Merge tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Support for split PMD page table lock on 64-bit Book3S (Power8/9).

   - Add support for HAVE_RELIABLE_STACKTRACE, so we properly support
     live patching again.

   - Add support for patching barrier_nospec in copy_from_user() and
     syscall entry.

   - A couple of fixes for our data breakpoints on Book3S.

   - A series from Nick optimising TLB/mm handling with the Radix MMU.

   - Numerous small cleanups to squash sparse/gcc warnings from Mathieu
     Malaterre.

   - Several series optimising various parts of the 32-bit code from
     Christophe Leroy.

   - Removal of support for two old machines, "SBC834xE" and "C2K"
     ("GEFanuc,C2K"), which is why the diffstat has so many deletions.

  And many other small improvements & fixes.

  There's a few out-of-area changes. Some minor ftrace changes OK'ed by
  Steve, and a fix to our powernv cpuidle driver. Then there's a series
  touching mm, x86 and fs/proc/task_mmu.c, which cleans up some details
  around pkey support. It was ack'ed/reviewed by Ingo & Dave and has
  been in next for several weeks.

  Thanks to: Akshay Adiga, Alastair D'Silva, Alexey Kardashevskiy, Al
  Viro, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Arnd
  Bergmann, Balbir Singh, Cédric Le Goater, Christophe Leroy, Christophe
  Lombard, Colin Ian King, Dave Hansen, Fabio Estevam, Finn Thain,
  Frederic Barrat, Gautham R. Shenoy, Haren Myneni, Hari Bathini, Ingo
  Molnar, Jonathan Neuschäfer, Josh Poimboeuf, Kamalesh Babulal,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mark Greer, Mathieu Malaterre,
  Matthew Wilcox, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Nicolai Stange, Olof Johansson, Paul Gortmaker, Paul
  Mackerras, Peter Rosin, Pridhiviraj Paidipeddi, Ram Pai, Rashmica
  Gupta, Ravi Bangoria, Russell Currey, Sam Bobroff, Samuel
  Mendoza-Jonas, Segher Boessenkool, Shilpasri G Bhat, Simon Guo,
  Souptick Joarder, Stewart Smith, Thiago Jung Bauermann, Torsten Duwe,
  Vaibhav Jain, Wei Yongjun, Wolfram Sang, Yisheng Xie, YueHaibing"

* tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (251 commits)
  powerpc/64s/radix: Fix missing ptesync in flush_cache_vmap
  cpuidle: powernv: Fix promotion from snooze if next state disabled
  powerpc: fix build failure by disabling attribute-alias warning in pci_32
  ocxl: Fix missing unlock on error in afu_ioctl_enable_p9_wait()
  powerpc-opal: fix spelling mistake "Uniterrupted" -> "Uninterrupted"
  powerpc: fix spelling mistake: "Usupported" -> "Unsupported"
  powerpc/pkeys: Detach execute_only key on !PROT_EXEC
  powerpc/powernv: copy/paste - Mask SO bit in CR
  powerpc: Remove core support for Marvell mv64x60 hostbridges
  powerpc/boot: Remove core support for Marvell mv64x60 hostbridges
  powerpc/boot: Remove support for Marvell mv64x60 i2c controller
  powerpc/boot: Remove support for Marvell MPSC serial controller
  powerpc/embedded6xx: Remove C2K board support
  powerpc/lib: optimise PPC32 memcmp
  powerpc/lib: optimise 32 bits __clear_user()
  powerpc/time: inline arch_vtime_task_switch()
  powerpc/Makefile: set -mcpu=860 flag for the 8xx
  powerpc: Implement csum_ipv6_magic in assembly
  powerpc/32: Optimise __csum_partial()
  powerpc/lib: Adjust .balign inside string functions for PPC32
  ...

11 files changed, 341 insertions, 93 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 653901042ad7..d0ca13ad8231 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -26,13 +26,14 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   string_64.o memcpy_64.o memcmp_64.o pmem.o
+	   memcpy_64.o pmem.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
 obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
-obj-y			+= checksum_$(BITS).o checksum_wrappers.o
+obj-y			+= checksum_$(BITS).o checksum_wrappers.o \
+			   string_$(BITS).o memcmp_$(BITS).o
 
 obj-y			+= sstep.o ldstfp.o quad.o
 obj64-y			+= quad.o
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 9a671c774b22..aa224069f93a 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -47,16 +47,25 @@ _GLOBAL(__csum_partial)
 	bdnz	2b
 21:	srwi.	r6,r4,4		/* # blocks of 4 words to do */
 	beq	3f
+	lwz	r0,4(r3)
 	mtctr	r6
-22:	lwz	r0,4(r3)
 	lwz	r6,8(r3)
+	adde	r5,r5,r0
 	lwz	r7,12(r3)
+	adde	r5,r5,r6
 	lwzu	r8,16(r3)
+	adde	r5,r5,r7
+	bdz	23f
+22:	lwz	r0,4(r3)
+	adde	r5,r5,r8
+	lwz	r6,8(r3)
 	adde	r5,r5,r0
+	lwz	r7,12(r3)
 	adde	r5,r5,r6
+	lwzu	r8,16(r3)
 	adde	r5,r5,r7
-	adde	r5,r5,r8
 	bdnz	22b
+23:	adde	r5,r5,r8
 3:	andi.	r0,r4,2
 	beq+	4f
 	lhz	r0,4(r3)
@@ -293,3 +302,36 @@ dst_error:
 	EX_TABLE(51b, dst_error);
 
 EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ *			   const struct in6_addr *daddr,
+ *			   __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+	lwz	r8, 0(r3)
+	lwz	r9, 4(r3)
+	addc	r0, r7, r8
+	lwz	r10, 8(r3)
+	adde	r0, r0, r9
+	lwz	r11, 12(r3)
+	adde	r0, r0, r10
+	lwz	r8, 0(r4)
+	adde	r0, r0, r11
+	lwz	r9, 4(r4)
+	adde	r0, r0, r8
+	lwz	r10, 8(r4)
+	adde	r0, r0, r9
+	lwz	r11, 12(r4)
+	adde	r0, r0, r10
+	add	r5, r5, r6	/* assumption: len + proto doesn't carry */
+	adde	r0, r0, r11
+	adde	r0, r0, r5
+	addze	r0, r0
+	rotlwi	r3, r0, 16
+	add	r3, r0, r3
+	not	r3, r3
+	rlwinm	r3, r3, 16, 16, 31
+	blr
+EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index d7f1a966136e..886ed94b9c13 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -429,3 +429,31 @@ dstnr;	stb	r6,0(r4)
 	stw	r6,0(r8)
 	blr
 EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ *			   const struct in6_addr *daddr,
+ *			   __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+	ld	r8, 0(r3)
+	ld	r9, 8(r3)
+	add	r5, r5, r6
+	addc	r0, r8, r9
+	ld	r10, 0(r4)
+	ld	r11, 8(r4)
+	adde	r0, r0, r10
+	add	r5, r5, r7
+	adde	r0, r0, r11
+	adde	r0, r0, r5
+	addze	r0, r0
+	rotldi  r3, r0, 32		/* fold two 32 bit halves together */
+	add	r3, r0, r3
+	srdi	r0, r3, 32
+	rotlwi	r3, r0, 16		/* fold two 16 bit halves together */
+	add	r3, r0, r3
+	not	r3, r3
+	rlwinm	r3, r3, 16, 16, 31
+	blr
+EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/powerpc/lib/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S
index f4613118132e..f16cec989506 100644
--- a/arch/powerpc/lib/feature-fixups-test.S
+++ b/arch/powerpc/lib/feature-fixups-test.S
@@ -167,16 +167,52 @@ globl(ftr_fixup_test6_expected)
 	blt	2b
 	b	3f
 	b	1b
-2:	or	1,1,1
+3:	or	1,1,1
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test7)
+	or	1,1,1
+BEGIN_FTR_SECTION
+	or	2,2,2
+	or	2,2,2
 	or	2,2,2
-3:	or	3,3,3
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+FTR_SECTION_ELSE
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+	bdnz	3b
+1:
+ALT_FTR_SECTION_END(0, 1)
+	or	1,1,1
+	or	1,1,1
+
+globl(end_ftr_fixup_test7)
+	nop
 
+globl(ftr_fixup_test7_expected)
+	or	1,1,1
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+	bdnz	3b
+1:	or	1,1,1
 
 #if 0
 /* Test that if we have a larger else case the assembler spots it and
  * reports an error. #if 0'ed so as not to break the build normally.
  */
-ftr_fixup_test7:
+ftr_fixup_test_too_big:
 	or	1,1,1
 BEGIN_FTR_SECTION
 	or	2,2,2
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index e1bcdc32a851..8b69f868298c 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -277,6 +277,43 @@ void do_rfi_flush_fixups(enum l1d_flush_type types)
 		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
 						: "unknown");
 }
+
+void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end)
+{
+	unsigned int instr, *dest;
+	long *start, *end;
+	int i;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	instr = 0x60000000; /* nop */
+
+	if (enable) {
+		pr_info("barrier-nospec: using ORI speculation barrier\n");
+		instr = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+		patch_instruction(dest, instr);
+	}
+
+	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
+}
+
+void do_barrier_nospec_fixups(bool enable)
+{
+	void *start, *end;
+
+	start = PTRRELOC(&__start___barrier_nospec_fixup),
+	end = PTRRELOC(&__stop___barrier_nospec_fixup);
+
+	do_barrier_nospec_fixups_range(enable, start, end);
+}
+
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
@@ -400,7 +437,7 @@ static void test_basic_patching(void)
 	extern unsigned int end_ftr_fixup_test1[];
 	extern unsigned int ftr_fixup_test1_orig[];
 	extern unsigned int ftr_fixup_test1_expected[];
-	int size = end_ftr_fixup_test1 - ftr_fixup_test1;
+	int size = 4 * (end_ftr_fixup_test1 - ftr_fixup_test1);
 
 	fixup.value = fixup.mask = 8;
 	fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1);
@@ -432,7 +469,7 @@ static void test_alternative_patching(void)
 	extern unsigned int ftr_fixup_test2_orig[];
 	extern unsigned int ftr_fixup_test2_alt[];
 	extern unsigned int ftr_fixup_test2_expected[];
-	int size = end_ftr_fixup_test2 - ftr_fixup_test2;
+	int size = 4 * (end_ftr_fixup_test2 - ftr_fixup_test2);
 
 	fixup.value = fixup.mask = 0xF;
 	fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1);
@@ -464,7 +501,7 @@ static void test_alternative_case_too_big(void)
 	extern unsigned int end_ftr_fixup_test3[];
 	extern unsigned int ftr_fixup_test3_orig[];
 	extern unsigned int ftr_fixup_test3_alt[];
-	int size = end_ftr_fixup_test3 - ftr_fixup_test3;
+	int size = 4 * (end_ftr_fixup_test3 - ftr_fixup_test3);
 
 	fixup.value = fixup.mask = 0xC;
 	fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1);
@@ -491,7 +528,7 @@ static void test_alternative_case_too_small(void)
 	extern unsigned int ftr_fixup_test4_orig[];
 	extern unsigned int ftr_fixup_test4_alt[];
 	extern unsigned int ftr_fixup_test4_expected[];
-	int size = end_ftr_fixup_test4 - ftr_fixup_test4;
+	int size = 4 * (end_ftr_fixup_test4 - ftr_fixup_test4);
 	unsigned long flag;
 
 	/* Check a high-bit flag */
@@ -525,7 +562,7 @@ static void test_alternative_case_with_branch(void)
 	extern unsigned int ftr_fixup_test5[];
 	extern unsigned int end_ftr_fixup_test5[];
 	extern unsigned int ftr_fixup_test5_expected[];
-	int size = end_ftr_fixup_test5 - ftr_fixup_test5;
+	int size = 4 * (end_ftr_fixup_test5 - ftr_fixup_test5);
 
 	check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0);
 }
@@ -535,11 +572,21 @@ static void test_alternative_case_with_external_branch(void)
 	extern unsigned int ftr_fixup_test6[];
 	extern unsigned int end_ftr_fixup_test6[];
 	extern unsigned int ftr_fixup_test6_expected[];
-	int size = end_ftr_fixup_test6 - ftr_fixup_test6;
+	int size = 4 * (end_ftr_fixup_test6 - ftr_fixup_test6);
 
 	check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0);
 }
 
+static void test_alternative_case_with_branch_to_end(void)
+{
+	extern unsigned int ftr_fixup_test7[];
+	extern unsigned int end_ftr_fixup_test7[];
+	extern unsigned int ftr_fixup_test7_expected[];
+	int size = 4 * (end_ftr_fixup_test7 - ftr_fixup_test7);
+
+	check(memcmp(ftr_fixup_test7, ftr_fixup_test7_expected, size) == 0);
+}
+
 static void test_cpu_macros(void)
 {
 	extern u8 ftr_fixup_test_FTR_macros[];
@@ -595,6 +642,7 @@ static int __init test_feature_fixups(void)
 	test_alternative_case_too_small();
 	test_alternative_case_with_branch();
 	test_alternative_case_with_external_branch();
+	test_alternative_case_with_branch_to_end();
 	test_cpu_macros();
 	test_fw_macros();
 	test_lwsync_macros();
diff --git a/arch/powerpc/lib/memcmp_32.S b/arch/powerpc/lib/memcmp_32.S
new file mode 100644
index 000000000000..5010e376f7b8
--- /dev/null
+++ b/arch/powerpc/lib/memcmp_32.S
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * memcmp for PowerPC32
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+	.text
+
+_GLOBAL(memcmp)
+	srawi.	r7, r5, 2		/* Divide len by 4 */
+	mr	r6, r3
+	beq-	3f
+	mtctr	r7
+	li	r7, 0
+1:	lwzx	r3, r6, r7
+	lwzx	r0, r4, r7
+	addi	r7, r7, 4
+	cmplw	cr0, r3, r0
+	bdnzt	eq, 1b
+	bne	5f
+3:	andi.	r3, r5, 3
+	beqlr
+	cmplwi	cr1, r3, 2
+	blt-	cr1, 4f
+	lhzx	r3, r6, r7
+	lhzx	r0, r4, r7
+	addi	r7, r7, 2
+	subf.	r3, r0, r3
+	beqlr	cr1
+	bnelr
+4:	lbzx	r3, r6, r7
+	lbzx	r0, r4, r7
+	subf.	r3, r0, r3
+	blr
+5:	li	r3, 1
+	bgtlr
+	li	r3, -1
+	blr
+EXPORT_SYMBOL(memcmp)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 34d68f1b1b40..d81568f783e5 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1065,9 +1065,10 @@ static nokprobe_inline void do_popcnt(const struct pt_regs *regs,
 {
 	unsigned long long out = v1;
 
-	out -= (out >> 1) & 0x5555555555555555;
-	out = (0x3333333333333333 & out) + (0x3333333333333333 & (out >> 2));
-	out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0f;
+	out -= (out >> 1) & 0x5555555555555555ULL;
+	out = (0x3333333333333333ULL & out) +
+	      (0x3333333333333333ULL & (out >> 2));
+	out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0fULL;
 
 	if (size == 8) {	/* popcntb */
 		op->val = out;
@@ -1076,7 +1077,7 @@ static nokprobe_inline void do_popcnt(const struct pt_regs *regs,
 	out += out >> 8;
 	out += out >> 16;
 	if (size == 32) {	/* popcntw */
-		op->val = out & 0x0000003f0000003f;
+		op->val = out & 0x0000003f0000003fULL;
 		return;
 	}
 
@@ -1114,7 +1115,7 @@ static nokprobe_inline void do_prty(const struct pt_regs *regs,
 
 	res ^= res >> 16;
 	if (size == 32) {		/* prtyw */
-		op->val = res & 0x0000000100000001;
+		op->val = res & 0x0000000100000001ULL;
 		return;
 	}
 
@@ -2544,6 +2545,15 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 #endif /* __powerpc64__ */
 
 	}
+
+#ifdef CONFIG_VSX
+	if ((GETTYPE(op->type) == LOAD_VSX ||
+	     GETTYPE(op->type) == STORE_VSX) &&
+	    !cpu_has_feature(CPU_FTR_VSX)) {
+		return -1;
+	}
+#endif /* CONFIG_VSX */
+
 	return 0;
 
  logical_done:
@@ -2641,7 +2651,7 @@ void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op)
 	unsigned long next_pc;
 
 	next_pc = truncate_if_32bit(regs->msr, regs->nip + 4);
-	switch (op->type & INSTR_TYPE_MASK) {
+	switch (GETTYPE(op->type)) {
 	case COMPUTE:
 		if (op->type & SETREG)
 			regs->gpr[op->reg] = op->val;
@@ -2739,7 +2749,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 
 	err = 0;
 	size = GETSIZE(op->type);
-	type = op->type & INSTR_TYPE_MASK;
+	type = GETTYPE(op->type);
 	cross_endian = (regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
 	ea = truncate_if_32bit(regs->msr, op->ea);
 
@@ -3001,7 +3011,7 @@ int emulate_step(struct pt_regs *regs, unsigned int instr)
 	}
 
 	err = 0;
-	type = op.type & INSTR_TYPE_MASK;
+	type = GETTYPE(op.type);
 
 	if (OP_IS_LOAD_STORE(type)) {
 		err = emulate_loadstore(regs, &op);
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index a787776822d8..4b41970e9ed8 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -8,10 +8,9 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-#include <asm/processor.h>
-#include <asm/errno.h>
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
+#include <asm/cache.h>
 
 	.text
 	
@@ -23,7 +22,7 @@ _GLOBAL(strncpy)
 	mtctr	r5
 	addi	r6,r3,-1
 	addi	r4,r4,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r0,1(r4)
 	cmpwi	0,r0,0
 	stbu	r0,1(r6)
@@ -43,7 +42,7 @@ _GLOBAL(strncmp)
 	mtctr	r5
 	addi	r5,r3,-1
 	addi	r4,r4,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r3,1(r5)
 	cmpwi	1,r3,0
 	lbzu	r0,1(r4)
@@ -55,29 +54,12 @@ _GLOBAL(strncmp)
 	blr
 EXPORT_SYMBOL(strncmp)
 
-#ifdef CONFIG_PPC32
-_GLOBAL(memcmp)
-	PPC_LCMPI 0,r5,0
-	beq-	2f
-	mtctr	r5
-	addi	r6,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r3,1(r6)
-	lbzu	r0,1(r4)
-	subf.	r3,r0,r3
-	bdnzt	2,1b
-	blr
-2:	li	r3,0
-	blr
-EXPORT_SYMBOL(memcmp)
-#endif
-
 _GLOBAL(memchr)
 	PPC_LCMPI 0,r5,0
 	beq-	2f
 	mtctr	r5
 	addi	r3,r3,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r0,1(r3)
 	cmpw	0,r0,r4
 	bdnzf	2,1b
@@ -85,47 +67,3 @@ _GLOBAL(memchr)
 2:	li	r3,0
 	blr
 EXPORT_SYMBOL(memchr)
-
-#ifdef CONFIG_PPC32
-_GLOBAL(__clear_user)
-	addi	r6,r3,-4
-	li	r3,0
-	li	r5,0
-	cmplwi	0,r4,4
-	blt	7f
-	/* clear a single word */
-11:	stwu	r5,4(r6)
-	beqlr
-	/* clear word sized chunks */
-	andi.	r0,r6,3
-	add	r4,r0,r4
-	subf	r6,r0,r6
-	srwi	r0,r4,2
-	andi.	r4,r4,3
-	mtctr	r0
-	bdz	7f
-1:	stwu	r5,4(r6)
-	bdnz	1b
-	/* clear byte sized chunks */
-7:	cmpwi	0,r4,0
-	beqlr
-	mtctr	r4
-	addi	r6,r6,3
-8:	stbu	r5,1(r6)
-	bdnz	8b
-	blr
-90:	mr	r3,r4
-	blr
-91:	mfctr	r3
-	slwi	r3,r3,2
-	add	r3,r3,r4
-	blr
-92:	mfctr	r3
-	blr
-
-	EX_TABLE(11b, 90b)
-	EX_TABLE(1b, 91b)
-	EX_TABLE(8b, 92b)
-
-EXPORT_SYMBOL(__clear_user)
-#endif
diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S
new file mode 100644
index 000000000000..f69a6aab7bfb
--- /dev/null
+++ b/arch/powerpc/lib/string_32.S
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * String handling functions for PowerPC32
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+
+CACHELINE_BYTES = L1_CACHE_BYTES
+LG_CACHELINE_BYTES = L1_CACHE_SHIFT
+CACHELINE_MASK = (L1_CACHE_BYTES-1)
+
+_GLOBAL(__clear_user)
+/*
+ * Use dcbz on the complete cache lines in the destination
+ * to set them to zero.  This requires that the destination
+ * area is cacheable.
+ */
+	cmplwi	cr0, r4, 4
+	mr	r10, r3
+	li	r3, 0
+	blt	7f
+
+11:	stw	r3, 0(r10)
+	beqlr
+	andi.	r0, r10, 3
+	add	r11, r0, r4
+	subf	r6, r0, r10
+
+	clrlwi	r7, r6, 32 - LG_CACHELINE_BYTES
+	add	r8, r7, r11
+	srwi	r9, r8, LG_CACHELINE_BYTES
+	addic.	r9, r9, -1	/* total number of complete cachelines */
+	ble	2f
+	xori	r0, r7, CACHELINE_MASK & ~3
+	srwi.	r0, r0, 2
+	beq	3f
+	mtctr	r0
+4:	stwu	r3, 4(r6)
+	bdnz	4b
+3:	mtctr	r9
+	li	r7, 4
+10:	dcbz	r7, r6
+	addi	r6, r6, CACHELINE_BYTES
+	bdnz	10b
+	clrlwi	r11, r8, 32 - LG_CACHELINE_BYTES
+	addi	r11, r11, 4
+
+2:	srwi	r0 ,r11 ,2
+	mtctr	r0
+	bdz	6f
+1:	stwu	r3, 4(r6)
+	bdnz	1b
+6:	andi.	r11, r11, 3
+	beqlr
+	mtctr	r11
+	addi	r6, r6, 3
+8:	stbu	r3, 1(r6)
+	bdnz	8b
+	blr
+
+7:	cmpwi	cr0, r4, 0
+	beqlr
+	mtctr	r4
+	addi	r6, r10, -1
+9:	stbu	r3, 1(r6)
+	bdnz	9b
+	blr
+
+90:	mr	r3, r4
+	blr
+91:	add	r3, r10, r4
+	subf	r3, r6, r3
+	blr
+
+	EX_TABLE(11b, 90b)
+	EX_TABLE(4b, 91b)
+	EX_TABLE(10b, 91b)
+	EX_TABLE(1b, 91b)
+	EX_TABLE(8b, 91b)
+	EX_TABLE(9b, 91b)
+
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 2534c1447554..6c47daa61614 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -387,10 +387,14 @@ static void __init test_lxvd2x_stxvd2x(void)
 	/* lxvd2x vsr39, r3, r4 */
 	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
 
-	if (stepped == 1)
+	if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
 		show_result("lxvd2x", "PASS");
-	else
-		show_result("lxvd2x", "FAIL");
+	} else {
+		if (!cpu_has_feature(CPU_FTR_VSX))
+			show_result("lxvd2x", "PASS (!CPU_FTR_VSX)");
+		else
+			show_result("lxvd2x", "FAIL");
+	}
 
 
 	/*** stxvd2x ***/
@@ -404,10 +408,15 @@ static void __init test_lxvd2x_stxvd2x(void)
 	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
 
 	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
-	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3] &&
+	    cpu_has_feature(CPU_FTR_VSX)) {
 		show_result("stxvd2x", "PASS");
-	else
-		show_result("stxvd2x", "FAIL");
+	} else {
+		if (!cpu_has_feature(CPU_FTR_VSX))
+			show_result("stxvd2x", "PASS (!CPU_FTR_VSX)");
+		else
+			show_result("stxvd2x", "FAIL");
+	}
 }
 #else
 static void __init test_lxvd2x_stxvd2x(void)
diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c
index 6521fe5e8cef..dab2b6bfcf36 100644
--- a/arch/powerpc/lib/xor_vmx_glue.c
+++ b/arch/powerpc/lib/xor_vmx_glue.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <asm/switch_to.h>
+#include <asm/xor_altivec.h>
 #include "xor_vmx.h"
 
 void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,