Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "The timer and timekeeping departement delivers:

  Core:

   - The consolidation of the VDSO code into a generic library including
     the conversion of x86 and ARM64. Conversion of ARM and MIPS are en
     route through the relevant maintainer trees and should end up in
     5.4.

     This gets rid of the unnecessary different copies of the same code
     and brings all architectures on the same level of VDSO
     functionality.

   - Make the NTP user space interface more robust by restricting the
     TAI offset to prevent undefined behaviour. Includes a selftest.

   - Validate user input in the compat settimeofday() syscall to catch
     invalid values which would be turned into valid values by a
     multiplication overflow

   - Consolidate the time accessors

   - Small fixes, improvements and cleanups all over the place

  Drivers:

   - Support for the NXP system counter, TI davinci timer

   - Move the Microsoft HyperV clocksource/events code into the
     drivers/clocksource directory so it can be shared between x86 and
     ARM64.

   - Overhaul of the Tegra driver

   - Delay timer support for IXP4xx

   - Small fixes, improvements and cleanups as usual"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits)
  time: Validate user input in compat_settimeofday()
  timer: Document TIMER_PINNED
  clocksource/drivers: Continue making Hyper-V clocksource ISA agnostic
  clocksource/drivers: Make Hyper-V clocksource ISA agnostic
  MAINTAINERS: Fix Andy's surname and the directory entries of VDSO
  hrtimer: Use a bullet for the returns bullet list
  arm64: vdso: Fix compilation with clang older than 8
  arm64: compat: Fix __arch_get_hw_counter() implementation
  arm64: Fix __arch_get_hw_counter() implementation
  lib/vdso: Make delta calculation work correctly
  MAINTAINERS: Add entry for the generic VDSO library
  arm64: compat: No need for pre-ARMv7 barriers on an ARMv8 system
  arm64: vdso: Remove unnecessary asm-offsets.c definitions
  vdso: Remove superfluous #ifdef __KERNEL__ in vdso/datapage.h
  clocksource/drivers/davinci: Add support for clocksource
  clocksource/drivers/davinci: Add support for clockevents
  clocksource/drivers/tegra: Set up maximum-ticks limit properly
  clocksource/drivers/tegra: Cycles can't be 0
  clocksource/drivers/tegra: Restore base address before cleanup
  clocksource/drivers/tegra: Add verbose definition for 1MHz constant
  ...

7 files changed, 330 insertions, 146 deletions

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index cdf44aa9a501..af78cd72b8f3 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_STATUS_INVALID_CONNECTION_ID		18
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
 
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
 typedef struct _HV_REFERENCE_TSC_PAGE {
 	__u32 tsc_sequence;
 	__u32 res1;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cc60e617931c..f4fa8a9d5d0b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -105,6 +105,17 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 #define hv_get_crash_ctl(val) \
 	rdmsrl(HV_X64_MSR_CRASH_CTL, val)
 
+#define hv_get_time_ref_count(val) \
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, val)
+
+#define hv_get_reference_tsc(val) \
+	rdmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_reference_tsc(val) \
+	wrmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_clocksource_vdso(val) \
+	((val).archdata.vclock_mode = VCLOCK_HVCLOCK)
+#define hv_get_raw_timer() rdtsc_ordered()
+
 void hyperv_callback_vector(void);
 void hyperv_reenlightenment_vector(void);
 #ifdef CONFIG_TRACING
@@ -133,7 +144,6 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 
 
 #if IS_ENABLED(CONFIG_HYPERV)
-extern struct clocksource *hyperv_cs;
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
 
@@ -387,73 +397,4 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 }
 #endif /* CONFIG_HYPERV */
 
-#ifdef CONFIG_HYPERV_TSCPAGE
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
-				       u64 *cur_tsc)
-{
-	u64 scale, offset;
-	u32 sequence;
-
-	/*
-	 * The protocol for reading Hyper-V TSC page is specified in Hypervisor
-	 * Top-Level Functional Specification ver. 3.0 and above. To get the
-	 * reference time we must do the following:
-	 * - READ ReferenceTscSequence
-	 *   A special '0' value indicates the time source is unreliable and we
-	 *   need to use something else. The currently published specification
-	 *   versions (up to 4.0b) contain a mistake and wrongly claim '-1'
-	 *   instead of '0' as the special value, see commit c35b82ef0294.
-	 * - ReferenceTime =
-	 *        ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
-	 * - READ ReferenceTscSequence again. In case its value has changed
-	 *   since our first reading we need to discard ReferenceTime and repeat
-	 *   the whole sequence as the hypervisor was updating the page in
-	 *   between.
-	 */
-	do {
-		sequence = READ_ONCE(tsc_pg->tsc_sequence);
-		if (!sequence)
-			return U64_MAX;
-		/*
-		 * Make sure we read sequence before we read other values from
-		 * TSC page.
-		 */
-		smp_rmb();
-
-		scale = READ_ONCE(tsc_pg->tsc_scale);
-		offset = READ_ONCE(tsc_pg->tsc_offset);
-		*cur_tsc = rdtsc_ordered();
-
-		/*
-		 * Make sure we read sequence after we read all other values
-		 * from TSC page.
-		 */
-		smp_rmb();
-
-	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
-
-	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
-}
-
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
-	u64 cur_tsc;
-
-	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
-}
-
-#else
-static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
-	return NULL;
-}
-
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
-				       u64 *cur_tsc)
-{
-	BUG();
-	return U64_MAX;
-}
-#endif
 #endif
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index b6033680d458..19b695ff2c68 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PVCLOCK_H
 #define _ASM_X86_PVCLOCK_H
 
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
 #include <asm/pvclock-abi.h>
 
 /* some helper functions for xen and kvm pv clock sources */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..ae91429129a6
--- /dev/null
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * Copyright (C) 2019 ARM Limited.
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <asm/pvclock.h>
+#include <clocksource/hyperv_timer.h>
+
+#define __vdso_data (VVAR(_vdso_data))
+
+#define VDSO_HAS_TIME 1
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+/*
+ * Declare the memory-mapped vclock data pages.  These come from hypervisors.
+ * If we ever reintroduce something like direct access to an MMIO clock like
+ * the HPET again, it will go here as well.
+ *
+ * A load from any of these pages will segfault if the clock in question is
+ * disabled, so appropriate compiler barriers and checks need to be used
+ * to prevent stray loads.
+ *
+ * These declarations MUST NOT be const.  The compiler will assume that
+ * an extern const variable has genuinely constant contents, and the
+ * resulting code won't work, since the whole point is that these pages
+ * change over time, possibly while we're accessing them.
+ */
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+/*
+ * This is the vCPU 0 pvclock page.  We only use pvclock from the vDSO
+ * if the hypervisor tells us that all vCPUs can get valid data from the
+ * vCPU 0 page.
+ */
+extern struct pvclock_vsyscall_time_info pvclock_page
+	__attribute__((visibility("hidden")));
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern struct ms_hyperv_tsc_page hvclock_page
+	__attribute__((visibility("hidden")));
+#endif
+
+#ifndef BUILD_VDSO32
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+	     "0" (__NR_clock_gettime), "D" (_clkid), "S" (_ts) :
+	     "rcx", "r11");
+
+	return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			   struct timezone *_tz)
+{
+	long ret;
+
+	asm("syscall" : "=a" (ret) :
+	    "0" (__NR_gettimeofday), "D" (_tv), "S" (_tz) : "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+	     "0" (__NR_clock_getres), "D" (_clkid), "S" (_ts) :
+	     "rcx", "r11");
+
+	return ret;
+}
+
+#else
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm (
+		"mov %%ebx, %%edx \n"
+		"mov %[clock], %%ebx \n"
+		"call __kernel_vsyscall \n"
+		"mov %%edx, %%ebx \n"
+		: "=a" (ret), "=m" (*_ts)
+		: "0" (__NR_clock_gettime64), [clock] "g" (_clkid), "c" (_ts)
+		: "edx");
+
+	return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			   struct timezone *_tz)
+{
+	long ret;
+
+	asm(
+		"mov %%ebx, %%edx \n"
+		"mov %2, %%ebx \n"
+		"call __kernel_vsyscall \n"
+		"mov %%edx, %%ebx \n"
+		: "=a" (ret)
+		: "0" (__NR_gettimeofday), "g" (_tv), "c" (_tz)
+		: "memory", "edx");
+
+	return ret;
+}
+
+static __always_inline long
+clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	long ret;
+
+	asm (
+		"mov %%ebx, %%edx \n"
+		"mov %[clock], %%ebx \n"
+		"call __kernel_vsyscall \n"
+		"mov %%edx, %%ebx \n"
+		: "=a" (ret), "=m" (*_ts)
+		: "0" (__NR_clock_getres_time64), [clock] "g" (_clkid), "c" (_ts)
+		: "edx");
+
+	return ret;
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+static u64 vread_pvclock(void)
+{
+	const struct pvclock_vcpu_time_info *pvti = &pvclock_page.pvti;
+	u32 version;
+	u64 ret;
+
+	/*
+	 * Note: The kernel and hypervisor must guarantee that cpu ID
+	 * number maps 1:1 to per-CPU pvclock time info.
+	 *
+	 * Because the hypervisor is entirely unaware of guest userspace
+	 * preemption, it cannot guarantee that per-CPU pvclock time
+	 * info is updated if the underlying CPU changes or that that
+	 * version is increased whenever underlying CPU changes.
+	 *
+	 * On KVM, we are guaranteed that pvti updates for any vCPU are
+	 * atomic as seen by *all* vCPUs.  This is an even stronger
+	 * guarantee than we get with a normal seqlock.
+	 *
+	 * On Xen, we don't appear to have that guarantee, but Xen still
+	 * supplies a valid seqlock using the version field.
+	 *
+	 * We only do pvclock vdso timing at all if
+	 * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+	 * mean that all vCPUs have matching pvti and that the TSC is
+	 * synced, so we can just look at vCPU 0's pvti.
+	 */
+
+	do {
+		version = pvclock_read_begin(pvti);
+
+		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+			return U64_MAX;
+
+		ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
+	} while (pvclock_read_retry(pvti, version));
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+static u64 vread_hvclock(void)
+{
+	return hv_read_tsc_page(&hvclock_page);
+}
+#endif
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+	if (clock_mode == VCLOCK_TSC)
+		return (u64)rdtsc_ordered();
+	/*
+	 * For any memory-mapped vclock type, we need to make sure that gcc
+	 * doesn't cleverly hoist a load before the mode check.  Otherwise we
+	 * might end up touching the memory-mapped page even if the vclock in
+	 * question isn't enabled, which will segfault.  Hence the barriers.
+	 */
+#ifdef CONFIG_PARAVIRT_CLOCK
+	if (clock_mode == VCLOCK_PVCLOCK) {
+		barrier();
+		return vread_pvclock();
+	}
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+	if (clock_mode == VCLOCK_HVCLOCK) {
+		barrier();
+		return vread_hvclock();
+	}
+#endif
+	return U64_MAX;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return __vdso_data;
+}
+
+/*
+ * x86 specific delta calculation.
+ *
+ * The regular implementation assumes that clocksource reads are globally
+ * monotonic. The TSC can be slightly off across sockets which can cause
+ * the regular delta calculation (@cycles - @last) to return a huge time
+ * jump.
+ *
+ * Therefore it needs to be verified that @cycles are greater than
+ * @last. If not then use @last, which is the base time of the current
+ * conversion period.
+ *
+ * This variant also removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on x86 is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+static __always_inline
+u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+	if (cycles > last)
+		return (cycles - last) * mult;
+	return 0;
+}
+#define vdso_calc_delta vdso_calc_delta
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..0026ab2123ce
--- /dev/null
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+int vclocks_used __read_mostly;
+
+DEFINE_VVAR(struct vdso_data, _vdso_data);
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__x86_get_k_vdso_data(void)
+{
+	return _vdso_data;
+}
+#define __arch_get_k_vdso_data __x86_get_k_vdso_data
+
+static __always_inline
+int __x86_get_clock_mode(struct timekeeper *tk)
+{
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
+	return vclock_mode;
+}
+#define __arch_get_clock_mode __x86_get_clock_mode
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 913a133f8e6f..a2638c6124ed 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -3,7 +3,9 @@
 #define _ASM_X86_VGTOD_H
 
 #include <linux/compiler.h>
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
 
 #include <uapi/linux/time.h>
 
@@ -13,81 +15,10 @@ typedef u64 gtod_long_t;
 typedef unsigned long gtod_long_t;
 #endif
 
-/*
- * There is one of these objects in the vvar page for each
- * vDSO-accelerated clockid.  For high-resolution clocks, this encodes
- * the time corresponding to vsyscall_gtod_data.cycle_last.  For coarse
- * clocks, this encodes the actual time.
- *
- * To confuse the reader, for high-resolution clocks, nsec is left-shifted
- * by vsyscall_gtod_data.shift.
- */
-struct vgtod_ts {
-	u64		sec;
-	u64		nsec;
-};
-
-#define VGTOD_BASES	(CLOCK_TAI + 1)
-#define VGTOD_HRES	(BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
-#define VGTOD_COARSE	(BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
-
-/*
- * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
- * so be carefull by modifying this structure.
- */
-struct vsyscall_gtod_data {
-	unsigned int	seq;
-
-	int		vclock_mode;
-	u64		cycle_last;
-	u64		mask;
-	u32		mult;
-	u32		shift;
-
-	struct vgtod_ts	basetime[VGTOD_BASES];
-
-	int		tz_minuteswest;
-	int		tz_dsttime;
-};
-extern struct vsyscall_gtod_data vsyscall_gtod_data;
-
 extern int vclocks_used;
 static inline bool vclock_was_used(int vclock)
 {
 	return READ_ONCE(vclocks_used) & (1 << vclock);
 }
 
-static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
-{
-	unsigned int ret;
-
-repeat:
-	ret = READ_ONCE(s->seq);
-	if (unlikely(ret & 1)) {
-		cpu_relax();
-		goto repeat;
-	}
-	smp_rmb();
-	return ret;
-}
-
-static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
-				  unsigned int start)
-{
-	smp_rmb();
-	return unlikely(s->seq != start);
-}
-
-static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
-{
-	++s->seq;
-	smp_wmb();
-}
-
-static inline void gtod_write_end(struct vsyscall_gtod_data *s)
-{
-	smp_wmb();
-	++s->seq;
-}
-
 #endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index e474f5c6e387..32f5d9a0b90e 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -32,19 +32,20 @@
 extern char __vvar_page;
 
 #define DECLARE_VVAR(offset, type, name)				\
-	extern type vvar_ ## name __attribute__((visibility("hidden")));
+	extern type vvar_ ## name[CS_BASES]				\
+	__attribute__((visibility("hidden")));
 
 #define VVAR(name) (vvar_ ## name)
 
 #define DEFINE_VVAR(type, name)						\
-	type name							\
+	type name[CS_BASES]						\
 	__attribute__((section(".vvar_" #name), aligned(16))) __visible
 
 #endif
 
 /* DECLARE_VVAR(offset, type, name) */
 
-DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
+DECLARE_VVAR(128, struct vdso_data, _vdso_data)
 
 #undef DECLARE_VVAR