Merge remote-tracking branch 'tip/auto-latest'

# Conflicts:
#	arch/x86/entry/entry_32.S
#	arch/x86/include/asm/pgtable_32_types.h
#	arch/x86/kernel/head_32.S
#	arch/x86/mm/pat_interval.c
#	include/trace/events/rpcrdma.h
#	kernel/time/time.c
#	kernel/trace/trace_export.c

28 files changed, 1806 insertions, 252 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index f2cc0d118a0b..e5ffd8c00254 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -23,6 +23,9 @@ endif
 # Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip()
 # in coverage traces.
 KCOV_INSTRUMENT_softirq.o := n
+# Avoid KCSAN instrumentation in softirq ("No shared variables, all the data
+# are CPU local" => assume no data races), to reduce overhead in interrupts.
+KCSAN_SANITIZE_softirq.o = n
 # These are called from save_stack_trace() on slub debug path,
 # and produce insane amounts of uninteresting coverage.
 KCOV_INSTRUMENT_module.o := n
@@ -30,6 +33,7 @@ KCOV_INSTRUMENT_extable.o := n
 # Don't self-instrument.
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
+KCSAN_SANITIZE_kcov.o := n
 CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 # cond_syscall is currently not LTO compatible
@@ -102,6 +106,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
+obj-$(CONFIG_KCSAN) += kcsan/
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
@@ -119,6 +124,7 @@ obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o
 
 obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
 KASAN_SANITIZE_stackleak.o := n
+KCSAN_SANITIZE_stackleak.o := n
 KCOV_INSTRUMENT_stackleak.o := n
 
 $(obj)/configs.o: $(obj)/config_data.gz
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index caca752ee5e6..3f958b90d914 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -289,7 +289,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 
 	if (irqs_disabled()) {
 		work = this_cpu_ptr(&up_read_work);
-		if (work->irq_work.flags & IRQ_WORK_BUSY)
+		if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY)
 			/* cannot queue more up_read, fallback */
 			irq_work_busy = true;
 	}
diff --git a/kernel/fork.c b/kernel/fork.c
index 21c6c1e29b98..2508a4f238a3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2185,7 +2185,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 
 	p->start_time = ktime_get_ns();
-	p->real_start_time = ktime_get_boottime_ns();
+	p->start_boottime = ktime_get_boottime_ns();
 
 	/*
 	 * Make it visible to the rest of the system, but dont wake it up yet.
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b76703b2c0af..b3fa2d87d2f3 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1298,6 +1298,50 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq);
 #endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */
 
 /**
+ * irq_chip_set_parent_state - set the state of a parent interrupt.
+ *
+ * @data: Pointer to interrupt specific data
+ * @which: State to be restored (one of IRQCHIP_STATE_*)
+ * @val: Value corresponding to @which
+ *
+ * Conditional success, if the underlying irqchip does not implement it.
+ */
+int irq_chip_set_parent_state(struct irq_data *data,
+			      enum irqchip_irq_state which,
+			      bool val)
+{
+	data = data->parent_data;
+
+	if (!data || !data->chip->irq_set_irqchip_state)
+		return 0;
+
+	return data->chip->irq_set_irqchip_state(data, which, val);
+}
+EXPORT_SYMBOL_GPL(irq_chip_set_parent_state);
+
+/**
+ * irq_chip_get_parent_state - get the state of a parent interrupt.
+ *
+ * @data: Pointer to interrupt specific data
+ * @which: one of IRQCHIP_STATE_* the caller wants to know
+ * @state: a pointer to a boolean where the state is to be stored
+ *
+ * Conditional success, if the underlying irqchip does not implement it.
+ */
+int irq_chip_get_parent_state(struct irq_data *data,
+			      enum irqchip_irq_state which,
+			      bool *state)
+{
+	data = data->parent_data;
+
+	if (!data || !data->chip->irq_get_irqchip_state)
+		return 0;
+
+	return data->chip->irq_get_irqchip_state(data, which, state);
+}
+EXPORT_SYMBOL_GPL(irq_chip_get_parent_state);
+
+/**
  * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if
  * NULL)
  * @data:	Pointer to interrupt specific data
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9be995fc3c5a..5b8fdd659e54 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -750,7 +750,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
 EXPORT_SYMBOL_GPL(irq_free_descs);
 
 /**
- * irq_alloc_descs - allocate and initialize a range of irq descriptors
+ * __irq_alloc_descs - allocate and initialize a range of irq descriptors
  * @irq:	Allocate for specific irq number if irq >= 0
  * @from:	Start the search from this irq number
  * @cnt:	Number of consecutive irqs to allocate.
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index d42acaf81886..828cc30774bc 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -29,24 +29,16 @@ static DEFINE_PER_CPU(struct llist_head, lazy_list);
  */
 static bool irq_work_claim(struct irq_work *work)
 {
-	unsigned long flags, oflags, nflags;
+	int oflags;
 
+	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags);
 	/*
-	 * Start with our best wish as a premise but only trust any
-	 * flag value after cmpxchg() result.
+	 * If the work is already pending, no need to raise the IPI.
+	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
+	 * everything we did before is visible.
 	 */
-	flags = work->flags & ~IRQ_WORK_PENDING;
-	for (;;) {
-		nflags = flags | IRQ_WORK_CLAIMED;
-		oflags = cmpxchg(&work->flags, flags, nflags);
-		if (oflags == flags)
-			break;
-		if (oflags & IRQ_WORK_PENDING)
-			return false;
-		flags = oflags;
-		cpu_relax();
-	}
-
+	if (oflags & IRQ_WORK_PENDING)
+		return false;
 	return true;
 }
 
@@ -61,7 +53,7 @@ void __weak arch_irq_work_raise(void)
 static void __irq_work_queue_local(struct irq_work *work)
 {
 	/* If the work is "lazy", handle it from next tick if any */
-	if (work->flags & IRQ_WORK_LAZY) {
+	if (atomic_read(&work->flags) & IRQ_WORK_LAZY) {
 		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
 		    tick_nohz_tick_stopped())
 			arch_irq_work_raise();
@@ -143,7 +135,6 @@ static void irq_work_run_list(struct llist_head *list)
 {
 	struct irq_work *work, *tmp;
 	struct llist_node *llnode;
-	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
@@ -152,6 +143,7 @@ static void irq_work_run_list(struct llist_head *list)
 
 	llnode = llist_del_all(list);
 	llist_for_each_entry_safe(work, tmp, llnode, llnode) {
+		int flags;
 		/*
 		 * Clear the PENDING bit, after this point the @work
 		 * can be re-used.
@@ -159,15 +151,15 @@ static void irq_work_run_list(struct llist_head *list)
 		 * to claim that work don't rely on us to handle their data
 		 * while we are in the middle of the func.
 		 */
-		flags = work->flags & ~IRQ_WORK_PENDING;
-		xchg(&work->flags, flags);
+		flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
 
 		work->func(work);
 		/*
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		(void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
+		flags &= ~IRQ_WORK_PENDING;
+		(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
 	}
 }
 
@@ -199,7 +191,7 @@ void irq_work_sync(struct irq_work *work)
 {
 	lockdep_assert_irqs_enabled();
 
-	while (work->flags & IRQ_WORK_BUSY)
+	while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile
new file mode 100644
index 000000000000..dd15b62ec0b5
--- /dev/null
+++ b/kernel/kcsan/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+KCSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
+
+CFLAGS_core.o := $(call cc-option,-fno-conserve-stack,) \
+	$(call cc-option,-fno-stack-protector,)
+
+obj-y := core.o debugfs.o report.o
+obj-$(CONFIG_KCSAN_SELFTEST) += test.o
diff --git a/kernel/kcsan/atomic.h b/kernel/kcsan/atomic.h
new file mode 100644
index 000000000000..576e03ddd6a3
--- /dev/null
+++ b/kernel/kcsan/atomic.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ATOMIC_H
+#define _KERNEL_KCSAN_ATOMIC_H
+
+#include <linux/jiffies.h>
+
+/*
+ * Helper that returns true if access to @ptr should be considered an atomic
+ * access, even though it is not explicitly atomic.
+ *
+ * List all volatile globals that have been observed in races, to suppress
+ * data race reports between accesses to these variables.
+ *
+ * For now, we assume that volatile accesses of globals are as strong as atomic
+ * accesses (READ_ONCE, WRITE_ONCE cast to volatile). The situation is still not
+ * entirely clear, as on some architectures (Alpha) READ_ONCE/WRITE_ONCE do more
+ * than cast to volatile. Eventually, we hope to be able to remove this
+ * function.
+ */
+static inline bool kcsan_is_atomic(const volatile void *ptr)
+{
+	/* only jiffies for now */
+	return ptr == &jiffies;
+}
+
+#endif /* _KERNEL_KCSAN_ATOMIC_H */
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
new file mode 100644
index 000000000000..3314fc29e236
--- /dev/null
+++ b/kernel/kcsan/core.c
@@ -0,0 +1,621 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include "atomic.h"
+#include "encoding.h"
+#include "kcsan.h"
+
+bool kcsan_enabled;
+
+/* Per-CPU kcsan_ctx for interrupts */
+static DEFINE_PER_CPU(struct kcsan_ctx, kcsan_cpu_ctx) = {
+	.disable_count		= 0,
+	.atomic_next		= 0,
+	.atomic_nest_count	= 0,
+	.in_flat_atomic		= false,
+};
+
+/*
+ * Helper macros to index into adjacent slots slots, starting from address slot
+ * itself, followed by the right and left slots.
+ *
+ * The purpose is 2-fold:
+ *
+ *	1. if during insertion the address slot is already occupied, check if
+ *	   any adjacent slots are free;
+ *	2. accesses that straddle a slot boundary due to size that exceeds a
+ *	   slot's range may check adjacent slots if any watchpoint matches.
+ *
+ * Note that accesses with very large size may still miss a watchpoint; however,
+ * given this should be rare, this is a reasonable trade-off to make, since this
+ * will avoid:
+ *
+ *	1. excessive contention between watchpoint checks and setup;
+ *	2. larger number of simultaneous watchpoints without sacrificing
+ *	   performance.
+ *
+ * Example: SLOT_IDX values for KCSAN_CHECK_ADJACENT=1, where i is [0, 1, 2]:
+ *
+ *   slot=0:  [ 1,  2,  0]
+ *   slot=9:  [10, 11,  9]
+ *   slot=63: [64, 65, 63]
+ */
+#define NUM_SLOTS (1 + 2*KCSAN_CHECK_ADJACENT)
+#define SLOT_IDX(slot, i) (slot + ((i + KCSAN_CHECK_ADJACENT) % NUM_SLOTS))
+
+/*
+ * SLOT_IDX_FAST is used in the fast-path. Not first checking the address's primary
+ * slot (middle) is fine if we assume that data races occur rarely. The set of
+ * indices {SLOT_IDX(slot, i) | i in [0, NUM_SLOTS)} is equivalent to
+ * {SLOT_IDX_FAST(slot, i) | i in [0, NUM_SLOTS)}.
+ */
+#define SLOT_IDX_FAST(slot, i) (slot + i)
+
+/*
+ * Watchpoints, with each entry encoded as defined in encoding.h: in order to be
+ * able to safely update and access a watchpoint without introducing locking
+ * overhead, we encode each watchpoint as a single atomic long. The initial
+ * zero-initialized state matches INVALID_WATCHPOINT.
+ *
+ * Add NUM_SLOTS-1 entries to account for overflow; this helps avoid having to
+ * use more complicated SLOT_IDX_FAST calculation with modulo in the fast-path.
+ */
+static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
+
+/*
+ * Instructions to skip watching counter, used in should_watch(). We use a
+ * per-CPU counter to avoid excessive contention.
+ */
+static DEFINE_PER_CPU(long, kcsan_skip);
+
+static inline atomic_long_t *find_watchpoint(unsigned long addr,
+					     size_t size,
+					     bool expect_write,
+					     long *encoded_watchpoint)
+{
+	const int slot = watchpoint_slot(addr);
+	const unsigned long addr_masked = addr & WATCHPOINT_ADDR_MASK;
+	atomic_long_t *watchpoint;
+	unsigned long wp_addr_masked;
+	size_t wp_size;
+	bool is_write;
+	int i;
+
+	BUILD_BUG_ON(CONFIG_KCSAN_NUM_WATCHPOINTS < NUM_SLOTS);
+
+	for (i = 0; i < NUM_SLOTS; ++i) {
+		watchpoint = &watchpoints[SLOT_IDX_FAST(slot, i)];
+		*encoded_watchpoint = atomic_long_read(watchpoint);
+		if (!decode_watchpoint(*encoded_watchpoint, &wp_addr_masked,
+				       &wp_size, &is_write))
+			continue;
+
+		if (expect_write && !is_write)
+			continue;
+
+		/* Check if the watchpoint matches the access. */
+		if (matching_access(wp_addr_masked, wp_size, addr_masked, size))
+			return watchpoint;
+	}
+
+	return NULL;
+}
+
+static inline atomic_long_t *
+insert_watchpoint(unsigned long addr, size_t size, bool is_write)
+{
+	const int slot = watchpoint_slot(addr);
+	const long encoded_watchpoint = encode_watchpoint(addr, size, is_write);
+	atomic_long_t *watchpoint;
+	int i;
+
+	/* Check slot index logic, ensuring we stay within array bounds. */
+	BUILD_BUG_ON(SLOT_IDX(0, 0) != KCSAN_CHECK_ADJACENT);
+	BUILD_BUG_ON(SLOT_IDX(0, KCSAN_CHECK_ADJACENT+1) != 0);
+	BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT) != ARRAY_SIZE(watchpoints)-1);
+	BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT+1) != ARRAY_SIZE(watchpoints) - NUM_SLOTS);
+
+	for (i = 0; i < NUM_SLOTS; ++i) {
+		long expect_val = INVALID_WATCHPOINT;
+
+		/* Try to acquire this slot. */
+		watchpoint = &watchpoints[SLOT_IDX(slot, i)];
+		if (atomic_long_try_cmpxchg_relaxed(watchpoint, &expect_val, encoded_watchpoint))
+			return watchpoint;
+	}
+
+	return NULL;
+}
+
+/*
+ * Return true if watchpoint was successfully consumed, false otherwise.
+ *
+ * This may return false if:
+ *
+ *	1. another thread already consumed the watchpoint;
+ *	2. the thread that set up the watchpoint already removed it;
+ *	3. the watchpoint was removed and then re-used.
+ */
+static inline bool
+try_consume_watchpoint(atomic_long_t *watchpoint, long encoded_watchpoint)
+{
+	return atomic_long_try_cmpxchg_relaxed(watchpoint, &encoded_watchpoint, CONSUMED_WATCHPOINT);
+}
+
+/*
+ * Return true if watchpoint was not touched, false if consumed.
+ */
+static inline bool remove_watchpoint(atomic_long_t *watchpoint)
+{
+	return atomic_long_xchg_relaxed(watchpoint, INVALID_WATCHPOINT) != CONSUMED_WATCHPOINT;
+}
+
+static inline struct kcsan_ctx *get_ctx(void)
+{
+	/*
+	 * In interrupts, use raw_cpu_ptr to avoid unnecessary checks, that would
+	 * also result in calls that generate warnings in uaccess regions.
+	 */
+	return in_task() ? &current->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx);
+}
+
+static inline bool is_atomic(const volatile void *ptr)
+{
+	struct kcsan_ctx *ctx = get_ctx();
+
+	if (unlikely(ctx->atomic_next > 0)) {
+		/*
+		 * Because we do not have separate contexts for nested
+		 * interrupts, in case atomic_next is set, we simply assume that
+		 * the outer interrupt set atomic_next. In the worst case, we
+		 * will conservatively consider operations as atomic. This is a
+		 * reasonable trade-off to make, since this case should be
+		 * extremely rare; however, even if extremely rare, it could
+		 * lead to false positives otherwise.
+		 */
+		if ((hardirq_count() >> HARDIRQ_SHIFT) < 2)
+			--ctx->atomic_next; /* in task, or outer interrupt */
+		return true;
+	}
+	if (unlikely(ctx->atomic_nest_count > 0 || ctx->in_flat_atomic))
+		return true;
+
+	return kcsan_is_atomic(ptr);
+}
+
+static inline bool should_watch(const volatile void *ptr, int type)
+{
+	/*
+	 * Never set up watchpoints when memory operations are atomic.
+	 *
+	 * Need to check this first, before kcsan_skip check below: (1) atomics
+	 * should not count towards skipped instructions, and (2) to actually
+	 * decrement kcsan_atomic_next for consecutive instruction stream.
+	 */
+	if ((type & KCSAN_ACCESS_ATOMIC) != 0 || is_atomic(ptr))
+		return false;
+
+	if (this_cpu_dec_return(kcsan_skip) >= 0)
+		return false;
+
+	/*
+	 * NOTE: If we get here, kcsan_skip must always be reset in slow path
+	 * via reset_kcsan_skip() to avoid underflow.
+	 */
+
+	/* this operation should be watched */
+	return true;
+}
+
+static inline void reset_kcsan_skip(void)
+{
+	long skip_count = CONFIG_KCSAN_SKIP_WATCH -
+			  (IS_ENABLED(CONFIG_KCSAN_SKIP_WATCH_RANDOMIZE) ?
+				   prandom_u32_max(CONFIG_KCSAN_SKIP_WATCH) :
+				   0);
+	this_cpu_write(kcsan_skip, skip_count);
+}
+
+static inline bool kcsan_is_enabled(void)
+{
+	return READ_ONCE(kcsan_enabled) && get_ctx()->disable_count == 0;
+}
+
+static inline unsigned int get_delay(void)
+{
+	unsigned int delay = in_task() ? CONFIG_KCSAN_UDELAY_TASK :
+					 CONFIG_KCSAN_UDELAY_INTERRUPT;
+	return delay - (IS_ENABLED(CONFIG_KCSAN_DELAY_RANDOMIZE) ?
+				prandom_u32_max(delay) :
+				0);
+}
+
+/*
+ * Pull everything together: check_access() below contains the performance
+ * critical operations; the fast-path (including check_access) functions should
+ * all be inlinable by the instrumentation functions.
+ *
+ * The slow-path (kcsan_found_watchpoint, kcsan_setup_watchpoint) are
+ * non-inlinable -- note that, we prefix these with "kcsan_" to ensure they can
+ * be filtered from the stacktrace, as well as give them unique names for the
+ * UACCESS whitelist of objtool. Each function uses user_access_save/restore(),
+ * since they do not access any user memory, but instrumentation is still
+ * emitted in UACCESS regions.
+ */
+
+static noinline void kcsan_found_watchpoint(const volatile void *ptr,
+					    size_t size,
+					    bool is_write,
+					    atomic_long_t *watchpoint,
+					    long encoded_watchpoint)
+{
+	unsigned long flags;
+	bool consumed;
+
+	if (!kcsan_is_enabled())
+		return;
+	/*
+	 * Consume the watchpoint as soon as possible, to minimize the chances
+	 * of !consumed. Consuming the watchpoint must always be guarded by
+	 * kcsan_is_enabled() check, as otherwise we might erroneously
+	 * triggering reports when disabled.
+	 */
+	consumed = try_consume_watchpoint(watchpoint, encoded_watchpoint);
+
+	/* keep this after try_consume_watchpoint */
+	flags = user_access_save();
+
+	if (consumed) {
+		kcsan_report(ptr, size, is_write, true, raw_smp_processor_id(),
+			     KCSAN_REPORT_CONSUMED_WATCHPOINT);
+	} else {
+		/*
+		 * The other thread may not print any diagnostics, as it has
+		 * already removed the watchpoint, or another thread consumed
+		 * the watchpoint before this thread.
+		 */
+		kcsan_counter_inc(KCSAN_COUNTER_REPORT_RACES);
+	}
+	kcsan_counter_inc(KCSAN_COUNTER_DATA_RACES);
+
+	user_access_restore(flags);
+}
+
+static noinline void
+kcsan_setup_watchpoint(const volatile void *ptr, size_t size, bool is_write)
+{
+	atomic_long_t *watchpoint;
+	union {
+		u8 _1;
+		u16 _2;
+		u32 _4;
+		u64 _8;
+	} expect_value;
+	bool value_change = false;
+	unsigned long ua_flags = user_access_save();
+	unsigned long irq_flags;
+
+	/*
+	 * Always reset kcsan_skip counter in slow-path to avoid underflow; see
+	 * should_watch().
+	 */
+	reset_kcsan_skip();
+
+	if (!kcsan_is_enabled())
+		goto out;
+
+	if (!check_encodable((unsigned long)ptr, size)) {
+		kcsan_counter_inc(KCSAN_COUNTER_UNENCODABLE_ACCESSES);
+		goto out;
+	}
+
+	/*
+	 * Disable interrupts & preemptions to avoid another thread on the same
+	 * CPU accessing memory locations for the set up watchpoint; this is to
+	 * avoid reporting races to e.g. CPU-local data.
+	 *
+	 * An alternative would be adding the source CPU to the watchpoint
+	 * encoding, and checking that watchpoint-CPU != this-CPU. There are
+	 * several problems with this:
+	 *   1. we should avoid stealing more bits from the watchpoint encoding
+	 *      as it would affect accuracy, as well as increase performance
+	 *      overhead in the fast-path;
+	 *   2. if we are preempted, but there *is* a genuine data race, we
+	 *      would *not* report it -- since this is the common case (vs.
+	 *      CPU-local data accesses), it makes more sense (from a data race
+	 *      detection point of view) to simply disable preemptions to ensure
+	 *      as many tasks as possible run on other CPUs.
+	 */
+	local_irq_save(irq_flags);
+
+	watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write);
+	if (watchpoint == NULL) {
+		/*
+		 * Out of capacity: the size of 'watchpoints', and the frequency
+		 * with which should_watch() returns true should be tweaked so
+		 * that this case happens very rarely.
+		 */
+		kcsan_counter_inc(KCSAN_COUNTER_NO_CAPACITY);
+		goto out_unlock;
+	}
+
+	kcsan_counter_inc(KCSAN_COUNTER_SETUP_WATCHPOINTS);
+	kcsan_counter_inc(KCSAN_COUNTER_USED_WATCHPOINTS);
+
+	/*
+	 * Read the current value, to later check and infer a race if the data
+	 * was modified via a non-instrumented access, e.g. from a device.
+	 */
+	switch (size) {
+	case 1:
+		expect_value._1 = READ_ONCE(*(const u8 *)ptr);
+		break;
+	case 2:
+		expect_value._2 = READ_ONCE(*(const u16 *)ptr);
+		break;
+	case 4:
+		expect_value._4 = READ_ONCE(*(const u32 *)ptr);
+		break;
+	case 8:
+		expect_value._8 = READ_ONCE(*(const u64 *)ptr);
+		break;
+	default:
+		break; /* ignore; we do not diff the values */
+	}
+
+	if (IS_ENABLED(CONFIG_KCSAN_DEBUG)) {
+		kcsan_disable_current();
+		pr_err("KCSAN: watching %s, size: %zu, addr: %px [slot: %d, encoded: %lx]\n",
+		       is_write ? "write" : "read", size, ptr,
+		       watchpoint_slot((unsigned long)ptr),
+		       encode_watchpoint((unsigned long)ptr, size, is_write));
+		kcsan_enable_current();
+	}
+
+	/*
+	 * Delay this thread, to increase probability of observing a racy
+	 * conflicting access.
+	 */
+	udelay(get_delay());
+
+	/*
+	 * Re-read value, and check if it is as expected; if not, we infer a
+	 * racy access.
+	 */
+	switch (size) {
+	case 1:
+		value_change = expect_value._1 != READ_ONCE(*(const u8 *)ptr);
+		break;
+	case 2:
+		value_change = expect_value._2 != READ_ONCE(*(const u16 *)ptr);
+		break;
+	case 4:
+		value_change = expect_value._4 != READ_ONCE(*(const u32 *)ptr);
+		break;
+	case 8:
+		value_change = expect_value._8 != READ_ONCE(*(const u64 *)ptr);
+		break;
+	default:
+		break; /* ignore; we do not diff the values */
+	}
+
+	/* Check if this access raced with another. */
+	if (!remove_watchpoint(watchpoint)) {
+		/*
+		 * No need to increment 'data_races' counter, as the racing
+		 * thread already did.
+		 */
+		kcsan_report(ptr, size, is_write, size > 8 || value_change,
+			     smp_processor_id(), KCSAN_REPORT_RACE_SIGNAL);
+	} else if (value_change) {
+		/* Inferring a race, since the value should not have changed. */
+		kcsan_counter_inc(KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN);
+		if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN))
+			kcsan_report(ptr, size, is_write, true,
+				     smp_processor_id(),
+				     KCSAN_REPORT_RACE_UNKNOWN_ORIGIN);
+	}
+
+	kcsan_counter_dec(KCSAN_COUNTER_USED_WATCHPOINTS);
+out_unlock:
+	local_irq_restore(irq_flags);
+out:
+	user_access_restore(ua_flags);
+}
+
+static __always_inline void check_access(const volatile void *ptr, size_t size,
+					 int type)
+{
+	const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
+	atomic_long_t *watchpoint;
+	long encoded_watchpoint;
+
+	/*
+	 * Avoid user_access_save in fast-path: find_watchpoint is safe without
+	 * user_access_save, as the address that ptr points to is only used to
+	 * check if a watchpoint exists; ptr is never dereferenced.
+	 */
+	watchpoint = find_watchpoint((unsigned long)ptr, size, !is_write,
+				     &encoded_watchpoint);
+	/*
+	 * It is safe to check kcsan_is_enabled() after find_watchpoint in the
+	 * slow-path, as long as no state changes that cause a data race to be
+	 * detected and reported have occurred until kcsan_is_enabled() is
+	 * checked.
+	 */
+
+	if (unlikely(watchpoint != NULL))
+		kcsan_found_watchpoint(ptr, size, is_write, watchpoint,
+				       encoded_watchpoint);
+	else if (unlikely(should_watch(ptr, type)))
+		kcsan_setup_watchpoint(ptr, size, is_write);
+}
+
+/* === Public interface ===================================================== */
+
+void __init kcsan_init(void)
+{
+	BUG_ON(!in_task());
+
+	kcsan_debugfs_init();
+
+	/*
+	 * We are in the init task, and no other tasks should be running;
+	 * WRITE_ONCE without memory barrier is sufficient.
+	 */
+	if (IS_ENABLED(CONFIG_KCSAN_EARLY_ENABLE))
+		WRITE_ONCE(kcsan_enabled, true);
+}
+
+/* === Exported interface =================================================== */
+
+void kcsan_disable_current(void)
+{
+	++get_ctx()->disable_count;
+}
+EXPORT_SYMBOL(kcsan_disable_current);
+
+void kcsan_enable_current(void)
+{
+	if (get_ctx()->disable_count-- == 0) {
+		/*
+		 * Warn if kcsan_enable_current() calls are unbalanced with
+		 * kcsan_disable_current() calls, which causes disable_count to
+		 * become negative and should not happen.
+		 */
+		kcsan_disable_current(); /* restore to 0, KCSAN still enabled */
+		kcsan_disable_current(); /* disable to generate warning */
+		WARN(1, "Unbalanced %s()", __func__);
+		kcsan_enable_current();
+	}
+}
+EXPORT_SYMBOL(kcsan_enable_current);
+
+void kcsan_nestable_atomic_begin(void)
+{
+	/*
+	 * Do *not* check and warn if we are in a flat atomic region: nestable
+	 * and flat atomic regions are independent from each other.
+	 * See include/linux/kcsan.h: struct kcsan_ctx comments for more
+	 * comments.
+	 */
+
+	++get_ctx()->atomic_nest_count;
+}
+EXPORT_SYMBOL(kcsan_nestable_atomic_begin);
+
+void kcsan_nestable_atomic_end(void)
+{
+	if (get_ctx()->atomic_nest_count-- == 0) {
+		/*
+		 * Warn if kcsan_nestable_atomic_end() calls are unbalanced with
+		 * kcsan_nestable_atomic_begin() calls, which causes
+		 * atomic_nest_count to become negative and should not happen.
+		 */
+		kcsan_nestable_atomic_begin(); /* restore to 0 */
+		kcsan_disable_current(); /* disable to generate warning */
+		WARN(1, "Unbalanced %s()", __func__);
+		kcsan_enable_current();
+	}
+}
+EXPORT_SYMBOL(kcsan_nestable_atomic_end);
+
+void kcsan_flat_atomic_begin(void)
+{
+	get_ctx()->in_flat_atomic = true;
+}
+EXPORT_SYMBOL(kcsan_flat_atomic_begin);
+
+void kcsan_flat_atomic_end(void)
+{
+	get_ctx()->in_flat_atomic = false;
+}
+EXPORT_SYMBOL(kcsan_flat_atomic_end);
+
+void kcsan_atomic_next(int n)
+{
+	get_ctx()->atomic_next = n;
+}
+EXPORT_SYMBOL(kcsan_atomic_next);
+
+void __kcsan_check_access(const volatile void *ptr, size_t size, int type)
+{
+	check_access(ptr, size, type);
+}
+EXPORT_SYMBOL(__kcsan_check_access);
+
+/*
+ * KCSAN uses the same instrumentation that is emitted by supported compilers
+ * for ThreadSanitizer (TSAN).
+ *
+ * When enabled, the compiler emits instrumentation calls (the functions
+ * prefixed with "__tsan" below) for all loads and stores that it generated;
+ * inline asm is not instrumented.
+ *
+ * Note that, not all supported compiler versions distinguish aligned/unaligned
+ * accesses, but e.g. recent versions of Clang do. We simply alias the unaligned
+ * version to the generic version, which can handle both.
+ */
+
+#define DEFINE_TSAN_READ_WRITE(size)                                           \
+	void __tsan_read##size(void *ptr)                                      \
+	{                                                                      \
+		check_access(ptr, size, 0);                                    \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_read##size);                                      \
+	void __tsan_unaligned_read##size(void *ptr)                            \
+		__alias(__tsan_read##size);                                    \
+	EXPORT_SYMBOL(__tsan_unaligned_read##size);                            \
+	void __tsan_write##size(void *ptr)                                     \
+	{                                                                      \
+		check_access(ptr, size, KCSAN_ACCESS_WRITE);                   \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_write##size);                                     \
+	void __tsan_unaligned_write##size(void *ptr)                           \
+		__alias(__tsan_write##size);                                   \
+	EXPORT_SYMBOL(__tsan_unaligned_write##size)
+
+DEFINE_TSAN_READ_WRITE(1);
+DEFINE_TSAN_READ_WRITE(2);
+DEFINE_TSAN_READ_WRITE(4);
+DEFINE_TSAN_READ_WRITE(8);
+DEFINE_TSAN_READ_WRITE(16);
+
+void __tsan_read_range(void *ptr, size_t size)
+{
+	check_access(ptr, size, 0);
+}
+EXPORT_SYMBOL(__tsan_read_range);
+
+void __tsan_write_range(void *ptr, size_t size)
+{
+	check_access(ptr, size, KCSAN_ACCESS_WRITE);
+}
+EXPORT_SYMBOL(__tsan_write_range);
+
+/*
+ * The below are not required by KCSAN, but can still be emitted by the
+ * compiler.
+ */
+void __tsan_func_entry(void *call_pc)
+{
+}
+EXPORT_SYMBOL(__tsan_func_entry);
+void __tsan_func_exit(void)
+{
+}
+EXPORT_SYMBOL(__tsan_func_exit);
+void __tsan_init(void)
+{
+}
+EXPORT_SYMBOL(__tsan_init);
diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c
new file mode 100644
index 000000000000..bec42dab32ee
--- /dev/null
+++ b/kernel/kcsan/debugfs.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/atomic.h>
+#include <linux/bsearch.h>
+#include <linux/bug.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+#include "kcsan.h"
+
+/*
+ * Statistics counters.
+ */
+static atomic_long_t counters[KCSAN_COUNTER_COUNT];
+
+/*
+ * Addresses for filtering functions from reporting. This list can be used as a
+ * whitelist or blacklist.
+ */
+static struct {
+	unsigned long	*addrs;		/* array of addresses */
+	size_t		size;		/* current size */
+	int		used;		/* number of elements used */
+	bool		sorted;		/* if elements are sorted */
+	bool		whitelist;	/* if list is a blacklist or whitelist */
+} report_filterlist = {
+	.addrs		= NULL,
+	.size		= 8,		/* small initial size */
+	.used		= 0,
+	.sorted		= false,
+	.whitelist	= false,	/* default is blacklist */
+};
+static DEFINE_SPINLOCK(report_filterlist_lock);
+
+static const char *counter_to_name(enum kcsan_counter_id id)
+{
+	switch (id) {
+	case KCSAN_COUNTER_USED_WATCHPOINTS:		return "used_watchpoints";
+	case KCSAN_COUNTER_SETUP_WATCHPOINTS:		return "setup_watchpoints";
+	case KCSAN_COUNTER_DATA_RACES:			return "data_races";
+	case KCSAN_COUNTER_NO_CAPACITY:			return "no_capacity";
+	case KCSAN_COUNTER_REPORT_RACES:		return "report_races";
+	case KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN:	return "races_unknown_origin";
+	case KCSAN_COUNTER_UNENCODABLE_ACCESSES:	return "unencodable_accesses";
+	case KCSAN_COUNTER_ENCODING_FALSE_POSITIVES:	return "encoding_false_positives";
+	case KCSAN_COUNTER_COUNT:
+		BUG();
+	}
+	return NULL;
+}
+
+void kcsan_counter_inc(enum kcsan_counter_id id)
+{
+	atomic_long_inc(&counters[id]);
+}
+
+void kcsan_counter_dec(enum kcsan_counter_id id)
+{
+	atomic_long_dec(&counters[id]);
+}
+
+/*
+ * The microbenchmark allows benchmarking KCSAN core runtime only. To run
+ * multiple threads, pipe 'microbench=<iters>' from multiple tasks into the
+ * debugfs file.
+ */
+static void microbenchmark(unsigned long iters)
+{
+	cycles_t cycles;
+
+	pr_info("KCSAN: %s begin | iters: %lu\n", __func__, iters);
+
+	cycles = get_cycles();
+	while (iters--) {
+		/*
+		 * We can run this benchmark from multiple tasks; this address
+		 * calculation increases likelyhood of some accesses overlapping
+		 * (they still won't conflict because all are reads).
+		 */
+		unsigned long addr =
+			iters % (CONFIG_KCSAN_NUM_WATCHPOINTS * PAGE_SIZE);
+		__kcsan_check_read((void *)addr, sizeof(long));
+	}
+	cycles = get_cycles() - cycles;
+
+	pr_info("KCSAN: %s end   | cycles: %llu\n", __func__, cycles);
+}
+
+static int cmp_filterlist_addrs(const void *rhs, const void *lhs)
+{
+	const unsigned long a = *(const unsigned long *)rhs;
+	const unsigned long b = *(const unsigned long *)lhs;
+
+	return a < b ? -1 : a == b ? 0 : 1;
+}
+
+bool kcsan_skip_report_debugfs(unsigned long func_addr)
+{
+	unsigned long symbolsize, offset;
+	unsigned long flags;
+	bool ret = false;
+
+	if (!kallsyms_lookup_size_offset(func_addr, &symbolsize, &offset))
+		return false;
+	func_addr -= offset; /* Get function start */
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	if (report_filterlist.used == 0)
+		goto out;
+
+	/* Sort array if it is unsorted, and then do a binary search. */
+	if (!report_filterlist.sorted) {
+		sort(report_filterlist.addrs, report_filterlist.used,
+		     sizeof(unsigned long), cmp_filterlist_addrs, NULL);
+		report_filterlist.sorted = true;
+	}
+	ret = !!bsearch(&func_addr, report_filterlist.addrs,
+			report_filterlist.used, sizeof(unsigned long),
+			cmp_filterlist_addrs);
+	if (report_filterlist.whitelist)
+		ret = !ret;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+	return ret;
+}
+
+static void set_report_filterlist_whitelist(bool whitelist)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	report_filterlist.whitelist = whitelist;
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+}
+
+/* Returns 0 on success, error-code otherwise. */
+static ssize_t insert_report_filterlist(const char *func)
+{
+	unsigned long flags;
+	unsigned long addr = kallsyms_lookup_name(func);
+	ssize_t ret = 0;
+
+	if (!addr) {
+		pr_err("KCSAN: could not find function: '%s'\n", func);
+		return -ENOENT;
+	}
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+
+	if (report_filterlist.addrs == NULL) {
+		/* initial allocation */
+		report_filterlist.addrs =
+			kmalloc_array(report_filterlist.size,
+				      sizeof(unsigned long), GFP_KERNEL);
+		if (report_filterlist.addrs == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	} else if (report_filterlist.used == report_filterlist.size) {
+		/* resize filterlist */
+		size_t new_size = report_filterlist.size * 2;
+		unsigned long *new_addrs =
+			krealloc(report_filterlist.addrs,
+				 new_size * sizeof(unsigned long), GFP_KERNEL);
+
+		if (new_addrs == NULL) {
+			/* leave filterlist itself untouched */
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		report_filterlist.size = new_size;
+		report_filterlist.addrs = new_addrs;
+	}
+
+	/* Note: deduplicating should be done in userspace. */
+	report_filterlist.addrs[report_filterlist.used++] =
+		kallsyms_lookup_name(func);
+	report_filterlist.sorted = false;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	return ret;
+}
+
+static int show_info(struct seq_file *file, void *v)
+{
+	int i;
+	unsigned long flags;
+
+	/* show stats */
+	seq_printf(file, "enabled: %i\n", READ_ONCE(kcsan_enabled));
+	for (i = 0; i < KCSAN_COUNTER_COUNT; ++i)
+		seq_printf(file, "%s: %ld\n", counter_to_name(i),
+			   atomic_long_read(&counters[i]));
+
+	/* show filter functions, and filter type */
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	seq_printf(file, "\n%s functions: %s\n",
+		   report_filterlist.whitelist ? "whitelisted" : "blacklisted",
+		   report_filterlist.used == 0 ? "none" : "");
+	for (i = 0; i < report_filterlist.used; ++i)
+		seq_printf(file, " %ps\n", (void *)report_filterlist.addrs[i]);
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	return 0;
+}
+
+static int debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_info, NULL);
+}
+
+static ssize_t
+debugfs_write(struct file *file, const char __user *buf, size_t count, loff_t *off)
+{
+	char kbuf[KSYM_NAME_LEN];
+	char *arg;
+	int read_len = count < (sizeof(kbuf) - 1) ? count : (sizeof(kbuf) - 1);
+
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EFAULT;
+	kbuf[read_len] = '\0';
+	arg = strstrip(kbuf);
+
+	if (!strcmp(arg, "on")) {
+		WRITE_ONCE(kcsan_enabled, true);
+	} else if (!strcmp(arg, "off")) {
+		WRITE_ONCE(kcsan_enabled, false);
+	} else if (!strncmp(arg, "microbench=", sizeof("microbench=") - 1)) {
+		unsigned long iters;
+
+		if (kstrtoul(&arg[sizeof("microbench=") - 1], 0, &iters))
+			return -EINVAL;
+		microbenchmark(iters);
+	} else if (!strcmp(arg, "whitelist")) {
+		set_report_filterlist_whitelist(true);
+	} else if (!strcmp(arg, "blacklist")) {
+		set_report_filterlist_whitelist(false);
+	} else if (arg[0] == '!') {
+		ssize_t ret = insert_report_filterlist(&arg[1]);
+
+		if (ret < 0)
+			return ret;
+	} else {
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static const struct file_operations debugfs_ops =
+{
+	.read	 = seq_read,
+	.open	 = debugfs_open,
+	.write	 = debugfs_write,
+	.release = single_release
+};
+
+void __init kcsan_debugfs_init(void)
+{
+	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
+}
diff --git a/kernel/kcsan/encoding.h b/kernel/kcsan/encoding.h
new file mode 100644
index 000000000000..b63890e86449
--- /dev/null
+++ b/kernel/kcsan/encoding.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ENCODING_H
+#define _KERNEL_KCSAN_ENCODING_H
+
+#include <linux/bits.h>
+#include <linux/log2.h>
+#include <linux/mm.h>
+
+#include "kcsan.h"
+
+#define SLOT_RANGE PAGE_SIZE
+
+#define INVALID_WATCHPOINT  0
+#define CONSUMED_WATCHPOINT 1
+
+/*
+ * The maximum useful size of accesses for which we set up watchpoints is the
+ * max range of slots we check on an access.
+ */
+#define MAX_ENCODABLE_SIZE (SLOT_RANGE * (1 + KCSAN_CHECK_ADJACENT))
+
+/*
+ * Number of bits we use to store size info.
+ */
+#define WATCHPOINT_SIZE_BITS bits_per(MAX_ENCODABLE_SIZE)
+/*
+ * This encoding for addresses discards the upper (1 for is-write + SIZE_BITS);
+ * however, most 64-bit architectures do not use the full 64-bit address space.
+ * Also, in order for a false positive to be observable 2 things need to happen:
+ *
+ *	1. different addresses but with the same encoded address race;
+ *	2. and both map onto the same watchpoint slots;
+ *
+ * Both these are assumed to be very unlikely. However, in case it still happens
+ * happens, the report logic will filter out the false positive (see report.c).
+ */
+#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS)
+
+/*
+ * Masks to set/retrieve the encoded data.
+ */
+#define WATCHPOINT_WRITE_MASK BIT(BITS_PER_LONG-1)
+#define WATCHPOINT_SIZE_MASK                                                   \
+	GENMASK(BITS_PER_LONG-2, BITS_PER_LONG-2 - WATCHPOINT_SIZE_BITS)
+#define WATCHPOINT_ADDR_MASK                                                   \
+	GENMASK(BITS_PER_LONG-3 - WATCHPOINT_SIZE_BITS, 0)
+
+static inline bool check_encodable(unsigned long addr, size_t size)
+{
+	return size <= MAX_ENCODABLE_SIZE;
+}
+
+static inline long
+encode_watchpoint(unsigned long addr, size_t size, bool is_write)
+{
+	return (long)((is_write ? WATCHPOINT_WRITE_MASK : 0) |
+		      (size << WATCHPOINT_ADDR_BITS) |
+		      (addr & WATCHPOINT_ADDR_MASK));
+}
+
+static inline bool decode_watchpoint(long watchpoint,
+				     unsigned long *addr_masked,
+				     size_t *size,
+				     bool *is_write)
+{
+	if (watchpoint == INVALID_WATCHPOINT ||
+	    watchpoint == CONSUMED_WATCHPOINT)
+		return false;
+
+	*addr_masked =    (unsigned long)watchpoint & WATCHPOINT_ADDR_MASK;
+	*size	     =   ((unsigned long)watchpoint & WATCHPOINT_SIZE_MASK) >> WATCHPOINT_ADDR_BITS;
+	*is_write    = !!((unsigned long)watchpoint & WATCHPOINT_WRITE_MASK);
+
+	return true;
+}
+
+/*
+ * Return watchpoint slot for an address.
+ */
+static inline int watchpoint_slot(unsigned long addr)
+{
+	return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS;
+}
+
+static inline bool matching_access(unsigned long addr1, size_t size1,
+				   unsigned long addr2, size_t size2)
+{
+	unsigned long end_range1 = addr1 + size1 - 1;
+	unsigned long end_range2 = addr2 + size2 - 1;
+
+	return addr1 <= end_range2 && addr2 <= end_range1;
+}
+
+#endif /* _KERNEL_KCSAN_ENCODING_H */
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
new file mode 100644
index 000000000000..d3b9a96ac8a4
--- /dev/null
+++ b/kernel/kcsan/kcsan.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
+ * see Documentation/dev-tools/kcsan.rst.
+ */
+
+#ifndef _KERNEL_KCSAN_KCSAN_H
+#define _KERNEL_KCSAN_KCSAN_H
+
+#include <linux/kcsan.h>
+
+/* The number of adjacent watchpoints to check. */
+#define KCSAN_CHECK_ADJACENT 1
+
+/*
+ * Globally enable and disable KCSAN.
+ */
+extern bool kcsan_enabled;
+
+/*
+ * Initialize debugfs file.
+ */
+void kcsan_debugfs_init(void);
+
+enum kcsan_counter_id {
+	/*
+	 * Number of watchpoints currently in use.
+	 */
+	KCSAN_COUNTER_USED_WATCHPOINTS,
+
+	/*
+	 * Total number of watchpoints set up.
+	 */
+	KCSAN_COUNTER_SETUP_WATCHPOINTS,
+
+	/*
+	 * Total number of data races.
+	 */
+	KCSAN_COUNTER_DATA_RACES,
+
+	/*
+	 * Number of times no watchpoints were available.
+	 */
+	KCSAN_COUNTER_NO_CAPACITY,
+
+	/*
+	 * A thread checking a watchpoint raced with another checking thread;
+	 * only one will be reported.
+	 */
+	KCSAN_COUNTER_REPORT_RACES,
+
+	/*
+	 * Observed data value change, but writer thread unknown.
+	 */
+	KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN,
+
+	/*
+	 * The access cannot be encoded to a valid watchpoint.
+	 */
+	KCSAN_COUNTER_UNENCODABLE_ACCESSES,
+
+	/*
+	 * Watchpoint encoding caused a watchpoint to fire on mismatching
+	 * accesses.
+	 */
+	KCSAN_COUNTER_ENCODING_FALSE_POSITIVES,
+
+	KCSAN_COUNTER_COUNT, /* number of counters */
+};
+
+/*
+ * Increment/decrement counter with given id; avoid calling these in fast-path.
+ */
+extern void kcsan_counter_inc(enum kcsan_counter_id id);
+extern void kcsan_counter_dec(enum kcsan_counter_id id);
+
+/*
+ * Returns true if data races in the function symbol that maps to func_addr
+ * (offsets are ignored) should *not* be reported.
+ */
+extern bool kcsan_skip_report_debugfs(unsigned long func_addr);
+
+enum kcsan_report_type {
+	/*
+	 * The thread that set up the watchpoint and briefly stalled was
+	 * signalled that another thread triggered the watchpoint.
+	 */
+	KCSAN_REPORT_RACE_SIGNAL,
+
+	/*
+	 * A thread found and consumed a matching watchpoint.
+	 */
+	KCSAN_REPORT_CONSUMED_WATCHPOINT,
+
+	/*
+	 * No other thread was observed to race with the access, but the data
+	 * value before and after the stall differs.
+	 */
+	KCSAN_REPORT_RACE_UNKNOWN_ORIGIN,
+};
+
+/*
+ * Print a race report from thread that encountered the race.
+ */
+extern void kcsan_report(const volatile void *ptr, size_t size, bool is_write,
+			 bool value_change, int cpu_id, enum kcsan_report_type type);
+
+#endif /* _KERNEL_KCSAN_KCSAN_H */
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
new file mode 100644
index 000000000000..0eea05a3135b
--- /dev/null
+++ b/kernel/kcsan/report.c
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/preempt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/stacktrace.h>
+
+#include "kcsan.h"
+#include "encoding.h"
+
+/*
+ * Max. number of stack entries to show in the report.
+ */
+#define NUM_STACK_ENTRIES 64
+
+/*
+ * Other thread info: communicated from other racing thread to thread that set
+ * up the watchpoint, which then prints the complete report atomically. Only
+ * need one struct, as all threads should to be serialized regardless to print
+ * the reports, with reporting being in the slow-path.
+ */
+static struct {
+	const volatile void	*ptr;
+	size_t			size;
+	bool			is_write;
+	int			task_pid;
+	int			cpu_id;
+	unsigned long		stack_entries[NUM_STACK_ENTRIES];
+	int			num_stack_entries;
+} other_info = { .ptr = NULL };
+
+/*
+ * This spinlock protects reporting and other_info, since other_info is usually
+ * required when reporting.
+ */
+static DEFINE_SPINLOCK(report_lock);
+
+/*
+ * Special rules to skip reporting.
+ */
+static bool
+skip_report(bool is_write, bool value_change, unsigned long top_frame)
+{
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) && is_write &&
+	    !value_change) {
+		/*
+		 * The access is a write, but the data value did not change.
+		 *
+		 * We opt-out of this filter for certain functions at request of
+		 * maintainers.
+		 */
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%ps", (void *)top_frame);
+		if (!strnstr(buf, "rcu_", sizeof(buf)) &&
+		    !strnstr(buf, "_rcu", sizeof(buf)) &&
+		    !strnstr(buf, "_srcu", sizeof(buf)))
+			return true;
+	}
+
+	return kcsan_skip_report_debugfs(top_frame);
+}
+
+static inline const char *get_access_type(bool is_write)
+{
+	return is_write ? "write" : "read";
+}
+
+/* Return thread description: in task or interrupt. */
+static const char *get_thread_desc(int task_id)
+{
+	if (task_id != -1) {
+		static char buf[32]; /* safe: protected by report_lock */
+
+		snprintf(buf, sizeof(buf), "task %i", task_id);
+		return buf;
+	}
+	return "interrupt";
+}
+
+/* Helper to skip KCSAN-related functions in stack-trace. */
+static int get_stack_skipnr(unsigned long stack_entries[], int num_entries)
+{
+	char buf[64];
+	int skip = 0;
+
+	for (; skip < num_entries; ++skip) {
+		snprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skip]);
+		if (!strnstr(buf, "csan_", sizeof(buf)) &&
+		    !strnstr(buf, "tsan_", sizeof(buf)) &&
+		    !strnstr(buf, "_once_size", sizeof(buf))) {
+			break;
+		}
+	}
+	return skip;
+}
+
+/* Compares symbolized strings of addr1 and addr2. */
+static int sym_strcmp(void *addr1, void *addr2)
+{
+	char buf1[64];
+	char buf2[64];
+
+	snprintf(buf1, sizeof(buf1), "%pS", addr1);
+	snprintf(buf2, sizeof(buf2), "%pS", addr2);
+
+	return strncmp(buf1, buf2, sizeof(buf1));
+}
+
+/*
+ * Returns true if a report was generated, false otherwise.
+ */
+static bool print_report(const volatile void *ptr, size_t size, bool is_write,
+			 bool value_change, int cpu_id,
+			 enum kcsan_report_type type)
+{
+	unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
+	int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
+	int skipnr = get_stack_skipnr(stack_entries, num_stack_entries);
+	int other_skipnr;
+
+	/*
+	 * Must check report filter rules before starting to print.
+	 */
+	if (skip_report(is_write, true, stack_entries[skipnr]))
+		return false;
+
+	if (type == KCSAN_REPORT_RACE_SIGNAL) {
+		other_skipnr = get_stack_skipnr(other_info.stack_entries,
+						other_info.num_stack_entries);
+
+		/* @value_change is only known for the other thread */
+		if (skip_report(other_info.is_write, value_change,
+				other_info.stack_entries[other_skipnr]))
+			return false;
+	}
+
+	/* Print report header. */
+	pr_err("==================================================================\n");
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL: {
+		void *this_fn = (void *)stack_entries[skipnr];
+		void *other_fn = (void *)other_info.stack_entries[other_skipnr];
+		int cmp;
+
+		/*
+		 * Order functions lexographically for consistent bug titles.
+		 * Do not print offset of functions to keep title short.
+		 */
+		cmp = sym_strcmp(other_fn, this_fn);
+		pr_err("BUG: KCSAN: data-race in %ps / %ps\n",
+		       cmp < 0 ? other_fn : this_fn,
+		       cmp < 0 ? this_fn : other_fn);
+	} break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("BUG: KCSAN: data-race in %pS\n",
+		       (void *)stack_entries[skipnr]);
+		break;
+
+	default:
+		BUG();
+	}
+
+	pr_err("\n");
+
+	/* Print information about the racing accesses. */
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL:
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(other_info.is_write), other_info.ptr,
+		       other_info.size, get_thread_desc(other_info.task_pid),
+		       other_info.cpu_id);
+
+		/* Print the other thread's stack trace. */
+		stack_trace_print(other_info.stack_entries + other_skipnr,
+				  other_info.num_stack_entries - other_skipnr,
+				  0);
+
+		pr_err("\n");
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(is_write), ptr, size,
+		       get_thread_desc(in_task() ? task_pid_nr(current) : -1),
+		       cpu_id);
+		break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("race at unknown origin, with %s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(is_write), ptr, size,
+		       get_thread_desc(in_task() ? task_pid_nr(current) : -1),
+		       cpu_id);
+		break;
+
+	default:
+		BUG();
+	}
+	/* Print stack trace of this thread. */
+	stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr,
+			  0);
+
+	/* Print report footer. */
+	pr_err("\n");
+	pr_err("Reported by Kernel Concurrency Sanitizer on:\n");
+	dump_stack_print_info(KERN_DEFAULT);
+	pr_err("==================================================================\n");
+
+	return true;
+}
+
+static void release_report(unsigned long *flags, enum kcsan_report_type type)
+{
+	if (type == KCSAN_REPORT_RACE_SIGNAL)
+		other_info.ptr = NULL; /* mark for reuse */
+
+	spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/*
+ * Depending on the report type either sets other_info and returns false, or
+ * acquires the matching other_info and returns true. If other_info is not
+ * required for the report type, simply acquires report_lock and returns true.
+ */
+static bool prepare_report(unsigned long *flags, const volatile void *ptr,
+			   size_t size, bool is_write, int cpu_id,
+			   enum kcsan_report_type type)
+{
+	if (type != KCSAN_REPORT_CONSUMED_WATCHPOINT &&
+	    type != KCSAN_REPORT_RACE_SIGNAL) {
+		/* other_info not required; just acquire report_lock */
+		spin_lock_irqsave(&report_lock, *flags);
+		return true;
+	}
+
+retry:
+	spin_lock_irqsave(&report_lock, *flags);
+
+	switch (type) {
+	case KCSAN_REPORT_CONSUMED_WATCHPOINT:
+		if (other_info.ptr != NULL)
+			break; /* still in use, retry */
+
+		other_info.ptr			= ptr;
+		other_info.size			= size;
+		other_info.is_write		= is_write;
+		other_info.task_pid		= in_task() ? task_pid_nr(current) : -1;
+		other_info.cpu_id		= cpu_id;
+		other_info.num_stack_entries	= stack_trace_save(other_info.stack_entries, NUM_STACK_ENTRIES, 1);
+
+		spin_unlock_irqrestore(&report_lock, *flags);
+
+		/*
+		 * The other thread will print the summary; other_info may now
+		 * be consumed.
+		 */
+		return false;
+
+	case KCSAN_REPORT_RACE_SIGNAL:
+		if (other_info.ptr == NULL)
+			break; /* no data available yet, retry */
+
+		/*
+		 * First check if this is the other_info we are expecting, i.e.
+		 * matches based on how watchpoint was encoded.
+		 */
+		if (!matching_access((unsigned long)other_info.ptr &
+					     WATCHPOINT_ADDR_MASK,
+				     other_info.size,
+				     (unsigned long)ptr & WATCHPOINT_ADDR_MASK,
+				     size))
+			break; /* mismatching watchpoint, retry */
+
+		if (!matching_access((unsigned long)other_info.ptr,
+				     other_info.size, (unsigned long)ptr,
+				     size)) {
+			/*
+			 * If the actual accesses to not match, this was a false
+			 * positive due to watchpoint encoding.
+			 */
+			kcsan_counter_inc(
+				KCSAN_COUNTER_ENCODING_FALSE_POSITIVES);
+
+			/* discard this other_info */
+			release_report(flags, KCSAN_REPORT_RACE_SIGNAL);
+			return false;
+		}
+
+		/*
+		 * Matching & usable access in other_info: keep other_info_lock
+		 * locked, as this thread consumes it to print the full report;
+		 * unlocked in release_report.
+		 */
+		return true;
+
+	default:
+		BUG();
+	}
+
+	spin_unlock_irqrestore(&report_lock, *flags);
+
+	goto retry;
+}
+
+void kcsan_report(const volatile void *ptr, size_t size, bool is_write,
+		  bool value_change, int cpu_id, enum kcsan_report_type type)
+{
+	unsigned long flags = 0;
+
+	kcsan_disable_current();
+	if (prepare_report(&flags, ptr, size, is_write, cpu_id, type)) {
+		if (print_report(ptr, size, is_write, value_change, cpu_id, type) && panic_on_warn)
+			panic("panic_on_warn set ...\n");
+
+		release_report(&flags, type);
+	}
+	kcsan_enable_current();
+}
diff --git a/kernel/kcsan/test.c b/kernel/kcsan/test.c
new file mode 100644
index 000000000000..cc6000239dc0
--- /dev/null
+++ b/kernel/kcsan/test.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/types.h>
+
+#include "encoding.h"
+
+#define ITERS_PER_TEST 2000
+
+/* Test requirements. */
+static bool test_requires(void)
+{
+	/* random should be initialized for the below tests */
+	return prandom_u32() + prandom_u32() != 0;
+}
+
+/*
+ * Test watchpoint encode and decode: check that encoding some access's info,
+ * and then subsequent decode preserves the access's info.
+ */
+static bool test_encode_decode(void)
+{
+	int i;
+
+	for (i = 0; i < ITERS_PER_TEST; ++i) {
+		size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1;
+		bool is_write = !!prandom_u32_max(2);
+		unsigned long addr;
+
+		prandom_bytes(&addr, sizeof(addr));
+		if (WARN_ON(!check_encodable(addr, size)))
+			return false;
+
+		/* Encode and decode */
+		{
+			const long encoded_watchpoint =
+				encode_watchpoint(addr, size, is_write);
+			unsigned long verif_masked_addr;
+			size_t verif_size;
+			bool verif_is_write;
+
+			/* Check special watchpoints */
+			if (WARN_ON(decode_watchpoint(
+				    INVALID_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(decode_watchpoint(
+				    CONSUMED_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+
+			/* Check decoding watchpoint returns same data */
+			if (WARN_ON(!decode_watchpoint(
+				    encoded_watchpoint, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(verif_masked_addr !=
+				    (addr & WATCHPOINT_ADDR_MASK)))
+				goto fail;
+			if (WARN_ON(verif_size != size))
+				goto fail;
+			if (WARN_ON(is_write != verif_is_write))
+				goto fail;
+
+			continue;
+fail:
+			pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n",
+			       __func__, is_write ? "write" : "read", size,
+			       addr, encoded_watchpoint,
+			       verif_is_write ? "write" : "read", verif_size,
+			       verif_masked_addr);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/* Test access matching function. */
+static bool test_matching_access(void)
+{
+	if (WARN_ON(!matching_access(10, 1, 10, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 2, 11, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 1, 9, 2)))
+		return false;
+	if (WARN_ON(matching_access(10, 1, 11, 1)))
+		return false;
+	if (WARN_ON(matching_access(9, 1, 10, 1)))
+		return false;
+	return true;
+}
+
+static int __init kcsan_selftest(void)
+{
+	int passed = 0;
+	int total = 0;
+
+#define RUN_TEST(do_test)                                                      \
+	do {                                                                   \
+		++total;                                                       \
+		if (do_test())                                                 \
+			++passed;                                              \
+		else                                                           \
+			pr_err("KCSAN selftest: " #do_test " failed");         \
+	} while (0)
+
+	RUN_TEST(test_requires);
+	RUN_TEST(test_encode_decode);
+	RUN_TEST(test_matching_access);
+
+	pr_info("KCSAN selftest: %d/%d tests passed\n", passed, total);
+	if (passed != total)
+		panic("KCSAN selftests failed");
+	return 0;
+}
+postcore_initcall(kcsan_selftest);
diff --git a/kernel/module.c b/kernel/module.c
index 3a486f826224..cb6250be6ee9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2031,49 +2031,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-/* Iterate through all modules and set each module's text as RW */
-void set_all_modules_text_rw(void)
-{
-	struct module *mod;
-
-	if (!rodata_enabled)
-		return;
-
-	mutex_lock(&module_mutex);
-	list_for_each_entry_rcu(mod, &modules, list) {
-		if (mod->state == MODULE_STATE_UNFORMED)
-			continue;
-
-		frob_text(&mod->core_layout, set_memory_rw);
-		frob_text(&mod->init_layout, set_memory_rw);
-	}
-	mutex_unlock(&module_mutex);
-}
-
-/* Iterate through all modules and set each module's text as RO */
-void set_all_modules_text_ro(void)
-{
-	struct module *mod;
-
-	if (!rodata_enabled)
-		return;
-
-	mutex_lock(&module_mutex);
-	list_for_each_entry_rcu(mod, &modules, list) {
-		/*
-		 * Ignore going modules since it's possible that ro
-		 * protection has already been disabled, otherwise we'll
-		 * run into protection faults at module deallocation.
-		 */
-		if (mod->state == MODULE_STATE_UNFORMED ||
-			mod->state == MODULE_STATE_GOING)
-			continue;
-
-		frob_text(&mod->core_layout, set_memory_ro);
-		frob_text(&mod->init_layout, set_memory_ro);
-	}
-	mutex_unlock(&module_mutex);
-}
 #else /* !CONFIG_STRICT_MODULE_RWX */
 static void module_enable_nx(const struct module *mod) { }
 #endif /*  CONFIG_STRICT_MODULE_RWX */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c8be5a0f5259..1ef6f75d92f1 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2961,7 +2961,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work)
 
 static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
 	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
+	.flags = ATOMIC_INIT(IRQ_WORK_LAZY),
 };
 
 void wake_up_klogd(void)
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 21fb5a5662b5..5fc9c9b70862 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -7,6 +7,12 @@ endif
 # that is not a function of syscall inputs. E.g. involuntary context switches.
 KCOV_INSTRUMENT := n
 
+# There are numerous data races here, however, most of them are due to plain accesses.
+# This would make it even harder for syzbot to find reproducers, because these
+# bugs trigger without specific input. Disable by default, but should re-enable
+# eventually.
+KCSAN_SANITIZE := n
+
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
 # needed for x86 only.  Why this used to be enabled for all architectures is beyond
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 9e20873148c6..8de90ea31280 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	timer->state = HRTIMER_STATE_ENQUEUED;
+	/* Pairs with the lockless read in hrtimer_is_queued() */
+	WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED);
 
 	return timerqueue_add(&base->active, &timer->node);
 }
@@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer,
 	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
 	u8 state = timer->state;
 
-	timer->state = newstate;
+	/* Pairs with the lockless read in hrtimer_is_queued() */
+	WRITE_ONCE(timer->state, newstate);
 	if (!(state & HRTIMER_STATE_ENQUEUED))
 		return;
 
@@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer,
 static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
-	if (hrtimer_is_queued(timer)) {
-		u8 state = timer->state;
+	u8 state = timer->state;
+
+	if (state & HRTIMER_STATE_ENQUEUED) {
 		int reprogram;
 
 		/*
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 58e312e7380f..082568f610f3 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -179,7 +179,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 		return error;
 
 	if (tz) {
-		/* Verify we're witin the +-15 hrs range */
+		/* Verify we're within the +-15 hrs range */
 		if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
 			return -EINVAL;
 
@@ -548,18 +548,21 @@ EXPORT_SYMBOL(set_normalized_timespec64);
  */
 struct timespec64 ns_to_timespec64(const s64 nsec)
 {
-	struct timespec64 ts;
+	struct timespec64 ts = { 0, 0 };
 	s32 rem;
 
-	if (!nsec)
-		return (struct timespec64) {0, 0};
-
-	ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
-	if (unlikely(rem < 0)) {
-		ts.tv_sec--;
-		rem += NSEC_PER_SEC;
+	if (likely(nsec > 0)) {
+		ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+		ts.tv_nsec = rem;
+	} else if (nsec < 0) {
+		/*
+		 * With negative times, tv_sec points to the earlier
+		 * second, and tv_nsec counts the nanoseconds since
+		 * then, so tv_nsec is always a positive number.
+		 */
+		ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1;
+		ts.tv_nsec = NSEC_PER_SEC - rem - 1;
 	}
-	ts.tv_nsec = rem;
 
 	return ts;
 }
@@ -879,7 +882,7 @@ int get_timespec64(struct timespec64 *ts,
 	ts->tv_sec = kts.tv_sec;
 
 	/* Zero out the padding for 32 bit systems or in compat mode */
-	if (in_compat_syscall())
+	if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
 		kts.tv_nsec &= 0xFFFFFFFFUL;
 
 	ts->tv_nsec = kts.tv_nsec;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ffc91d4935ac..e5ef4ae9edb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -739,7 +739,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig)
 			return -EINVAL;
 
 		work = this_cpu_ptr(&send_signal_work);
-		if (work->irq_work.flags & IRQ_WORK_BUSY)
+		if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY)
 			return -EBUSY;
 
 		/* Add the current task, which is the target of sending signal,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ca7fccafbcbb..7372e87f7f75 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -52,6 +52,9 @@ enum trace_type {
 #undef __field
 #define __field(type, item)		type	item;
 
+#undef __field_fn
+#define __field_fn(type, item)		type	item;
+
 #undef __field_struct
 #define __field_struct(type, item)	__field(type, item)
 
@@ -71,26 +74,22 @@ enum trace_type {
 #define F_STRUCT(args...)		args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
 	struct struct_name {						\
 		struct trace_entry	ent;				\
 		tstruct							\
 	}
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
 
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
-			 filter, regfn) \
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter)
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	regfn)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
 
 #undef FTRACE_ENTRY_PACKED
-#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print,	\
-			    filter)					\
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter) __packed
+#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed
 
 #include "trace_entries.h"
 
@@ -1916,17 +1915,15 @@ extern void tracing_log_err(struct trace_array *tr,
 #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str))
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)	\
 	extern struct trace_event_call					\
 	__aligned(4) event_##call;
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
-	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter)
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)	\
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #undef FTRACE_ENTRY_PACKED
-#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \
-	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter)
+#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 
 #include "trace_entries.h"
 
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index fc8e97328e54..3e9d81608284 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -61,15 +61,13 @@ FTRACE_ENTRY_REG(function, ftrace_entry,
 	TRACE_FN,
 
 	F_STRUCT(
-		__field(	unsigned long,	ip		)
-		__field(	unsigned long,	parent_ip	)
+		__field_fn(	unsigned long,	ip		)
+		__field_fn(	unsigned long,	parent_ip	)
 	),
 
 	F_printk(" %ps <-- %ps",
 		 (void *)__entry->ip, (void *)__entry->parent_ip),
 
-	FILTER_TRACE_FN,
-
 	perf_ftrace_event_register
 );
 
@@ -84,9 +82,7 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 		__field_desc(	int,		graph_ent,	depth		)
 	),
 
-	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth),
-
-	FILTER_OTHER
+	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
 );
 
 /* Function return entry */
@@ -97,18 +93,16 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
 		__field_desc(	unsigned long,	ret,		func	)
+		__field_desc(	unsigned long,	ret,		overrun	)
 		__field_desc(	unsigned long long, ret,	calltime)
 		__field_desc(	unsigned long long, ret,	rettime	)
-		__field_desc(	unsigned long,	ret,		overrun	)
 		__field_desc(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
 		 (void *)__entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
-		 __entry->depth),
-
-	FILTER_OTHER
+		 __entry->depth)
 );
 
 /*
@@ -137,9 +131,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu),
-
-	FILTER_OTHER
+		 __entry->next_cpu)
 );
 
 /*
@@ -157,9 +149,7 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu),
-
-	FILTER_OTHER
+		 __entry->next_cpu)
 );
 
 /*
@@ -183,9 +173,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 		 (void *)__entry->caller[0], (void *)__entry->caller[1],
 		 (void *)__entry->caller[2], (void *)__entry->caller[3],
 		 (void *)__entry->caller[4], (void *)__entry->caller[5],
-		 (void *)__entry->caller[6], (void *)__entry->caller[7]),
-
-	FILTER_OTHER
+		 (void *)__entry->caller[6], (void *)__entry->caller[7])
 );
 
 FTRACE_ENTRY(user_stack, userstack_entry,
@@ -203,9 +191,7 @@ FTRACE_ENTRY(user_stack, userstack_entry,
 		 (void *)__entry->caller[0], (void *)__entry->caller[1],
 		 (void *)__entry->caller[2], (void *)__entry->caller[3],
 		 (void *)__entry->caller[4], (void *)__entry->caller[5],
-		 (void *)__entry->caller[6], (void *)__entry->caller[7]),
-
-	FILTER_OTHER
+		 (void *)__entry->caller[6], (void *)__entry->caller[7])
 );
 
 /*
@@ -222,9 +208,7 @@ FTRACE_ENTRY(bprint, bprint_entry,
 	),
 
 	F_printk("%ps: %s",
-		 (void *)__entry->ip, __entry->fmt),
-
-	FILTER_OTHER
+		 (void *)__entry->ip, __entry->fmt)
 );
 
 FTRACE_ENTRY_REG(print, print_entry,
@@ -239,8 +223,6 @@ FTRACE_ENTRY_REG(print, print_entry,
 	F_printk("%ps: %s",
 		 (void *)__entry->ip, __entry->buf),
 
-	FILTER_OTHER,
-
 	ftrace_event_register
 );
 
@@ -254,9 +236,7 @@ FTRACE_ENTRY(raw_data, raw_data_entry,
 	),
 
 	F_printk("id:%04x %08x",
-		 __entry->id, (int)__entry->buf[0]),
-
-	FILTER_OTHER
+		 __entry->id, (int)__entry->buf[0])
 );
 
 FTRACE_ENTRY(bputs, bputs_entry,
@@ -269,9 +249,7 @@ FTRACE_ENTRY(bputs, bputs_entry,
 	),
 
 	F_printk("%ps: %s",
-		 (void *)__entry->ip, __entry->str),
-
-	FILTER_OTHER
+		 (void *)__entry->ip, __entry->str)
 );
 
 FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@@ -283,16 +261,14 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
 		__field_desc(	resource_size_t, rw,	phys	)
 		__field_desc(	unsigned long,	rw,	value	)
 		__field_desc(	unsigned long,	rw,	pc	)
-		__field_desc(	int, 		rw,	map_id	)
+		__field_desc(	int,		rw,	map_id	)
 		__field_desc(	unsigned char,	rw,	opcode	)
 		__field_desc(	unsigned char,	rw,	width	)
 	),
 
 	F_printk("%lx %lx %lx %d %x %x",
 		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
-		 __entry->map_id, __entry->opcode, __entry->width),
-
-	FILTER_OTHER
+		 __entry->map_id, __entry->opcode, __entry->width)
 );
 
 FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@@ -304,15 +280,13 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
 		__field_desc(	resource_size_t, map,	phys	)
 		__field_desc(	unsigned long,	map,	virt	)
 		__field_desc(	unsigned long,	map,	len	)
-		__field_desc(	int, 		map,	map_id	)
+		__field_desc(	int,		map,	map_id	)
 		__field_desc(	unsigned char,	map,	opcode	)
 	),
 
 	F_printk("%lx %lx %lx %d %x",
 		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
-		 __entry->map_id, __entry->opcode),
-
-	FILTER_OTHER
+		 __entry->map_id, __entry->opcode)
 );
 
 
@@ -334,9 +308,7 @@ FTRACE_ENTRY(branch, trace_branch,
 	F_printk("%u:%s:%s (%u)%s",
 		 __entry->line,
 		 __entry->func, __entry->file, __entry->correct,
-		 __entry->constant ? " CONSTANT" : ""),
-
-	FILTER_OTHER
+		 __entry->constant ? " CONSTANT" : "")
 );
 
 
@@ -362,7 +334,5 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
 		 __entry->duration,
 		 __entry->outer_duration,
 		 __entry->nmi_total_ts,
-		 __entry->nmi_count),
-
-	FILTER_OTHER
+		 __entry->nmi_count)
 );
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6b3a69e9aa6a..ae0f0bc30828 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -24,6 +24,7 @@
 #include <linux/delay.h>
 
 #include <trace/events/sched.h>
+#include <trace/syscall.h>
 
 #include <asm/setup.h>
 
@@ -2017,7 +2018,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	 */
 	head = trace_get_fields(call);
 	if (list_empty(head)) {
-		ret = call->class->define_fields(call);
+		struct trace_event_fields *field = call->class->fields_array;
+		unsigned int offset = sizeof(struct trace_entry);
+
+		for (; field->type; field++) {
+			if (field->type == TRACE_FUNCTION_TYPE) {
+				ret = field->define_fields(call);
+				break;
+			}
+
+			offset = ALIGN(offset, field->align);
+			ret = trace_define_field(call, field->type, field->name,
+						 offset, field->size,
+						 field->is_signed, field->filter_type);
+			if (ret)
+				break;
+
+			offset += field->size;
+		}
 		if (ret < 0) {
 			pr_warn("Could not initialize trace point events/%s\n",
 				name);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f49d1a36d3ae..23b0195ac977 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1135,6 +1135,12 @@ static struct synth_event *find_synth_event(const char *name)
 	return NULL;
 }
 
+static struct trace_event_fields synth_event_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = synth_event_define_fields },
+	{}
+};
+
 static int register_synth_event(struct synth_event *event)
 {
 	struct trace_event_call *call = &event->call;
@@ -1156,7 +1162,7 @@ static int register_synth_event(struct synth_event *event)
 
 	INIT_LIST_HEAD(&call->class->fields);
 	call->event.funcs = &synth_event_funcs;
-	call->class->define_fields = synth_event_define_fields;
+	call->class->fields_array = synth_event_fields_array;
 
 	ret = register_trace_event(&call->event);
 	if (!ret) {
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 2e6d2e9741cc..77ce5a3b6773 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -29,10 +29,8 @@ static int ftrace_event_register(struct trace_event_call *call,
  * function and thus become accesible via perf.
  */
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
-			 filter, regfn) \
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter)
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
 
 /* not needed for this file */
 #undef __field_struct
@@ -41,6 +39,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __field
 #define __field(type, item)				type item;
 
+#undef __field_fn
+#define __field_fn(type, item)				type item;
+
 #undef __field_desc
 #define __field_desc(type, container, item)		type item;
 
@@ -60,7 +61,7 @@ static int ftrace_event_register(struct trace_event_call *call,
 #define F_printk(fmt, args...) fmt, args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
 struct ____ftrace_##name {						\
 	tstruct								\
 };									\
@@ -73,76 +74,46 @@ static void __always_unused ____ftrace_check_##name(void)		\
 }
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter)	\
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
-		     filter)
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)		\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
 
 #include "trace_entries.h"
 
+#undef __field_ext
+#define __field_ext(_type, _item, _filter_type) {			\
+	.type = #_type, .name = #_item,					\
+	.size = sizeof(_type), .align = __alignof__(_type),		\
+	is_signed_type(_type), .filter_type = _filter_type },
+
 #undef __field
-#define __field(type, item)						\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item),			\
-				 is_signed_type(type), filter_type);	\
-	if (ret)							\
-		return ret;
+#define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER)
+
+#undef __field_fn
+#define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN)
 
 #undef __field_desc
-#define __field_desc(type, container, item)	\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field),		\
-					  container.item),		\
-				 sizeof(field.container.item),		\
-				 is_signed_type(type), filter_type);	\
-	if (ret)							\
-		return ret;
+#define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER)
 
 #undef __array
-#define __array(type, item, len)					\
-	do {								\
-		char *type_str = #type"["__stringify(len)"]";		\
-		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		ret = trace_define_field(event_call, type_str, #item,	\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item),			\
-				 is_signed_type(type), filter_type);	\
-		if (ret)						\
-			return ret;					\
-	} while (0);
+#define __array(_type, _item, _len) {					\
+	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
+	.size = sizeof(_type[_len]), .align = __alignof__(_type),	\
+	is_signed_type(_type), .filter_type = FILTER_OTHER },
 
 #undef __array_desc
-#define __array_desc(type, container, item, len)			\
-	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
-				 offsetof(typeof(field),		\
-					  container.item),		\
-				 sizeof(field.container.item),		\
-				 is_signed_type(type), filter_type);	\
-	if (ret)							\
-		return ret;
+#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
 
 #undef __dynamic_array
-#define __dynamic_array(type, item)					\
-	ret = trace_define_field(event_call, #type "[]", #item,  \
-				 offsetof(typeof(field), item),		\
-				 0, is_signed_type(type), filter_type);\
-	if (ret)							\
-		return ret;
+#define __dynamic_array(_type, _item) {					\
+	.type = #_type "[]", .name = #_item,				\
+	.size = 0, .align = __alignof__(_type),				\
+	is_signed_type(_type), .filter_type = FILTER_OTHER },
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
-static int __init							\
-ftrace_define_fields_##name(struct trace_event_call *event_call)	\
-{									\
-	struct struct_name field;					\
-	int ret;							\
-	int filter_type = filter;					\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
+static struct trace_event_fields ftrace_event_fields_##name[] = {	\
+	tstruct								\
+	{} };
 
 #include "trace_entries.h"
 
@@ -152,6 +123,9 @@ ftrace_define_fields_##name(struct trace_event_call *event_call)	\
 #undef __field
 #define __field(type, item)
 
+#undef __field_fn
+#define __field_fn(type, item)
+
 #undef __field_desc
 #define __field_desc(type, container, item)
 
@@ -168,12 +142,10 @@ ftrace_define_fields_##name(struct trace_event_call *event_call)	\
 #define F_printk(fmt, args...) __stringify(fmt) ", "  __stringify(args)
 
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
-			 regfn)						\
-									\
+#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \
 static struct trace_event_class __refdata event_class_ftrace_##call = {	\
 	.system			= __stringify(TRACE_SYSTEM),		\
-	.define_fields		= ftrace_define_fields_##call,		\
+	.fields_array		= ftrace_event_fields_##call,		\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
 	.reg			= regfn,				\
 };									\
@@ -191,9 +163,9 @@ static struct trace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter)	\
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
 	FTRACE_ENTRY_REG(call, struct_name, etype,			\
-			 PARAMS(tstruct), PARAMS(print), filter, NULL)
+			 PARAMS(tstruct), PARAMS(print), NULL)
 
 bool ftrace_event_is_function(struct trace_event_call *call)
 {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7f890262c8a3..cbdc4f4e64c7 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1555,16 +1555,28 @@ static struct trace_event_functions kprobe_funcs = {
 	.trace		= print_kprobe_event
 };
 
+static struct trace_event_fields kretprobe_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = kretprobe_event_define_fields },
+	{}
+};
+
+static struct trace_event_fields kprobe_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = kprobe_event_define_fields },
+	{}
+};
+
 static inline void init_trace_event_call(struct trace_kprobe *tk)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tk->tp);
 
 	if (trace_kprobe_is_return(tk)) {
 		call->event.funcs = &kretprobe_funcs;
-		call->class->define_fields = kretprobe_event_define_fields;
+		call->class->fields_array = kretprobe_fields_array;
 	} else {
 		call->event.funcs = &kprobe_funcs;
-		call->class->define_fields = kprobe_event_define_fields;
+		call->class->fields_array = kprobe_fields_array;
 	}
 
 	call->flags = TRACE_EVENT_FL_KPROBE;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 16fa218556fa..73140d80dd46 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -203,11 +203,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 
 extern char *__bad_type_size(void);
 
-#define SYSCALL_FIELD(type, field, name)				\
-	sizeof(type) != sizeof(trace.field) ?				\
-		__bad_type_size() :					\
-		#type, #name, offsetof(typeof(trace), field),		\
-		sizeof(trace.field), is_signed_type(type)
+#define SYSCALL_FIELD(_type, _name) {					\
+	.type = #_type, .name = #_name,					\
+	.size = sizeof(_type), .align = __alignof__(_type),		\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }
 
 static int __init
 __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
@@ -274,42 +273,22 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call)
 {
 	struct syscall_trace_enter trace;
 	struct syscall_metadata *meta = call->data;
-	int ret;
-	int i;
 	int offset = offsetof(typeof(trace), args);
-
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
-				 FILTER_OTHER);
-	if (ret)
-		return ret;
+	int ret, i;
 
 	for (i = 0; i < meta->nb_args; i++) {
 		ret = trace_define_field(call, meta->types[i],
 					 meta->args[i], offset,
 					 sizeof(unsigned long), 0,
 					 FILTER_OTHER);
+		if (ret)
+			break;
 		offset += sizeof(unsigned long);
 	}
 
 	return ret;
 }
 
-static int __init syscall_exit_define_fields(struct trace_event_call *call)
-{
-	struct syscall_trace_exit trace;
-	int ret;
-
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
-				 FILTER_OTHER);
-	if (ret)
-		return ret;
-
-	ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
-				 FILTER_OTHER);
-
-	return ret;
-}
-
 static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 {
 	struct trace_array *tr = data;
@@ -507,6 +486,13 @@ static int __init init_syscall_trace(struct trace_event_call *call)
 	return id;
 }
 
+static struct trace_event_fields __refdata syscall_enter_fields_array[] = {
+	SYSCALL_FIELD(int, __syscall_nr),
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = syscall_enter_define_fields },
+	{}
+};
+
 struct trace_event_functions enter_syscall_print_funcs = {
 	.trace		= print_syscall_enter,
 };
@@ -518,7 +504,7 @@ struct trace_event_functions exit_syscall_print_funcs = {
 struct trace_event_class __refdata event_class_syscall_enter = {
 	.system		= "syscalls",
 	.reg		= syscall_enter_register,
-	.define_fields	= syscall_enter_define_fields,
+	.fields_array	= syscall_enter_fields_array,
 	.get_fields	= syscall_get_enter_fields,
 	.raw_init	= init_syscall_trace,
 };
@@ -526,7 +512,11 @@ struct trace_event_class __refdata event_class_syscall_enter = {
 struct trace_event_class __refdata event_class_syscall_exit = {
 	.system		= "syscalls",
 	.reg		= syscall_exit_register,
-	.define_fields	= syscall_exit_define_fields,
+	.fields_array	= (struct trace_event_fields[]){
+		SYSCALL_FIELD(int, __syscall_nr),
+		SYSCALL_FIELD(long, ret),
+		{}
+	},
 	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
 	.raw_init	= init_syscall_trace,
 };
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 352073d36585..476a382f1f1b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1507,12 +1507,17 @@ static struct trace_event_functions uprobe_funcs = {
 	.trace		= print_uprobe_event
 };
 
+static struct trace_event_fields uprobe_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = uprobe_event_define_fields },
+	{}
+};
+
 static inline void init_trace_event_call(struct trace_uprobe *tu)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tu->tp);
-
 	call->event.funcs = &uprobe_funcs;
-	call->class->define_fields = uprobe_event_define_fields;
+	call->class->fields_array = uprobe_fields_array;
 
 	call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY;
 	call->class->reg = trace_uprobe_register;