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

3 files changed, 25 insertions, 242 deletions

diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index dfd34f68bfa1..4a8c5e4d25c0 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -1,8 +1,20 @@
 # SPDX-License-Identifier: GPL-2.0
 # List of files in the vdso, has to be asm only for now
 
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+include $(srctree)/lib/vdso/Makefile
+
 obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
 
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+  CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+  CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
+  CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
+  CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
+  CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+endif
+
 # Build rules
 
 targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
@@ -11,6 +23,7 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
 
 ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
 	-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
@@ -20,12 +33,14 @@ obj-y += vdso64_wrapper.o
 targets += vdso64.lds
 CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
 
+$(obj)/vgettimeofday.o: %.o: %.c FORCE
+
 # Force dependency (incbin is bad)
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
-	$(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE
+	$(call if_changed,vdso64ld_and_check)
 
 # strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -33,8 +48,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso64ld_and_check = VDSO64L $@
+      cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 20f8be40c653..d7a7bfb51081 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -12,6 +12,7 @@
 #include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/vdso/gettimeofday.h>
 
 	.text
 /*
@@ -21,31 +22,7 @@
  *
  */
 V_FUNCTION_BEGIN(__kernel_gettimeofday)
-  .cfi_startproc
-	mflr	r12
-  .cfi_register lr,r12
-
-	mr	r11,r3			/* r11 holds tv */
-	mr	r10,r4			/* r10 holds tz */
-	get_datapage	r3, r0
-	cmpldi	r11,0			/* check if tv is NULL */
-	beq	2f
-	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
-	addi	r7,r7,1000000@l
-	bl	V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
-	std	r4,TVAL64_TV_SEC(r11)	/* store sec in tv */
-	std	r5,TVAL64_TV_USEC(r11)	/* store usec in tv */
-2:	cmpldi	r10,0			/* check if tz is NULL */
-	beq	1f
-	lwz	r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
-	lwz	r5,CFG_TZ_DSTTIME(r3)
-	stw	r4,TZONE_TZ_MINWEST(r10)
-	stw	r5,TZONE_TZ_DSTTIME(r10)
-1:	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0			/* always success */
-	blr
-  .cfi_endproc
+	cvdso_call __c_kernel_gettimeofday
 V_FUNCTION_END(__kernel_gettimeofday)
 
 
@@ -56,120 +33,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
  *
  */
 V_FUNCTION_BEGIN(__kernel_clock_gettime)
-  .cfi_startproc
-	/* Check for supported clock IDs */
-	cmpwi	cr0,r3,CLOCK_REALTIME
-	cmpwi	cr1,r3,CLOCK_MONOTONIC
-	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-
-	cmpwi	cr5,r3,CLOCK_REALTIME_COARSE
-	cmpwi	cr6,r3,CLOCK_MONOTONIC_COARSE
-	cror	cr5*4+eq,cr5*4+eq,cr6*4+eq
-
-	cror	cr0*4+eq,cr0*4+eq,cr5*4+eq
-	bne	cr0,99f
-
-	mflr	r12			/* r12 saves lr */
-  .cfi_register lr,r12
-	mr	r11,r4			/* r11 saves tp */
-	get_datapage	r3, r0
-	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
-	ori	r7,r7,NSEC_PER_SEC@l
-	beq	cr5,70f
-50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
-	bne	cr1,80f			/* if not monotonic, all done */
-
-	/*
-	 * CLOCK_MONOTONIC
-	 */
-
-	/* now we must fixup using wall to monotonic. We need to snapshot
-	 * that value and do the counter trick again. Fortunately, we still
-	 * have the counter value in r8 that was returned by __do_get_tspec.
-	 * At this point, r4,r5 contain our sec/nsec values.
-	 */
-
-	ld	r6,WTOM_CLOCK_SEC(r3)
-	lwa	r9,WTOM_CLOCK_NSEC(r3)
-
-	/* We now have our result in r6,r9. We create a fake dependency
-	 * on that result and re-check the counter
-	 */
-	or	r0,r6,r9
-	xor	r0,r0,r0
-	add	r3,r3,r0
-	ld	r0,CFG_TB_UPDATE_COUNT(r3)
-        cmpld   cr0,r0,r8		/* check if updated */
-	bne-	50b
-	b	78f
-
-	/*
-	 * For coarse clocks we get data directly from the vdso data page, so
-	 * we don't need to call __do_get_tspec, but we still need to do the
-	 * counter trick.
-	 */
-70:	ld      r8,CFG_TB_UPDATE_COUNT(r3)
-	andi.   r0,r8,1                 /* pending update ? loop */
-	bne-    70b
-	add     r3,r3,r0		/* r0 is already 0 */
-
-	/*
-	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
-	 * too
-	 */
-	ld      r4,STAMP_XTIME_SEC(r3)
-	ld      r5,STAMP_XTIME_NSEC(r3)
-	bne     cr6,75f
-
-	/* CLOCK_MONOTONIC_COARSE */
-	ld	r6,WTOM_CLOCK_SEC(r3)
-	lwa     r9,WTOM_CLOCK_NSEC(r3)
-
-	/* check if counter has updated */
-	or      r0,r6,r9
-75:	or	r0,r0,r4
-	or	r0,r0,r5
-	xor     r0,r0,r0
-	add     r3,r3,r0
-	ld      r0,CFG_TB_UPDATE_COUNT(r3)
-	cmpld   cr0,r0,r8               /* check if updated */
-	bne-    70b
-
-	/* Counter has not updated, so continue calculating proper values for
-	 * sec and nsec if monotonic coarse, or just return with the proper
-	 * values for realtime.
-	 */
-	bne     cr6,80f
-
-	/* Add wall->monotonic offset and check for overflow or underflow */
-78:	add     r4,r4,r6
-	add     r5,r5,r9
-	cmpd    cr0,r5,r7
-	cmpdi   cr1,r5,0
-	blt     79f
-	subf    r5,r7,r5
-	addi    r4,r4,1
-79:	bge     cr1,80f
-	addi    r4,r4,-1
-	add     r5,r5,r7
-
-80:	std	r4,TSPC64_TV_SEC(r11)
-	std	r5,TSPC64_TV_NSEC(r11)
-
-	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
-	blr
-
-	/*
-	 * syscall fallback
-	 */
-99:
-	li	r0,__NR_clock_gettime
-  .cfi_restore lr
-	sc
-	blr
-  .cfi_endproc
+	cvdso_call __c_kernel_clock_gettime
 V_FUNCTION_END(__kernel_clock_gettime)
 
 
@@ -180,34 +44,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
  *
  */
 V_FUNCTION_BEGIN(__kernel_clock_getres)
-  .cfi_startproc
-	/* Check for supported clock IDs */
-	cmpwi	cr0,r3,CLOCK_REALTIME
-	cmpwi	cr1,r3,CLOCK_MONOTONIC
-	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
-
-	mflr	r12
-  .cfi_register lr,r12
-	get_datapage	r3, r0
-	lwz	r5, CLOCK_HRTIMER_RES(r3)
-	mtlr	r12
-	li	r3,0
-	cmpldi	cr0,r4,0
-	crclr	cr0*4+so
-	beqlr
-	std	r3,TSPC64_TV_SEC(r4)
-	std	r5,TSPC64_TV_NSEC(r4)
-	blr
-
-	/*
-	 * syscall fallback
-	 */
-99:
-	li	r0,__NR_clock_getres
-	sc
-	blr
-  .cfi_endproc
+	cvdso_call __c_kernel_clock_getres
 V_FUNCTION_END(__kernel_clock_getres)
 
 /*
@@ -217,74 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
  *
  */
 V_FUNCTION_BEGIN(__kernel_time)
-  .cfi_startproc
-	mflr	r12
-  .cfi_register lr,r12
-
-	mr	r11,r3			/* r11 holds t */
-	get_datapage	r3, r0
-
-	ld	r4,STAMP_XTIME_SEC(r3)
-
-	cmpldi	r11,0			/* check if t is NULL */
-	beq	2f
-	std	r4,0(r11)		/* store result at *t */
-2:	mtlr	r12
-	crclr	cr0*4+so
-	mr	r3,r4
-	blr
-  .cfi_endproc
+	cvdso_call_time __c_kernel_time
 V_FUNCTION_END(__kernel_time)
-
-
-/*
- * This is the core of clock_gettime() and gettimeofday(),
- * it returns the current time in r4 (seconds) and r5.
- * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
- * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
- * It expects the datapage ptr in r3 and doesn't clobber it.
- * It clobbers r0, r6 and r9.
- * On return, r8 contains the counter value that can be reused.
- * This clobbers cr0 but not any other cr field.
- */
-V_FUNCTION_BEGIN(__do_get_tspec)
-  .cfi_startproc
-	/* check for update count & load values */
-1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
-	andi.	r0,r8,1			/* pending update ? loop */
-	bne-	1b
-	xor	r0,r8,r8		/* create dependency */
-	add	r3,r3,r0
-
-	/* Get TB & offset it. We use the MFTB macro which will generate
-	 * workaround code for Cell.
-	 */
-	MFTB(r6)
-	ld	r9,CFG_TB_ORIG_STAMP(r3)
-	subf	r6,r9,r6
-
-	/* Scale result */
-	ld	r5,CFG_TB_TO_XS(r3)
-	sldi	r6,r6,12		/* compute time since stamp_xtime */
-	mulhdu	r6,r6,r5		/* in units of 2^-32 seconds */
-
-	/* Add stamp since epoch */
-	ld	r4,STAMP_XTIME_SEC(r3)
-	lwz	r5,STAMP_SEC_FRAC(r3)
-	or	r0,r4,r5
-	or	r0,r0,r6
-	xor	r0,r0,r0
-	add	r3,r3,r0
-	ld	r0,CFG_TB_UPDATE_COUNT(r3)
-	cmpld   r0,r8			/* check if updated */
-	bne-	1b			/* reload if so */
-
-	/* convert to seconds & nanoseconds and add to stamp */
-	add	r6,r6,r5		/* add on fractional seconds of xtime */
-	mulhwu	r5,r6,r7		/* compute micro or nanoseconds and */
-	srdi	r6,r6,32		/* seconds since stamp_xtime */
-	clrldi	r5,r5,32
-	add	r4,r4,r6
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 256fb9720298..71be083b24ed 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -61,7 +61,6 @@ SECTIONS
 	.gcc_except_table : { *(.gcc_except_table) }
 	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
 
-	.opd ALIGN(8)	: { KEEP (*(.opd)) }
 	.got ALIGN(8)	: { *(.got .toc) }
 
 	_end = .;
@@ -111,6 +110,7 @@ SECTIONS
 		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
+		*(.opd)
 	}
 }