1 files changed, 545 insertions, 106 deletions

diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index d0854320bb50..8db1a15d7acb 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
 
@@ -22,15 +23,15 @@
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
-#include <asm/debugfs.h>
 #include <asm/hvcall.h>
+#include <asm/inst.h>
 #include <linux/uaccess.h>
 
 /*
  * Stores the breakpoints currently in use on each breakpoint address
  * register for every cpu
  */
-static DEFINE_PER_CPU(struct perf_event *, bp_per_reg);
+static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM_MAX]);
 
 /*
  * Returns total number of data or instruction breakpoints available.
@@ -38,10 +39,21 @@ static DEFINE_PER_CPU(struct perf_event *, bp_per_reg);
 int hw_breakpoint_slots(int type)
 {
 	if (type == TYPE_DATA)
-		return HBP_NUM;
+		return nr_wp_slots();
 	return 0;		/* no instruction breakpoints available */
 }
 
+static bool single_step_pending(void)
+{
+	int i;
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (current->thread.last_hit_ubp[i])
+			return true;
+	}
+	return false;
+}
+
 /*
  * Install a perf counter breakpoint.
  *
@@ -54,16 +66,26 @@ int hw_breakpoint_slots(int type)
 int arch_install_hw_breakpoint(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
+	struct perf_event **slot;
+	int i;
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		slot = this_cpu_ptr(&bp_per_reg[i]);
+		if (!*slot) {
+			*slot = bp;
+			break;
+		}
+	}
 
-	*slot = bp;
+	if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
+		return -EBUSY;
 
 	/*
 	 * Do not install DABR values if the instruction must be single-stepped.
 	 * If so, DABR will be populated in single_step_dabr_instruction().
 	 */
-	if (current->thread.last_hit_ubp != bp)
-		__set_breakpoint(info);
+	if (!single_step_pending())
+		__set_breakpoint(i, info);
 
 	return 0;
 }
@@ -79,15 +101,274 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
  */
 void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 {
-	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
+	struct arch_hw_breakpoint null_brk = {0};
+	struct perf_event **slot;
+	int i;
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		slot = this_cpu_ptr(&bp_per_reg[i]);
+		if (*slot == bp) {
+			*slot = NULL;
+			break;
+		}
+	}
 
-	if (*slot != bp) {
-		WARN_ONCE(1, "Can't find the breakpoint");
+	if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
 		return;
+
+	__set_breakpoint(i, &null_brk);
+}
+
+static bool is_ptrace_bp(struct perf_event *bp)
+{
+	return bp->overflow_handler == ptrace_triggered;
+}
+
+struct breakpoint {
+	struct list_head list;
+	struct perf_event *bp;
+	bool ptrace_bp;
+};
+
+/*
+ * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot
+ * rely on it safely synchronizing internals here; however, we can rely on it
+ * not requesting more breakpoints than available.
+ */
+static DEFINE_SPINLOCK(cpu_bps_lock);
+static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]);
+static DEFINE_SPINLOCK(task_bps_lock);
+static LIST_HEAD(task_bps);
+
+static struct breakpoint *alloc_breakpoint(struct perf_event *bp)
+{
+	struct breakpoint *tmp;
+
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return ERR_PTR(-ENOMEM);
+	tmp->bp = bp;
+	tmp->ptrace_bp = is_ptrace_bp(bp);
+	return tmp;
+}
+
+static bool bp_addr_range_overlap(struct perf_event *bp1, struct perf_event *bp2)
+{
+	__u64 bp1_saddr, bp1_eaddr, bp2_saddr, bp2_eaddr;
+
+	bp1_saddr = ALIGN_DOWN(bp1->attr.bp_addr, HW_BREAKPOINT_SIZE);
+	bp1_eaddr = ALIGN(bp1->attr.bp_addr + bp1->attr.bp_len, HW_BREAKPOINT_SIZE);
+	bp2_saddr = ALIGN_DOWN(bp2->attr.bp_addr, HW_BREAKPOINT_SIZE);
+	bp2_eaddr = ALIGN(bp2->attr.bp_addr + bp2->attr.bp_len, HW_BREAKPOINT_SIZE);
+
+	return (bp1_saddr < bp2_eaddr && bp1_eaddr > bp2_saddr);
+}
+
+static bool alternate_infra_bp(struct breakpoint *b, struct perf_event *bp)
+{
+	return is_ptrace_bp(bp) ? !b->ptrace_bp : b->ptrace_bp;
+}
+
+static bool can_co_exist(struct breakpoint *b, struct perf_event *bp)
+{
+	return !(alternate_infra_bp(b, bp) && bp_addr_range_overlap(b->bp, bp));
+}
+
+static int task_bps_add(struct perf_event *bp)
+{
+	struct breakpoint *tmp;
+
+	tmp = alloc_breakpoint(bp);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
+
+	spin_lock(&task_bps_lock);
+	list_add(&tmp->list, &task_bps);
+	spin_unlock(&task_bps_lock);
+	return 0;
+}
+
+static void task_bps_remove(struct perf_event *bp)
+{
+	struct list_head *pos, *q;
+
+	spin_lock(&task_bps_lock);
+	list_for_each_safe(pos, q, &task_bps) {
+		struct breakpoint *tmp = list_entry(pos, struct breakpoint, list);
+
+		if (tmp->bp == bp) {
+			list_del(&tmp->list);
+			kfree(tmp);
+			break;
+		}
 	}
+	spin_unlock(&task_bps_lock);
+}
 
-	*slot = NULL;
-	hw_breakpoint_disable();
+/*
+ * If any task has breakpoint from alternate infrastructure,
+ * return true. Otherwise return false.
+ */
+static bool all_task_bps_check(struct perf_event *bp)
+{
+	struct breakpoint *tmp;
+	bool ret = false;
+
+	spin_lock(&task_bps_lock);
+	list_for_each_entry(tmp, &task_bps, list) {
+		if (!can_co_exist(tmp, bp)) {
+			ret = true;
+			break;
+		}
+	}
+	spin_unlock(&task_bps_lock);
+	return ret;
+}
+
+/*
+ * If same task has breakpoint from alternate infrastructure,
+ * return true. Otherwise return false.
+ */
+static bool same_task_bps_check(struct perf_event *bp)
+{
+	struct breakpoint *tmp;
+	bool ret = false;
+
+	spin_lock(&task_bps_lock);
+	list_for_each_entry(tmp, &task_bps, list) {
+		if (tmp->bp->hw.target == bp->hw.target &&
+		    !can_co_exist(tmp, bp)) {
+			ret = true;
+			break;
+		}
+	}
+	spin_unlock(&task_bps_lock);
+	return ret;
+}
+
+static int cpu_bps_add(struct perf_event *bp)
+{
+	struct breakpoint **cpu_bp;
+	struct breakpoint *tmp;
+	int i = 0;
+
+	tmp = alloc_breakpoint(bp);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
+
+	spin_lock(&cpu_bps_lock);
+	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!cpu_bp[i]) {
+			cpu_bp[i] = tmp;
+			break;
+		}
+	}
+	spin_unlock(&cpu_bps_lock);
+	return 0;
+}
+
+static void cpu_bps_remove(struct perf_event *bp)
+{
+	struct breakpoint **cpu_bp;
+	int i = 0;
+
+	spin_lock(&cpu_bps_lock);
+	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!cpu_bp[i])
+			continue;
+
+		if (cpu_bp[i]->bp == bp) {
+			kfree(cpu_bp[i]);
+			cpu_bp[i] = NULL;
+			break;
+		}
+	}
+	spin_unlock(&cpu_bps_lock);
+}
+
+static bool cpu_bps_check(int cpu, struct perf_event *bp)
+{
+	struct breakpoint **cpu_bp;
+	bool ret = false;
+	int i;
+
+	spin_lock(&cpu_bps_lock);
+	cpu_bp = per_cpu_ptr(cpu_bps, cpu);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) {
+			ret = true;
+			break;
+		}
+	}
+	spin_unlock(&cpu_bps_lock);
+	return ret;
+}
+
+static bool all_cpu_bps_check(struct perf_event *bp)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (cpu_bps_check(cpu, bp))
+			return true;
+	}
+	return false;
+}
+
+int arch_reserve_bp_slot(struct perf_event *bp)
+{
+	int ret;
+
+	/* ptrace breakpoint */
+	if (is_ptrace_bp(bp)) {
+		if (all_cpu_bps_check(bp))
+			return -ENOSPC;
+
+		if (same_task_bps_check(bp))
+			return -ENOSPC;
+
+		return task_bps_add(bp);
+	}
+
+	/* perf breakpoint */
+	if (is_kernel_addr(bp->attr.bp_addr))
+		return 0;
+
+	if (bp->hw.target && bp->cpu == -1) {
+		if (same_task_bps_check(bp))
+			return -ENOSPC;
+
+		return task_bps_add(bp);
+	} else if (!bp->hw.target && bp->cpu != -1) {
+		if (all_task_bps_check(bp))
+			return -ENOSPC;
+
+		return cpu_bps_add(bp);
+	}
+
+	if (same_task_bps_check(bp))
+		return -ENOSPC;
+
+	ret = cpu_bps_add(bp);
+	if (ret)
+		return ret;
+	ret = task_bps_add(bp);
+	if (ret)
+		cpu_bps_remove(bp);
+
+	return ret;
+}
+
+void arch_release_bp_slot(struct perf_event *bp)
+{
+	if (!is_kernel_addr(bp->attr.bp_addr)) {
+		if (bp->hw.target)
+			task_bps_remove(bp);
+		if (bp->cpu != -1)
+			cpu_bps_remove(bp);
+	}
 }
 
 /*
@@ -102,8 +383,14 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 	 * restoration variables to prevent dangling pointers.
 	 * FIXME, this should not be using bp->ctx at all! Sayeth peterz.
 	 */
-	if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L))
-		bp->ctx->task->thread.last_hit_ubp = NULL;
+	if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) {
+		int i;
+
+		for (i = 0; i < nr_wp_slots(); i++) {
+			if (bp->ctx->task->thread.last_hit_ubp[i] == bp)
+				bp->ctx->task->thread.last_hit_ubp[i] = NULL;
+		}
+	}
 }
 
 /*
@@ -140,10 +427,10 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
  *    <---8 bytes--->
  *
  * In this case, we should configure hw as:
- *   start_addr = address & ~HW_BREAKPOINT_ALIGN
+ *   start_addr = address & ~(HW_BREAKPOINT_SIZE - 1)
  *   len = 16 bytes
  *
- * @start_addr and @end_addr are inclusive.
+ * @start_addr is inclusive but @end_addr is exclusive.
  */
 static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
 {
@@ -151,14 +438,15 @@ static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
 	u16 hw_len;
 	unsigned long start_addr, end_addr;
 
-	start_addr = hw->address & ~HW_BREAKPOINT_ALIGN;
-	end_addr = (hw->address + hw->len - 1) | HW_BREAKPOINT_ALIGN;
-	hw_len = end_addr - start_addr + 1;
+	start_addr = ALIGN_DOWN(hw->address, HW_BREAKPOINT_SIZE);
+	end_addr = ALIGN(hw->address + hw->len, HW_BREAKPOINT_SIZE);
+	hw_len = end_addr - start_addr;
 
 	if (dawr_enabled()) {
 		max_len = DAWR_MAX_LEN;
-		/* DAWR region can't cross 512 bytes boundary */
-		if ((start_addr >> 9) != (end_addr >> 9))
+		/* DAWR region can't cross 512 bytes boundary on p10 predecessors */
+		if (!cpu_has_feature(CPU_FTR_ARCH_31) &&
+		    (ALIGN_DOWN(start_addr, SZ_512) != ALIGN_DOWN(end_addr - 1, SZ_512)))
 			return -EINVAL;
 	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
 		/* 8xx can setup a range without limitation */
@@ -215,90 +503,150 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 {
 	struct arch_hw_breakpoint *info;
+	int i;
 
-	if (likely(!tsk->thread.last_hit_ubp))
-		return;
-
-	info = counter_arch_bp(tsk->thread.last_hit_ubp);
-	regs->msr &= ~MSR_SE;
-	__set_breakpoint(info);
-	tsk->thread.last_hit_ubp = NULL;
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (unlikely(tsk->thread.last_hit_ubp[i]))
+			goto reset;
+	}
+	return;
+
+reset:
+	regs_set_return_msr(regs, regs->msr & ~MSR_SE);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		info = counter_arch_bp(__this_cpu_read(bp_per_reg[i]));
+		__set_breakpoint(i, info);
+		tsk->thread.last_hit_ubp[i] = NULL;
+	}
 }
 
-static bool dar_within_range(unsigned long dar, struct arch_hw_breakpoint *info)
+static bool is_larx_stcx_instr(int type)
 {
-	return ((info->address <= dar) && (dar - info->address < info->len));
+	return type == LARX || type == STCX;
 }
 
-static bool
-dar_range_overlaps(unsigned long dar, int size, struct arch_hw_breakpoint *info)
+static bool is_octword_vsx_instr(int type, int size)
 {
-	return ((dar <= info->address + info->len - 1) &&
-		(dar + size - 1 >= info->address));
+	return ((type == LOAD_VSX || type == STORE_VSX) && size == 32);
 }
 
 /*
- * Handle debug exception notifications.
+ * We've failed in reliably handling the hw-breakpoint. Unregister
+ * it and throw a warning message to let the user know about it.
  */
-static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp,
-			     struct arch_hw_breakpoint *info)
+static void handler_error(struct perf_event *bp, struct arch_hw_breakpoint *info)
 {
-	unsigned int instr = 0;
-	int ret, type, size;
-	struct instruction_op op;
-	unsigned long addr = info->address;
-
-	if (__get_user_inatomic(instr, (unsigned int *)regs->nip))
-		goto fail;
-
-	ret = analyse_instr(&op, regs, instr);
-	type = GETTYPE(op.type);
-	size = GETSIZE(op.type);
+	WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.",
+	     info->address);
+	perf_event_disable_inatomic(bp);
+}
 
-	if (!ret && (type == LARX || type == STCX)) {
-		printk_ratelimited("Breakpoint hit on instruction that can't be emulated."
-				   " Breakpoint at 0x%lx will be disabled.\n", addr);
-		goto disable;
-	}
+static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info)
+{
+	printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n",
+			   info->address);
+	perf_event_disable_inatomic(bp);
+}
 
-	/*
-	 * If it's extraneous event, we still need to emulate/single-
-	 * step the instruction, but we don't generate an event.
-	 */
-	if (size && !dar_range_overlaps(regs->dar, size, info))
-		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
+			     struct arch_hw_breakpoint **info, int *hit,
+			     ppc_inst_t instr)
+{
+	int i;
+	int stepped;
 
 	/* Do not emulate user-space instructions, instead single-step them */
 	if (user_mode(regs)) {
-		current->thread.last_hit_ubp = bp;
-		regs->msr |= MSR_SE;
+		for (i = 0; i < nr_wp_slots(); i++) {
+			if (!hit[i])
+				continue;
+			current->thread.last_hit_ubp[i] = bp[i];
+			info[i] = NULL;
+		}
+		regs_set_return_msr(regs, regs->msr | MSR_SE);
 		return false;
 	}
 
-	if (!emulate_step(regs, instr))
-		goto fail;
-
+	stepped = emulate_step(regs, instr);
+	if (!stepped) {
+		for (i = 0; i < nr_wp_slots(); i++) {
+			if (!hit[i])
+				continue;
+			handler_error(bp[i], info[i]);
+			info[i] = NULL;
+		}
+		return false;
+	}
 	return true;
+}
+
+static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
+					     int *hit, unsigned long ea)
+{
+	int i;
+	unsigned long hw_end_addr;
 
-fail:
 	/*
-	 * We've failed in reliably handling the hw-breakpoint. Unregister
-	 * it and throw a warning message to let the user know about it.
+	 * Handle spurious exception only when any bp_per_reg is set.
+	 * Otherwise this might be created by xmon and not actually a
+	 * spurious exception.
 	 */
-	WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
-		"0x%lx will be disabled.", addr);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!info[i])
+			continue;
+
+		hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE);
+
+		/*
+		 * Ending address of DAWR range is less than starting
+		 * address of op.
+		 */
+		if ((hw_end_addr - 1) >= ea)
+			continue;
+
+		/*
+		 * Those addresses need to be in the same or in two
+		 * consecutive 512B blocks;
+		 */
+		if (((hw_end_addr - 1) >> 10) != (ea >> 10))
+			continue;
+
+		/*
+		 * 'op address + 64B' generates an address that has a
+		 * carry into bit 52 (crosses 2K boundary).
+		 */
+		if ((ea & 0x800) == ((ea + 64) & 0x800))
+			continue;
 
-disable:
-	perf_event_disable_inatomic(bp);
-	return false;
+		break;
+	}
+
+	if (i == nr_wp_slots())
+		return;
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (info[i]) {
+			hit[i] = 1;
+			info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+		}
+	}
 }
 
 int hw_breakpoint_handler(struct die_args *args)
 {
+	bool err = false;
 	int rc = NOTIFY_STOP;
-	struct perf_event *bp;
+	struct perf_event *bp[HBP_NUM_MAX] = { NULL };
 	struct pt_regs *regs = args->regs;
-	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint *info[HBP_NUM_MAX] = { NULL };
+	int i;
+	int hit[HBP_NUM_MAX] = {0};
+	int nr_hit = 0;
+	bool ptrace_bp = false;
+	ppc_inst_t instr = ppc_inst(0);
+	int type = 0;
+	int size = 0;
+	unsigned long ea;
 
 	/* Disable breakpoints during exception handling */
 	hw_breakpoint_disable();
@@ -311,12 +659,46 @@ int hw_breakpoint_handler(struct die_args *args)
 	 */
 	rcu_read_lock();
 
-	bp = __this_cpu_read(bp_per_reg);
-	if (!bp) {
-		rc = NOTIFY_DONE;
-		goto out;
+	if (!IS_ENABLED(CONFIG_PPC_8xx))
+		wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		bp[i] = __this_cpu_read(bp_per_reg[i]);
+		if (!bp[i])
+			continue;
+
+		info[i] = counter_arch_bp(bp[i]);
+		info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+
+		if (wp_check_constraints(regs, instr, ea, type, size, info[i])) {
+			if (!IS_ENABLED(CONFIG_PPC_8xx) &&
+			    ppc_inst_equal(instr, ppc_inst(0))) {
+				handler_error(bp[i], info[i]);
+				info[i] = NULL;
+				err = 1;
+				continue;
+			}
+
+			if (is_ptrace_bp(bp[i]))
+				ptrace_bp = true;
+			hit[i] = 1;
+			nr_hit++;
+		}
+	}
+
+	if (err)
+		goto reset;
+
+	if (!nr_hit) {
+		/* Workaround for Power10 DD1 */
+		if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 &&
+		    is_octword_vsx_instr(type, size)) {
+			handle_p10dd1_spurious_exception(info, hit, ea);
+		} else {
+			rc = NOTIFY_DONE;
+			goto out;
+		}
 	}
-	info = counter_arch_bp(bp);
 
 	/*
 	 * Return early after invoking user-callback function without restoring
@@ -324,29 +706,50 @@ int hw_breakpoint_handler(struct die_args *args)
 	 * one-shot mode. The ptrace-ed process will receive the SIGTRAP signal
 	 * generated in do_dabr().
 	 */
-	if (bp->overflow_handler == ptrace_triggered) {
-		perf_bp_event(bp, regs);
+	if (ptrace_bp) {
+		for (i = 0; i < nr_wp_slots(); i++) {
+			if (!hit[i])
+				continue;
+			perf_bp_event(bp[i], regs);
+			info[i] = NULL;
+		}
 		rc = NOTIFY_DONE;
-		goto out;
+		goto reset;
 	}
 
-	info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		if (!dar_within_range(regs->dar, info))
-			info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	} else {
-		if (!stepping_handler(regs, bp, info))
-			goto out;
+	if (!IS_ENABLED(CONFIG_PPC_8xx)) {
+		if (is_larx_stcx_instr(type)) {
+			for (i = 0; i < nr_wp_slots(); i++) {
+				if (!hit[i])
+					continue;
+				larx_stcx_err(bp[i], info[i]);
+				info[i] = NULL;
+			}
+			goto reset;
+		}
+
+		if (!stepping_handler(regs, bp, info, hit, instr))
+			goto reset;
 	}
 
 	/*
 	 * As a policy, the callback is invoked in a 'trigger-after-execute'
 	 * fashion
 	 */
-	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
-		perf_bp_event(bp, regs);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!hit[i])
+			continue;
+		if (!(info[i]->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+			perf_bp_event(bp[i], regs);
+	}
+
+reset:
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!info[i])
+			continue;
+		__set_breakpoint(i, info[i]);
+	}
 
-	__set_breakpoint(info);
 out:
 	rcu_read_unlock();
 	return rc;
@@ -361,26 +764,43 @@ static int single_step_dabr_instruction(struct die_args *args)
 	struct pt_regs *regs = args->regs;
 	struct perf_event *bp = NULL;
 	struct arch_hw_breakpoint *info;
+	int i;
+	bool found = false;
 
-	bp = current->thread.last_hit_ubp;
 	/*
 	 * Check if we are single-stepping as a result of a
 	 * previous HW Breakpoint exception
 	 */
-	if (!bp)
+	for (i = 0; i < nr_wp_slots(); i++) {
+		bp = current->thread.last_hit_ubp[i];
+
+		if (!bp)
+			continue;
+
+		found = true;
+		info = counter_arch_bp(bp);
+
+		/*
+		 * We shall invoke the user-defined callback function in the
+		 * single stepping handler to confirm to 'trigger-after-execute'
+		 * semantics
+		 */
+		if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+			perf_bp_event(bp, regs);
+		current->thread.last_hit_ubp[i] = NULL;
+	}
+
+	if (!found)
 		return NOTIFY_DONE;
 
-	info = counter_arch_bp(bp);
+	for (i = 0; i < nr_wp_slots(); i++) {
+		bp = __this_cpu_read(bp_per_reg[i]);
+		if (!bp)
+			continue;
 
-	/*
-	 * We shall invoke the user-defined callback function in the single
-	 * stepping handler to confirm to 'trigger-after-execute' semantics
-	 */
-	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
-		perf_bp_event(bp, regs);
-
-	__set_breakpoint(info);
-	current->thread.last_hit_ubp = NULL;
+		info = counter_arch_bp(bp);
+		__set_breakpoint(i, info);
+	}
 
 	/*
 	 * If the process was being single-stepped by ptrace, let the
@@ -419,13 +839,32 @@ NOKPROBE_SYMBOL(hw_breakpoint_exceptions_notify);
  */
 void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
 {
+	int i;
 	struct thread_struct *t = &tsk->thread;
 
-	unregister_hw_breakpoint(t->ptrace_bps[0]);
-	t->ptrace_bps[0] = NULL;
+	for (i = 0; i < nr_wp_slots(); i++) {
+		unregister_hw_breakpoint(t->ptrace_bps[i]);
+		t->ptrace_bps[i] = NULL;
+	}
 }
 
 void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
+
+void ptrace_triggered(struct perf_event *bp,
+		      struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event_attr attr;
+
+	/*
+	 * Disable the breakpoint request here since ptrace has defined a
+	 * one-shot behaviour for breakpoint exceptions in PPC64.
+	 * The SIGTRAP signal is generated automatically for us in do_dabr().
+	 * We don't have to do anything about that here
+	 */
+	attr = bp->attr;
+	attr.disabled = true;
+	modify_user_hw_breakpoint(bp, &attr);
+}