diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 570b3d91e2e4..17e63244e885 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -15,6 +15,9 @@
 #define TASK_SIZE_MAX		TASK_SIZE_USER64
 #endif
 
+/* Threshold above which VMX copy path is used */
+#define VMX_COPY_THRESHOLD 3328
+
 #include <asm-generic/access_ok.h>
 
 /*
@@ -326,40 +329,62 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
-#ifdef __powerpc64__
+unsigned long __copy_tofrom_user_base(void __user *to,
+				      const void __user *from, unsigned long size);
+
+unsigned long __copy_tofrom_user_power7_vmx(void __user *to,
+					    const void __user *from, unsigned long size);
+
+static __always_inline bool will_use_vmx(unsigned long n)
+{
+	return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) &&
+	       n > VMX_COPY_THRESHOLD;
+}
+
+static __always_inline unsigned long
+raw_copy_tofrom_user(void __user *to, const void __user *from,
+		     unsigned long n, unsigned long dir)
+{
+	unsigned long ret;
+
+	if (will_use_vmx(n) && enter_vmx_usercopy()) {
+		allow_user_access(to, dir);
+		ret = __copy_tofrom_user_power7_vmx(to, from, n);
+		prevent_user_access(dir);
+		exit_vmx_usercopy();
+
+		if (unlikely(ret)) {
+			allow_user_access(to, dir);
+			ret = __copy_tofrom_user_base(to, from, n);
+			prevent_user_access(dir);
+		}
+		return ret;
+	}
+
+	allow_user_access(to, dir);
+	ret = __copy_tofrom_user(to, from, n);
+	prevent_user_access(dir);
+	return ret;
+}
+
+#ifdef CONFIG_PPC64
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
-
 	barrier_nospec();
-	allow_user_access(to, KUAP_READ_WRITE);
-	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(KUAP_READ_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE);
 }
-#endif /* __powerpc64__ */
+#endif /* CONFIG_PPC64 */
 
-static inline unsigned long raw_copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(NULL, KUAP_READ);
-	ret = __copy_tofrom_user((__force void __user *)to, from, n);
-	prevent_user_access(KUAP_READ);
-	return ret;
+	return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(to, KUAP_WRITE);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
-	prevent_user_access(KUAP_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE);
 }
 
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0ce71310b7d9..d122e8447831 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 				    struct device *dev,
 				    struct iommu_domain *old)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev);
 	struct iommu_table_group *table_group;
 	struct iommu_group *grp;
 
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index cb5b73adc250..b1761909c23f 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,7 +35,6 @@
 #include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
-#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p)
 
 	initmem_init();
 
-	/*
-	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
-	 * hugetlb. These must be called after initmem_init(), so that
-	 * pageblock_order is initialised.
-	 */
-	fadump_cma_init();
-	kdump_cma_reserve();
-	kvm_cma_reserve();
-
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 
 	if (ppc_md.setup_arch)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 9af969d2cc0c..25a99108caff 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -562,3 +562,4 @@ exc;	std	r10,32(3)
 	li	r5,4096
 	b	.Ldst_aligned
 EXPORT_SYMBOL(__copy_tofrom_user)
+EXPORT_SYMBOL(__copy_tofrom_user_base)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 8474c682a178..17dbcfbae25f 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -5,13 +5,9 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 
-#ifndef SELFTEST_CASE
-/* 0 == don't use VMX, 1 == use VMX */
-#define SELFTEST_CASE	0
-#endif
-
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
@@ -47,10 +43,14 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	CFUNC(exit_vmx_usercopy)
+	ld      r6,STK_REG(R31)(r1)	/* original destination pointer */
+	ld      r5,STK_REG(R29)(r1)	/* original number of bytes */
+	subf    r7,r6,r3		/* #bytes copied */
+	subf    r3,r7,r5		/* #bytes not copied in r3 */
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
-	b	.Lexit
+	addi    r1,r1,STACKFRAMESIZE
+	blr
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
@@ -74,7 +74,6 @@
 
 _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
-	cmpldi	cr1,r5,3328
 
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
@@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7)
 
 	blt	.Lshort_copy
 
-#ifdef CONFIG_ALTIVEC
-test_feature = SELFTEST_CASE
-BEGIN_FTR_SECTION
-	bgt	cr1,.Lvmx_copy
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif
 
 .Lnonvmx_copy:
 	/* Get the source 8B aligned */
@@ -263,23 +256,14 @@ err1;	stb	r0,0(r3)
 15:	li	r3,0
 	blr
 
-.Lunwind_stack_nonvmx_copy:
-	addi	r1,r1,STACKFRAMESIZE
-	b	.Lnonvmx_copy
-
-.Lvmx_copy:
 #ifdef CONFIG_ALTIVEC
+_GLOBAL(__copy_tofrom_user_power7_vmx)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	CFUNC(enter_vmx_usercopy)
-	cmpwi	cr1,r3,0
-	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STK_REG(R31)(r1)
-	ld	r4,STK_REG(R30)(r1)
-	ld	r5,STK_REG(R29)(r1)
-	mtlr	r0
 
+	std     r3,STK_REG(R31)(r1)
+	std     r5,STK_REG(R29)(r1)
 	/*
 	 * We prefetch both the source and destination using enhanced touch
 	 * instructions. We use a stream ID of 0 for the load side and
@@ -300,8 +284,6 @@ err1;	stb	r0,0(r3)
 
 	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
-	beq	cr1,.Lunwind_stack_nonvmx_copy
-
 	/*
 	 * If source and destination are not relatively aligned we use a
 	 * slower permute loop.
@@ -478,7 +460,8 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -681,5 +664,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
+EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx)
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 54340912398f..554b248002b4 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,6 +27,7 @@ int enter_vmx_usercopy(void)
 
 	return 1;
 }
+EXPORT_SYMBOL(enter_vmx_usercopy);
 
 /*
  * This function must return 0 because we tail call optimise when calling
@@ -49,6 +50,7 @@ int exit_vmx_usercopy(void)
 		set_dec(1);
 	return 0;
 }
+EXPORT_SYMBOL(exit_vmx_usercopy);
 
 int enter_vmx_ops(void)
 {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index a985fc96b953..b7982d0243d4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -30,6 +30,10 @@
 #include <asm/setup.h>
 #include <asm/fixmap.h>
 
+#include <asm/fadump.h>
+#include <asm/kexec.h>
+#include <asm/kvm_ppc.h>
+
 #include <mm/mmu_decl.h>
 
 unsigned long long memory_limit __initdata;
@@ -268,6 +272,16 @@ void __init paging_init(void)
 
 void __init arch_mm_preinit(void)
 {
+
+	/*
+	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM
+	 * and hugetlb. These must be called after pageblock_order is
+	 * initialised.
+	 */
+	fadump_cma_init();
+	kdump_cma_reserve();
+	kvm_cma_reserve();
+
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
 	 * a 4-bit field for slices.
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 26aa26482c9a..992cc5c98214 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
+
+	if (!current->mm)
+		return;
+
 	if (!is_32bit_task())
 		perf_callchain_user_64(entry, regs);
 	else
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ddcc2d8aa64a..0de21c5d272c 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 115d1c105e8a..30fb61c5f0cb 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned long __user *) sp;
diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index 7283e8b07b75..80d4270a71ac 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -2,8 +2,8 @@
 copyuser_64_t0
 copyuser_64_t1
 copyuser_64_t2
-copyuser_p7_t0
-copyuser_p7_t1
+copyuser_p7
+copyuser_p7_vmx
 memcpy_64_t0
 memcpy_64_t1
 memcpy_64_t2
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 42940f92d832..0c8efb0bddeb 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
-		copyuser_p7_t0 copyuser_p7_t1 \
+		copyuser_p7 copyuser_p7_vmx \
 		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
 		memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \
 		copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \
@@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%:	copyuser_64.S $(EXTRA_SOURCES)
 		-D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \
 		-o $@ $^
 
-$(OUTPUT)/copyuser_p7_t%:	copyuser_power7.S $(EXTRA_SOURCES)
+$(OUTPUT)/copyuser_p7:	copyuser_power7.S $(EXTRA_SOURCES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) \
 		-D COPY_LOOP=test___copy_tofrom_user_power7 \
-		-D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \
+		-o $@ $^
+
+$(OUTPUT)/copyuser_p7_vmx:       copyuser_power7.S $(EXTRA_SOURCES) ../utils.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test___copy_tofrom_user_power7_vmx \
+		-D VMX_TEST \
 		-o $@ $^
 
 # Strictly speaking, we only need the memcpy_64 test cases for big-endian
diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S
index ec8bcf2bf1c2..3a9cb8c9a3ee 100644
--- a/tools/testing/selftests/powerpc/copyloops/stubs.S
+++ b/tools/testing/selftests/powerpc/copyloops/stubs.S
@@ -1,13 +1,5 @@
 #include <asm/ppc_asm.h>
 
-FUNC_START(enter_vmx_usercopy)
-	li	r3,1
-	blr
-
-FUNC_START(exit_vmx_usercopy)
-	li	r3,0
-	blr
-
 FUNC_START(enter_vmx_ops)
 	li	r3,1
 	blr
diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c
index 0f6873618552..fb822534fbe9 100644
--- a/tools/testing/selftests/powerpc/copyloops/validate.c
+++ b/tools/testing/selftests/powerpc/copyloops/validate.c
@@ -12,6 +12,10 @@
 #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE)
 #define POISON 0xa5
 
+#ifdef VMX_TEST
+#define VMX_COPY_THRESHOLD 3328
+#endif
+
 unsigned long COPY_LOOP(void *to, const void *from, unsigned long size);
 
 static void do_one(char *src, char *dst, unsigned long src_off,
@@ -81,8 +85,12 @@ int test_copy_loop(void)
 	/* Fill with sequential bytes */
 	for (i = 0; i < BUFLEN; i++)
 		fill[i] = i & 0xff;
-
+#ifdef VMX_TEST
+	/* Force sizes above kernel VMX threshold (3328) */
+	for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) {
+#else
 	for (len = 1; len < MAX_LEN; len++) {
+#endif
 		for (src_off = 0; src_off < MAX_OFFSET; src_off++) {
 			for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) {
 				do_one(src, dst, src_off, dst_off, len,
@@ -96,5 +104,10 @@ int test_copy_loop(void)
 
 int main(void)
 {
+#ifdef VMX_TEST
+	/* Skip if Altivec not present */
+	SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported");
+#endif
+
 	return test_harness(test_copy_loop, str(COPY_LOOP));
 }