_monotonic(struct timespec64 *ts)
+{
+	struct timens_offsets *ns_offsets = &current->nsproxy->time_ns->offsets;
+
+	*ts = timespec64_add(*ts, ns_offsets->monotonic);
+}
+
+static inline void timens_add_boottime(struct timespec64 *ts)
+{
+	struct timens_offsets *ns_offsets = &current->nsproxy->time_ns->offsets;
+
+	*ts = timespec64_add(*ts, ns_offsets->boottime);
+}
+
+ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
+				struct timens_offsets *offsets);
+
+static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
+{
+	struct time_namespace *ns = current->nsproxy->time_ns;
+
+	if (likely(ns == &init_time_ns))
+		return tim;
+
+	return do_timens_ktime_to_host(clockid, tim, &ns->offsets);
+}
+
+#else
+static inline int vdso_join_timens(struct task_struct *task,
+				   struct time_namespace *ns)
+{
+	return 0;
+}
+
+static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
+{
+	return NULL;
+}
+
+static inline void put_time_ns(struct time_namespace *ns)
+{
+}
+
+static inline
+struct time_namespace *copy_time_ns(unsigned long flags,
+				    struct user_namespace *user_ns,
+				    struct time_namespace *old_ns)
+{
+	if (flags & CLONE_NEWTIME)
+		return ERR_PTR(-EINVAL);
+
+	return old_ns;
+}
+
+static inline int timens_on_fork(struct nsproxy *nsproxy,
+				 struct task_struct *tsk)
+{
+	return 0;
+}
+
+static inline void timens_add_monotonic(struct timespec64 *ts) { }
+static inline void timens_add_boottime(struct timespec64 *ts) { }
+static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
+{
+	return tim;
+}
+#endif
+
+#endif /* _LINUX_TIMENS_H */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index fb9f4f799554..6ef1c7109fc4 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -45,6 +45,7 @@ enum ucount_type {
 	UCOUNT_NET_NAMESPACES,
 	UCOUNT_MNT_NAMESPACES,
 	UCOUNT_CGROUP_NAMESPACES,
+	UCOUNT_TIME_NAMESPACES,
 #ifdef CONFIG_INOTIFY_USER
 	UCOUNT_INOTIFY_INSTANCES,
 	UCOUNT_INOTIFY_WATCHES,
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 4a0217832464..2e3bc22c6f20 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -36,6 +36,12 @@
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME	0x00000080	/* New time namespace */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 2e302c0f41f7..c5f347cc5e55 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -21,6 +21,8 @@
 #define CS_RAW		1
 #define CS_BASES	(CS_RAW + 1)
 
+#define VCLOCK_TIMENS	UINT_MAX
+
 /**
  * struct vdso_timestamp - basetime per clock_id
  * @sec:	seconds
@@ -48,6 +50,7 @@ struct vdso_timestamp {
  * @mult:		clocksource multiplier
  * @shift:		clocksource shift
  * @basetime[clock_id]:	basetime per clock_id
+ * @offset[clock_id]:	time namespace offset per clock_id
  * @tz_minuteswest:	minutes west of Greenwich
  * @tz_dsttime:		type of DST correction
  * @hrtimer_res:	hrtimer resolution
@@ -55,6 +58,17 @@ struct vdso_timestamp {
  *
  * vdso_data will be accessed by 64 bit and compat code at the same time
  * so we should be careful before modifying this structure.
+ *
+ * @basetime is used to store the base time for the system wide time getter
+ * VVAR page.
+ *
+ * @offset is used by the special time namespace VVAR pages which are
+ * installed instead of the real VVAR page. These namespace pages must set
+ * @seq to 1 and @clock_mode to VLOCK_TIMENS to force the code into the
+ * time namespace slow path. The namespace aware functions retrieve the
+ * real system wide VVAR page, read host time and add the per clock offset.
+ * For clocks which are not affected by time namespace adjustment the
+ * offset must be zero.
  */
 struct vdso_data {
 	u32			seq;
@@ -65,7 +79,10 @@ struct vdso_data {
 	u32			mult;
 	u32			shift;
 
-	struct vdso_timestamp	basetime[VDSO_BASES];
+	union {
+		struct vdso_timestamp	basetime[VDSO_BASES];
+		struct timens_offset	offset[VDSO_BASES];
+	};
 
 	s32			tz_minuteswest;
 	s32			tz_dsttime;
diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
index 01641dbb68ef..9a2af9fca45e 100644
--- a/include/vdso/helpers.h
+++ b/include/vdso/helpers.h
@@ -10,7 +10,7 @@ static __always_inline u32 vdso_read_begin(const struct vdso_data *vd)
 {
 	u32 seq;
 
-	while ((seq = READ_ONCE(vd->seq)) & 1)
+	while (unlikely((seq = READ_ONCE(vd->seq)) & 1))
 		cpu_relax();
 
 	smp_rmb();
diff --git a/init/Kconfig b/init/Kconfig
index a34064a031a5..9b7f144a6d35 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1080,6 +1080,14 @@ config UTS_NS
 	  In this namespace tasks see different info provided with the
 	  uname() system call
 
+config TIME_NS
+	bool "TIME namespace"
+	depends on GENERIC_VDSO_TIME_NS
+	default y
+	help
+	  In this namespace boottime and monotonic clocks can be set.
+	  The time will keep going with the same pace.
+
 config IPC_NS
 	bool "IPC namespace"
 	depends on (SYSVIPC || POSIX_MQUEUE)
diff --git a/kernel/fork.c b/kernel/fork.c
index 2508a4f238a3..363595815144 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1832,6 +1832,7 @@ static __latent_entropy struct task_struct *copy_process(
 	struct multiprocess_signals delayed;
 	struct file *pidfile = NULL;
 	u64 clone_flags = args->flags;
+	struct nsproxy *nsp = current->nsproxy;
 
 	/*
 	 * Don't allow sharing the root directory with processes in a different
@@ -1874,8 +1875,16 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 	if (clone_flags & CLONE_THREAD) {
 		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
-		    (task_active_pid_ns(current) !=
-				current->nsproxy->pid_ns_for_children))
+		    (task_active_pid_ns(current) != nsp->pid_ns_for_children))
+			return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * If the new process will be in a different time namespace
+	 * do not allow it to share VM or a thread group with the forking task.
+	 */
+	if (clone_flags & (CLONE_THREAD | CLONE_VM)) {
+		if (nsp->time_ns != nsp->time_ns_for_children)
 			return ERR_PTR(-EINVAL);
 	}
 
@@ -2811,7 +2820,8 @@ static int check_unshare_flags(unsigned long unshare_flags)
 	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
 				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
 				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
-				CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP))
+				CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP|
+				CLONE_NEWTIME))
 		return -EINVAL;
 	/*
 	 * Not implemented, but pretend it works if there is nothing
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index c815f58e6bc0..ed9882108cd2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -18,6 +18,7 @@
 #include <linux/pid_namespace.h>
 #include <net/net_namespace.h>
 #include <linux/ipc_namespace.h>
+#include <linux/time_namespace.h>
 #include <linux/proc_ns.h>
 #include <linux/file.h>
 #include <linux/syscalls.h>
@@ -40,6 +41,10 @@ struct nsproxy init_nsproxy = {
 #ifdef CONFIG_CGROUPS
 	.cgroup_ns		= &init_cgroup_ns,
 #endif
+#ifdef CONFIG_TIME_NS
+	.time_ns		= &init_time_ns,
+	.time_ns_for_children	= &init_time_ns,
+#endif
 };
 
 static inline struct nsproxy *create_nsproxy(void)
@@ -106,8 +111,18 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_net;
 	}
 
+	new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns,
+					tsk->nsproxy->time_ns_for_children);
+	if (IS_ERR(new_nsp->time_ns_for_children)) {
+		err = PTR_ERR(new_nsp->time_ns_for_children);
+		goto out_time;
+	}
+	new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns);
+
 	return new_nsp;
 
+out_time:
+	put_net(new_nsp->net_ns);
 out_net:
 	put_cgroup_ns(new_nsp->cgroup_ns);
 out_cgroup:
@@ -136,15 +151,16 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	struct nsproxy *old_ns = tsk->nsproxy;
 	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
 	struct nsproxy *new_ns;
+	int ret;
 
 	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
 			      CLONE_NEWPID | CLONE_NEWNET |
-			      CLONE_NEWCGROUP)))) {
-		get_nsproxy(old_ns);
-		return 0;
-	}
-
-	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+			      CLONE_NEWCGROUP | CLONE_NEWTIME)))) {
+		if (likely(old_ns->time_ns_for_children == old_ns->time_ns)) {
+			get_nsproxy(old_ns);
+			return 0;
+		}
+	} else if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
@@ -162,6 +178,12 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	if (IS_ERR(new_ns))
 		return  PTR_ERR(new_ns);
 
+	ret = timens_on_fork(new_ns, tsk);
+	if (ret) {
+		free_nsproxy(new_ns);
+		return ret;
+	}
+
 	tsk->nsproxy = new_ns;
 	return 0;
 }
@@ -176,6 +198,10 @@ void free_nsproxy(struct nsproxy *ns)
 		put_ipc_ns(ns->ipc_ns);
 	if (ns->pid_ns_for_children)
 		put_pid_ns(ns->pid_ns_for_children);
+	if (ns->time_ns)
+		put_time_ns(ns->time_ns);
+	if (ns->time_ns_for_children)
+		put_time_ns(ns->time_ns_for_children);
 	put_cgroup_ns(ns->cgroup_ns);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
@@ -192,7 +218,8 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 	int err = 0;
 
 	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-			       CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP)))
+			       CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP |
+			       CLONE_NEWTIME)))
 		return 0;
 
 	user_ns = new_cred ? new_cred->user_ns : current_user_ns();
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 1867044800bb..c8f00168afe8 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -19,3 +19,4 @@ obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
 obj-$(CONFIG_HAVE_GENERIC_VDSO)			+= vsyscall.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
+obj-$(CONFIG_TIME_NS)				+= namespace.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 451f9d05ccfe..2ffb466af77e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -26,6 +26,7 @@
 #include <linux/freezer.h>
 #include <linux/compat.h>
 #include <linux/module.h>
+#include <linux/time_namespace.h>
 
 #include "posix-timers.h"
 
@@ -36,13 +37,15 @@
  * struct alarm_base - Alarm timer bases
  * @lock:		Lock for syncrhonized access to the base
  * @timerqueue:		Timerqueue head managing the list of events
- * @gettime:		Function to read the time correlating to the base
+ * @get_ktime:		Function to read the time correlating to the base
+ * @get_timespec:	Function to read the namespace time correlating to the base
  * @base_clockid:	clockid for the base
  */
 static struct alarm_base {
 	spinlock_t		lock;
 	struct timerqueue_head	timerqueue;
-	ktime_t			(*gettime)(void);
+	ktime_t			(*get_ktime)(void);
+	void			(*get_timespec)(struct timespec64 *tp);
 	clockid_t		base_clockid;
 } alarm_bases[ALARM_NUMTYPE];
 
@@ -55,8 +58,6 @@ static DEFINE_SPINLOCK(freezer_delta_lock);
 #endif
 
 #ifdef CONFIG_RTC_CLASS
-static struct wakeup_source *ws;
-
 /* rtc timer and device for setting alarm wakeups at suspend */
 static struct rtc_timer		rtctimer;
 static struct rtc_device	*rtcdev;
@@ -66,8 +67,6 @@ static DEFINE_SPINLOCK(rtcdev_lock);
  * alarmtimer_get_rtcdev - Return selected rtcdevice
  *
  * This function returns the rtc device to use for wakealarms.
- * If one has not already been chosen, it checks to see if a
- * functional rtc device is available.
  */
 struct rtc_device *alarmtimer_get_rtcdev(void)
 {
@@ -87,7 +86,8 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 {
 	unsigned long flags;
 	struct rtc_device *rtc = to_rtc_device(dev);
-	struct wakeup_source *__ws;
+	struct platform_device *pdev;
+	int ret = 0;
 
 	if (rtcdev)
 		return -EBUSY;
@@ -97,26 +97,31 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 	if (!device_may_wakeup(rtc->dev.parent))
 		return -1;
 
-	__ws = wakeup_source_register(dev, "alarmtimer");
+	pdev = platform_device_register_data(dev, "alarmtimer",
+					     PLATFORM_DEVID_AUTO, NULL, 0);
+	if (!IS_ERR(pdev))
+		device_init_wakeup(&pdev->dev, true);
 
 	spin_lock_irqsave(&rtcdev_lock, flags);
-	if (!rtcdev) {
+	if (!IS_ERR(pdev) && !rtcdev) {
 		if (!try_module_get(rtc->owner)) {
-			spin_unlock_irqrestore(&rtcdev_lock, flags);
-			return -1;
+			ret = -1;
+			goto unlock;
 		}
 
 		rtcdev = rtc;
 		/* hold a reference so it doesn't go away */
 		get_device(dev);
-		ws = __ws;
-		__ws = NULL;
+		pdev = NULL;
+	} else {
+		ret = -1;
 	}
+unlock:
 	spin_unlock_irqrestore(&rtcdev_lock, flags);
 
-	wakeup_source_unregister(__ws);
+	platform_device_unregister(pdev);
 
-	return 0;
+	return ret;
 }
 
 static inline void alarmtimer_rtc_timer_init(void)
@@ -138,11 +143,6 @@ static void alarmtimer_rtc_interface_remove(void)
 	class_interface_unregister(&alarmtimer_rtc_interface);
 }
 #else
-struct rtc_device *alarmtimer_get_rtcdev(void)
-{
-	return NULL;
-}
-#define rtcdev (NULL)
 static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
 static inline void alarmtimer_rtc_interface_remove(void) { }
 static inline void alarmtimer_rtc_timer_init(void) { }
@@ -207,7 +207,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	if (alarm->function)
-		restart = alarm->function(alarm, base->gettime());
+		restart = alarm->function(alarm, base->get_ktime());
 
 	spin_lock_irqsave(&base->lock, flags);
 	if (restart != ALARMTIMER_NORESTART) {
@@ -217,7 +217,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 	}
 	spin_unlock_irqrestore(&base->lock, flags);
 
-	trace_alarmtimer_fired(alarm, base->gettime());
+	trace_alarmtimer_fired(alarm, base->get_ktime());
 	return ret;
 
 }
@@ -225,7 +225,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 ktime_t alarm_expires_remaining(const struct alarm *alarm)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
-	return ktime_sub(alarm->node.expires, base->gettime());
+	return ktime_sub(alarm->node.expires, base->get_ktime());
 }
 EXPORT_SYMBOL_GPL(alarm_expires_remaining);
 
@@ -270,7 +270,7 @@ static int alarmtimer_suspend(struct device *dev)
 		spin_unlock_irqrestore(&base->lock, flags);
 		if (!next)
 			continue;
-		delta = ktime_sub(next->expires, base->gettime());
+		delta = ktime_sub(next->expires, base->get_ktime());
 		if (!min || (delta < min)) {
 			expires = next->expires;
 			min = delta;
@@ -281,7 +281,7 @@ static int alarmtimer_suspend(struct device *dev)
 		return 0;
 
 	if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
-		__pm_wakeup_event(ws, 2 * MSEC_PER_SEC);
+		pm_wakeup_event(dev, 2 * MSEC_PER_SEC);
 		return -EBUSY;
 	}
 
@@ -296,7 +296,7 @@ static int alarmtimer_suspend(struct device *dev)
 	/* Set alarm, if in the past reject suspend briefly to handle */
 	ret = rtc_timer_start(rtc, &rtctimer, now, 0);
 	if (ret < 0)
-		__pm_wakeup_event(ws, MSEC_PER_SEC);
+		pm_wakeup_event(dev, MSEC_PER_SEC);
 	return ret;
 }
 
@@ -364,7 +364,7 @@ void alarm_start(struct alarm *alarm, ktime_t start)
 	hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
 	spin_unlock_irqrestore(&base->lock, flags);
 
-	trace_alarmtimer_start(alarm, base->gettime());
+	trace_alarmtimer_start(alarm, base->get_ktime());
 }
 EXPORT_SYMBOL_GPL(alarm_start);
 
@@ -377,7 +377,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
-	start = ktime_add_safe(start, base->gettime());
+	start = ktime_add_safe(start, base->get_ktime());
 	alarm_start(alarm, start);
 }
 EXPORT_SYMBOL_GPL(alarm_start_relative);
@@ -414,7 +414,7 @@ int alarm_try_to_cancel(struct alarm *alarm)
 		alarmtimer_dequeue(base, alarm);
 	spin_unlock_irqrestore(&base->lock, flags);
 
-	trace_alarmtimer_cancel(alarm, base->gettime());
+	trace_alarmtimer_cancel(alarm, base->get_ktime());
 	return ret;
 }
 EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
@@ -474,7 +474,7 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
-	return alarm_forward(alarm, base->gettime(), interval);
+	return alarm_forward(alarm, base->get_ktime(), interval);
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 
@@ -500,7 +500,7 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
 		return;
 	}
 
-	delta = ktime_sub(absexp, base->gettime());
+	delta = ktime_sub(absexp, base->get_ktime());
 
 	spin_lock_irqsave(&freezer_delta_lock, flags);
 	if (!freezer_delta || (delta < freezer_delta)) {
@@ -632,7 +632,7 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
 	if (!absolute)
-		expires = ktime_add_safe(expires, base->gettime());
+		expires = ktime_add_safe(expires, base->get_ktime());
 	if (sigev_none)
 		alarm->node.expires = expires;
 	else
@@ -657,23 +657,40 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp
 }
 
 /**
- * alarm_clock_get - posix clock_get interface
+ * alarm_clock_get_timespec - posix clock_get_timespec interface
  * @which_clock: clockid
  * @tp: timespec to fill.
  *
- * Provides the underlying alarm base time.
+ * Provides the underlying alarm base time in a tasks time namespace.
  */
-static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp)
+static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp)
 {
 	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
 
 	if (!alarmtimer_get_rtcdev())
 		return -EINVAL;
 
-	*tp = ktime_to_timespec64(base->gettime());
+	base->get_timespec(tp);
+
 	return 0;
 }
 
+/**
+ * alarm_clock_get_ktime - posix clock_get_ktime interface
+ * @which_clock: clockid
+ *
+ * Provides the underlying alarm base time in the root namespace.
+ */
+static ktime_t alarm_clock_get_ktime(clockid_t which_clock)
+{
+	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+	if (!alarmtimer_get_rtcdev())
+		return -EINVAL;
+
+	return base->get_ktime();
+}
+
 /**
  * alarm_timer_create - posix timer_create interface
  * @new_timer: k_itimer pointer to manage
@@ -747,7 +764,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
 		struct timespec64 rmt;
 		ktime_t rem;
 
-		rem = ktime_sub(absexp, alarm_bases[type].gettime());
+		rem = ktime_sub(absexp, alarm_bases[type].get_ktime());
 
 		if (rem <= 0)
 			return 0;
@@ -816,9 +833,11 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	exp = timespec64_to_ktime(*tsreq);
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
-		ktime_t now = alarm_bases[type].gettime();
+		ktime_t now = alarm_bases[type].get_ktime();
 
 		exp = ktime_add_safe(now, exp);
+	} else {
+		exp = timens_ktime_to_host(which_clock, exp);
 	}
 
 	ret = alarmtimer_do_nsleep(&alarm, exp, type);
@@ -837,7 +856,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 
 const struct k_clock alarm_clock = {
 	.clock_getres		= alarm_clock_getres,
-	.clock_get		= alarm_clock_get,
+	.clock_get_ktime	= alarm_clock_get_ktime,
+	.clock_get_timespec	= alarm_clock_get_timespec,
 	.timer_create		= alarm_timer_create,
 	.timer_set		= common_timer_set,
 	.timer_del		= common_timer_del,
@@ -866,6 +886,12 @@ static struct platform_driver alarmtimer_driver = {
 	}
 };
 
+static void get_boottime_timespec(struct timespec64 *tp)
+{
+	ktime_get_boottime_ts64(tp);
+	timens_add_boottime(tp);
+}
+
 /**
  * alarmtimer_init - Initialize alarm timer code
  *
@@ -874,17 +900,18 @@ static struct platform_driver alarmtimer_driver = {
  */
 static int __init alarmtimer_init(void)
 {
-	struct platform_device *pdev;
-	int error = 0;
+	int error;
 	int i;
 
 	alarmtimer_rtc_timer_init();
 
 	/* Initialize alarm bases */
 	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
-	alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real;
+	alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real;
+	alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64,
 	alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
-	alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime;
+	alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime;
+	alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec;
 	for (i = 0; i < ALARM_NUMTYPE; i++) {
 		timerqueue_init_head(&alarm_bases[i].timerqueue);
 		spin_lock_init(&alarm_bases[i].lock);
@@ -898,15 +925,7 @@ static int __init alarmtimer_init(void)
 	if (error)
 		goto out_if;
 
-	pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0);
-	if (IS_ERR(pdev)) {
-		error = PTR_ERR(pdev);
-		goto out_drv;
-	}
 	return 0;
-
-out_drv:
-	platform_driver_unregister(&alarmtimer_driver);
 out_if:
 	alarmtimer_rtc_interface_remove();
 	return error;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8de90ea31280..3a609e7344f3 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1477,7 +1477,7 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
 static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 			  struct hrtimer_clock_base *base,
 			  struct hrtimer *timer, ktime_t *now,
-			  unsigned long flags)
+			  unsigned long flags) __must_hold(&cpu_base->lock)
 {
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
@@ -1910,8 +1910,8 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 	return ret;
 }
 
-long hrtimer_nanosleep(const struct timespec64 *rqtp,
-		       const enum hrtimer_mode mode, const clockid_t clockid)
+long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
+		       const clockid_t clockid)
 {
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
@@ -1923,7 +1923,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp,
 		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-	hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
+	hrtimer_set_expires_range_ns(&t.timer, rqtp, slack);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
 		goto out;
@@ -1958,7 +1958,8 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
 
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
-	return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+	return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
+				 CLOCK_MONOTONIC);
 }
 
 #endif
@@ -1978,7 +1979,8 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
 
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;
-	return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+	return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
+				 CLOCK_MONOTONIC);
 }
 #endif
 
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
new file mode 100644
index 000000000000..12858507d75a
--- /dev/null
+++ b/kernel/time/namespace.c
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Andrei Vagin <avagin@openvz.org>
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+
+#include <linux/time_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/seq_file.h>
+#include <linux/proc_ns.h>
+#include <linux/export.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+#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)
+{
+	ktime_t offset;
+
+	switch (clockid) {
+	case CLOCK_MONOTONIC:
+		offset = timespec64_to_ktime(ns_offsets->monotonic);
+		break;
+	case CLOCK_BOOTTIME:
+	case CLOCK_BOOTTIME_ALARM:
+		offset = timespec64_to_ktime(ns_offsets->boottime);
+		break;
+	default:
+		return tim;
+	}
+
+	/*
+	 * Check that @tim value is in [offset, KTIME_MAX + offset]
+	 * and subtract offset.
+	 */
+	if (tim < offset) {
+		/*
+		 * User can specify @tim *absolute* value - if it's lesser than
+		 * the time namespace's offset - it's already expired.
+		 */
+		tim = 0;
+	} else {
+		tim = ktime_sub(tim, offset);
+		if (unlikely(tim > KTIME_MAX))
+			tim = KTIME_MAX;
+	}
+
+	return tim;
+}
+
+static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES);
+}
+
+static void dec_time_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES);
+}
+
+/**
+ * clone_time_ns - Clone a time namespace
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * Clone @old_ns and set the clone refcount to 1
+ *
+ * Return: The new namespace or ERR_PTR.
+ */
+static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
+					  struct time_namespace *old_ns)
+{
+	struct time_namespace *ns;
+	struct ucounts *ucounts;
+	int err;
+
+	err = -ENOSPC;
+	ucounts = inc_time_namespaces(user_ns);
+	if (!ucounts)
+		goto fail;
+
+	err = -ENOMEM;
+	ns = kmalloc(sizeof(*ns), GFP_KERNEL);
+	if (!ns)
+		goto fail_dec;
+
+	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_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:
+	dec_time_namespaces(ucounts);
+fail:
+	return ERR_PTR(err);
+}
+
+/**
+ * copy_time_ns - Create timens_for_children from @old_ns
+ * @flags:	Cloning flags
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children;
+ * adds a refcounter to @old_ns otherwise.
+ *
+ * Return: timens_for_children namespace or ERR_PTR.
+ */
+struct time_namespace *copy_time_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct time_namespace *old_ns)
+{
+	if (!(flags & CLONE_NEWTIME))
+		return get_time_ns(old_ns);
+
+	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;
+
+	ns = container_of(kref, struct time_namespace, kref);
+	dec_time_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+	ns_free_inum(&ns->ns);
+	__free_page(ns->vvar_page);
+	kfree(ns);
+}
+
+static struct time_namespace *to_time_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct time_namespace, ns);
+}
+
+static struct ns_common *timens_get(struct task_struct *task)
+{
+	struct time_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->time_ns;
+		get_time_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static struct ns_common *timens_for_children_get(struct task_struct *task)
+{
+	struct time_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->time_ns_for_children;
+		get_time_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void timens_put(struct ns_common *ns)
+{
+	put_time_ns(to_time_ns(ns));
+}
+
+static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
+{
+	struct time_namespace *ns = to_time_ns(new);
+	int err;
+
+	if (!current_is_single_threaded())
+		return -EUSERS;
+
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	timens_set_vvar_page(current, ns);
+
+	err = vdso_join_timens(current, ns);
+	if (err)
+		return err;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns_for_children);
+	nsproxy->time_ns_for_children = ns;
+	return 0;
+}
+
+int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
+{
+	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
+	struct time_namespace *ns = to_time_ns(nsc);
+	int err;
+
+	/* create_new_namespaces() already incremented the ref counter */
+	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
+		return 0;
+
+	timens_set_vvar_page(tsk, ns);
+
+	err = vdso_join_timens(tsk, ns);
+	if (err)
+		return err;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	return 0;
+}
+
+static struct user_namespace *timens_owner(struct ns_common *ns)
+{
+	return to_time_ns(ns)->user_ns;
+}
+
+static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
+{
+	seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
+}
+
+void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
+{
+	struct ns_common *ns;
+	struct time_namespace *time_ns;
+
+	ns = timens_for_children_get(p);
+	if (!ns)
+		return;
+	time_ns = to_time_ns(ns);
+
+	show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic);
+	show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime);
+	put_time_ns(time_ns);
+}
+
+int proc_timens_set_offset(struct file *file, struct task_struct *p,
+			   struct proc_timens_offset *offsets, int noffsets)
+{
+	struct ns_common *ns;
+	struct time_namespace *time_ns;
+	struct timespec64 tp;
+	int i, err;
+
+	ns = timens_for_children_get(p);
+	if (!ns)
+		return -ESRCH;
+	time_ns = to_time_ns(ns);
+
+	if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) {
+		put_time_ns(time_ns);
+		return -EPERM;
+	}
+
+	for (i = 0; i < noffsets; i++) {
+		struct proc_timens_offset *off = &offsets[i];
+
+		switch (off->clockid) {
+		case CLOCK_MONOTONIC:
+			ktime_get_ts64(&tp);
+			break;
+		case CLOCK_BOOTTIME:
+			ktime_get_boottime_ts64(&tp);
+			break;
+		default:
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = -ERANGE;
+
+		if (off->val.tv_sec > KTIME_SEC_MAX ||
+		    off->val.tv_sec < -KTIME_SEC_MAX)
+			goto out;
+
+		tp = timespec64_add(tp, off->val);
+		/*
+		 * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is
+		 * still unreachable.
+		 */
+		if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2)
+			goto out;
+	}
+
+	mutex_lock(&offset_lock);
+	if (time_ns->frozen_offsets) {
+		err = -EACCES;
+		goto out_unlock;
+	}
+
+	err = 0;
+	/* Don't report errors after this line */
+	for (i = 0; i < noffsets; i++) {
+		struct proc_timens_offset *off = &offsets[i];
+		struct timespec64 *offset = NULL;
+
+		switch (off->clockid) {
+		case CLOCK_MONOTONIC:
+			offset = &time_ns->offsets.monotonic;
+			break;
+		case CLOCK_BOOTTIME:
+			offset = &time_ns->offsets.boottime;
+			break;
+		}
+
+		*offset = off->val;
+	}
+
+out_unlock:
+	mutex_unlock(&offset_lock);
+out:
+	put_time_ns(time_ns);
+
+	return err;
+}
+
+const struct proc_ns_operations timens_operations = {
+	.name		= "time",
+	.type		= CLONE_NEWTIME,
+	.get		= timens_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+const struct proc_ns_operations timens_for_children_operations = {
+	.name		= "time_for_children",
+	.type		= CLONE_NEWTIME,
+	.get		= timens_for_children_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+struct time_namespace init_time_ns = {
+	.kref		= KREF_INIT(3),
+	.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)
+{
+	return 0;
+}
+subsys_initcall(time_ns_init);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 200fb2d3be99..77c0c2370b6d 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -310,8 +310,8 @@ static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
 }
 
 const struct k_clock clock_posix_dynamic = {
-	.clock_getres	= pc_clock_getres,
-	.clock_set	= pc_clock_settime,
-	.clock_get	= pc_clock_gettime,
-	.clock_adj	= pc_clock_adjtime,
+	.clock_getres		= pc_clock_getres,
+	.clock_set		= pc_clock_settime,
+	.clock_get_timespec	= pc_clock_gettime,
+	.clock_adj		= pc_clock_adjtime,
 };
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 42d512fcfda2..8ff6da77a01f 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1391,26 +1391,26 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
 }
 
 const struct k_clock clock_posix_cpu = {
-	.clock_getres	= posix_cpu_clock_getres,
-	.clock_set	= posix_cpu_clock_set,
-	.clock_get	= posix_cpu_clock_get,
-	.timer_create	= posix_cpu_timer_create,
-	.nsleep		= posix_cpu_nsleep,
-	.timer_set	= posix_cpu_timer_set,
-	.timer_del	= posix_cpu_timer_del,
-	.timer_get	= posix_cpu_timer_get,
-	.timer_rearm	= posix_cpu_timer_rearm,
+	.clock_getres		= posix_cpu_clock_getres,
+	.clock_set		= posix_cpu_clock_set,
+	.clock_get_timespec	= posix_cpu_clock_get,
+	.timer_create		= posix_cpu_timer_create,
+	.nsleep			= posix_cpu_nsleep,
+	.timer_set		= posix_cpu_timer_set,
+	.timer_del		= posix_cpu_timer_del,
+	.timer_get		= posix_cpu_timer_get,
+	.timer_rearm		= posix_cpu_timer_rearm,
 };
 
 const struct k_clock clock_process = {
-	.clock_getres	= process_cpu_clock_getres,
-	.clock_get	= process_cpu_clock_get,
-	.timer_create	= process_cpu_timer_create,
-	.nsleep		= process_cpu_nsleep,
+	.clock_getres		= process_cpu_clock_getres,
+	.clock_get_timespec	= process_cpu_clock_get,
+	.timer_create		= process_cpu_timer_create,
+	.nsleep			= process_cpu_nsleep,
 };
 
 const struct k_clock clock_thread = {
-	.clock_getres	= thread_cpu_clock_getres,
-	.clock_get	= thread_cpu_clock_get,
-	.timer_create	= thread_cpu_timer_create,
+	.clock_getres		= thread_cpu_clock_getres,
+	.clock_get_timespec	= thread_cpu_clock_get,
+	.timer_create		= thread_cpu_timer_create,
 };
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 20c65a7d4e3a..fcb3b21d8bdc 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -14,6 +14,7 @@
 #include <linux/ktime.h>
 #include <linux/timekeeping.h>
 #include <linux/posix-timers.h>
+#include <linux/time_namespace.h>
 #include <linux/compat.h>
 
 #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
@@ -77,9 +78,11 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 		break;
 	case CLOCK_MONOTONIC:
 		ktime_get_ts64(tp);
+		timens_add_monotonic(tp);
 		break;
 	case CLOCK_BOOTTIME:
 		ktime_get_boottime_ts64(tp);
+		timens_add_boottime(tp);
 		break;
 	default:
 		return -EINVAL;
@@ -126,6 +129,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		struct __kernel_timespec __user *, rmtp)
 {
 	struct timespec64 t;
+	ktime_t texp;
 
 	switch (which_clock) {
 	case CLOCK_REALTIME:
@@ -144,7 +148,10 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		rmtp = NULL;
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
-	return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
+	texp = timespec64_to_ktime(t);
+	if (flags & TIMER_ABSTIME)
+		texp = timens_ktime_to_host(which_clock, texp);
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
 }
@@ -215,6 +222,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 		struct old_timespec32 __user *, rmtp)
 {
 	struct timespec64 t;
+	ktime_t texp;
 
 	switch (which_clock) {
 	case CLOCK_REALTIME:
@@ -233,7 +241,10 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 		rmtp = NULL;
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;
-	return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
+	texp = timespec64_to_ktime(t);
+	if (flags & TIMER_ABSTIME)
+		texp = timens_ktime_to_host(which_clock, texp);
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
 }
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 0ec5b7a1d769..ff0eb30de346 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -30,6 +30,7 @@
 #include <linux/hashtable.h>
 #include <linux/compat.h>
 #include <linux/nospec.h>
+#include <linux/time_namespace.h>
 
 #include "timekeeping.h"
 #include "posix-timers.h"
@@ -165,12 +166,17 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 }
 
 /* Get clock_realtime */
-static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp)
 {
 	ktime_get_real_ts64(tp);
 	return 0;
 }
 
+static ktime_t posix_get_realtime_ktime(clockid_t which_clock)
+{
+	return ktime_get_real();
+}
+
 /* Set clock_realtime */
 static int posix_clock_realtime_set(const clockid_t which_clock,
 				    const struct timespec64 *tp)
@@ -187,18 +193,25 @@ static int posix_clock_realtime_adj(const clockid_t which_clock,
 /*
  * Get monotonic time for posix timers
  */
-static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp)
 {
 	ktime_get_ts64(tp);
+	timens_add_monotonic(tp);
 	return 0;
 }
 
+static ktime_t posix_get_monotonic_ktime(clockid_t which_clock)
+{
+	return ktime_get();
+}
+
 /*
  * Get monotonic-raw time for posix timers
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
 {
 	ktime_get_raw_ts64(tp);
+	timens_add_monotonic(tp);
 	return 0;
 }
 
@@ -213,6 +226,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock,
 						struct timespec64 *tp)
 {
 	ktime_get_coarse_ts64(tp);
+	timens_add_monotonic(tp);
 	return 0;
 }
 
@@ -222,18 +236,29 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 	return 0;
 }
 
-static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp)
 {
 	ktime_get_boottime_ts64(tp);
+	timens_add_boottime(tp);
 	return 0;
 }
 
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static ktime_t posix_get_boottime_ktime(const clockid_t which_clock)
+{
+	return ktime_get_boottime();
+}
+
+static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp)
 {
 	ktime_get_clocktai_ts64(tp);
 	return 0;
 }
 
+static ktime_t posix_get_tai_ktime(clockid_t which_clock)
+{
+	return ktime_get_clocktai();
+}
+
 static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
 {
 	tp->tv_sec = 0;
@@ -645,7 +670,6 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 {
 	const struct k_clock *kc = timr->kclock;
 	ktime_t now, remaining, iv;
-	struct timespec64 ts64;
 	bool sig_none;
 
 	sig_none = timr->it_sigev_notify == SIGEV_NONE;
@@ -663,12 +687,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 			return;
 	}
 
-	/*
-	 * The timespec64 based conversion is suboptimal, but it's not
-	 * worth to implement yet another callback.
-	 */
-	kc->clock_get(timr->it_clock, &ts64);
-	now = timespec64_to_ktime(ts64);
+	now = kc->clock_get_ktime(timr->it_clock);
 
 	/*
 	 * When a requeue is pending or this is a SIGEV_NONE timer move the
@@ -781,7 +800,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
 	 * Posix magic: Relative CLOCK_REALTIME timers are not affected by
 	 * clock modifications, so they become CLOCK_MONOTONIC based under the
 	 * hood. See hrtimer_init(). Update timr->kclock, so the generic
-	 * functions which use timr->kclock->clock_get() work.
+	 * functions which use timr->kclock->clock_get_*() work.
 	 *
 	 * Note: it_clock stays unmodified, because the next timer_set() might
 	 * use ABSTIME, so it needs to switch back.
@@ -866,6 +885,8 @@ int common_timer_set(struct k_itimer *timr, int flags,
 
 	timr->it_interval = timespec64_to_ktime(new_setting->it_interval);
 	expires = timespec64_to_ktime(new_setting->it_value);
+	if (flags & TIMER_ABSTIME)
+		expires = timens_ktime_to_host(timr->it_clock, expires);
 	sigev_none = timr->it_sigev_notify == SIGEV_NONE;
 
 	kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none);
@@ -1067,7 +1088,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 	if (!kc)
 		return -EINVAL;
 
-	error = kc->clock_get(which_clock, &kernel_tp);
+	error = kc->clock_get_timespec(which_clock, &kernel_tp);
 
 	if (!error && put_timespec64(&kernel_tp, tp))
 		error = -EFAULT;
@@ -1149,7 +1170,7 @@ SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
 	if (!kc)
 		return -EINVAL;
 
-	err = kc->clock_get(which_clock, &ts);
+	err = kc->clock_get_timespec(which_clock, &ts);
 
 	if (!err && put_old_timespec32(&ts, tp))
 		err = -EFAULT;
@@ -1200,7 +1221,22 @@ SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
 static int common_nsleep(const clockid_t which_clock, int flags,
 			 const struct timespec64 *rqtp)
 {
-	return hrtimer_nanosleep(rqtp, flags & TIMER_ABSTIME ?
+	ktime_t texp = timespec64_to_ktime(*rqtp);
+
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
+				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+				 which_clock);
+}
+
+static int common_nsleep_timens(const clockid_t which_clock, int flags,
+			 const struct timespec64 *rqtp)
+{
+	ktime_t texp = timespec64_to_ktime(*rqtp);
+
+	if (flags & TIMER_ABSTIME)
+		texp = timens_ktime_to_host(which_clock, texp);
+
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
 }
@@ -1261,7 +1297,8 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 
 static const struct k_clock clock_realtime = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_clock_realtime_get,
+	.clock_get_timespec	= posix_get_realtime_timespec,
+	.clock_get_ktime	= posix_get_realtime_ktime,
 	.clock_set		= posix_clock_realtime_set,
 	.clock_adj		= posix_clock_realtime_adj,
 	.nsleep			= common_nsleep,
@@ -1279,8 +1316,9 @@ static const struct k_clock clock_realtime = {
 
 static const struct k_clock clock_monotonic = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_ktime_get_ts,
-	.nsleep			= common_nsleep,
+	.clock_get_timespec	= posix_get_monotonic_timespec,
+	.clock_get_ktime	= posix_get_monotonic_ktime,
+	.nsleep			= common_nsleep_timens,
 	.timer_create		= common_timer_create,
 	.timer_set		= common_timer_set,
 	.timer_get		= common_timer_get,
@@ -1295,22 +1333,23 @@ static const struct k_clock clock_monotonic = {
 
 static const struct k_clock clock_monotonic_raw = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_get_monotonic_raw,
+	.clock_get_timespec	= posix_get_monotonic_raw,
 };
 
 static const struct k_clock clock_realtime_coarse = {
 	.clock_getres		= posix_get_coarse_res,
-	.clock_get		= posix_get_realtime_coarse,
+	.clock_get_timespec	= posix_get_realtime_coarse,
 };
 
 static const struct k_clock clock_monotonic_coarse = {
 	.clock_getres		= posix_get_coarse_res,
-	.clock_get		= posix_get_monotonic_coarse,
+	.clock_get_timespec	= posix_get_monotonic_coarse,
 };
 
 static const struct k_clock clock_tai = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_get_tai,
+	.clock_get_ktime	= posix_get_tai_ktime,
+	.clock_get_timespec	= posix_get_tai_timespec,
 	.nsleep			= common_nsleep,
 	.timer_create		= common_timer_create,
 	.timer_set		= common_timer_set,
@@ -1326,8 +1365,9 @@ static const struct k_clock clock_tai = {
 
 static const struct k_clock clock_boottime = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_get_boottime,
-	.nsleep			= common_nsleep,
+	.clock_get_ktime	= posix_get_boottime_ktime,
+	.clock_get_timespec	= posix_get_boottime_timespec,
+	.nsleep			= common_nsleep_timens,
 	.timer_create		= common_timer_create,
 	.timer_set		= common_timer_set,
 	.timer_get		= common_timer_get,
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 897c29e162b9..f32a2ebba9b8 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -6,8 +6,11 @@ struct k_clock {
 				struct timespec64 *tp);
 	int	(*clock_set)(const clockid_t which_clock,
 			     const struct timespec64 *tp);
-	int	(*clock_get)(const clockid_t which_clock,
-			     struct timespec64 *tp);
+	/* Returns the clock value in the current time namespace. */
+	int	(*clock_get_timespec)(const clockid_t which_clock,
+				      struct timespec64 *tp);
+	/* Returns the clock value in the root time namespace. */
+	ktime_t	(*clock_get_ktime)(const clockid_t which_clock);
 	int	(*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx);
 	int	(*timer_create)(struct k_itimer *timer);
 	int	(*nsleep)(const clockid_t which_clock, int flags,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index dbd69052eaa6..e4332e3e2d56 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -169,14 +169,15 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 {
 	u64 res, wrap, new_mask, new_epoch, cyc, ns;
 	u32 new_mult, new_shift;
-	unsigned long r;
+	unsigned long r, flags;
 	char r_unit;
 	struct clock_read_data rd;
 
 	if (cd.rate > rate)
 		return;
 
-	WARN_ON(!irqs_disabled());
+	/* Cannot register a sched_clock with interrupts on */
+	local_irq_save(flags);
 
 	/* Calculate the mult/shift to convert counter ticks to ns. */
 	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
@@ -233,6 +234,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
 		enable_sched_clock_irqtime();
 
+	local_irq_restore(flags);
+
 	pr_debug("Registered %pS as sched_clock source\n", read);
 }
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 59225b484e4e..7e5d3524e924 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/hrtimer.h>
 #include <linux/interrupt.h>
+#include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
@@ -558,6 +559,7 @@ void tick_unfreeze(void)
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
 	} else {
+		touch_softlockup_watchdog();
 		tick_resume_local();
 	}
 
diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index 9fe698ff62ec..d883ac299508 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -24,4 +24,10 @@ config GENERIC_COMPAT_VDSO
 	help
 	  This config option enables the compat VDSO layer.
 
+config GENERIC_VDSO_TIME_NS
+	bool
+	help
+	  Selected by architectures which support time namespaces in the
+	  VDSO
+
 endif
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 42bd8ab955fa..f8b8ec5e63ac 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -38,12 +38,22 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 }
 #endif
 
-static int do_hres(const struct vdso_data *vd, clockid_t clk,
-		   struct __kernel_timespec *ts)
+#ifdef CONFIG_TIME_NS
+static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+			  struct __kernel_timespec *ts)
 {
-	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
-	u64 cycles, last, sec, ns;
+	const struct vdso_data *vd = __arch_get_timens_vdso_data();
+	const struct timens_offset *offs = &vdns->offset[clk];
+	const struct vdso_timestamp *vdso_ts;
+	u64 cycles, last, ns;
 	u32 seq;
+	s64 sec;
+
+	if (clk != CLOCK_MONOTONIC_RAW)
+		vd = &vd[CS_HRES_COARSE];
+	else
+		vd = &vd[CS_RAW];
+	vdso_ts = &vd->basetime[clk];
 
 	do {
 		seq = vdso_read_begin(vd);
@@ -58,6 +68,10 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
 		sec = vdso_ts->sec;
 	} while (unlikely(vdso_read_retry(vd, seq)));
 
+	/* Add the namespace offset */
+	sec += offs->sec;
+	ns += offs->nsec;
+
 	/*
 	 * Do this outside the loop: a race inside the loop could result
 	 * in __iter_div_u64_rem() being extremely slow.
@@ -67,18 +81,128 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
 
 	return 0;
 }
+#else
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+	return NULL;
+}
+
+static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+			  struct __kernel_timespec *ts)
+{
+	return -EINVAL;
+}
+#endif
 
-static void do_coarse(const struct vdso_data *vd, clockid_t clk,
-		      struct __kernel_timespec *ts)
+static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
+				   struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	u64 cycles, last, sec, ns;
 	u32 seq;
 
+	do {
+		/*
+		 * Open coded to handle VCLOCK_TIMENS. Time namespace
+		 * enabled tasks have a special VVAR page installed which
+		 * has vd->seq set to 1 and vd->clock_mode set to
+		 * VCLOCK_TIMENS. For non time namespace affected tasks
+		 * this does not affect performance because if vd->seq is
+		 * odd, i.e. a concurrent update is in progress the extra
+		 * check for vd->clock_mode is just a few extra
+		 * instructions while spin waiting for vd->seq to become
+		 * even again.
+		 */
+		while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) {
+			if (IS_ENABLED(CONFIG_TIME_NS) &&
+			    vd->clock_mode == VCLOCK_TIMENS)
+				return do_hres_timens(vd, clk, ts);
+			cpu_relax();
+		}
+		smp_rmb();
+
+		cycles = __arch_get_hw_counter(vd->clock_mode);
+		ns = vdso_ts->nsec;
+		last = vd->cycle_last;
+		if (unlikely((s64)cycles < 0))
+			return -1;
+
+		ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
+		ns >>= vd->shift;
+		sec = vdso_ts->sec;
+	} while (unlikely(vdso_read_retry(vd, seq)));
+
+	/*
+	 * Do this outside the loop: a race inside the loop could result
+	 * in __iter_div_u64_rem() being extremely slow.
+	 */
+	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	ts->tv_nsec = ns;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+			    struct __kernel_timespec *ts)
+{
+	const struct vdso_data *vd = __arch_get_timens_vdso_data();
+	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	const struct timens_offset *offs = &vdns->offset[clk];
+	u64 nsec;
+	s64 sec;
+	s32 seq;
+
 	do {
 		seq = vdso_read_begin(vd);
+		sec = vdso_ts->sec;
+		nsec = vdso_ts->nsec;
+	} while (unlikely(vdso_read_retry(vd, seq)));
+
+	/* Add the namespace offset */
+	sec += offs->sec;
+	nsec += offs->nsec;
+
+	/*
+	 * Do this outside the loop: a race inside the loop could result
+	 * in __iter_div_u64_rem() being extremely slow.
+	 */
+	ts->tv_sec = sec + __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
+	ts->tv_nsec = nsec;
+	return 0;
+}
+#else
+static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+			    struct __kernel_timespec *ts)
+{
+	return -1;
+}
+#endif
+
+static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
+				     struct __kernel_timespec *ts)
+{
+	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	u32 seq;
+
+	do {
+		/*
+		 * Open coded to handle VCLOCK_TIMENS. See comment in
+		 * do_hres().
+		 */
+		while ((seq = READ_ONCE(vd->seq)) & 1) {
+			if (IS_ENABLED(CONFIG_TIME_NS) &&
+			    vd->clock_mode == VCLOCK_TIMENS)
+				return do_coarse_timens(vd, clk, ts);
+			cpu_relax();
+		}
+		smp_rmb();
+
 		ts->tv_sec = vdso_ts->sec;
 		ts->tv_nsec = vdso_ts->nsec;
 	} while (unlikely(vdso_read_retry(vd, seq)));
+
+	return 0;
 }
 
 static __maybe_unused int
@@ -96,15 +220,16 @@ __cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts)
 	 * clocks are handled in the VDSO directly.
 	 */
 	msk = 1U << clock;
-	if (likely(msk & VDSO_HRES)) {
-		return do_hres(&vd[CS_HRES_COARSE], clock, ts);
-	} else if (msk & VDSO_COARSE) {
-		do_coarse(&vd[CS_HRES_COARSE], clock, ts);
-		return 0;
-	} else if (msk & VDSO_RAW) {
-		return do_hres(&vd[CS_RAW], clock, ts);
-	}
-	return -1;
+	if (likely(msk & VDSO_HRES))
+		vd = &vd[CS_HRES_COARSE];
+	else if (msk & VDSO_COARSE)
+		return do_coarse(&vd[CS_HRES_COARSE], clock, ts);
+	else if (msk & VDSO_RAW)
+		vd = &vd[CS_RAW];
+	else
+		return -1;
+
+	return do_hres(vd, clock, ts);
 }
 
 static __maybe_unused int
@@ -117,6 +242,7 @@ __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 	return 0;
 }
 
+#ifdef BUILD_VDSO32
 static __maybe_unused int
 __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 {
@@ -125,20 +251,16 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 
 	ret = __cvdso_clock_gettime_common(clock, &ts);
 
-#ifdef VDSO_HAS_32BIT_FALLBACK
 	if (unlikely(ret))
 		return clock_gettime32_fallback(clock, res);
-#else
-	if (unlikely(ret))
-		ret = clock_gettime_fallback(clock, &ts);
-#endif
 
-	if (likely(!ret)) {
-		res->tv_sec = ts.tv_sec;
-		res->tv_nsec = ts.tv_nsec;
-	}
+	/* For ret == 0 */
+	res->tv_sec = ts.tv_sec;
+	res->tv_nsec = ts.tv_nsec;
+
 	return ret;
 }
+#endif /* BUILD_VDSO32 */
 
 static __maybe_unused int
 __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
@@ -156,6 +278,10 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 	}
 
 	if (unlikely(tz != NULL)) {
+		if (IS_ENABLED(CONFIG_TIME_NS) &&
+		    vd->clock_mode == VCLOCK_TIMENS)
+			vd = __arch_get_timens_vdso_data();
+
 		tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest;
 		tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime;
 	}
@@ -167,7 +293,12 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
-	__kernel_old_time_t t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
+	__kernel_old_time_t t;
+
+	if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VCLOCK_TIMENS)
+		vd = __arch_get_timens_vdso_data();
+
+	t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
 
 	if (time)
 		*time = t;
@@ -181,7 +312,6 @@ static __maybe_unused
 int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
-	u64 hrtimer_res;
 	u32 msk;
 	u64 ns;
 
@@ -189,27 +319,24 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
 	if (unlikely((u32) clock >= MAX_CLOCKS))
 		return -1;
 
-	hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
+	if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VCLOCK_TIMENS)
+		vd = __arch_get_timens_vdso_data();
+
 	/*
 	 * Convert the clockid to a bitmask and use it to check which
 	 * clocks are handled in the VDSO directly.
 	 */
 	msk = 1U << clock;
-	if (msk & VDSO_HRES) {
+	if (msk & (VDSO_HRES | VDSO_RAW)) {
 		/*
 		 * Preserves the behaviour of posix_get_hrtimer_res().
 		 */
-		ns = hrtimer_res;
+		ns = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
 	} else if (msk & VDSO_COARSE) {
 		/*
 		 * Preserves the behaviour of posix_get_coarse_res().
 		 */
 		ns = LOW_RES_NSEC;
-	} else if (msk & VDSO_RAW) {
-		/*
-		 * Preserves the behaviour of posix_get_hrtimer_res().
-		 */
-		ns = hrtimer_res;
 	} else {
 		return -1;
 	}
@@ -231,6 +358,7 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
 	return 0;
 }
 
+#ifdef BUILD_VDSO32
 static __maybe_unused int
 __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 {
@@ -239,18 +367,14 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 
 	ret = __cvdso_clock_getres_common(clock, &ts);
 
-#ifdef VDSO_HAS_32BIT_FALLBACK
 	if (unlikely(ret))
 		return clock_getres32_fallback(clock, res);
-#else
-	if (unlikely(ret))
-		ret = clock_getres_fallback(clock, &ts);
-#endif
 
-	if (likely(!ret && res)) {
+	if (likely(res)) {
 		res->tv_sec = ts.tv_sec;
 		res->tv_nsec = ts.tv_nsec;
 	}
 	return ret;
 }
+#endif /* BUILD_VDSO32 */
 #endif /* VDSO_HAS_CLOCK_GETRES */
diff --git a/mm/mmap.c b/mm/mmap.c
index 9c648524e4dc..60c17d3c8762 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3342,6 +3342,8 @@ static const struct vm_operations_struct special_mapping_vmops = {
 	.fault = special_mapping_fault,
 	.mremap = special_mapping_mremap,
 	.name = special_mapping_name,
+	/* vDSO code relies that VVAR can't be accessed remotely */
+	.access = NULL,
 };
 
 static const struct vm_operations_struct legacy_special_mapping_vmops = {
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index b9c203219691..e6b6181c6dc6 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -41,9 +41,11 @@
 
 #include <bpf.h>
 
-int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+#define NSEC_PER_SEC	1000000000L
+
+int probe(hrtimer_nanosleep, rqtp)(void *ctx, int err, long long sec)
 {
-	return sec == 5;
+	return sec / NSEC_PER_SEC == 5ULL;
 }
 
 license(GPL);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b001c602414b..c4939a2a5f5d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -50,6 +50,7 @@ TARGETS += splice
 TARGETS += static_keys
 TARGETS += sync
 TARGETS += sysctl
+TARGETS += timens
 ifneq (1, $(quicktest))
 TARGETS += timers
 endif
diff --git a/tools/testing/selftests/timens/.gitignore b/tools/testing/selftests/timens/.gitignore
new file mode 100644
index 000000000000..789f21e81028
--- /dev/null
+++ b/tools/testing/selftests/timens/.gitignore
@@ -0,0 +1,8 @@
+clock_nanosleep
+exec
+gettime_perf
+gettime_perf_cold
+procfs
+timens
+timer
+timerfd
diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile
new file mode 100644
index 000000000000..e9fb30bd8aeb
--- /dev/null
+++ b/tools/testing/selftests/timens/Makefile
@@ -0,0 +1,7 @@
+TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec
+TEST_GEN_PROGS_EXTENDED := gettime_perf
+
+CFLAGS := -Wall -Werror -pthread
+LDFLAGS := -lrt -ldl
+
+include ../lib.mk
diff --git a/tools/testing/selftests/timens/clock_nanosleep.c b/tools/testing/selftests/timens/clock_nanosleep.c
new file mode 100644
index 000000000000..8e7b7c72ef65
--- /dev/null
+++ b/tools/testing/selftests/timens/clock_nanosleep.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <sys/timerfd.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <pthread.h>
+#include <signal.h>
+#include <string.h>
+
+#include "log.h"
+#include "timens.h"
+
+void test_sig(int sig)
+{
+	if (sig == SIGUSR2)
+		pthread_exit(NULL);
+}
+
+struct thread_args {
+	struct timespec *now, *rem;
+	pthread_mutex_t *lock;
+	int clockid;
+	int abs;
+};
+
+void *call_nanosleep(void *_args)
+{
+	struct thread_args *args = _args;
+
+	clock_nanosleep(args->clockid, args->abs ? TIMER_ABSTIME : 0, args->now, args->rem);
+	pthread_mutex_unlock(args->lock);
+	return NULL;
+}
+
+int run_test(int clockid, int abs)
+{
+	struct timespec now = {}, rem;
+	struct thread_args args = { .now = &now, .rem = &rem, .clockid = clockid};
+	struct timespec start;
+	pthread_mutex_t lock;
+	pthread_t thread;
+	int j, ok, ret;
+
+	signal(SIGUSR1, test_sig);
+	signal(SIGUSR2, test_sig);
+
+	pthread_mutex_init(&lock, NULL);
+	pthread_mutex_lock(&lock);
+
+	if (clock_gettime(clockid, &start) == -1) {
+		if (errno == EINVAL && check_skip(clockid))
+			return 0;
+		return pr_perror("clock_gettime");
+	}
+
+
+	if (abs) {
+		now.tv_sec = start.tv_sec;
+		now.tv_nsec = start.tv_nsec;
+	}
+
+	now.tv_sec += 3600;
+	args.abs = abs;
+	args.lock = &lock;
+	ret = pthread_create(&thread, NULL, call_nanosleep, &args);
+	if (ret != 0) {
+		pr_err("Unable to create a thread: %s", strerror(ret));
+		return 1;
+	}
+
+	/* Wait when the thread will call clock_nanosleep(). */
+	ok = 0;
+	for (j = 0; j < 8; j++) {
+		/* The maximum timeout is about 5 seconds. */
+		usleep(10000 << j);
+
+		/* Try to interrupt clock_nanosleep(). */
+		pthread_kill(thread, SIGUSR1);
+
+		usleep(10000 << j);
+		/* Check whether clock_nanosleep() has been interrupted or not. */
+		if (pthread_mutex_trylock(&lock) == 0) {
+			/**/
+			ok = 1;
+			break;
+		}
+	}
+	if (!ok)
+		pthread_kill(thread, SIGUSR2);
+	pthread_join(thread, NULL);
+	pthread_mutex_destroy(&lock);
+
+	if (!ok) {
+		ksft_test_result_pass("clockid: %d abs:%d timeout\n", clockid, abs);
+		return 1;
+	}
+
+	if (rem.tv_sec < 3300 || rem.tv_sec > 3900) {
+		pr_fail("clockid: %d abs: %d remain: %ld\n",
+			clockid, abs, rem.tv_sec);
+		return 1;
+	}
+	ksft_test_result_pass("clockid: %d abs:%d\n", clockid, abs);
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int ret, nsfd;
+
+	nscheck();
+
+	ksft_set_plan(4);
+
+	check_config_posix_timers();
+
+	if (unshare_timens())
+		return 1;
+
+	if (_settime(CLOCK_MONOTONIC, 7 * 24 * 3600))
+		return 1;
+	if (_settime(CLOCK_BOOTTIME, 9 * 24 * 3600))
+		return 1;
+
+	nsfd = open("/proc/self/ns/time_for_children", O_RDONLY);
+	if (nsfd < 0)
+		return pr_perror("Unable to open timens_for_children");
+
+	if (setns(nsfd, CLONE_NEWTIME))
+		return pr_perror("Unable to set timens");
+
+	ret = 0;
+	ret |= run_test(CLOCK_MONOTONIC, 0);
+	ret |= run_test(CLOCK_MONOTONIC, 1);
+	ret |= run_test(CLOCK_BOOTTIME_ALARM, 0);
+	ret |= run_test(CLOCK_BOOTTIME_ALARM, 1);
+
+	if (ret)
+		ksft_exit_fail();
+	ksft_exit_pass();
+	return ret;
+}
diff --git a/tools/testing/selftests/timens/config b/tools/testing/selftests/timens/config
new file mode 100644
index 000000000000..4480620f6f49
--- /dev/null
+++ b/tools/testing/selftests/timens/config
@@ -0,0 +1 @@
+CONFIG_TIME_NS=y
diff --git a/tools/testing/selftests/timens/exec.c b/tools/testing/selftests/timens/exec.c
new file mode 100644
index 000000000000..87b47b557a7a
--- /dev/null
+++ b/tools/testing/selftests/timens/exec.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+#include <time.h>
+#include <string.h>
+
+#include "log.h"
+#include "timens.h"
+
+#define OFFSET (36000)
+
+int main(int argc, char *argv[])
+{
+	struct timespec now, tst;
+	int status, i;
+	pid_t pid;
+
+	if (argc > 1) {
+		if (sscanf(argv[1], "%ld", &now.tv_sec) != 1)
+			return pr_perror("sscanf");
+
+		for (i = 0; i < 2; i++) {
+			_gettime(CLOCK_MONOTONIC, &tst, i);
+			if (abs(tst.tv_sec - now.tv_sec) > 5)
+				return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec);
+		}
+		return 0;
+	}
+
+	nscheck();
+
+	ksft_set_plan(1);
+
+	clock_gettime(CLOCK_MONOTONIC, &now);
+
+	if (unshare_timens())
+		return 1;
+
+	if (_settime(CLOCK_MONOTONIC, OFFSET))
+		return 1;
+
+	for (i = 0; i < 2; i++) {
+		_gettime(CLOCK_MONOTONIC, &tst, i);
+		if (abs(tst.tv_sec - now.tv_sec) > 5)
+			return pr_fail("%ld %ld\n",
+					now.tv_sec, tst.tv_sec);
+	}
+
+	if (argc > 1)
+		return 0;
+
+	pid = fork();
+	if (pid < 0)
+		return pr_perror("fork");
+
+	if (pid == 0) {
+		char now_str[64];
+		char *cargv[] = {"exec", now_str, NULL};
+		char *cenv[] = {NULL};
+
+		/* Check that a child process is in the new timens. */
+		for (i = 0; i < 2; i++) {
+			_gettime(CLOCK_MONOTONIC, &tst, i);
+			if (abs(tst.tv_sec - now.tv_sec - OFFSET) > 5)
+				return pr_fail("%ld %ld\n",
+						now.tv_sec + OFFSET, tst.tv_sec);
+		}
+
+		/* Check for proper vvar offsets after execve. */
+		snprintf(now_str, sizeof(now_str), "%ld", now.tv_sec + OFFSET);
+		execve("/proc/self/exe", cargv, cenv);
+		return pr_perror("execve");
+	}
+
+	if (waitpid(pid, &status, 0) != pid)
+		return pr_perror("waitpid");
+
+	if (status)
+		ksft_exit_fail();
+
+	ksft_test_result_pass("exec\n");
+	ksft_exit_pass();
+	return 0;
+}
diff --git a/tools/testing/selftests/timens/gettime_perf.c b/tools/testing/selftests/timens/gettime_perf.c
new file mode 100644
index 000000000000..7bf841a3967b
--- /dev/null
+++ b/tools/testing/selftests/timens/gettime_perf.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <time.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <dlfcn.h>
+
+#include "log.h"
+#include "timens.h"
+
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+
+vgettime_t vdso_clock_gettime;
+
+static void fill_function_pointers(void)
+{
+	void *vdso = dlopen("linux-vdso.so.1",
+			    RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso)
+		vdso = dlopen("linux-gate.so.1",
+			      RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso) {
+		pr_err("[WARN]\tfailed to find vDSO\n");
+		return;
+	}
+
+	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+	if (!vdso_clock_gettime)
+		pr_err("Warning: failed to find clock_gettime in vDSO\n");
+
+}
+
+static void test(clock_t clockid, char *clockstr, bool in_ns)
+{
+	struct timespec tp, start;
+	long i = 0;
+	const int timeout = 3;
+
+	vdso_clock_gettime(clockid, &start);
+	tp = start;
+	for (tp = start; start.tv_sec + timeout > tp.tv_sec ||
+			 (start.tv_sec + timeout == tp.tv_sec &&
+			  start.tv_nsec > tp.tv_nsec); i++) {
+		vdso_clock_gettime(clockid, &tp);
+	}
+
+	ksft_test_result_pass("%s:\tclock: %10s\tcycles:\t%10ld\n",
+			      in_ns ? "ns" : "host", clockstr, i);
+}
+
+int main(int argc, char *argv[])
+{
+	time_t offset = 10;
+	int nsfd;
+
+	ksft_set_plan(8);
+
+	fill_function_pointers();
+
+	test(CLOCK_MONOTONIC, "monotonic", false);
+	test(CLOCK_MONOTONIC_COARSE, "monotonic-coarse", false);
+	test(CLOCK_MONOTONIC_RAW, "monotonic-raw", false);
+	test(CLOCK_BOOTTIME, "boottime", false);
+
+	nscheck();
+
+	if (unshare_timens())
+		return 1;
+
+	nsfd = open("/proc/self/ns/time_for_children", O_RDONLY);
+	if (nsfd < 0)
+		return pr_perror("Can't open a time namespace");
+
+	if (_settime(CLOCK_MONOTONIC, offset))
+		return 1;
+	if (_settime(CLOCK_BOOTTIME, offset))
+		return 1;
+
+	if (setns(nsfd, CLONE_NEWTIME))
+		return pr_perror("setns");
+
+	test(CLOCK_MONOTONIC, "monotonic", true);
+	test(CLOCK_MONOTONIC_COARSE, "monotonic-coarse", true);
+	test(CLOCK_MONOTONIC_RAW, "monotonic-raw", true);
+	test(CLOCK_BOOTTIME, "boottime", true);
+
+	ksft_exit_pass();
+	return 0;
+}
diff --git a/tools/testing/selftests/timens/log.h b/tools/testing/selftests/timens/log.h
new file mode 100644
index 000000000000..db64df2a8483
--- /dev/null
+++ b/tools/testing/selftests/timens/log.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SELFTEST_TIMENS_LOG_H__
+#define __SELFTEST_TIMENS_LOG_H__
+
+#define pr_msg(fmt, lvl, ...)						\
+	ksft_print_msg("[%s] (%s:%d)\t" fmt "\n",			\
+			lvl, __FILE__, __LINE__, ##__VA_ARGS__)
+
+#define pr_p(func, fmt, ...)	func(fmt ": %m", ##__VA_ARGS__)
+
+#define pr_err(fmt, ...)						\
+	({								\
+		ksft_test_result_error(fmt "\n", ##__VA_ARGS__);		\
+		-1;							\
+	})
+
+#define pr_fail(fmt, ...)					\
+	({							\
+		ksft_test_result_fail(fmt, ##__VA_ARGS__);	\
+		-1;						\
+	})
+
+#define pr_perror(fmt, ...)	pr_p(pr_err, fmt, ##__VA_ARGS__)
+
+#endif
diff --git a/tools/testing/selftests/timens/procfs.c b/tools/testing/selftests/timens/procfs.c
new file mode 100644
index 000000000000..43d93f4006b9
--- /dev/null
+++ b/tools/testing/selftests/timens/procfs.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <time.h>
+
+#include "log.h"
+#include "timens.h"
+
+/*
+ * Test shouldn't be run for a day, so add 10 days to child
+ * time and check parent's time to be in the same day.
+ */
+#define MAX_TEST_TIME_SEC		(60*5)
+#define DAY_IN_SEC			(60*60*24)
+#define TEN_DAYS_IN_SEC			(10*DAY_IN_SEC)
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static int child_ns, parent_ns;
+
+static int switch_ns(int fd)
+{
+	if (setns(fd, CLONE_NEWTIME))
+		return pr_perror("setns()");
+
+	return 0;
+}
+
+static int init_namespaces(void)
+{
+	char path[] = "/proc/self/ns/time_for_children";
+	struct stat st1, st2;
+
+	parent_ns = open(path, O_RDONLY);
+	if (parent_ns <= 0)
+		return pr_perror("Unable to open %s", path);
+
+	if (fstat(parent_ns, &st1))
+		return pr_perror("Unable to stat the parent timens");
+
+	if (unshare_timens())
+		return -1;
+
+	child_ns = open(path, O_RDONLY);
+	if (child_ns <= 0)
+		return pr_perror("Unable to open %s", path);
+
+	if (fstat(child_ns, &st2))
+		return pr_perror("Unable to stat the timens");
+
+	if (st1.st_ino == st2.st_ino)
+		return pr_err("The same child_ns after CLONE_NEWTIME");
+
+	if (_settime(CLOCK_BOOTTIME, TEN_DAYS_IN_SEC))
+		return -1;
+
+	return 0;
+}
+
+static int read_proc_uptime(struct timespec *uptime)
+{
+	unsigned long up_sec, up_nsec;
+	FILE *proc;
+
+	proc = fopen("/proc/uptime", "r");
+	if (proc == NULL) {
+		pr_perror("Unable to open /proc/uptime");
+		return -1;
+	}
+
+	if (fscanf(proc, "%lu.%02lu", &up_sec, &up_nsec) != 2) {
+		if (errno) {
+			pr_perror("fscanf");
+			return -errno;
+		}
+		pr_err("failed to parse /proc/uptime");
+		return -1;
+	}
+	fclose(proc);
+
+	uptime->tv_sec = up_sec;
+	uptime->tv_nsec = up_nsec;
+	return 0;
+}
+
+static int check_uptime(void)
+{
+	struct timespec uptime_new, uptime_old;
+	time_t uptime_expected;
+	double prec = MAX_TEST_TIME_SEC;
+
+	if (switch_ns(parent_ns))
+		return pr_err("switch_ns(%d)", parent_ns);
+
+	if (read_proc_uptime(&uptime_old))
+		return 1;
+
+	if (switch_ns(child_ns))
+		return pr_err("switch_ns(%d)", child_ns);
+
+	if (read_proc_uptime(&uptime_new))
+		return 1;
+
+	uptime_expected = uptime_old.tv_sec + TEN_DAYS_IN_SEC;
+	if (fabs(difftime(uptime_new.tv_sec, uptime_expected)) > prec) {
+		pr_fail("uptime in /proc/uptime: old %ld, new %ld [%ld]",
+			uptime_old.tv_sec, uptime_new.tv_sec,
+			uptime_old.tv_sec + TEN_DAYS_IN_SEC);
+		return 1;
+	}
+
+	ksft_test_result_pass("Passed for /proc/uptime\n");
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int ret = 0;
+
+	nscheck();
+
+	ksft_set_plan(1);
+
+	if (init_namespaces())
+		return 1;
+
+	ret |= check_uptime();
+
+	if (ret)
+		ksft_exit_fail();
+	ksft_exit_pass();
+	return ret;
+}
diff --git a/tools/testing/selftests/timens/timens.c b/tools/testing/selftests/timens/timens.c
new file mode 100644
index 000000000000..559d26e21ba0
--- /dev/null
+++ b/tools/testing/selftests/timens/timens.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <time.h>
+#include <string.h>
+
+#include "log.h"
+#include "timens.h"
+
+/*
+ * Test shouldn't be run for a day, so add 10 days to child
+ * time and check parent's time to be in the same day.
+ */
+#define DAY_IN_SEC			(60*60*24)
+#define TEN_DAYS_IN_SEC			(10*DAY_IN_SEC)
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+struct test_clock {
+	clockid_t id;
+	char *name;
+	/*
+	 * off_id is -1 if a clock has own offset, or it contains an index
+	 * which contains a right offset of this clock.
+	 */
+	int off_id;
+	time_t offset;
+};
+
+#define ct(clock, off_id)	{ clock, #clock, off_id }
+static struct test_clock clocks[] = {
+	ct(CLOCK_BOOTTIME, -1),
+	ct(CLOCK_BOOTTIME_ALARM, 1),
+	ct(CLOCK_MONOTONIC, -1),
+	ct(CLOCK_MONOTONIC_COARSE, 1),
+	ct(CLOCK_MONOTONIC_RAW, 1),
+};
+#undef ct
+
+static int child_ns, parent_ns = -1;
+
+static int switch_ns(int fd)
+{
+	if (setns(fd, CLONE_NEWTIME)) {
+		pr_perror("setns()");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int init_namespaces(void)
+{
+	char path[] = "/proc/self/ns/time_for_children";
+	struct stat st1, st2;
+
+	if (parent_ns == -1) {
+		parent_ns = open(path, O_RDONLY);
+		if (parent_ns <= 0)
+			return pr_perror("Unable to open %s", path);
+	}
+
+	if (fstat(parent_ns, &st1))
+		return pr_perror("Unable to stat the parent timens");
+
+	if (unshare_timens())
+		return  -1;
+
+	child_ns = open(path, O_RDONLY);
+	if (child_ns <= 0)
+		return pr_perror("Unable to open %s", path);
+
+	if (fstat(child_ns, &st2))
+		return pr_perror("Unable to stat the timens");
+
+	if (st1.st_ino == st2.st_ino)
+		return pr_perror("The same child_ns after CLONE_NEWTIME");
+
+	return 0;
+}
+
+static int test_gettime(clockid_t clock_index, bool raw_syscall, time_t offset)
+{
+	struct timespec child_ts_new, parent_ts_old, cur_ts;
+	char *entry = raw_syscall ? "syscall" : "vdso";
+	double precision = 0.0;
+
+	if (check_skip(clocks[clock_index].id))
+		return 0;
+
+	switch (clocks[clock_index].id) {
+	case CLOCK_MONOTONIC_COARSE:
+	case CLOCK_MONOTONIC_RAW:
+		precision = -2.0;
+		break;
+	}
+
+	if (switch_ns(parent_ns))
+		return pr_err("switch_ns(%d)", child_ns);
+
+	if (_gettime(clocks[clock_index].id, &parent_ts_old, raw_syscall))
+		return -1;
+
+	child_ts_new.tv_nsec = parent_ts_old.tv_nsec;
+	child_ts_new.tv_sec = parent_ts_old.tv_sec + offset;
+
+	if (switch_ns(child_ns))
+		return pr_err("switch_ns(%d)", child_ns);
+
+	if (_gettime(clocks[clock_index].id, &cur_ts, raw_syscall))
+		return -1;
+
+	if (difftime(cur_ts.tv_sec, child_ts_new.tv_sec) < precision) {
+		ksft_test_result_fail(
+			"Child's %s (%s) time has not changed: %lu -> %lu [%lu]\n",
+			clocks[clock_index].name, entry, parent_ts_old.tv_sec,
+			child_ts_new.tv_sec, cur_ts.tv_sec);
+		return -1;
+	}
+
+	if (switch_ns(parent_ns))
+		return pr_err("switch_ns(%d)", parent_ns);
+
+	if (_gettime(clocks[clock_index].id, &cur_ts, raw_syscall))
+		return -1;
+
+	if (difftime(cur_ts.tv_sec, parent_ts_old.tv_sec) > DAY_IN_SEC) {
+		ksft_test_result_fail(
+			"Parent's %s (%s) time has changed: %lu -> %lu [%lu]\n",
+			clocks[clock_index].name, entry, parent_ts_old.tv_sec,
+			child_ts_new.tv_sec, cur_ts.tv_sec);
+		/* Let's play nice and put it closer to original */
+		clock_settime(clocks[clock_index].id, &cur_ts);
+		return -1;
+	}
+
+	ksft_test_result_pass("Passed for %s (%s)\n",
+				clocks[clock_index].name, entry);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned int i;
+	time_t offset;
+	int ret = 0;
+
+	nscheck();
+
+	check_config_posix_timers();
+
+	ksft_set_plan(ARRAY_SIZE(clocks) * 2);
+
+	if (init_namespaces())
+		return 1;
+
+	/* Offsets have to be set before tasks enter the namespace. */
+	for (i = 0; i < ARRAY_SIZE(clocks); i++) {
+		if (clocks[i].off_id != -1)
+			continue;
+		offset = TEN_DAYS_IN_SEC + i * 1000;
+		clocks[i].offset = offset;
+		if (_settime(clocks[i].id, offset))
+			return 1;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(clocks); i++) {
+		if (clocks[i].off_id != -1)
+			offset = clocks[clocks[i].off_id].offset;
+		else
+			offset = clocks[i].offset;
+		ret |= test_gettime(i, true, offset);
+		ret |= test_gettime(i, false, offset);
+	}
+
+	if (ret)
+		ksft_exit_fail();
+
+	ksft_exit_pass();
+	return !!ret;
+}
diff --git a/tools/testing/selftests/timens/timens.h b/tools/testing/selftests/timens/timens.h
new file mode 100644
index 000000000000..e09e7e39bc52
--- /dev/null
+++ b/tools/testing/selftests/timens/timens.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TIMENS_H__
+#define __TIMENS_H__
+
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#include "../kselftest.h"
+
+#ifndef CLONE_NEWTIME
+# define CLONE_NEWTIME	0x00000080
+#endif
+
+static int config_posix_timers = true;
+
+static inline void check_config_posix_timers(void)
+{
+	if (timer_create(-1, 0, 0) == -1 && errno == ENOSYS)
+		config_posix_timers = false;
+}
+
+static inline bool check_skip(int clockid)
+{
+	if (config_posix_timers)
+		return false;
+
+	switch (clockid) {
+	/* Only these clocks are supported without CONFIG_POSIX_TIMERS. */
+	case CLOCK_BOOTTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_REALTIME:
+		return false;
+	default:
+		ksft_test_result_skip("Posix Clocks & timers are not supported\n");
+		return true;
+	}
+
+	return false;
+}
+
+static inline int unshare_timens(void)
+{
+	if (unshare(CLONE_NEWTIME)) {
+		if (errno == EPERM)
+			ksft_exit_skip("need to run as root\n");
+		return pr_perror("Can't unshare() timens");
+	}
+	return 0;
+}
+
+static inline int _settime(clockid_t clk_id, time_t offset)
+{
+	int fd, len;
+	char buf[4096];
+
+	if (clk_id == CLOCK_MONOTONIC_COARSE || clk_id == CLOCK_MONOTONIC_RAW)
+		clk_id = CLOCK_MONOTONIC;
+
+	len = snprintf(buf, sizeof(buf), "%d %ld 0", clk_id, offset);
+
+	fd = open("/proc/self/timens_offsets", O_WRONLY);
+	if (fd < 0)
+		return pr_perror("/proc/self/timens_offsets");
+
+	if (write(fd, buf, len) != len)
+		return pr_perror("/proc/self/timens_offsets");
+
+	close(fd);
+
+	return 0;
+}
+
+static inline int _gettime(clockid_t clk_id, struct timespec *res, bool raw_syscall)
+{
+	int err;
+
+	if (!raw_syscall) {
+		if (clock_gettime(clk_id, res)) {
+			pr_perror("clock_gettime(%d)", (int)clk_id);
+			return -1;
+		}
+		return 0;
+	}
+
+	err = syscall(SYS_clock_gettime, clk_id, res);
+	if (err)
+		pr_perror("syscall(SYS_clock_gettime(%d))", (int)clk_id);
+
+	return err;
+}
+
+static inline void nscheck(void)
+{
+	if (access("/proc/self/ns/time", F_OK) < 0)
+		ksft_exit_skip("Time namespaces are not supported\n");
+}
+
+#endif
diff --git a/tools/testing/selftests/timens/timer.c b/tools/testing/selftests/timens/timer.c
new file mode 100644
index 000000000000..0cca7aafc4bd
--- /dev/null
+++ b/tools/testing/selftests/timens/timer.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <time.h>
+
+#include "log.h"
+#include "timens.h"
+
+int run_test(int clockid, struct timespec now)
+{
+	struct itimerspec new_value;
+	long long elapsed;
+	timer_t fd;
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		struct sigevent sevp = {.sigev_notify = SIGEV_NONE};
+		int flags = 0;
+
+		new_value.it_value.tv_sec = 3600;
+		new_value.it_value.tv_nsec = 0;
+		new_value.it_interval.tv_sec = 1;
+		new_value.it_interval.tv_nsec = 0;
+
+		if (i == 1) {
+			new_value.it_value.tv_sec += now.tv_sec;
+			new_value.it_value.tv_nsec += now.tv_nsec;
+		}
+
+		if (timer_create(clockid, &sevp, &fd) == -1) {
+			if (errno == ENOSYS) {
+				ksft_test_result_skip("Posix Clocks & timers are supported\n");
+				return 0;
+			}
+			return pr_perror("timerfd_create");
+		}
+
+		if (i == 1)
+			flags |= TIMER_ABSTIME;
+		if (timer_settime(fd, flags, &new_value, NULL) == -1)
+			return pr_perror("timerfd_settime");
+
+		if (timer_gettime(fd, &new_value) == -1)
+			return pr_perror("timerfd_gettime");
+
+		elapsed = new_value.it_value.tv_sec;
+		if (abs(elapsed - 3600) > 60) {
+			ksft_test_result_fail("clockid: %d elapsed: %lld\n",
+					      clockid, elapsed);
+			return 1;
+		}
+	}
+
+	ksft_test_result_pass("clockid=%d\n", clockid);
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int ret, status, len, fd;
+	char buf[4096];
+	pid_t pid;
+	struct timespec btime_now, mtime_now;
+
+	nscheck();
+
+	ksft_set_plan(3);
+
+	clock_gettime(CLOCK_MONOTONIC, &mtime_now);
+	clock_gettime(CLOCK_BOOTTIME, &btime_now);
+
+	if (unshare_timens())
+		return 1;
+
+	len = snprintf(buf, sizeof(buf), "%d %d 0\n%d %d 0",
+			CLOCK_MONOTONIC, 70 * 24 * 3600,
+			CLOCK_BOOTTIME, 9 * 24 * 3600);
+	fd = open("/proc/self/timens_offsets", O_WRONLY);
+	if (fd < 0)
+		return pr_perror("/proc/self/timens_offsets");
+
+	if (write(fd, buf, len) != len)
+		return pr_perror("/proc/self/timens_offsets");
+
+	close(fd);
+	mtime_now.tv_sec += 70 * 24 * 3600;
+	btime_now.tv_sec += 9 * 24 * 3600;
+
+	pid = fork();
+	if (pid < 0)
+		return pr_perror("Unable to fork");
+	if (pid == 0) {
+		ret = 0;
+		ret |= run_test(CLOCK_BOOTTIME, btime_now);
+		ret |= run_test(CLOCK_MONOTONIC, mtime_now);
+		ret |= run_test(CLOCK_BOOTTIME_ALARM, btime_now);
+
+		if (ret)
+			ksft_exit_fail();
+		ksft_exit_pass();
+		return ret;
+	}
+
+	if (waitpid(pid, &status, 0) != pid)
+		return pr_perror("Unable to wait the child process");
+
+	if (WIFEXITED(status))
+		return WEXITSTATUS(status);
+
+	return 1;
+}
diff --git a/tools/testing/selftests/timens/timerfd.c b/tools/testing/selftests/timens/timerfd.c
new file mode 100644
index 000000000000..eff1ec5ff215
--- /dev/null
+++ b/tools/testing/selftests/timens/timerfd.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <sys/timerfd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+
+#include "log.h"
+#include "timens.h"
+
+static int tclock_gettime(clock_t clockid, struct timespec *now)
+{
+	if (clockid == CLOCK_BOOTTIME_ALARM)
+		clockid = CLOCK_BOOTTIME;
+	return clock_gettime(clockid, now);
+}
+
+int run_test(int clockid, struct timespec now)
+{
+	struct itimerspec new_value;
+	long long elapsed;
+	int fd, i;
+
+	if (tclock_gettime(clockid, &now))
+		return pr_perror("clock_gettime(%d)", clockid);
+
+	for (i = 0; i < 2; i++) {
+		int flags = 0;
+
+		new_value.it_value.tv_sec = 3600;
+		new_value.it_value.tv_nsec = 0;
+		new_value.it_interval.tv_sec = 1;
+		new_value.it_interval.tv_nsec = 0;
+
+		if (i == 1) {
+			new_value.it_value.tv_sec += now.tv_sec;
+			new_value.it_value.tv_nsec += now.tv_nsec;
+		}
+
+		fd = timerfd_create(clockid, 0);
+		if (fd == -1)
+			return pr_perror("timerfd_create(%d)", clockid);
+
+		if (i == 1)
+			flags |= TFD_TIMER_ABSTIME;
+
+		if (timerfd_settime(fd, flags, &new_value, NULL))
+			return pr_perror("timerfd_settime(%d)", clockid);
+
+		if (timerfd_gettime(fd, &new_value))
+			return pr_perror("timerfd_gettime(%d)", clockid);
+
+		elapsed = new_value.it_value.tv_sec;
+		if (abs(elapsed - 3600) > 60) {
+			ksft_test_result_fail("clockid: %d elapsed: %lld\n",
+					      clockid, elapsed);
+			return 1;
+		}
+
+		close(fd);
+	}
+
+	ksft_test_result_pass("clockid=%d\n", clockid);
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int ret, status, len, fd;
+	char buf[4096];
+	pid_t pid;
+	struct timespec btime_now, mtime_now;
+
+	nscheck();
+
+	ksft_set_plan(3);
+
+	clock_gettime(CLOCK_MONOTONIC, &mtime_now);
+	clock_gettime(CLOCK_BOOTTIME, &btime_now);
+
+	if (unshare_timens())
+		return 1;
+
+	len = snprintf(buf, sizeof(buf), "%d %d 0\n%d %d 0",
+			CLOCK_MONOTONIC, 70 * 24 * 3600,
+			CLOCK_BOOTTIME, 9 * 24 * 3600);
+	fd = open("/proc/self/timens_offsets", O_WRONLY);
+	if (fd < 0)
+		return pr_perror("/proc/self/timens_offsets");
+
+	if (write(fd, buf, len) != len)
+		return pr_perror("/proc/self/timens_offsets");
+
+	close(fd);
+	mtime_now.tv_sec += 70 * 24 * 3600;
+	btime_now.tv_sec += 9 * 24 * 3600;
+
+	pid = fork();
+	if (pid < 0)
+		return pr_perror("Unable to fork");
+	if (pid == 0) {
+		ret = 0;
+		ret |= run_test(CLOCK_BOOTTIME, btime_now);
+		ret |= run_test(CLOCK_MONOTONIC, mtime_now);
+		ret |= run_test(CLOCK_BOOTTIME_ALARM, btime_now);
+
+		if (ret)
+			ksft_exit_fail();
+		ksft_exit_pass();
+		return ret;
+	}
+
+	if (waitpid(pid, &status, 0) != pid)
+		return pr_perror("Unable to wait the child process");
+
+	if (WIFEXITED(status))
+		return WEXITSTATUS(status);
+
+	return 1;
+}

Re: [GIT pull] timers/core for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-core-2020-01-27

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/e279160f491392f1345f6eb4b0eeec5a6a2ecdd7

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] core/debugobjects for

[Thomas Gleixner]

Linus,

please pull the latest core/debugobjects branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-debugobjects-2020-01-28

up to:  35fd7a637c42: debugobjects: Fix various data races


A single commit for debug objects which fixes a pile of potential data
races detected by KCSAN.


Thanks,

	tglx

------------------>
Marco Elver (1):
      debugobjects: Fix various data races


 lib/debugobjects.c | 46 +++++++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 21 deletions(-)

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 61261195f5b6..48054dbf1b51 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -132,14 +132,18 @@ static void fill_pool(void)
 	struct debug_obj *obj;
 	unsigned long flags;
 
-	if (likely(obj_pool_free >= debug_objects_pool_min_level))
+	if (likely(READ_ONCE(obj_pool_free) >= debug_objects_pool_min_level))
 		return;
 
 	/*
 	 * Reuse objs from the global free list; they will be reinitialized
 	 * when allocating.
+	 *
+	 * Both obj_nr_tofree and obj_pool_free are checked locklessly; the
+	 * READ_ONCE()s pair with the WRITE_ONCE()s in pool_lock critical
+	 * sections.
 	 */
-	while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) {
+	while (READ_ONCE(obj_nr_tofree) && (READ_ONCE(obj_pool_free) < obj_pool_min_free)) {
 		raw_spin_lock_irqsave(&pool_lock, flags);
 		/*
 		 * Recheck with the lock held as the worker thread might have
@@ -148,9 +152,9 @@ static void fill_pool(void)
 		while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) {
 			obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
 			hlist_del(&obj->node);
-			obj_nr_tofree--;
+			WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1);
 			hlist_add_head(&obj->node, &obj_pool);
-			obj_pool_free++;
+			WRITE_ONCE(obj_pool_free, obj_pool_free + 1);
 		}
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
@@ -158,7 +162,7 @@ static void fill_pool(void)
 	if (unlikely(!obj_cache))
 		return;
 
-	while (obj_pool_free < debug_objects_pool_min_level) {
+	while (READ_ONCE(obj_pool_free) < debug_objects_pool_min_level) {
 		struct debug_obj *new[ODEBUG_BATCH_SIZE];
 		int cnt;
 
@@ -174,7 +178,7 @@ static void fill_pool(void)
 		while (cnt) {
 			hlist_add_head(&new[--cnt]->node, &obj_pool);
 			debug_objects_allocated++;
-			obj_pool_free++;
+			WRITE_ONCE(obj_pool_free, obj_pool_free + 1);
 		}
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
@@ -236,7 +240,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 	obj = __alloc_object(&obj_pool);
 	if (obj) {
 		obj_pool_used++;
-		obj_pool_free--;
+		WRITE_ONCE(obj_pool_free, obj_pool_free - 1);
 
 		/*
 		 * Looking ahead, allocate one batch of debug objects and
@@ -255,7 +259,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 					       &percpu_pool->free_objs);
 				percpu_pool->obj_free++;
 				obj_pool_used++;
-				obj_pool_free--;
+				WRITE_ONCE(obj_pool_free, obj_pool_free - 1);
 			}
 		}
 
@@ -309,8 +313,8 @@ static void free_obj_work(struct work_struct *work)
 		obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
 		hlist_del(&obj->node);
 		hlist_add_head(&obj->node, &obj_pool);
-		obj_pool_free++;
-		obj_nr_tofree--;
+		WRITE_ONCE(obj_pool_free, obj_pool_free + 1);
+		WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1);
 	}
 	raw_spin_unlock_irqrestore(&pool_lock, flags);
 	return;
@@ -324,7 +328,7 @@ static void free_obj_work(struct work_struct *work)
 	if (obj_nr_tofree) {
 		hlist_move_list(&obj_to_free, &tofree);
 		debug_objects_freed += obj_nr_tofree;
-		obj_nr_tofree = 0;
+		WRITE_ONCE(obj_nr_tofree, 0);
 	}
 	raw_spin_unlock_irqrestore(&pool_lock, flags);
 
@@ -375,10 +379,10 @@ static void __free_object(struct debug_obj *obj)
 	obj_pool_used--;
 
 	if (work) {
-		obj_nr_tofree++;
+		WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1);
 		hlist_add_head(&obj->node, &obj_to_free);
 		if (lookahead_count) {
-			obj_nr_tofree += lookahead_count;
+			WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + lookahead_count);
 			obj_pool_used -= lookahead_count;
 			while (lookahead_count) {
 				hlist_add_head(&objs[--lookahead_count]->node,
@@ -396,15 +400,15 @@ static void __free_object(struct debug_obj *obj)
 			for (i = 0; i < ODEBUG_BATCH_SIZE; i++) {
 				obj = __alloc_object(&obj_pool);
 				hlist_add_head(&obj->node, &obj_to_free);
-				obj_pool_free--;
-				obj_nr_tofree++;
+				WRITE_ONCE(obj_pool_free, obj_pool_free - 1);
+				WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1);
 			}
 		}
 	} else {
-		obj_pool_free++;
+		WRITE_ONCE(obj_pool_free, obj_pool_free + 1);
 		hlist_add_head(&obj->node, &obj_pool);
 		if (lookahead_count) {
-			obj_pool_free += lookahead_count;
+			WRITE_ONCE(obj_pool_free, obj_pool_free + lookahead_count);
 			obj_pool_used -= lookahead_count;
 			while (lookahead_count) {
 				hlist_add_head(&objs[--lookahead_count]->node,
@@ -423,7 +427,7 @@ static void __free_object(struct debug_obj *obj)
 static void free_object(struct debug_obj *obj)
 {
 	__free_object(obj);
-	if (!obj_freeing && obj_nr_tofree) {
+	if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) {
 		WRITE_ONCE(obj_freeing, true);
 		schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY);
 	}
@@ -982,7 +986,7 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 		debug_objects_maxchecked = objs_checked;
 
 	/* Schedule work to actually kmem_cache_free() objects */
-	if (!obj_freeing && obj_nr_tofree) {
+	if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) {
 		WRITE_ONCE(obj_freeing, true);
 		schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY);
 	}
@@ -1008,12 +1012,12 @@ static int debug_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "max_checked   :%d\n", debug_objects_maxchecked);
 	seq_printf(m, "warnings      :%d\n", debug_objects_warnings);
 	seq_printf(m, "fixups        :%d\n", debug_objects_fixups);
-	seq_printf(m, "pool_free     :%d\n", obj_pool_free + obj_percpu_free);
+	seq_printf(m, "pool_free     :%d\n", READ_ONCE(obj_pool_free) + obj_percpu_free);
 	seq_printf(m, "pool_pcp_free :%d\n", obj_percpu_free);
 	seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free);
 	seq_printf(m, "pool_used     :%d\n", obj_pool_used - obj_percpu_free);
 	seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used);
-	seq_printf(m, "on_free_list  :%d\n", obj_nr_tofree);
+	seq_printf(m, "on_free_list  :%d\n", READ_ONCE(obj_nr_tofree));
 	seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated);
 	seq_printf(m, "objs_freed    :%d\n", debug_objects_freed);
 	return 0;

Re: [GIT pull] core/debugobjects for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-debugobjects-2020-01-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/534b0a8b677443c0aa8c4c71ff7887f08a2b9b41

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] irq/core for

[Thomas Gleixner]

Linus,

please pull the latest irq/core branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-core-2020-01-28

up to:  43ee74487bd2: Merge tag 'irqchip-5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core


The interrupt departement provides:

 - A mechanism to shield isolated tasks from managed interrupts:

   The affinity of managed interrupts is completely controlled by the
   kernel and user space has no influence on them. The reason is that
   the automatically assigned affinity correlates to the multi-queue
   CPU handling of block devices.

   If the generated affinity mask spaws both housekeeping and isolated CPUs
   the interrupt could be routed to an isolated CPU which would then be
   disturbed by I/O submitted by a housekeeping CPU.

   The new mechamism ensures that as long as one housekeeping CPU is online
   in the assigned affinity mask the interrupt is routed to a housekeeping
   CPU.

   If there is no online housekeeping CPU in the affinity mask, then the
   interrupt is routed to an isolated CPU to keep the device queue intact,
   but unless the isolated CPU submits I/O by itself these interrupts are
   not raised.

 - A small addon to the device tree irqdomain core code to avoid
   duplication in irq chip drivers

 - Conversion of the SiFive PLIC to hierarchical domains

 - The usual pile of new irq chip drivers: SiFive GPIO, Aspeed SCI, NXP
   INTMUX, Meson A1 GPIO

 - The first cut of support for the new ARM GICv4.1

 - The usual pile of fixes and improvements in core and driver code

Thanks,

	tglx

------------------>
Eddie James (2):
      dt-bindings: interrupt-controller: Add Aspeed SCU interrupt controller
      irqchip: Add Aspeed SCU interrupt controller

Hyunki Koo (1):
      irqchip: Define EXYNOS_IRQ_COMBINER

Joakim Zhang (2):
      dt-bindings: interrupt-controller: Add binding for NXP INTMUX interrupt multiplexer
      irqchip: Add NXP INTMUX interrupt multiplexer support

John Garry (1):
      irqchip/mbigen: Set driver .suppress_bind_attrs to avoid remove problems

Jules Irenge (2):
      genirq: Add missing __releases() sparse annotation
      genirq: Add missing __must_hold() sparse annotation

Kevin Hao (1):
      irqdomain: Fix a memory leak in irq_domain_push_irq()

Luca Ceresoli (1):
      genirq: Show irq name in non-oneshot error message

Marc Zyngier (14):
      irqchip/gic-v3-its: Fix get_vlpi_map() breakage with doorbells
      irqchip/gic-v3: Detect GICv4.1 supporting RVPEID
      irqchip/gic-v3: Add GICv4.1 VPEID size discovery
      irqchip/gic-v4.1: VPE table (aka GICR_VPROPBASER) allocation
      irqchip/gic-v4.1: Implement the v4.1 flavour of VMAPP
      irqchip/gic-v4.1: Don't use the VPE proxy if RVPEID is set
      irqchip/gic-v4.1: Implement the v4.1 flavour of VMOVP
      irqchip/gic-v4.1: Plumb skeletal VPE irqchip
      irqchip/gic-v4.1: Add mask/unmask doorbell callbacks
      irqchip/gic-v4.1: Add VPE residency callback
      irqchip/gic-v4.1: Add VPE eviction callback
      irqchip/gic-v4.1: Add VPE INVALL callback
      irqchip/gic-v4.1: Suppress per-VLPI doorbell
      irqchip/gic-v4.1: Allow direct invalidation of VLPIs

Ming Lei (1):
      genirq, sched/isolation: Isolate from handling managed interrupts

Qianggui Song (3):
      dt-bindings: interrupt-controller: New binding for Meson-A1 SoCs
      irqchip/meson-gpio: Rework meson irqchip driver to support meson-A1 SoCs
      irqchip/meson-gpio: Add support for meson a1 SoCs

Yash Shah (5):
      genirq: Introduce irq_domain_translate_onecell
      irqchip/nvic: Use irq_domain_translate_onecell instead of custom func
      irqchip/sifive-plic: Support irq domain hierarchy
      gpio/sifive: Add DT documentation for SiFive GPIO
      gpio/sifive: Add GPIO driver for SiFive SoCs


 Documentation/admin-guide/kernel-parameters.txt    |  26 +-
 .../devicetree/bindings/gpio/sifive,gpio.yaml      |  68 ++
 .../amlogic,meson-gpio-intc.txt                    |   1 +
 .../interrupt-controller/aspeed,ast2xxx-scu-ic.txt |  23 +
 .../bindings/interrupt-controller/fsl,intmux.yaml  |  68 ++
 MAINTAINERS                                        |   8 +
 arch/arm/include/asm/arch_gicv3.h                  |   2 +
 arch/arm/mach-exynos/Kconfig                       |   1 +
 arch/arm64/include/asm/arch_gicv3.h                |   1 +
 drivers/gpio/Kconfig                               |   9 +
 drivers/gpio/Makefile                              |   1 +
 drivers/gpio/gpio-sifive.c                         | 252 ++++++++
 drivers/irqchip/Kconfig                            |  14 +
 drivers/irqchip/Makefile                           |   5 +-
 drivers/irqchip/irq-aspeed-scu-ic.c                | 239 +++++++
 drivers/irqchip/irq-gic-v3-its.c                   | 698 +++++++++++++++++++--
 drivers/irqchip/irq-gic-v3.c                       |  24 +-
 drivers/irqchip/irq-imx-intmux.c                   | 309 +++++++++
 drivers/irqchip/irq-mbigen.c                       |   1 +
 drivers/irqchip/irq-meson-gpio.c                   | 137 +++-
 drivers/irqchip/irq-nvic.c                         |  15 +-
 drivers/irqchip/irq-sifive-plic.c                  |  30 +-
 .../interrupt-controller/aspeed-scu-ic.h           |  23 +
 include/linux/irqchip/arm-gic-v3.h                 |  59 +-
 include/linux/irqchip/arm-gic-v4.h                 |  23 +-
 include/linux/irqdomain.h                          |   5 +
 include/linux/sched/isolation.h                    |   1 +
 kernel/irq/cpuhotplug.c                            |  21 +-
 kernel/irq/irqdesc.c                               |   1 +
 kernel/irq/irqdomain.c                             |  18 +
 kernel/irq/manage.c                                |  45 +-
 kernel/irq/spurious.c                              |   1 +
 kernel/sched/isolation.c                           |   6 +
 33 files changed, 2024 insertions(+), 111 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/gpio/sifive,gpio.yaml
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2xxx-scu-ic.txt
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/fsl,intmux.yaml
 create mode 100644 drivers/gpio/gpio-sifive.c
 create mode 100644 drivers/irqchip/irq-aspeed-scu-ic.c
 create mode 100644 drivers/irqchip/irq-imx-intmux.c
 create mode 100644 include/dt-bindings/interrupt-controller/aspeed-scu-ic.h

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ade4e6ec23e0..765e4274ba71 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1933,9 +1933,31 @@
 			  <cpu number> begins at 0 and the maximum value is
 			  "number of CPUs in system - 1".
 
-			The format of <cpu-list> is described above.
-
+			managed_irq
+
+			  Isolate from being targeted by managed interrupts
+			  which have an interrupt mask containing isolated
+			  CPUs. The affinity of managed interrupts is
+			  handled by the kernel and cannot be changed via
+			  the /proc/irq/* interfaces.
+
+			  This isolation is best effort and only effective
+			  if the automatically assigned interrupt mask of a
+			  device queue contains isolated and housekeeping
+			  CPUs. If housekeeping CPUs are online then such
+			  interrupts are directed to the housekeeping CPU
+			  so that IO submitted on the housekeeping CPU
+			  cannot disturb the isolated CPU.
+
+			  If a queue's affinity mask contains only isolated
+			  CPUs then this parameter has no effect on the
+			  interrupt routing decision, though interrupts are
+			  only delivered when tasks running on those
+			  isolated CPUs submit IO. IO submitted on
+			  housekeeping CPUs has no influence on those
+			  queues.
 
+			The format of <cpu-list> is described above.
 
 	iucv=		[HW,NET]
 
diff --git a/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml
new file mode 100644
index 000000000000..418e8381e07c
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/gpio/sifive,gpio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SiFive GPIO controller
+
+maintainers:
+  - Yash Shah <yash.shah@sifive.com>
+  - Paul Walmsley <paul.walmsley@sifive.com>
+
+properties:
+  compatible:
+    items:
+      - const: sifive,fu540-c000-gpio
+      - const: sifive,gpio0
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description:
+      interrupt mapping one per GPIO. Maximum 16 GPIOs.
+    minItems: 1
+    maxItems: 16
+
+  interrupt-controller: true
+
+  "#interrupt-cells":
+    const: 2
+
+  clocks:
+    maxItems: 1
+
+  "#gpio-cells":
+    const: 2
+
+  gpio-controller: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-controller
+  - "#interrupt-cells"
+  - clocks
+  - "#gpio-cells"
+  - gpio-controller
+
+additionalProperties: false
+
+examples:
+  - |
+      #include <dt-bindings/clock/sifive-fu540-prci.h>
+      gpio@10060000 {
+        compatible = "sifive,fu540-c000-gpio", "sifive,gpio0";
+        interrupt-parent = <&plic>;
+        interrupts = <7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22>;
+        reg = <0x0 0x10060000 0x0 0x1000>;
+        clocks = <&tlclk PRCI_CLK_TLCLK>;
+        gpio-controller;
+        #gpio-cells = <2>;
+        interrupt-controller;
+        #interrupt-cells = <2>;
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index 684bb1cd75ec..23b18b92c558 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -17,6 +17,7 @@ Required properties:
     "amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
     "amlogic,meson-g12a-gpio-intc" for G12A SoCs (S905D2, S905X2, S905Y2)
     "amlogic,meson-sm1-gpio-intc" for SM1 SoCs (S905D3, S905X3, S905Y3)
+    "amlogic,meson-a1-gpio-intc" for A1 SoCs (A113L)
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2xxx-scu-ic.txt b/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2xxx-scu-ic.txt
new file mode 100644
index 000000000000..251ed44171db
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2xxx-scu-ic.txt
@@ -0,0 +1,23 @@
+Aspeed AST25XX and AST26XX SCU Interrupt Controller
+
+Required Properties:
+ - #interrupt-cells		: must be 1
+ - compatible			: must be "aspeed,ast2500-scu-ic",
+				  "aspeed,ast2600-scu-ic0" or
+				  "aspeed,ast2600-scu-ic1"
+ - interrupts			: interrupt from the parent controller
+ - interrupt-controller		: indicates that the controller receives and
+				  fires new interrupts for child busses
+
+Example:
+
+    syscon@1e6e2000 {
+        ranges = <0 0x1e6e2000 0x1a8>;
+
+        scu_ic: interrupt-controller@18 {
+            #interrupt-cells = <1>;
+            compatible = "aspeed,ast2500-scu-ic";
+            interrupts = <21>;
+            interrupt-controller;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/fsl,intmux.yaml b/Documentation/devicetree/bindings/interrupt-controller/fsl,intmux.yaml
new file mode 100644
index 000000000000..43c6effbb5bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/fsl,intmux.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/fsl,intmux.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale INTMUX interrupt multiplexer
+
+maintainers:
+  - Joakim Zhang <qiangqing.zhang@nxp.com>
+
+properties:
+  compatible:
+    const: fsl,imx-intmux
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 8
+    description: |
+      Should contain the parent interrupt lines (up to 8) used to multiplex
+      the input interrupts.
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 2
+    description: |
+      The 1st cell is hw interrupt number, the 2nd cell is channel index.
+
+  clocks:
+    description: ipg clock.
+
+  clock-names:
+    const: ipg
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-controller
+  - '#interrupt-cells'
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    interrupt-controller@37400000 {
+        compatible = "fsl,imx-intmux";
+        reg = <0x37400000 0x1000>;
+        interrupts = <0 16 4>,
+                     <0 17 4>,
+                     <0 18 4>,
+                     <0 19 4>,
+                     <0 20 4>,
+                     <0 21 4>,
+                     <0 22 4>,
+                     <0 23 4>;
+        interrupt-controller;
+        interrupt-parent = <&gic>;
+        #interrupt-cells = <2>;
+        clocks = <&clk>;
+        clock-names = "ipg";
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index 8982c6e013b3..4535780c81e8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2694,6 +2694,14 @@ S:	Maintained
 F:	drivers/pinctrl/aspeed/
 F:	Documentation/devicetree/bindings/pinctrl/aspeed,*
 
+ASPEED SCU INTERRUPT CONTROLLER DRIVER
+M:	Eddie James <eajames@linux.ibm.com>
+L:	linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2xxx-scu-ic.txt
+F:	drivers/irqchip/irq-aspeed-scu-ic.c
+F:	include/dt-bindings/interrupt-controller/aspeed-scu-ic.h
+
 ASPEED VIDEO ENGINE DRIVER
 M:	Eddie James <eajames@linux.ibm.com>
 L:	linux-media@vger.kernel.org
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index fa50bb04f580..b5752f0e8936 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 #include <asm/cp15.h>
@@ -327,6 +328,7 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr)
 /*
  * GITS_VPROPBASER - hi and lo bits may be accessed independently.
  */
+#define gits_read_vpropbaser(c)		__gic_readq_nonatomic(c)
 #define gits_write_vpropbaser(v, c)	__gic_writeq_nonatomic(v, c)
 
 /*
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 4ef56571145b..6e7f10c8098a 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -12,6 +12,7 @@ menuconfig ARCH_EXYNOS
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_GIC
+	select EXYNOS_IRQ_COMBINER
 	select COMMON_CLK_SAMSUNG
 	select EXYNOS_ASV
 	select EXYNOS_CHIPID
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 89e4c8b79349..4750fc8030c3 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -141,6 +141,7 @@ static inline u32 gic_read_rpr(void)
 #define gicr_read_pendbaser(c)		readq_relaxed(c)
 
 #define gits_write_vpropbaser(v, c)	writeq_relaxed(v, c)
+#define gits_read_vpropbaser(c)		readq_relaxed(c)
 
 #define gits_write_vpendbaser(v, c)	writeq_relaxed(v, c)
 #define gits_read_vpendbaser(c)		readq_relaxed(c)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 6ab25fe1c423..809dd54a2e82 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -479,6 +479,15 @@ config GPIO_SAMA5D2_PIOBU
 	  The difference from regular GPIOs is that they
 	  maintain their value during backup/self-refresh.
 
+config GPIO_SIFIVE
+	bool "SiFive GPIO support"
+	depends on OF_GPIO && IRQ_DOMAIN_HIERARCHY
+	select GPIO_GENERIC
+	select GPIOLIB_IRQCHIP
+	select REGMAP_MMIO
+	help
+	  Say yes here to support the GPIO device on SiFive SoCs.
+
 config GPIO_SIOX
 	tristate "SIOX GPIO support"
 	depends on SIOX
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 34eb8b2b12dd..11eeeebbde0d 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -124,6 +124,7 @@ obj-$(CONFIG_ARCH_SA1100)		+= gpio-sa1100.o
 obj-$(CONFIG_GPIO_SAMA5D2_PIOBU)	+= gpio-sama5d2-piobu.o
 obj-$(CONFIG_GPIO_SCH311X)		+= gpio-sch311x.o
 obj-$(CONFIG_GPIO_SCH)			+= gpio-sch.o
+obj-$(CONFIG_GPIO_SIFIVE)		+= gpio-sifive.o
 obj-$(CONFIG_GPIO_SIOX)			+= gpio-siox.o
 obj-$(CONFIG_GPIO_SODAVILLE)		+= gpio-sodaville.o
 obj-$(CONFIG_GPIO_SPEAR_SPICS)		+= gpio-spear-spics.o
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
new file mode 100644
index 000000000000..147a1bd04515
--- /dev/null
+++ b/drivers/gpio/gpio-sifive.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/of_irq.h>
+#include <linux/gpio/driver.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/regmap.h>
+
+#define SIFIVE_GPIO_INPUT_VAL	0x00
+#define SIFIVE_GPIO_INPUT_EN	0x04
+#define SIFIVE_GPIO_OUTPUT_EN	0x08
+#define SIFIVE_GPIO_OUTPUT_VAL	0x0C
+#define SIFIVE_GPIO_RISE_IE	0x18
+#define SIFIVE_GPIO_RISE_IP	0x1C
+#define SIFIVE_GPIO_FALL_IE	0x20
+#define SIFIVE_GPIO_FALL_IP	0x24
+#define SIFIVE_GPIO_HIGH_IE	0x28
+#define SIFIVE_GPIO_HIGH_IP	0x2C
+#define SIFIVE_GPIO_LOW_IE	0x30
+#define SIFIVE_GPIO_LOW_IP	0x34
+#define SIFIVE_GPIO_OUTPUT_XOR	0x40
+
+#define SIFIVE_GPIO_MAX		32
+#define SIFIVE_GPIO_IRQ_OFFSET	7
+
+struct sifive_gpio {
+	void __iomem		*base;
+	struct gpio_chip	gc;
+	struct regmap		*regs;
+	u32			irq_state;
+	unsigned int		trigger[SIFIVE_GPIO_MAX];
+	unsigned int		irq_parent[SIFIVE_GPIO_MAX];
+};
+
+static void sifive_gpio_set_ie(struct sifive_gpio *chip, unsigned int offset)
+{
+	unsigned long flags;
+	unsigned int trigger;
+
+	spin_lock_irqsave(&chip->gc.bgpio_lock, flags);
+	trigger = (chip->irq_state & BIT(offset)) ? chip->trigger[offset] : 0;
+	regmap_update_bits(chip->regs, SIFIVE_GPIO_RISE_IE, BIT(offset),
+			   (trigger & IRQ_TYPE_EDGE_RISING) ? BIT(offset) : 0);
+	regmap_update_bits(chip->regs, SIFIVE_GPIO_FALL_IE, BIT(offset),
+			   (trigger & IRQ_TYPE_EDGE_FALLING) ? BIT(offset) : 0);
+	regmap_update_bits(chip->regs, SIFIVE_GPIO_HIGH_IE, BIT(offset),
+			   (trigger & IRQ_TYPE_LEVEL_HIGH) ? BIT(offset) : 0);
+	regmap_update_bits(chip->regs, SIFIVE_GPIO_LOW_IE, BIT(offset),
+			   (trigger & IRQ_TYPE_LEVEL_LOW) ? BIT(offset) : 0);
+	spin_unlock_irqrestore(&chip->gc.bgpio_lock, flags);
+}
+
+static int sifive_gpio_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct sifive_gpio *chip = gpiochip_get_data(gc);
+	int offset = irqd_to_hwirq(d);
+
+	if (offset < 0 || offset >= gc->ngpio)
+		return -EINVAL;
+
+	chip->trigger[offset] = trigger;
+	sifive_gpio_set_ie(chip, offset);
+	return 0;
+}
+
+static void sifive_gpio_irq_enable(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct sifive_gpio *chip = gpiochip_get_data(gc);
+	int offset = irqd_to_hwirq(d) % SIFIVE_GPIO_MAX;
+	u32 bit = BIT(offset);
+	unsigned long flags;
+
+	irq_chip_enable_parent(d);
+
+	/* Switch to input */
+	gc->direction_input(gc, offset);
+
+	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	/* Clear any sticky pending interrupts */
+	regmap_write(chip->regs, SIFIVE_GPIO_RISE_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_FALL_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_HIGH_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_LOW_IP, bit);
+	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+
+	/* Enable interrupts */
+	assign_bit(offset, (unsigned long *)&chip->irq_state, 1);
+	sifive_gpio_set_ie(chip, offset);
+}
+
+static void sifive_gpio_irq_disable(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct sifive_gpio *chip = gpiochip_get_data(gc);
+	int offset = irqd_to_hwirq(d) % SIFIVE_GPIO_MAX;
+
+	assign_bit(offset, (unsigned long *)&chip->irq_state, 0);
+	sifive_gpio_set_ie(chip, offset);
+	irq_chip_disable_parent(d);
+}
+
+static void sifive_gpio_irq_eoi(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct sifive_gpio *chip = gpiochip_get_data(gc);
+	int offset = irqd_to_hwirq(d) % SIFIVE_GPIO_MAX;
+	u32 bit = BIT(offset);
+	unsigned long flags;
+
+	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	/* Clear all pending interrupts */
+	regmap_write(chip->regs, SIFIVE_GPIO_RISE_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_FALL_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_HIGH_IP, bit);
+	regmap_write(chip->regs, SIFIVE_GPIO_LOW_IP, bit);
+	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+
+	irq_chip_eoi_parent(d);
+}
+
+static struct irq_chip sifive_gpio_irqchip = {
+	.name		= "sifive-gpio",
+	.irq_set_type	= sifive_gpio_irq_set_type,
+	.irq_mask	= irq_chip_mask_parent,
+	.irq_unmask	= irq_chip_unmask_parent,
+	.irq_enable	= sifive_gpio_irq_enable,
+	.irq_disable	= sifive_gpio_irq_disable,
+	.irq_eoi	= sifive_gpio_irq_eoi,
+};
+
+static int sifive_gpio_child_to_parent_hwirq(struct gpio_chip *gc,
+					     unsigned int child,
+					     unsigned int child_type,
+					     unsigned int *parent,
+					     unsigned int *parent_type)
+{
+	*parent_type = IRQ_TYPE_NONE;
+	*parent = child + SIFIVE_GPIO_IRQ_OFFSET;
+	return 0;
+}
+
+static const struct regmap_config sifive_gpio_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+	.disable_locking = true,
+};
+
+static int sifive_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *irq_parent;
+	struct irq_domain *parent;
+	struct gpio_irq_chip *girq;
+	struct sifive_gpio *chip;
+	int ret, ngpio;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(chip->base)) {
+		dev_err(dev, "failed to allocate device memory\n");
+		return PTR_ERR(chip->base);
+	}
+
+	chip->regs = devm_regmap_init_mmio(dev, chip->base,
+					   &sifive_gpio_regmap_config);
+	if (IS_ERR(chip->regs))
+		return PTR_ERR(chip->regs);
+
+	ngpio = of_irq_count(node);
+	if (ngpio >= SIFIVE_GPIO_MAX) {
+		dev_err(dev, "Too many GPIO interrupts (max=%d)\n",
+			SIFIVE_GPIO_MAX);
+		return -ENXIO;
+	}
+
+	irq_parent = of_irq_find_parent(node);
+	if (!irq_parent) {
+		dev_err(dev, "no IRQ parent node\n");
+		return -ENODEV;
+	}
+	parent = irq_find_host(irq_parent);
+	if (!parent) {
+		dev_err(dev, "no IRQ parent domain\n");
+		return -ENODEV;
+	}
+
+	ret = bgpio_init(&chip->gc, dev, 4,
+			 chip->base + SIFIVE_GPIO_INPUT_VAL,
+			 chip->base + SIFIVE_GPIO_OUTPUT_VAL,
+			 NULL,
+			 chip->base + SIFIVE_GPIO_OUTPUT_EN,
+			 chip->base + SIFIVE_GPIO_INPUT_EN,
+			 0);
+	if (ret) {
+		dev_err(dev, "unable to init generic GPIO\n");
+		return ret;
+	}
+
+	/* Disable all GPIO interrupts before enabling parent interrupts */
+	regmap_write(chip->regs, SIFIVE_GPIO_RISE_IE, 0);
+	regmap_write(chip->regs, SIFIVE_GPIO_FALL_IE, 0);
+	regmap_write(chip->regs, SIFIVE_GPIO_HIGH_IE, 0);
+	regmap_write(chip->regs, SIFIVE_GPIO_LOW_IE, 0);
+	chip->irq_state = 0;
+
+	chip->gc.base = -1;
+	chip->gc.ngpio = ngpio;
+	chip->gc.label = dev_name(dev);
+	chip->gc.parent = dev;
+	chip->gc.owner = THIS_MODULE;
+	girq = &chip->gc.irq;
+	girq->chip = &sifive_gpio_irqchip;
+	girq->fwnode = of_node_to_fwnode(node);
+	girq->parent_domain = parent;
+	girq->child_to_parent_hwirq = sifive_gpio_child_to_parent_hwirq;
+	girq->handler = handle_bad_irq;
+	girq->default_type = IRQ_TYPE_NONE;
+
+	platform_set_drvdata(pdev, chip);
+	return gpiochip_add_data(&chip->gc, chip);
+}
+
+static const struct of_device_id sifive_gpio_match[] = {
+	{ .compatible = "sifive,gpio0" },
+	{ .compatible = "sifive,fu540-c000-gpio" },
+	{ },
+};
+
+static struct platform_driver sifive_gpio_driver = {
+	.probe		= sifive_gpio_probe,
+	.driver = {
+		.name	= "sifive_gpio",
+		.of_match_table = of_match_ptr(sifive_gpio_match),
+	},
+};
+builtin_platform_driver(sifive_gpio_driver)
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 697e6a8ccaae..1006c694d9fb 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -457,6 +457,12 @@ config IMX_IRQSTEER
 	help
 	  Support for the i.MX IRQSTEER interrupt multiplexer/remapper.
 
+config IMX_INTMUX
+	def_bool y if ARCH_MXC
+	select IRQ_DOMAIN
+	help
+	  Support for the i.MX INTMUX interrupt multiplexer.
+
 config LS1X_IRQ
 	bool "Loongson-1 Interrupt Controller"
 	depends on MACH_LOONGSON32
@@ -490,6 +496,7 @@ config TI_SCI_INTA_IRQCHIP
 config SIFIVE_PLIC
 	bool "SiFive Platform-Level Interrupt Controller"
 	depends on RISCV
+	select IRQ_DOMAIN_HIERARCHY
 	help
 	   This enables support for the PLIC chip found in SiFive (and
 	   potentially other) RISC-V systems.  The PLIC controls devices
@@ -499,4 +506,11 @@ config SIFIVE_PLIC
 
 	   If you don't know what to do here, say Y.
 
+config EXYNOS_IRQ_COMBINER
+	bool "Samsung Exynos IRQ combiner support" if COMPILE_TEST
+	depends on (ARCH_EXYNOS && ARM) || COMPILE_TEST
+	help
+	  Say yes here to add support for the IRQ combiner devices embedded
+	  in Samsung Exynos chips.
+
 endmenu
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index e806dda690ea..eae0d78cbf22 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2836.o
 obj-$(CONFIG_DAVINCI_AINTC)		+= irq-davinci-aintc.o
 obj-$(CONFIG_DAVINCI_CP_INTC)		+= irq-davinci-cp-intc.o
-obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
+obj-$(CONFIG_EXYNOS_IRQ_COMBINER)	+= exynos-combiner.o
 obj-$(CONFIG_FARADAY_FTINTC010)		+= irq-ftintc010.o
 obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_LPC32XX)		+= irq-lpc32xx.o
@@ -87,7 +87,7 @@ obj-$(CONFIG_MVEBU_SEI)			+= irq-mvebu-sei.o
 obj-$(CONFIG_LS_EXTIRQ)			+= irq-ls-extirq.o
 obj-$(CONFIG_LS_SCFG_MSI)		+= irq-ls-scfg-msi.o
 obj-$(CONFIG_EZNPS_GIC)			+= irq-eznps.o
-obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o
+obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o irq-aspeed-scu-ic.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
 obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
 obj-$(CONFIG_IRQ_UNIPHIER_AIDET)	+= irq-uniphier-aidet.o
@@ -100,6 +100,7 @@ obj-$(CONFIG_CSKY_MPINTC)		+= irq-csky-mpintc.o
 obj-$(CONFIG_CSKY_APB_INTC)		+= irq-csky-apb-intc.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
+obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o
 obj-$(CONFIG_MADERA_IRQ)		+= irq-madera.o
 obj-$(CONFIG_LS1X_IRQ)			+= irq-ls1x.o
 obj-$(CONFIG_TI_SCI_INTR_IRQCHIP)	+= irq-ti-sci-intr.o
diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c
new file mode 100644
index 000000000000..c90a3346b985
--- /dev/null
+++ b/drivers/irqchip/irq-aspeed-scu-ic.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Aspeed AST24XX, AST25XX, and AST26XX SCU Interrupt Controller
+ * Copyright 2019 IBM Corporation
+ *
+ * Eddie James <eajames@linux.ibm.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+
+#define ASPEED_SCU_IC_REG		0x018
+#define ASPEED_SCU_IC_SHIFT		0
+#define ASPEED_SCU_IC_ENABLE		GENMASK(6, ASPEED_SCU_IC_SHIFT)
+#define ASPEED_SCU_IC_NUM_IRQS		7
+#define ASPEED_SCU_IC_STATUS_SHIFT	16
+
+#define ASPEED_AST2600_SCU_IC0_REG	0x560
+#define ASPEED_AST2600_SCU_IC0_SHIFT	0
+#define ASPEED_AST2600_SCU_IC0_ENABLE	\
+	GENMASK(5, ASPEED_AST2600_SCU_IC0_SHIFT)
+#define ASPEED_AST2600_SCU_IC0_NUM_IRQS	6
+
+#define ASPEED_AST2600_SCU_IC1_REG	0x570
+#define ASPEED_AST2600_SCU_IC1_SHIFT	4
+#define ASPEED_AST2600_SCU_IC1_ENABLE	\
+	GENMASK(5, ASPEED_AST2600_SCU_IC1_SHIFT)
+#define ASPEED_AST2600_SCU_IC1_NUM_IRQS	2
+
+struct aspeed_scu_ic {
+	unsigned long irq_enable;
+	unsigned long irq_shift;
+	unsigned int num_irqs;
+	unsigned int reg;
+	struct regmap *scu;
+	struct irq_domain *irq_domain;
+};
+
+static void aspeed_scu_ic_irq_handler(struct irq_desc *desc)
+{
+	unsigned int irq;
+	unsigned int sts;
+	unsigned long bit;
+	unsigned long enabled;
+	unsigned long max;
+	unsigned long status;
+	struct aspeed_scu_ic *scu_ic = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int mask = scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT;
+
+	chained_irq_enter(chip, desc);
+
+	/*
+	 * The SCU IC has just one register to control its operation and read
+	 * status. The interrupt enable bits occupy the lower 16 bits of the
+	 * register, while the interrupt status bits occupy the upper 16 bits.
+	 * The status bit for a given interrupt is always 16 bits shifted from
+	 * the enable bit for the same interrupt.
+	 * Therefore, perform the IRQ operations in the enable bit space by
+	 * shifting the status down to get the mapping and then back up to
+	 * clear the bit.
+	 */
+	regmap_read(scu_ic->scu, scu_ic->reg, &sts);
+	enabled = sts & scu_ic->irq_enable;
+	status = (sts >> ASPEED_SCU_IC_STATUS_SHIFT) & enabled;
+
+	bit = scu_ic->irq_shift;
+	max = scu_ic->num_irqs + bit;
+
+	for_each_set_bit_from(bit, &status, max) {
+		irq = irq_find_mapping(scu_ic->irq_domain,
+				       bit - scu_ic->irq_shift);
+		generic_handle_irq(irq);
+
+		regmap_update_bits(scu_ic->scu, scu_ic->reg, mask,
+				   BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void aspeed_scu_ic_irq_mask(struct irq_data *data)
+{
+	struct aspeed_scu_ic *scu_ic = irq_data_get_irq_chip_data(data);
+	unsigned int mask = BIT(data->hwirq + scu_ic->irq_shift) |
+		(scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT);
+
+	/*
+	 * Status bits are cleared by writing 1. In order to prevent the mask
+	 * operation from clearing the status bits, they should be under the
+	 * mask and written with 0.
+	 */
+	regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, 0);
+}
+
+static void aspeed_scu_ic_irq_unmask(struct irq_data *data)
+{
+	struct aspeed_scu_ic *scu_ic = irq_data_get_irq_chip_data(data);
+	unsigned int bit = BIT(data->hwirq + scu_ic->irq_shift);
+	unsigned int mask = bit |
+		(scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT);
+
+	/*
+	 * Status bits are cleared by writing 1. In order to prevent the unmask
+	 * operation from clearing the status bits, they should be under the
+	 * mask and written with 0.
+	 */
+	regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, bit);
+}
+
+static int aspeed_scu_ic_irq_set_affinity(struct irq_data *data,
+					  const struct cpumask *dest,
+					  bool force)
+{
+	return -EINVAL;
+}
+
+static struct irq_chip aspeed_scu_ic_chip = {
+	.name			= "aspeed-scu-ic",
+	.irq_mask		= aspeed_scu_ic_irq_mask,
+	.irq_unmask		= aspeed_scu_ic_irq_unmask,
+	.irq_set_affinity	= aspeed_scu_ic_irq_set_affinity,
+};
+
+static int aspeed_scu_ic_map(struct irq_domain *domain, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &aspeed_scu_ic_chip, handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops aspeed_scu_ic_domain_ops = {
+	.map = aspeed_scu_ic_map,
+};
+
+static int aspeed_scu_ic_of_init_common(struct aspeed_scu_ic *scu_ic,
+					struct device_node *node)
+{
+	int irq;
+	int rc = 0;
+
+	if (!node->parent) {
+		rc = -ENODEV;
+		goto err;
+	}
+
+	scu_ic->scu = syscon_node_to_regmap(node->parent);
+	if (IS_ERR(scu_ic->scu)) {
+		rc = PTR_ERR(scu_ic->scu);
+		goto err;
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq < 0) {
+		rc = irq;
+		goto err;
+	}
+
+	scu_ic->irq_domain = irq_domain_add_linear(node, scu_ic->num_irqs,
+						   &aspeed_scu_ic_domain_ops,
+						   scu_ic);
+	if (!scu_ic->irq_domain) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	irq_set_chained_handler_and_data(irq, aspeed_scu_ic_irq_handler,
+					 scu_ic);
+
+	return 0;
+
+err:
+	kfree(scu_ic);
+
+	return rc;
+}
+
+static int __init aspeed_scu_ic_of_init(struct device_node *node,
+					struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_SCU_IC_ENABLE;
+	scu_ic->irq_shift = ASPEED_SCU_IC_SHIFT;
+	scu_ic->num_irqs = ASPEED_SCU_IC_NUM_IRQS;
+	scu_ic->reg = ASPEED_SCU_IC_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+static int __init aspeed_ast2600_scu_ic0_of_init(struct device_node *node,
+						 struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_AST2600_SCU_IC0_ENABLE;
+	scu_ic->irq_shift = ASPEED_AST2600_SCU_IC0_SHIFT;
+	scu_ic->num_irqs = ASPEED_AST2600_SCU_IC0_NUM_IRQS;
+	scu_ic->reg = ASPEED_AST2600_SCU_IC0_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+static int __init aspeed_ast2600_scu_ic1_of_init(struct device_node *node,
+						 struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_AST2600_SCU_IC1_ENABLE;
+	scu_ic->irq_shift = ASPEED_AST2600_SCU_IC1_SHIFT;
+	scu_ic->num_irqs = ASPEED_AST2600_SCU_IC1_NUM_IRQS;
+	scu_ic->reg = ASPEED_AST2600_SCU_IC1_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+IRQCHIP_DECLARE(ast2400_scu_ic, "aspeed,ast2400-scu-ic", aspeed_scu_ic_of_init);
+IRQCHIP_DECLARE(ast2500_scu_ic, "aspeed,ast2500-scu-ic", aspeed_scu_ic_of_init);
+IRQCHIP_DECLARE(ast2600_scu_ic0, "aspeed,ast2600-scu-ic0",
+		aspeed_ast2600_scu_ic0_of_init);
+IRQCHIP_DECLARE(ast2600_scu_ic1, "aspeed,ast2600-scu-ic1",
+		aspeed_ast2600_scu_ic1_of_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index e05673bcd52b..f71758632f8d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -106,6 +106,7 @@ struct its_node {
 	u64			typer;
 	u64			cbaser_save;
 	u32			ctlr_save;
+	u32			mpidr;
 	struct list_head	its_device_list;
 	u64			flags;
 	unsigned long		list_nr;
@@ -116,12 +117,22 @@ struct its_node {
 };
 
 #define is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
+#define is_v4_1(its)		(!!((its)->typer & GITS_TYPER_VMAPP))
 #define device_ids(its)		(FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
 
 #define ITS_ITT_ALIGN		SZ_256
 
 /* The maximum number of VPEID bits supported by VLPI commands */
-#define ITS_MAX_VPEID_BITS	(16)
+#define ITS_MAX_VPEID_BITS						\
+	({								\
+		int nvpeid = 16;					\
+		if (gic_rdists->has_rvpeid &&				\
+		    gic_rdists->gicd_typer2 & GICD_TYPER2_VIL)		\
+			nvpeid = 1 + (gic_rdists->gicd_typer2 &		\
+				      GICD_TYPER2_VID);			\
+									\
+		nvpeid;							\
+	})
 #define ITS_MAX_VPEID		(1 << (ITS_MAX_VPEID_BITS))
 
 /* Convert page order to size in bytes */
@@ -216,11 +227,27 @@ static struct its_vlpi_map *dev_event_to_vlpi_map(struct its_device *its_dev,
 	return &its_dev->event_map.vlpi_maps[event];
 }
 
-static struct its_collection *irq_to_col(struct irq_data *d)
+static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
+{
+	if (irqd_is_forwarded_to_vcpu(d)) {
+		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+		u32 event = its_get_event_id(d);
+
+		return dev_event_to_vlpi_map(its_dev, event);
+	}
+
+	return NULL;
+}
+
+static int irq_to_cpuid(struct irq_data *d)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	struct its_vlpi_map *map = get_vlpi_map(d);
 
-	return dev_event_to_col(its_dev, its_get_event_id(d));
+	if (map)
+		return map->vpe->col_idx;
+
+	return its_dev->event_map.col_map[its_get_event_id(d)];
 }
 
 static struct its_collection *valid_col(struct its_collection *col)
@@ -322,6 +349,10 @@ struct its_cmd_desc {
 			u16 seq_num;
 			u16 its_list;
 		} its_vmovp_cmd;
+
+		struct {
+			struct its_vpe *vpe;
+		} its_invdb_cmd;
 	};
 };
 
@@ -438,6 +469,38 @@ static void its_encode_vpt_size(struct its_cmd_block *cmd, u8 vpt_size)
 	its_mask_encode(&cmd->raw_cmd[3], vpt_size, 4, 0);
 }
 
+static void its_encode_vconf_addr(struct its_cmd_block *cmd, u64 vconf_pa)
+{
+	its_mask_encode(&cmd->raw_cmd[0], vconf_pa >> 16, 51, 16);
+}
+
+static void its_encode_alloc(struct its_cmd_block *cmd, bool alloc)
+{
+	its_mask_encode(&cmd->raw_cmd[0], alloc, 8, 8);
+}
+
+static void its_encode_ptz(struct its_cmd_block *cmd, bool ptz)
+{
+	its_mask_encode(&cmd->raw_cmd[0], ptz, 9, 9);
+}
+
+static void its_encode_vmapp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_vmovp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[3], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_db(struct its_cmd_block *cmd, bool db)
+{
+	its_mask_encode(&cmd->raw_cmd[2], db, 63, 63);
+}
+
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 {
 	/* Let's fixup BE commands */
@@ -621,19 +684,45 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
 					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
-	unsigned long vpt_addr;
+	unsigned long vpt_addr, vconf_addr;
 	u64 target;
-
-	vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
-	target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+	bool alloc;
 
 	its_encode_cmd(cmd, GITS_CMD_VMAPP);
 	its_encode_vpeid(cmd, desc->its_vmapp_cmd.vpe->vpe_id);
 	its_encode_valid(cmd, desc->its_vmapp_cmd.valid);
+
+	if (!desc->its_vmapp_cmd.valid) {
+		if (is_v4_1(its)) {
+			alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
+			its_encode_alloc(cmd, alloc);
+		}
+
+		goto out;
+	}
+
+	vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
+	target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+
 	its_encode_target(cmd, target);
 	its_encode_vpt_addr(cmd, vpt_addr);
 	its_encode_vpt_size(cmd, LPI_NRBITS - 1);
 
+	if (!is_v4_1(its))
+		goto out;
+
+	vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page));
+
+	alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count);
+
+	its_encode_alloc(cmd, alloc);
+
+	/* We can only signal PTZ when alloc==1. Why do we have two bits? */
+	its_encode_ptz(cmd, alloc);
+	its_encode_vconf_addr(cmd, vconf_addr);
+	its_encode_vmapp_default_db(cmd, desc->its_vmapp_cmd.vpe->vpe_db_lpi);
+
+out:
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmapp_cmd.vpe);
@@ -645,7 +734,7 @@ static struct its_vpe *its_build_vmapti_cmd(struct its_node *its,
 {
 	u32 db;
 
-	if (desc->its_vmapti_cmd.db_enabled)
+	if (!is_v4_1(its) && desc->its_vmapti_cmd.db_enabled)
 		db = desc->its_vmapti_cmd.vpe->vpe_db_lpi;
 	else
 		db = 1023;
@@ -668,7 +757,7 @@ static struct its_vpe *its_build_vmovi_cmd(struct its_node *its,
 {
 	u32 db;
 
-	if (desc->its_vmovi_cmd.db_enabled)
+	if (!is_v4_1(its) && desc->its_vmovi_cmd.db_enabled)
 		db = desc->its_vmovi_cmd.vpe->vpe_db_lpi;
 	else
 		db = 1023;
@@ -698,6 +787,11 @@ static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
 	its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id);
 	its_encode_target(cmd, target);
 
+	if (is_v4_1(its)) {
+		its_encode_db(cmd, true);
+		its_encode_vmovp_default_db(cmd, desc->its_vmovp_cmd.vpe->vpe_db_lpi);
+	}
+
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmovp_cmd.vpe);
@@ -757,6 +851,21 @@ static struct its_vpe *its_build_vclear_cmd(struct its_node *its,
 	return valid_vpe(its, map->vpe);
 }
 
+static struct its_vpe *its_build_invdb_cmd(struct its_node *its,
+					   struct its_cmd_block *cmd,
+					   struct its_cmd_desc *desc)
+{
+	if (WARN_ON(!is_v4_1(its)))
+		return NULL;
+
+	its_encode_cmd(cmd, GITS_CMD_INVDB);
+	its_encode_vpeid(cmd, desc->its_invdb_cmd.vpe->vpe_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, desc->its_invdb_cmd.vpe);
+}
+
 static u64 its_cmd_ptr_to_offset(struct its_node *its,
 				 struct its_cmd_block *ptr)
 {
@@ -1165,20 +1274,17 @@ static void its_send_vclear(struct its_device *dev, u32 event_id)
 	its_send_single_vcommand(dev->its, its_build_vclear_cmd, &desc);
 }
 
-/*
- * irqchip functions - assumes MSI, mostly.
- */
-static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
+static void its_send_invdb(struct its_node *its, struct its_vpe *vpe)
 {
-	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	u32 event = its_get_event_id(d);
-
-	if (!irqd_is_forwarded_to_vcpu(d))
-		return NULL;
+	struct its_cmd_desc desc;
 
-	return dev_event_to_vlpi_map(its_dev, event);
+	desc.its_invdb_cmd.vpe = vpe;
+	its_send_single_vcommand(its, its_build_invdb_cmd, &desc);
 }
 
+/*
+ * irqchip functions - assumes MSI, mostly.
+ */
 static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 {
 	struct its_vlpi_map *map = get_vlpi_map(d);
@@ -1221,13 +1327,25 @@ static void wait_for_syncr(void __iomem *rdbase)
 
 static void direct_lpi_inv(struct irq_data *d)
 {
-	struct its_collection *col;
+	struct its_vlpi_map *map = get_vlpi_map(d);
 	void __iomem *rdbase;
+	u64 val;
+
+	if (map) {
+		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+
+		WARN_ON(!is_v4_1(its_dev->its));
+
+		val  = GICR_INVLPIR_V;
+		val |= FIELD_PREP(GICR_INVLPIR_VPEID, map->vpe->vpe_id);
+		val |= FIELD_PREP(GICR_INVLPIR_INTID, map->vintid);
+	} else {
+		val = d->hwirq;
+	}
 
 	/* Target the redistributor this LPI is currently routed to */
-	col = irq_to_col(d);
-	rdbase = per_cpu_ptr(gic_rdists->rdist, col->col_id)->rd_base;
-	gic_write_lpir(d->hwirq, rdbase + GICR_INVLPIR);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, irq_to_cpuid(d))->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVLPIR);
 
 	wait_for_syncr(rdbase);
 }
@@ -1237,7 +1355,8 @@ static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 
 	lpi_write_config(d, clr, set);
-	if (gic_rdists->has_direct_lpi && !irqd_is_forwarded_to_vcpu(d))
+	if (gic_rdists->has_direct_lpi &&
+	    (is_v4_1(its_dev->its) || !irqd_is_forwarded_to_vcpu(d)))
 		direct_lpi_inv(d);
 	else if (!irqd_is_forwarded_to_vcpu(d))
 		its_send_inv(its_dev, its_get_event_id(d));
@@ -1251,6 +1370,13 @@ static void its_vlpi_set_doorbell(struct irq_data *d, bool enable)
 	u32 event = its_get_event_id(d);
 	struct its_vlpi_map *map;
 
+	/*
+	 * GICv4.1 does away with the per-LPI nonsense, nothing to do
+	 * here.
+	 */
+	if (is_v4_1(its_dev->its))
+		return;
+
 	map = dev_event_to_vlpi_map(its_dev, event);
 
 	if (map->db_enabled == enable)
@@ -2090,6 +2216,65 @@ static bool its_parse_indirect_baser(struct its_node *its,
 	return indirect;
 }
 
+static u32 compute_common_aff(u64 val)
+{
+	u32 aff, clpiaff;
+
+	aff = FIELD_GET(GICR_TYPER_AFFINITY, val);
+	clpiaff = FIELD_GET(GICR_TYPER_COMMON_LPI_AFF, val);
+
+	return aff & ~(GENMASK(31, 0) >> (clpiaff * 8));
+}
+
+static u32 compute_its_aff(struct its_node *its)
+{
+	u64 val;
+	u32 svpet;
+
+	/*
+	 * Reencode the ITS SVPET and MPIDR as a GICR_TYPER, and compute
+	 * the resulting affinity. We then use that to see if this match
+	 * our own affinity.
+	 */
+	svpet = FIELD_GET(GITS_TYPER_SVPET, its->typer);
+	val  = FIELD_PREP(GICR_TYPER_COMMON_LPI_AFF, svpet);
+	val |= FIELD_PREP(GICR_TYPER_AFFINITY, its->mpidr);
+	return compute_common_aff(val);
+}
+
+static struct its_node *find_sibling_its(struct its_node *cur_its)
+{
+	struct its_node *its;
+	u32 aff;
+
+	if (!FIELD_GET(GITS_TYPER_SVPET, cur_its->typer))
+		return NULL;
+
+	aff = compute_its_aff(cur_its);
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		u64 baser;
+
+		if (!is_v4_1(its) || its == cur_its)
+			continue;
+
+		if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+			continue;
+
+		if (aff != compute_its_aff(its))
+			continue;
+
+		/* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+		baser = its->tables[2].val;
+		if (!(baser & GITS_BASER_VALID))
+			continue;
+
+		return its;
+	}
+
+	return NULL;
+}
+
 static void its_free_tables(struct its_node *its)
 {
 	int i;
@@ -2132,6 +2317,17 @@ static int its_alloc_tables(struct its_node *its)
 			break;
 
 		case GITS_BASER_TYPE_VCPU:
+			if (is_v4_1(its)) {
+				struct its_node *sibling;
+
+				WARN_ON(i != 2);
+				if ((sibling = find_sibling_its(its))) {
+					*baser = sibling->tables[2];
+					its_write_baser(its, baser, baser->val);
+					continue;
+				}
+			}
+
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
 							    ITS_MAX_VPEID_BITS);
@@ -2153,6 +2349,220 @@ static int its_alloc_tables(struct its_node *its)
 	return 0;
 }
 
+static u64 inherit_vpe_l1_table_from_its(void)
+{
+	struct its_node *its;
+	u64 val;
+	u32 aff;
+
+	val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+	aff = compute_common_aff(val);
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		u64 baser, addr;
+
+		if (!is_v4_1(its))
+			continue;
+
+		if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+			continue;
+
+		if (aff != compute_its_aff(its))
+			continue;
+
+		/* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+		baser = its->tables[2].val;
+		if (!(baser & GITS_BASER_VALID))
+			continue;
+
+		/* We have a winner! */
+		val  = GICR_VPROPBASER_4_1_VALID;
+		if (baser & GITS_BASER_INDIRECT)
+			val |= GICR_VPROPBASER_4_1_INDIRECT;
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE,
+				  FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser));
+		switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) {
+		case GIC_PAGE_SIZE_64K:
+			addr = GITS_BASER_ADDR_48_to_52(baser);
+			break;
+		default:
+			addr = baser & GENMASK_ULL(47, 12);
+			break;
+		}
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
+		val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+				  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+		val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+				  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
+
+		return val;
+	}
+
+	return 0;
+}
+
+static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
+{
+	u32 aff;
+	u64 val;
+	int cpu;
+
+	val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+	aff = compute_common_aff(val);
+
+	for_each_possible_cpu(cpu) {
+		void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+		u32 tmp;
+
+		if (!base || cpu == smp_processor_id())
+			continue;
+
+		val = gic_read_typer(base + GICR_TYPER);
+		tmp = compute_common_aff(val);
+		if (tmp != aff)
+			continue;
+
+		/*
+		 * At this point, we have a victim. This particular CPU
+		 * has already booted, and has an affinity that matches
+		 * ours wrt CommonLPIAff. Let's use its own VPROPBASER.
+		 * Make sure we don't write the Z bit in that case.
+		 */
+		val = gits_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+		val &= ~GICR_VPROPBASER_4_1_Z;
+
+		*mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
+
+		return val;
+	}
+
+	return 0;
+}
+
+static int allocate_vpe_l1_table(void)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val, gpsz, npg, pa;
+	unsigned int psz = SZ_64K;
+	unsigned int np, epp, esz;
+	struct page *page;
+
+	if (!gic_rdists->has_rvpeid)
+		return 0;
+
+	/*
+	 * if VPENDBASER.Valid is set, disable any previously programmed
+	 * VPE by setting PendingLast while clearing Valid. This has the
+	 * effect of making sure no doorbell will be generated and we can
+	 * then safely clear VPROPBASER.Valid.
+	 */
+	if (gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid)
+		gits_write_vpendbaser(GICR_VPENDBASER_PendingLast,
+				      vlpi_base + GICR_VPENDBASER);
+
+	/*
+	 * If we can inherit the configuration from another RD, let's do
+	 * so. Otherwise, we have to go through the allocation process. We
+	 * assume that all RDs have the exact same requirements, as
+	 * nothing will work otherwise.
+	 */
+	val = inherit_vpe_l1_table_from_rd(&gic_data_rdist()->vpe_table_mask);
+	if (val & GICR_VPROPBASER_4_1_VALID)
+		goto out;
+
+	gic_data_rdist()->vpe_table_mask = kzalloc(sizeof(cpumask_t), GFP_KERNEL);
+	if (!gic_data_rdist()->vpe_table_mask)
+		return -ENOMEM;
+
+	val = inherit_vpe_l1_table_from_its();
+	if (val & GICR_VPROPBASER_4_1_VALID)
+		goto out;
+
+	/* First probe the page size */
+	val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K);
+	gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+	val = gits_read_vpropbaser(vlpi_base + GICR_VPROPBASER);
+	gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+	esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val);
+
+	switch (gpsz) {
+	default:
+		gpsz = GIC_PAGE_SIZE_4K;
+		/* fall through */
+	case GIC_PAGE_SIZE_4K:
+		psz = SZ_4K;
+		break;
+	case GIC_PAGE_SIZE_16K:
+		psz = SZ_16K;
+		break;
+	case GIC_PAGE_SIZE_64K:
+		psz = SZ_64K;
+		break;
+	}
+
+	/*
+	 * Start populating the register from scratch, including RO fields
+	 * (which we want to print in debug cases...)
+	 */
+	val = 0;
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, gpsz);
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ENTRY_SIZE, esz);
+
+	/* How many entries per GIC page? */
+	esz++;
+	epp = psz / (esz * SZ_8);
+
+	/*
+	 * If we need more than just a single L1 page, flag the table
+	 * as indirect and compute the number of required L1 pages.
+	 */
+	if (epp < ITS_MAX_VPEID) {
+		int nl2;
+
+		val |= GICR_VPROPBASER_4_1_INDIRECT;
+
+		/* Number of L2 pages required to cover the VPEID space */
+		nl2 = DIV_ROUND_UP(ITS_MAX_VPEID, epp);
+
+		/* Number of L1 pages to point to the L2 pages */
+		npg = DIV_ROUND_UP(nl2 * SZ_8, psz);
+	} else {
+		npg = 1;
+	}
+
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg);
+
+	/* Right, that's the number of CPU pages we need for L1 */
+	np = DIV_ROUND_UP(npg * psz, PAGE_SIZE);
+
+	pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
+		 np, npg, psz, epp, esz);
+	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(np * PAGE_SIZE));
+	if (!page)
+		return -ENOMEM;
+
+	gic_data_rdist()->vpe_l1_page = page;
+	pa = virt_to_phys(page_address(page));
+	WARN_ON(!IS_ALIGNED(pa, psz));
+
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
+	val |= GICR_VPROPBASER_RaWb;
+	val |= GICR_VPROPBASER_InnerShareable;
+	val |= GICR_VPROPBASER_4_1_Z;
+	val |= GICR_VPROPBASER_4_1_VALID;
+
+out:
+	gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+	cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask);
+
+	pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n",
+		 smp_processor_id(), val,
+		 cpumask_pr_args(gic_data_rdist()->vpe_table_mask));
+
+	return 0;
+}
+
 static int its_alloc_collections(struct its_node *its)
 {
 	int i;
@@ -2244,7 +2654,7 @@ static int __init allocate_lpi_tables(void)
 	return 0;
 }
 
-static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
+static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
 {
 	u32 count = 1000000;	/* 1s! */
 	bool clean;
@@ -2252,6 +2662,8 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
 
 	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
 	val &= ~GICR_VPENDBASER_Valid;
+	val &= ~clr;
+	val |= set;
 	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
 
 	do {
@@ -2264,6 +2676,11 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
 		}
 	} while (!clean && count);
 
+	if (unlikely(val & GICR_VPENDBASER_Dirty)) {
+		pr_err_ratelimited("ITS virtual pending table not cleaning\n");
+		val |= GICR_VPENDBASER_PendingLast;
+	}
+
 	return val;
 }
 
@@ -2352,7 +2769,7 @@ static void its_cpu_init_lpis(void)
 	val |= GICR_CTLR_ENABLE_LPIS;
 	writel_relaxed(val, rbase + GICR_CTLR);
 
-	if (gic_rdists->has_vlpis) {
+	if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
 		void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 
 		/*
@@ -2372,10 +2789,20 @@ static void its_cpu_init_lpis(void)
 		 * ancient programming gets left in and has possibility of
 		 * corrupting memory.
 		 */
-		val = its_clear_vpend_valid(vlpi_base);
+		val = its_clear_vpend_valid(vlpi_base, 0, 0);
 		WARN_ON(val & GICR_VPENDBASER_Dirty);
 	}
 
+	if (allocate_vpe_l1_table()) {
+		/*
+		 * If the allocation has failed, we're in massive trouble.
+		 * Disable direct injection, and pray that no VM was
+		 * already running...
+		 */
+		gic_rdists->has_rvpeid = false;
+		gic_rdists->has_vlpis = false;
+	}
+
 	/* Make sure the GIC has seen the above */
 	dsb(sy);
 out:
@@ -2859,7 +3286,7 @@ static const struct irq_domain_ops its_domain_ops = {
 /*
  * This is insane.
  *
- * If a GICv4 doesn't implement Direct LPIs (which is extremely
+ * If a GICv4.0 doesn't implement Direct LPIs (which is extremely
  * likely), the only way to perform an invalidate is to use a fake
  * device to issue an INV command, implying that the LPI has first
  * been mapped to some event on that device. Since this is not exactly
@@ -2867,9 +3294,20 @@ static const struct irq_domain_ops its_domain_ops = {
  * only issue an UNMAP if we're short on available slots.
  *
  * Broken by design(tm).
+ *
+ * GICv4.1, on the other hand, mandates that we're able to invalidate
+ * by writing to a MMIO register. It doesn't implement the whole of
+ * DirectLPI, but that's good enough. And most of the time, we don't
+ * even have to invalidate anything, as the redistributor can be told
+ * whether to generate a doorbell or not (we thus leave it enabled,
+ * always).
  */
 static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already unmapped? */
 	if (vpe->vpe_proxy_event == -1)
 		return;
@@ -2892,6 +3330,10 @@ static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
 
 static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (!gic_rdists->has_direct_lpi) {
 		unsigned long flags;
 
@@ -2903,6 +3345,10 @@ static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
 
 static void its_vpe_db_proxy_map_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already mapped? */
 	if (vpe->vpe_proxy_event != -1)
 		return;
@@ -2925,6 +3371,10 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to)
 	unsigned long flags;
 	struct its_collection *target_col;
 
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (gic_rdists->has_direct_lpi) {
 		void __iomem *rdbase;
 
@@ -2951,7 +3401,7 @@ static int its_vpe_set_affinity(struct irq_data *d,
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	int cpu = cpumask_first(mask_val);
+	int from, cpu = cpumask_first(mask_val);
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
@@ -2959,14 +3409,24 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * into the proxy device, we need to move the doorbell
 	 * interrupt to its new location.
 	 */
-	if (vpe->col_idx != cpu) {
-		int from = vpe->col_idx;
+	if (vpe->col_idx == cpu)
+		goto out;
 
-		vpe->col_idx = cpu;
-		its_send_vmovp(vpe);
-		its_vpe_db_proxy_move(vpe, from, cpu);
-	}
+	from = vpe->col_idx;
+	vpe->col_idx = cpu;
 
+	/*
+	 * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
+	 * is sharing its VPE table with the current one.
+	 */
+	if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
+	    cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+		goto out;
+
+	its_send_vmovp(vpe);
+	its_vpe_db_proxy_move(vpe, from, cpu);
+
+out:
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;
@@ -3009,16 +3469,10 @@ static void its_vpe_deschedule(struct its_vpe *vpe)
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 	u64 val;
 
-	val = its_clear_vpend_valid(vlpi_base);
+	val = its_clear_vpend_valid(vlpi_base, 0, 0);
 
-	if (unlikely(val & GICR_VPENDBASER_Dirty)) {
-		pr_err_ratelimited("ITS virtual pending table not cleaning\n");
-		vpe->idai = false;
-		vpe->pending_last = true;
-	} else {
-		vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
-		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
-	}
+	vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
+	vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
 }
 
 static void its_vpe_invall(struct its_vpe *vpe)
@@ -3151,6 +3605,139 @@ static struct irq_chip its_vpe_irq_chip = {
 	.irq_set_vcpu_affinity	= its_vpe_set_vcpu_affinity,
 };
 
+static struct its_node *find_4_1_its(void)
+{
+	static struct its_node *its = NULL;
+
+	if (!its) {
+		list_for_each_entry(its, &its_nodes, entry) {
+			if (is_v4_1(its))
+				return its;
+		}
+
+		/* Oops? */
+		its = NULL;
+	}
+
+	return its;
+}
+
+static void its_vpe_4_1_send_inv(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
+
+	/*
+	 * GICv4.1 wants doorbells to be invalidated using the
+	 * INVDB command in order to be broadcast to all RDs. Send
+	 * it to the first valid ITS, and let the HW do its magic.
+	 */
+	its = find_4_1_its();
+	if (its)
+		its_send_invdb(its, vpe);
+}
+
+static void its_vpe_4_1_mask_irq(struct irq_data *d)
+{
+	lpi_write_config(d->parent_data, LPI_PROP_ENABLED, 0);
+	its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_unmask_irq(struct irq_data *d)
+{
+	lpi_write_config(d->parent_data, 0, LPI_PROP_ENABLED);
+	its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_schedule(struct its_vpe *vpe,
+				 struct its_cmd_info *info)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val = 0;
+
+	/* Schedule the VPE */
+	val |= GICR_VPENDBASER_Valid;
+	val |= info->g0en ? GICR_VPENDBASER_4_1_VGRP0EN : 0;
+	val |= info->g1en ? GICR_VPENDBASER_4_1_VGRP1EN : 0;
+	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
+
+	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+}
+
+static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
+				   struct its_cmd_info *info)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	if (info->req_db) {
+		/*
+		 * vPE is going to block: make the vPE non-resident with
+		 * PendingLast clear and DB set. The GIC guarantees that if
+		 * we read-back PendingLast clear, then a doorbell will be
+		 * delivered when an interrupt comes.
+		 */
+		val = its_clear_vpend_valid(vlpi_base,
+					    GICR_VPENDBASER_PendingLast,
+					    GICR_VPENDBASER_4_1_DB);
+		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+	} else {
+		/*
+		 * We're not blocking, so just make the vPE non-resident
+		 * with PendingLast set, indicating that we'll be back.
+		 */
+		val = its_clear_vpend_valid(vlpi_base,
+					    0,
+					    GICR_VPENDBASER_PendingLast);
+		vpe->pending_last = true;
+	}
+}
+
+static void its_vpe_4_1_invall(struct its_vpe *vpe)
+{
+	void __iomem *rdbase;
+	u64 val;
+
+	val  = GICR_INVALLR_V;
+	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
+
+	/* Target the redistributor this vPE is currently known on */
+	rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVALLR);
+}
+
+static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_info *info = vcpu_info;
+
+	switch (info->cmd_type) {
+	case SCHEDULE_VPE:
+		its_vpe_4_1_schedule(vpe, info);
+		return 0;
+
+	case DESCHEDULE_VPE:
+		its_vpe_4_1_deschedule(vpe, info);
+		return 0;
+
+	case INVALL_VPE:
+		its_vpe_4_1_invall(vpe);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct irq_chip its_vpe_4_1_irq_chip = {
+	.name			= "GICv4.1-vpe",
+	.irq_mask		= its_vpe_4_1_mask_irq,
+	.irq_unmask		= its_vpe_4_1_unmask_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= its_vpe_set_affinity,
+	.irq_set_vcpu_affinity	= its_vpe_4_1_set_vcpu_affinity,
+};
+
 static int its_vpe_id_alloc(void)
 {
 	return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL);
@@ -3186,7 +3773,10 @@ static int its_vpe_init(struct its_vpe *vpe)
 
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
-	vpe->vpe_proxy_event = -1;
+	if (gic_rdists->has_rvpeid)
+		atomic_set(&vpe->vmapp_count, 0);
+	else
+		vpe->vpe_proxy_event = -1;
 
 	return 0;
 }
@@ -3228,6 +3818,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				    unsigned int nr_irqs, void *args)
 {
+	struct irq_chip *irqchip = &its_vpe_irq_chip;
 	struct its_vm *vm = args;
 	unsigned long *bitmap;
 	struct page *vprop_page;
@@ -3255,6 +3846,9 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 	vm->nr_db_lpis = nr_ids;
 	vm->vprop_page = vprop_page;
 
+	if (gic_rdists->has_rvpeid)
+		irqchip = &its_vpe_4_1_irq_chip;
+
 	for (i = 0; i < nr_irqs; i++) {
 		vm->vpes[i]->vpe_db_lpi = base + i;
 		err = its_vpe_init(vm->vpes[i]);
@@ -3265,7 +3859,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (err)
 			break;
 		irq_domain_set_hwirq_and_chip(domain, virq + i, i,
-					      &its_vpe_irq_chip, vm->vpes[i]);
+					      irqchip, vm->vpes[i]);
 		set_bit(i, bitmap);
 	}
 
@@ -3778,6 +4372,14 @@ static int __init its_probe_one(struct resource *res,
 		} else {
 			pr_info("ITS@%pa: Single VMOVP capable\n", &res->start);
 		}
+
+		if (is_v4_1(its)) {
+			u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer);
+			its->mpidr = readl_relaxed(its_base + GITS_MPIDR);
+
+			pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n",
+				&res->start, its->mpidr, svpet);
+		}
 	}
 
 	its->numa_node = numa_node;
@@ -4138,6 +4740,8 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	bool has_v4 = false;
 	int err;
 
+	gic_rdists = rdists;
+
 	its_parent = parent_domain;
 	of_node = to_of_node(handle);
 	if (of_node)
@@ -4150,8 +4754,6 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 		return -ENXIO;
 	}
 
-	gic_rdists = rdists;
-
 	err = allocate_lpi_tables();
 	if (err)
 		return err;
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index d6218012097b..286f98222878 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -858,8 +858,21 @@ static int __gic_update_rdist_properties(struct redist_region *region,
 					 void __iomem *ptr)
 {
 	u64 typer = gic_read_typer(ptr + GICR_TYPER);
+
 	gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS);
-	gic_data.rdists.has_direct_lpi &= !!(typer & GICR_TYPER_DirectLPIS);
+
+	/* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */
+	gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
+	gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
+					   gic_data.rdists.has_rvpeid);
+
+	/* Detect non-sensical configurations */
+	if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
+		gic_data.rdists.has_direct_lpi = false;
+		gic_data.rdists.has_vlpis = false;
+		gic_data.rdists.has_rvpeid = false;
+	}
+
 	gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr);
 
 	return 1;
@@ -872,9 +885,10 @@ static void gic_update_rdist_properties(void)
 	if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
 		gic_data.ppi_nr = 0;
 	pr_info("%d PPIs implemented\n", gic_data.ppi_nr);
-	pr_info("%sVLPI support, %sdirect LPI support\n",
+	pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n",
 		!gic_data.rdists.has_vlpis ? "no " : "",
-		!gic_data.rdists.has_direct_lpi ? "no " : "");
+		!gic_data.rdists.has_direct_lpi ? "no " : "",
+		!gic_data.rdists.has_rvpeid ? "no " : "");
 }
 
 /* Check whether it's single security state view */
@@ -1562,10 +1576,14 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
 	pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
+
+	gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
+
 	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
 						 &gic_data);
 	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
 	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
+	gic_data.rdists.has_rvpeid = true;
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
 
diff --git a/drivers/irqchip/irq-imx-intmux.c b/drivers/irqchip/irq-imx-intmux.c
new file mode 100644
index 000000000000..c27577c81126
--- /dev/null
+++ b/drivers/irqchip/irq-imx-intmux.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright 2017 NXP
+
+/*                     INTMUX Block Diagram
+ *
+ *                               ________________
+ * interrupt source #  0  +---->|                |
+ *                        |     |                |
+ * interrupt source #  1  +++-->|                |
+ *            ...         | |   |   channel # 0  |--------->interrupt out # 0
+ *            ...         | |   |                |
+ *            ...         | |   |                |
+ * interrupt source # X-1 +++-->|________________|
+ *                        | | |
+ *                        | | |
+ *                        | | |  ________________
+ *                        +---->|                |
+ *                        | | | |                |
+ *                        | +-->|                |
+ *                        | | | |   channel # 1  |--------->interrupt out # 1
+ *                        | | +>|                |
+ *                        | | | |                |
+ *                        | | | |________________|
+ *                        | | |
+ *                        | | |
+ *                        | | |       ...
+ *                        | | |       ...
+ *                        | | |
+ *                        | | |  ________________
+ *                        +---->|                |
+ *                          | | |                |
+ *                          +-->|                |
+ *                            | |   channel # N  |--------->interrupt out # N
+ *                            +>|                |
+ *                              |                |
+ *                              |________________|
+ *
+ *
+ * N: Interrupt Channel Instance Number (N=7)
+ * X: Interrupt Source Number for each channel (X=32)
+ *
+ * The INTMUX interrupt multiplexer has 8 channels, each channel receives 32
+ * interrupt sources and generates 1 interrupt output.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+
+#define CHANIER(n)	(0x10 + (0x40 * n))
+#define CHANIPR(n)	(0x20 + (0x40 * n))
+
+#define CHAN_MAX_NUM		0x8
+
+struct intmux_irqchip_data {
+	int			chanidx;
+	int			irq;
+	struct irq_domain	*domain;
+};
+
+struct intmux_data {
+	raw_spinlock_t			lock;
+	void __iomem			*regs;
+	struct clk			*ipg_clk;
+	int				channum;
+	struct intmux_irqchip_data	irqchip_data[];
+};
+
+static void imx_intmux_irq_mask(struct irq_data *d)
+{
+	struct intmux_irqchip_data *irqchip_data = d->chip_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long flags;
+	void __iomem *reg;
+	u32 val;
+
+	raw_spin_lock_irqsave(&data->lock, flags);
+	reg = data->regs + CHANIER(idx);
+	val = readl_relaxed(reg);
+	/* disable the interrupt source of this channel */
+	val &= ~BIT(d->hwirq);
+	writel_relaxed(val, reg);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static void imx_intmux_irq_unmask(struct irq_data *d)
+{
+	struct intmux_irqchip_data *irqchip_data = d->chip_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long flags;
+	void __iomem *reg;
+	u32 val;
+
+	raw_spin_lock_irqsave(&data->lock, flags);
+	reg = data->regs + CHANIER(idx);
+	val = readl_relaxed(reg);
+	/* enable the interrupt source of this channel */
+	val |= BIT(d->hwirq);
+	writel_relaxed(val, reg);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static struct irq_chip imx_intmux_irq_chip = {
+	.name		= "intmux",
+	.irq_mask	= imx_intmux_irq_mask,
+	.irq_unmask	= imx_intmux_irq_unmask,
+};
+
+static int imx_intmux_irq_map(struct irq_domain *h, unsigned int irq,
+			      irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, h->host_data);
+	irq_set_chip_and_handler(irq, &imx_intmux_irq_chip, handle_level_irq);
+
+	return 0;
+}
+
+static int imx_intmux_irq_xlate(struct irq_domain *d, struct device_node *node,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	struct intmux_irqchip_data *irqchip_data = d->host_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+
+	/*
+	 * two cells needed in interrupt specifier:
+	 * the 1st cell: hw interrupt number
+	 * the 2nd cell: channel index
+	 */
+	if (WARN_ON(intsize != 2))
+		return -EINVAL;
+
+	if (WARN_ON(intspec[1] >= data->channum))
+		return -EINVAL;
+
+	*out_hwirq = intspec[0];
+	*out_type = IRQ_TYPE_LEVEL_HIGH;
+
+	return 0;
+}
+
+static int imx_intmux_irq_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+				 enum irq_domain_bus_token bus_token)
+{
+	struct intmux_irqchip_data *irqchip_data = d->host_data;
+
+	/* Not for us */
+	if (fwspec->fwnode != d->fwnode)
+		return false;
+
+	return irqchip_data->chanidx == fwspec->param[1];
+}
+
+static const struct irq_domain_ops imx_intmux_domain_ops = {
+	.map		= imx_intmux_irq_map,
+	.xlate		= imx_intmux_irq_xlate,
+	.select		= imx_intmux_irq_select,
+};
+
+static void imx_intmux_irq_handler(struct irq_desc *desc)
+{
+	struct intmux_irqchip_data *irqchip_data = irq_desc_get_handler_data(desc);
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long irqstat;
+	int pos, virq;
+
+	chained_irq_enter(irq_desc_get_chip(desc), desc);
+
+	/* read the interrupt source pending status of this channel */
+	irqstat = readl_relaxed(data->regs + CHANIPR(idx));
+
+	for_each_set_bit(pos, &irqstat, 32) {
+		virq = irq_find_mapping(irqchip_data->domain, pos);
+		if (virq)
+			generic_handle_irq(virq);
+	}
+
+	chained_irq_exit(irq_desc_get_chip(desc), desc);
+}
+
+static int imx_intmux_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct irq_domain *domain;
+	struct intmux_data *data;
+	int channum;
+	int i, ret;
+
+	channum = platform_irq_count(pdev);
+	if (channum == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else if (channum > CHAN_MAX_NUM) {
+		dev_err(&pdev->dev, "supports up to %d multiplex channels\n",
+			CHAN_MAX_NUM);
+		return -EINVAL;
+	}
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data) +
+			    channum * sizeof(data->irqchip_data[0]), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(data->regs)) {
+		dev_err(&pdev->dev, "failed to initialize reg\n");
+		return PTR_ERR(data->regs);
+	}
+
+	data->ipg_clk = devm_clk_get(&pdev->dev, "ipg");
+	if (IS_ERR(data->ipg_clk)) {
+		ret = PTR_ERR(data->ipg_clk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "failed to get ipg clk: %d\n", ret);
+		return ret;
+	}
+
+	data->channum = channum;
+	raw_spin_lock_init(&data->lock);
+
+	ret = clk_prepare_enable(data->ipg_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < channum; i++) {
+		data->irqchip_data[i].chanidx = i;
+
+		data->irqchip_data[i].irq = irq_of_parse_and_map(np, i);
+		if (data->irqchip_data[i].irq <= 0) {
+			ret = -EINVAL;
+			dev_err(&pdev->dev, "failed to get irq\n");
+			goto out;
+		}
+
+		domain = irq_domain_add_linear(np, 32, &imx_intmux_domain_ops,
+					       &data->irqchip_data[i]);
+		if (!domain) {
+			ret = -ENOMEM;
+			dev_err(&pdev->dev, "failed to create IRQ domain\n");
+			goto out;
+		}
+		data->irqchip_data[i].domain = domain;
+
+		/* disable all interrupt sources of this channel firstly */
+		writel_relaxed(0, data->regs + CHANIER(i));
+
+		irq_set_chained_handler_and_data(data->irqchip_data[i].irq,
+						 imx_intmux_irq_handler,
+						 &data->irqchip_data[i]);
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	return 0;
+out:
+	clk_disable_unprepare(data->ipg_clk);
+	return ret;
+}
+
+static int imx_intmux_remove(struct platform_device *pdev)
+{
+	struct intmux_data *data = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < data->channum; i++) {
+		/* disable all interrupt sources of this channel */
+		writel_relaxed(0, data->regs + CHANIER(i));
+
+		irq_set_chained_handler_and_data(data->irqchip_data[i].irq,
+						 NULL, NULL);
+
+		irq_domain_remove(data->irqchip_data[i].domain);
+	}
+
+	clk_disable_unprepare(data->ipg_clk);
+
+	return 0;
+}
+
+static const struct of_device_id imx_intmux_id[] = {
+	{ .compatible = "fsl,imx-intmux", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver imx_intmux_driver = {
+	.driver = {
+		.name = "imx-intmux",
+		.of_match_table = imx_intmux_id,
+	},
+	.probe = imx_intmux_probe,
+	.remove = imx_intmux_remove,
+};
+builtin_platform_driver(imx_intmux_driver);
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 3f09f658e8e2..6b566bba263b 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -374,6 +374,7 @@ static struct platform_driver mbigen_platform_driver = {
 		.name		= "Hisilicon MBIGEN-V2",
 		.of_match_table	= mbigen_of_match,
 		.acpi_match_table = ACPI_PTR(mbigen_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe			= mbigen_device_probe,
 };
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index 829084b568fa..ccc7f823911b 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -24,50 +24,101 @@
 #define REG_PIN_47_SEL	0x08
 #define REG_FILTER_SEL	0x0c
 
+/* use for A1 like chips */
+#define REG_PIN_A1_SEL	0x04
+
 /*
  * Note: The S905X3 datasheet reports that BOTH_EDGE is controlled by
  * bits 24 to 31. Tests on the actual HW show that these bits are
  * stuck at 0. Bits 8 to 15 are responsive and have the expected
  * effect.
  */
-#define REG_EDGE_POL_EDGE(x)	BIT(x)
-#define REG_EDGE_POL_LOW(x)	BIT(16 + (x))
-#define REG_BOTH_EDGE(x)	BIT(8 + (x))
-#define REG_EDGE_POL_MASK(x)    (	\
-		REG_EDGE_POL_EDGE(x) |	\
-		REG_EDGE_POL_LOW(x)  |	\
-		REG_BOTH_EDGE(x))
+#define REG_EDGE_POL_EDGE(params, x)	BIT((params)->edge_single_offset + (x))
+#define REG_EDGE_POL_LOW(params, x)	BIT((params)->pol_low_offset + (x))
+#define REG_BOTH_EDGE(params, x)	BIT((params)->edge_both_offset + (x))
+#define REG_EDGE_POL_MASK(params, x)    (	\
+		REG_EDGE_POL_EDGE(params, x) |	\
+		REG_EDGE_POL_LOW(params, x)  |	\
+		REG_BOTH_EDGE(params, x))
 #define REG_PIN_SEL_SHIFT(x)	(((x) % 4) * 8)
 #define REG_FILTER_SEL_SHIFT(x)	((x) * 4)
 
+struct meson_gpio_irq_controller;
+static void meson8_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				    unsigned int channel, unsigned long hwirq);
+static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl);
+static void meson_a1_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				      unsigned int channel,
+				      unsigned long hwirq);
+static void meson_a1_gpio_irq_init(struct meson_gpio_irq_controller *ctl);
+
+struct irq_ctl_ops {
+	void (*gpio_irq_sel_pin)(struct meson_gpio_irq_controller *ctl,
+				 unsigned int channel, unsigned long hwirq);
+	void (*gpio_irq_init)(struct meson_gpio_irq_controller *ctl);
+};
+
 struct meson_gpio_irq_params {
 	unsigned int nr_hwirq;
 	bool support_edge_both;
+	unsigned int edge_both_offset;
+	unsigned int edge_single_offset;
+	unsigned int pol_low_offset;
+	unsigned int pin_sel_mask;
+	struct irq_ctl_ops ops;
 };
 
+#define INIT_MESON_COMMON(irqs, init, sel)			\
+	.nr_hwirq = irqs,					\
+	.ops = {						\
+		.gpio_irq_init = init,				\
+		.gpio_irq_sel_pin = sel,			\
+	},
+
+#define INIT_MESON8_COMMON_DATA(irqs)				\
+	INIT_MESON_COMMON(irqs, meson_gpio_irq_init_dummy,	\
+			  meson8_gpio_irq_sel_pin)		\
+	.edge_single_offset = 0,				\
+	.pol_low_offset = 16,					\
+	.pin_sel_mask = 0xff,					\
+
+#define INIT_MESON_A1_COMMON_DATA(irqs)				\
+	INIT_MESON_COMMON(irqs, meson_a1_gpio_irq_init,		\
+			  meson_a1_gpio_irq_sel_pin)		\
+	.support_edge_both = true,				\
+	.edge_both_offset = 16,					\
+	.edge_single_offset = 8,				\
+	.pol_low_offset = 0,					\
+	.pin_sel_mask = 0x7f,					\
+
 static const struct meson_gpio_irq_params meson8_params = {
-	.nr_hwirq = 134,
+	INIT_MESON8_COMMON_DATA(134)
 };
 
 static const struct meson_gpio_irq_params meson8b_params = {
-	.nr_hwirq = 119,
+	INIT_MESON8_COMMON_DATA(119)
 };
 
 static const struct meson_gpio_irq_params gxbb_params = {
-	.nr_hwirq = 133,
+	INIT_MESON8_COMMON_DATA(133)
 };
 
 static const struct meson_gpio_irq_params gxl_params = {
-	.nr_hwirq = 110,
+	INIT_MESON8_COMMON_DATA(110)
 };
 
 static const struct meson_gpio_irq_params axg_params = {
-	.nr_hwirq = 100,
+	INIT_MESON8_COMMON_DATA(100)
 };
 
 static const struct meson_gpio_irq_params sm1_params = {
-	.nr_hwirq = 100,
+	INIT_MESON8_COMMON_DATA(100)
 	.support_edge_both = true,
+	.edge_both_offset = 8,
+};
+
+static const struct meson_gpio_irq_params a1_params = {
+	INIT_MESON_A1_COMMON_DATA(62)
 };
 
 static const struct of_device_id meson_irq_gpio_matches[] = {
@@ -78,6 +129,7 @@ static const struct of_device_id meson_irq_gpio_matches[] = {
 	{ .compatible = "amlogic,meson-axg-gpio-intc", .data = &axg_params },
 	{ .compatible = "amlogic,meson-g12a-gpio-intc", .data = &axg_params },
 	{ .compatible = "amlogic,meson-sm1-gpio-intc", .data = &sm1_params },
+	{ .compatible = "amlogic,meson-a1-gpio-intc", .data = &a1_params },
 	{ }
 };
 
@@ -100,9 +152,43 @@ static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
 	writel_relaxed(tmp, ctl->base + reg);
 }
 
-static unsigned int meson_gpio_irq_channel_to_reg(unsigned int channel)
+static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
+{
+}
+
+static void meson8_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				    unsigned int channel, unsigned long hwirq)
+{
+	unsigned int reg_offset;
+	unsigned int bit_offset;
+
+	reg_offset = (channel < 4) ? REG_PIN_03_SEL : REG_PIN_47_SEL;
+	bit_offset = REG_PIN_SEL_SHIFT(channel);
+
+	meson_gpio_irq_update_bits(ctl, reg_offset,
+				   ctl->params->pin_sel_mask << bit_offset,
+				   hwirq << bit_offset);
+}
+
+static void meson_a1_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				      unsigned int channel,
+				      unsigned long hwirq)
 {
-	return (channel < 4) ? REG_PIN_03_SEL : REG_PIN_47_SEL;
+	unsigned int reg_offset;
+	unsigned int bit_offset;
+
+	bit_offset = ((channel % 2) == 0) ? 0 : 16;
+	reg_offset = REG_PIN_A1_SEL + ((channel / 2) << 2);
+
+	meson_gpio_irq_update_bits(ctl, reg_offset,
+				   ctl->params->pin_sel_mask << bit_offset,
+				   hwirq << bit_offset);
+}
+
+/* For a1 or later chips like a1 there is a switch to enable/disable irq */
+static void meson_a1_gpio_irq_init(struct meson_gpio_irq_controller *ctl)
+{
+	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL, BIT(31), BIT(31));
 }
 
 static int
@@ -110,7 +196,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 			       unsigned long  hwirq,
 			       u32 **channel_hwirq)
 {
-	unsigned int reg, idx;
+	unsigned int idx;
 
 	spin_lock(&ctl->lock);
 
@@ -129,10 +215,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	 * Setup the mux of the channel to route the signal of the pad
 	 * to the appropriate input of the GIC
 	 */
-	reg = meson_gpio_irq_channel_to_reg(idx);
-	meson_gpio_irq_update_bits(ctl, reg,
-				   0xff << REG_PIN_SEL_SHIFT(idx),
-				   hwirq << REG_PIN_SEL_SHIFT(idx));
+	ctl->params->ops.gpio_irq_sel_pin(ctl, idx, hwirq);
 
 	/*
 	 * Get the hwirq number assigned to this channel through
@@ -173,7 +256,9 @@ static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl,
 {
 	u32 val = 0;
 	unsigned int idx;
+	const struct meson_gpio_irq_params *params;
 
+	params = ctl->params;
 	idx = meson_gpio_irq_get_channel_idx(ctl, channel_hwirq);
 
 	/*
@@ -190,22 +275,22 @@ static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl,
 	 * precedence over the other edge/polarity settings
 	 */
 	if (type == IRQ_TYPE_EDGE_BOTH) {
-		if (!ctl->params->support_edge_both)
+		if (!params->support_edge_both)
 			return -EINVAL;
 
-		val |= REG_BOTH_EDGE(idx);
+		val |= REG_BOTH_EDGE(params, idx);
 	} else {
 		if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))
-			val |= REG_EDGE_POL_EDGE(idx);
+			val |= REG_EDGE_POL_EDGE(params, idx);
 
 		if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_EDGE_FALLING))
-			val |= REG_EDGE_POL_LOW(idx);
+			val |= REG_EDGE_POL_LOW(params, idx);
 	}
 
 	spin_lock(&ctl->lock);
 
 	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL,
-				   REG_EDGE_POL_MASK(idx), val);
+				   REG_EDGE_POL_MASK(params, idx), val);
 
 	spin_unlock(&ctl->lock);
 
@@ -371,6 +456,8 @@ static int __init meson_gpio_irq_parse_dt(struct device_node *node,
 		return ret;
 	}
 
+	ctl->params->ops.gpio_irq_init(ctl);
+
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c
index a166d30deea2..f747e2209ea9 100644
--- a/drivers/irqchip/irq-nvic.c
+++ b/drivers/irqchip/irq-nvic.c
@@ -45,17 +45,6 @@ nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs)
 	handle_IRQ(irq, regs);
 }
 
-static int nvic_irq_domain_translate(struct irq_domain *d,
-				     struct irq_fwspec *fwspec,
-				     unsigned long *hwirq, unsigned int *type)
-{
-	if (WARN_ON(fwspec->param_count < 1))
-		return -EINVAL;
-	*hwirq = fwspec->param[0];
-	*type = IRQ_TYPE_NONE;
-	return 0;
-}
-
 static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				unsigned int nr_irqs, void *arg)
 {
@@ -64,7 +53,7 @@ static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	unsigned int type = IRQ_TYPE_NONE;
 	struct irq_fwspec *fwspec = arg;
 
-	ret = nvic_irq_domain_translate(domain, fwspec, &hwirq, &type);
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
 	if (ret)
 		return ret;
 
@@ -75,7 +64,7 @@ static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 }
 
 static const struct irq_domain_ops nvic_irq_domain_ops = {
-	.translate = nvic_irq_domain_translate,
+	.translate = irq_domain_translate_onecell,
 	.alloc = nvic_irq_domain_alloc,
 	.free = irq_domain_free_irqs_top,
 };
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 0aca5807a119..aa4af886e43a 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -154,15 +154,37 @@ static struct irq_chip plic_chip = {
 static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &plic_chip, handle_fasteoi_irq);
-	irq_set_chip_data(irq, NULL);
+	irq_domain_set_info(d, irq, hwirq, &plic_chip, d->host_data,
+			    handle_fasteoi_irq, NULL, NULL);
 	irq_set_noprobe(irq);
 	return 0;
 }
 
+static int plic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	struct irq_fwspec *fwspec = arg;
+
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = plic_irqdomain_map(domain, virq + i, hwirq + i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static const struct irq_domain_ops plic_irqdomain_ops = {
-	.map		= plic_irqdomain_map,
-	.xlate		= irq_domain_xlate_onecell,
+	.translate	= irq_domain_translate_onecell,
+	.alloc		= plic_irq_domain_alloc,
+	.free		= irq_domain_free_irqs_top,
 };
 
 static struct irq_domain *plic_irqdomain;
diff --git a/include/dt-bindings/interrupt-controller/aspeed-scu-ic.h b/include/dt-bindings/interrupt-controller/aspeed-scu-ic.h
new file mode 100644
index 000000000000..f315d5a7f5ee
--- /dev/null
+++ b/include/dt-bindings/interrupt-controller/aspeed-scu-ic.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _DT_BINDINGS_INTERRUPT_CONTROLLER_ASPEED_SCU_IC_H_
+#define _DT_BINDINGS_INTERRUPT_CONTROLLER_ASPEED_SCU_IC_H_
+
+#define ASPEED_SCU_IC_VGA_CURSOR_CHANGE			0
+#define ASPEED_SCU_IC_VGA_SCRATCH_REG_CHANGE		1
+
+#define ASPEED_AST2500_SCU_IC_PCIE_RESET_LO_TO_HI	2
+#define ASPEED_AST2500_SCU_IC_PCIE_RESET_HI_TO_LO	3
+#define ASPEED_AST2500_SCU_IC_LPC_RESET_LO_TO_HI	4
+#define ASPEED_AST2500_SCU_IC_LPC_RESET_HI_TO_LO	5
+#define ASPEED_AST2500_SCU_IC_ISSUE_MSI			6
+
+#define ASPEED_AST2600_SCU_IC0_PCIE_PERST_LO_TO_HI	2
+#define ASPEED_AST2600_SCU_IC0_PCIE_PERST_HI_TO_LO	3
+#define ASPEED_AST2600_SCU_IC0_PCIE_RCRST_LO_TO_HI	4
+#define ASPEED_AST2600_SCU_IC0_PCIE_RCRST_HI_TO_LO	5
+
+#define ASPEED_AST2600_SCU_IC1_LPC_RESET_LO_TO_HI	0
+#define ASPEED_AST2600_SCU_IC1_LPC_RESET_HI_TO_LO	1
+
+#endif /* _DT_BINDINGS_INTERRUPT_CONTROLLER_ASPEED_SCU_IC_H_ */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index de991d6633a5..f0b8ca766e7d 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -13,6 +13,7 @@
 #define GICD_CTLR			0x0000
 #define GICD_TYPER			0x0004
 #define GICD_IIDR			0x0008
+#define GICD_TYPER2			0x000C
 #define GICD_STATUSR			0x0010
 #define GICD_SETSPI_NSR			0x0040
 #define GICD_CLRSPI_NSR			0x0048
@@ -89,6 +90,9 @@
 #define GICD_TYPER_ESPIS(typer)						\
 	(((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0)
 
+#define GICD_TYPER2_VIL			(1U << 7)
+#define GICD_TYPER2_VID			GENMASK(4, 0)
+
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
 #define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
 
@@ -98,6 +102,11 @@
 
 #define GIC_V3_DIST_SIZE		0x10000
 
+#define GIC_PAGE_SIZE_4K		0ULL
+#define GIC_PAGE_SIZE_16K		1ULL
+#define GIC_PAGE_SIZE_64K		2ULL
+#define GIC_PAGE_SIZE_MASK		3ULL
+
 /*
  * Re-Distributor registers, offsets from RD_base
  */
@@ -234,6 +243,16 @@
 #define GICR_TYPER_VLPIS		(1U << 1)
 #define GICR_TYPER_DirectLPIS		(1U << 3)
 #define GICR_TYPER_LAST			(1U << 4)
+#define GICR_TYPER_RVPEID		(1U << 7)
+#define GICR_TYPER_COMMON_LPI_AFF	GENMASK_ULL(25, 24)
+#define GICR_TYPER_AFFINITY		GENMASK_ULL(63, 32)
+
+#define GICR_INVLPIR_INTID		GENMASK_ULL(31, 0)
+#define GICR_INVLPIR_VPEID		GENMASK_ULL(47, 32)
+#define GICR_INVLPIR_V			GENMASK_ULL(63, 63)
+
+#define GICR_INVALLR_VPEID		GICR_INVLPIR_VPEID
+#define GICR_INVALLR_V			GICR_INVLPIR_V
 
 #define GIC_V3_REDIST_SIZE		0x20000
 
@@ -272,6 +291,18 @@
 #define GICR_VPROPBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt)
 #define GICR_VPROPBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb)
 
+/*
+ * GICv4.1 VPROPBASER reinvention. A subtle mix between the old
+ * VPROPBASER and ITS_BASER. Just not quite any of the two.
+ */
+#define GICR_VPROPBASER_4_1_VALID	(1ULL << 63)
+#define GICR_VPROPBASER_4_1_ENTRY_SIZE	GENMASK_ULL(61, 59)
+#define GICR_VPROPBASER_4_1_INDIRECT	(1ULL << 55)
+#define GICR_VPROPBASER_4_1_PAGE_SIZE	GENMASK_ULL(54, 53)
+#define GICR_VPROPBASER_4_1_Z		(1ULL << 52)
+#define GICR_VPROPBASER_4_1_ADDR	GENMASK_ULL(51, 12)
+#define GICR_VPROPBASER_4_1_SIZE	GENMASK_ULL(6, 0)
+
 #define GICR_VPENDBASER			0x0078
 
 #define GICR_VPENDBASER_SHAREABILITY_SHIFT		(10)
@@ -303,12 +334,22 @@
 #define GICR_VPENDBASER_IDAI		(1ULL << 62)
 #define GICR_VPENDBASER_Valid		(1ULL << 63)
 
+/*
+ * GICv4.1 VPENDBASER, used for VPE residency. On top of these fields,
+ * also use the above Valid, PendingLast and Dirty.
+ */
+#define GICR_VPENDBASER_4_1_DB		(1ULL << 62)
+#define GICR_VPENDBASER_4_1_VGRP0EN	(1ULL << 59)
+#define GICR_VPENDBASER_4_1_VGRP1EN	(1ULL << 58)
+#define GICR_VPENDBASER_4_1_VPEID	GENMASK_ULL(15, 0)
+
 /*
  * ITS registers, offsets from ITS_base
  */
 #define GITS_CTLR			0x0000
 #define GITS_IIDR			0x0004
 #define GITS_TYPER			0x0008
+#define GITS_MPIDR			0x0018
 #define GITS_CBASER			0x0080
 #define GITS_CWRITER			0x0088
 #define GITS_CREADR			0x0090
@@ -342,6 +383,8 @@
 #define GITS_TYPER_HCC_SHIFT		24
 #define GITS_TYPER_HCC(r)		(((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)
 #define GITS_TYPER_VMOVP		(1ULL << 37)
+#define GITS_TYPER_VMAPP		(1ULL << 40)
+#define GITS_TYPER_SVPET		GENMASK_ULL(42, 41)
 
 #define GITS_IIDR_REV_SHIFT		12
 #define GITS_IIDR_REV_MASK		(0xf << GITS_IIDR_REV_SHIFT)
@@ -412,10 +455,11 @@
 #define GITS_BASER_InnerShareable					\
 	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
 #define GITS_BASER_PAGE_SIZE_SHIFT	(8)
-#define GITS_BASER_PAGE_SIZE_4K		(0ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_16K	(1ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_64K	(2ULL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_MASK	(3ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define __GITS_BASER_PSZ(sz)		(GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_4K		__GITS_BASER_PSZ(4K)
+#define GITS_BASER_PAGE_SIZE_16K	__GITS_BASER_PSZ(16K)
+#define GITS_BASER_PAGE_SIZE_64K	__GITS_BASER_PSZ(64K)
+#define GITS_BASER_PAGE_SIZE_MASK	__GITS_BASER_PSZ(MASK)
 #define GITS_BASER_PAGES_MAX		256
 #define GITS_BASER_PAGES_SHIFT		(0)
 #define GITS_BASER_NR_PAGES(r)		(((r) & 0xff) + 1)
@@ -456,8 +500,9 @@
 #define GITS_CMD_VMAPTI			GITS_CMD_GICv4(GITS_CMD_MAPTI)
 #define GITS_CMD_VMOVI			GITS_CMD_GICv4(GITS_CMD_MOVI)
 #define GITS_CMD_VSYNC			GITS_CMD_GICv4(GITS_CMD_SYNC)
-/* VMOVP is the odd one, as it doesn't have a physical counterpart */
+/* VMOVP and INVDB are the odd ones, as they dont have a physical counterpart */
 #define GITS_CMD_VMOVP			GITS_CMD_GICv4(2)
+#define GITS_CMD_INVDB			GITS_CMD_GICv4(0xe)
 
 /*
  * ITS error numbers
@@ -607,14 +652,18 @@ struct rdists {
 	struct {
 		void __iomem	*rd_base;
 		struct page	*pend_page;
+		struct page	*vpe_l1_page;
 		phys_addr_t	phys_base;
 		bool		lpi_enabled;
+		cpumask_t	*vpe_table_mask;
 	} __percpu		*rdist;
 	phys_addr_t		prop_table_pa;
 	void			*prop_table_va;
 	u64			flags;
 	u32			gicd_typer;
+	u32			gicd_typer2;
 	bool			has_vlpis;
+	bool			has_rvpeid;
 	bool			has_direct_lpi;
 };
 
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 5dbcfc65f21e..d9c34968467a 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -39,8 +39,20 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
-	/* VPE proxy mapping */
-	int			vpe_proxy_event;
+	union {
+		/* GICv4.0 implementations */
+		struct {
+			/* VPE proxy mapping */
+			int	vpe_proxy_event;
+			/* Implementation Defined Area Invalid */
+			bool	idai;
+		};
+		/* GICv4.1 implementations */
+		struct {
+			atomic_t vmapp_count;
+		};
+	};
+
 	/*
 	 * This collection ID is used to indirect the target
 	 * redistributor for this VPE. The ID itself isn't involved in
@@ -49,8 +61,6 @@ struct its_vpe {
 	u16			col_idx;
 	/* Unique (system-wide) VPE identifier */
 	u16			vpe_id;
-	/* Implementation Defined Area Invalid */
-	bool			idai;
 	/* Pending VLPIs on schedule out? */
 	bool			pending_last;
 };
@@ -90,6 +100,11 @@ struct its_cmd_info {
 	union {
 		struct its_vlpi_map	*map;
 		u8			config;
+		bool			req_db;
+		struct {
+			bool		g0en;
+			bool		g1en;
+		};
 	};
 };
 
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 3c340dbc5a1f..698749f42ced 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -427,6 +427,11 @@ int irq_domain_translate_twocell(struct irq_domain *d,
 				 unsigned long *out_hwirq,
 				 unsigned int *out_type);
 
+int irq_domain_translate_onecell(struct irq_domain *d,
+				 struct irq_fwspec *fwspec,
+				 unsigned long *out_hwirq,
+				 unsigned int *out_type);
+
 /* IPI functions */
 int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest);
 int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest);
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 6c8512d3be88..0fbcbacd1b29 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -13,6 +13,7 @@ enum hk_flags {
 	HK_FLAG_TICK		= (1 << 4),
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
+	HK_FLAG_MANAGED_IRQ	= (1 << 7),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 6c7ca2e983a5..02236b13b359 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -12,6 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/ratelimit.h>
 #include <linux/irq.h>
+#include <linux/sched/isolation.h>
 
 #include "internals.h"
 
@@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void)
 	}
 }
 
+static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
+{
+	const struct cpumask *hk_mask;
+
+	if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+		return false;
+
+	hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+	if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
+		return false;
+
+	return cpumask_test_cpu(cpu, hk_mask);
+}
+
 static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
 	/*
 	 * If the interrupt can only be directed to a single target
 	 * CPU then it is already assigned to a CPU in the affinity
-	 * mask. No point in trying to move it around.
+	 * mask. No point in trying to move it around unless the
+	 * isolation mechanism requests to move it to an upcoming
+	 * housekeeping CPU.
 	 */
-	if (!irqd_is_single_target(data))
+	if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
 		irq_set_affinity_locked(data, affinity, false);
 }
 
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 5b8fdd659e54..98a5f10d1900 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -891,6 +891,7 @@ __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
 }
 
 void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+	__releases(&desc->lock)
 {
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	if (bus)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index dd822fd8a7d5..7527e5ef6fe5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -986,6 +986,23 @@ const struct irq_domain_ops irq_domain_simple_ops = {
 };
 EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
 
+/**
+ * irq_domain_translate_onecell() - Generic translate for direct one cell
+ * bindings
+ */
+int irq_domain_translate_onecell(struct irq_domain *d,
+				 struct irq_fwspec *fwspec,
+				 unsigned long *out_hwirq,
+				 unsigned int *out_type)
+{
+	if (WARN_ON(fwspec->param_count < 1))
+		return -EINVAL;
+	*out_hwirq = fwspec->param[0];
+	*out_type = IRQ_TYPE_NONE;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_domain_translate_onecell);
+
 /**
  * irq_domain_translate_twocell() - Generic translate for direct two cell
  * bindings
@@ -1459,6 +1476,7 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg)
 	if (rv) {
 		/* Restore the original irq_data. */
 		*root_irq_data = *child_irq_data;
+		kfree(child_irq_data);
 		goto error;
 	}
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1753486b440c..818b2802d3e7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/task.h>
+#include <linux/sched/isolation.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/task_work.h>
 
@@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
-	ret = chip->irq_set_affinity(data, mask, force);
+	/*
+	 * If this is a managed interrupt and housekeeping is enabled on
+	 * it check whether the requested affinity mask intersects with
+	 * a housekeeping CPU. If so, then remove the isolated CPUs from
+	 * the mask and just keep the housekeeping CPU(s). This prevents
+	 * the affinity setter from routing the interrupt to an isolated
+	 * CPU to avoid that I/O submitted from a housekeeping CPU causes
+	 * interrupts on an isolated one.
+	 *
+	 * If the masks do not intersect or include online CPU(s) then
+	 * keep the requested mask. The isolated target CPUs are only
+	 * receiving interrupts when the I/O operation was submitted
+	 * directly from them.
+	 *
+	 * If all housekeeping CPUs in the affinity mask are offline, the
+	 * interrupt will be migrated by the CPU hotplug code once a
+	 * housekeeping CPU which belongs to the affinity mask comes
+	 * online.
+	 */
+	if (irqd_affinity_is_managed(data) &&
+	    housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+		const struct cpumask *hk_mask, *prog_mask;
+
+		static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
+		static struct cpumask tmp_mask;
+
+		hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+
+		raw_spin_lock(&tmp_mask_lock);
+		cpumask_and(&tmp_mask, mask, hk_mask);
+		if (!cpumask_intersects(&tmp_mask, cpu_online_mask))
+			prog_mask = mask;
+		else
+			prog_mask = &tmp_mask;
+		ret = chip->irq_set_affinity(data, prog_mask, force);
+		raw_spin_unlock(&tmp_mask_lock);
+	} else {
+		ret = chip->irq_set_affinity(data, mask, force);
+	}
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
@@ -1500,8 +1539,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * has. The type flags are unreliable as the
 		 * underlying chip implementation can override them.
 		 */
-		pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
-		       irq);
+		pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n",
+		       new->name, irq);
 		ret = -EINVAL;
 		goto out_unlock;
 	}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 2ed97a7c9b2a..f865e5f4d382 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -34,6 +34,7 @@ static atomic_t irq_poll_active;
  * true and let the handler run.
  */
 bool irq_wait_for_poll(struct irq_desc *desc)
+	__must_hold(&desc->lock)
 {
 	if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
 		      "irq poll in progress on cpu %d for irq %d\n",
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9fcb2a695a41..008d6ac2342b 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
+		if (!strncmp(str, "managed_irq,", 12)) {
+			str += 12;
+			flags |= HK_FLAG_MANAGED_IRQ;
+			continue;
+		}
+
 		pr_warn("isolcpus: Error, unknown flag\n");
 		return 0;
 	}

Re: [GIT pull] irq/core for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-core-2020-01-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/3d3b44a61a9cfd268fc071ea1b1c5dfea7ed133d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] smp/core for

[Thomas Gleixner]

Linus,

please pull the latest smp/core branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-core-2020-01-28

up to:  cb923159bbb8: smp: Remove allocation mask from on_each_cpu_cond.*()


A small set of SMP core code changes:

 - Rework the smp function call core code to avoid the allocation of an
   additional cpumask.

 - Remove the not longer required GFP argument from on_each_cpu_cond() and
   on_each_cpu_cond_mask() and fixup the callers.

Thanks,

	tglx

------------------>
Sebastian Andrzej Siewior (3):
      smp: Use smp_cond_func_t as type for the conditional function
      smp: Add a smp_cond_func_t argument to smp_call_function_many()
      smp: Remove allocation mask from on_each_cpu_cond.*()


 arch/x86/mm/tlb.c   |  2 +-
 fs/buffer.c         |  2 +-
 include/linux/smp.h | 11 +++---
 kernel/smp.c        | 99 +++++++++++++++++++++++------------------------------
 kernel/up.c         | 12 +++----
 mm/slub.c           |  2 +-
 6 files changed, 56 insertions(+), 72 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e6a9edc5baaf..66f96f21a7b6 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -708,7 +708,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 			       (void *)info, 1);
 	else
 		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote,
-				(void *)info, 1, GFP_ATOMIC, cpumask);
+				(void *)info, 1, cpumask);
 }
 
 /*
diff --git a/fs/buffer.c b/fs/buffer.c
index 18a87ec8a465..b8d28370cfd7 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1433,7 +1433,7 @@ static bool has_bh_in_lru(int cpu, void *dummy)
 
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 6fc856c9eda5..cbc9162689d0 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -15,6 +15,7 @@
 #include <linux/llist.h>
 
 typedef void (*smp_call_func_t)(void *info);
+typedef bool (*smp_cond_func_t)(int cpu, void *info);
 struct __call_single_data {
 	struct llist_node llist;
 	smp_call_func_t func;
@@ -49,13 +50,11 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
  * cond_func returns a positive value. This may include the local
  * processor.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		smp_call_func_t func, void *info, bool wait,
-		gfp_t gfp_flags);
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait);
 
-void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
-		smp_call_func_t func, void *info, bool wait,
-		gfp_t gfp_flags, const struct cpumask *mask);
+void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
+			   void *info, bool wait, const struct cpumask *mask);
 
 int smp_call_function_single_async(int cpu, call_single_data_t *csd);
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 7dbcb402c2fc..3b7bedc97af3 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -395,22 +395,9 @@ int smp_call_function_any(const struct cpumask *mask,
 }
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
-/**
- * smp_call_function_many(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on (only runs on online subset).
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed
- *        on other CPUs.
- *
- * If @wait is true, then returns once @func has returned.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler. Preemption
- * must be disabled when calling this function.
- */
-void smp_call_function_many(const struct cpumask *mask,
-			    smp_call_func_t func, void *info, bool wait)
+static void smp_call_function_many_cond(const struct cpumask *mask,
+					smp_call_func_t func, void *info,
+					bool wait, smp_cond_func_t cond_func)
 {
 	struct call_function_data *cfd;
 	int cpu, next_cpu, this_cpu = smp_processor_id();
@@ -448,7 +435,8 @@ void smp_call_function_many(const struct cpumask *mask,
 
 	/* Fastpath: do that cpu by itself. */
 	if (next_cpu >= nr_cpu_ids) {
-		smp_call_function_single(cpu, func, info, wait);
+		if (!cond_func || (cond_func && cond_func(cpu, info)))
+			smp_call_function_single(cpu, func, info, wait);
 		return;
 	}
 
@@ -465,6 +453,9 @@ void smp_call_function_many(const struct cpumask *mask,
 	for_each_cpu(cpu, cfd->cpumask) {
 		call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu);
 
+		if (cond_func && !cond_func(cpu, info))
+			continue;
+
 		csd_lock(csd);
 		if (wait)
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
@@ -486,6 +477,26 @@ void smp_call_function_many(const struct cpumask *mask,
 		}
 	}
 }
+
+/**
+ * smp_call_function_many(): Run a function on a set of other CPUs.
+ * @mask: The set of cpus to run on (only runs on online subset).
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
+ *
+ * If @wait is true, then returns once @func has returned.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler. Preemption
+ * must be disabled when calling this function.
+ */
+void smp_call_function_many(const struct cpumask *mask,
+			    smp_call_func_t func, void *info, bool wait)
+{
+	smp_call_function_many_cond(mask, func, info, wait, NULL);
+}
 EXPORT_SYMBOL(smp_call_function_many);
 
 /**
@@ -668,11 +679,6 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * @info:	An arbitrary pointer to pass to both functions.
  * @wait:	If true, wait (atomically) until function has
  *		completed on other CPUs.
- * @gfp_flags:	GFP flags to use when allocating the cpumask
- *		used internally by the function.
- *
- * The function might sleep if the GFP flags indicates a non
- * atomic allocation is allowed.
  *
  * Preemption is disabled to protect against CPUs going offline but not online.
  * CPUs going online during the call will not be seen or sent an IPI.
@@ -680,46 +686,27 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * You must not call this function with disabled interrupts or
  * from a hardware interrupt handler or from a bottom half handler.
  */
-void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
-			smp_call_func_t func, void *info, bool wait,
-			gfp_t gfp_flags, const struct cpumask *mask)
+void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
+			   void *info, bool wait, const struct cpumask *mask)
 {
-	cpumask_var_t cpus;
-	int cpu, ret;
-
-	might_sleep_if(gfpflags_allow_blocking(gfp_flags));
-
-	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
-		preempt_disable();
-		for_each_cpu(cpu, mask)
-			if (cond_func(cpu, info))
-				__cpumask_set_cpu(cpu, cpus);
-		on_each_cpu_mask(cpus, func, info, wait);
-		preempt_enable();
-		free_cpumask_var(cpus);
-	} else {
-		/*
-		 * No free cpumask, bother. No matter, we'll
-		 * just have to IPI them one by one.
-		 */
-		preempt_disable();
-		for_each_cpu(cpu, mask)
-			if (cond_func(cpu, info)) {
-				ret = smp_call_function_single(cpu, func,
-								info, wait);
-				WARN_ON_ONCE(ret);
-			}
-		preempt_enable();
+	int cpu = get_cpu();
+
+	smp_call_function_many_cond(mask, func, info, wait, cond_func);
+	if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		func(info);
+		local_irq_restore(flags);
 	}
+	put_cpu();
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-			smp_call_func_t func, void *info, bool wait,
-			gfp_t gfp_flags)
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait)
 {
-	on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags,
-				cpu_online_mask);
+	on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
 }
 EXPORT_SYMBOL(on_each_cpu_cond);
 
diff --git a/kernel/up.c b/kernel/up.c
index 862b460ab97a..53144d056252 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -68,9 +68,8 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * Preemption is disabled here to make sure the cond_func is called under the
  * same condtions in UP and SMP.
  */
-void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
-			   smp_call_func_t func, void *info, bool wait,
-			   gfp_t gfp_flags, const struct cpumask *mask)
+void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
+			   void *info, bool wait, const struct cpumask *mask)
 {
 	unsigned long flags;
 
@@ -84,11 +83,10 @@ void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		      smp_call_func_t func, void *info, bool wait,
-		      gfp_t gfp_flags)
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait)
 {
-	on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, NULL);
+	on_each_cpu_cond_mask(cond_func, func, info, wait, NULL);
 }
 EXPORT_SYMBOL(on_each_cpu_cond);
 
diff --git a/mm/slub.c b/mm/slub.c
index 8eafccf75940..2e1a57723f8e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2341,7 +2341,7 @@ static bool has_cpu_slab(int cpu, void *info)
 
 static void flush_all(struct kmem_cache *s)
 {
-	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
+	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
 }
 
 /*

Re: [GIT pull] smp/core for

[pr-tracker-bot]

The pull request you sent on Mon, 27 Jan 2020 23:49:25 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-core-2020-01-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/ab67f600253f0f7b3992399918cf69e71b22ff37

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

Re: [GIT pull 0/7] Various tip branches

[Linus Torvalds]

On Mon, Jan 27, 2020 at 4:06 PM Thomas Gleixner <tglx@linutronix.de> wrote:
>
> the following pull request are my first attempt of using signed
> tags. Please double check and yell if something went wrong.

Well, the first one looked fine, but the subject lines were a bit odd
on most of them.

They say "[GIT pull] xyz for" without saying what they are for.  So
there's a missing "5.6-rc1" there ;)

Not a big deal, and I don't think it has anything to do with the
tagging, which looked fine in at least the timer fixes case.

              Linus

Re: [GIT pull 0/7] Various tip branches

[Thomas Gleixner]

Linus Torvalds <torvalds@linux-foundation.org> writes:
> On Mon, Jan 27, 2020 at 4:06 PM Thomas Gleixner <tglx@linutronix.de> wrote:
>>
>> the following pull request are my first attempt of using signed
>> tags. Please double check and yell if something went wrong.
>
> Well, the first one looked fine, but the subject lines were a bit odd
> on most of them.
>
> They say "[GIT pull] xyz for" without saying what they are for.  So
> there's a missing "5.6-rc1" there ;)

Indeed. Seems I deleted the check for that second argument when adding
the tag magic to the pull request scripting. Added it back now.

Thanks,

        tglx