powerpc: Add prefixed instructions to instruction data type

For powerpc64, redefine the ppc_inst type so both word and prefixed
instructions can be represented. On powerpc32 the type will remain the
same. Update places which had assumed instructions to be 4 bytes long.
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Alistair Popple <alistair@popple.id.au>
[mpe: Rework the get_user_inst() macros to be parameterised, and don't
      assign to the dest if an error occurred. Use CONFIG_PPC64 not
      __powerpc64__ in a few places. Address other comments from
      Christophe. Fix some sparse complaints.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200506034050.24806-24-jniethe5@gmail.com

arch/powerpc/include/asm/inst.h

@@ -2,29 +2,80 @@
 #ifndef _ASM_POWERPC_INST_H
 #define _ASM_POWERPC_INST_H
 
+#include <asm/ppc-opcode.h>
+
 /*
  * Instruction data type for POWER
  */
 
 struct ppc_inst {
 	u32 val;
+#ifdef CONFIG_PPC64
+	u32 suffix;
+#endif
 } __packed;
 
-#define ppc_inst(x) ((struct ppc_inst){ .val = x })
-
 static inline u32 ppc_inst_val(struct ppc_inst x)
 {
 	return x.val;
 }
 
-static inline int ppc_inst_len(struct ppc_inst x)
+static inline int ppc_inst_primary_opcode(struct ppc_inst x)
 {
-	return sizeof(struct ppc_inst);
+	return ppc_inst_val(x) >> 26;
 }
 
-static inline int ppc_inst_primary_opcode(struct ppc_inst x)
+#ifdef CONFIG_PPC64
+#define ppc_inst(x) ((struct ppc_inst){ .val = (x), .suffix = 0xff })
+
+#define ppc_inst_prefix(x, y) ((struct ppc_inst){ .val = (x), .suffix = (y) })
+
+static inline u32 ppc_inst_suffix(struct ppc_inst x)
 {
-	return ppc_inst_val(x) >> 26;
+	return x.suffix;
+}
+
+static inline bool ppc_inst_prefixed(struct ppc_inst x)
+{
+	return (ppc_inst_primary_opcode(x) == 1) && ppc_inst_suffix(x) != 0xff;
+}
+
+static inline struct ppc_inst ppc_inst_swab(struct ppc_inst x)
+{
+	return ppc_inst_prefix(swab32(ppc_inst_val(x)),
+			       swab32(ppc_inst_suffix(x)));
+}
+
+static inline struct ppc_inst ppc_inst_read(const struct ppc_inst *ptr)
+{
+	u32 val, suffix;
+
+	val = *(u32 *)ptr;
+	if ((val >> 26) == OP_PREFIX) {
+		suffix = *((u32 *)ptr + 1);
+		return ppc_inst_prefix(val, suffix);
+	} else {
+		return ppc_inst(val);
+	}
+}
+
+static inline bool ppc_inst_equal(struct ppc_inst x, struct ppc_inst y)
+{
+	return *(u64 *)&x == *(u64 *)&y;
+}
+
+#else
+
+#define ppc_inst(x) ((struct ppc_inst){ .val = x })
+
+static inline bool ppc_inst_prefixed(struct ppc_inst x)
+{
+	return false;
+}
+
+static inline u32 ppc_inst_suffix(struct ppc_inst x)
+{
+	return 0;
 }
 
 static inline struct ppc_inst ppc_inst_swab(struct ppc_inst x)
@@ -42,6 +93,13 @@ static inline bool ppc_inst_equal(struct ppc_inst x, struct ppc_inst y)
 	return ppc_inst_val(x) == ppc_inst_val(y);
 }
 
+#endif /* CONFIG_PPC64 */
+
+static inline int ppc_inst_len(struct ppc_inst x)
+{
+	return ppc_inst_prefixed(x) ? 8 : 4;
+}
+
 int probe_user_read_inst(struct ppc_inst *inst,
 			 struct ppc_inst __user *nip);
 

arch/powerpc/include/asm/kprobes.h

@@ -43,7 +43,7 @@ extern kprobe_opcode_t optprobe_template_ret[];
 extern kprobe_opcode_t optprobe_template_end[];
 
 /* Fixed instruction size for powerpc */
-#define MAX_INSN_SIZE		1
+#define MAX_INSN_SIZE		2
 #define MAX_OPTIMIZED_LENGTH	sizeof(kprobe_opcode_t)	/* 4 bytes */
 #define MAX_OPTINSN_SIZE	(optprobe_template_end - optprobe_template_entry)
 #define RELATIVEJUMP_SIZE	sizeof(kprobe_opcode_t)	/* 4 bytes */

arch/powerpc/include/asm/ppc-opcode.h

@@ -158,6 +158,9 @@
 /* VMX Vector Store Instructions */
 #define OP_31_XOP_STVX          231
 
+/* Prefixed Instructions */
+#define OP_PREFIX		1
+
 #define OP_31   31
 #define OP_LWZ  32
 #define OP_STFS 52

arch/powerpc/include/asm/uaccess.h

@@ -105,6 +105,40 @@ static inline int __access_ok(unsigned long addr, unsigned long size,
 #define __put_user_inatomic(x, ptr) \
 	__put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
+#ifdef CONFIG_PPC64
+
+#define ___get_user_instr(gu_op, dest, ptr)				\
+({									\
+	long __gui_ret = 0;						\
+	unsigned long __gui_ptr = (unsigned long)ptr;			\
+	struct ppc_inst __gui_inst;					\
+	unsigned int __prefix, __suffix;				\
+	__gui_ret = gu_op(__prefix, (unsigned int __user *)__gui_ptr);	\
+	if (__gui_ret == 0) {						\
+		if ((__prefix >> 26) == OP_PREFIX) {			\
+			__gui_ret = gu_op(__suffix,			\
+				(unsigned int __user *)__gui_ptr + 1);	\
+			__gui_inst = ppc_inst_prefix(__prefix,		\
+						     __suffix);		\
+		} else {						\
+			__gui_inst = ppc_inst(__prefix);		\
+		}							\
+		if (__gui_ret == 0)					\
+			(dest) = __gui_inst;				\
+	}								\
+	__gui_ret;							\
+})
+
+#define get_user_instr(x, ptr) \
+	___get_user_instr(get_user, x, ptr)
+
+#define __get_user_instr(x, ptr) \
+	___get_user_instr(__get_user, x, ptr)
+
+#define __get_user_instr_inatomic(x, ptr) \
+	___get_user_instr(__get_user_inatomic, x, ptr)
+
+#else /* !CONFIG_PPC64 */
 #define get_user_instr(x, ptr) \
 	get_user((x).val, (u32 __user *)(ptr))
 
@@ -114,6 +148,8 @@ static inline int __access_ok(unsigned long addr, unsigned long size,
 #define __get_user_instr_inatomic(x, ptr) \
 	__get_user_nosleep((x).val, (u32 __user *)(ptr), sizeof(u32))
 
+#endif /* CONFIG_PPC64 */
+
 extern long __put_user_bad(void);
 
 /*

arch/powerpc/include/asm/uprobes.h

@@ -15,7 +15,7 @@
 
 typedef ppc_opcode_t uprobe_opcode_t;
 
-#define MAX_UINSN_BYTES		4
+#define MAX_UINSN_BYTES		8
 #define UPROBE_XOL_SLOT_BYTES	(MAX_UINSN_BYTES)
 
 /* The following alias is needed for reference from arch-agnostic code */

arch/powerpc/kernel/crash_dump.c

@@ -46,7 +46,7 @@ static void __init create_trampoline(unsigned long addr)
 	 * two instructions it doesn't require any registers.
 	 */
 	patch_instruction(p, ppc_inst(PPC_INST_NOP));
-	patch_branch(++p, addr + PHYSICAL_START, 0);
+	patch_branch((void *)p + 4, addr + PHYSICAL_START, 0);
 }
 
 void __init setup_kdump_trampoline(void)

arch/powerpc/kernel/optprobes.c

@@ -198,7 +198,7 @@ void patch_imm64_load_insns(unsigned long val, int reg, kprobe_opcode_t *addr)
 
 int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
 {
-	struct ppc_inst branch_op_callback, branch_emulate_step;
+	struct ppc_inst branch_op_callback, branch_emulate_step, temp;
 	kprobe_opcode_t *op_callback_addr, *emulate_step_addr, *buff;
 	long b_offset;
 	unsigned long nip, size;
@@ -282,7 +282,9 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
 	/*
 	 * 3. load instruction to be emulated into relevant register, and
 	 */
-	patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX);
+	temp = ppc_inst_read((struct ppc_inst *)p->ainsn.insn);
+	patch_imm64_load_insns(ppc_inst_val(temp) | ((u64)ppc_inst_suffix(temp) << 32),
+			       4, buff + TMPL_INSN_IDX);
 
 	/*
 	 * 4. branch back from trampoline

arch/powerpc/kernel/optprobes_head.S

@@ -94,6 +94,9 @@ optprobe_template_insn:
 	/* 2, Pass instruction to be emulated in r4 */
 	nop
 	nop
+	nop
+	nop
+	nop
 
 	.global optprobe_template_call_emulate
 optprobe_template_call_emulate:

arch/powerpc/lib/code-patching.c

@@ -24,7 +24,18 @@ static int __patch_instruction(struct ppc_inst *exec_addr, struct ppc_inst instr
 {
 	int err = 0;
 
-	__put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw");
+	if (!ppc_inst_prefixed(instr)) {
+		__put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw");
+	} else {
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+		__put_user_asm((u64)ppc_inst_suffix(instr) << 32 |
+			       ppc_inst_val(instr), patch_addr, err, "std");
+#else
+		__put_user_asm((u64)ppc_inst_val(instr) << 32 |
+			       ppc_inst_suffix(instr), patch_addr, err, "std");
+#endif
+	}
+
 	if (err)
 		return err;
 

arch/powerpc/lib/feature-fixups.c

@@ -84,12 +84,13 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
 	src = alt_start;
 	dest = start;
 
-	for (; src < alt_end; src++, dest++) {
+	for (; src < alt_end; src = (void *)src + ppc_inst_len(ppc_inst_read(src)),
+	     (dest = (void *)dest + ppc_inst_len(ppc_inst_read(dest)))) {
 		if (patch_alt_instruction(src, dest, alt_start, alt_end))
 			return 1;
 	}
 
-	for (; dest < end; dest++)
+	for (; dest < end; dest = (void *)dest + ppc_inst_len(ppc_inst(PPC_INST_NOP)))
 		raw_patch_instruction(dest, ppc_inst(PPC_INST_NOP));
 
 	return 0;

arch/powerpc/lib/inst.c

@@ -4,8 +4,47 @@
  */
 
 #include <linux/uaccess.h>
+#include <asm/disassemble.h>
 #include <asm/inst.h>
+#include <asm/ppc-opcode.h>
 
+#ifdef CONFIG_PPC64
+int probe_user_read_inst(struct ppc_inst *inst,
+			 struct ppc_inst __user *nip)
+{
+	unsigned int val, suffix;
+	int err;
+
+	err = probe_user_read(&val, nip, sizeof(val));
+	if (err)
+		return err;
+	if (get_op(val) == OP_PREFIX) {
+		err = probe_user_read(&suffix, (void __user *)nip + 4, 4);
+		*inst = ppc_inst_prefix(val, suffix);
+	} else {
+		*inst = ppc_inst(val);
+	}
+	return err;
+}
+
+int probe_kernel_read_inst(struct ppc_inst *inst,
+			   struct ppc_inst *src)
+{
+	unsigned int val, suffix;
+	int err;
+
+	err = probe_kernel_read(&val, src, sizeof(val));
+	if (err)
+		return err;
+	if (get_op(val) == OP_PREFIX) {
+		err = probe_kernel_read(&suffix, (void *)src + 4, 4);
+		*inst = ppc_inst_prefix(val, suffix);
+	} else {
+		*inst = ppc_inst(val);
+	}
+	return err;
+}
+#else /* !CONFIG_PPC64 */
 int probe_user_read_inst(struct ppc_inst *inst,
 			 struct ppc_inst __user *nip)
 {
@@ -31,3 +70,4 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
 
 	return err;
 }
+#endif /* CONFIG_PPC64 */

arch/powerpc/lib/sstep.c

@@ -1169,10 +1169,12 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 	unsigned long int imm;
 	unsigned long int val, val2;
 	unsigned int mb, me, sh;
-	unsigned int word;
+	unsigned int word, suffix;
 	long ival;
 
 	word = ppc_inst_val(instr);
+	suffix = ppc_inst_suffix(instr);
+
 	op->type = COMPUTE;
 
 	opcode = ppc_inst_primary_opcode(instr);

arch/powerpc/xmon/xmon.c

@@ -758,8 +758,8 @@ static int xmon_bpt(struct pt_regs *regs)
 
 	/* Are we at the trap at bp->instr[1] for some bp? */
 	bp = in_breakpoint_table(regs->nip, &offset);
-	if (bp != NULL && offset == 4) {
-		regs->nip = bp->address + 4;
+	if (bp != NULL && (offset == 4 || offset == 8)) {
+		regs->nip = bp->address + offset;
 		atomic_dec(&bp->ref_count);
 		return 1;
 	}

arch/powerpc/xmon/xmon_bpts.S

@@ -4,6 +4,8 @@
 #include <asm/asm-offsets.h>
 #include "xmon_bpts.h"
 
+/* Prefixed instructions can not cross 64 byte boundaries */
+.align 6
 .global bpt_table
 bpt_table:
 	.space NBPTS * BPT_SIZE