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
  ...

5 files changed, 90 insertions, 225 deletions

diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 8771766d46b6..34a5c1715148 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		set_dr_addr_mask(0, i);
 }
 
-/*
- * Check for virtual address in kernel space.
- */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+static int arch_bp_generic_len(int x86_len)
 {
-	unsigned int len;
-	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	va = info->address;
-	len = bp->attr.bp_len;
-
-	/*
-	 * We don't need to worry about va + len - 1 overflowing:
-	 * we already require that va is aligned to a multiple of len.
-	 */
-	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+	switch (x86_len) {
+	case X86_BREAKPOINT_LEN_1:
+		return HW_BREAKPOINT_LEN_1;
+	case X86_BREAKPOINT_LEN_2:
+		return HW_BREAKPOINT_LEN_2;
+	case X86_BREAKPOINT_LEN_4:
+		return HW_BREAKPOINT_LEN_4;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		return HW_BREAKPOINT_LEN_8;
+#endif
+	default:
+		return -EINVAL;
+	}
 }
 
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
+	int len;
+
 	/* Type */
 	switch (x86_type) {
 	case X86_BREAKPOINT_EXECUTE:
@@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 	}
 
 	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_1:
-		*gen_len = HW_BREAKPOINT_LEN_1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		*gen_len = HW_BREAKPOINT_LEN_2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		*gen_len = HW_BREAKPOINT_LEN_4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		*gen_len = HW_BREAKPOINT_LEN_8;
-		break;
-#endif
-	default:
+	len = arch_bp_generic_len(x86_len);
+	if (len < 0)
 		return -EINVAL;
-	}
+	*gen_len = len;
 
 	return 0;
 }
 
-
-static int arch_build_bp_info(struct perf_event *bp)
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned long va;
+	int len;
 
-	info->address = bp->attr.bp_addr;
+	va = hw->address;
+	len = arch_bp_generic_len(hw->len);
+	WARN_ON_ONCE(len < 0);
+
+	/*
+	 * We don't need to worry about va + len - 1 overflowing:
+	 * we already require that va is aligned to a multiple of len.
+	 */
+	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+}
+
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
+{
+	hw->address = attr->bp_addr;
+	hw->mask = 0;
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_W:
-		info->type = X86_BREAKPOINT_WRITE;
+		hw->type = X86_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = X86_BREAKPOINT_RW;
+		hw->type = X86_BREAKPOINT_RW;
 		break;
 	case HW_BREAKPOINT_X:
 		/*
@@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * acceptable for kprobes.  On non-kprobes kernels, we don't
 		 * allow kernel breakpoints at all.
 		 */
-		if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+		if (attr->bp_addr >= TASK_SIZE_MAX) {
 #ifdef CONFIG_KPROBES
-			if (within_kprobe_blacklist(bp->attr.bp_addr))
+			if (within_kprobe_blacklist(attr->bp_addr))
 				return -EINVAL;
 #else
 			return -EINVAL;
 #endif
 		}
 
-		info->type = X86_BREAKPOINT_EXECUTE;
+		hw->type = X86_BREAKPOINT_EXECUTE;
 		/*
 		 * x86 inst breakpoints need to have a specific undefined len.
 		 * But we still need to check userspace is not trying to setup
 		 * an unsupported length, to get a range breakpoint for example.
 		 */
-		if (bp->attr.bp_len == sizeof(long)) {
-			info->len = X86_BREAKPOINT_LEN_X;
+		if (attr->bp_len == sizeof(long)) {
+			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
 	default:
@@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
-	info->mask = 0;
-
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = X86_BREAKPOINT_LEN_2;
+		hw->len = X86_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = X86_BREAKPOINT_LEN_4;
+		hw->len = X86_BREAKPOINT_LEN_4;
 		break;
 #ifdef CONFIG_X86_64
 	case HW_BREAKPOINT_LEN_8:
-		info->len = X86_BREAKPOINT_LEN_8;
+		hw->len = X86_BREAKPOINT_LEN_8;
 		break;
 #endif
 	default:
 		/* AMD range breakpoint */
-		if (!is_power_of_2(bp->attr.bp_len))
+		if (!is_power_of_2(attr->bp_len))
 			return -EINVAL;
-		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+		if (attr->bp_addr & (attr->bp_len - 1))
 			return -EINVAL;
 
 		if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		info->mask = bp->attr.bp_len - 1;
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->mask = attr->bp_len - 1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
@@ -322,22 +326,23 @@ 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);
 	unsigned int align;
 	int ret;
 
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
-		if (info->mask)
-			align = info->mask;
+		if (hw->mask)
+			align = hw->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index ae38dccf0c8f..2b949f4fd4d8 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 }
 #endif
 
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6f4d42377fe5..b0d1e81c96bb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -66,8 +66,6 @@
 
 #include "common.h"
 
-void jprobe_return_end(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);
@@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 		 * stepping.
 		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
 		return;
 	}
 #endif
@@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 		 * Raise a BUG or we'll continue in an endless reentering loop
 		 * and eventually a stack overflow.
 		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
+		pr_err("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 	default:
@@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing. We conditionally
-	 * re-enable preemption at the end of this function,
-	 * and also in reenter_kprobe() and setup_singlestep().
+	 * We don't want to be preempted for the entire duration of kprobe
+	 * processing. Since int3 and debug trap disables irqs and we clear
+	 * IF while singlestepping, it must be no preemptible.
 	 */
-	preempt_disable();
 
 	kcb = get_kprobe_ctlblk();
 	p = get_kprobe(addr);
@@ -690,13 +682,14 @@ int kprobe_int3_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
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * pre-handler and it returned non-zero, that means
+			 * user handler setup registers to exit to another
+			 * instruction, we must skip the single stepping.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 		 * the original instruction.
 		 */
 		regs->ip = (unsigned long)addr;
-		preempt_enable_no_resched();
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			if (!skip_singlestep(p, regs, kcb))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
 	} /* else: not a kprobe fault; let the kernel handle it */
 
-	preempt_enable_no_resched();
 	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_int3_handler);
@@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs)
 	}
 	reset_current_kprobe();
 out:
-	preempt_enable_no_resched();
-
 	/*
 	 * if somebody else is singlestepping across a probe point, flags
 	 * will have TF set, in which case, continue the remaining processing
@@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
 		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
@@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = stack_addr(regs);
-	addr = (unsigned long)(kcb->jprobe_saved_sp);
-
-	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
-	 * raw stack chunk with redzones:
-	 */
-	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->ip = (unsigned long)(jp->entry);
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/* Unpoison stack redzones in the frames we are going to jump over. */
-	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
-
-	asm volatile (
-#ifdef CONFIG_X86_64
-			"       xchg   %%rbx,%%rsp	\n"
-#else
-			"       xchgl   %%ebx,%%esp	\n"
-#endif
-			"       int3			\n"
-			"       .globl jprobe_return_end\n"
-			"       jprobe_return_end:	\n"
-			"       nop			\n"::"b"
-			(kcb->jprobe_saved_sp):"memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-NOKPROBE_SYMBOL(jprobe_return_end);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	u8 *addr = (u8 *) (regs->ip - 1);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	void *saved_sp = kcb->jprobe_saved_sp;
-
-	if ((addr > (u8 *) jprobe_return) &&
-	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != saved_sp) {
-			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
-			printk(KERN_ERR
-			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), saved_sp);
-			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk(KERN_ERR "Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		/* It's OK to start function graph tracing again */
-		unpause_graph_tracing();
-		*regs = kcb->jprobe_saved_regs;
-		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	bool is_in_entry_trampoline_section = false;
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..ef819e19650b 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,36 +25,6 @@
 
 #include "common.h"
 
-static nokprobe_inline
-void __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_ip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_ip)
-		regs->ip = orig_ip;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p)) {
-		__skip_singlestep(p, regs, kcb, 0);
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
-		/* To emulate trap based kprobes, preempt_disable here */
-		preempt_disable();
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
-			__skip_singlestep(p, regs, kcb, orig_ip);
-			preempt_enable_no_resched();
+			/*
+			 * Emulate singlestep (and also recover regs->ip)
+			 * as if there is a 5byte nop
+			 */
+			regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			regs->ip = orig_ip;
 		}
 		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe, and keep preempt count +1.
+		 * If pre_handler returns !0, it changes regs->ip. We have to
+		 * skip emulating post_handler.
 		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 203d398802a3..eaf02f2e7300 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
 		if (!reenter)
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 	return 0;