Merge tag 'timers-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Updates for timekeeping, timers and clockevent/source drivers:

  Core:

   - Yet another round of improvements to make the clocksource watchdog
     more robust:

       - Relax the clocksource-watchdog skew criteria to match the NTP
         criteria.

       - Temporarily skip the watchdog when high memory latencies are
         detected which can lead to false-positives.

       - Provide an option to enable TSC skew detection even on systems
         where TSC is marked as reliable.

     Sigh!

   - Initialize the restart block in the nanosleep syscalls to be
     directed to the no restart function instead of doing a partial
     setup on entry.

     This prevents an erroneous restart_syscall() invocation from
     corrupting user space data. While such a situation is clearly a
     user space bug, preventing this is a correctness issue and caters
     to the least suprise principle.

   - Ignore the hrtimer slack for realtime tasks in schedule_hrtimeout()
     to align it with the nanosleep semantics.

  Drivers:

   - The obligatory new driver bindings for Mediatek, Rockchip and
     RISC-V variants.

   - Add support for the C3STOP misfeature to the RISC-V timer to handle
     the case where the timer stops in deeper idle state.

   - Set up a static key in the RISC-V timer correctly before first use.

   - The usual small improvements and fixes all over the place"

* tag 'timers-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  clocksource/drivers/timer-sun4i: Add CLOCK_EVT_FEAT_DYNIRQ
  clocksource/drivers/em_sti: Mark driver as non-removable
  clocksource/drivers/sh_tmu: Mark driver as non-removable
  clocksource/drivers/riscv: Patch riscv_clock_next_event() jump before first use
  clocksource/drivers/timer-microchip-pit64b: Add delay timer
  clocksource/drivers/timer-microchip-pit64b: Select driver only on ARM
  dt-bindings: timer: sifive,clint: add comaptibles for T-Head's C9xx
  dt-bindings: timer: mediatek,mtk-timer: add MT8365
  clocksource/drivers/riscv: Get rid of clocksource_arch_init() callback
  clocksource/drivers/sh_cmt: Mark driver as non-removable
  clocksource/drivers/timer-microchip-pit64b: Drop obsolete dependency on COMPILE_TEST
  clocksource/drivers/riscv: Increase the clock source rating
  clocksource/drivers/timer-riscv: Set CLOCK_EVT_FEAT_C3STOP based on DT
  dt-bindings: timer: Add bindings for the RISC-V timer device
  RISC-V: time: initialize hrtimer based broadcast clock event device
  dt-bindings: timer: rk-timer: Add rktimer for rv1126
  time/debug: Fix memory leak with using debugfs_lookup()
  clocksource: Enable TSC watchdog checking of HPET and PMTMR only when requested
  posix-timers: Use atomic64_try_cmpxchg() in __update_gt_cputime()
  clocksource: Verify HPET and PMTMR when TSC unverified
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -6369,6 +6369,16 @@
 			in situations with strict latency requirements (where
 			interruptions from clocksource watchdog are not
 			acceptable).
+			[x86] recalibrate: force recalibration against a HW timer
+			(HPET or PM timer) on systems whose TSC frequency was
+			obtained from HW or FW using either an MSR or CPUID(0x15).
+			Warn if the difference is more than 500 ppm.
+			[x86] watchdog: Use TSC as the watchdog clocksource with
+			which to check other HW timers (HPET or PM timer), but
+			only on systems where TSC has been deemed trustworthy.
+			This will be suppressed by an earlier tsc=nowatchdog and
+			can be overridden by a later tsc=nowatchdog.  A console
+			message will flag any such suppression or overriding.
 
 	tsc_early_khz=  [X86] Skip early TSC calibration and use the given
 			value instead. Useful when the early TSC frequency discovery

Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt

@@ -33,6 +33,7 @@ Required properties:
 
 	For those SoCs that use CPUX
 	* "mediatek,mt6795-systimer" for MT6795 compatible timers (CPUX)
+	* "mediatek,mt8365-systimer" for MT8365 compatible timers (CPUX)
 
 - reg: Should contain location and length for timer register.
 - clocks: Should contain system clock.

Documentation/devicetree/bindings/timer/riscv,timer.yaml

@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/timer/riscv,timer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: RISC-V timer
+
+maintainers:
+  - Anup Patel <[email protected]>
+
+description: |+
+  RISC-V platforms always have a RISC-V timer device for the supervisor-mode
+  based on the time CSR defined by the RISC-V privileged specification. The
+  timer interrupts of this device are configured using the RISC-V SBI Time
+  extension or the RISC-V Sstc extension.
+
+  The clock frequency of RISC-V timer device is specified via the
+  "timebase-frequency" DT property of "/cpus" DT node which is described
+  in Documentation/devicetree/bindings/riscv/cpus.yaml
+
+properties:
+  compatible:
+    enum:
+      - riscv,timer
+
+  interrupts-extended:
+    minItems: 1
+    maxItems: 4096   # Should be enough?
+
+  riscv,timer-cannot-wake-cpu:
+    type: boolean
+    description:
+      If present, the timer interrupt cannot wake up the CPU from one or
+      more suspend/idle states.
+
+additionalProperties: false
+
+required:
+  - compatible
+  - interrupts-extended
+
+examples:
+  - |
+    timer {
+      compatible = "riscv,timer";
+      interrupts-extended = <&cpu1intc 5>,
+                            <&cpu2intc 5>,
+                            <&cpu3intc 5>,
+                            <&cpu4intc 5>;
+    };
+...

Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml

@@ -17,6 +17,7 @@ properties:
       - items:
           - enum:
               - rockchip,rv1108-timer
+              - rockchip,rv1126-timer
               - rockchip,rk3036-timer
               - rockchip,rk3128-timer
               - rockchip,rk3188-timer

Documentation/devicetree/bindings/timer/sifive,clint.yaml

@@ -20,6 +20,10 @@ description:
   property of "/cpus" DT node. The "timebase-frequency" DT property is
   described in Documentation/devicetree/bindings/riscv/cpus.yaml
 
+  T-Head C906/C910 CPU cores include an implementation of CLINT too, however
+  their implementation lacks a memory-mapped MTIME register, thus not
+  compatible with SiFive ones.
+
 properties:
   compatible:
     oneOf:
@@ -29,6 +33,10 @@ properties:
               - starfive,jh7100-clint
               - canaan,k210-clint
           - const: sifive,clint0
+      - items:
+          - enum:
+              - allwinner,sun20i-d1-clint
+          - const: thead,c900-clint
       - items:
           - const: sifive,clint0
           - const: riscv,clint0

arch/riscv/Kconfig

@@ -12,7 +12,6 @@ config 32BIT
 
 config RISCV
 	def_bool y
-	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_HAS_BINFMT_FLAT

arch/riscv/kernel/time.c

@@ -5,6 +5,7 @@
  */
 
 #include <linux/of_clk.h>
+#include <linux/clockchips.h>
 #include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <asm/sbi.h>
@@ -29,13 +30,6 @@ void __init time_init(void)
 
 	of_clk_init(NULL);
 	timer_probe();
-}
 
-void clocksource_arch_init(struct clocksource *cs)
-{
-#ifdef CONFIG_GENERIC_GETTIMEOFDAY
-	cs->vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER;
-#else
-	cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
-#endif
+	tick_setup_hrtimer_broadcast();
 }

arch/x86/include/asm/time.h

@@ -8,6 +8,7 @@
 extern void hpet_time_init(void);
 extern void time_init(void);
 extern bool pit_timer_init(void);
+extern bool tsc_clocksource_watchdog_disabled(void);
 
 extern struct clock_event_device *global_clock_event;
 

arch/x86/kernel/hpet.c

@@ -1091,6 +1091,8 @@ int __init hpet_enable(void)
 	if (!hpet_counting())
 		goto out_nohpet;
 
+	if (tsc_clocksource_watchdog_disabled())
+		clocksource_hpet.flags |= CLOCK_SOURCE_MUST_VERIFY;
 	clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
 
 	if (id & HPET_ID_LEGSUP) {

arch/x86/kernel/tsc.c

@@ -48,6 +48,8 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
+static int __read_mostly tsc_force_recalibrate;
+
 static u32 art_to_tsc_numerator;
 static u32 art_to_tsc_denominator;
 static u64 art_to_tsc_offset;
@@ -291,6 +293,7 @@ __setup("notsc", notsc_setup);
 
 static int no_sched_irq_time;
 static int no_tsc_watchdog;
+static int tsc_as_watchdog;
 
 static int __init tsc_setup(char *str)
 {
@@ -300,8 +303,22 @@ static int __init tsc_setup(char *str)
 		no_sched_irq_time = 1;
 	if (!strcmp(str, "unstable"))
 		mark_tsc_unstable("boot parameter");
-	if (!strcmp(str, "nowatchdog"))
+	if (!strcmp(str, "nowatchdog")) {
 		no_tsc_watchdog = 1;
+		if (tsc_as_watchdog)
+			pr_alert("%s: Overriding earlier tsc=watchdog with tsc=nowatchdog\n",
+				 __func__);
+		tsc_as_watchdog = 0;
+	}
+	if (!strcmp(str, "recalibrate"))
+		tsc_force_recalibrate = 1;
+	if (!strcmp(str, "watchdog")) {
+		if (no_tsc_watchdog)
+			pr_alert("%s: tsc=watchdog overridden by earlier tsc=nowatchdog\n",
+				 __func__);
+		else
+			tsc_as_watchdog = 1;
+	}
 	return 1;
 }
 
@@ -1184,6 +1201,12 @@ static void __init tsc_disable_clocksource_watchdog(void)
 	clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 }
 
+bool tsc_clocksource_watchdog_disabled(void)
+{
+	return !(clocksource_tsc.flags & CLOCK_SOURCE_MUST_VERIFY) &&
+	       tsc_as_watchdog && !no_tsc_watchdog;
+}
+
 static void __init check_system_tsc_reliable(void)
 {
 #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1372,6 +1395,25 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	else
 		freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
 
+	/* Will hit this only if tsc_force_recalibrate has been set */
+	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+
+		/* Warn if the deviation exceeds 500 ppm */
+		if (abs(tsc_khz - freq) > (tsc_khz >> 11)) {
+			pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n");
+			pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n",
+				(unsigned long)tsc_khz / 1000,
+				(unsigned long)tsc_khz % 1000);
+		}
+
+		pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n",
+			hpet ? "HPET" : "PM_TIMER",
+			(unsigned long)freq / 1000,
+			(unsigned long)freq % 1000);
+
+		return;
+	}
+
 	/* Make sure we're within 1% */
 	if (abs(tsc_khz - freq) > tsc_khz/100)
 		goto out;
@@ -1405,8 +1447,10 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
-	if (tsc_unstable)
-		goto unreg;
+	if (tsc_unstable) {
+		clocksource_unregister(&clocksource_tsc_early);
+		return 0;
+	}
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1419,9 +1463,10 @@ static int __init init_tsc_clocksource(void)
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
-unreg:
 		clocksource_unregister(&clocksource_tsc_early);
-		return 0;
+
+		if (!tsc_force_recalibrate)
+			return 0;
 	}
 
 	schedule_delayed_work(&tsc_irqwork, 0);