powerpc/vdso32: inline __get_datapage()

__get_datapage() is only a few instructions to retrieve the
address of the page where the kernel stores data to the VDSO.

By inlining this function into its users, a bl/blr pair and
a mflr/mtlr pair is avoided, plus a few reg moves.

The improvement is noticeable (about 55 nsec/call on an 8xx)

vdsotest before the patch:
gettimeofday:    vdso: 731 nsec/call
clock-gettime-realtime-coarse:    vdso: 668 nsec/call
clock-gettime-monotonic-coarse:    vdso: 745 nsec/call

vdsotest after the patch:
gettimeofday:    vdso: 677 nsec/call
clock-gettime-realtime-coarse:    vdso: 613 nsec/call
clock-gettime-monotonic-coarse:    vdso: 690 nsec/call

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c39ef7f3dfa25356b01e211d539671f279086c09.1575273217.git.christophe.leroy@c-s.fr

arch/powerpc/include/asm/vdso_datapage.h

@@ -118,6 +118,16 @@ struct vdso_data {
 
 extern struct vdso_data *vdso_data;
 
+#else /* __ASSEMBLY__ */
+
+.macro get_datapage ptr, tmp
+	bcl	20, 31, .+4
+	mflr	\ptr
+	addi	\ptr, \ptr, (__kernel_datapage_offset - (.-4))@l
+	lwz	\tmp, 0(\ptr)
+	add	\ptr, \tmp, \ptr
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

arch/powerpc/kernel/vdso32/cacheflush.S

@@ -8,6 +8,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
 
 	.text
@@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	mr	r11,r3
+	get_datapage	r10, r0
-	bl	__get_datapage@local
 	mtlr	r12
-	mr	r10,r3
 
 	lwz	r7,CFG_DCACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
 	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
@@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
 
 	lwz	r7,CFG_ICACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
 	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)

arch/powerpc/kernel/vdso32/datapage.S

@@ -10,35 +10,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 
 	.text
 	.global	__kernel_datapage_offset;
 __kernel_datapage_offset:
 	.long	0
 
-V_FUNCTION_BEGIN(__get_datapage)
-  .cfi_startproc
-	/* We don't want that exposed or overridable as we want other objects
-	 * to be able to bl directly to here
-	 */
-	.protected __get_datapage
-	.hidden __get_datapage
-
-	mflr	r0
-  .cfi_register lr,r0
-
-	bcl	20,31,data_page_branch
-data_page_branch:
-	mflr	r3
-	mtlr	r0
-	addi	r3, r3, __kernel_datapage_offset-data_page_branch
-	lwz	r0,0(r3)
-  .cfi_restore lr
-	add	r3,r0,r3
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
 /*
  * void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
  *
@@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr	r4,r3
-	bl	__get_datapage@local
+	get_datapage	r3, r0
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP32
 	cmpli	cr0,r4,0
@@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local
+	get_datapage	r3, r0
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 	lwz	r3,CFG_TB_TICKS_PER_SEC(r3)
 	mtlr	r12

arch/powerpc/kernel/vdso32/gettimeofday.S

@@ -9,6 +9,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
@@ -33,8 +34,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 
 	mr	r10,r3			/* r10 saves tv */
 	mr	r11,r4			/* r11 saves tz */
-	bl	__get_datapage@local	/* get data page */
+	get_datapage	r9, r0
-	mr	r9, r3			/* datapage ptr in r9 */
 	cmplwi	r10,0			/* check if tv is NULL */
 	beq	3f
 	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
@@ -80,8 +80,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
 	mr	r11,r4			/* r11 saves tp */
-	bl	__get_datapage@local	/* get data page */
+	get_datapage	r9, r0
-	mr	r9,r3			/* datapage ptr in r9 */
 	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
 	ori	r7,r7,NSEC_PER_SEC@l
 	beq	cr5, .Lcoarse_clocks
@@ -206,7 +205,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local	/* get data page */
+	get_datapage	r3, r0
 	lwz	r5, CLOCK_HRTIMER_RES(r3)
 	mtlr	r12
 	li	r3,0
@@ -240,8 +239,7 @@ V_FUNCTION_BEGIN(__kernel_time)
   .cfi_register lr,r12
 
 	mr	r11,r3			/* r11 holds t */
-	bl	__get_datapage@local
+	get_datapage	r9, r0
-	mr	r9, r3			/* datapage ptr in r9 */
 
 	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)