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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Ftrace is one of the last W^X violators (after this only KLP is
     left). These patches move it over to the generic text_poke()
     interface and thereby get rid of this oddity. This requires a
     surprising amount of surgery, by Peter Zijlstra.

   - x86/AMD PMUs: add support for 'Large Increment per Cycle Events' to
     count certain types of events that have a special, quirky hw ABI
     (by Kim Phillips)

   - kprobes fixes by Masami Hiramatsu

  Lots of tooling updates as well, the following subcommands were
  updated: annotate/report/top, c2c, clang, record, report/top TUI,
  sched timehist, tests; plus updates were done to the gtk ui, libperf,
  headers and the parser"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  perf/x86/amd: Add support for Large Increment per Cycle Events
  perf/x86/amd: Constrain Large Increment per Cycle events
  perf/x86/intel/rapl: Add Comet Lake support
  tracing: Initialize ret in syscall_enter_define_fields()
  perf header: Use last modification time for timestamp
  perf c2c: Fix return type for histogram sorting comparision functions
  perf beauty sockaddr: Fix augmented syscall format warning
  perf/ui/gtk: Fix gtk2 build
  perf ui gtk: Add missing zalloc object
  perf tools: Use %define api.pure full instead of %pure-parser
  libperf: Setup initial evlist::all_cpus value
  perf report: Fix no libunwind compiled warning break s390 issue
  perf tools: Support --prefix/--prefix-strip
  perf report: Clarify in help that --children is default
  tools build: Fix test-clang.cpp with Clang 8+
  perf clang: Fix build with Clang 9
  kprobes: Fix optimize_kprobe()/unoptimize_kprobe() cancellation logic
  tools lib: Fix builds when glibc contains strlcpy()
  perf report/top: Make 'e' visible in the help and make it toggle showing callchains
  perf report/top: Do not offer annotation for symbols without samples
  ...

16 files changed, 590 insertions, 881 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index a7752cd78b89..1f22b6bbda68 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -14,6 +14,10 @@
 static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp);
 static unsigned long perf_nmi_window;
 
+/* AMD Event 0xFFF: Merge.  Used with Large Increment per Cycle events */
+#define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL)
+#define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE)
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -301,6 +305,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
 	return offset;
 }
 
+/*
+ * AMD64 events are detected based on their event codes.
+ */
+static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
+{
+	return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+}
+
+static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc)
+{
+	if (!(x86_pmu.flags & PMU_FL_PAIR))
+		return false;
+
+	switch (amd_get_event_code(hwc)) {
+	case 0x003:	return true;	/* Retired SSE/AVX FLOPs */
+	default:	return false;
+	}
+}
+
 static int amd_core_hw_config(struct perf_event *event)
 {
 	if (event->attr.exclude_host && event->attr.exclude_guest)
@@ -316,15 +339,10 @@ static int amd_core_hw_config(struct perf_event *event)
 	else if (event->attr.exclude_guest)
 		event->hw.config |= AMD64_EVENTSEL_HOSTONLY;
 
-	return 0;
-}
+	if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw))
+		event->hw.flags |= PERF_X86_EVENT_PAIR;
 
-/*
- * AMD64 events are detected based on their event codes.
- */
-static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
-{
-	return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+	return 0;
 }
 
 static inline int amd_is_nb_event(struct hw_perf_event *hwc)
@@ -855,6 +873,29 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 	}
 }
 
+static struct event_constraint pair_constraint;
+
+static struct event_constraint *
+amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
+			       struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (amd_is_pair_event_code(hwc))
+		return &pair_constraint;
+
+	return &unconstrained;
+}
+
+static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc,
+					   struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (is_counter_pair(hwc))
+		--cpuc->n_pair;
+}
+
 static ssize_t amd_event_sysfs_show(char *page, u64 config)
 {
 	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
@@ -898,33 +939,15 @@ static __initconst const struct x86_pmu amd_pmu = {
 
 static int __init amd_core_pmu_init(void)
 {
+	u64 even_ctr_mask = 0ULL;
+	int i;
+
 	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
-	/* Avoid calulating the value each time in the NMI handler */
+	/* Avoid calculating the value each time in the NMI handler */
 	perf_nmi_window = msecs_to_jiffies(100);
 
-	switch (boot_cpu_data.x86) {
-	case 0x15:
-		pr_cont("Fam15h ");
-		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
-		break;
-	case 0x17:
-		pr_cont("Fam17h ");
-		/*
-		 * In family 17h, there are no event constraints in the PMC hardware.
-		 * We fallback to using default amd_get_event_constraints.
-		 */
-		break;
-	case 0x18:
-		pr_cont("Fam18h ");
-		/* Using default amd_get_event_constraints. */
-		break;
-	default:
-		pr_err("core perfctr but no constraints; unknown hardware!\n");
-		return -ENODEV;
-	}
-
 	/*
 	 * If core performance counter extensions exists, we must use
 	 * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also
@@ -939,6 +962,32 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.amd_nb_constraints = 0;
 
+	if (boot_cpu_data.x86 == 0x15) {
+		pr_cont("Fam15h ");
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
+	}
+	if (boot_cpu_data.x86 >= 0x17) {
+		pr_cont("Fam17h+ ");
+		/*
+		 * Family 17h and compatibles have constraints for Large
+		 * Increment per Cycle events: they may only be assigned an
+		 * even numbered counter that has a consecutive adjacent odd
+		 * numbered counter following it.
+		 */
+		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+			even_ctr_mask |= 1 << i;
+
+		pair_constraint = (struct event_constraint)
+				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
+				    x86_pmu.num_counters / 2, 0,
+				    PERF_X86_EVENT_PAIR);
+
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
+		x86_pmu.put_event_constraints = amd_put_event_constraints_f17h;
+		x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE;
+		x86_pmu.flags |= PMU_FL_PAIR;
+	}
+
 	pr_cont("core perfctr, ");
 	return 0;
 }
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f118af9f0718..3bb738f5a472 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -618,6 +618,7 @@ void x86_pmu_disable_all(void)
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 		u64 val;
 
 		if (!test_bit(idx, cpuc->active_mask))
@@ -627,6 +628,8 @@ void x86_pmu_disable_all(void)
 			continue;
 		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(x86_pmu_config_addr(idx), val);
+		if (is_counter_pair(hwc))
+			wrmsrl(x86_pmu_config_addr(idx + 1), 0);
 	}
 }
 
@@ -699,7 +702,7 @@ struct sched_state {
 	int	counter;	/* counter index */
 	int	unassigned;	/* number of events to be assigned left */
 	int	nr_gp;		/* number of GP counters used */
-	unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	u64	used;
 };
 
 /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */
@@ -756,8 +759,12 @@ static bool perf_sched_restore_state(struct perf_sched *sched)
 	sched->saved_states--;
 	sched->state = sched->saved[sched->saved_states];
 
-	/* continue with next counter: */
-	clear_bit(sched->state.counter++, sched->state.used);
+	/* this assignment didn't work out */
+	/* XXX broken vs EVENT_PAIR */
+	sched->state.used &= ~BIT_ULL(sched->state.counter);
+
+	/* try the next one */
+	sched->state.counter++;
 
 	return true;
 }
@@ -782,20 +789,32 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 	if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
 		idx = INTEL_PMC_IDX_FIXED;
 		for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) {
-			if (!__test_and_set_bit(idx, sched->state.used))
-				goto done;
+			u64 mask = BIT_ULL(idx);
+
+			if (sched->state.used & mask)
+				continue;
+
+			sched->state.used |= mask;
+			goto done;
 		}
 	}
 
 	/* Grab the first unused counter starting with idx */
 	idx = sched->state.counter;
 	for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
-		if (!__test_and_set_bit(idx, sched->state.used)) {
-			if (sched->state.nr_gp++ >= sched->max_gp)
-				return false;
+		u64 mask = BIT_ULL(idx);
 
-			goto done;
-		}
+		if (c->flags & PERF_X86_EVENT_PAIR)
+			mask |= mask << 1;
+
+		if (sched->state.used & mask)
+			continue;
+
+		if (sched->state.nr_gp++ >= sched->max_gp)
+			return false;
+
+		sched->state.used |= mask;
+		goto done;
 	}
 
 	return false;
@@ -872,12 +891,10 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
 	struct event_constraint *c;
-	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	struct perf_event *e;
 	int n0, i, wmin, wmax, unsched = 0;
 	struct hw_perf_event *hwc;
-
-	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+	u64 used_mask = 0;
 
 	/*
 	 * Compute the number of events already present; see x86_pmu_add(),
@@ -920,6 +937,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 * fastpath, try to reuse previous register
 	 */
 	for (i = 0; i < n; i++) {
+		u64 mask;
+
 		hwc = &cpuc->event_list[i]->hw;
 		c = cpuc->event_constraint[i];
 
@@ -931,11 +950,16 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		if (!test_bit(hwc->idx, c->idxmsk))
 			break;
 
+		mask = BIT_ULL(hwc->idx);
+		if (is_counter_pair(hwc))
+			mask |= mask << 1;
+
 		/* not already used */
-		if (test_bit(hwc->idx, used_mask))
+		if (used_mask & mask)
 			break;
 
-		__set_bit(hwc->idx, used_mask);
+		used_mask |= mask;
+
 		if (assign)
 			assign[i] = hwc->idx;
 	}
@@ -958,6 +982,15 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		    READ_ONCE(cpuc->excl_cntrs->exclusive_present))
 			gpmax /= 2;
 
+		/*
+		 * Reduce the amount of available counters to allow fitting
+		 * the extra Merge events needed by large increment events.
+		 */
+		if (x86_pmu.flags & PMU_FL_PAIR) {
+			gpmax = x86_pmu.num_counters - cpuc->n_pair;
+			WARN_ON(gpmax <= 0);
+		}
+
 		unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
 					     wmax, gpmax, assign);
 	}
@@ -1038,6 +1071,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 			return -EINVAL;
 		cpuc->event_list[n] = leader;
 		n++;
+		if (is_counter_pair(&leader->hw))
+			cpuc->n_pair++;
 	}
 	if (!dogrp)
 		return n;
@@ -1052,6 +1087,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 		cpuc->event_list[n] = event;
 		n++;
+		if (is_counter_pair(&event->hw))
+			cpuc->n_pair++;
 	}
 	return n;
 }
@@ -1238,6 +1275,13 @@ int x86_perf_event_set_period(struct perf_event *event)
 	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
 
 	/*
+	 * Clear the Merge event counter's upper 16 bits since
+	 * we currently declare a 48-bit counter width
+	 */
+	if (is_counter_pair(hwc))
+		wrmsrl(x86_pmu_event_addr(idx + 1), 0);
+
+	/*
 	 * Due to erratum on certan cpu we need
 	 * a second write to be sure the register
 	 * is updated properly
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 5053a403e4ae..09913121e726 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -741,6 +741,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	model_hsw),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L,		model_skl),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE,		model_skl),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L,		model_skl),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE,		model_skl),
 	{},
 };
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 930611db8f9a..f1cd1ca1a77b 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -77,6 +77,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 #define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
+#define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -272,6 +273,7 @@ struct cpu_hw_events {
 	struct amd_nb			*amd_nb;
 	/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
 	u64				perf_ctr_virt_mask;
+	int				n_pair; /* Large increment events */
 
 	void				*kfree_on_online[X86_PERF_KFREE_MAX];
 };
@@ -694,6 +696,7 @@ struct x86_pmu {
 	 * AMD bits
 	 */
 	unsigned int	amd_nb_constraints : 1;
+	u64		perf_ctr_pair_en;
 
 	/*
 	 * Extra registers for events
@@ -743,6 +746,7 @@ do {									\
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
 #define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 #define PMU_FL_TFA		0x20 /* deal with TSX force abort */
+#define PMU_FL_PAIR		0x40 /* merge counters for large incr. events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -838,6 +842,11 @@ int x86_pmu_hw_config(struct perf_event *event);
 
 void x86_pmu_disable_all(void);
 
+static inline bool is_counter_pair(struct hw_perf_event *hwc)
+{
+	return hwc->flags & PERF_X86_EVENT_PAIR;
+}
+
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 					  u64 enable_mask)
 {
@@ -845,6 +854,14 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 
 	if (hwc->extra_reg.reg)
 		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
+
+	/*
+	 * Add enabled Merge event on next counter
+	 * if large increment event being enabled on this counter
+	 */
+	if (is_counter_pair(hwc))
+		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
+
 	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
@@ -861,6 +878,9 @@ static inline void x86_pmu_disable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 
 	wrmsrl(hwc->config_base, hwc->config);
+
+	if (is_counter_pair(hwc))
+		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
 }
 
 void x86_pmu_enable_event(struct perf_event *event);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index c2a7458f912c..85be2f506272 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -47,8 +47,6 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-int ftrace_int3_handler(struct pt_regs *regs);
-
 #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 5dc909d9ad81..95b1f053bd96 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -11,12 +11,11 @@
 
 #include <asm-generic/kprobes.h>
 
-#define BREAKPOINT_INSTRUCTION	0xcc
-
 #ifdef CONFIG_KPROBES
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/text-patching.h>
 #include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
@@ -25,10 +24,7 @@ struct pt_regs;
 struct kprobe;
 
 typedef u8 kprobe_opcode_t;
-#define RELATIVEJUMP_OPCODE 0xe9
-#define RELATIVEJUMP_SIZE 5
-#define RELATIVECALL_OPCODE 0xe8
-#define RELATIVE_ADDR_SIZE 4
+
 #define MAX_STACK_SIZE 64
 #define CUR_STACK_SIZE(ADDR) \
 	(current_top_of_stack() - (unsigned long)(ADDR))
@@ -43,11 +39,11 @@ extern __visible kprobe_opcode_t optprobe_template_entry[];
 extern __visible kprobe_opcode_t optprobe_template_val[];
 extern __visible kprobe_opcode_t optprobe_template_call[];
 extern __visible kprobe_opcode_t optprobe_template_end[];
-#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
+#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE)
 #define MAX_OPTINSN_SIZE 				\
 	(((unsigned long)optprobe_template_end -	\
 	  (unsigned long)optprobe_template_entry) +	\
-	 MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
+	 MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE)
 
 extern const int kretprobe_blacklist_size;
 
@@ -73,7 +69,7 @@ struct arch_specific_insn {
 
 struct arch_optimized_insn {
 	/* copy of the original instructions */
-	kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE];
+	kprobe_opcode_t copied_insn[DISP32_SIZE];
 	/* detour code buffer */
 	kprobe_opcode_t *insn;
 	/* the size of instructions copied to detour code buffer */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 2ee8e469dcf5..64c3dce374e5 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -81,8 +81,6 @@ int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 
 extern int kernel_set_to_readonly;
-void set_kernel_text_rw(void);
-void set_kernel_text_ro(void);
 
 #ifdef CONFIG_X86_64
 static inline int set_mce_nospec(unsigned long pfn)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 23c626a742e8..67315fa3956a 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -25,14 +25,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  */
 #define POKE_MAX_OPCODE_SIZE	5
 
-struct text_poke_loc {
-	void *addr;
-	int len;
-	s32 rel32;
-	u8 opcode;
-	const u8 text[POKE_MAX_OPCODE_SIZE];
-};
-
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
@@ -50,21 +42,13 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len);
  * an inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void text_poke_sync(void);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
-extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
-extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
-			       const void *opcode, size_t len, const void *emulate);
-extern int after_bootmem;
-extern __ro_after_init struct mm_struct *poking_mm;
-extern __ro_after_init unsigned long poking_addr;
 
-#ifndef CONFIG_UML_X86
-static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
-{
-	regs->ip = ip;
-}
+extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate);
+extern void text_poke_finish(void);
 
 #define INT3_INSN_SIZE		1
 #define INT3_INSN_OPCODE	0xCC
@@ -78,6 +62,67 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
 #define JMP8_INSN_SIZE		2
 #define JMP8_INSN_OPCODE	0xEB
 
+#define DISP32_SIZE		4
+
+static inline int text_opcode_size(u8 opcode)
+{
+	int size = 0;
+
+#define __CASE(insn)	\
+	case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break
+
+	switch(opcode) {
+	__CASE(INT3);
+	__CASE(CALL);
+	__CASE(JMP32);
+	__CASE(JMP8);
+	}
+
+#undef __CASE
+
+	return size;
+}
+
+union text_poke_insn {
+	u8 text[POKE_MAX_OPCODE_SIZE];
+	struct {
+		u8 opcode;
+		s32 disp;
+	} __attribute__((packed));
+};
+
+static __always_inline
+void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
+{
+	static union text_poke_insn insn; /* per instance */
+	int size = text_opcode_size(opcode);
+
+	insn.opcode = opcode;
+
+	if (size > 1) {
+		insn.disp = (long)dest - (long)(addr + size);
+		if (size == 2) {
+			/*
+			 * Ensure that for JMP9 the displacement
+			 * actually fits the signed byte.
+			 */
+			BUG_ON((insn.disp >> 31) != (insn.disp >> 7));
+		}
+	}
+
+	return &insn.text;
+}
+
+extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
+
+#ifndef CONFIG_UML_X86
+static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
+{
+	regs->ip = ip;
+}
+
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
 	/*
@@ -85,6 +130,9 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 	 * stack where the break point happened, and the saving of
 	 * pt_regs. We can extend the original stack because of
 	 * this gap. See the idtentry macro's create_gap option.
+	 *
+	 * Similarly entry_32.S will have a gap on the stack for (any) hardware
+	 * exception and pt_regs; see FIXUP_FRAME.
 	 */
 	regs->sp -= sizeof(unsigned long);
 	*(unsigned long *)regs->sp = val;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9ec463fe96f2..34360ca301a2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -936,44 +936,81 @@ static void do_sync_core(void *info)
 	sync_core();
 }
 
-static struct bp_patching_desc {
+void text_poke_sync(void)
+{
+	on_each_cpu(do_sync_core, NULL, 1);
+}
+
+struct text_poke_loc {
+	s32 rel_addr; /* addr := _stext + rel_addr */
+	s32 rel32;
+	u8 opcode;
+	const u8 text[POKE_MAX_OPCODE_SIZE];
+};
+
+struct bp_patching_desc {
 	struct text_poke_loc *vec;
 	int nr_entries;
-} bp_patching;
+	atomic_t refs;
+};
+
+static struct bp_patching_desc *bp_desc;
+
+static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+{
+	struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */
+
+	if (!desc || !atomic_inc_not_zero(&desc->refs))
+		return NULL;
+
+	return desc;
+}
+
+static inline void put_desc(struct bp_patching_desc *desc)
+{
+	smp_mb__before_atomic();
+	atomic_dec(&desc->refs);
+}
 
-static int patch_cmp(const void *key, const void *elt)
+static inline void *text_poke_addr(struct text_poke_loc *tp)
+{
+	return _stext + tp->rel_addr;
+}
+
+static int notrace patch_cmp(const void *key, const void *elt)
 {
 	struct text_poke_loc *tp = (struct text_poke_loc *) elt;
 
-	if (key < tp->addr)
+	if (key < text_poke_addr(tp))
 		return -1;
-	if (key > tp->addr)
+	if (key > text_poke_addr(tp))
 		return 1;
 	return 0;
 }
 NOKPROBE_SYMBOL(patch_cmp);
 
-int poke_int3_handler(struct pt_regs *regs)
+int notrace poke_int3_handler(struct pt_regs *regs)
 {
+	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;
+	int len, ret = 0;
 	void *ip;
 
+	if (user_mode(regs))
+		return 0;
+
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_patching.nr_entries.
+	 * bp_desc:
 	 *
-	 *	nr_entries != 0			INT3
+	 *	bp_desc = desc			INT3
 	 *	WMB				RMB
-	 *	write INT3			if (nr_entries)
-	 *
-	 * Idem for other elements in bp_patching.
+	 *	write INT3			if (desc)
 	 */
 	smp_rmb();
 
-	if (likely(!bp_patching.nr_entries))
-		return 0;
-
-	if (user_mode(regs))
+	desc = try_get_desc(&bp_desc);
+	if (!desc)
 		return 0;
 
 	/*
@@ -984,19 +1021,20 @@ int poke_int3_handler(struct pt_regs *regs)
 	/*
 	 * Skip the binary search if there is a single member in the vector.
 	 */
-	if (unlikely(bp_patching.nr_entries > 1)) {
-		tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries,
+	if (unlikely(desc->nr_entries > 1)) {
+		tp = bsearch(ip, desc->vec, desc->nr_entries,
 			     sizeof(struct text_poke_loc),
 			     patch_cmp);
 		if (!tp)
-			return 0;
+			goto out_put;
 	} else {
-		tp = bp_patching.vec;
-		if (tp->addr != ip)
-			return 0;
+		tp = desc->vec;
+		if (text_poke_addr(tp) != ip)
+			goto out_put;
 	}
 
-	ip += tp->len;
+	len = text_opcode_size(tp->opcode);
+	ip += len;
 
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
@@ -1004,7 +1042,7 @@ int poke_int3_handler(struct pt_regs *regs)
 		 * Someone poked an explicit INT3, they'll want to handle it,
 		 * do not consume.
 		 */
-		return 0;
+		goto out_put;
 
 	case CALL_INSN_OPCODE:
 		int3_emulate_call(regs, (long)ip + tp->rel32);
@@ -1019,10 +1057,18 @@ int poke_int3_handler(struct pt_regs *regs)
 		BUG();
 	}
 
-	return 1;
+	ret = 1;
+
+out_put:
+	put_desc(desc);
+	return ret;
 }
 NOKPROBE_SYMBOL(poke_int3_handler);
 
+#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
+static struct text_poke_loc tp_vec[TP_VEC_MAX];
+static int tp_vec_nr;
+
 /**
  * text_poke_bp_batch() -- update instructions on live kernel on SMP
  * @tp:			vector of instructions to patch
@@ -1044,16 +1090,20 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *		  replacing opcode
  *	- sync cores
  */
-void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
+static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
+	struct bp_patching_desc desc = {
+		.vec = tp,
+		.nr_entries = nr_entries,
+		.refs = ATOMIC_INIT(1),
+	};
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
-	bp_patching.vec = tp;
-	bp_patching.nr_entries = nr_entries;
+	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
 
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
@@ -1065,18 +1115,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
 	for (i = 0; i < nr_entries; i++)
-		text_poke(tp[i].addr, &int3, sizeof(int3));
+		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
 
-	on_each_cpu(do_sync_core, NULL, 1);
+	text_poke_sync();
 
 	/*
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		if (tp[i].len - sizeof(int3) > 0) {
-			text_poke((char *)tp[i].addr + sizeof(int3),
-				  (const char *)tp[i].text + sizeof(int3),
-				  tp[i].len - sizeof(int3));
+		int len = text_opcode_size(tp[i].opcode);
+
+		if (len - INT3_INSN_SIZE > 0) {
+			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+				  (const char *)tp[i].text + INT3_INSN_SIZE,
+				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
 	}
@@ -1087,7 +1139,7 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 		 * not necessary and we'd be safe even without it. But
 		 * better safe than sorry (plus there's not only Intel).
 		 */
-		on_each_cpu(do_sync_core, NULL, 1);
+		text_poke_sync();
 	}
 
 	/*
@@ -1098,19 +1150,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 		if (tp[i].text[0] == INT3_INSN_OPCODE)
 			continue;
 
-		text_poke(tp[i].addr, tp[i].text, sizeof(int3));
+		text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE);
 		do_sync++;
 	}
 
 	if (do_sync)
-		on_each_cpu(do_sync_core, NULL, 1);
+		text_poke_sync();
 
 	/*
-	 * sync_core() implies an smp_mb() and orders this store against
-	 * the writing of the new instruction.
+	 * Remove and synchronize_rcu(), except we have a very primitive
+	 * refcount based completion.
 	 */
-	bp_patching.vec = NULL;
-	bp_patching.nr_entries = 0;
+	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
+	if (!atomic_dec_and_test(&desc.refs))
+		atomic_cond_read_acquire(&desc.refs, !VAL);
 }
 
 void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
@@ -1118,11 +1171,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 {
 	struct insn insn;
 
-	if (!opcode)
-		opcode = (void *)tp->text;
-	else
-		memcpy((void *)tp->text, opcode, len);
-
+	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
@@ -1132,8 +1181,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	BUG_ON(!insn_complete(&insn));
 	BUG_ON(len != insn.length);
 
-	tp->addr = addr;
-	tp->len = len;
+	tp->rel_addr = addr - (void *)_stext;
 	tp->opcode = insn.opcode.bytes[0];
 
 	switch (tp->opcode) {
@@ -1167,6 +1215,55 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	}
 }
 
+/*
+ * We hard rely on the tp_vec being ordered; ensure this is so by flushing
+ * early if needed.
+ */
+static bool tp_order_fail(void *addr)
+{
+	struct text_poke_loc *tp;
+
+	if (!tp_vec_nr)
+		return false;
+
+	if (!addr) /* force */
+		return true;
+
+	tp = &tp_vec[tp_vec_nr - 1];
+	if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr)
+		return true;
+
+	return false;
+}
+
+static void text_poke_flush(void *addr)
+{
+	if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) {
+		text_poke_bp_batch(tp_vec, tp_vec_nr);
+		tp_vec_nr = 0;
+	}
+}
+
+void text_poke_finish(void)
+{
+	text_poke_flush(NULL);
+}
+
+void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
+{
+	struct text_poke_loc *tp;
+
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
+	text_poke_flush(addr);
+
+	tp = &tp_vec[tp_vec_nr++];
+	text_poke_loc_init(tp, addr, opcode, len, emulate);
+}
+
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
  * @addr:	address to patch
@@ -1178,10 +1275,15 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
  * dynamically allocated memory. This function should be used when it is
  * not possible to allocate memory.
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
+void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
 	struct text_poke_loc tp;
 
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
 	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2009047bb015..37a0aeaf89e7 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -35,6 +35,8 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+static int ftrace_poke_late = 0;
+
 int ftrace_arch_code_modify_prepare(void)
     __acquires(&text_mutex)
 {
@@ -44,84 +46,37 @@ int ftrace_arch_code_modify_prepare(void)
 	 * ftrace has it set to "read/write".
 	 */
 	mutex_lock(&text_mutex);
-	set_kernel_text_rw();
-	set_all_modules_text_rw();
+	ftrace_poke_late = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
     __releases(&text_mutex)
 {
-	set_all_modules_text_ro();
-	set_kernel_text_ro();
+	/*
+	 * ftrace_make_{call,nop}() may be called during
+	 * module load, and we need to finish the text_poke_queue()
+	 * that they do, here.
+	 */
+	text_poke_finish();
+	ftrace_poke_late = 0;
 	mutex_unlock(&text_mutex);
 	return 0;
 }
 
-union ftrace_code_union {
-	char code[MCOUNT_INSN_SIZE];
-	struct {
-		unsigned char op;
-		int offset;
-	} __attribute__((packed));
-};
-
-static int ftrace_calc_offset(long ip, long addr)
-{
-	return (int)(addr - ip);
-}
-
-static unsigned char *
-ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr)
+static const char *ftrace_nop_replace(void)
 {
-	static union ftrace_code_union calc;
-
-	calc.op		= op;
-	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
-
-	return calc.code;
-}
-
-static unsigned char *
-ftrace_call_replace(unsigned long ip, unsigned long addr)
-{
-	return ftrace_text_replace(0xe8, ip, addr);
-}
-
-static inline int
-within(unsigned long addr, unsigned long start, unsigned long end)
-{
-	return addr >= start && addr < end;
+	return ideal_nops[NOP_ATOMIC5];
 }
 
-static unsigned long text_ip_addr(unsigned long ip)
+static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
-	/*
-	 * On x86_64, kernel text mappings are mapped read-only, so we use
-	 * the kernel identity mapping instead of the kernel text mapping
-	 * to modify the kernel text.
-	 *
-	 * For 32bit kernels, these mappings are same and we can use
-	 * kernel identity mapping to modify code.
-	 */
-	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
-		ip = (unsigned long)__va(__pa_symbol(ip));
-
-	return ip;
+	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
 }
 
-static const unsigned char *ftrace_nop_replace(void)
+static int ftrace_verify_code(unsigned long ip, const char *old_code)
 {
-	return ideal_nops[NOP_ATOMIC5];
-}
-
-static int
-ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code)
-{
-	unsigned char replaced[MCOUNT_INSN_SIZE];
-
-	ftrace_expected = old_code;
+	char cur_code[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note:
@@ -130,31 +85,46 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 	 * Carefully read and modify the code with probe_kernel_*(), and make
 	 * sure what we read is what we expected it to be before modifying it.
 	 */
-
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
+		WARN_ON(1);
 		return -EFAULT;
+	}
 
 	/* Make sure it is what we expect it to be */
-	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+	if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) {
+		WARN_ON(1);
 		return -EINVAL;
+	}
 
-	ip = text_ip_addr(ip);
-
-	/* replace the text with the new text */
-	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
-		return -EPERM;
+	return 0;
+}
 
-	sync_core();
+/*
+ * Marked __ref because it calls text_poke_early() which is .init.text. That is
+ * ok because that call will happen early, during boot, when .init sections are
+ * still present.
+ */
+static int __ref
+ftrace_modify_code_direct(unsigned long ip, const char *old_code,
+			  const char *new_code)
+{
+	int ret = ftrace_verify_code(ip, old_code);
+	if (ret)
+		return ret;
 
+	/* replace the text with the new text */
+	if (ftrace_poke_late)
+		text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
+	else
+		text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
-int ftrace_make_nop(struct module *mod,
-		    struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
+	const char *new, *old;
 
 	old = ftrace_call_replace(ip, addr);
 	new = ftrace_nop_replace();
@@ -168,19 +138,20 @@ int ftrace_make_nop(struct module *mod,
 	 * just modify the code directly.
 	 */
 	if (addr == MCOUNT_ADDR)
-		return ftrace_modify_code_direct(rec->ip, old, new);
+		return ftrace_modify_code_direct(ip, old, new);
 
-	ftrace_expected = NULL;
-
-	/* Normal cases use add_brk_on_nop */
+	/*
+	 * x86 overrides ftrace_replace_code -- this function will never be used
+	 * in this case.
+	 */
 	WARN_ONCE(1, "invalid use of ftrace_make_nop");
 	return -EINVAL;
 }
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
+	const char *new, *old;
 
 	old = ftrace_nop_replace();
 	new = ftrace_call_replace(ip, addr);
@@ -190,43 +161,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 }
 
 /*
- * The modifying_ftrace_code is used to tell the breakpoint
- * handler to call ftrace_int3_handler(). If it fails to
- * call this handler for a breakpoint added by ftrace, then
- * the kernel may crash.
- *
- * As atomic_writes on x86 do not need a barrier, we do not
- * need to add smp_mb()s for this to work. It is also considered
- * that we can not read the modifying_ftrace_code before
- * executing the breakpoint. That would be quite remarkable if
- * it could do that. Here's the flow that is required:
- *
- *   CPU-0                          CPU-1
- *
- * atomic_inc(mfc);
- * write int3s
- *				<trap-int3> // implicit (r)mb
- *				if (atomic_read(mfc))
- *					call ftrace_int3_handler()
- *
- * Then when we are finished:
- *
- * atomic_dec(mfc);
- *
- * If we hit a breakpoint that was not set by ftrace, it does not
- * matter if ftrace_int3_handler() is called or not. It will
- * simply be ignored. But it is crucial that a ftrace nop/caller
- * breakpoint is handled. No other user should ever place a
- * breakpoint on an ftrace nop/caller location. It must only
- * be done by this code.
- */
-atomic_t modifying_ftrace_code __read_mostly;
-
-static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code);
-
-/*
  * Should never be called:
  *  As it is only called by __ftrace_replace_code() which is called by
  *  ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
@@ -238,452 +172,84 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 				 unsigned long addr)
 {
 	WARN_ON(1);
-	ftrace_expected = NULL;
 	return -EINVAL;
 }
 
-static unsigned long ftrace_update_func;
-static unsigned long ftrace_update_func_call;
-
-static int update_ftrace_func(unsigned long ip, void *new)
-{
-	unsigned char old[MCOUNT_INSN_SIZE];
-	int ret;
-
-	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
-
-	ftrace_update_func = ip;
-	/* Make sure the breakpoints see the ftrace_update_func update */
-	smp_wmb();
-
-	/* See comment above by declaration of modifying_ftrace_code */
-	atomic_inc(&modifying_ftrace_code);
-
-	ret = ftrace_modify_code(ip, old, new);
-
-	atomic_dec(&modifying_ftrace_code);
-
-	return ret;
-}
-
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char *new;
-	int ret;
-
-	ftrace_update_func_call = (unsigned long)func;
-
-	new = ftrace_call_replace(ip, (unsigned long)func);
-	ret = update_ftrace_func(ip, new);
-
-	/* Also update the regs callback function */
-	if (!ret) {
-		ip = (unsigned long)(&ftrace_regs_call);
-		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = update_ftrace_func(ip, new);
-	}
-
-	return ret;
-}
-
-static nokprobe_inline int is_ftrace_caller(unsigned long ip)
-{
-	if (ip == ftrace_update_func)
-		return 1;
-
-	return 0;
-}
-
-/*
- * A breakpoint was added to the code address we are about to
- * modify, and this is the handle that will just skip over it.
- * We are either changing a nop into a trace call, or a trace
- * call to a nop. While the change is taking place, we treat
- * it just like it was a nop.
- */
-int ftrace_int3_handler(struct pt_regs *regs)
-{
 	unsigned long ip;
+	const char *new;
 
-	if (WARN_ON_ONCE(!regs))
-		return 0;
-
-	ip = regs->ip - INT3_INSN_SIZE;
-
-	if (ftrace_location(ip)) {
-		int3_emulate_call(regs, (unsigned long)ftrace_regs_caller);
-		return 1;
-	} else if (is_ftrace_caller(ip)) {
-		if (!ftrace_update_func_call) {
-			int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
-			return 1;
-		}
-		int3_emulate_call(regs, ftrace_update_func_call);
-		return 1;
-	}
-
-	return 0;
-}
-NOKPROBE_SYMBOL(ftrace_int3_handler);
-
-static int ftrace_write(unsigned long ip, const char *val, int size)
-{
-	ip = text_ip_addr(ip);
-
-	if (probe_kernel_write((void *)ip, val, size))
-		return -EPERM;
-
-	return 0;
-}
-
-static int add_break(unsigned long ip, const char *old)
-{
-	unsigned char replaced[MCOUNT_INSN_SIZE];
-	unsigned char brk = BREAKPOINT_INSTRUCTION;
-
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	ftrace_expected = old;
-
-	/* Make sure it is what we expect it to be */
-	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
-		return -EINVAL;
-
-	return ftrace_write(ip, &brk, 1);
-}
-
-static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned const char *old;
-	unsigned long ip = rec->ip;
-
-	old = ftrace_call_replace(ip, addr);
-
-	return add_break(rec->ip, old);
-}
-
-
-static int add_brk_on_nop(struct dyn_ftrace *rec)
-{
-	unsigned const char *old;
-
-	old = ftrace_nop_replace();
-
-	return add_break(rec->ip, old);
-}
-
-static int add_breakpoints(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ftrace_addr = ftrace_get_addr_curr(rec);
-
-	ret = ftrace_test_record(rec, enable);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return add_brk_on_nop(rec);
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return add_brk_on_call(rec, ftrace_addr);
-	}
-	return 0;
-}
-
-/*
- * On error, we need to remove breakpoints. This needs to
- * be done caefully. If the address does not currently have a
- * breakpoint, we know we are done. Otherwise, we look at the
- * remaining 4 bytes of the instruction. If it matches a nop
- * we replace the breakpoint with the nop. Otherwise we replace
- * it with the call instruction.
- */
-static int remove_breakpoint(struct dyn_ftrace *rec)
-{
-	unsigned char ins[MCOUNT_INSN_SIZE];
-	unsigned char brk = BREAKPOINT_INSTRUCTION;
-	const unsigned char *nop;
-	unsigned long ftrace_addr;
-	unsigned long ip = rec->ip;
-
-	/* If we fail the read, just give up */
-	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	/* If this does not have a breakpoint, we are done */
-	if (ins[0] != brk)
-		return 0;
-
-	nop = ftrace_nop_replace();
-
-	/*
-	 * If the last 4 bytes of the instruction do not match
-	 * a nop, then we assume that this is a call to ftrace_addr.
-	 */
-	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
-		/*
-		 * For extra paranoidism, we check if the breakpoint is on
-		 * a call that would actually jump to the ftrace_addr.
-		 * If not, don't touch the breakpoint, we make just create
-		 * a disaster.
-		 */
-		ftrace_addr = ftrace_get_addr_new(rec);
-		nop = ftrace_call_replace(ip, ftrace_addr);
-
-		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
-			goto update;
-
-		/* Check both ftrace_addr and ftrace_old_addr */
-		ftrace_addr = ftrace_get_addr_curr(rec);
-		nop = ftrace_call_replace(ip, ftrace_addr);
-
-		ftrace_expected = nop;
-
-		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
-			return -EINVAL;
-	}
-
- update:
-	return ftrace_write(ip, nop, 1);
-}
-
-static int add_update_code(unsigned long ip, unsigned const char *new)
-{
-	/* skip breakpoint */
-	ip++;
-	new++;
-	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
-}
-
-static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_call_replace(ip, addr);
-	return add_update_code(ip, new);
-}
-
-static int add_update_nop(struct dyn_ftrace *rec)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_nop_replace();
-	return add_update_code(ip, new);
-}
-
-static int add_update(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ret = ftrace_test_record(rec, enable);
-
-	ftrace_addr  = ftrace_get_addr_new(rec);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return add_update_call(rec, ftrace_addr);
-
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return add_update_nop(rec);
-	}
-
-	return 0;
-}
-
-static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_call_replace(ip, addr);
-
-	return ftrace_write(ip, new, 1);
-}
-
-static int finish_update_nop(struct dyn_ftrace *rec)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_nop_replace();
-
-	return ftrace_write(ip, new, 1);
-}
-
-static int finish_update(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ret = ftrace_update_record(rec, enable);
-
-	ftrace_addr = ftrace_get_addr_new(rec);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return finish_update_call(rec, ftrace_addr);
+	ip = (unsigned long)(&ftrace_call);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return finish_update_nop(rec);
-	}
+	ip = (unsigned long)(&ftrace_regs_call);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 
 	return 0;
 }
 
-static void do_sync_core(void *data)
-{
-	sync_core();
-}
-
-static void run_sync(void)
-{
-	int enable_irqs;
-
-	/* No need to sync if there's only one CPU */
-	if (num_online_cpus() == 1)
-		return;
-
-	enable_irqs = irqs_disabled();
-
-	/* We may be called with interrupts disabled (on bootup). */
-	if (enable_irqs)
-		local_irq_enable();
-	on_each_cpu(do_sync_core, NULL, 1);
-	if (enable_irqs)
-		local_irq_disable();
-}
-
 void ftrace_replace_code(int enable)
 {
 	struct ftrace_rec_iter *iter;
 	struct dyn_ftrace *rec;
-	const char *report = "adding breakpoints";
-	int count = 0;
+	const char *new, *old;
 	int ret;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 
-		ret = add_breakpoints(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
-	}
-
-	run_sync();
+		switch (ftrace_test_record(rec, enable)) {
+		case FTRACE_UPDATE_IGNORE:
+		default:
+			continue;
 
-	report = "updating code";
-	count = 0;
+		case FTRACE_UPDATE_MAKE_CALL:
+			old = ftrace_nop_replace();
+			break;
 
-	for_ftrace_rec_iter(iter) {
-		rec = ftrace_rec_iter_record(iter);
+		case FTRACE_UPDATE_MODIFY_CALL:
+		case FTRACE_UPDATE_MAKE_NOP:
+			old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec));
+			break;
+		}
 
-		ret = add_update(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
+		ret = ftrace_verify_code(rec->ip, old);
+		if (ret) {
+			ftrace_bug(ret, rec);
+			return;
+		}
 	}
 
-	run_sync();
-
-	report = "removing breakpoints";
-	count = 0;
-
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 
-		ret = finish_update(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
-	}
+		switch (ftrace_test_record(rec, enable)) {
+		case FTRACE_UPDATE_IGNORE:
+		default:
+			continue;
 
-	run_sync();
+		case FTRACE_UPDATE_MAKE_CALL:
+		case FTRACE_UPDATE_MODIFY_CALL:
+			new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec));
+			break;
 
-	return;
+		case FTRACE_UPDATE_MAKE_NOP:
+			new = ftrace_nop_replace();
+			break;
+		}
 
- remove_breakpoints:
-	pr_warn("Failed on %s (%d):\n", report, count);
-	ftrace_bug(ret, rec);
-	for_ftrace_rec_iter(iter) {
-		rec = ftrace_rec_iter_record(iter);
-		/*
-		 * Breakpoints are handled only when this function is in
-		 * progress. The system could not work with them.
-		 */
-		if (remove_breakpoint(rec))
-			BUG();
+		text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
+		ftrace_update_record(rec, enable);
 	}
-	run_sync();
-}
-
-static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code)
-{
-	int ret;
-
-	ret = add_break(ip, old_code);
-	if (ret)
-		goto out;
-
-	run_sync();
-
-	ret = add_update_code(ip, new_code);
-	if (ret)
-		goto fail_update;
-
-	run_sync();
-
-	ret = ftrace_write(ip, new_code, 1);
-	/*
-	 * The breakpoint is handled only when this function is in progress.
-	 * The system could not work if we could not remove it.
-	 */
-	BUG_ON(ret);
- out:
-	run_sync();
-	return ret;
-
- fail_update:
-	/* Also here the system could not work with the breakpoint */
-	if (ftrace_write(ip, old_code, 1))
-		BUG();
-	goto out;
+	text_poke_finish();
 }
 
 void arch_ftrace_update_code(int command)
 {
-	/* See comment above by declaration of modifying_ftrace_code */
-	atomic_inc(&modifying_ftrace_code);
-
 	ftrace_modify_all_code(command);
-
-	atomic_dec(&modifying_ftrace_code);
 }
 
 int __init ftrace_dyn_arch_init(void)
@@ -748,6 +314,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long start_offset;
 	unsigned long end_offset;
 	unsigned long op_offset;
+	unsigned long call_offset;
 	unsigned long offset;
 	unsigned long npages;
 	unsigned long size;
@@ -764,10 +331,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		start_offset = (unsigned long)ftrace_regs_caller;
 		end_offset = (unsigned long)ftrace_regs_caller_end;
 		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
+		call_offset = (unsigned long)ftrace_regs_call;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
 		end_offset = (unsigned long)ftrace_epilogue;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
+		call_offset = (unsigned long)ftrace_call;
 	}
 
 	size = end_offset - start_offset;
@@ -824,16 +393,21 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* put in the new offset to the ftrace_ops */
 	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
 
+	/* put in the call to the function */
+	mutex_lock(&text_mutex);
+	call_offset -= start_offset;
+	memcpy(trampoline + call_offset,
+	       text_gen_insn(CALL_INSN_OPCODE,
+			     trampoline + call_offset,
+			     ftrace_ops_get_func(ops)), CALL_INSN_SIZE);
+	mutex_unlock(&text_mutex);
+
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
 	set_vm_flush_reset_perms(trampoline);
 
-	/*
-	 * Module allocation needs to be completed by making the page
-	 * executable. The page is still writable, which is a security hazard,
-	 * but anyhow ftrace breaks W^X completely.
-	 */
+	set_memory_ro((unsigned long)trampoline, npages);
 	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
@@ -860,62 +434,54 @@ static unsigned long calc_trampoline_call_offset(bool save_regs)
 void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 {
 	ftrace_func_t func;
-	unsigned char *new;
 	unsigned long offset;
 	unsigned long ip;
 	unsigned int size;
-	int ret, npages;
+	const char *new;
 
-	if (ops->trampoline) {
-		/*
-		 * The ftrace_ops caller may set up its own trampoline.
-		 * In such a case, this code must not modify it.
-		 */
-		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
-			return;
-		npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT;
-		set_memory_rw(ops->trampoline, npages);
-	} else {
+	if (!ops->trampoline) {
 		ops->trampoline = create_trampoline(ops, &size);
 		if (!ops->trampoline)
 			return;
 		ops->trampoline_size = size;
-		npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+		return;
 	}
 
+	/*
+	 * The ftrace_ops caller may set up its own trampoline.
+	 * In such a case, this code must not modify it.
+	 */
+	if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+		return;
+
 	offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
 	ip = ops->trampoline + offset;
-
 	func = ftrace_ops_get_func(ops);
 
-	ftrace_update_func_call = (unsigned long)func;
-
+	mutex_lock(&text_mutex);
 	/* Do a safe modify in case the trampoline is executing */
 	new = ftrace_call_replace(ip, (unsigned long)func);
-	ret = update_ftrace_func(ip, new);
-	set_memory_ro(ops->trampoline, npages);
-
-	/* The update should never fail */
-	WARN_ON(ret);
+	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	mutex_unlock(&text_mutex);
 }
 
 /* Return the address of the function the trampoline calls */
 static void *addr_from_call(void *ptr)
 {
-	union ftrace_code_union calc;
+	union text_poke_insn call;
 	int ret;
 
-	ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE);
+	ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE);
 	if (WARN_ON_ONCE(ret < 0))
 		return NULL;
 
 	/* Make sure this is a call */
-	if (WARN_ON_ONCE(calc.op != 0xe8)) {
-		pr_warn("Expected e8, got %x\n", calc.op);
+	if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) {
+		pr_warn("Expected E8, got %x\n", call.opcode);
 		return NULL;
 	}
 
-	return ptr + MCOUNT_INSN_SIZE + calc.offset;
+	return ptr + CALL_INSN_SIZE + call.disp;
 }
 
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
@@ -982,19 +548,18 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
-static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
+static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
-	return ftrace_text_replace(0xe9, ip, addr);
+	return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
 }
 
 static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
-	unsigned char *new;
+	const char *new;
 
-	ftrace_update_func_call = 0UL;
 	new = ftrace_jmp_replace(ip, (unsigned long)func);
-
-	return update_ftrace_func(ip, new);
+	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	return 0;
 }
 
 int ftrace_enable_ftrace_graph_caller(void)
@@ -1020,10 +585,9 @@ int ftrace_disable_ftrace_graph_caller(void)
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
 	unsigned long old;
 	int faulted;
-	unsigned long return_hooker = (unsigned long)
-				&return_to_handler;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index c1a8b9e71408..9c4498ea0b3c 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -16,15 +16,7 @@
 #include <asm/alternative.h>
 #include <asm/text-patching.h>
 
-union jump_code_union {
-	char code[JUMP_LABEL_NOP_SIZE];
-	struct {
-		char jump;
-		int offset;
-	} __attribute__((packed));
-};
-
-static void bug_at(unsigned char *ip, int line)
+static void bug_at(const void *ip, int line)
 {
 	/*
 	 * The location is not an op that we were expecting.
@@ -35,42 +27,42 @@ static void bug_at(unsigned char *ip, int line)
 	BUG();
 }
 
-static void __jump_label_set_jump_code(struct jump_entry *entry,
-				       enum jump_label_type type,
-				       union jump_code_union *code,
-				       int init)
+static const void *
+__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init)
 {
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
-	const void *expect;
+	const void *expect, *code;
+	const void *addr, *dest;
 	int line;
 
-	code->jump = 0xe9;
-	code->offset = jump_entry_target(entry) -
-		       (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+	addr = (void *)jump_entry_code(entry);
+	dest = (void *)jump_entry_target(entry);
+
+	code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest);
 
 	if (init) {
 		expect = default_nop; line = __LINE__;
 	} else if (type == JUMP_LABEL_JMP) {
 		expect = ideal_nop; line = __LINE__;
 	} else {
-		expect = code->code; line = __LINE__;
+		expect = code; line = __LINE__;
 	}
 
-	if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE))
-		bug_at((void *)jump_entry_code(entry), line);
+	if (memcmp(addr, expect, JUMP_LABEL_NOP_SIZE))
+		bug_at(addr, line);
 
 	if (type == JUMP_LABEL_NOP)
-		memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE);
+		code = ideal_nop;
+
+	return code;
 }
 
-static void __ref __jump_label_transform(struct jump_entry *entry,
-					 enum jump_label_type type,
-					 int init)
+static void inline __jump_label_transform(struct jump_entry *entry,
+					  enum jump_label_type type,
+					  int init)
 {
-	union jump_code_union code;
-
-	__jump_label_set_jump_code(entry, type, &code, init);
+	const void *opcode = __jump_label_set_jump_code(entry, type, init);
 
 	/*
 	 * As long as only a single processor is running and the code is still
@@ -84,31 +76,33 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	 * always nop being the 'currently valid' instruction
 	 */
 	if (init || system_state == SYSTEM_BOOTING) {
-		text_poke_early((void *)jump_entry_code(entry), &code,
+		text_poke_early((void *)jump_entry_code(entry), opcode,
 				JUMP_LABEL_NOP_SIZE);
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL);
+	text_poke_bp((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE, NULL);
 }
 
-void arch_jump_label_transform(struct jump_entry *entry,
-			       enum jump_label_type type)
+static void __ref jump_label_transform(struct jump_entry *entry,
+				       enum jump_label_type type,
+				       int init)
 {
 	mutex_lock(&text_mutex);
-	__jump_label_transform(entry, type, 0);
+	__jump_label_transform(entry, type, init);
 	mutex_unlock(&text_mutex);
 }
 
-#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
-static struct text_poke_loc tp_vec[TP_VEC_MAX];
-static int tp_vec_nr;
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	jump_label_transform(entry, type, 0);
+}
 
 bool arch_jump_label_transform_queue(struct jump_entry *entry,
 				     enum jump_label_type type)
 {
-	struct text_poke_loc *tp;
-	void *entry_code;
+	const void *opcode;
 
 	if (system_state == SYSTEM_BOOTING) {
 		/*
@@ -118,53 +112,19 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 		return true;
 	}
 
-	/*
-	 * No more space in the vector, tell upper layer to apply
-	 * the queue before continuing.
-	 */
-	if (tp_vec_nr == TP_VEC_MAX)
-		return false;
-
-	tp = &tp_vec[tp_vec_nr];
-
-	entry_code = (void *)jump_entry_code(entry);
-
-	/*
-	 * The INT3 handler will do a bsearch in the queue, so we need entries
-	 * to be sorted. We can survive an unsorted list by rejecting the entry,
-	 * forcing the generic jump_label code to apply the queue. Warning once,
-	 * to raise the attention to the case of an unsorted entry that is
-	 * better not happen, because, in the worst case we will perform in the
-	 * same way as we do without batching - with some more overhead.
-	 */
-	if (tp_vec_nr > 0) {
-		int prev = tp_vec_nr - 1;
-		struct text_poke_loc *prev_tp = &tp_vec[prev];
-
-		if (WARN_ON_ONCE(prev_tp->addr > entry_code))
-			return false;
-	}
-
-	__jump_label_set_jump_code(entry, type,
-				   (union jump_code_union *)&tp->text, 0);
-
-	text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
-
-	tp_vec_nr++;
-
+	mutex_lock(&text_mutex);
+	opcode = __jump_label_set_jump_code(entry, type, 0);
+	text_poke_queue((void *)jump_entry_code(entry),
+			opcode, JUMP_LABEL_NOP_SIZE, NULL);
+	mutex_unlock(&text_mutex);
 	return true;
 }
 
 void arch_jump_label_transform_apply(void)
 {
-	if (!tp_vec_nr)
-		return;
-
 	mutex_lock(&text_mutex);
-	text_poke_bp_batch(tp_vec, tp_vec_nr);
+	text_poke_finish();
 	mutex_unlock(&text_mutex);
-
-	tp_vec_nr = 0;
 }
 
 static enum {
@@ -193,5 +153,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 			jlstate = JL_STATE_NO_UPDATE;
 	}
 	if (jlstate == JL_STATE_UPDATE)
-		__jump_label_transform(entry, type, 1);
+		jump_label_transform(entry, type, 1);
 }
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a0c223ab7264..4d7022a740ab 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -120,14 +120,14 @@ __synthesize_relative_insn(void *dest, void *from, void *to, u8 op)
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
 void synthesize_reljump(void *dest, void *from, void *to)
 {
-	__synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE);
+	__synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE);
 }
 NOKPROBE_SYMBOL(synthesize_reljump);
 
 /* Insert a call instruction at address 'from', which calls address 'to'.*/
 void synthesize_relcall(void *dest, void *from, void *to)
 {
-	__synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE);
+	__synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE);
 }
 NOKPROBE_SYMBOL(synthesize_relcall);
 
@@ -302,7 +302,7 @@ static int can_probe(unsigned long paddr)
 		 * Another debugging subsystem might insert this breakpoint.
 		 * In that case, we can't recover it.
 		 */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
 			return 0;
 		addr += insn.length;
 	}
@@ -357,7 +357,7 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 		return 0;
 
 	/* Another subsystem puts a breakpoint, failed to recover */
-	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+	if (insn->opcode.bytes[0] == INT3_INSN_OPCODE)
 		return 0;
 
 	/* We should not singlestep on the exception masking instructions */
@@ -401,14 +401,14 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p,
 	int len = insn->length;
 
 	if (can_boost(insn, p->addr) &&
-	    MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) {
+	    MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) {
 		/*
 		 * These instructions can be executed directly if it
 		 * jumps back to correct address.
 		 */
 		synthesize_reljump(buf + len, p->ainsn.insn + len,
 				   p->addr + insn->length);
-		len += RELATIVEJUMP_SIZE;
+		len += JMP32_INSN_SIZE;
 		p->ainsn.boostable = true;
 	} else {
 		p->ainsn.boostable = false;
@@ -502,12 +502,14 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
+	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	text_poke_sync();
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
 	text_poke(p->addr, &p->opcode, 1);
+	text_poke_sync();
 }
 
 void arch_remove_kprobe(struct kprobe *p)
@@ -610,7 +612,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 	regs->flags |= X86_EFLAGS_TF;
 	regs->flags &= ~X86_EFLAGS_IF;
 	/* single step inline if the instruction is an int3 */
-	if (p->opcode == BREAKPOINT_INSTRUCTION)
+	if (p->opcode == INT3_INSN_OPCODE)
 		regs->ip = (unsigned long)p->addr;
 	else
 		regs->ip = (unsigned long)p->ainsn.insn;
@@ -696,7 +698,7 @@ int kprobe_int3_handler(struct pt_regs *regs)
 				reset_current_kprobe();
 			return 1;
 		}
-	} else if (*addr != BREAKPOINT_INSTRUCTION) {
+	} else if (*addr != INT3_INSN_OPCODE) {
 		/*
 		 * The breakpoint instruction was removed right
 		 * after we hit it.  Another cpu has removed
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 8900329c28a7..3f45b5c43a71 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -38,7 +38,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	long offs;
 	int i;
 
-	for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
+	for (i = 0; i < JMP32_INSN_SIZE; i++) {
 		kp = get_kprobe((void *)addr - i);
 		/* This function only handles jump-optimized kprobe */
 		if (kp && kprobe_optimized(kp)) {
@@ -62,10 +62,10 @@ found:
 
 	if (addr == (unsigned long)kp->addr) {
 		buf[0] = kp->opcode;
-		memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+		memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE);
 	} else {
 		offs = addr - (unsigned long)kp->addr - 1;
-		memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
+		memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs);
 	}
 
 	return (unsigned long)buf;
@@ -141,8 +141,6 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func);
 #define TMPL_END_IDX \
 	((long)optprobe_template_end - (long)optprobe_template_entry)
 
-#define INT3_SIZE sizeof(kprobe_opcode_t)
-
 /* Optimized kprobe call back function: called from optinsn */
 static void
 optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
@@ -162,7 +160,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 		regs->cs |= get_kernel_rpl();
 		regs->gs = 0;
 #endif
-		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
+		regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE;
 		regs->orig_ax = ~0UL;
 
 		__this_cpu_write(current_kprobe, &op->kp);
@@ -179,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
 	struct insn insn;
 	int len = 0, ret;
 
-	while (len < RELATIVEJUMP_SIZE) {
+	while (len < JMP32_INSN_SIZE) {
 		ret = __copy_instruction(dest + len, src + len, real + len, &insn);
 		if (!ret || !can_boost(&insn, src + len))
 			return -EINVAL;
@@ -271,7 +269,7 @@ static int can_optimize(unsigned long paddr)
 		return 0;
 
 	/* Check there is enough space for a relative jump. */
-	if (size - offset < RELATIVEJUMP_SIZE)
+	if (size - offset < JMP32_INSN_SIZE)
 		return 0;
 
 	/* Decode instructions */
@@ -290,15 +288,15 @@ static int can_optimize(unsigned long paddr)
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */
-		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
 			return 0;
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
 		/* Check any instructions don't jump into target */
 		if (insn_is_indirect_jump(&insn) ||
-		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
-					 RELATIVE_ADDR_SIZE))
+		    insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE,
+					 DISP32_SIZE))
 			return 0;
 		addr += insn.length;
 	}
@@ -374,7 +372,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	 * Verify if the address gap is in 2GB range, because this uses
 	 * a relative jump.
 	 */
-	rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE;
+	rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE;
 	if (abs(rel) > 0x7fffffff) {
 		ret = -ERANGE;
 		goto err;
@@ -401,7 +399,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	/* Set returning jmp instruction at the tail of out-of-line buffer */
 	synthesize_reljump(buf + len, slot + len,
 			   (u8 *)op->kp.addr + op->optinsn.size);
-	len += RELATIVEJUMP_SIZE;
+	len += JMP32_INSN_SIZE;
 
 	/* We have to use text_poke() for instruction buffer because it is RO */
 	text_poke(slot, buf, len);
@@ -416,49 +414,50 @@ err:
 }
 
 /*
- * Replace breakpoints (int3) with relative jumps.
+ * Replace breakpoints (INT3) with relative jumps (JMP.d32).
  * Caller must call with locking kprobe_mutex and text_mutex.
+ *
+ * The caller will have installed a regular kprobe and after that issued
+ * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in
+ * the 4 bytes after the INT3 are unused and can now be overwritten.
  */
 void arch_optimize_kprobes(struct list_head *oplist)
 {
 	struct optimized_kprobe *op, *tmp;
-	u8 insn_buff[RELATIVEJUMP_SIZE];
+	u8 insn_buff[JMP32_INSN_SIZE];
 
 	list_for_each_entry_safe(op, tmp, oplist, list) {
 		s32 rel = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+			((long)op->kp.addr + JMP32_INSN_SIZE));
 
 		WARN_ON(kprobe_disabled(&op->kp));
 
 		/* Backup instructions which will be replaced by jump address */
-		memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-		       RELATIVE_ADDR_SIZE);
+		memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE,
+		       DISP32_SIZE);
 
-		insn_buff[0] = RELATIVEJUMP_OPCODE;
+		insn_buff[0] = JMP32_INSN_OPCODE;
 		*(s32 *)(&insn_buff[1]) = rel;
 
-		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL);
+		text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
 
 		list_del_init(&op->list);
 	}
 }
 
-/* Replace a relative jump with a breakpoint (int3).  */
+/*
+ * Replace a relative jump (JMP.d32) with a breakpoint (INT3).
+ *
+ * After that, we can restore the 4 bytes after the INT3 to undo what
+ * arch_optimize_kprobes() scribbled. This is safe since those bytes will be
+ * unused once the INT3 lands.
+ */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	u8 insn_buff[RELATIVEJUMP_SIZE];
-	u8 emulate_buff[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	insn_buff[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	emulate_buff[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-	text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-		     emulate_buff);
+	arch_arm_kprobe(&op->kp);
+	text_poke(op->kp.addr + INT3_INSN_SIZE,
+		  op->optinsn.copied_insn, DISP32_SIZE);
+	text_poke_sync();
 }
 
 /*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 05da6b5b167b..f19de6f45d48 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -572,15 +572,6 @@ NOKPROBE_SYMBOL(do_general_protection);
 
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/*
-	 * ftrace must be first, everything else may cause a recursive crash.
-	 * See note by declaration of modifying_ftrace_code in ftrace.c
-	 */
-	if (unlikely(atomic_read(&modifying_ftrace_code)) &&
-	    ftrace_int3_handler(regs))
-		return;
-#endif
 	if (poke_int3_handler(regs))
 		return;
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8d29ae8d3eb7..23df4885bbed 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -873,34 +873,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 
 int kernel_set_to_readonly __read_mostly;
 
-void set_kernel_text_rw(void)
-{
-	unsigned long start = PFN_ALIGN(_text);
-	unsigned long size = PFN_ALIGN(_etext) - start;
-
-	if (!kernel_set_to_readonly)
-		return;
-
-	pr_debug("Set kernel text: %lx - %lx for read write\n",
-		 start, start+size);
-
-	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
-}
-
-void set_kernel_text_ro(void)
-{
-	unsigned long start = PFN_ALIGN(_text);
-	unsigned long size = PFN_ALIGN(_etext) - start;
-
-	if (!kernel_set_to_readonly)
-		return;
-
-	pr_debug("Set kernel text: %lx - %lx for read only\n",
-		 start, start+size);
-
-	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
-}
-
 static void mark_nxdata_nx(void)
 {
 	/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bcfede46fe02..abbdecb75fad 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1258,42 +1258,6 @@ void __init mem_init(void)
 
 int kernel_set_to_readonly;
 
-void set_kernel_text_rw(void)
-{
-	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(_etext);
-
-	if (!kernel_set_to_readonly)
-		return;
-
-	pr_debug("Set kernel text: %lx - %lx for read write\n",
-		 start, end);
-
-	/*
-	 * Make the kernel identity mapping for text RW. Kernel text
-	 * mapping will always be RO. Refer to the comment in
-	 * static_protections() in pageattr.c
-	 */
-	set_memory_rw(start, (end - start) >> PAGE_SHIFT);
-}
-
-void set_kernel_text_ro(void)
-{
-	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(_etext);
-
-	if (!kernel_set_to_readonly)
-		return;
-
-	pr_debug("Set kernel text: %lx - %lx for read only\n",
-		 start, end);
-
-	/*
-	 * Set the kernel identity mapping for text RO.
-	 */
-	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
-}
-
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);