powerpc/vdso: Switch VDSO to generic C implementation.

With the C VDSO, the performance is slightly lower, but it is worth
it as it will ease maintenance and evolution, and also brings clocks
that are not supported with the ASM VDSO.

On an 8xx at 132 MHz, vdsotest with the ASM VDSO:
  gettimeofday:    		  vdso:  828 nsec/call
  clock-getres-realtime-coarse:   vdso:  391 nsec/call
  clock-gettime-realtime-coarse:  vdso:  614 nsec/call
  clock-getres-realtime:    	  vdso:  460 nsec/call
  clock-gettime-realtime:    	  vdso:  876 nsec/call
  clock-getres-monotonic-coarse:  vdso:  399 nsec/call
  clock-gettime-monotonic-coarse: vdso:  691 nsec/call
  clock-getres-monotonic:    	  vdso:  460 nsec/call
  clock-gettime-monotonic:    	  vdso: 1026 nsec/call

On an 8xx at 132 MHz, vdsotest with the C VDSO:
  gettimeofday:    		  vdso:  955 nsec/call
  clock-getres-realtime-coarse:   vdso:  545 nsec/call
  clock-gettime-realtime-coarse:  vdso:  592 nsec/call
  clock-getres-realtime:          vdso:  545 nsec/call
  clock-gettime-realtime:    	  vdso:  941 nsec/call
  clock-getres-monotonic-coarse:  vdso:  545 nsec/call
  clock-gettime-monotonic-coarse: vdso:  591 nsec/call
  clock-getres-monotonic:         vdso:  545 nsec/call
  clock-gettime-monotonic:        vdso:  940 nsec/call

It is even better for gettime with monotonic clocks.

Unsupported clocks with ASM VDSO:
  clock-gettime-boottime:         vdso: 3851 nsec/call
  clock-gettime-tai:      	  vdso: 3852 nsec/call
  clock-gettime-monotonic-raw:    vdso: 3396 nsec/call

Same clocks with C VDSO:
  clock-gettime-tai:              vdso:  941 nsec/call
  clock-gettime-monotonic-raw:    vdso: 1001 nsec/call
  clock-gettime-monotonic-coarse: vdso:  591 nsec/call

On an 8321E at 333 MHz, vdsotest with the ASM VDSO:
  gettimeofday:     		  vdso: 220 nsec/call
  clock-getres-realtime-coarse:   vdso: 102 nsec/call
  clock-gettime-realtime-coarse:  vdso: 178 nsec/call
  clock-getres-realtime:          vdso: 129 nsec/call
  clock-gettime-realtime:    	  vdso: 235 nsec/call
  clock-getres-monotonic-coarse:  vdso: 105 nsec/call
  clock-gettime-monotonic-coarse: vdso: 208 nsec/call
  clock-getres-monotonic:         vdso: 129 nsec/call
  clock-gettime-monotonic:        vdso: 274 nsec/call

On an 8321E at 333 MHz, vdsotest with the C VDSO:
  gettimeofday:    		  vdso: 272 nsec/call
  clock-getres-realtime-coarse:   vdso: 160 nsec/call
  clock-gettime-realtime-coarse:  vdso: 184 nsec/call
  clock-getres-realtime:          vdso: 166 nsec/call
  clock-gettime-realtime:         vdso: 281 nsec/call
  clock-getres-monotonic-coarse:  vdso: 160 nsec/call
  clock-gettime-monotonic-coarse: vdso: 184 nsec/call
  clock-getres-monotonic:         vdso: 169 nsec/call
  clock-gettime-monotonic:        vdso: 275 nsec/call

On a Power9 Nimbus DD2.2 at 3.8GHz, with the ASM VDSO:
  clock-gettime-monotonic:    	  vdso:  35 nsec/call
  clock-getres-monotonic:    	  vdso:  16 nsec/call
  clock-gettime-monotonic-coarse: vdso:  18 nsec/call
  clock-getres-monotonic-coarse:  vdso: 522 nsec/call
  clock-gettime-monotonic-raw:    vdso: 598 nsec/call
  clock-getres-monotonic-raw:     vdso: 520 nsec/call
  clock-gettime-realtime:    	  vdso:  34 nsec/call
  clock-getres-realtime:    	  vdso:  16 nsec/call
  clock-gettime-realtime-coarse:  vdso:  18 nsec/call
  clock-getres-realtime-coarse:   vdso: 517 nsec/call
  getcpu:    			  vdso:   8 nsec/call
  gettimeofday:    		  vdso:  25 nsec/call

And with the C VDSO:
  clock-gettime-monotonic:    	  vdso:  37 nsec/call
  clock-getres-monotonic:    	  vdso:  20 nsec/call
  clock-gettime-monotonic-coarse: vdso:  21 nsec/call
  clock-getres-monotonic-coarse:  vdso:  19 nsec/call
  clock-gettime-monotonic-raw:    vdso:  38 nsec/call
  clock-getres-monotonic-raw:     vdso:  20 nsec/call
  clock-gettime-realtime:    	  vdso:  37 nsec/call
  clock-getres-realtime:    	  vdso:  20 nsec/call
  clock-gettime-realtime-coarse:  vdso:  20 nsec/call
  clock-getres-realtime-coarse:   vdso:  19 nsec/call
  getcpu:    			  vdso:   8 nsec/call
  gettimeofday:    		  vdso:  28 nsec/call

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201126131006.2431205-8-mpe@ellerman.id.au

1 files changed, 13 insertions, 27 deletions

diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index b9ef6cf50ea5..c4d320504d26 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -36,6 +36,7 @@
 
 #include <linux/unistd.h>
 #include <linux/time.h>
+#include <vdso/datapage.h>
 
 #define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
 
@@ -45,7 +46,7 @@
 
 #ifdef CONFIG_PPC64
 
-struct vdso_data {
+struct vdso_arch_data {
 	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
 	struct {			/* Systemcfg version numbers	     */
 		__u32 major;		/* Major number			0x10 */
@@ -59,13 +60,13 @@ struct vdso_data {
 	__u32 processor;		/* Processor type		0x1C */
 	__u64 processorCount;		/* # of physical processors	0x20 */
 	__u64 physicalMemorySize;	/* Size of real memory(B)	0x28 */
-	__u64 tb_orig_stamp;		/* Timebase at boot		0x30 */
+	__u64 tb_orig_stamp;		/* (NU) Timebase at boot	0x30 */
 	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
-	__u64 tb_to_xs;			/* Inverse of TB to 2^20	0x40 */
-	__u64 stamp_xsec;		/*				0x48 */
-	__u64 tb_update_count;		/* Timebase atomicity ctr	0x50 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x58 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x5C */
+	__u64 tb_to_xs;			/* (NU) Inverse of TB to 2^20	0x40 */
+	__u64 stamp_xsec;		/* (NU)				0x48 */
+	__u64 tb_update_count;		/* (NU) Timebase atomicity ctr	0x50 */
+	__u32 tz_minuteswest;		/* (NU) Min. west of Greenwich	0x58 */
+	__u32 tz_dsttime;		/* (NU) Type of dst correction	0x5C */
 	__u32 dcache_size;		/* L1 d-cache size		0x60 */
 	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
 	__u32 icache_size;		/* L1 i-cache size		0x68 */
@@ -78,14 +79,10 @@ struct vdso_data {
 	__u32 icache_block_size;		/* L1 i-cache block size     */
 	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
 	__u32 icache_log_block_size;		/* L1 i-cache log block size */
-	__u32 stamp_sec_fraction;		/* fractional seconds of stamp_xtime */
-	__s32 wtom_clock_nsec;			/* Wall to monotonic clock nsec */
-	__s64 wtom_clock_sec;			/* Wall to monotonic clock sec */
-	__s64 stamp_xtime_sec;			/* xtime secs as at tb_orig_stamp */
-	__s64 stamp_xtime_nsec;			/* xtime nsecs as at tb_orig_stamp */
-	__u32 hrtimer_res;			/* hrtimer resolution */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+
+	struct vdso_data data[CS_BASES];
 };
 
 #else /* CONFIG_PPC64 */
@@ -93,26 +90,15 @@ struct vdso_data {
 /*
  * And here is the simpler 32 bits version
  */
-struct vdso_data {
-	__u64 tb_orig_stamp;		/* Timebase at boot		0x30 */
+struct vdso_arch_data {
 	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
-	__u64 tb_to_xs;			/* Inverse of TB to 2^20	0x40 */
-	__u64 stamp_xsec;		/*				0x48 */
-	__u32 tb_update_count;		/* Timebase atomicity ctr	0x50 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x58 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x5C */
-	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
-	__s32 wtom_clock_nsec;
-	__s32 stamp_xtime_sec;		/* xtime seconds as at tb_orig_stamp */
-	__s32 stamp_xtime_nsec;		/* xtime nsecs as at tb_orig_stamp */
-	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
-	__u32 hrtimer_res;		/* hrtimer resolution */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+	struct vdso_data data[CS_BASES];
 };
 
 #endif /* CONFIG_PPC64 */
 
-extern struct vdso_data *vdso_data;
+extern struct vdso_arch_data *vdso_data;
 
 #else /* __ASSEMBLY__ */