Merge tag 'timers-vdso-2025-03-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull VDSO infrastructure updates from Thomas Gleixner:

 - Consolidate the VDSO storage

   The VDSO data storage and data layout has been largely architecture
   specific for historical reasons. That increases the maintenance
   effort and causes inconsistencies over and over.

   There is no real technical reason for architecture specific layouts
   and implementations. The architecture specific details can easily be
   integrated into a generic layout, which also reduces the amount of
   duplicated code for managing the mappings.

   Convert all architectures over to a unified layout and common mapping
   infrastructure. This splits the VDSO data layout into subsystem
   specific blocks, timekeeping, random and architecture parts, which
   provides a better structure and allows to improve and update the
   functionalities without conflict and interaction.

 - Rework the timekeeping data storage

   The current implementation is designed for exposing system
   timekeeping accessors, which was good enough at the time when it was
   designed.

   PTP and Time Sensitive Networking (TSN) change that as there are
   requirements to expose independent PTP clocks, which are not related
   to system timekeeping.

   Replace the monolithic data storage by a structured layout, which
   allows to add support for independent PTP clocks on top while reusing
   both the data structures and the time accessor implementations.

* tag 'timers-vdso-2025-03-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  sparc/vdso: Always reject undefined references during linking
  x86/vdso: Always reject undefined references during linking
  vdso: Rework struct vdso_time_data and introduce struct vdso_clock
  vdso: Move architecture related data before basetime data
  powerpc/vdso: Prepare introduction of struct vdso_clock
  arm64/vdso: Prepare introduction of struct vdso_clock
  x86/vdso: Prepare introduction of struct vdso_clock
  time/namespace: Prepare introduction of struct vdso_clock
  vdso/namespace: Rename timens_setup_vdso_data() to reflect new vdso_clock struct
  vdso/vsyscall: Prepare introduction of struct vdso_clock
  vdso/gettimeofday: Prepare helper functions for introduction of struct vdso_clock
  vdso/gettimeofday: Prepare do_coarse_timens() for introduction of struct vdso_clock
  vdso/gettimeofday: Prepare do_coarse() for introduction of struct vdso_clock
  vdso/gettimeofday: Prepare do_hres_timens() for introduction of struct vdso_clock
  vdso/gettimeofday: Prepare do_hres() for introduction of struct vdso_clock
  vdso/gettimeofday: Prepare introduction of struct vdso_clock
  vdso/helpers: Prepare introduction of struct vdso_clock
  vdso/datapage: Define vdso_clock to prepare for multiple PTP clocks
  vdso: Make vdso_time_data cacheline aligned
  arm64: Make asm/cache.h compatible with vDSO
  ...

2 files changed, 46 insertions, 44 deletions

diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 0775b9ec952a..e3642278df43 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -165,26 +165,26 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
  *     HVCLOCK
  *     VVAR
  *
- * The check for vdso_data->clock_mode is in the unlikely path of
+ * The check for vdso_clock->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
+ * for vdso_clock->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 VDSO_CLOCKMODE_TIMENS which
+ * Timens page has vdso_clock->clock_mode set to VDSO_CLOCKMODE_TIMENS which
  * enforces the time namespace handling path.
  */
-static void timens_setup_vdso_data(struct vdso_data *vdata,
-				   struct time_namespace *ns)
+static void timens_setup_vdso_clock_data(struct vdso_clock *vc,
+					 struct time_namespace *ns)
 {
-	struct timens_offset *offset = vdata->offset;
+	struct timens_offset *offset = vc->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		= VDSO_CLOCKMODE_TIMENS;
+	vc->seq				= 1;
+	vc->clock_mode			= VDSO_CLOCKMODE_TIMENS;
 	offset[CLOCK_MONOTONIC]		= monotonic;
 	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
 	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
@@ -219,7 +219,8 @@ static DEFINE_MUTEX(offset_lock);
 static void timens_set_vvar_page(struct task_struct *task,
 				struct time_namespace *ns)
 {
-	struct vdso_data *vdata;
+	struct vdso_time_data *vdata;
+	struct vdso_clock *vc;
 	unsigned int i;
 
 	if (ns == &init_time_ns)
@@ -235,10 +236,11 @@ static void timens_set_vvar_page(struct task_struct *task,
 		goto out;
 
 	ns->frozen_offsets = true;
-	vdata = arch_get_vdso_data(page_address(ns->vvar_page));
+	vdata = page_address(ns->vvar_page);
+	vc = vdata->clock_data;
 
 	for (i = 0; i < CS_BASES; i++)
-		timens_setup_vdso_data(&vdata[i], ns);
+		timens_setup_vdso_clock_data(&vc[i], ns);
 
 out:
 	mutex_unlock(&offset_lock);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 05d383143165..01c2ab1e8971 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -15,29 +15,29 @@
 
 #include "timekeeping_internal.h"
 
-static inline void update_vdso_data(struct vdso_data *vdata,
-				    struct timekeeper *tk)
+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;
 	u64 nsec, sec;
 
-	vdata[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
+	vc[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-	vdata[CS_HRES_COARSE].max_cycles	= tk->tkr_mono.clock->max_cycles;
+	vc[CS_HRES_COARSE].max_cycles	= tk->tkr_mono.clock->max_cycles;
 #endif
-	vdata[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
-	vdata[CS_HRES_COARSE].mult		= tk->tkr_mono.mult;
-	vdata[CS_HRES_COARSE].shift		= tk->tkr_mono.shift;
-	vdata[CS_RAW].cycle_last		= tk->tkr_raw.cycle_last;
+	vc[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
+	vc[CS_HRES_COARSE].mult		= tk->tkr_mono.mult;
+	vc[CS_HRES_COARSE].shift	= tk->tkr_mono.shift;
+	vc[CS_RAW].cycle_last		= tk->tkr_raw.cycle_last;
 #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
-	vdata[CS_RAW].max_cycles		= tk->tkr_raw.clock->max_cycles;
+	vc[CS_RAW].max_cycles		= tk->tkr_raw.clock->max_cycles;
 #endif
-	vdata[CS_RAW].mask			= tk->tkr_raw.mask;
-	vdata[CS_RAW].mult			= tk->tkr_raw.mult;
-	vdata[CS_RAW].shift			= tk->tkr_raw.shift;
+	vc[CS_RAW].mask			= tk->tkr_raw.mask;
+	vc[CS_RAW].mult			= tk->tkr_raw.mult;
+	vc[CS_RAW].shift		= tk->tkr_raw.shift;
 
 	/* CLOCK_MONOTONIC */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 
 	nsec = tk->tkr_mono.xtime_nsec;
@@ -55,7 +55,7 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
 
 	/* CLOCK_BOOTTIME */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
 	vdso_ts->sec	= sec;
 
 	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
@@ -65,19 +65,20 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 	vdso_ts->nsec	= nsec;
 
 	/* CLOCK_MONOTONIC_RAW */
-	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+	vdso_ts		= &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
 	vdso_ts->sec	= tk->raw_sec;
 	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
 
 	/* CLOCK_TAI */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_TAI];
 	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
 }
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_clock *vc = vdata->clock_data;
 	struct vdso_timestamp *vdso_ts;
 	s32 clock_mode;
 	u64 nsec;
@@ -86,21 +87,21 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_write_begin(vdata);
 
 	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
-	vdata[CS_HRES_COARSE].clock_mode	= clock_mode;
-	vdata[CS_RAW].clock_mode		= clock_mode;
+	vc[CS_HRES_COARSE].clock_mode	= clock_mode;
+	vc[CS_RAW].clock_mode		= clock_mode;
 
 	/* CLOCK_REALTIME also required for time() */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
+	vdso_ts		= &vc[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		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
 	vdso_ts->sec	= tk->xtime_sec;
 	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 
 	/* CLOCK_MONOTONIC_COARSE */
-	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 	nsec		= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
@@ -108,32 +109,31 @@ 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
 	 * update of the high resolution parts.
 	 */
 	if (clock_mode != VDSO_CLOCKMODE_NONE)
-		update_vdso_data(vdata, tk);
+		update_vdso_time_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata);
 
 	vdso_write_end(vdata);
 
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 }
 
 void update_vsyscall_tz(void)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_time_data *vdata = vdso_k_time_data;
 
-	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
-	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
+	vdata->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata->tz_dsttime = sys_tz.tz_dsttime;
 
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 }
 
 /**
@@ -150,7 +150,7 @@ void update_vsyscall_tz(void)
  */
 unsigned long vdso_update_begin(void)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_time_data *vdata = vdso_k_time_data;
 	unsigned long flags = timekeeper_lock_irqsave();
 
 	vdso_write_begin(vdata);
@@ -167,9 +167,9 @@ unsigned long vdso_update_begin(void)
  */
 void vdso_update_end(unsigned long flags)
 {
-	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	struct vdso_time_data *vdata = vdso_k_time_data;
 
 	vdso_write_end(vdata);
-	__arch_sync_vdso_data(vdata);
+	__arch_sync_vdso_time_data(vdata);
 	timekeeper_unlock_irqrestore(flags);
 }