Merge Will Deacon's for-next/perf branch into for-next/core

* will/for-next/perf:
  selftests: arm64: add test for unaligned/inexact watchpoint handling
  arm64: Allow hw watchpoint of length 3,5,6 and 7
  arm64: hw_breakpoint: Handle inexact watchpoint addresses
  arm64: Allow hw watchpoint at varied offset from base address
  hw_breakpoint: Allow watchpoint of length 3,5,6 and 7

3 files changed, 124 insertions, 42 deletions

diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9510ace570e2..b6b167ac082b 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -77,7 +77,11 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Lengths */
 #define ARM_BREAKPOINT_LEN_1	0x1
 #define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_3	0x7
 #define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_5	0x1f
+#define ARM_BREAKPOINT_LEN_6	0x3f
+#define ARM_BREAKPOINT_LEN_7	0x7f
 #define ARM_BREAKPOINT_LEN_8	0xff
 
 /* Kernel stepping */
@@ -119,7 +123,7 @@ struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-				  int *gen_len, int *gen_type);
+				  int *gen_len, int *gen_type, int *offset);
 extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 948b73148d56..1b3c747fedda 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -317,9 +317,21 @@ static int get_hbp_len(u8 hbp_len)
 	case ARM_BREAKPOINT_LEN_2:
 		len_in_bytes = 2;
 		break;
+	case ARM_BREAKPOINT_LEN_3:
+		len_in_bytes = 3;
+		break;
 	case ARM_BREAKPOINT_LEN_4:
 		len_in_bytes = 4;
 		break;
+	case ARM_BREAKPOINT_LEN_5:
+		len_in_bytes = 5;
+		break;
+	case ARM_BREAKPOINT_LEN_6:
+		len_in_bytes = 6;
+		break;
+	case ARM_BREAKPOINT_LEN_7:
+		len_in_bytes = 7;
+		break;
 	case ARM_BREAKPOINT_LEN_8:
 		len_in_bytes = 8;
 		break;
@@ -349,7 +361,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
  * to generic breakpoint descriptions.
  */
 int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-			   int *gen_len, int *gen_type)
+			   int *gen_len, int *gen_type, int *offset)
 {
 	/* Type */
 	switch (ctrl.type) {
@@ -369,17 +381,33 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 		return -EINVAL;
 	}
 
+	if (!ctrl.len)
+		return -EINVAL;
+	*offset = __ffs(ctrl.len);
+
 	/* Len */
-	switch (ctrl.len) {
+	switch (ctrl.len >> *offset) {
 	case ARM_BREAKPOINT_LEN_1:
 		*gen_len = HW_BREAKPOINT_LEN_1;
 		break;
 	case ARM_BREAKPOINT_LEN_2:
 		*gen_len = HW_BREAKPOINT_LEN_2;
 		break;
+	case ARM_BREAKPOINT_LEN_3:
+		*gen_len = HW_BREAKPOINT_LEN_3;
+		break;
 	case ARM_BREAKPOINT_LEN_4:
 		*gen_len = HW_BREAKPOINT_LEN_4;
 		break;
+	case ARM_BREAKPOINT_LEN_5:
+		*gen_len = HW_BREAKPOINT_LEN_5;
+		break;
+	case ARM_BREAKPOINT_LEN_6:
+		*gen_len = HW_BREAKPOINT_LEN_6;
+		break;
+	case ARM_BREAKPOINT_LEN_7:
+		*gen_len = HW_BREAKPOINT_LEN_7;
+		break;
 	case ARM_BREAKPOINT_LEN_8:
 		*gen_len = HW_BREAKPOINT_LEN_8;
 		break;
@@ -423,9 +451,21 @@ static int arch_build_bp_info(struct perf_event *bp)
 	case HW_BREAKPOINT_LEN_2:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
+	case HW_BREAKPOINT_LEN_3:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		break;
 	case HW_BREAKPOINT_LEN_4:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
+	case HW_BREAKPOINT_LEN_5:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		break;
+	case HW_BREAKPOINT_LEN_6:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		break;
+	case HW_BREAKPOINT_LEN_7:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		break;
 	case HW_BREAKPOINT_LEN_8:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
@@ -517,18 +557,17 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		default:
 			return -EINVAL;
 		}
-
-		info->address &= ~alignment_mask;
-		info->ctrl.len <<= offset;
 	} else {
 		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		if (info->address & alignment_mask)
-			return -EINVAL;
+		offset = info->address & alignment_mask;
 	}
 
+	info->address &= ~alignment_mask;
+	info->ctrl.len <<= offset;
+
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
@@ -661,12 +700,47 @@ unlock:
 }
 NOKPROBE_SYMBOL(breakpoint_handler);
 
+/*
+ * Arm64 hardware does not always report a watchpoint hit address that matches
+ * one of the watchpoints set. It can also report an address "near" the
+ * watchpoint if a single instruction access both watched and unwatched
+ * addresses. There is no straight-forward way, short of disassembling the
+ * offending instruction, to map that address back to the watchpoint. This
+ * function computes the distance of the memory access from the watchpoint as a
+ * heuristic for the likelyhood that a given access triggered the watchpoint.
+ *
+ * See Section D2.10.5 "Determining the memory location that caused a Watchpoint
+ * exception" of ARMv8 Architecture Reference Manual for details.
+ *
+ * The function returns the distance of the address from the bytes watched by
+ * the watchpoint. In case of an exact match, it returns 0.
+ */
+static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
+					struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	u64 wp_low, wp_high;
+	u32 lens, lene;
+
+	lens = __ffs(ctrl->len);
+	lene = __fls(ctrl->len);
+
+	wp_low = val + lens;
+	wp_high = val + lene;
+	if (addr < wp_low)
+		return wp_low - addr;
+	else if (addr > wp_high)
+		return addr - wp_high;
+	else
+		return 0;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
-	int i, step = 0, *kernel_step, access;
+	int i, step = 0, *kernel_step, access, closest_match = 0;
+	u64 min_dist = -1, dist;
 	u32 ctrl_reg;
-	u64 val, alignment_mask;
+	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
 	struct arch_hw_breakpoint *info;
@@ -675,35 +749,15 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	slots = this_cpu_ptr(wp_on_reg);
 	debug_info = &current->thread.debug;
 
+	/*
+	 * Find all watchpoints that match the reported address. If no exact
+	 * match is found. Attribute the hit to the closest watchpoint.
+	 */
+	rcu_read_lock();
 	for (i = 0; i < core_num_wrps; ++i) {
-		rcu_read_lock();
-
 		wp = slots[i];
-
 		if (wp == NULL)
-			goto unlock;
-
-		info = counter_arch_bp(wp);
-		/* AArch32 watchpoints are either 4 or 8 bytes aligned. */
-		if (is_compat_task()) {
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
-				alignment_mask = 0x7;
-			else
-				alignment_mask = 0x3;
-		} else {
-			alignment_mask = 0x7;
-		}
-
-		/* Check if the watchpoint value matches. */
-		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
-		if (val != (addr & ~alignment_mask))
-			goto unlock;
-
-		/* Possible match, check the byte address select to confirm. */
-		ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
-		decode_ctrl_reg(ctrl_reg, &ctrl);
-		if (!((1 << (addr & alignment_mask)) & ctrl.len))
-			goto unlock;
+			continue;
 
 		/*
 		 * Check that the access type matches.
@@ -712,18 +766,41 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W :
 			 HW_BREAKPOINT_R;
 		if (!(access & hw_breakpoint_type(wp)))
-			goto unlock;
+			continue;
 
+		/* Check if the watchpoint value and byte select match. */
+		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
+		ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
+		decode_ctrl_reg(ctrl_reg, &ctrl);
+		dist = get_distance_from_watchpoint(addr, val, &ctrl);
+		if (dist < min_dist) {
+			min_dist = dist;
+			closest_match = i;
+		}
+		/* Is this an exact match? */
+		if (dist != 0)
+			continue;
+
+		info = counter_arch_bp(wp);
 		info->trigger = addr;
 		perf_bp_event(wp, regs);
 
 		/* Do we need to handle the stepping? */
 		if (is_default_overflow_handler(wp))
 			step = 1;
+	}
+	if (min_dist > 0 && min_dist != -1) {
+		/* No exact match found. */
+		wp = slots[closest_match];
+		info = counter_arch_bp(wp);
+		info->trigger = addr;
+		perf_bp_event(wp, regs);
 
-unlock:
-		rcu_read_unlock();
+		/* Do we need to handle the stepping? */
+		if (is_default_overflow_handler(wp))
+			step = 1;
 	}
+	rcu_read_unlock();
 
 	if (!step)
 		return 0;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e0c81da60f76..fc35e06ccaac 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -327,13 +327,13 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 				     struct arch_hw_breakpoint_ctrl ctrl,
 				     struct perf_event_attr *attr)
 {
-	int err, len, type, disabled = !ctrl.enabled;
+	int err, len, type, offset, disabled = !ctrl.enabled;
 
 	attr->disabled = disabled;
 	if (disabled)
 		return 0;
 
-	err = arch_bp_generic_fields(ctrl, &len, &type);
+	err = arch_bp_generic_fields(ctrl, &len, &type, &offset);
 	if (err)
 		return err;
 
@@ -352,6 +352,7 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
+	attr->bp_addr	+= offset;
 
 	return 0;
 }
@@ -404,7 +405,7 @@ static int ptrace_hbp_get_addr(unsigned int note_type,
 	if (IS_ERR(bp))
 		return PTR_ERR(bp);
 
-	*addr = bp ? bp->attr.bp_addr : 0;
+	*addr = bp ? counter_arch_bp(bp)->address : 0;
 	return 0;
 }