diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 6702868..b8de3be 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,16 +3,29 @@
 # Makefile for ppc-specific library files..
 #
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
-obj-y += string.o alloc.o code-patching.o feature-fixups.o
+KASAN_SANITIZE_code-patching.o := n
+KASAN_SANITIZE_feature-fixups.o := n
 
-obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o strlen_32.o
+ifdef CONFIG_KASAN
+CFLAGS_code-patching.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+obj-y += alloc.o code-patching.o feature-fixups.o pmem.o
+
+ifndef CONFIG_KASAN
+obj-y	+=	string.o memcmp_$(BITS).o
+obj-$(CONFIG_PPC32)	+= strlen_32.o
+endif
+
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 
 # See corresponding test in arch/powerpc/Makefile
 # 64-bit linker creates .sfpr on demand for final link (vmlinux),
@@ -26,16 +39,18 @@
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o pmem.o
+	   memcpy_64.o memcpy_mcsafe_64.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
-obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST)	+= test_emulate_step.o \
+					   test_emulate_step_exec_instr.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o \
-			   string_$(BITS).o memcmp_$(BITS).o
+			   string_$(BITS).o
 
-obj-y			+= sstep.o ldstfp.o quad.o
+obj-y			+= sstep.o
+obj-$(CONFIG_PPC_FPU)	+= ldstfp.o
 obj64-y			+= quad.o
 
 obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index 06796de..ce18087 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -2,7 +2,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/string.h>
 #include <asm/setup.h>
 
@@ -14,7 +14,10 @@
 	if (slab_is_available())
 		p = kzalloc(size, mask);
 	else {
-		p = memblock_virt_alloc(size, 0);
+		p = memblock_alloc(size, SMP_CACHE_BYTES);
+		if (!p)
+			panic("%s: Failed to allocate %zu bytes\n", __func__,
+			      size);
 	}
 	return p;
 }
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index aa22406..ecd150d 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains assembly-language implementations
  * of IP-style 1's complement checksum routines.
  *	
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index d05c8af..514978f 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains assembly-language implementations
  * of IP-style 1's complement checksum routines.
  *	
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index a0cb63f..fabe4db 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2010
  *
@@ -29,6 +17,7 @@
 	unsigned int csum;
 
 	might_sleep();
+	allow_read_from_user(src, len);
 
 	*err_ptr = 0;
 
@@ -37,7 +26,7 @@
 		goto out;
 	}
 
-	if (unlikely((len < 0) || !access_ok(VERIFY_READ, src, len))) {
+	if (unlikely((len < 0) || !access_ok(src, len))) {
 		*err_ptr = -EFAULT;
 		csum = (__force unsigned int)sum;
 		goto out;
@@ -60,6 +49,7 @@
 	}
 
 out:
+	prevent_read_from_user(src, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -70,6 +60,7 @@
 	unsigned int csum;
 
 	might_sleep();
+	allow_write_to_user(dst, len);
 
 	*err_ptr = 0;
 
@@ -78,7 +69,7 @@
 		goto out;
 	}
 
-	if (unlikely((len < 0) || !access_ok(VERIFY_WRITE, dst, len))) {
+	if (unlikely((len < 0) || !access_ok(dst, len))) {
 		*err_ptr = -EFAULT;
 		csum = -1; /* invalid checksum */
 		goto out;
@@ -97,6 +88,7 @@
 	}
 
 out:
+	prevent_write_to_user(dst, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 5ffee29..3345f03 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright 2008 Michael Ellerman, IBM Corporation.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -15,7 +11,6 @@
 #include <linux/cpuhotplug.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
-#include <linux/kprobes.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -26,9 +21,9 @@
 static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
 			       unsigned int *patch_addr)
 {
-	int err;
+	int err = 0;
 
-	__put_user_size(instr, patch_addr, 4, err);
+	__put_user_asm(instr, patch_addr, err, "stw");
 	if (err)
 		return err;
 
@@ -98,8 +93,7 @@
 	else
 		pfn = __pa_symbol(addr) >> PAGE_SHIFT;
 
-	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT),
-				pgprot_val(PAGE_KERNEL));
+	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT), PAGE_KERNEL);
 
 	pr_devel("Mapped addr %lx with pfn %lx:%d\n", text_poke_addr, pfn, err);
 	if (err)
@@ -205,22 +199,6 @@
 	return patch_instruction(addr, create_branch(addr, target, flags));
 }
 
-int patch_branch_site(s32 *site, unsigned long target, int flags)
-{
-	unsigned int *addr;
-
-	addr = (unsigned int *)((unsigned long)site + *site);
-	return patch_instruction(addr, create_branch(addr, target, flags));
-}
-
-int patch_instruction_site(s32 *site, unsigned int instr)
-{
-	unsigned int *addr;
-
-	addr = (unsigned int *)((unsigned long)site + *site);
-	return patch_instruction(addr, instr);
-}
-
 bool is_offset_in_branch_range(long offset)
 {
 	/*
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index ba66846..a3bcf47 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Memory copy functions for 32-bit PowerPC.
  *
  * Copyright (C) 1996-2005 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * 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/cache.h>
@@ -14,6 +10,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
 #include <asm/code-patching-asm.h>
+#include <asm/kasan.h>
 
 #define COPY_16_BYTES		\
 	lwz	r7,4(r4);	\
@@ -68,6 +65,7 @@
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
+#ifndef CONFIG_KASAN
 _GLOBAL(memset16)
 	rlwinm.	r0 ,r5, 31, 1, 31
 	addi	r6, r3, -4
@@ -81,6 +79,7 @@
 	sth	r4, 4(r6)
 	blr
 EXPORT_SYMBOL(memset16)
+#endif
 
 /*
  * Use dcbz on the complete cache lines in the destination
@@ -91,7 +90,7 @@
  * We therefore skip the optimised bloc that uses dcbz. This jump is
  * replaced by a nop once cache is active. This is done in machine_init()
  */
-_GLOBAL(memset)
+_GLOBAL_KASAN(memset)
 	cmplwi	0,r5,4
 	blt	7f
 
@@ -151,6 +150,7 @@
 	bdnz	9b
 	blr
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL_KASAN(memset)
 
 /*
  * This version uses dcbz on the complete cache lines in the
@@ -163,12 +163,12 @@
  * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
  * replaced by a nop once cache is active. This is done in machine_init()
  */
-_GLOBAL(memmove)
+_GLOBAL_KASAN(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	/* fall through */
 
-_GLOBAL(memcpy)
+_GLOBAL_KASAN(memcpy)
 1:	b	generic_memcpy
 	patch_site	1b, patch__memcpy_nocache
 
@@ -244,6 +244,8 @@
 65:	blr
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL_KASAN(memcpy)
+EXPORT_SYMBOL_KASAN(memmove)
 
 generic_memcpy:
 	srwi.	r7,r5,3
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 6943903..d1091b5 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2008 Mark Nelson, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/page.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index e38f956..a9844c6 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 96c514b..db8719a 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * 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/ppc_asm.h>
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 1a1fe18..28f0be5 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2011
  *
diff --git a/arch/powerpc/lib/div64.S b/arch/powerpc/lib/div64.S
index 83d9832..3d5426e 100644
--- a/arch/powerpc/lib/div64.S
+++ b/arch/powerpc/lib/div64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Divide a 64-bit unsigned number by a 32-bit unsigned number.
  * This routine assumes that the top 32 bits of the dividend are
@@ -7,11 +8,6 @@
  * On exit, r3 contains the remainder.
  *
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/error-inject.c b/arch/powerpc/lib/error-inject.c
new file mode 100644
index 0000000..407b992
--- /dev/null
+++ b/arch/powerpc/lib/error-inject.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	/*
+	 * Emulate 'blr'. 'regs' represents the state on entry of a predefined
+	 * function in the kernel/module, captured on a kprobe. We don't need
+	 * to worry about 32-bit userspace on a 64-bit kernel.
+	 */
+	regs->nip = regs->link;
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/powerpc/lib/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S
index ee7c5fd..b12168c 100644
--- a/arch/powerpc/lib/feature-fixups-test.S
+++ b/arch/powerpc/lib/feature-fixups-test.S
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2008 Michael Ellerman, IBM Corporation.
- *
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/feature-fixups.h>
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index e613b02..4ba634b 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
@@ -5,11 +6,6 @@
  *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
  *
  *  Copyright 2008 Michael Ellerman, IBM Corporation.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
@@ -118,7 +114,7 @@
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
-void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+static void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
 {
 	unsigned int instrs[3], *dest;
 	long *start, *end;
@@ -168,7 +164,7 @@
 		                                           : "unknown");
 }
 
-void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+static void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
 {
 	unsigned int instrs[6], *dest;
 	long *start, *end;
@@ -347,6 +343,29 @@
 
 	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
 }
+
+static void patch_btb_flush_section(long *curr)
+{
+	unsigned int *start, *end;
+
+	start = (void *)curr + *curr;
+	end = (void *)curr + *(curr + 1);
+	for (; start < end; start++) {
+		pr_devel("patching dest %lx\n", (unsigned long)start);
+		patch_instruction(start, PPC_INST_NOP);
+	}
+}
+
+void do_btb_flush_fixups(void)
+{
+	long *start, *end;
+
+	start = PTRRELOC(&__start__btb_flush_fixup);
+	end = PTRRELOC(&__stop__btb_flush_fixup);
+
+	for (; start < end; start += 2)
+		patch_btb_flush_section(start);
+}
 #endif /* CONFIG_PPC_FSL_BOOK3E */
 
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index 0526b22..6effad9 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2010
  *
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index 32e9199..e00abea 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Floating-point, VMX/Altivec and VSX loads and stores
  * for use in instruction emulation.
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
@@ -18,8 +14,6 @@
 #include <asm/asm-compat.h>
 #include <linux/errno.h>
 
-#ifdef CONFIG_PPC_FPU
-
 #define STKFRM	(PPC_MIN_STKFRM + 16)
 
 /* Get the contents of frN into *p; N is in r3 and p is in r4. */
@@ -241,5 +235,3 @@
 	MTMSRD(r6)
 	isync
 	blr
-
-#endif	/* CONFIG_PPC_FPU */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 35a0ef9..6440d59 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Spin and read/write lock operations.
  *
@@ -5,11 +6,6 @@
  * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
  * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
  *   Rework to support virtual processors
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -22,7 +18,7 @@
 #include <asm/hvcall.h>
 #include <asm/smp.h>
 
-void __spin_yield(arch_spinlock_t *lock)
+void splpar_spin_yield(arch_spinlock_t *lock)
 {
 	unsigned int lock_value, holder_cpu, yield_count;
 
@@ -40,14 +36,14 @@
 	plpar_hcall_norets(H_CONFER,
 		get_hard_smp_processor_id(holder_cpu), yield_count);
 }
-EXPORT_SYMBOL_GPL(__spin_yield);
+EXPORT_SYMBOL_GPL(splpar_spin_yield);
 
 /*
  * Waiting for a read lock or a write lock on a rwlock...
  * This turns out to be the same for read and write locks, since
  * we only know the holder if it is write-locked.
  */
-void __rw_yield(arch_rwlock_t *rw)
+void splpar_rw_yield(arch_rwlock_t *rw)
 {
 	int lock_value;
 	unsigned int holder_cpu, yield_count;
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index ec531de..9351ffa 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -1,18 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * String handling functions for PowerPC.
  *
  * Copyright (C) 1996 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * 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/kasan.h>
 
+#ifndef CONFIG_KASAN
 _GLOBAL(__memset16)
 	rlwimi	r4,r4,16,0,15
 	/* fall through */
@@ -29,8 +27,9 @@
 EXPORT_SYMBOL(__memset16)
 EXPORT_SYMBOL(__memset32)
 EXPORT_SYMBOL(__memset64)
+#endif
 
-_GLOBAL(memset)
+_GLOBAL_KASAN(memset)
 	neg	r0,r3
 	rlwimi	r4,r4,8,16,23
 	andi.	r0,r0,7			/* # bytes to be 8-byte aligned */
@@ -40,7 +39,7 @@
 .Lms:	PPC_MTOCRF(1,r0)
 	mr	r6,r3
 	blt	cr1,8f
-	beq+	3f			/* if already 8-byte aligned */
+	beq	3f			/* if already 8-byte aligned */
 	subf	r5,r0,r5
 	bf	31,1f
 	stb	r4,0(r6)
@@ -85,7 +84,7 @@
 	addi	r6,r6,8
 8:	cmpwi	r5,0
 	PPC_MTOCRF(1,r5)
-	beqlr+
+	beqlr
 	bf	29,9f
 	stw	r4,0(r6)
 	addi	r6,r6,4
@@ -96,8 +95,9 @@
 	stb	r4,0(r6)
 	blr
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL_KASAN(memset)
 
-_GLOBAL_TOC(memmove)
+_GLOBAL_TOC_KASAN(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	b	memcpy
@@ -139,3 +139,4 @@
 	mtctr	r7
 	b	1b
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL_KASAN(memmove)
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 844d8e7..384218d 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Author: Anton Blanchard <anton@au.ibm.com>
  * Copyright 2015 IBM Corporation.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
@@ -215,11 +211,20 @@
 	beq	.Lzero
 
 .Lcmp_rest_lt8bytes:
-	/* Here we have only less than 8 bytes to compare with. at least s1
-	 * Address is aligned with 8 bytes.
-	 * The next double words are load and shift right with appropriate
-	 * bits.
+	/*
+	 * Here we have less than 8 bytes to compare. At least s1 is aligned to
+	 * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
+	 * page boundary, otherwise we might read past the end of the buffer and
+	 * trigger a page fault. We use 4K as the conservative minimum page
+	 * size. If we detect that case we go to the byte-by-byte loop.
+	 *
+	 * Otherwise the next double word is loaded from s1 and s2, and shifted
+	 * right to compare the appropriate bits.
 	 */
+	clrldi	r6,r4,(64-12)	// r6 = r4 & 0xfff
+	cmpdi	r6,0xff8
+	bgt	.Lshort
+
 	subfic  r6,r5,8
 	slwi	r6,r6,3
 	LD	rA,0,r3
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 273ea67..016c91e 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -1,16 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * 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/ppc_asm.h>
 #include <asm/export.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
+#include <asm/kasan.h>
 
 #ifndef SELFTEST_CASE
 /* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */
@@ -18,7 +15,7 @@
 #endif
 
 	.align	7
-_GLOBAL_TOC(memcpy)
+_GLOBAL_TOC_KASAN(memcpy)
 BEGIN_FTR_SECTION
 #ifdef __LITTLE_ENDIAN__
 	cmpdi	cr7,r5,0
@@ -230,3 +227,4 @@
 	blr
 #endif
 EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL_KASAN(memcpy)
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
new file mode 100644
index 0000000..cb882d9
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:	EX_TABLE(300b,.Ldone)
+	.endm
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	/* Do a byte by byte copy to get the exact remaining size */
+	mtctr	r7
+46:
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	46b
+	li	r3,0
+	blr
+
+.Ldone:
+	mfctr	r3
+	blr
+
+
+_GLOBAL(memcpy_mcsafe)
+	mr	r7,r5
+	cmpldi	r5,16
+	blt	.Lshort_copy
+
+.Lcopy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+	subi	r7,r7,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	blt	5f
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+err2;	ld	r15,64(r4)
+err2;	ld	r16,72(r4)
+err2;	ld	r17,80(r4)
+err2;	ld	r18,88(r4)
+err2;	ld	r19,96(r4)
+err2;	ld	r20,104(r4)
+err2;	ld	r21,112(r4)
+err2;	ld	r22,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+err2;	std	r15,64(r3)
+err2;	std	r16,72(r3)
+err2;	std	r17,80(r3)
+err2;	std	r18,88(r3)
+err2;	std	r19,96(r3)
+err2;	std	r20,104(r3)
+err2;	std	r21,112(r3)
+err2;	std	r22,120(r3)
+	addi	r3,r3,128
+	subi	r7,r7,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+	addi	r4,r4,64
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+	addi	r3,r3,64
+	subi	r7,r7,64
+
+7:	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 63B to go */
+	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r8,16(r4)
+err1;	ld	r9,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r8,16(r3)
+err1;	std	r9,24(r3)
+	addi	r3,r3,32
+	subi	r7,r7,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+	subi	r7,r7,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+	subi	r7,r7,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 89bfefc..54f2263 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
index 53c0187..377712e 100644
--- a/arch/powerpc/lib/pmem.c
+++ b/arch/powerpc/lib/pmem.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright(c) 2017 IBM Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #include <linux/string.h>
@@ -23,14 +15,14 @@
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 }
 EXPORT_SYMBOL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 }
 EXPORT_SYMBOL(arch_invalidate_pmem);
 
@@ -43,7 +35,7 @@
 	unsigned long copied, start = (unsigned long) dest;
 
 	copied = __copy_from_user(dest, src, size);
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 
 	return copied;
 }
@@ -53,7 +45,7 @@
 	unsigned long start = (unsigned long) dest;
 
 	memcpy(dest, src, size);
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 
 	return dest;
 }
diff --git a/arch/powerpc/lib/quad.S b/arch/powerpc/lib/quad.S
index c4d12fa..da71760 100644
--- a/arch/powerpc/lib/quad.S
+++ b/arch/powerpc/lib/quad.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Quadword loads and stores
  * for use in instruction emulation.
  *
  * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index d81568f..c077acb 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Single-step support.
  *
  * Copyright (C) 2004 Paul Mackerras <paulus@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
@@ -1169,7 +1165,7 @@
 int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 		  unsigned int instr)
 {
-	unsigned int opcode, ra, rb, rd, spr, u;
+	unsigned int opcode, ra, rb, rc, rd, spr, u;
 	unsigned long int imm;
 	unsigned long int val, val2;
 	unsigned int mb, me, sh;
@@ -1292,6 +1288,7 @@
 	rd = (instr >> 21) & 0x1f;
 	ra = (instr >> 16) & 0x1f;
 	rb = (instr >> 11) & 0x1f;
+	rc = (instr >> 6) & 0x1f;
 
 	switch (opcode) {
 #ifdef __powerpc64__
@@ -1305,6 +1302,38 @@
 			goto trap;
 		return 1;
 
+#ifdef __powerpc64__
+	case 4:
+		if (!cpu_has_feature(CPU_FTR_ARCH_300))
+			return -1;
+
+		switch (instr & 0x3f) {
+		case 48:	/* maddhd */
+			asm volatile(PPC_MADDHD(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+
+		case 49:	/* maddhdu */
+			asm volatile(PPC_MADDHDU(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+
+		case 51:	/* maddld */
+			asm volatile(PPC_MADDLD(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+		}
+
+		/*
+		 * There are other instructions from ISA 3.0 with the same
+		 * primary opcode which do not have emulation support yet.
+		 */
+		return -1;
+#endif
+
 	case 7:		/* mulli */
 		op->val = regs->gpr[ra] * (short) instr;
 		goto compute_done;
@@ -1671,10 +1700,23 @@
 				(int) regs->gpr[rb];
 
 			goto arith_done;
-
+#ifdef __powerpc64__
+		case 265:	/* modud */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = regs->gpr[ra] % regs->gpr[rb];
+			goto compute_done;
+#endif
 		case 266:	/* add */
 			op->val = regs->gpr[ra] + regs->gpr[rb];
 			goto arith_done;
+
+		case 267:	/* moduw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (unsigned int) regs->gpr[ra] %
+				(unsigned int) regs->gpr[rb];
+			goto compute_done;
 #ifdef __powerpc64__
 		case 457:	/* divdu */
 			op->val = regs->gpr[ra] / regs->gpr[rb];
@@ -1695,6 +1737,42 @@
 				(int) regs->gpr[rb];
 			goto arith_done;
 
+		case 755:	/* darn */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			switch (ra & 0x3) {
+			case 0:
+				/* 32-bit conditioned */
+				asm volatile(PPC_DARN(%0, 0) : "=r" (op->val));
+				goto compute_done;
+
+			case 1:
+				/* 64-bit conditioned */
+				asm volatile(PPC_DARN(%0, 1) : "=r" (op->val));
+				goto compute_done;
+
+			case 2:
+				/* 64-bit raw */
+				asm volatile(PPC_DARN(%0, 2) : "=r" (op->val));
+				goto compute_done;
+			}
+
+			return -1;
+#ifdef __powerpc64__
+		case 777:	/* modsd */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (long int) regs->gpr[ra] %
+				(long int) regs->gpr[rb];
+			goto compute_done;
+#endif
+		case 779:	/* modsw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (int) regs->gpr[ra] %
+				(int) regs->gpr[rb];
+			goto compute_done;
+
 
 /*
  * Logical instructions
@@ -1765,6 +1843,20 @@
 			do_popcnt(regs, op, regs->gpr[rd], 64);
 			goto logical_done_nocc;
 #endif
+		case 538:	/* cnttzw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			val = (unsigned int) regs->gpr[rd];
+			op->val = (val ? __builtin_ctz(val) : 32);
+			goto logical_done;
+#ifdef __powerpc64__
+		case 570:	/* cnttzd */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			val = regs->gpr[rd];
+			op->val = (val ? __builtin_ctzl(val) : 64);
+			goto logical_done;
+#endif
 		case 922:	/* extsh */
 			op->val = (signed short) regs->gpr[rd];
 			goto logical_done;
@@ -1866,6 +1958,20 @@
 				op->xerval &= ~XER_CA;
 			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
+
+		case 890:	/* extswsli with sh_5 = 0 */
+		case 891:	/* extswsli with sh_5 = 1 */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->type = COMPUTE + SETREG;
+			sh = rb | ((instr & 2) << 4);
+			val = (signed int) regs->gpr[rd];
+			if (sh)
+				op->val = ROTATE(val, sh) & MASK64(0, 63 - sh);
+			else
+				op->val = val;
+			goto logical_done;
+
 #endif /* __powerpc64__ */
 
 /*
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 4b41970..2752b1c 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * String handling functions for PowerPC.
  *
  * Copyright (C) 1996 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 56aac4c..507b18b 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 6c47daa..4234706 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Simple sanity test for emulate_step load/store instructions.
+ * Simple sanity tests for instruction emulation infrastructure.
  *
  * Copyright IBM Corp. 2016
- *
- * This program is free software;  you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "emulate_step_test: " fmt
@@ -14,6 +10,7 @@
 #include <linux/ptrace.h>
 #include <asm/sstep.h>
 #include <asm/ppc-opcode.h>
+#include <asm/code-patching.h>
 
 #define IMM_L(i)		((uintptr_t)(i) & 0xffff)
 
@@ -48,7 +45,20 @@
 					___PPC_RA(a) | ___PPC_RB(b))
 #define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
 #define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_ADD(t, a, b)	(PPC_INST_ADD | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_ADD_DOT(t, a, b)	(PPC_INST_ADD | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b) | 0x1)
+#define TEST_ADDC(t, a, b)	(PPC_INST_ADDC | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_ADDC_DOT(t, a, b)	(PPC_INST_ADDC | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b) | 0x1)
 
+#define MAX_SUBTESTS	16
+
+#define IGNORE_GPR(n)	(0x1UL << (n))
+#define IGNORE_XER	(0x1UL << 32)
+#define IGNORE_CCR	(0x1UL << 33)
 
 static void __init init_pt_regs(struct pt_regs *regs)
 {
@@ -72,9 +82,15 @@
 	msr_cached = true;
 }
 
-static void __init show_result(char *ins, char *result)
+static void __init show_result(char *mnemonic, char *result)
 {
-	pr_info("%-14s : %s\n", ins, result);
+	pr_info("%-14s : %s\n", mnemonic, result);
+}
+
+static void __init show_result_with_descr(char *mnemonic, char *descr,
+					  char *result)
+{
+	pr_info("%-14s : %-50s %s\n", mnemonic, descr, result);
 }
 
 static void __init test_ld(void)
@@ -426,7 +442,7 @@
 }
 #endif /* CONFIG_VSX */
 
-static int __init test_emulate_step(void)
+static void __init run_tests_load_store(void)
 {
 	test_ld();
 	test_lwz();
@@ -437,6 +453,513 @@
 	test_lfdx_stfdx();
 	test_lvx_stvx();
 	test_lxvd2x_stxvd2x();
+}
+
+struct compute_test {
+	char *mnemonic;
+	struct {
+		char *descr;
+		unsigned long flags;
+		unsigned int instr;
+		struct pt_regs regs;
+	} subtests[MAX_SUBTESTS + 1];
+};
+
+static struct compute_test compute_tests[] = {
+	{
+		.mnemonic = "nop",
+		.subtests = {
+			{
+				.descr = "R0 = LONG_MAX",
+				.instr = PPC_INST_NOP,
+				.regs = {
+					.gpr[0] = LONG_MAX,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "add",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "add.",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "addc",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN | (uint)INT_MIN,
+					.gpr[22] = LONG_MIN | (uint)INT_MIN,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "addc.",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN | (uint)INT_MIN,
+					.gpr[22] = LONG_MIN | (uint)INT_MIN,
+				}
+			}
+		}
+	}
+};
+
+static int __init emulate_compute_instr(struct pt_regs *regs,
+					unsigned int instr)
+{
+	struct instruction_op op;
+
+	if (!regs || !instr)
+		return -EINVAL;
+
+	if (analyse_instr(&op, regs, instr) != 1 ||
+	    GETTYPE(op.type) != COMPUTE) {
+		pr_info("emulation failed, instruction = 0x%08x\n", instr);
+		return -EFAULT;
+	}
+
+	emulate_update_regs(regs, &op);
+	return 0;
+}
+
+static int __init execute_compute_instr(struct pt_regs *regs,
+					unsigned int instr)
+{
+	extern int exec_instr(struct pt_regs *regs);
+	extern s32 patch__exec_instr;
+
+	if (!regs || !instr)
+		return -EINVAL;
+
+	/* Patch the NOP with the actual instruction */
+	patch_instruction_site(&patch__exec_instr, instr);
+	if (exec_instr(regs)) {
+		pr_info("execution failed, instruction = 0x%08x\n", instr);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+#define gpr_mismatch(gprn, exp, got)	\
+	pr_info("GPR%u mismatch, exp = 0x%016lx, got = 0x%016lx\n",	\
+		gprn, exp, got)
+
+#define reg_mismatch(name, exp, got)	\
+	pr_info("%s mismatch, exp = 0x%016lx, got = 0x%016lx\n",	\
+		name, exp, got)
+
+static void __init run_tests_compute(void)
+{
+	unsigned long flags;
+	struct compute_test *test;
+	struct pt_regs *regs, exp, got;
+	unsigned int i, j, k, instr;
+	bool ignore_gpr, ignore_xer, ignore_ccr, passed;
+
+	for (i = 0; i < ARRAY_SIZE(compute_tests); i++) {
+		test = &compute_tests[i];
+
+		for (j = 0; j < MAX_SUBTESTS && test->subtests[j].descr; j++) {
+			instr = test->subtests[j].instr;
+			flags = test->subtests[j].flags;
+			regs = &test->subtests[j].regs;
+			ignore_xer = flags & IGNORE_XER;
+			ignore_ccr = flags & IGNORE_CCR;
+			passed = true;
+
+			memcpy(&exp, regs, sizeof(struct pt_regs));
+			memcpy(&got, regs, sizeof(struct pt_regs));
+
+			/*
+			 * Set a compatible MSR value explicitly to ensure
+			 * that XER and CR bits are updated appropriately
+			 */
+			exp.msr = MSR_KERNEL;
+			got.msr = MSR_KERNEL;
+
+			if (emulate_compute_instr(&got, instr) ||
+			    execute_compute_instr(&exp, instr)) {
+				passed = false;
+				goto print;
+			}
+
+			/* Verify GPR values */
+			for (k = 0; k < 32; k++) {
+				ignore_gpr = flags & IGNORE_GPR(k);
+				if (!ignore_gpr && exp.gpr[k] != got.gpr[k]) {
+					passed = false;
+					gpr_mismatch(k, exp.gpr[k], got.gpr[k]);
+				}
+			}
+
+			/* Verify LR value */
+			if (exp.link != got.link) {
+				passed = false;
+				reg_mismatch("LR", exp.link, got.link);
+			}
+
+			/* Verify XER value */
+			if (!ignore_xer && exp.xer != got.xer) {
+				passed = false;
+				reg_mismatch("XER", exp.xer, got.xer);
+			}
+
+			/* Verify CR value */
+			if (!ignore_ccr && exp.ccr != got.ccr) {
+				passed = false;
+				reg_mismatch("CR", exp.ccr, got.ccr);
+			}
+
+print:
+			show_result_with_descr(test->mnemonic,
+					       test->subtests[j].descr,
+					       passed ? "PASS" : "FAIL");
+		}
+	}
+}
+
+static int __init test_emulate_step(void)
+{
+	printk(KERN_INFO "Running instruction emulation self-tests ...\n");
+	run_tests_load_store();
+	run_tests_compute();
 
 	return 0;
 }
diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S
new file mode 100644
index 0000000..1580f34
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Non-emulated single-stepping support (currently limited to basic integer
+ * computations) used to validate the instruction emulation infrastructure.
+ *
+ * Copyright (C) 2019 IBM Corporation
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/code-patching-asm.h>
+#include <linux/errno.h>
+
+/* int exec_instr(struct pt_regs *regs) */
+_GLOBAL(exec_instr)
+
+	/*
+	 * Stack frame layout (INT_FRAME_SIZE bytes)
+	 *   In-memory pt_regs	(SP + STACK_FRAME_OVERHEAD)
+	 *   Scratch space	(SP + 8)
+	 *   Back chain		(SP + 0)
+	 */
+
+	/*
+	 * Allocate a new stack frame with enough space to hold the register
+	 * states in an in-memory pt_regs and also create the back chain to
+	 * the caller's stack frame.
+	 */
+	stdu	r1, -INT_FRAME_SIZE(r1)
+
+	/*
+	 * Save non-volatile GPRs on stack. This includes TOC pointer (GPR2)
+	 * and local variables (GPR14 to GPR31). The register for the pt_regs
+	 * parameter (GPR3) is saved additionally to ensure that the resulting
+	 * register state can still be saved even if GPR3 gets overwritten
+	 * when loading the initial register state for the test instruction.
+	 * The stack pointer (GPR1) and the thread pointer (GPR13) are not
+	 * saved as these should not be modified anyway.
+	 */
+	SAVE_2GPRS(2, r1)
+	SAVE_NVGPRS(r1)
+
+	/*
+	 * Save LR on stack to ensure that the return address is available
+	 * even if it gets overwritten by the test instruction.
+	 */
+	mflr	r0
+	std	r0, _LINK(r1)
+
+	/*
+	 * Save CR on stack. For simplicity, the entire register is saved
+	 * even though only fields 2 to 4 are non-volatile.
+	 */
+	mfcr	r0
+	std	r0, _CCR(r1)
+
+	/*
+	 * Load register state for the test instruction without touching the
+	 * critical non-volatile registers. The register state is passed as a
+	 * pointer to a pt_regs instance.
+	 */
+	subi	r31, r3, GPR0
+
+	/* Load LR from pt_regs */
+	ld	r0, _LINK(r31)
+	mtlr	r0
+
+	/* Load CR from pt_regs */
+	ld	r0, _CCR(r31)
+	mtcr	r0
+
+	/* Load XER from pt_regs */
+	ld	r0, _XER(r31)
+	mtxer	r0
+
+	/* Load GPRs from pt_regs */
+	REST_GPR(0, r31)
+	REST_10GPRS(2, r31)
+	REST_GPR(12, r31)
+	REST_NVGPRS(r31)
+
+	/* Placeholder for the test instruction */
+1:	nop
+	patch_site 1b patch__exec_instr
+
+	/*
+	 * Since GPR3 is overwritten, temporarily restore it back to its
+	 * original state, i.e. the pointer to pt_regs, to ensure that the
+	 * resulting register state can be saved. Before doing this, a copy
+	 * of it is created in the scratch space which is used later on to
+	 * save it to pt_regs.
+	 */
+	std	r3, 8(r1)
+	REST_GPR(3, r1)
+
+	/* Save resulting GPR state to pt_regs */
+	subi	r3, r3, GPR0
+	SAVE_GPR(0, r3)
+	SAVE_GPR(2, r3)
+	SAVE_8GPRS(4, r3)
+	SAVE_GPR(12, r3)
+	SAVE_NVGPRS(r3)
+
+	/* Save resulting LR to pt_regs */
+	mflr	r0
+	std	r0, _LINK(r3)
+
+	/* Save resulting CR to pt_regs */
+	mfcr	r0
+	std	r0, _CCR(r3)
+
+	/* Save resulting XER to pt_regs */
+	mfxer	r0
+	std	r0, _XER(r3)
+
+	/* Restore resulting GPR3 from scratch space and save it to pt_regs */
+	ld	r0, 8(r1)
+	std	r0, GPR3(r3)
+
+	/* Set return value to denote execution success */
+	li	r3, 0
+
+	/* Continue */
+	b	3f
+
+	/* Set return value to denote execution failure */
+2:	li	r3, -EFAULT
+
+	/* Restore the non-volatile GPRs from stack */
+3:	REST_GPR(2, r1)
+	REST_NVGPRS(r1)
+
+	/* Restore LR from stack to be able to return */
+	ld	r0, _LINK(r1)
+	mtlr	r0
+
+	/* Restore CR from stack */
+	ld	r0, _CCR(r1)
+	mtcr	r0
+
+	/* Tear down stack frame */
+	addi	r1, r1, INT_FRAME_SIZE
+
+	/* Return */
+	blr
+
+	/* Setup exception table */
+	EX_TABLE(1b, 2b)
+
+_ASM_NOKPROBE_SYMBOL(exec_instr)
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 9f34049..62e6c30 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2011
  *
diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c
index 4df240a..54e6197 100644
--- a/arch/powerpc/lib/xor_vmx.c
+++ b/arch/powerpc/lib/xor_vmx.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c
index dab2b6b..80dba91 100644
--- a/arch/powerpc/lib/xor_vmx_glue.c
+++ b/arch/powerpc/lib/xor_vmx_glue.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Altivec XOR operations
  *
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/preempt.h>