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
  ...

12 files changed, 205 insertions, 267 deletions

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;