LoongArch: ptrace: Add hardware single step support

Use the generic ptrace_resume code for PTRACE_SYSCALL, PTRACE_CONT,
PTRACE_KILL and PTRACE_SINGLESTEP handling. This implies defining
arch_has_single_step() and implementing the user_enable_single_step()
and user_disable_single_step() functions.

LoongArch cannot do hardware single-stepping per se, the hardware
single-stepping it is achieved by configuring the instruction fetch
watchpoints (FWPS) and specifies that the next instruction must trigger
the watch exception by setting the mask bit. In some scenarios
CSR.FWPS.Skip is used to ignore the next hit result, avoid endless
repeated triggering of the same watchpoint without canceling it.
Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/include/asm/inst.h

@@ -351,6 +351,44 @@ static inline bool is_stack_alloc_ins(union loongarch_instruction *ip)
 		is_imm12_negative(ip->reg2i12_format.immediate);
 }
 
+static inline bool is_self_loop_ins(union loongarch_instruction *ip, struct pt_regs *regs)
+{
+	switch (ip->reg0i26_format.opcode) {
+	case b_op:
+	case bl_op:
+		if (ip->reg0i26_format.immediate_l == 0
+		    && ip->reg0i26_format.immediate_h == 0)
+			return true;
+	}
+
+	switch (ip->reg1i21_format.opcode) {
+	case beqz_op:
+	case bnez_op:
+	case bceqz_op:
+		if (ip->reg1i21_format.immediate_l == 0
+		    && ip->reg1i21_format.immediate_h == 0)
+			return true;
+	}
+
+	switch (ip->reg2i16_format.opcode) {
+	case beq_op:
+	case bne_op:
+	case blt_op:
+	case bge_op:
+	case bltu_op:
+	case bgeu_op:
+		if (ip->reg2i16_format.immediate == 0)
+			return true;
+		break;
+	case jirl_op:
+		if (regs->regs[ip->reg2i16_format.rj] +
+		    ((unsigned long)ip->reg2i16_format.immediate << 2) == (unsigned long)ip)
+			return true;
+	}
+
+	return false;
+}
+
 int larch_insn_read(void *addr, u32 *insnp);
 int larch_insn_write(void *addr, u32 insn);
 int larch_insn_patch_text(void *addr, u32 insn);

arch/loongarch/include/asm/loongarch.h

@@ -1055,6 +1055,9 @@ static __always_inline void iocsr_write64(u64 val, u32 reg)
 #define LOONGARCH_CSR_DERA		0x501	/* debug era */
 #define LOONGARCH_CSR_DESAVE		0x502	/* debug save */
 
+#define CSR_FWPC_SKIP_SHIFT		16
+#define CSR_FWPC_SKIP			(_ULCAST_(1) << CSR_FWPC_SKIP_SHIFT)
+
 /*
  * CSR_ECFG IM
  */

arch/loongarch/include/asm/processor.h

@@ -125,6 +125,7 @@ struct thread_struct {
 	/* Other stuff associated with the thread. */
 	unsigned long trap_nr;
 	unsigned long error_code;
+	unsigned long single_step; /* Used by PTRACE_SINGLESTEP */
 	struct loongarch_vdso_info *vdso;
 
 	/*

arch/loongarch/include/asm/ptrace.h

@@ -183,4 +183,8 @@ static inline void user_stack_pointer_set(struct pt_regs *regs,
 	regs->regs[3] = val;
 }
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#define arch_has_single_step()		(1)
+#endif
+
 #endif /* _ASM_PTRACE_H */

arch/loongarch/kernel/hw_breakpoint.c

@@ -153,6 +153,22 @@ void ptrace_hw_copy_thread(struct task_struct *tsk)
  */
 void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
 {
+	int i;
+	struct thread_struct *t = &tsk->thread;
+
+	for (i = 0; i < LOONGARCH_MAX_BRP; i++) {
+		if (t->hbp_break[i]) {
+			unregister_hw_breakpoint(t->hbp_break[i]);
+			t->hbp_break[i] = NULL;
+		}
+	}
+
+	for (i = 0; i < LOONGARCH_MAX_WRP; i++) {
+		if (t->hbp_watch[i]) {
+			unregister_hw_breakpoint(t->hbp_watch[i]);
+			t->hbp_watch[i] = NULL;
+		}
+	}
 }
 
 static int hw_breakpoint_control(struct perf_event *bp,
@@ -501,12 +517,21 @@ arch_initcall(arch_hw_breakpoint_init);
 
 void hw_breakpoint_thread_switch(struct task_struct *next)
 {
+	u64 addr, mask;
 	struct pt_regs *regs = task_pt_regs(next);
 
-	/* Update breakpoints */
-	update_bp_registers(regs, 1, 0);
-	/* Update watchpoints */
-	update_bp_registers(regs, 1, 1);
+	if (test_tsk_thread_flag(next, TIF_SINGLESTEP)) {
+		addr = read_wb_reg(CSR_CFG_ADDR, 0, 0);
+		mask = read_wb_reg(CSR_CFG_MASK, 0, 0);
+		if (!((regs->csr_era ^ addr) & ~mask))
+			csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS);
+		regs->csr_prmd |= CSR_PRMD_PWE;
+	} else {
+		/* Update breakpoints */
+		update_bp_registers(regs, 1, 0);
+		/* Update watchpoints */
+		update_bp_registers(regs, 1, 1);
+	}
 }
 
 void hw_breakpoint_pmu_read(struct perf_event *bp)

arch/loongarch/kernel/ptrace.c

@@ -31,6 +31,7 @@
 #include <linux/smp.h>
 #include <linux/stddef.h>
 #include <linux/seccomp.h>
+#include <linux/thread_info.h>
 #include <linux/uaccess.h>
 
 #include <asm/byteorder.h>
@@ -41,6 +42,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/reg.h>
 #include <asm/syscall.h>
 
@@ -833,3 +835,71 @@ long arch_ptrace(struct task_struct *child, long request,
 
 	return ret;
 }
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static void ptrace_triggered(struct perf_event *bp,
+		      struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event_attr attr;
+
+	attr = bp->attr;
+	attr.disabled = true;
+	modify_user_hw_breakpoint(bp, &attr);
+}
+
+static int set_single_step(struct task_struct *tsk, unsigned long addr)
+{
+	struct perf_event *bp;
+	struct perf_event_attr attr;
+	struct arch_hw_breakpoint *info;
+	struct thread_struct *thread = &tsk->thread;
+
+	bp = thread->hbp_break[0];
+	if (!bp) {
+		ptrace_breakpoint_init(&attr);
+
+		attr.bp_addr = addr;
+		attr.bp_len = HW_BREAKPOINT_LEN_8;
+		attr.bp_type = HW_BREAKPOINT_X;
+
+		bp = register_user_hw_breakpoint(&attr, ptrace_triggered,
+						 NULL, tsk);
+		if (IS_ERR(bp))
+			return PTR_ERR(bp);
+
+		thread->hbp_break[0] = bp;
+	} else {
+		int err;
+
+		attr = bp->attr;
+		attr.bp_addr = addr;
+
+		/* Reenable breakpoint */
+		attr.disabled = false;
+		err = modify_user_hw_breakpoint(bp, &attr);
+		if (unlikely(err))
+			return err;
+
+		csr_write64(attr.bp_addr, LOONGARCH_CSR_IB0ADDR);
+	}
+	info = counter_arch_bp(bp);
+	info->mask = TASK_SIZE - 1;
+
+	return 0;
+}
+
+/* ptrace API */
+void user_enable_single_step(struct task_struct *task)
+{
+	struct thread_info *ti = task_thread_info(task);
+
+	set_single_step(task, task_pt_regs(task)->csr_era);
+	task->thread.single_step = task_pt_regs(task)->csr_era;
+	set_ti_thread_flag(ti, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+#endif

arch/loongarch/kernel/traps.c

@@ -513,14 +513,49 @@ asmlinkage void noinstr do_watch(struct pt_regs *regs)
 {
 	irqentry_state_t state = irqentry_enter(regs);
 
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	breakpoint_handler(regs);
-	watchpoint_handler(regs);
-	force_sig(SIGTRAP);
-#else
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
 	pr_warn("Hardware watch point handler not implemented!\n");
-#endif
+#else
+	if (test_tsk_thread_flag(current, TIF_SINGLESTEP)) {
+		int llbit = (csr_read32(LOONGARCH_CSR_LLBCTL) & 0x1);
+		unsigned long pc = instruction_pointer(regs);
+		union loongarch_instruction *ip = (union loongarch_instruction *)pc;
+
+		if (llbit) {
+			/*
+			 * When the ll-sc combo is encountered, it is regarded as an single
+			 * instruction. So don't clear llbit and reset CSR.FWPS.Skip until
+			 * the llsc execution is completed.
+			 */
+			csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS);
+			csr_write32(CSR_LLBCTL_KLO, LOONGARCH_CSR_LLBCTL);
+			goto out;
+		}
 
+		if (pc == current->thread.single_step) {
+			/*
+			 * Certain insns are occasionally not skipped when CSR.FWPS.Skip is
+			 * set, such as fld.d/fst.d. So singlestep needs to compare whether
+			 * the csr_era is equal to the value of singlestep which last time set.
+			 */
+			if (!is_self_loop_ins(ip, regs)) {
+				/*
+				 * Check if the given instruction the target pc is equal to the
+				 * current pc, If yes, then we should not set the CSR.FWPS.SKIP
+				 * bit to break the original instruction stream.
+				 */
+				csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS);
+				goto out;
+			}
+		}
+	} else {
+		breakpoint_handler(regs);
+		watchpoint_handler(regs);
+	}
+
+	force_sig(SIGTRAP);
+out:
+#endif
 	irqentry_exit(regs, state);
 }