Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

4 files changed, 795 insertions, 7 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 3bf9fc6fd36c..79396e184bca 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -30,7 +30,8 @@ obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_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
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index d81568f783e5..3d33fb509ef4 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1169,7 +1169,7 @@ static nokprobe_inline int trap_compare(long v1, long v2)
 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 +1292,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 	rd = (instr >> 21) & 0x1f;
 	ra = (instr >> 16) & 0x1f;
 	rb = (instr >> 11) & 0x1f;
+	rc = (instr >> 6) & 0x1f;
 
 	switch (opcode) {
 #ifdef __powerpc64__
@@ -1305,6 +1306,38 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			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 +1704,23 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				(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 +1741,42 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				(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 +1847,20 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			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 +1962,20 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				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/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 6c47daa61614..9992c1ea7a1d 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -1,5 +1,5 @@
 /*
- * Simple sanity test for emulate_step load/store instructions.
+ * Simple sanity tests for instruction emulation infrastructure.
  *
  * Copyright IBM Corp. 2016
  *
@@ -14,6 +14,7 @@
 #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 +49,20 @@
 					___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 +86,15 @@ static void __init init_pt_regs(struct pt_regs *regs)
 	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 +446,7 @@ static void __init test_lxvd2x_stxvd2x(void)
 }
 #endif /* CONFIG_VSX */
 
-static int __init test_emulate_step(void)
+static void __init run_tests_load_store(void)
 {
 	test_ld();
 	test_lwz();
@@ -437,6 +457,513 @@ static int __init test_emulate_step(void)
 	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 000000000000..1580f34f4f4f
--- /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)