s390: convert to GENERIC_VDSO

Convert s390 to generic vDSO. There are a few special things on s390:

- vDSO can be called without a stack frame - glibc did this in the past.
  So we need to allocate a stackframe on our own.

- The former assembly code used stcke to get the TOD clock and applied
  time steering to it. We need to do the same in the new code. This is done
  in the architecture specific __arch_get_hw_counter function. The steering
  information is stored in an architecure specific area in the vDSO data.

- CPUCLOCK_VIRT is now handled with a syscall fallback, which might
  be slower/less accurate than the old implementation.

The getcpu() function stays as an assembly function because there is no
generic implementation and the code is just a few lines.

Performance number from my system do 100 mio gettimeofday() calls:

Plain syscall: 8.6s
Generic VDSO:  1.3s
old ASM VDSO:  1s

So it's a bit slower but still much faster than syscalls.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

arch/s390/Kconfig

@@ -73,6 +73,7 @@ config S390
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_VDSO_DATA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
 	select ARCH_INLINE_READ_LOCK_BH
@@ -118,6 +119,7 @@ config S390
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_GETTIMEOFDAY
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
@@ -149,6 +151,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_VDSO
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4

arch/s390/include/asm/clocksource.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* s390-specific clocksource additions */
+
+#ifndef _ASM_S390_CLOCKSOURCE_H
+#define _ASM_S390_CLOCKSOURCE_H
+
+#endif /* _ASM_S390_CLOCKSOURCE_H */

arch/s390/include/asm/vdso.h

@@ -2,6 +2,8 @@
 #ifndef __S390_VDSO_H__
 #define __S390_VDSO_H__
 
+#include <vdso/datapage.h>
+
 /* Default link addresses for the vDSOs */
 #define VDSO32_LBASE	0
 #define VDSO64_LBASE	0
@@ -18,30 +20,7 @@
  * itself and may change without notice.
  */
 
-struct vdso_data {
-	__u64 tb_update_count;		/* Timebase atomicity ctr	0x00 */
-	__u64 xtime_tod_stamp;		/* TOD clock for xtime		0x08 */
-	__u64 xtime_clock_sec;		/* Kernel time			0x10 */
-	__u64 xtime_clock_nsec;		/*				0x18 */
-	__u64 xtime_coarse_sec;		/* Coarse kernel time		0x20 */
-	__u64 xtime_coarse_nsec;	/*				0x28 */
-	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x30 */
-	__u64 wtom_clock_nsec;		/*				0x38 */
-	__u64 wtom_coarse_sec;		/* Coarse wall to monotonic	0x40 */
-	__u64 wtom_coarse_nsec;		/*				0x48 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x50 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x54 */
-	__u32 ectg_available;		/* ECTG instruction present	0x58 */
-	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x5c */
-	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
-	__u32 ts_dir;			/* TOD steering direction	0x64 */
-	__u64 ts_end;			/* TOD steering end		0x68 */
-	__u32 hrtimer_res;		/* hrtimer resolution		0x70 */
-};
-
 struct vdso_per_cpu_data {
-	__u64 ectg_timer_base;
-	__u64 ectg_user_time;
 	/*
 	 * Note: node_id and cpu_nr must be at adjacent memory locations.
 	 * VDSO userspace must read both values with a single instruction.

arch/s390/include/asm/vdso/clocksource.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_CLOCKSOURCE_H
+#define __ASM_VDSO_CLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES	\
+	VDSO_CLOCKMODE_TOD
+
+#endif /* __ASM_VDSO_CLOCKSOURCE_H */

arch/s390/include/asm/vdso/data.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __S390_ASM_VDSO_DATA_H
+#define __S390_ASM_VDSO_DATA_H
+
+#include <linux/types.h>
+#include <vdso/datapage.h>
+
+struct arch_vdso_data {
+	__u64 tod_steering_delta;
+	__u64 tod_steering_end;
+};
+
+#endif /* __S390_ASM_VDSO_DATA_H */

arch/s390/include/asm/vdso/gettimeofday.h

@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_VDSO_GETTIMEOFDAY_H
+#define ASM_VDSO_GETTIMEOFDAY_H
+
+#define VDSO_HAS_TIME 1
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+#include <asm/timex.h>
+#include <asm/unistd.h>
+#include <asm/vdso.h>
+#include <linux/compiler.h>
+
+#define vdso_calc_delta __arch_vdso_calc_delta
+static __always_inline u64 __arch_vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+	return (cycles - last) * mult;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd)
+{
+	const struct vdso_data *vdso = __arch_get_vdso_data();
+	u64 adj, now;
+
+	now = get_tod_clock();
+	adj = vdso->arch_data.tod_steering_end - now;
+	if (unlikely((s64) adj > 0))
+		now += (vdso->arch_data.tod_steering_delta < 0) ? (adj >> 15) : -(adj >> 15);
+	return now;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t clkid, struct __kernel_timespec *ts)
+{
+	register unsigned long r1 __asm__("r1") = __NR_clock_gettime;
+	register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
+	register void *r3 __asm__("r3") = ts;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+static __always_inline
+long gettimeofday_fallback(register struct __kernel_old_timeval *tv,
+			   register struct timezone *tz)
+{
+	register unsigned long r1 __asm__("r1") = __NR_gettimeofday;
+	register unsigned long r2 __asm__("r2") = (unsigned long)tv;
+	register void *r3 __asm__("r3") = tz;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+static __always_inline
+long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
+{
+	register unsigned long r1 __asm__("r1") = __NR_clock_getres;
+	register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
+	register void *r3 __asm__("r3") = ts;
+
+	asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
+	return r2;
+}
+
+#endif

arch/s390/include/asm/vdso/processor.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#define cpu_relax() barrier()
+
+#endif /* __ASM_VDSO_PROCESSOR_H */

arch/s390/include/asm/vdso/vsyscall.h

@@ -0,0 +1,26 @@
+/* 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/vdso.h>
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+
+static __always_inline struct vdso_data *__s390_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+#define __arch_get_k_vdso_data __s390_get_k_vdso_data
+
+/* 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 */

arch/s390/kernel/asm-offsets.c

@@ -59,26 +59,6 @@ int main(void)
 	OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
 	OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]);
 	BLANK();
-	/* timeval/timezone offsets for use by vdso */
-	OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count);
-	OFFSET(__VDSO_XTIME_STAMP, vdso_data, xtime_tod_stamp);
-	OFFSET(__VDSO_XTIME_SEC, vdso_data, xtime_clock_sec);
-	OFFSET(__VDSO_XTIME_NSEC, vdso_data, xtime_clock_nsec);
-	OFFSET(__VDSO_XTIME_CRS_SEC, vdso_data, xtime_coarse_sec);
-	OFFSET(__VDSO_XTIME_CRS_NSEC, vdso_data, xtime_coarse_nsec);
-	OFFSET(__VDSO_WTOM_SEC, vdso_data, wtom_clock_sec);
-	OFFSET(__VDSO_WTOM_NSEC, vdso_data, wtom_clock_nsec);
-	OFFSET(__VDSO_WTOM_CRS_SEC, vdso_data, wtom_coarse_sec);
-	OFFSET(__VDSO_WTOM_CRS_NSEC, vdso_data, wtom_coarse_nsec);
-	OFFSET(__VDSO_TIMEZONE, vdso_data, tz_minuteswest);
-	OFFSET(__VDSO_ECTG_OK, vdso_data, ectg_available);
-	OFFSET(__VDSO_TK_MULT, vdso_data, tk_mult);
-	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
-	OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
-	OFFSET(__VDSO_TS_END, vdso_data, ts_end);
-	OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
-	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
-	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
 	BLANK();
 	/* constants used by the vdso */

arch/s390/kernel/entry.S

@@ -435,10 +435,8 @@ ENTRY(system_call)
 	jz	.Lsysc_skip_fpu
 	brasl	%r14,load_fpu_regs
 .Lsysc_skip_fpu:
-	lg	%r14,__LC_VDSO_PER_CPU
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r0,%r15,__PT_R0(%r11)
 	b	__LC_RETURN_LPSWE
 
@@ -797,13 +795,11 @@ ENTRY(io_int_handler)
 	TRACE_IRQS_ON
 0:
 #endif
-	lg	%r14,__LC_VDSO_PER_CPU
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jno	.Lio_exit_kernel
 	BPEXIT	__TI_flags(%r12),_TIF_ISOLATE_BP
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 .Lio_exit_kernel:
 	lmg	%r0,%r15,__PT_R0(%r11)
 	b	__LC_RETURN_LPSWE
@@ -1213,14 +1209,12 @@ ENTRY(mcck_int_handler)
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
 .Lmcck_return:
-	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
 	BPEXIT	__TI_flags(%r12),_TIF_ISOLATE_BP
 	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 0:	lmg	%r11,%r15,__PT_R11(%r11)
 	b	__LC_RETURN_MCCK_LPSWE
 

arch/s390/kernel/setup.c

@@ -402,7 +402,6 @@ static void __init setup_lowcore_dat_off(void)
 	memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
 	       sizeof(lc->alt_stfle_fac_list));
 	nmi_alloc_boot_cpu(lc);
-	vdso_alloc_boot_cpu(lc);
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
 	lc->async_enter_timer = S390_lowcore.async_enter_timer;
 	lc->exit_timer = S390_lowcore.exit_timer;