vdso: Rework struct vdso_time_data and introduce struct vdso_clock

To support multiple PTP clocks, the VDSO data structure needs to be
reworked. All clock specific data will end up in struct vdso_clock and in
struct vdso_time_data there will be an array of VDSO clocks.

Now that all preparatory changes are in place:

Split the clock related struct members into a separate struct
vdso_clock. Make sure all users are aware, that vdso_time_data is no longer
initialized as an array and vdso_clock is now the array inside
vdso_data. Remove the vdso_clock define, which mapped it to vdso_time_data
for the transition.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250303-vdso-clock-v1-19-c1b5c69a166f@linutronix.de

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -149,7 +149,7 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 	 * where __aarch64_get_vdso_u_time_data() is called, and then keep the
 	 * result in a register.
 	 */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(vdso_u_time_data));
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(&vdso_u_time_data));
 
 	return ret;
 }

arch/arm64/include/asm/vdso/vsyscall.h

@@ -15,8 +15,8 @@
 static __always_inline
 void __arm64_update_vsyscall(struct vdso_time_data *vdata)
 {
-	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
-	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_RAW].mask		= VDSO_PRECISION_MASK;
 }
 #define __arch_update_vsyscall __arm64_update_vsyscall
 

arch/s390/kernel/time.c

@@ -79,12 +79,10 @@ void __init time_early_init(void)
 {
 	struct ptff_qto qto;
 	struct ptff_qui qui;
-	int cs;
 
 	/* Initialize TOD steering parameters */
 	tod_steering_end = tod_clock_base.tod;
-	for (cs = 0; cs < CS_BASES; cs++)
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
-		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -373,7 +371,6 @@ static void clock_sync_global(long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
-	int cs;
 
 	/* Fixup the monotonic sched clock. */
 	tod_clock_base.eitod += delta;
@@ -389,10 +386,8 @@ static void clock_sync_global(long delta)
 		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
-	for (cs = 0; cs < CS_BASES; cs++) {
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
-		vdso_k_time_data[cs].arch_data.tod_steering_end = tod_steering_end;
+	vdso_k_time_data->arch_data.tod_steering_delta = tod_steering_delta;
-		vdso_k_time_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
-	}
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)

include/asm-generic/vdso/vsyscall.h

@@ -9,7 +9,7 @@
 #ifndef __arch_get_vdso_u_time_data
 static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return vdso_u_time_data;
+	return &vdso_u_time_data;
 }
 #endif
 

include/vdso/datapage.h

@@ -69,9 +69,7 @@ struct vdso_timestamp {
 };
 
 /**
- * struct vdso_time_data - vdso datapage representation
+ * struct vdso_clock - vdso per clocksource datapage representation
- * @arch_data:		architecture specific data (optional, defaults
- *			to an empty struct)
  * @seq:		timebase sequence counter
  * @clock_mode:		clock mode
  * @cycle_last:		timebase at clocksource init
@@ -81,17 +79,9 @@ struct vdso_timestamp {
  * @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
- * @__unused:		unused
  *
- * vdso_time_data will be accessed by 64 bit and compat code at the same time
+ * See also struct vdso_time_data for basic access and ordering information as
- * so we should be careful before modifying this structure.
+ * struct vdso_clock is used there.
- *
- * The ordering of the struct members is optimized to have fast access to the
- * often required struct members which are related to CLOCK_REALTIME and
- * CLOCK_MONOTONIC. This information is stored in the first cache lines.
  *
  * @basetime is used to store the base time for the system wide time getter
  * VVAR page.
@@ -104,9 +94,7 @@ struct vdso_timestamp {
  * For clocks which are not affected by time namespace adjustment the
  * offset must be zero.
  */
-struct vdso_time_data {
+struct vdso_clock {
-	struct arch_vdso_time_data arch_data;
-
 	u32			seq;
 
 	s32			clock_mode;
@@ -122,15 +110,36 @@ struct vdso_time_data {
 		struct vdso_timestamp	basetime[VDSO_BASES];
 		struct timens_offset	offset[VDSO_BASES];
 	};
+};
 
-	s32			tz_minuteswest;
+/**
-	s32			tz_dsttime;
+ * struct vdso_time_data - vdso datapage representation
-	u32			hrtimer_res;
+ * @arch_data:		architecture specific data (optional, defaults
-	u32			__unused;
+ *			to an empty struct)
+ * @clock_data:		clocksource related data (array)
+ * @tz_minuteswest:	minutes west of Greenwich
+ * @tz_dsttime:		type of DST correction
+ * @hrtimer_res:	hrtimer resolution
+ * @__unused:		unused
+ *
+ * vdso_time_data will be accessed by 64 bit and compat code at the same time
+ * so we should be careful before modifying this structure.
+ *
+ * The ordering of the struct members is optimized to have fast acces to the
+ * often required struct members which are related to CLOCK_REALTIME and
+ * CLOCK_MONOTONIC. This information is stored in the first cache lines.
+ */
+struct vdso_time_data {
+	struct arch_vdso_time_data	arch_data;
+
+	struct vdso_clock		clock_data[CS_BASES];
+
+	s32				tz_minuteswest;
+	s32				tz_dsttime;
+	u32				hrtimer_res;
+	u32				__unused;
 } ____cacheline_aligned;
 
-#define vdso_clock vdso_time_data
-
 /**
  * struct vdso_rng_data - vdso RNG state information
  * @generation:	counter representing the number of RNG reseeds
@@ -151,7 +160,7 @@ struct vdso_rng_data {
  * relocation, and this is what we need.
  */
 #ifdef CONFIG_GENERIC_VDSO_DATA_STORE
-extern struct vdso_time_data vdso_u_time_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_time_data vdso_u_time_data __attribute__((visibility("hidden")));
 extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
 extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden")));
 

include/vdso/helpers.h

@@ -30,7 +30,7 @@ static __always_inline u32 vdso_read_retry(const struct vdso_clock *vc,
 
 static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 {
-	struct vdso_clock *vc = vd;
+	struct vdso_clock *vc = vd->clock_data;
 
 	/*
 	 * WRITE_ONCE() is required otherwise the compiler can validly tear
@@ -44,7 +44,7 @@ static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
 
 static __always_inline void vdso_write_end(struct vdso_time_data *vd)
 {
-	struct vdso_clock *vc = vd;
+	struct vdso_clock *vc = vd->clock_data;
 
 	smp_wmb();
 	/*

kernel/time/namespace.c

@@ -237,7 +237,7 @@ static void timens_set_vvar_page(struct task_struct *task,
 
 	ns->frozen_offsets = true;
 	vdata = page_address(ns->vvar_page);
-	vc = vdata;
+	vc = vdata->clock_data;
 
 	for (i = 0; i < CS_BASES; i++)
 		timens_setup_vdso_clock_data(&vc[i], ns);

kernel/time/vsyscall.c

@@ -17,8 +17,8 @@
 
 static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk)
 {
+	struct vdso_clock *vc = vdata->clock_data;
 	struct vdso_timestamp *vdso_ts;
-	struct vdso_clock *vc = vdata;
 	u64 nsec, sec;
 
 	vc[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
@@ -78,8 +78,8 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 void update_vsyscall(struct timekeeper *tk)
 {
 	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_clock *vc = vdata->clock_data;
 	struct vdso_timestamp *vdso_ts;
-	struct vdso_clock *vc = vdata;
 	s32 clock_mode;
 	u64 nsec;
 
@@ -109,9 +109,8 @@ void update_vsyscall(struct timekeeper *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);
+	WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution);
 
 	/*
 	 * If the current clocksource is not VDSO capable, then spare the
@@ -131,8 +130,8 @@ void update_vsyscall_tz(void)
 {
 	struct vdso_time_data *vdata = vdso_k_time_data;
 
-	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata->tz_minuteswest = sys_tz.tz_minuteswest;
-	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
+	vdata->tz_dsttime = sys_tz.tz_dsttime;
 
 	__arch_sync_vdso_time_data(vdata);
 }

lib/vdso/datastore.c

@@ -13,10 +13,10 @@
  */
 #ifdef CONFIG_HAVE_GENERIC_VDSO
 static union {
-	struct vdso_time_data	data[CS_BASES];
+	struct vdso_time_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_time_data_store __page_aligned_data;
-struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
+struct vdso_time_data *vdso_k_time_data = &vdso_time_data_store.data;
 static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
 #endif /* CONFIG_HAVE_GENERIC_VDSO */
 

lib/vdso/gettimeofday.c

@@ -87,8 +87,8 @@ int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *v
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
+	const struct vdso_clock *vc = vd->clock_data;
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_clock *vc = vd;
 	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
@@ -199,8 +199,8 @@ int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
+	const struct vdso_clock *vc = vd->clock_data;
 	const struct vdso_timestamp *vdso_ts;
-	const struct vdso_clock *vc = vd;
 	u64 nsec;
 	s64 sec;
 	s32 seq;
@@ -265,7 +265,7 @@ static __always_inline int
 __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 
 	/* Check for negative values or invalid clocks */
@@ -337,7 +337,7 @@ static __maybe_unused int
 __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 			  struct __kernel_old_timeval *tv, struct timezone *tz)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 
 	if (likely(tv != NULL)) {
 		struct __kernel_timespec ts;
@@ -371,13 +371,13 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 static __maybe_unused __kernel_old_time_t
 __cvdso_time_data(const struct vdso_time_data *vd, __kernel_old_time_t *time)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	__kernel_old_time_t t;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
 	    vc->clock_mode == VDSO_CLOCKMODE_TIMENS) {
 		vd = __arch_get_vdso_u_timens_data(vd);
-		vc = vd;
+		vc = vd->clock_data;
 	}
 
 	t = READ_ONCE(vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
@@ -399,7 +399,7 @@ static __maybe_unused
 int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
 				struct __kernel_timespec *res)
 {
-	const struct vdso_clock *vc = vd;
+	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 	u64 ns;
 
@@ -420,7 +420,7 @@ int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock
 		/*
 		 * Preserves the behaviour of posix_get_hrtimer_res().
 		 */
-		ns = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
+		ns = READ_ONCE(vd->hrtimer_res);
 	} else if (msk & VDSO_COARSE) {
 		/*
 		 * Preserves the behaviour of posix_get_coarse_res().