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
  ...

133 files changed, 2606 insertions, 1867 deletions

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index cb3b0de83fc6..10f4499e677c 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the
 "post_handler," if any, that is associated with the kprobe.
 Execution then continues with the instruction following the probepoint.
 
+Changing Execution Path
+-----------------------
+
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
+
 Return Probes
 -------------
 
@@ -262,7 +282,7 @@ is optimized, that modification is ignored.  Thus, if you want to
 tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 
-- Specify an empty function for the kprobe's post_handler or break_handler.
+- Specify an empty function for the kprobe's post_handler.
 
 or
 
@@ -474,7 +494,7 @@ error occurs during registration, all probes in the array, up to
 the bad probe, are safely unregistered before the register_*probes
 function returns.
 
-- kps/rps/jps: an array of pointers to ``*probe`` data structures
+- kps/rps: an array of pointers to ``*probe`` data structures
 - num: the number of the array entries.
 
 .. note::
@@ -566,12 +586,11 @@ the same handler) may run concurrently on different CPUs.
 Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
-Probe handlers are run with preemption disabled.  Depending on the
-architecture and optimization state, handlers may also run with
-interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-handlers run without interrupt disabled on x86/x86-64).  In any case,
-your handler should not yield the CPU (e.g., by attempting to acquire
-a semaphore).
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state.  (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64).  In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 2e52d18e6bc7..2c1b479d5aea 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -45,8 +45,6 @@ struct prev_kprobe {
 
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 42b05046fad9..df35d4c0b0b8 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, 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 - which is expected from setjmp_pre_handler for
-		 * jprobe, we return without single stepping and leave that to
-		 * the break-handler which is invoked by a kprobe from
-		 * jprobe_return
+		 * non-zero - which 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->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			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)) {
-			setup_singlestep(p, regs);
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			return 1;
-		}
 	}
 
 	/* no_kprobe: */
@@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-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();
-	unsigned long sp_addr = regs->sp;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ret = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	__asm__ __volatile__("unimp_s");
-	return;
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr;
-
-	*regs = kcb->jprobe_saved_regs;
-	sp_addr = regs->sp;
-	memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
-	preempt_enable_no_resched();
-
-	return 1;
-}
-
 static void __used kretprobe_trampoline_holder(void)
 {
 	__asm__ __volatile__(".global kretprobe_trampoline\n"
@@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	regs->ret = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
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");
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 41770766d964..6a53e59ced95 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg,
 
 struct task_struct;
 struct notifier_block;
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  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 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/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 6deb8d726041..d5a44cf859e9 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -48,7 +48,6 @@ struct kprobe_ctlblk {
 	unsigned long saved_irqflag;
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
-	struct pt_regs jprobe_saved_regs;
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 413dbe530da8..8c9644376326 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -343,14 +343,13 @@ 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);
 }
@@ -421,53 +420,53 @@ 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_3:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_3;
 		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_5:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_5;
 		break;
 	case HW_BREAKPOINT_LEN_6:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_6;
 		break;
 	case HW_BREAKPOINT_LEN_7:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_7;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
@@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * AArch32 also requires breakpoints of length 2 for Thumb.
 	 * Watchpoints can be of length 1, 2, 4 or 8 bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		if (is_compat_bp(bp)) {
-			if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-			    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+			if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+			    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 				return -EINVAL;
-		} else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) {
+		} else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) {
 			/*
 			 * FIXME: Some tools (I'm looking at you perf) assume
 			 *	  that breakpoints should be sizeof(long). This
 			 *	  is nonsense. For now, we fix up the parameter
 			 *	  but we should probably return -EINVAL instead.
 			 */
-			info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+			hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		}
 	}
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/*
 	 * Privilege
 	 * Note that we disallow combined EL0/EL1 breakpoints because
 	 * that would complicate the stepping code.
 	 */
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
 	else
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	return 0;
 }
@@ -516,14 +515,15 @@ 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;
 	u64 alignment_mask, offset;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
@@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * that here.
 	 */
 	if (is_compat_bp(bp)) {
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 			alignment_mask = 0x7;
 		else
 			alignment_mask = 0x3;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 		switch (offset) {
 		case 0:
 			/* Aligned */
 			break;
 		case 1:
 			/* Allow single byte watchpoint. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 		default:
 			return -EINVAL;
 		}
 	} else {
-		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
+		if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
 	 */
-	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
+	if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d849d9804011..e78c3ef04d95 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 		break;
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
-		pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+		pr_warn("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 		break;
@@ -395,9 +395,9 @@ static 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.
+			 * 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.
 			 *
 			 * pre_handler can hit a breakpoint and can step thru
 			 * before return, keep PSTATE D-flag enabled until
@@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
-				return;
-			}
-		}
-	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
-	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur_kprobe->break_handler  &&
-		     cur_kprobe->break_handler(cur_kprobe, regs)) {
-			setup_singlestep(cur_kprobe, regs, kcb, 0);
-			return;
+			} else
+				reset_current_kprobe();
 		}
 	}
 	/*
@@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-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();
-
-	kcb->jprobe_saved_regs = *regs;
-	/*
-	 * Since we can't be sure where in the stack frame "stacked"
-	 * pass-by-value arguments are stored we just don't try to
-	 * duplicate any of the stack. Do not use jprobes on functions that
-	 * use more than 64 bytes (after padding each to an 8 byte boundary)
-	 * of arguments, or pass individual arguments larger than 16 bytes.
-	 */
-
-	instruction_pointer_set(regs, (unsigned long) jp->entry);
-	preempt_disable();
-	pause_graph_tracing();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/*
-	 * Jprobe handler return by entering break exception,
-	 * encoded same as kprobe, but with following conditions
-	 * -a special PC to identify it from the other kprobes.
-	 * -restore stack addr to original saved pt_regs
-	 */
-	asm volatile("				mov sp, %0	\n"
-		     "jprobe_return_break:	brk %1		\n"
-		     :
-		     : "r" (kcb->jprobe_saved_regs.sp),
-		       "I" (BRK64_ESR_KPROBES)
-		     : "memory");
-
-	unreachable();
-}
-
-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.sp;
-	long orig_sp = kernel_stack_pointer(regs);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	extern const char jprobe_return_break[];
-
-	if (instruction_pointer(regs) != (u64) jprobe_return_break)
-		return 0;
-
-	if (orig_sp != stack_addr) {
-		struct pt_regs *saved_regs =
-		    (struct pt_regs *)kcb->jprobe_saved_regs.sp;
-		pr_err("current sp %lx does not match saved sp %lx\n",
-		       orig_sp, stack_addr);
-		pr_err("Saved registers for jprobe %p\n", jp);
-		__show_regs(saved_regs);
-		pr_err("Current registers\n");
-		__show_regs(regs);
-		BUG();
-	}
-	unpause_graph_tracing();
-	*regs = kcb->jprobe_saved_regs;
-	preempt_enable_no_resched();
-	return 1;
-}
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	if ((addr >= (unsigned long)__kprobes_text_start &&
diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h
index 0302b3664789..580356a2eea6 100644
--- a/arch/ia64/include/asm/kprobes.h
+++ b/arch/ia64/include/asm/kprobes.h
@@ -82,8 +82,6 @@ struct prev_kprobe {
 #define ARCH_PREV_KPROBE_SZ 2
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE];
 	unsigned long *bsp;
 	unsigned long cfm;
 	atomic_t prev_kprobe_index;
diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h
index 5d742bcb0018..4ca110f0a94b 100644
--- a/arch/ia64/include/uapi/asm/break.h
+++ b/arch/ia64/include/uapi/asm/break.h
@@ -14,7 +14,6 @@
  */
 #define __IA64_BREAK_KDB		0x80100
 #define __IA64_BREAK_KPROBE		0x81000 /* .. 0x81fff */
-#define __IA64_BREAK_JPROBE		0x82000
 
 /*
  * OS-specific break numbers:
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 498f3da3f225..d0c0ccdd656a 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_PERFMON)		+= perfmon_default_smpl.o
 obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S
deleted file mode 100644
index f69389c7be1d..000000000000
--- a/arch/ia64/kernel/jprobes.S
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Jprobe specific operations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Intel Corporation, 2005
- *
- * 2005-May     Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy
- *              <anil.s.keshavamurthy@intel.com> initial implementation
- *
- * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a
- * probe to be inserted into the beginning of a function call.  The fundamental
- * difference between a jprobe and a kprobe is the jprobe handler is executed
- * in the same context as the target function, while the kprobe handlers
- * are executed in interrupt context.
- *
- * For jprobes we initially gain control by placing a break point in the
- * first instruction of the targeted function.  When we catch that specific
- * break, we:
- *        * set the return address to our jprobe_inst_return() function
- *        * jump to the jprobe handler function
- *
- * Since we fixed up the return address, the jprobe handler will return to our
- * jprobe_inst_return() function, giving us control again.  At this point we
- * are back in the parents frame marker, so we do yet another call to our
- * jprobe_break() function to fix up the frame marker as it would normally
- * exist in the target function.
- *
- * Our jprobe_return function then transfers control back to kprobes.c by
- * executing a break instruction using one of our reserved numbers.  When we
- * catch that break in kprobes.c, we continue like we do for a normal kprobe
- * by single stepping the emulated instruction, and then returning execution
- * to the correct location.
- */
-#include <asm/asmmacro.h>
-#include <asm/break.h>
-
-	/*
-	 * void jprobe_break(void)
-	 */
-	.section .kprobes.text, "ax"
-ENTRY(jprobe_break)
-	break.m __IA64_BREAK_JPROBE
-END(jprobe_break)
-
-	/*
-	 * void jprobe_inst_return(void)
-	 */
-GLOBAL_ENTRY(jprobe_inst_return)
-	br.call.sptk.many b0=jprobe_break
-END(jprobe_inst_return)
-
-GLOBAL_ENTRY(invalidate_stacked_regs)
-	movl r16=invalidate_restore_cfm
-	;;
-	mov b6=r16
-	;;
-	br.ret.sptk.many b6
-	;;
-invalidate_restore_cfm:
-	mov r16=ar.rsc
-	;;
-	mov ar.rsc=r0
-	;;
-	loadrs
-	;;
-	mov ar.rsc=r16
-	;;
-	br.cond.sptk.many rp
-END(invalidate_stacked_regs)
-
-GLOBAL_ENTRY(flush_register_stack)
-	// flush dirty regs to backing store (must be first in insn group)
-	flushrs
-	;;
-	br.ret.sptk.many rp
-END(flush_register_stack)
-
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index f5f3a5e6fcd1..aa41bd5cf9b7 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -35,8 +35,6 @@
 #include <asm/sections.h>
 #include <asm/exception.h>
 
-extern void jprobe_inst_return(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			 */
 			break;
 	}
-
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			prepare_ss(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else if (args->err == __IA64_BREAK_JPROBE) {
-			/*
-			 * jprobe instrumented function just completed
-			 */
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		} else if (!is_ia64_break_inst(regs)) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
@@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 	set_current_kprobe(p, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/*
-		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is used for both the jprobe pre-handler
-		 * and the kretprobe trampoline
-		 */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
@@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	case DIE_BREAK:
 		/* err is break number from ia64_bad_break() */
 		if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12)
-			|| args->err == __IA64_BREAK_JPROBE
 			|| args->err == 0)
 			if (pre_kprobes_handler(args))
 				ret = NOTIFY_STOP;
@@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry)
 	return ((struct fnptr *)entry)->ip;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr = arch_deref_entry_point(jp->entry);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	struct param_bsp_cfm pa;
-	int bytes;
-
-	/*
-	 * Callee owns the argument space and could overwrite it, eg
-	 * tail call optimization. So to be absolutely safe
-	 * we save the argument space before transferring the control
-	 * to instrumented jprobe function which runs in
-	 * the process context
-	 */
-	pa.ip = regs->cr_iip;
-	unw_init_running(ia64_get_bsp_cfm, &pa);
-	bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f)
-				- (char *)pa.bsp;
-	memcpy( kcb->jprobes_saved_stacked_regs,
-		pa.bsp,
-		bytes );
-	kcb->bsp = pa.bsp;
-	kcb->cfm = pa.cfm;
-
-	/* save architectural state */
-	kcb->jprobe_saved_regs = *regs;
-
-	/* after rfi, execute the jprobe instrumented function */
-	regs->cr_iip = addr & ~0xFULL;
-	ia64_psr(regs)->ri = addr & 0xf;
-	regs->r1 = ((struct fnptr *)(jp->entry))->gp;
-
-	/*
-	 * fix the return address to our jprobe_inst_return() function
-	 * in the jprobes.S file
-	 */
-	regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip;
-
-	return 1;
-}
-
-/* ia64 does not need this */
-void __kprobes jprobe_return(void)
-{
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	int bytes;
-
-	/* restoring architectural state */
-	*regs = kcb->jprobe_saved_regs;
-
-	/* restoring the original argument space */
-	flush_register_stack();
-	bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f)
-				- (char *)kcb->bsp;
-	memcpy( kcb->bsp,
-		kcb->jprobes_saved_stacked_regs,
-		bytes );
-	invalidate_stacked_regs();
-
-	preempt_enable_no_resched();
-	return 1;
-}
-
 static struct kprobe trampoline_p = {
 	.pre_handler = trampoline_probe_handler
 };
diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h
index ad1a99948f27..a72dfbf1babb 100644
--- a/arch/mips/include/asm/kprobes.h
+++ b/arch/mips/include/asm/kprobes.h
@@ -68,16 +68,6 @@ struct prev_kprobe {
 	unsigned long saved_epc;
 };
 
-#define MAX_JPROBES_STACK_SIZE 128
-#define MAX_JPROBES_STACK_ADDR \
-	(((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs))
-
-#define MIN_JPROBES_STACK_SIZE(ADDR)					\
-	((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR)	\
-		? MAX_JPROBES_STACK_ADDR - (ADDR)			\
-		: MAX_JPROBES_STACK_SIZE)
-
-
 #define SKIP_DELAYSLOT 0x0001
 
 /* per-cpu kprobe control block */
@@ -86,12 +76,9 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_old_SR;
 	unsigned long kprobe_saved_SR;
 	unsigned long kprobe_saved_epc;
-	unsigned long jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
 	/* Per-thread fields, used while emulating branches */
 	unsigned long flags;
 	unsigned long target_epc;
-	u8 jprobes_stack[MAX_JPROBES_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index f5c8bce70db2..54cd675c5d1d 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				preempt_enable_no_resched();
 			}
 			return 1;
-		} else {
-			if (addr->word != breakpoint_insn.word) {
-				/*
-				 * The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+		} else if (addr->word != breakpoint_insn.word) {
+			/*
+			 * The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
 	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	if (kcb->flags & SKIP_DELAYSLOT) {
 		kcb->kprobe_status = KPROBE_HIT_SSDONE;
@@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-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();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = regs->regs[29];
-
-	memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
-	       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-
-	regs->cp0_epc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-/* Defined in the inline asm below. */
-void jprobe_return_end(void);
-
-void __kprobes jprobe_return(void)
-{
-	/* Assembler quirk necessitates this '0,code' business.	 */
-	asm volatile(
-		"break 0,%0\n\t"
-		".globl jprobe_return_end\n"
-		"jprobe_return_end:\n"
-		: : "n" (BRK_KPROBE_BP) : "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->cp0_epc >= (unsigned long)jprobe_return &&
-	    regs->cp0_epc <= (unsigned long)jprobe_return_end) {
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
-		       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-		preempt_enable_no_resched();
-
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * Function return probe trampoline:
  *	- init_kprobes() establishes a probepoint here
@@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	instruction_pointer(regs) = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 8e7b09703ca4..27d6e3c8fde9 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -52,6 +52,7 @@ struct arch_hw_breakpoint {
 #include <asm/reg.h>
 #include <asm/debug.h>
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 struct perf_sample_data;
@@ -60,8 +61,10 @@ struct perf_sample_data;
 
 extern int hw_breakpoint_slots(int type);
 extern int arch_bp_generic_fields(int type, int *gen_bp_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);
 int arch_install_hw_breakpoint(struct perf_event *bp);
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 9f3be5c8a4a3..785c464b6588 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -88,7 +88,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_saved_msr;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
@@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int __is_active_jprobe(unsigned long addr);
-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
 #else
 static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
 static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 80547dad37da..fec8a6773119 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	return is_kernel_addr(info->address);
+	return is_kernel_addr(hw->address);
 }
 
 int arch_bp_generic_fields(int type, int *gen_bp_type)
@@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
 /*
  * 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)
 {
 	int ret = -EINVAL, length_max;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	if (!bp)
 		return ret;
 
-	info->type = HW_BRK_TYPE_TRANSLATE;
-	if (bp->attr.bp_type & HW_BREAKPOINT_R)
-		info->type |= HW_BRK_TYPE_READ;
-	if (bp->attr.bp_type & HW_BREAKPOINT_W)
-		info->type |= HW_BRK_TYPE_WRITE;
-	if (info->type == HW_BRK_TYPE_TRANSLATE)
+	hw->type = HW_BRK_TYPE_TRANSLATE;
+	if (attr->bp_type & HW_BREAKPOINT_R)
+		hw->type |= HW_BRK_TYPE_READ;
+	if (attr->bp_type & HW_BREAKPOINT_W)
+		hw->type |= HW_BRK_TYPE_WRITE;
+	if (hw->type == HW_BRK_TYPE_TRANSLATE)
 		/* must set alteast read or write */
 		return ret;
-	if (!(bp->attr.exclude_user))
-		info->type |= HW_BRK_TYPE_USER;
-	if (!(bp->attr.exclude_kernel))
-		info->type |= HW_BRK_TYPE_KERNEL;
-	if (!(bp->attr.exclude_hv))
-		info->type |= HW_BRK_TYPE_HYP;
-	info->address = bp->attr.bp_addr;
-	info->len = bp->attr.bp_len;
+	if (!attr->exclude_user)
+		hw->type |= HW_BRK_TYPE_USER;
+	if (!attr->exclude_kernel)
+		hw->type |= HW_BRK_TYPE_KERNEL;
+	if (!attr->exclude_hv)
+		hw->type |= HW_BRK_TYPE_HYP;
+	hw->address = attr->bp_addr;
+	hw->len = attr->bp_len;
 
 	/*
 	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
@@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (cpu_has_feature(CPU_FTR_DAWR)) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
-		if ((bp->attr.bp_addr >> 9) !=
-		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9))
+		if ((attr->bp_addr >> 9) !=
+		    ((attr->bp_addr + attr->bp_len - 1) >> 9))
 			return -EINVAL;
 	}
-	if (info->len >
-	    (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
+	if (hw->len >
+	    (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 7a1f99f1b47f..e4a49c051325 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -25,50 +25,6 @@
 #include <linux/preempt.h>
 #include <linux/ftrace.h>
 
-/*
- * This is called from ftrace code after invoking registered handlers to
- * disambiguate regs->nip changes done by jprobes and livepatch. We check if
- * there is an active jprobe at the provided address (mcount location).
- */
-int __is_active_jprobe(unsigned long addr)
-{
-	if (!preemptible()) {
-		struct kprobe *p = raw_cpu_read(current_kprobe);
-		return (p && (unsigned long)p->addr == addr) ? 1 : 0;
-	}
-
-	return 0;
-}
-
-static nokprobe_inline
-int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_nip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->nip)
-	 * as if there is a nop
-	 */
-	regs->nip = (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_nip)
-		regs->nip = orig_nip;
-	return 1;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb, 0);
-	else
-		return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes */
 void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	preempt_disable();
-
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
+		return;
 
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		unsigned long orig_nip = regs->nip;
-
 		/*
 		 * On powerpc, NIP is *before* this instruction for the
 		 * pre handler
@@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 
 		__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_nip);
-		else {
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			/*
-			 * If pre_handler returns !0, it sets regs->nip and
-			 * resets current kprobe. In this case, we should not
-			 * re-enable preemption.
+			 * Emulate singlestep (and also recover regs->nip)
+			 * as if there is a nop
 			 */
-			return;
+			regs->nip += MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
 		}
+		/*
+		 * If pre_handler returns !0, it changes regs->nip. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
-end:
-	preempt_enable_no_resched();
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index e4c5bf33970b..5c60bb0f927f 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs)
 			}
 			prepare_singlestep(p, regs);
 			return 1;
-		} else {
-			if (*addr != BREAKPOINT_INSTRUCTION) {
-				/* If trap variant, then it belongs not to us */
-				kprobe_opcode_t cur_insn = *addr;
-				if (is_trap(cur_insn))
-		       			goto no_kprobe;
-				/* The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
+		} else if (*addr != BREAKPOINT_INSTRUCTION) {
+			/* If trap variant, then it belongs not to us */
+			kprobe_opcode_t cur_insn = *addr;
+
+			if (is_trap(cur_insn))
 				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				if (!skip_singlestep(p, regs, kcb))
-					goto ss_probe;
-				ret = 1;
-			}
+			/* The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs)
 			 */
 			kprobe_opcode_t cur_insn = *addr;
 			if (is_trap(cur_insn))
-		       		goto no_kprobe;
+				goto no_kprobe;
 			/*
 			 * The breakpoint instruction was removed right
 			 * after we hit it.  Another cpu has removed
@@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs)
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs, kcb);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* handler changed execution path, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
 
@@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry)
 }
 NOKPROBE_SYMBOL(arch_deref_entry_point);
 
-int 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();
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef PPC64_ELF_ABI_v2
-	regs->gpr[12] = (unsigned long)jp->entry;
-#elif defined(PPC64_ELF_ABI_v1)
-	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
-#endif
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void __used jprobe_return(void)
-{
-	asm volatile("jprobe_return_trap:\n"
-		     "trap\n"
-		     ::: "memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) {
-		pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n",
-				regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap"));
-		return 0;
-	}
-
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 9a5b5a513604..32476a6e4e9c 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -104,39 +104,13 @@ ftrace_regs_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load the possibly modified NIP */
-	ld	r15, _NIP(r1)
-
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14, r15	/* has NIP been altered? */
+	cmpd	r14, r3		/* has NIP been altered? */
 #endif
 
-#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
-	/* NIP has not been altered, skip over further checks */
-	beq	1f
-
-	/* Check if there is an active jprobe on us */
-	subi	r3, r14, 4
-	bl	__is_active_jprobe
-	nop
-
-	/*
-	 * If r3 == 1, then this is a kprobe/jprobe.
-	 * else, this is livepatched function.
-	 *
-	 * The conditional branch for livepatch_handler below will use the
-	 * result of this comparison. For kprobe/jprobe, we just need to branch to
-	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
-	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
-	 * CR0[EQ] = (r3 == 1).
-	 */
-	cmpdi	r3, 1
-1:
-#endif
-
-	/* Load CTR with the possibly modified NIP */
-	mtctr	r15
-
 	/* Restore gprs */
 	REST_GPR(0,r1)
 	REST_10GPRS(2,r1)
@@ -154,10 +128,7 @@ ftrace_regs_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /*
-	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
-	 * not on a kprobe/jprobe, then handle livepatch.
-	 */
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
 	bne-	livepatch_handler
 #endif
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3f66fcf8ad99..19d8ab49d1bd 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count,
 }
 
 /*
- * Add a event to the PMU.
+ * Add an event to the PMU.
  * If all events are not already frozen, then we disable and
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
@@ -1548,7 +1548,7 @@ nocheck:
 }
 
 /*
- * Remove a event from the PMU.
+ * Remove an event from the PMU.
  */
 static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
@@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
- * A event can only go on a limited PMC if it counts something
+ * An event can only go on a limited PMC if it counts something
  * that a limited PMC can count, doesn't require interrupts, and
  * doesn't exclude any processor mode.
  */
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 13de80cf741c..b106aa29bf55 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -68,8 +68,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_saved_imask;
 	unsigned long kprobe_saved_ctl[3];
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *p);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 60f60afa645c..7c0a095e9c5f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs)
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with single stepping. 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.
+			 * for changing execution path, so get out doing
+			 * nothing more here.
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-			if (p->pre_handler && p->pre_handler(p, regs))
+			if (p->pre_handler && p->pre_handler(p, regs)) {
+				pop_kprobe(kcb);
+				preempt_enable_no_resched();
 				return 1;
+			}
 			kcb->kprobe_status = KPROBE_HIT_SS;
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			/*
-			 * Continuation after the jprobe completed and
-			 * caused the jprobe_return trap. The jprobe
-			 * break_handler "returns" to the original
-			 * function that still has the kprobe breakpoint
-			 * installed. We continue with single stepping.
-			 */
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			enable_singlestep(kcb, regs,
-					  (unsigned long) p->ainsn.insn);
-			return 1;
-		} /* else:
-		   * No kprobe at this address and the current kprobe
-		   * has no break handler (no jprobe!). The kernel just
-		   * exploded, let the standard trap handler pick up the
-		   * pieces.
-		   */
 	} /* else:
 	   * No kprobe at this address and no active kprobe. The trap has
 	   * not been caused by a kprobe breakpoint. The race of breakpoint
@@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 
 	regs->psw.addr = orig_ret_address;
 
-	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self,
 }
 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);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry;
-	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-
-	/* r15 is the stack pointer */
-	stack = (unsigned long) regs->gprs[15];
-
-	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
-
-	/*
-	 * 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)
-{
-	asm volatile(".word 0x0002");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-
-	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
-
-	/* Put the regs back */
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* put the stack back */
-	memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 7431c172c0cb..199d17b765f2 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 
 struct arch_hw_breakpoint {
-	char		*name; /* Contains name of the symbol to set bkpt */
 	unsigned long	address;
 	u16		len;
 	u16		type;
@@ -41,6 +40,7 @@ struct sh_ubc {
 	struct clk	*clk;	/* optional interface clock / MSTP bit */
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct task_struct;
 struct pmu;
@@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type)
 }
 
 /* arch/sh/kernel/hw_breakpoint.c */
-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/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 85d8bcaa8493..6171682f7798 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -27,7 +27,6 @@ struct kprobe;
 
 void arch_remove_kprobe(struct kprobe *);
 void kretprobe_trampoline(void);
-void jprobe_return_end(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
@@ -43,9 +42,6 @@ struct prev_kprobe {
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	unsigned long jprobe_saved_r15;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 8648ed05ccf0..d9ff3b42da7c 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len)
 /*
  * Check for virtual address 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->len);
+	va = hw->address;
+	len = get_hbp_len(hw->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type,
 	return 0;
 }
 
-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);
-
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = SH_BREAKPOINT_LEN_1;
+		hw->len = SH_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = SH_BREAKPOINT_LEN_2;
+		hw->len = SH_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = SH_BREAKPOINT_LEN_4;
+		hw->len = SH_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->len = SH_BREAKPOINT_LEN_8;
+		hw->len = SH_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_READ;
+		hw->type = SH_BREAKPOINT_READ;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = SH_BREAKPOINT_WRITE;
+		hw->type = SH_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_RW;
+		hw->type = SH_BREAKPOINT_RW;
 		break;
 	default:
 		return -EINVAL;
@@ -219,19 +218,20 @@ 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;
 
 	ret = -EINVAL;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case SH_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
@@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	}
 
 	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)kallsyms_lookup_name(info->name);
-
-	/*
 	 * 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;
@@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (!arch_check_bp_in_kernelspace(bp)) {
+		if (!arch_check_bp_in_kernelspace(&bp->hw.info)) {
 			force_sig_fault(SIGTRAP, TRAP_HWBKPT,
 					(void __user *)NULL, current);
 		}
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 52a5e11247d1..241e903dd3ee 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else {
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		}
 		goto no_kprobe;
 	}
@@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->pc = orig_ret_address;
 	kretprobe_hash_unlock(current, &flags);
 
-	preempt_enable_no_resched();
-
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
@@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				if (post_kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
 			} else {
-				if (kprobe_handler(args->regs)) {
+				if (kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
-				} else {
-					p = __this_cpu_read(current_kprobe);
-					if (p->break_handler &&
-					    p->break_handler(p, args->regs))
-						ret = NOTIFY_STOP;
-				}
 			}
 		}
 	}
@@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes 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_r15 = regs->regs[15];
-	addr = kcb->jprobe_saved_r15;
-
-	/*
-	 * TBD: 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.
-	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
-	       MIN_STACK_SIZE(addr));
-
-	regs->pc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack_addr = kcb->jprobe_saved_r15;
-	u8 *addr = (u8 *)regs->pc;
-
-	if ((addr >= (u8 *)jprobe_return) &&
-	    (addr <= (u8 *)jprobe_return_end)) {
-		*regs = kcb->jprobe_saved_regs;
-
-		memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-
-		kcb->kprobe_status = KPROBE_HIT_SS;
-		preempt_enable_no_resched();
-		return 1;
-	}
-
-	return 0;
-}
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 3704490b4488..bfcaa6326c20 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -44,7 +44,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_orig_tnpc;
 	unsigned long kprobe_orig_tstate_pil;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index ab4ba4347941..dfbca2470536 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			kcb->kprobe_status = KPROBE_REENTER;
 			prepare_singlestep(p, regs, kcb);
 			return 1;
-		} else {
-			if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
+		} else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
 			 * handling of this interrupt is appropriate
 			 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -441,53 +437,6 @@ out:
 	exception_exit(prev_state);
 }
 
-/* Jprobes support.  */
-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();
-
-	memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
-
-	regs->tpc  = (unsigned long) jp->entry;
-	regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
-	regs->tstate |= TSTATE_PIL;
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	register unsigned long orig_fp asm("g1");
-
-	orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
-	__asm__ __volatile__("\n"
-"1:	cmp		%%sp, %0\n\t"
-	"blu,a,pt	%%xcc, 1b\n\t"
-	" restore\n\t"
-	".globl		jprobe_return_trap_instruction\n"
-"jprobe_return_trap_instruction:\n\t"
-	"ta		0x70"
-	: /* no outputs */
-	: "r" (orig_fp));
-}
-
-extern void jprobe_return_trap_instruction(void);
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	u32 *addr = (u32 *) regs->tpc;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (addr == (u32 *) jprobe_return_trap_instruction) {
-		memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 /* The value stored in the return address register is actually 2
  * instructions before where the callee will return to.
  * Sequences usually look something like this
@@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 86f0c15dcc2d..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
-
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
 		x86_perf_event_update(event);
 }
 
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
+	u64 ctrl_val, mask, bits = 0;
 
 	/*
-	 * Enable IRQ generation (0x8),
+	 * Enable IRQ generation (0x8), if not PEBS,
 	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
 	 * if requested:
 	 */
-	bits = 0x8ULL;
+	if (!event->attr.precise_ip)
+		bits |= 0x8;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event_is_checkpointed(event)))
 		cpuc->intel_cp_status |= (1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc);
+		intel_pmu_enable_fixed(event);
 		return;
 	}
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
-
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
@@ -2280,7 +2282,10 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		status &= ~cpuc->pebs_enabled;
+	else
+		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -4072,7 +4077,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_skl();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_glm_extra_regs;
 		/*
 		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4082,6 +4086,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
 		x86_pmu.cpu_events = glm_events_attrs;
 		/* Goldmont Plus has 4-wide pipeline */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8dbba77e0518..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_glp_pebs_event_constraints[] = {
-	/* Allow all events as PEBS with no flags */
-	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
-	EVENT_CONSTRAINT_END
-};
-
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -871,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * Extended PEBS support
+	 * Makes the PEBS code search the normal constraints.
+	 */
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		return NULL;
+
 	return &emptyconstraint;
 }
 
@@ -896,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	u64 threshold;
+	int reserved;
+
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+	else
+		reserved = x86_pmu.max_pebs_events;
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+			reserved * x86_pmu.pebs_record_size;
 	} else {
 		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 	}
@@ -963,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		ds->pebs_event_reset[hwc->idx] =
+		unsigned int idx = hwc->idx;
+
+		if (idx >= INTEL_PMC_IDX_FIXED)
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
@@ -1481,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	short counts[MAX_PEBS_EVENTS] = {};
-	short error[MAX_PEBS_EVENTS] = {};
-	int bit, i;
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int bit, i, size;
+	u64 mask;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1493,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
+	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+	size = x86_pmu.max_pebs_events;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+	}
+
 	if (unlikely(base >= top)) {
 		/*
 		 * The drain_pebs() could be called twice in a short period
@@ -1502,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * update the event->count for this case.
 		 */
 		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 x86_pmu.max_pebs_events) {
+				 size) {
 			event = cpuc->events[bit];
 			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 				intel_pmu_save_and_restart_reload(event, 0);
@@ -1515,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		u64 pebs_status;
 
 		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+		pebs_status &= mask;
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
 			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+					 size)
 				counts[bit]++;
 
 			continue;
@@ -1568,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+	for (bit = 0; bit < size; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
 
 void intel_pmu_lbr_reset(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
 	if (!x86_pmu.lbr_nr)
 		return;
 
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
+
+	cpuc->last_task_ctx = NULL;
+	cpuc->last_log_id = 0;
 }
 
 /*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
 
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
@@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		return;
 	}
 
-	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
-	for (i = 0; i < tos; i++) {
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Did not enter C6
+	 */
+	if ((task_ctx == cpuc->last_task_ctx) &&
+	    (task_ctx->log_id == cpuc->last_log_id) &&
+	    rdlbr_from(tos)) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
 		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+
+	for (; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrlbr_from(lbr_idx, 0);
+		wrlbr_to(lbr_idx, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+	}
+
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned lbr_idx, mask;
-	u64 tos;
+	u64 tos, from;
 	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
@@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		from = rdlbr_from(lbr_idx);
+		if (!from)
+			break;
+		task_ctx->lbr_from[i] = from;
 		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = task_ctx;
+	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
@@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
-	bool need_info = false;
+	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	if (cpuc->lbr_sel) {
 		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
 		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-			num = tos;
+			call_stack = true;
 	}
 
 	for (i = 0; i < num; i++) {
@@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		from = rdlbr_from(lbr_idx);
 		to   = rdlbr_to(lbr_idx);
 
+		/*
+		 * Read LBR call stack entries
+		 * until invalid entry (0s) is detected.
+		 */
+		if (call_stack && !from)
+			break;
+
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9f3711470ec1..156286335351 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -163,6 +163,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
+struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
@@ -214,6 +215,8 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
 	u64				br_sel;
+	struct x86_perf_task_context	*last_task_ctx;
+	int				last_log_id;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -648,8 +651,10 @@ struct x86_perf_task_context {
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
 	int tos;
+	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
+	int log_id;
 };
 
 #define x86_add_quirk(func_)						\
@@ -668,6 +673,7 @@ do {									\
 #define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
 #define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index f59c39835a5a..a1f0e90d0818 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type)
 	return HBP_NUM;
 }
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
-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/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 62a9f4966b42..ae26df1c2789 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,6 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
+#define MAX_FIXED_PEBS_EVENTS	3
 
 /*
  * A debug store configuration.
@@ -23,7 +24,7 @@ struct debug_store {
 	u64	pebs_index;
 	u64	pebs_absolute_maximum;
 	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+	u64	pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS];
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 367d99cff426..c8cec1b39b88 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -78,7 +78,7 @@ struct arch_specific_insn {
 	 * boostable = true: This instruction has been boosted: we have
 	 * added a relative jump after the instruction copy in insn,
 	 * so no single-step and fixup are needed (unless there's
-	 * a post_handler or break_handler).
+	 * a post_handler).
 	 */
 	bool boostable;
 	bool if_modifier;
@@ -111,9 +111,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_old_flags;
 	unsigned long kprobe_saved_flags;
-	unsigned long *jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
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;
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index dbe3053b284a..9f119c1ca0b5 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -30,13 +30,16 @@ struct arch_hw_breakpoint {
 	u16 type;
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct pt_regs;
 struct task_struct;
 
 int hw_breakpoint_slots(int type);
-int arch_check_bp_in_kernelspace(struct perf_event *bp);
-int arch_validate_hwbkpt_settings(struct perf_event *bp);
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw);
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
 
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index b35656ab7dbd..c2e387c19cda 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type)
 	}
 }
 
-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 = bp->attr.bp_len;
+	va = hw->address;
+	len = hw->len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(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);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->type = XTENSA_BREAKPOINT_EXECUTE;
+		hw->type = XTENSA_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->type = XTENSA_BREAKPOINT_LOAD;
+		hw->type = XTENSA_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	info->len = bp->attr.bp_len;
-	if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len))
+	hw->len = attr->bp_len;
+	if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len))
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
-	if (info->address & (info->len - 1))
+	hw->address = attr->bp_addr;
+	if (hw->address & (hw->len - 1))
 		return -EINVAL;
 
 	return 0;
 }
 
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
-{
-	int ret;
-
-	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
-	return ret;
-}
-
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data)
 {
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..e909413e4e38 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -63,7 +63,6 @@ struct pt_regs;
 struct kretprobe;
 struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
-typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
 				       unsigned long flags);
 typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
@@ -101,12 +100,6 @@ struct kprobe {
 	 */
 	kprobe_fault_handler_t fault_handler;
 
-	/*
-	 * ... called if breakpoint trap occurs in probe handler.
-	 * Return 1 if it handled break, otherwise kernel will see it.
-	 */
-	kprobe_break_handler_t break_handler;
-
 	/* Saved opcode (which has been replaced with breakpoint) */
 	kprobe_opcode_t opcode;
 
@@ -155,24 +148,6 @@ static inline int kprobe_ftrace(struct kprobe *p)
 }
 
 /*
- * Special probe type that uses setjmp-longjmp type tricks to resume
- * execution at a specified entry with a matching prototype corresponding
- * to the probed function - a trick to enable arguments to become
- * accessible seamlessly by probe handling logic.
- * Note:
- * Because of the way compilers allocate stack space for local variables
- * etc upfront, regardless of sub-scopes within a function, this mirroring
- * principle currently works only for probes placed on function entry points.
- */
-struct jprobe {
-	struct kprobe kp;
-	void *entry;	/* probe handling code to jump to */
-};
-
-/* For backward compatibility with old code using JPROBE_ENTRY() */
-#define JPROBE_ENTRY(handler)	(handler)
-
-/*
  * Function-return probe -
  * Note:
  * User needs to provide a handler function, and initialize maxactive.
@@ -389,9 +364,6 @@ int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
 int register_kprobes(struct kprobe **kps, int num);
 void unregister_kprobes(struct kprobe **kps, int num);
-int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
-int longjmp_break_handler(struct kprobe *, struct pt_regs *);
-void jprobe_return(void);
 unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
@@ -439,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p)
 static inline void unregister_kprobes(struct kprobe **kps, int num)
 {
 }
-static inline void jprobe_return(void)
-{
-}
 static inline int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
@@ -468,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp)
 	return -ENOSYS;
 }
 #endif /* CONFIG_KPROBES */
-static inline int register_jprobe(struct jprobe *p)
-{
-	return -ENOSYS;
-}
-static inline int register_jprobes(struct jprobe **jps, int num)
-{
-	return -ENOSYS;
-}
-static inline void unregister_jprobe(struct jprobe *p)
-{
-}
-static inline void unregister_jprobes(struct jprobe **jps, int num)
-{
-}
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
 	return disable_kprobe(&rp->kp);
@@ -490,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp)
 {
 	return enable_kprobe(&rp->kp);
 }
-static inline int disable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
-static inline int enable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
 
 #ifndef CONFIG_KPROBES
 static inline bool is_kprobe_insn_slot(unsigned long addr)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 87f6db437e4a..53c500f0ca79 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -490,7 +490,7 @@ struct perf_addr_filters_head {
 };
 
 /**
- * enum perf_event_state - the states of a event
+ * enum perf_event_state - the states of an event:
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -4,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eec2d5fb676b..f6ea33a9f904 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event)
 				typeof(*event), group_node))
 
 /*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event)
 }
 
 /*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event,
 }
 
 /*
- * Disable a event.
+ * Disable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event,
 }
 
 /*
- * Enable a event.
+ * Enable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info)
 	 * events will refuse to restart because of rb::aux_mmap_count==0,
 	 * see comments in perf_aux_output_begin().
 	 *
-	 * Since this is happening on a event-local CPU, no trace is lost
+	 * Since this is happening on an event-local CPU, no trace is lost
 	 * while restarting.
 	 */
 	if (sd->restart)
@@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count)
 	int ret;
 
 	/*
-	 * Return end-of-file for a read on a event that is in
+	 * Return end-of-file for a read on an event that is in
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
@@ -5273,11 +5273,11 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
 {
 	struct perf_event *event = vmf->vma->vm_file->private_data;
 	struct ring_buffer *rb;
-	int ret = VM_FAULT_SIGBUS;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	if (vmf->flags & FAULT_FLAG_MKWRITE) {
 		if (vmf->pgoff == 0)
@@ -9904,7 +9904,7 @@ enabled:
 }
 
 /*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
  */
 static struct perf_event *
 perf_event_alloc(struct perf_event_attr *attr, int cpu,
@@ -11235,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
  *
  * Returns:
  *  - valid pointer on success
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6e28d2866be5..b3814fce5ecb 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp)
 	mutex_unlock(&nr_bp_mutex);
 }
 
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int err;
 
 	__release_bp_slot(bp, old_type);
 
-	err = __reserve_bp_slot(bp, bp->attr.bp_type);
+	err = __reserve_bp_slot(bp, new_type);
 	if (err) {
 		/*
 		 * Reserve the old_type slot back in case
@@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
 	return err;
 }
 
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int ret;
 
 	mutex_lock(&nr_bp_mutex);
-	ret = __modify_bp_slot(bp, old_type);
+	ret = __modify_bp_slot(bp, old_type, new_type);
 	mutex_unlock(&nr_bp_mutex);
 	return ret;
 }
@@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
-static int validate_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_parse(struct perf_event *bp,
+			       const struct perf_event_attr *attr,
+			       struct arch_hw_breakpoint *hw)
 {
-	int ret;
+	int err;
 
-	ret = arch_validate_hwbkpt_settings(bp);
-	if (ret)
-		return ret;
+	err = hw_breakpoint_arch_parse(bp, attr, hw);
+	if (err)
+		return err;
 
-	if (arch_check_bp_in_kernelspace(bp)) {
-		if (bp->attr.exclude_kernel)
+	if (arch_check_bp_in_kernelspace(hw)) {
+		if (attr->exclude_kernel)
 			return -EINVAL;
 		/*
 		 * Don't let unprivileged users set a breakpoint in the trap
@@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp)
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
-	int ret;
-
-	ret = reserve_bp_slot(bp);
-	if (ret)
-		return ret;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	ret = validate_hw_breakpoint(bp);
+	err = reserve_bp_slot(bp);
+	if (err)
+		return err;
 
-	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
-	if (ret)
+	err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+	if (err) {
 		release_bp_slot(bp);
+		return err;
+	}
 
-	return ret;
+	bp->hw.info = hw;
+
+	return 0;
 }
 
 /**
@@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+				    struct perf_event_attr *from)
+{
+	to->bp_addr = from->bp_addr;
+	to->bp_type = from->bp_type;
+	to->bp_len  = from->bp_len;
+	to->disabled = from->disabled;
+}
+
 int
 modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
 			        bool check)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len  = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	bool modify  = attr->bp_type != old_type;
-	int err = 0;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	bp->attr.bp_addr = attr->bp_addr;
-	bp->attr.bp_type = attr->bp_type;
-	bp->attr.bp_len  = attr->bp_len;
+	err = hw_breakpoint_parse(bp, attr, &hw);
+	if (err)
+		return err;
 
-	if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
-		return -EINVAL;
+	if (check) {
+		struct perf_event_attr old_attr;
 
-	err = validate_hw_breakpoint(bp);
-	if (!err && modify)
-		err = modify_bp_slot(bp, old_type);
+		old_attr = bp->attr;
+		hw_breakpoint_copy_attr(&old_attr, attr);
+		if (memcmp(&old_attr, attr, sizeof(*attr)))
+			return -EINVAL;
+	}
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len  = old_len;
-		return err;
+	if (bp->attr.bp_type != attr->bp_type) {
+		err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+		if (err)
+			return err;
 	}
 
-	bp->attr.disabled = attr->disabled;
+	hw_breakpoint_copy_attr(&bp->attr, attr);
+	bp->hw.info = hw;
+
 	return 0;
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ccc579a7d32e..aed1ba569954 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 EXPORT_SYMBOL_GPL(uprobe_register);
 
 /*
- * uprobe_apply - unregister a already registered probe.
+ * uprobe_apply - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: consumer which wants to add more or remove some breakpoints
@@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 }
 
 /*
- * uprobe_unregister - unregister a already registered probe.
+ * uprobe_unregister - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: identify which probe if multiple probes are colocated.
@@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri)
 
 /*
  * Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
  */
 void uprobe_free_utask(struct task_struct *t)
 {
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 5349c91c2298..bc80a4e268c0 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
 	if (should_fail(&fei_fault_attr, 1)) {
 		regs_set_return_value(regs, attr->retval);
 		override_function_with_return(regs);
-		/* Kprobe specific fixup */
-		reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ea619021d901..ab257be4d924 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p)
 	    (kprobe_disabled(p) || kprobes_all_disarmed))
 		return;
 
-	/* Both of break_handler and post_handler are not supported. */
-	if (p->break_handler || p->post_handler)
+	/* kprobes with post_handler can not be optimized */
+	if (p->post_handler)
 		return;
 
 	op = container_of(p, struct optimized_kprobe, kp);
@@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	 * there is still a relative jump) and disabled.
 	 */
 	op = container_of(ap, struct optimized_kprobe, kp);
-	if (unlikely(list_empty(&op->list)))
-		printk(KERN_WARNING "Warning: found a stray unused "
-			"aggrprobe@%p\n", ap->addr);
+	WARN_ON_ONCE(list_empty(&op->list));
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
@@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p)
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 				   (unsigned long)p->addr, 0, 0);
 	if (ret) {
-		pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+		pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+			 p->addr, ret);
 		return ret;
 	}
 
@@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 			   (unsigned long)p->addr, 1, 0);
-	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+		  p->addr, ret);
 	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
@@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(aggr_fault_handler);
 
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe *cur = __this_cpu_read(kprobe_instance);
-	int ret = 0;
-
-	if (cur && cur->break_handler) {
-		if (cur->break_handler(cur, regs))
-			ret = 1;
-	}
-	reset_kprobe_instance();
-	return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
 /* Walks the list and increments nmissed count for multiprobe case */
 void kprobes_inc_nmissed_count(struct kprobe *p)
 {
@@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 }
 NOKPROBE_SYMBOL(cleanup_rp_inst);
 
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
-*/
+/* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 
-	if (p->break_handler || p->post_handler)
+	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
-	if (p->break_handler) {
-		if (ap->break_handler)
-			return -EEXIST;
-		list_add_tail_rcu(&p->list, &ap->list);
-		ap->break_handler = aggr_break_handler;
-	} else
-		list_add_rcu(&p->list, &ap->list);
+	list_add_rcu(&p->list, &ap->list);
 	if (p->post_handler && !ap->post_handler)
 		ap->post_handler = aggr_post_handler;
 
@@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	/* We don't care the kprobe which has gone. */
 	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
-	if (p->break_handler && !kprobe_gone(p))
-		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
 	INIT_HLIST_NODE(&ap->hlist);
@@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p)
 		goto disarmed;
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
-		if (p->break_handler && !kprobe_gone(p))
-			ap->break_handler = NULL;
 		if (p->post_handler && !kprobe_gone(p)) {
 			list_for_each_entry_rcu(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
@@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
-	int ret = 0, i;
-
-	if (num <= 0)
-		return -EINVAL;
-
-	for (i = 0; i < num; i++) {
-		ret = register_jprobe(jps[i]);
-
-		if (ret < 0) {
-			if (i > 0)
-				unregister_jprobes(jps, i);
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
-	unsigned long addr, offset;
-	struct kprobe *kp = &jp->kp;
-
-	/*
-	 * Verify probepoint as well as the jprobe handler are
-	 * valid function entry points.
-	 */
-	addr = arch_deref_entry_point(jp->entry);
-
-	if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
-	    kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
-		kp->pre_handler = setjmp_pre_handler;
-		kp->break_handler = longjmp_break_handler;
-		return register_kprobe(kp);
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
-	unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
-	int i;
-
-	if (num <= 0)
-		return;
-	mutex_lock(&kprobe_mutex);
-	for (i = 0; i < num; i++)
-		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
-			jps[i]->kp.addr = NULL;
-	mutex_unlock(&kprobe_mutex);
-
-	synchronize_sched();
-	for (i = 0; i < num; i++) {
-		if (jps[i]->kp.addr)
-			__unregister_kprobe_bottom(&jps[i]->kp);
-	}
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
 #ifdef CONFIG_KRETPROBES
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
@@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp)
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 	rp->kp.fault_handler = NULL;
-	rp->kp.break_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
@@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p)
 		list_for_each_entry_rcu(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
-		p->break_handler = NULL;
 		kill_optimized_kprobe(p);
 	}
 	/*
@@ -2169,11 +2069,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(enable_kprobe);
 
+/* Caller must NOT call this in usual path. This is only for critical case */
 void dump_kprobe(struct kprobe *kp)
 {
-	printk(KERN_WARNING "Dumping kprobe:\n");
-	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
-	       kp->symbol_name, kp->addr, kp->offset);
+	pr_err("Dumping kprobe:\n");
+	pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+	       kp->symbol_name, kp->offset, kp->addr);
 }
 NOKPROBE_SYMBOL(dump_kprobe);
 
@@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 		entry = arch_deref_entry_point((void *)*iter);
 
 		if (!kernel_text_address(entry) ||
-		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
-			pr_err("Failed to find blacklist at %p\n",
-				(void *)entry);
+		    !kallsyms_lookup_size_offset(entry, &size, &offset))
 			continue;
-		}
 
 		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 		if (!ent)
@@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
+	void *addr = p->addr;
 
 	if (p->pre_handler == pre_handler_kretprobe)
 		kprobe_type = "r";
-	else if (p->pre_handler == setjmp_pre_handler)
-		kprobe_type = "j";
 	else
 		kprobe_type = "k";
 
+	if (!kallsyms_show_value())
+		addr = NULL;
+
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s ",
-			p->addr, kprobe_type, sym, offset,
+		seq_printf(pi, "%px  %s  %s+0x%x  %s ",
+			addr, kprobe_type, sym, offset,
 			(modname ? modname : " "));
-	else
-		seq_printf(pi, "%p  %s  %p ",
-			p->addr, kprobe_type, p->addr);
+	else	/* try to use %pS */
+		seq_printf(pi, "%px  %s  %pS ",
+			addr, kprobe_type, p->addr);
 
 	if (!pp)
 		pp = p;
@@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	struct kprobe_blacklist_entry *ent =
 		list_entry(v, struct kprobe_blacklist_entry, list);
 
-	seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
-		   (void *)ent->end_addr, (void *)ent->start_addr);
+	/*
+	 * If /proc/kallsyms is not showing kernel address, we won't
+	 * show them here either.
+	 */
+	if (!kallsyms_show_value())
+		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+			   (void *)ent->start_addr);
+	else
+		seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+			   (void *)ent->end_addr, (void *)ent->start_addr);
 	return 0;
 }
 
@@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!dir)
 		return -ENOMEM;
 
-	file = debugfs_create_file("list", 0444, dir, NULL,
+	file = debugfs_create_file("list", 0400, dir, NULL,
 				&debugfs_kprobes_operations);
 	if (!file)
 		goto error;
@@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!file)
 		goto error;
 
-	file = debugfs_create_file("blacklist", 0444, dir, NULL,
+	file = debugfs_create_file("blacklist", 0400, dir, NULL,
 				&debugfs_kprobe_blacklist_ops);
 	if (!file)
 		goto error;
@@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init);
 #endif /* CONFIG_DEBUG_FS */
 
 module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index dd53e354f630..7bca480151b0 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -162,90 +162,6 @@ static int test_kprobes(void)
 
 }
 
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("jprobe-handler is preemptible\n");
-	}
-	if (value != rand1) {
-		handler_errors++;
-		pr_err("incorrect value in jprobe handler\n");
-	}
-
-	jph_val = rand1;
-	jprobe_return();
-	return 0;
-}
-
-static struct jprobe jp = {
-	.entry		= j_kprobe_target,
-	.kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
-	int ret;
-
-	ret = register_jprobe(&jp);
-	if (ret < 0) {
-		pr_err("register_jprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
-	unregister_jprobe(&jp);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
-}
-
-static struct jprobe jp2 = {
-	.entry          = j_kprobe_target,
-	.kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
-	int ret;
-	struct jprobe *jps[2] = {&jp, &jp2};
-
-	/* addr and flags should be cleard for reusing kprobe. */
-	jp.kp.addr = NULL;
-	jp.kp.flags = 0;
-	ret = register_jprobes(jps, 2);
-	if (ret < 0) {
-		pr_err("register_jprobes returned %d\n", ret);
-		return ret;
-	}
-
-	jph_val = 0;
-	ret = target(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	jph_val = 0;
-	ret = target2(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler2 not called\n");
-		handler_errors++;
-	}
-	unregister_jprobes(jps, 2);
-
-	return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
 #ifdef CONFIG_KRETPROBES
 static u32 krph_val;
 
@@ -383,16 +299,6 @@ int init_test_probes(void)
 	if (ret < 0)
 		errors++;
 
-	num_tests++;
-	ret = test_jprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_jprobes();
-	if (ret < 0)
-		errors++;
-
 #ifdef CONFIG_KRETPROBES
 	num_tests++;
 	ret = test_kretprobe();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6b71860f3998..e9d99463e5df 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1228,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 		/*
 		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the single stepping.
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
+		 * pt_regs, and if so return 1 so that we don't do the
+		 * single stepping.
 		 */
-		if (orig_ip != instruction_pointer(regs)) {
-			reset_current_kprobe();
-			preempt_enable_no_resched();
+		if (orig_ip != instruction_pointer(regs))
 			return 1;
-		}
 		if (!ret)
 			return 0;
 	}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..0b066b3c9284 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST
 	default n
 	help
 	  This option provides for testing basic kprobes functionality on
-	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  boot. Samples of kprobe and kretprobe are inserted and
 	  verified for functionality.
 
 	  Say N if you are unsure.
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5072cbd15c82
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 000000000000..42990676a55e
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+	       compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+	       compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+	       compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+	       compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+	  compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+	  compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+	  compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+	  compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+	  compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+	  compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+	  compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+	  compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+	  compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+	  compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+	  compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+	  compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+	  compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+	  compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at         264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+	  compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+          compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+          compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions of the Internet Protocol.
+ *
+ * Version:	@(#)in.h	1.0.1	04/21/93
+ *
+ * Authors:	Original taken from the GNU Project <netinet/in.h> file.
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
+#define IPPROTO_IP		IPPROTO_IP
+  IPPROTO_ICMP = 1,		/* Internet Control Message Protocol	*/
+#define IPPROTO_ICMP		IPPROTO_ICMP
+  IPPROTO_IGMP = 2,		/* Internet Group Management Protocol	*/
+#define IPPROTO_IGMP		IPPROTO_IGMP
+  IPPROTO_IPIP = 4,		/* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP		IPPROTO_IPIP
+  IPPROTO_TCP = 6,		/* Transmission Control Protocol	*/
+#define IPPROTO_TCP		IPPROTO_TCP
+  IPPROTO_EGP = 8,		/* Exterior Gateway Protocol		*/
+#define IPPROTO_EGP		IPPROTO_EGP
+  IPPROTO_PUP = 12,		/* PUP protocol				*/
+#define IPPROTO_PUP		IPPROTO_PUP
+  IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
+#define IPPROTO_UDP		IPPROTO_UDP
+  IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+#define IPPROTO_IDP		IPPROTO_IDP
+  IPPROTO_TP = 29,		/* SO Transport Protocol Class 4	*/
+#define IPPROTO_TP		IPPROTO_TP
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP		IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,		/* IPv6-in-IPv4 tunnelling		*/
+#define IPPROTO_IPV6		IPPROTO_IPV6
+  IPPROTO_RSVP = 46,		/* RSVP Protocol			*/
+#define IPPROTO_RSVP		IPPROTO_RSVP
+  IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
+#define IPPROTO_GRE		IPPROTO_GRE
+  IPPROTO_ESP = 50,		/* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP		IPPROTO_ESP
+  IPPROTO_AH = 51,		/* Authentication Header protocol	*/
+#define IPPROTO_AH		IPPROTO_AH
+  IPPROTO_MTP = 92,		/* Multicast Transport Protocol		*/
+#define IPPROTO_MTP		IPPROTO_MTP
+  IPPROTO_BEETPH = 94,		/* IP option pseudo header for BEET	*/
+#define IPPROTO_BEETPH		IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,		/* Encapsulation Header			*/
+#define IPPROTO_ENCAP		IPPROTO_ENCAP
+  IPPROTO_PIM = 103,		/* Protocol Independent Multicast	*/
+#define IPPROTO_PIM		IPPROTO_PIM
+  IPPROTO_COMP = 108,		/* Compression Header Protocol		*/
+#define IPPROTO_COMP		IPPROTO_COMP
+  IPPROTO_SCTP = 132,		/* Stream Control Transport Protocol	*/
+#define IPPROTO_SCTP		IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,	/* UDP-Lite (RFC 3828)			*/
+#define IPPROTO_UDPLITE		IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
+#define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_RAW = 255,		/* Raw IP packets			*/
+#define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+	__be32	s_addr;
+};
+#endif
+
+#define IP_TOS		1
+#define IP_TTL		2
+#define IP_HDRINCL	3
+#define IP_OPTIONS	4
+#define IP_ROUTER_ALERT	5
+#define IP_RECVOPTS	6
+#define IP_RETOPTS	7
+#define IP_PKTINFO	8
+#define IP_PKTOPTIONS	9
+#define IP_MTU_DISCOVER	10
+#define IP_RECVERR	11
+#define IP_RECVTTL	12
+#define	IP_RECVTOS	13
+#define IP_MTU		14
+#define IP_FREEBIND	15
+#define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
+#define IP_PASSSEC	18
+#define IP_TRANSPARENT	19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS	IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
+#define IP_BIND_ADDRESS_NO_PORT	24
+#define IP_RECVFRAGSIZE	25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT		0	/* Never send DF frames */
+#define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
+#define IP_PMTUDISC_DO			2	/* Always DF		*/
+#define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT		5
+
+#define IP_MULTICAST_IF			32
+#define IP_MULTICAST_TTL 		33
+#define IP_MULTICAST_LOOP 		34
+#define IP_ADD_MEMBERSHIP		35
+#define IP_DROP_MEMBERSHIP		36
+#define IP_UNBLOCK_SOURCE		37
+#define IP_BLOCK_SOURCE			38
+#define IP_ADD_SOURCE_MEMBERSHIP	39
+#define IP_DROP_SOURCE_MEMBERSHIP	40
+#define IP_MSFILTER			41
+#define MCAST_JOIN_GROUP		42
+#define MCAST_BLOCK_SOURCE		43
+#define MCAST_UNBLOCK_SOURCE		44
+#define MCAST_LEAVE_GROUP		45
+#define MCAST_JOIN_SOURCE_GROUP		46
+#define MCAST_LEAVE_SOURCE_GROUP	47
+#define MCAST_MSFILTER			48
+#define IP_MULTICAST_ALL		49
+#define IP_UNICAST_IF			50
+
+#define MCAST_EXCLUDE	0
+#define MCAST_INCLUDE	1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+	struct in_addr imr_multiaddr;	/* IP multicast address of group */
+	struct in_addr imr_interface;	/* local IP address of interface */
+};
+
+struct ip_mreqn {
+	struct in_addr	imr_multiaddr;		/* IP multicast address of group */
+	struct in_addr	imr_address;		/* local IP address of interface */
+	int		imr_ifindex;		/* Interface index */
+};
+
+struct ip_mreq_source {
+	__be32		imr_multiaddr;
+	__be32		imr_interface;
+	__be32		imr_sourceaddr;
+};
+
+struct ip_msfilter {
+	__be32		imsf_multiaddr;
+	__be32		imsf_interface;
+	__u32		imsf_fmode;
+	__u32		imsf_numsrc;
+	__be32		imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+	(sizeof(struct ip_msfilter) - sizeof(__u32) \
+	+ (numsrc) * sizeof(__u32))
+
+struct group_req {
+	__u32				 gr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gr_group;	/* group address */
+};
+
+struct group_source_req {
+	__u32				 gsr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gsr_group;	/* group address */
+	struct __kernel_sockaddr_storage gsr_source;	/* source address */
+};
+
+struct group_filter {
+	__u32				 gf_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+	__u32				 gf_fmode;	/* filter mode */
+	__u32				 gf_numsrc;	/* number of sources */
+	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+	int		ipi_ifindex;
+	struct in_addr	ipi_spec_dst;
+	struct in_addr	ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
+struct sockaddr_in {
+  __kernel_sa_family_t	sin_family;	/* Address family		*/
+  __be16		sin_port;	/* Port number			*/
+  struct in_addr	sin_addr;	/* Internet address		*/
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char		__pad[__SOCK_SIZE__ - sizeof(short int) -
+			sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define	IN_CLASSA(a)		((((long int) (a)) & 0x80000000) == 0)
+#define	IN_CLASSA_NET		0xff000000
+#define	IN_CLASSA_NSHIFT	24
+#define	IN_CLASSA_HOST		(0xffffffff & ~IN_CLASSA_NET)
+#define	IN_CLASSA_MAX		128
+
+#define	IN_CLASSB(a)		((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define	IN_CLASSB_NET		0xffff0000
+#define	IN_CLASSB_NSHIFT	16
+#define	IN_CLASSB_HOST		(0xffffffff & ~IN_CLASSB_NET)
+#define	IN_CLASSB_MAX		65536
+
+#define	IN_CLASSC(a)		((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define	IN_CLASSC_NET		0xffffff00
+#define	IN_CLASSC_NSHIFT	8
+#define	IN_CLASSC_HOST		(0xffffffff & ~IN_CLASSC_NET)
+
+#define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define	IN_MULTICAST(a)		IN_CLASSD(a)
+#define IN_MULTICAST_NET	0xF0000000
+
+#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define	INADDR_ANY		((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define	INADDR_BROADCAST	((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define	INADDR_NONE		((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define	IN_LOOPBACKNET		127
+
+/* Address to loopback in software to local host.  */
+#define	INADDR_LOOPBACK		0x7f000001	/* 127.0.0.1   */
+#define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
 	selects either tracepoint event(s) or a hardware trace PMU
 	(e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
-	a event selector (-e) which selects tracepoint event(s). It adds a
+	an event selector (-e) which selects tracepoint event(s). It adds a
 	filter expression 'common_pid != $PERFPID' to filters. If other
 	'--filter' exists, the new filter expression will be combined with
 	them by '&&'.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f5a3b402589e..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
@@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..f013b115dc86 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..52e197317d3e
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#define __ARCH_WANT_RENAMEAT
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index ef5d59a5742e..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
 	}
 
 	/*
-	 * Check if return address is on the stack.
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
 	 */
-	if (nops != 0 || ops != NULL)
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
 		return 0;
 
 	/*
@@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	if (!chain || chain->nr < 3)
 		return skip_slot;
 
-	ip = chain->ips[2];
+	ip = chain->ips[1];
 
 	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-	if (strstr(cpuid, "IBM/S390")) {
+	if (strstr(cpuid, "IBM")) {
 		kvm->exit_reasons = sie_exit_reasons;
 		kvm->exit_reasons_isa = "SIE";
 	} else
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
 	fprintf(out, "%s\n", bf);
 	fprintf(out, "  -------------------------------------------------------------\n");
 
-	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 	fprintf(out, "#\n");
 
-	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
 	fprintf(out, "\n");
 	fprintf(out, "=================================================\n");
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
 	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-		       symbol_conf.use_callchain);
+		       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c04dc7b53797..02f7a3c27761 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-			       symbol_conf.use_callchain ||
-			       symbol_conf.show_branchflag_count);
+			       !(symbol_conf.use_callchain ||
+			         symbol_conf.show_branchflag_count));
 		fprintf(stdout, "\n\n");
 	}
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 05be023c3f0e..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		return 1;
-
-	return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double msecs = avg / NSEC_PER_MSEC;
-	const char *fmt_v, *fmt_n;
-	char name[25];
-
-	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-	fmt_n = csv_output ? "%s" : "%-25s";
-
-	aggr_printout(evsel, id, nr);
-
-	scnprintf(name, sizeof(name), "%s%s",
-		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-	fprintf(output, fmt_v, msecs, csv_sep);
-
-	if (csv_output)
-		fprintf(output, "%s%s", evsel->unit, csv_sep);
-	else
-		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-	fprintf(output, fmt_n, name);
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
 	int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (metric_only)
-		/* nothing */;
-	else if (nsec_counter(counter))
-		nsec_printout(id, nr, counter, uval);
-	else
+	if (!metric_only)
 		abs_printout(id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    nsec_counter(alias) != nsec_counter(counter))
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
 		cb(alias, data, false);
@@ -2449,6 +2405,18 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		/* Handle -T as -M transaction. Once platform specific metrics
+		 * support has been added to the json files, all archictures
+		 * will use this approach. To determine transaction support
+		 * on an architecture test for such a metric name.
+		 */
+		if (metricgroup__has_metric("transaction")) {
+			struct option opt = { .value = &evsel_list };
+
+			return metricgroup__parse_groups(&opt, "transaction",
+							 &metric_events);
+		}
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout, symbol_conf.use_callchain);
+		       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +761,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
@@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1I_L3_LOCAL_WRITES",
 		"BriefDescription": "L1I L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1D_L3_LOCAL_WRITES",
 		"BriefDescription": "L1D L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1I_L3_REMOTE_WRITES",
 		"BriefDescription": "L1I L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L3_REMOTE_WRITES",
 		"BriefDescription": "L1D L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_CACHELINE_INVALIDATES",
 		"BriefDescription": "L1I Cacheline Invalidates",
 		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
 		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB1_MISSES",
 		"BriefDescription": "L1C TLB1 Misses",
 		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "176",
 		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "218",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "219",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "220",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB2_WRITES",
 		"BriefDescription": "DTLB2 Writes",
 		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB2_MISSES",
 		"BriefDescription": "DTLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB2_GPAGE_WRITES",
 		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
 		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB2_WRITES",
 		"BriefDescription": "ITLB2 Writes",
 		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB2_MISSES",
 		"BriefDescription": "ITLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_ENGINES_BUSY",
 		"BriefDescription": "TLB2 Engines Busy",
 		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB2_MISSES",
 		"BriefDescription": "L1C TLB2 Misses",
 		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "224",
 		"EventName": "BCD_DFP_EXECUTION_SLOTS",
 		"BriefDescription": "BCD DFP Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "225",
 		"EventName": "VX_BCD_EXECUTION_SLOTS",
 		"BriefDescription": "VX BCD Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "226",
 		"EventName": "DECIMAL_INSTRUCTIONS",
 		"BriefDescription": "Decimal Instructions",
 		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "232",
 		"EventName": "LAST_HOST_TRANSLATIONS",
 		"BriefDescription": "Last host translation done",
 		"PublicDescription": "Last Host Translation done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "243",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "244",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "245",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
 		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1D_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1D L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
 	{ "iMPH-U", "uncore_arb" },
+	{ "CPU-M-CF", "cpum_cf" },
+	{ "CPU-M-SF", "cpum_sf" },
 	{}
 };
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index dd850a26d579..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 61211918bfba..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = {
 		.check = test__intel_pt,
 		.id    = 52,
 	},
+	{
+		.name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+		.check = test__checkevent_complex_name,
+		.id    = 53
+	}
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
 		.check = test__checkevent_pmu_partial_time_callgraph,
 		.id    = 2,
 	},
+	{
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+		.check = test__checkevent_complex_name,
+		.id    = 3,
+	}
 };
 
 struct terms_test {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 94e513e62b34..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,11 +13,24 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
 trace_libc_inet_pton_backtrace() {
 
 	expected=`mktemp -u /tmp/expected.XXX`
 
-	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
 	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
@@ -26,6 +39,12 @@ trace_libc_inet_pton_backtrace() {
 		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
@@ -35,7 +54,7 @@ trace_libc_inet_pton_backtrace() {
 
 	perf_data=`mktemp -u /tmp/perf.data.XXX`
 	perf_script=`mktemp -u /tmp/perf.script.XXX`
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
 	perf script -i $perf_data > $perf_script
 
 	exec 3<$perf_script
@@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() {
 		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
 			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
-			exit 1
+			return 1
 		fi
 	done
 
@@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
 	# even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${perf_data} ${perf_script} ${expected}
-perf probe -q -d probe_libc:inet_pton
+delete_libc_inet_pton_event
 exit $err
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
-			       bool use_callchain)
+			       bool ignore_callchains)
 {
 	int ret;
 	int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (hist_entry__has_callchains(he) && use_callchain)
+	if (hist_entry__has_callchains(he) && !ignore_callchains)
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain)
+		      bool ignore_callchains)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs)
-		refcount_inc(&cs->refcnt);
-	return cs;
+	if (cs && refcount_inc_not_zero(&cs->refcnt))
+		return cs;
+
+	return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 		parent = *p;
 		iter = rb_entry(parent, struct comm_str, rb_node);
 
+		/*
+		 * If we race with comm_str__put, iter->refcnt is 0
+		 * and it will be removed within comm_str__put call
+		 * shortly, ignore it in this search.
+		 */
 		cmp = strcmp(str, iter->str);
-		if (!cmp)
-			return comm_str__get(iter);
+		if (!cmp && comm_str__get(iter))
+			return iter;
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->tail = 0;
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
-		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].exc = false;
 		decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch) {
-		ret = cs_etm__synth_branch_sample(etmq);
-		if (ret)
-			return ret;
+	if (etm->sample_branches && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
@@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 		err = cs_etm__synth_instruction_sample(
 			etmq, addr,
 			etmq->period_instructions);
+		if (err)
+			return err;
+
 		etmq->period_instructions = 0;
 
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		evsel->attr.sample_period = 1;
 	}
 
+	if (perf_evsel__is_clock(evsel)) {
+		/*
+		 * The evsel->unit points to static alias->unit
+		 * so it's ok to use static string in here.
+		 */
+		static const char *unit = "msec";
+
+		evsel->unit = unit;
+		evsel->scale = 1e-6;
+	}
+
 	return evsel;
 }
 
@@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..973c03167947 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
 
-	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-		(attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
 struct perf_attr_details {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 653ff65aa2c3..5af58aac91ad 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(NUMA_TOPOLOGY,	numa_topology,	true),
 	FEAT_OPN(BRANCH_STACK,	branch_stack,	false),
 	FEAT_OPR(PMU_MAPPINGS,	pmu_mappings,	false),
-	FEAT_OPN(GROUP_DESC,	group_desc,	false),
+	FEAT_OPR(GROUP_DESC,	group_desc,	false),
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain);
+		      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..b300a3973448 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+			  int pid, int tid)
 {
-	struct rb_node **p = &threads->entries.rb_node;
-	struct rb_node *parent = NULL;
 	struct thread *th;
 
-	/*
-	 * Front-end cache - TID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
 	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
@@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		threads->last_match = NULL;
 	}
 
+	return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
+{
+	struct thread *th = NULL;
+
+	if (perf_singlethreaded)
+		th = __threads__get_last_match(threads, machine, pid, tid);
+
+	return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	if (perf_singlethreaded)
+		__threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
+						  pid_t pid, pid_t tid,
+						  bool create)
+{
+	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	th = threads__get_last_match(threads, machine, pid, tid);
+	if (th)
+		return th;
+
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			threads->last_match = th;
+			threads__set_last_match(threads, th);
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		threads->last_match = th;
+		threads__set_last_match(threads, th);
 		++threads->nr;
 	}
 
@@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	struct threads *threads = machine__threads(machine, th->tid);
 
 	if (threads->last_match == th)
-		threads->last_match = NULL;
+		threads__set_last_match(threads, NULL);
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
@@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
+	u64 addr;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
 		return 0;
 
-	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+	/*
+	 * Convert entry->ip from a virtual address to an offset in
+	 * its corresponding binary.
+	 */
+	addr = map__map_ip(entry->map, entry->ip);
+
+	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
 				       false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}
 
@@ -490,3 +490,25 @@ out:
 	metricgroup__free_egroups(&group_list);
 	return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
+	struct pmu_event *pe;
+	int i;
+
+	if (!map)
+		return false;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_name, metric))
+			return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
 			struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 3ba6a1742f91..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
-	/* Look for cpu sysfs (specific to s390) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-		  sysfs, name);
-	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-		return 1;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-				     avg / ratio);
+				     avg / (ratio * evsel->scale));
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e->ip  = al.addr;
+	e->ip  = ip;
 	e->map = al.map;
 	e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
 	struct addr_location al;
 
 	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-	e.ip = al.addr;
+	e.ip  = ip;
 	e.map = al.map;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",