powerpc/vdso: Wire up getrandom() vDSO implementation on VDSO64

Extend getrandom() vDSO implementation to VDSO64.

Tested on QEMU on both ppc64_defconfig and ppc64le_defconfig.

Results from a Power9 (PowerNV):
~ # ./vdso_test_getrandom bench-single
   vdso: 25000000 times in 0.787943615 seconds
   libc: 25000000 times in 14.101887252 seconds
   syscall: 25000000 times in 14.047475082 seconds
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

arch/powerpc/Kconfig

@@ -311,7 +311,7 @@ config PPC
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select TRACE_IRQFLAGS_SUPPORT
-	select VDSO_GETRANDOM			if VDSO32
+	select VDSO_GETRANDOM
 	#
 	# Please keep this list sorted alphabetically.
 	#

arch/powerpc/kernel/vdso/Makefile

@@ -9,6 +9,7 @@ obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o not
 obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
 
 obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o
+obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
@@ -21,6 +22,7 @@ endif
 
 ifneq ($(c-getrandom-y),)
   CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y)
+  CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) $(call cc-option, -ffixed-r30)
 endif
 
 # Build rules
@@ -34,7 +36,7 @@ endif
 targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o vgetrandom-32.o
 targets += crtsavres-32.o
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
-targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o
+targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o vgetrandom-64.o
 obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
 
 ccflags-y := -fno-common -fno-builtin -DBUILD_VDSO
@@ -71,7 +73,7 @@ CPPFLAGS_vdso64.lds += -P -C
 # link rule for the .so file, .lds has to be first
 $(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE
 	$(call if_changed,vdso32ld_and_check)
-$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o $(obj)/vgetrandom-64.o FORCE
 	$(call if_changed,vdso64ld_and_check)
 
 # assembly rules for the .S files
@@ -87,6 +89,8 @@ $(obj-vdso64): %-64.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE
 	$(call if_changed_dep,cc_o_c)
+$(obj)/vgetrandom-64.o: %-64.o: %.c FORCE
+	$(call if_changed_dep,cc_o_c)
 
 # Generate VDSO offsets using helper script
 gen-vdso32sym := $(src)/gen_vdso32_offsets.sh

arch/powerpc/kernel/vdso/getrandom.S

@@ -27,10 +27,18 @@
   .cfi_adjust_cfa_offset PPC_MIN_STKFRM
 	PPC_STL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
   .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
+#ifdef __powerpc64__
+	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
+#endif
 	get_realdatapage	r8, r11
 	addi		r8, r8, VDSO_RNG_DATA_OFFSET
 	bl		CFUNC(DOTSYM(\funct))
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+	PPC_LL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_restore r2
+#endif
 	cmpwi		r3, 0
 	mtlr		r0
 	addi		r1, r1, 2 * PPC_MIN_STKFRM

arch/powerpc/kernel/vdso/vdso64.lds.S

@@ -123,6 +123,7 @@ VERSION
 		__kernel_sigtramp_rt64;
 		__kernel_getcpu;
 		__kernel_time;
+		__kernel_getrandom;
 
 	local: *;
 	};

arch/powerpc/kernel/vdso/vgetrandom-chacha.S

@@ -124,6 +124,26 @@
  */
 SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 #ifdef __powerpc64__
+	std	counter, -216(r1)
+
+	std	r14, -144(r1)
+	std	r15, -136(r1)
+	std	r16, -128(r1)
+	std	r17, -120(r1)
+	std	r18, -112(r1)
+	std	r19, -104(r1)
+	std	r20, -96(r1)
+	std	r21, -88(r1)
+	std	r22, -80(r1)
+	std	r23, -72(r1)
+	std	r24, -64(r1)
+	std	r25, -56(r1)
+	std	r26, -48(r1)
+	std	r27, -40(r1)
+	std	r28, -32(r1)
+	std	r29, -24(r1)
+	std	r30, -16(r1)
+	std	r31, -8(r1)
 #else
 	stwu	r1, -96(r1)
 	stw	counter, 20(r1)
@@ -149,9 +169,13 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	stw	r30, 88(r1)
 	stw	r31, 92(r1)
 #endif
+#endif	/* __powerpc64__ */
 
 	lwz	counter0, 0(counter)
 	lwz	counter1, 4(counter)
+#ifdef __powerpc64__
+	rldimi	counter0, counter1, 32, 0
+#endif
 	mr	idx_r0, nblocks
 	subi	dst_bytes, dst_bytes, 4
 
@@ -267,12 +291,21 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 
 	subic.	idx_r0, idx_r0, 1	/* subi. can't use r0 as source */
 
+#ifdef __powerpc64__
+	addi	counter0, counter0, 1
+	srdi	counter1, counter0, 32
+#else
 	addic	counter0, counter0, 1
 	addze	counter1, counter1
+#endif
 
 	bne	.Lblock
 
+#ifdef __powerpc64__
+	ld	counter, -216(r1)
+#else
 	lwz	counter, 20(r1)
+#endif
 	stw	counter0, 0(counter)
 	stw	counter1, 4(counter)
 
@@ -284,6 +317,26 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	li	r11, 0
 	li	r12, 0
 
+#ifdef __powerpc64__
+	ld	r14, -144(r1)
+	ld	r15, -136(r1)
+	ld	r16, -128(r1)
+	ld	r17, -120(r1)
+	ld	r18, -112(r1)
+	ld	r19, -104(r1)
+	ld	r20, -96(r1)
+	ld	r21, -88(r1)
+	ld	r22, -80(r1)
+	ld	r23, -72(r1)
+	ld	r24, -64(r1)
+	ld	r25, -56(r1)
+	ld	r26, -48(r1)
+	ld	r27, -40(r1)
+	ld	r28, -32(r1)
+	ld	r29, -24(r1)
+	ld	r30, -16(r1)
+	ld	r31, -8(r1)
+#else
 #ifdef __BIG_ENDIAN__
 	lmw	r14, 24(r1)
 #else