Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf update from Thomas Gleixner:
 "The perf crowd presents:

  Kernel updates:

   - Removal of jprobes

   - Cleanup and consolidatation the handling of kprobes

   - Cleanup and consolidation of hardware breakpoints

   - The usual pile of fixes and updates to PMUs and event descriptors

  Tooling updates:

   - Updates and improvements all over the place. Nothing outstanding,
     just the (good) boring incremental grump work"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  perf trace: Do not require --no-syscalls to suppress strace like output
  perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h
  perf tools: Allow overriding MAX_NR_CPUS at compile time
  perf bpf: Show better message when failing to load an object
  perf list: Unify metric group description format with PMU event description
  perf vendor events arm64: Update ThunderX2 implementation defined pmu core events
  perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet
  perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON packet
  perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet
  perf cs-etm: Fix start tracing packet handling
  perf build: Fix installation directory for eBPF
  perf c2c report: Fix crash for empty browser
  perf tests: Fix indexing when invoking subtests
  perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
  perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg
  perf trace beauty: Do not print NULL strarray entries
  perf beauty: Add a generator for IPPROTO_ socket's protocol constants
  tools include uapi: Grab a copy of linux/in.h
  perf tests: Fix complex event name parsing
  perf evlist: Fix error out while applying initial delay and LBR
  ...

6 files changed, 51 insertions, 177 deletions

diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e46e4e7bdba3..ac54c06764e6 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg,
 	asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
 } while (0)
 
+struct perf_event_attr;
 struct notifier_block;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 59655459da59..82290f212d8e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,8 +44,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
index 1e5b9bb92270..991c9127c650 100644
--- a/arch/arm/include/asm/probes.h
+++ b/arch/arm/include/asm/probes.h
@@ -51,7 +51,6 @@ struct arch_probes_insn {
  * We assume one instruction can consume at most 64 bytes stack, which is
  * 'push {r0-r15}'. Instructions consume more or unknown stack space like
  * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
  */
 #define MAX_STACK_SIZE			64
 
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 629e25152c0d..1d5fbf1d1c67 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
-		if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
 	default:
@@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * 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)
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Privilege */
-	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+	hw->ctrl.privilege = ARM_BREAKPOINT_USER;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	/* Mismatch */
-	info->ctrl.mismatch = 0;
+	hw->ctrl.mismatch = 0;
 
 	return 0;
 }
@@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret = 0;
 	u32 offset, alignment_mask = 0x3;
 
@@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		return -ENODEV;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		goto out;
 
 	/* Check address alignment. */
-	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+	if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 		alignment_mask = 0x7;
-	offset = info->address & alignment_mask;
+	offset = hw->address & alignment_mask;
 	switch (offset) {
 	case 0:
 		/* Aligned */
@@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	case 1:
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
 	case 3:
 		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
 	default:
 		ret = -EINVAL;
 		goto out;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	if (is_default_overflow_handler(bp)) {
 		/*
@@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 			return -EINVAL;
 
 		/* We don't allow mismatch breakpoints in kernel space. */
-		if (arch_check_bp_in_kernelspace(bp))
+		if (arch_check_bp_in_kernelspace(hw))
 			return -EPERM;
 
 		/*
@@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		 * reports them.
 		 */
 		if (!debug_exception_updates_fsr() &&
-		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
-		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+		    (hw->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     hw->ctrl.type == ARM_BREAKPOINT_STORE))
 			return -EINVAL;
 	}
 
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index e90cc8a08186..f8bd523d64d1 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -47,9 +47,6 @@
 			   (unsigned long)(addr) +	\
 			   (size))
 
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR		0xffffffff
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				break;
 			case KPROBE_REENTER:
 				/* A nested probe was hit in FIQ, it is a BUG */
-				pr_warn("Unrecoverable kprobe detected at %p.\n",
-					p->addr);
+				pr_warn("Unrecoverable kprobe detected.\n");
+				dump_kprobe(p);
 				/* fall through */
 			default:
 				/* impossible cases */
@@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 
 			/*
 			 * If we have no pre-handler or it returned 0, we
-			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * continue with normal processing. If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				kcb->kprobe_status = KPROBE_HIT_SS;
@@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 					kcb->kprobe_status = KPROBE_HIT_SSDONE;
 					p->post_handler(p, regs, 0);
 				}
-				reset_current_kprobe();
-			}
-		}
-	} else if (cur) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur->break_handler && cur->break_handler(cur, regs)) {
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			singlestep(cur, regs, kcb);
-			if (cur->post_handler) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				cur->post_handler(cur, regs, 0);
 			}
+			reset_current_kprobe();
 		}
-		reset_current_kprobe();
 	} else {
 		/*
 		 * The probe was removed and a race is in progress.
@@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long sp_addr = regs->ARM_sp;
-	long cpsr;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ARM_pc = (long)jp->entry;
-
-	cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
-	/* Set correct Thumb state in cpsr */
-	if (regs->ARM_pc & 1)
-		cpsr |= PSR_T_BIT;
-	else
-		cpsr &= ~PSR_T_BIT;
-#endif
-	regs->ARM_cpsr = cpsr;
-
-	preempt_disable();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	__asm__ __volatile__ (
-		/*
-		 * Setup an empty pt_regs. Fill SP and PC fields as
-		 * they're needed by longjmp_break_handler.
-		 *
-		 * We allocate some slack between the original SP and start of
-		 * our fabricated regs. To be precise we want to have worst case
-		 * covered which is STMFD with all 16 regs so we allocate 2 *
-		 * sizeof(struct_pt_regs)).
-		 *
-		 * This is to prevent any simulated instruction from writing
-		 * over the regs when they are accessing the stack.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"sub    r0, %0, %1		\n\t"
-		"mov    sp, r0			\n\t"
-#else
-		"sub    sp, %0, %1		\n\t"
-#endif
-		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
-		"str    %0, [sp, %2]		\n\t"
-		"str    r0, [sp, %3]		\n\t"
-		"mov    r0, sp			\n\t"
-		"bl     kprobe_handler		\n\t"
-
-		/*
-		 * Return to the context saved by setjmp_pre_handler
-		 * and restored by longjmp_break_handler.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
-		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
-		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
-		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
-						      /* rfe context */
-		"ldmia	sp, {r0 - r12}		\n\t"
-		"mov	sp, lr			\n\t"
-		"ldr	lr, [sp], #4		\n\t"
-		"rfeia	sp!			\n\t"
-#else
-		"ldr	r0, [sp, %4]		\n\t"
-		"msr	cpsr_cxsf, r0		\n\t"
-		"ldmia	sp, {r0 - pc}		\n\t"
-#endif
-		:
-		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
-		: "memory", "cc");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.ARM_sp;
-	long orig_sp = regs->ARM_sp;
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
-		if (orig_sp != stack_addr) {
-			struct pt_regs *saved_regs =
-				(struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
-			printk("current sp %lx does not match saved sp %lx\n",
-			       orig_sp, stack_addr);
-			printk("Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk("Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 14db14152909..cc237fa9b90f 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -1461,7 +1461,6 @@ fail:
 	print_registers(&result_regs);
 
 	if (mem) {
-		pr_err("current_stack=%p\n", current_stack);
 		pr_err("expected_memory:\n");
 		print_memory(expected_memory, mem_size);
 		pr_err("result_memory:\n");