1 files changed, 319 insertions, 224 deletions

diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 21e3a4ab3b8c..c9f3f0467570 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -24,6 +24,7 @@
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
 #include <linux/errno.h>
+#include <linux/hardirq.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/smp.h>
@@ -44,6 +45,7 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
+static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -52,87 +54,6 @@ static u8 debug_arch;
 /* Maximum supported watchpoint length. */
 static u8 max_watchpoint_len;
 
-/* Determine number of BRP registers available. */
-static int get_num_brps(void)
-{
-	u32 didr;
-	ARM_DBG_READ(c0, 0, didr);
-	return ((didr >> 24) & 0xf) + 1;
-}
-
-/* Determine number of WRP registers available. */
-static int get_num_wrps(void)
-{
-	/*
-	 * FIXME: When a watchpoint fires, the only way to work out which
-	 * watchpoint it was is by disassembling the faulting instruction
-	 * and working out the address of the memory access.
-	 *
-	 * Furthermore, we can only do this if the watchpoint was precise
-	 * since imprecise watchpoints prevent us from calculating register
-	 * based addresses.
-	 *
-	 * For the time being, we only report 1 watchpoint register so we
-	 * always know which watchpoint fired. In the future we can either
-	 * add a disassembler and address generation emulator, or we can
-	 * insert a check to see if the DFAR is set on watchpoint exception
-	 * entry [the ARM ARM states that the DFAR is UNKNOWN, but
-	 * experience shows that it is set on some implementations].
-	 */
-
-#if 0
-	u32 didr, wrps;
-	ARM_DBG_READ(c0, 0, didr);
-	return ((didr >> 28) & 0xf) + 1;
-#endif
-
-	return 1;
-}
-
-int hw_breakpoint_slots(int type)
-{
-	/*
-	 * We can be called early, so don't rely on
-	 * our static variables being initialised.
-	 */
-	switch (type) {
-	case TYPE_INST:
-		return get_num_brps();
-	case TYPE_DATA:
-		return get_num_wrps();
-	default:
-		pr_warning("unknown slot type: %d\n", type);
-		return 0;
-	}
-}
-
-/* Determine debug architecture. */
-static u8 get_debug_arch(void)
-{
-	u32 didr;
-
-	/* Do we implement the extended CPUID interface? */
-	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
-		pr_warning("CPUID feature registers not supported. "
-				"Assuming v6 debug is present.\n");
-		return ARM_DEBUG_ARCH_V6;
-	}
-
-	ARM_DBG_READ(c0, 0, didr);
-	return (didr >> 16) & 0xf;
-}
-
-/* Does this core support mismatch breakpoints? */
-static int core_has_mismatch_bps(void)
-{
-	return debug_arch >= ARM_DEBUG_ARCH_V7_ECP14 && core_num_brps > 1;
-}
-
-u8 arch_get_debug_arch(void)
-{
-	return debug_arch;
-}
-
 #define READ_WB_REG_CASE(OP2, M, VAL)		\
 	case ((OP2 << 4) + M):			\
 		ARM_DBG_READ(c ## M, OP2, VAL); \
@@ -210,6 +131,94 @@ static void write_wb_reg(int n, u32 val)
 	isb();
 }
 
+/* Determine debug architecture. */
+static u8 get_debug_arch(void)
+{
+	u32 didr;
+
+	/* Do we implement the extended CPUID interface? */
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+		pr_warning("CPUID feature registers not supported. "
+				"Assuming v6 debug is present.\n");
+		return ARM_DEBUG_ARCH_V6;
+	}
+
+	ARM_DBG_READ(c0, 0, didr);
+	return (didr >> 16) & 0xf;
+}
+
+u8 arch_get_debug_arch(void)
+{
+	return debug_arch;
+}
+
+/* Determine number of BRP register available. */
+static int get_num_brp_resources(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 24) & 0xf) + 1;
+}
+
+/* Does this core support mismatch breakpoints? */
+static int core_has_mismatch_brps(void)
+{
+	return (get_debug_arch() >= ARM_DEBUG_ARCH_V7_ECP14 &&
+		get_num_brp_resources() > 1);
+}
+
+/* Determine number of usable WRPs available. */
+static int get_num_wrps(void)
+{
+	/*
+	 * FIXME: When a watchpoint fires, the only way to work out which
+	 * watchpoint it was is by disassembling the faulting instruction
+	 * and working out the address of the memory access.
+	 *
+	 * Furthermore, we can only do this if the watchpoint was precise
+	 * since imprecise watchpoints prevent us from calculating register
+	 * based addresses.
+	 *
+	 * Providing we have more than 1 breakpoint register, we only report
+	 * a single watchpoint register for the time being. This way, we always
+	 * know which watchpoint fired. In the future we can either add a
+	 * disassembler and address generation emulator, or we can insert a
+	 * check to see if the DFAR is set on watchpoint exception entry
+	 * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
+	 * that it is set on some implementations].
+	 */
+
+#if 0
+	int wrps;
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	wrps = ((didr >> 28) & 0xf) + 1;
+#endif
+	int wrps = 1;
+
+	if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
+		wrps = get_num_brp_resources() - 1;
+
+	return wrps;
+}
+
+/* We reserve one breakpoint for each watchpoint. */
+static int get_num_reserved_brps(void)
+{
+	if (core_has_mismatch_brps())
+		return get_num_wrps();
+	return 0;
+}
+
+/* Determine number of usable BRPs available. */
+static int get_num_brps(void)
+{
+	int brps = get_num_brp_resources();
+	if (core_has_mismatch_brps())
+		brps -= get_num_reserved_brps();
+	return brps;
+}
+
 /*
  * In order to access the breakpoint/watchpoint control registers,
  * we must be running in debug monitor mode. Unfortunately, we can
@@ -230,8 +239,12 @@ static int enable_monitor_mode(void)
 		goto out;
 	}
 
+	/* If monitor mode is already enabled, just return. */
+	if (dscr & ARM_DSCR_MDBGEN)
+		goto out;
+
 	/* Write to the corresponding DSCR. */
-	switch (debug_arch) {
+	switch (get_debug_arch()) {
 	case ARM_DEBUG_ARCH_V6:
 	case ARM_DEBUG_ARCH_V6_1:
 		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
@@ -246,15 +259,30 @@ static int enable_monitor_mode(void)
 
 	/* Check that the write made it through. */
 	ARM_DBG_READ(c1, 0, dscr);
-	if (WARN_ONCE(!(dscr & ARM_DSCR_MDBGEN),
-				"failed to enable monitor mode.")) {
+	if (!(dscr & ARM_DSCR_MDBGEN))
 		ret = -EPERM;
-	}
 
 out:
 	return ret;
 }
 
+int hw_breakpoint_slots(int type)
+{
+	/*
+	 * We can be called early, so don't rely on
+	 * our static variables being initialised.
+	 */
+	switch (type) {
+	case TYPE_INST:
+		return get_num_brps();
+	case TYPE_DATA:
+		return get_num_wrps();
+	default:
+		pr_warning("unknown slot type: %d\n", type);
+		return 0;
+	}
+}
+
 /*
  * Check if 8-bit byte-address select is available.
  * This clobbers WRP 0.
@@ -268,9 +296,6 @@ static u8 get_max_wp_len(void)
 	if (debug_arch < ARM_DEBUG_ARCH_V7_ECP14)
 		goto out;
 
-	if (enable_monitor_mode())
-		goto out;
-
 	memset(&ctrl, 0, sizeof(ctrl));
 	ctrl.len = ARM_BREAKPOINT_LEN_8;
 	ctrl_reg = encode_ctrl_reg(ctrl);
@@ -290,23 +315,6 @@ u8 arch_get_max_wp_len(void)
 }
 
 /*
- * Handler for reactivating a suspended watchpoint when the single
- * step `mismatch' breakpoint is triggered.
- */
-static void wp_single_step_handler(struct perf_event *bp, int unused,
-				   struct perf_sample_data *data,
-				   struct pt_regs *regs)
-{
-	perf_event_enable(counter_arch_bp(bp)->suspended_wp);
-	unregister_hw_breakpoint(bp);
-}
-
-static int bp_is_single_step(struct perf_event *bp)
-{
-	return bp->overflow_handler == wp_single_step_handler;
-}
-
-/*
  * Install a perf counter breakpoint.
  */
 int arch_install_hw_breakpoint(struct perf_event *bp)
@@ -314,30 +322,41 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	struct perf_event **slot, **slots;
 	int i, max_slots, ctrl_base, val_base, ret = 0;
+	u32 addr, ctrl;
 
 	/* Ensure that we are in monitor mode and halting mode is disabled. */
 	ret = enable_monitor_mode();
 	if (ret)
 		goto out;
 
+	addr = info->address;
+	ctrl = encode_ctrl_reg(info->ctrl) | 0x1;
+
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		ctrl_base = ARM_BASE_BCR;
 		val_base = ARM_BASE_BVR;
-		slots = __get_cpu_var(bp_on_reg);
-		max_slots = core_num_brps - 1;
-
-		if (bp_is_single_step(bp)) {
-			info->ctrl.mismatch = 1;
-			i = max_slots;
-			slots[i] = bp;
-			goto setup;
+		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		max_slots = core_num_brps;
+		if (info->step_ctrl.enabled) {
+			/* Override the breakpoint data with the step data. */
+			addr = info->trigger & ~0x3;
+			ctrl = encode_ctrl_reg(info->step_ctrl);
 		}
 	} else {
 		/* Watchpoint */
-		ctrl_base = ARM_BASE_WCR;
-		val_base = ARM_BASE_WVR;
-		slots = __get_cpu_var(wp_on_reg);
+		if (info->step_ctrl.enabled) {
+			/* Install into the reserved breakpoint region. */
+			ctrl_base = ARM_BASE_BCR + core_num_brps;
+			val_base = ARM_BASE_BVR + core_num_brps;
+			/* Override the watchpoint data with the step data. */
+			addr = info->trigger & ~0x3;
+			ctrl = encode_ctrl_reg(info->step_ctrl);
+		} else {
+			ctrl_base = ARM_BASE_WCR;
+			val_base = ARM_BASE_WVR;
+		}
+		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -355,12 +374,11 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		goto out;
 	}
 
-setup:
 	/* Setup the address register. */
-	write_wb_reg(val_base + i, info->address);
+	write_wb_reg(val_base + i, addr);
 
 	/* Setup the control register. */
-	write_wb_reg(ctrl_base + i, encode_ctrl_reg(info->ctrl) | 0x1);
+	write_wb_reg(ctrl_base + i, ctrl);
 
 out:
 	return ret;
@@ -375,18 +393,15 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		base = ARM_BASE_BCR;
-		slots = __get_cpu_var(bp_on_reg);
-		max_slots = core_num_brps - 1;
-
-		if (bp_is_single_step(bp)) {
-			i = max_slots;
-			slots[i] = NULL;
-			goto reset;
-		}
+		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
-		base = ARM_BASE_WCR;
-		slots = __get_cpu_var(wp_on_reg);
+		if (info->step_ctrl.enabled)
+			base = ARM_BASE_BCR + core_num_brps;
+		else
+			base = ARM_BASE_WCR;
+		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -403,7 +418,6 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
 		return;
 
-reset:
 	/* Reset the control register. */
 	write_wb_reg(base + i, 0);
 }
@@ -537,12 +551,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 		return -EINVAL;
 	}
 
+	/*
+	 * Breakpoints must be of length 2 (thumb) or 4 (ARM) bytes.
+	 * Watchpoints can be of length 1, 2, 4 or 8 bytes if supported
+	 * by the hardware and must be aligned to the appropriate number of
+	 * bytes.
+	 */
+	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+	    info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+	    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+		return -EINVAL;
+
 	/* Address */
 	info->address = bp->attr.bp_addr;
 
 	/* Privilege */
 	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(bp) && !bp_is_single_step(bp))
+	if (arch_check_bp_in_kernelspace(bp))
 		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
@@ -561,7 +586,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret = 0;
-	u32 bytelen, max_len, offset, alignment_mask = 0x3;
+	u32 offset, alignment_mask = 0x3;
 
 	/* Build the arch_hw_breakpoint. */
 	ret = arch_build_bp_info(bp);
@@ -571,84 +596,85 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	/* Check address alignment. */
 	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
 		alignment_mask = 0x7;
-	if (info->address & alignment_mask) {
-		/*
-		 * Try to fix the alignment. This may result in a length
-		 * that is too large, so we must check for that.
-		 */
-		bytelen = get_hbp_len(info->ctrl.len);
-		max_len = info->ctrl.type == ARM_BREAKPOINT_EXECUTE ? 4 :
-				max_watchpoint_len;
-
-		if (max_len >= 8)
-			offset = info->address & 0x7;
-		else
-			offset = info->address & 0x3;
-
-		if (bytelen > (1 << ((max_len - (offset + 1)) >> 1))) {
-			ret = -EFBIG;
-			goto out;
-		}
-
-		info->ctrl.len <<= offset;
-		info->address &= ~offset;
-
-		pr_debug("breakpoint alignment fixup: length = 0x%x, "
-			"address = 0x%x\n", info->ctrl.len, info->address);
+	offset = info->address & alignment_mask;
+	switch (offset) {
+	case 0:
+		/* Aligned */
+		break;
+	case 1:
+		/* Allow single byte watchpoint. */
+		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			break;
+	case 2:
+		/* Allow halfword watchpoints and breakpoints. */
+		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+			break;
+	default:
+		ret = -EINVAL;
+		goto out;
 	}
 
+	info->address &= ~alignment_mask;
+	info->ctrl.len <<= offset;
+
 	/*
 	 * Currently we rely on an overflow handler to take
 	 * care of single-stepping the breakpoint when it fires.
 	 * In the case of userspace breakpoints on a core with V7 debug,
-	 * we can use the mismatch feature as a poor-man's hardware single-step.
+	 * we can use the mismatch feature as a poor-man's hardware
+	 * single-step, but this only works for per-task breakpoints.
 	 */
 	if (WARN_ONCE(!bp->overflow_handler &&
-		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_bps()),
+		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
+		 || !bp->hw.bp_target),
 			"overflow handler required but none found")) {
 		ret = -EINVAL;
-		goto out;
 	}
 out:
 	return ret;
 }
 
-static void update_mismatch_flag(int idx, int flag)
+/*
+ * Enable/disable single-stepping over the breakpoint bp at address addr.
+ */
+static void enable_single_step(struct perf_event *bp, u32 addr)
 {
-	struct perf_event *bp = __get_cpu_var(bp_on_reg[idx]);
-	struct arch_hw_breakpoint *info;
-
-	if (bp == NULL)
-		return;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	info = counter_arch_bp(bp);
+	arch_uninstall_hw_breakpoint(bp);
+	info->step_ctrl.mismatch  = 1;
+	info->step_ctrl.len	  = ARM_BREAKPOINT_LEN_4;
+	info->step_ctrl.type	  = ARM_BREAKPOINT_EXECUTE;
+	info->step_ctrl.privilege = info->ctrl.privilege;
+	info->step_ctrl.enabled	  = 1;
+	info->trigger		  = addr;
+	arch_install_hw_breakpoint(bp);
+}
 
-	/* Update the mismatch field to enter/exit `single-step' mode */
-	if (!bp->overflow_handler && info->ctrl.mismatch != flag) {
-		info->ctrl.mismatch = flag;
-		write_wb_reg(ARM_BASE_BCR + idx, encode_ctrl_reg(info->ctrl) | 0x1);
-	}
+static void disable_single_step(struct perf_event *bp)
+{
+	arch_uninstall_hw_breakpoint(bp);
+	counter_arch_bp(bp)->step_ctrl.enabled = 0;
+	arch_install_hw_breakpoint(bp);
 }
 
 static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 {
 	int i;
-	struct perf_event *bp, **slots = __get_cpu_var(wp_on_reg);
+	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
-	struct perf_event_attr attr;
+
+	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
 	/* Without a disassembler, we can only handle 1 watchpoint. */
 	BUG_ON(core_num_wrps > 1);
 
-	hw_breakpoint_init(&attr);
-	attr.bp_addr	= regs->ARM_pc & ~0x3;
-	attr.bp_len	= HW_BREAKPOINT_LEN_4;
-	attr.bp_type	= HW_BREAKPOINT_X;
-
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
-		if (slots[i] == NULL) {
+		wp = slots[i];
+
+		if (wp == NULL) {
 			rcu_read_unlock();
 			continue;
 		}
@@ -658,24 +684,51 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 		 * single watchpoint, we can set the trigger to the lowest
 		 * possible faulting address.
 		 */
-		info = counter_arch_bp(slots[i]);
-		info->trigger = slots[i]->attr.bp_addr;
+		info = counter_arch_bp(wp);
+		info->trigger = wp->attr.bp_addr;
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
-		perf_bp_event(slots[i], regs);
+		perf_bp_event(wp, regs);
 
 		/*
 		 * If no overflow handler is present, insert a temporary
 		 * mismatch breakpoint so we can single-step over the
 		 * watchpoint trigger.
 		 */
-		if (!slots[i]->overflow_handler) {
-			bp = register_user_hw_breakpoint(&attr,
-							 wp_single_step_handler,
-							 current);
-			counter_arch_bp(bp)->suspended_wp = slots[i];
-			perf_event_disable(slots[i]);
-		}
+		if (!wp->overflow_handler)
+			enable_single_step(wp, instruction_pointer(regs));
+
+		rcu_read_unlock();
+	}
+}
 
+static void watchpoint_single_step_handler(unsigned long pc)
+{
+	int i;
+	struct perf_event *wp, **slots;
+	struct arch_hw_breakpoint *info;
+
+	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+
+	for (i = 0; i < core_num_reserved_brps; ++i) {
+		rcu_read_lock();
+
+		wp = slots[i];
+
+		if (wp == NULL)
+			goto unlock;
+
+		info = counter_arch_bp(wp);
+		if (!info->step_ctrl.enabled)
+			goto unlock;
+
+		/*
+		 * Restore the original watchpoint if we've completed the
+		 * single-step.
+		 */
+		if (info->trigger != pc)
+			disable_single_step(wp);
+
+unlock:
 		rcu_read_unlock();
 	}
 }
@@ -683,62 +736,69 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
 {
 	int i;
-	int mismatch;
 	u32 ctrl_reg, val, addr;
-	struct perf_event *bp, **slots = __get_cpu_var(bp_on_reg);
+	struct perf_event *bp, **slots;
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
+	slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+
 	/* The exception entry code places the amended lr in the PC. */
 	addr = regs->ARM_pc;
 
+	/* Check the currently installed breakpoints first. */
 	for (i = 0; i < core_num_brps; ++i) {
 		rcu_read_lock();
 
 		bp = slots[i];
 
-		if (bp == NULL) {
-			rcu_read_unlock();
-			continue;
-		}
+		if (bp == NULL)
+			goto unlock;
 
-		mismatch = 0;
+		info = counter_arch_bp(bp);
 
 		/* Check if the breakpoint value matches. */
 		val = read_wb_reg(ARM_BASE_BVR + i);
 		if (val != (addr & ~0x3))
-			goto unlock;
+			goto mismatch;
 
 		/* Possible match, check the byte address select to confirm. */
 		ctrl_reg = read_wb_reg(ARM_BASE_BCR + i);
 		decode_ctrl_reg(ctrl_reg, &ctrl);
 		if ((1 << (addr & 0x3)) & ctrl.len) {
-			mismatch = 1;
-			info = counter_arch_bp(bp);
 			info->trigger = addr;
-		}
-
-unlock:
-		if ((mismatch && !info->ctrl.mismatch) || bp_is_single_step(bp)) {
 			pr_debug("breakpoint fired: address = 0x%x\n", addr);
 			perf_bp_event(bp, regs);
+			if (!bp->overflow_handler)
+				enable_single_step(bp, addr);
+			goto unlock;
 		}
 
-		update_mismatch_flag(i, mismatch);
+mismatch:
+		/* If we're stepping a breakpoint, it can now be restored. */
+		if (info->step_ctrl.enabled)
+			disable_single_step(bp);
+unlock:
 		rcu_read_unlock();
 	}
+
+	/* Handle any pending watchpoint single-step breakpoints. */
+	watchpoint_single_step_handler(addr);
 }
 
 /*
  * Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint].
+ * Prefetch Abort Handler [breakpoint] with preemption disabled.
  */
 static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 				 struct pt_regs *regs)
 {
-	int ret = 1; /* Unhandled fault. */
+	int ret = 0;
 	u32 dscr;
 
+	/* We must be called with preemption disabled. */
+	WARN_ON(preemptible());
+
 	/* We only handle watchpoints and hardware breakpoints. */
 	ARM_DBG_READ(c1, 0, dscr);
 
@@ -753,25 +813,47 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		watchpoint_handler(addr, regs);
 		break;
 	default:
-		goto out;
+		ret = 1; /* Unhandled fault. */
 	}
 
-	ret = 0;
-out:
+	/*
+	 * Re-enable preemption after it was disabled in the
+	 * low-level exception handling code.
+	 */
+	preempt_enable();
+
 	return ret;
 }
 
 /*
  * One-time initialisation.
  */
-static void __init reset_ctrl_regs(void *unused)
+static void reset_ctrl_regs(void *unused)
 {
 	int i;
 
+	/*
+	 * v7 debug contains save and restore registers so that debug state
+	 * can be maintained across low-power modes without leaving
+	 * the debug logic powered up. It is IMPLEMENTATION DEFINED whether
+	 * we can write to the debug registers out of reset, so we must
+	 * unlock the OS Lock Access Register to avoid taking undefined
+	 * instruction exceptions later on.
+	 */
+	if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+		/*
+		 * Unconditionally clear the lock by writing a value
+		 * other than 0xC5ACCE55 to the access register.
+		 */
+		asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
+		isb();
+	}
+
 	if (enable_monitor_mode())
 		return;
 
-	for (i = 0; i < core_num_brps; ++i) {
+	/* We must also reset any reserved registers. */
+	for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
 		write_wb_reg(ARM_BASE_BCR + i, 0UL);
 		write_wb_reg(ARM_BASE_BVR + i, 0UL);
 	}
@@ -782,45 +864,57 @@ static void __init reset_ctrl_regs(void *unused)
 	}
 }
 
+static int __cpuinit dbg_reset_notify(struct notifier_block *self,
+				      unsigned long action, void *cpu)
+{
+	if (action == CPU_ONLINE)
+		smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata dbg_reset_nb = {
+	.notifier_call = dbg_reset_notify,
+};
+
 static int __init arch_hw_breakpoint_init(void)
 {
-	int ret = 0;
 	u32 dscr;
 
 	debug_arch = get_debug_arch();
 
 	if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) {
 		pr_info("debug architecture 0x%x unsupported.\n", debug_arch);
-		ret = -ENODEV;
-		goto out;
+		return 0;
 	}
 
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
+	core_num_reserved_brps = get_num_reserved_brps();
 	core_num_wrps = get_num_wrps();
 
 	pr_info("found %d breakpoint and %d watchpoint registers.\n",
-			core_num_brps, core_num_wrps);
+		core_num_brps + core_num_reserved_brps, core_num_wrps);
 
-	if (core_has_mismatch_bps())
-		pr_info("1 breakpoint reserved for watchpoint single-step.\n");
+	if (core_num_reserved_brps)
+		pr_info("%d breakpoint(s) reserved for watchpoint "
+				"single-step.\n", core_num_reserved_brps);
 
 	ARM_DBG_READ(c1, 0, dscr);
 	if (dscr & ARM_DSCR_HDBGEN) {
 		pr_warning("halting debug mode enabled. Assuming maximum "
 				"watchpoint size of 4 bytes.");
 	} else {
-		/* Work out the maximum supported watchpoint length. */
-		max_watchpoint_len = get_max_wp_len();
-		pr_info("maximum watchpoint size is %u bytes.\n",
-				max_watchpoint_len);
-
 		/*
 		 * Reset the breakpoint resources. We assume that a halting
 		 * debugger will leave the world in a nice state for us.
 		 */
 		smp_call_function(reset_ctrl_regs, NULL, 1);
 		reset_ctrl_regs(NULL);
+
+		/* Work out the maximum supported watchpoint length. */
+		max_watchpoint_len = get_max_wp_len();
+		pr_info("maximum watchpoint size is %u bytes.\n",
+				max_watchpoint_len);
 	}
 
 	/* Register debug fault handler. */
@@ -829,8 +923,9 @@ static int __init arch_hw_breakpoint_init(void)
 	hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
 			"breakpoint debug exception");
 
-out:
-	return ret;
+	/* Register hotplug notifier. */
+	register_cpu_notifier(&dbg_reset_nb);
+	return 0;
 }
 arch_initcall(arch_hw_breakpoint_init);