Merge tag 'perf-urgent-for-mingo-5.5-20191216' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes:

perf top:

 Arnaldo Carvalho de Melo:

 - Do not bail out when perf_env__read_cpuid() returns ENOSYS, which
   has been reported happening on aarch64.

perf metricgroup:

  Kajol Jain:

  - Fix printing event names of metric group with multiple events

vendor events:

x86:

  Ravi Bangoria:

  - Fix Kernel_Utilization metric.

s390:

  Ed Maste:

  - Fix counter long description for DTLB1_GPAGE_WRITES and L1D_RO_EXCL_WRITES.

perf header:

  Michael Petlan:

  - Fix false warning when there are no duplicate cache entries

libtraceevent:

  Sudip Mukherjee:

  - Allow custom libdir path

API headers:

  Arnaldo Carvalho de Melo:

  - Sync linux/kvm.h with the kernel sources.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

29 files changed, 1032 insertions, 154 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index f0902a7bd1b3..f2cc0d118a0b 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -130,7 +130,7 @@ $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE
 $(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz
 
 quiet_cmd_genikh = CHK     $(obj)/kheaders_data.tar.xz
-      cmd_genikh = $(BASH) $(srctree)/kernel/gen_kheaders.sh $@
+      cmd_genikh = $(CONFIG_SHELL) $(srctree)/kernel/gen_kheaders.sh $@
 $(obj)/kheaders_data.tar.xz: FORCE
 	$(call cmd,genikh)
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 40efde5eedcb..7d40da240891 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3463,6 +3463,7 @@ enum {
 	__ctx_convert##_id,
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
+	__ctx_convert_unused, /* to avoid empty enum in extreme .config */
 };
 static u8 bpf_ctx_convert_map[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
@@ -3976,8 +3977,10 @@ static int __get_type_size(struct btf *btf, u32 btf_id,
 	t = btf_type_by_id(btf, btf_id);
 	while (t && btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
-	if (!t)
+	if (!t) {
+		*bad_type = btf->types[0];
 		return -EINVAL;
+	}
 	if (btf_type_is_ptr(t))
 		/* kernel size of pointer. Not BPF's size of pointer*/
 		return sizeof(void *);
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/bpf/verifier.c b/kernel/bpf/verifier.c
index a0482e1c4a77..034ef81f935b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9636,7 +9636,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				ret = -EINVAL;
 				goto out;
 			}
-			addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
+			if (subprog == 0)
+				addr = (long) tgt_prog->bpf_func;
+			else
+				addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
 		} else {
 			addr = kallsyms_lookup_name(tname);
 			if (!addr) {
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index d47bd40fc0f5..d14cbc83986a 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -178,7 +178,7 @@ bool dma_in_atomic_pool(void *start, size_t size)
 	if (unlikely(!atomic_pool))
 		return false;
 
-	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+	return gen_pool_has_addr(atomic_pool, (unsigned long)start, size);
 }
 
 void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
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/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 5a0fc0b0403a..e13ca842eb7e 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
 # This script generates an archive consisting of kernel headers
@@ -21,30 +21,38 @@ arch/$SRCARCH/include/
 # Uncomment it for debugging.
 # if [ ! -f /tmp/iter ]; then iter=1; echo 1 > /tmp/iter;
 # else iter=$(($(cat /tmp/iter) + 1)); echo $iter > /tmp/iter; fi
-# find $src_file_list -name "*.h" | xargs ls -l > /tmp/src-ls-$iter
-# find $obj_file_list -name "*.h" | xargs ls -l > /tmp/obj-ls-$iter
+# find $all_dirs -name "*.h" | xargs ls -l > /tmp/ls-$iter
+
+all_dirs=
+if [ "$building_out_of_srctree" ]; then
+	for d in $dir_list; do
+		all_dirs="$all_dirs $srctree/$d"
+	done
+fi
+all_dirs="$all_dirs $dir_list"
 
 # include/generated/compile.h is ignored because it is touched even when none
-# of the source files changed. This causes pointless regeneration, so let us
-# ignore them for md5 calculation.
-pushd $srctree > /dev/null
-src_files_md5="$(find $dir_list -name "*.h"			   |
-		grep -v "include/generated/compile.h"		   |
-		grep -v "include/generated/autoconf.h"		   |
-		xargs ls -l | md5sum | cut -d ' ' -f1)"
-popd > /dev/null
-obj_files_md5="$(find $dir_list -name "*.h"			   |
-		grep -v "include/generated/compile.h"		   |
-		grep -v "include/generated/autoconf.h"		   |
+# of the source files changed.
+#
+# When Kconfig regenerates include/generated/autoconf.h, its timestamp is
+# updated, but the contents might be still the same. When any CONFIG option is
+# changed, Kconfig touches the corresponding timestamp file include/config/*.h.
+# Hence, the md5sum detects the configuration change anyway. We do not need to
+# check include/generated/autoconf.h explicitly.
+#
+# Ignore them for md5 calculation to avoid pointless regeneration.
+headers_md5="$(find $all_dirs -name "*.h"			|
+		grep -v "include/generated/compile.h"	|
+		grep -v "include/generated/autoconf.h"	|
 		xargs ls -l | md5sum | cut -d ' ' -f1)"
+
 # Any changes to this script will also cause a rebuild of the archive.
 this_file_md5="$(ls -l $sfile | md5sum | cut -d ' ' -f1)"
 if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi
 if [ -f kernel/kheaders.md5 ] &&
-	[ "$(cat kernel/kheaders.md5|head -1)" == "$src_files_md5" ] &&
-	[ "$(cat kernel/kheaders.md5|head -2|tail -1)" == "$obj_files_md5" ] &&
-	[ "$(cat kernel/kheaders.md5|head -3|tail -1)" == "$this_file_md5" ] &&
-	[ "$(cat kernel/kheaders.md5|tail -1)" == "$tarfile_md5" ]; then
+	[ "$(head -n 1 kernel/kheaders.md5)" = "$headers_md5" ] &&
+	[ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] &&
+	[ "$(tail -n 1 kernel/kheaders.md5)" = "$tarfile_md5" ]; then
 		exit
 fi
 
@@ -55,14 +63,17 @@ fi
 rm -rf $cpio_dir
 mkdir $cpio_dir
 
-pushd $srctree > /dev/null
-for f in $dir_list;
-	do find "$f" -name "*.h";
-done | cpio --quiet -pd $cpio_dir
-popd > /dev/null
+if [ "$building_out_of_srctree" ]; then
+	(
+		cd $srctree
+		for f in $dir_list
+			do find "$f" -name "*.h";
+		done | cpio --quiet -pd $cpio_dir
+	)
+fi
 
-# The second CPIO can complain if files already exist which can
-# happen with out of tree builds. Just silence CPIO for now.
+# The second CPIO can complain if files already exist which can happen with out
+# of tree builds having stale headers in srctree. Just silence CPIO for now.
 for f in $dir_list;
 	do find "$f" -name "*.h";
 done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1
@@ -79,8 +90,7 @@ find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \
     --owner=0 --group=0 --numeric-owner --no-recursion \
     -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null
 
-echo "$src_files_md5" >  kernel/kheaders.md5
-echo "$obj_files_md5" >> kernel/kheaders.md5
+echo $headers_md5 > kernel/kheaders.md5
 echo "$this_file_md5" >> kernel/kheaders.md5
 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5
 
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/kcov.c b/kernel/kcov.c
index 2ee38727844a..f50354202dbe 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/hashtable.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/preempt.h>
@@ -21,8 +22,11 @@
 #include <linux/uaccess.h>
 #include <linux/kcov.h>
 #include <linux/refcount.h>
+#include <linux/log2.h>
 #include <asm/setup.h>
 
+#define kcov_debug(fmt, ...) pr_debug("%s: " fmt, __func__, ##__VA_ARGS__)
+
 /* Number of 64-bit words written per one comparison: */
 #define KCOV_WORDS_PER_CMP 4
 
@@ -44,19 +48,100 @@ struct kcov {
 	 * Reference counter. We keep one for:
 	 *  - opened file descriptor
 	 *  - task with enabled coverage (we can't unwire it from another task)
+	 *  - each code section for remote coverage collection
 	 */
 	refcount_t		refcount;
 	/* The lock protects mode, size, area and t. */
 	spinlock_t		lock;
 	enum kcov_mode		mode;
-	/* Size of arena (in long's for KCOV_MODE_TRACE). */
-	unsigned		size;
+	/* Size of arena (in long's). */
+	unsigned int		size;
 	/* Coverage buffer shared with user space. */
 	void			*area;
 	/* Task for which we collect coverage, or NULL. */
 	struct task_struct	*t;
+	/* Collecting coverage from remote (background) threads. */
+	bool			remote;
+	/* Size of remote area (in long's). */
+	unsigned int		remote_size;
+	/*
+	 * Sequence is incremented each time kcov is reenabled, used by
+	 * kcov_remote_stop(), see the comment there.
+	 */
+	int			sequence;
 };
 
+struct kcov_remote_area {
+	struct list_head	list;
+	unsigned int		size;
+};
+
+struct kcov_remote {
+	u64			handle;
+	struct kcov		*kcov;
+	struct hlist_node	hnode;
+};
+
+static DEFINE_SPINLOCK(kcov_remote_lock);
+static DEFINE_HASHTABLE(kcov_remote_map, 4);
+static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas);
+
+/* Must be called with kcov_remote_lock locked. */
+static struct kcov_remote *kcov_remote_find(u64 handle)
+{
+	struct kcov_remote *remote;
+
+	hash_for_each_possible(kcov_remote_map, remote, hnode, handle) {
+		if (remote->handle == handle)
+			return remote;
+	}
+	return NULL;
+}
+
+static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle)
+{
+	struct kcov_remote *remote;
+
+	if (kcov_remote_find(handle))
+		return ERR_PTR(-EEXIST);
+	remote = kmalloc(sizeof(*remote), GFP_ATOMIC);
+	if (!remote)
+		return ERR_PTR(-ENOMEM);
+	remote->handle = handle;
+	remote->kcov = kcov;
+	hash_add(kcov_remote_map, &remote->hnode, handle);
+	return remote;
+}
+
+/* Must be called with kcov_remote_lock locked. */
+static struct kcov_remote_area *kcov_remote_area_get(unsigned int size)
+{
+	struct kcov_remote_area *area;
+	struct list_head *pos;
+
+	kcov_debug("size = %u\n", size);
+	list_for_each(pos, &kcov_remote_areas) {
+		area = list_entry(pos, struct kcov_remote_area, list);
+		if (area->size == size) {
+			list_del(&area->list);
+			kcov_debug("rv = %px\n", area);
+			return area;
+		}
+	}
+	kcov_debug("rv = NULL\n");
+	return NULL;
+}
+
+/* Must be called with kcov_remote_lock locked. */
+static void kcov_remote_area_put(struct kcov_remote_area *area,
+					unsigned int size)
+{
+	kcov_debug("area = %px, size = %u\n", area, size);
+	INIT_LIST_HEAD(&area->list);
+	area->size = size;
+	list_add(&area->list, &kcov_remote_areas);
+}
+
 static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
 {
 	unsigned int mode;
@@ -73,7 +158,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru
 	 * in_interrupt() returns false (e.g. preempt_schedule_irq()).
 	 * READ_ONCE()/barrier() effectively provides load-acquire wrt
 	 * interrupts, there are paired barrier()/WRITE_ONCE() in
-	 * kcov_ioctl_locked().
+	 * kcov_start().
 	 */
 	barrier();
 	return mode == needed_mode;
@@ -227,6 +312,78 @@ void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
 EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
 #endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
 
+static void kcov_start(struct task_struct *t, unsigned int size,
+			void *area, enum kcov_mode mode, int sequence)
+{
+	kcov_debug("t = %px, size = %u, area = %px\n", t, size, area);
+	/* Cache in task struct for performance. */
+	t->kcov_size = size;
+	t->kcov_area = area;
+	/* See comment in check_kcov_mode(). */
+	barrier();
+	WRITE_ONCE(t->kcov_mode, mode);
+	t->kcov_sequence = sequence;
+}
+
+static void kcov_stop(struct task_struct *t)
+{
+	WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
+	barrier();
+	t->kcov_size = 0;
+	t->kcov_area = NULL;
+}
+
+static void kcov_task_reset(struct task_struct *t)
+{
+	kcov_stop(t);
+	t->kcov = NULL;
+	t->kcov_sequence = 0;
+	t->kcov_handle = 0;
+}
+
+void kcov_task_init(struct task_struct *t)
+{
+	kcov_task_reset(t);
+	t->kcov_handle = current->kcov_handle;
+}
+
+static void kcov_reset(struct kcov *kcov)
+{
+	kcov->t = NULL;
+	kcov->mode = KCOV_MODE_INIT;
+	kcov->remote = false;
+	kcov->remote_size = 0;
+	kcov->sequence++;
+}
+
+static void kcov_remote_reset(struct kcov *kcov)
+{
+	int bkt;
+	struct kcov_remote *remote;
+	struct hlist_node *tmp;
+
+	spin_lock(&kcov_remote_lock);
+	hash_for_each_safe(kcov_remote_map, bkt, tmp, remote, hnode) {
+		if (remote->kcov != kcov)
+			continue;
+		kcov_debug("removing handle %llx\n", remote->handle);
+		hash_del(&remote->hnode);
+		kfree(remote);
+	}
+	/* Do reset before unlock to prevent races with kcov_remote_start(). */
+	kcov_reset(kcov);
+	spin_unlock(&kcov_remote_lock);
+}
+
+static void kcov_disable(struct task_struct *t, struct kcov *kcov)
+{
+	kcov_task_reset(t);
+	if (kcov->remote)
+		kcov_remote_reset(kcov);
+	else
+		kcov_reset(kcov);
+}
+
 static void kcov_get(struct kcov *kcov)
 {
 	refcount_inc(&kcov->refcount);
@@ -235,20 +392,12 @@ static void kcov_get(struct kcov *kcov)
 static void kcov_put(struct kcov *kcov)
 {
 	if (refcount_dec_and_test(&kcov->refcount)) {
+		kcov_remote_reset(kcov);
 		vfree(kcov->area);
 		kfree(kcov);
 	}
 }
 
-void kcov_task_init(struct task_struct *t)
-{
-	WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
-	barrier();
-	t->kcov_size = 0;
-	t->kcov_area = NULL;
-	t->kcov = NULL;
-}
-
 void kcov_task_exit(struct task_struct *t)
 {
 	struct kcov *kcov;
@@ -256,15 +405,36 @@ void kcov_task_exit(struct task_struct *t)
 	kcov = t->kcov;
 	if (kcov == NULL)
 		return;
+
 	spin_lock(&kcov->lock);
+	kcov_debug("t = %px, kcov->t = %px\n", t, kcov->t);
+	/*
+	 * For KCOV_ENABLE devices we want to make sure that t->kcov->t == t,
+	 * which comes down to:
+	 *        WARN_ON(!kcov->remote && kcov->t != t);
+	 *
+	 * For KCOV_REMOTE_ENABLE devices, the exiting task is either:
+	 * 2. A remote task between kcov_remote_start() and kcov_remote_stop().
+	 *    In this case we should print a warning right away, since a task
+	 *    shouldn't be exiting when it's in a kcov coverage collection
+	 *    section. Here t points to the task that is collecting remote
+	 *    coverage, and t->kcov->t points to the thread that created the
+	 *    kcov device. Which means that to detect this case we need to
+	 *    check that t != t->kcov->t, and this gives us the following:
+	 *        WARN_ON(kcov->remote && kcov->t != t);
+	 *
+	 * 2. The task that created kcov exiting without calling KCOV_DISABLE,
+	 *    and then again we can make sure that t->kcov->t == t:
+	 *        WARN_ON(kcov->remote && kcov->t != t);
+	 *
+	 * By combining all three checks into one we get:
+	 */
 	if (WARN_ON(kcov->t != t)) {
 		spin_unlock(&kcov->lock);
 		return;
 	}
 	/* Just to not leave dangling references behind. */
-	kcov_task_init(t);
-	kcov->t = NULL;
-	kcov->mode = KCOV_MODE_INIT;
+	kcov_disable(t, kcov);
 	spin_unlock(&kcov->lock);
 	kcov_put(kcov);
 }
@@ -313,6 +483,7 @@ static int kcov_open(struct inode *inode, struct file *filep)
 	if (!kcov)
 		return -ENOMEM;
 	kcov->mode = KCOV_MODE_DISABLED;
+	kcov->sequence = 1;
 	refcount_set(&kcov->refcount, 1);
 	spin_lock_init(&kcov->lock);
 	filep->private_data = kcov;
@@ -325,6 +496,20 @@ static int kcov_close(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+static int kcov_get_mode(unsigned long arg)
+{
+	if (arg == KCOV_TRACE_PC)
+		return KCOV_MODE_TRACE_PC;
+	else if (arg == KCOV_TRACE_CMP)
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+		return KCOV_MODE_TRACE_CMP;
+#else
+		return -ENOTSUPP;
+#endif
+	else
+		return -EINVAL;
+}
+
 /*
  * Fault in a lazily-faulted vmalloc area before it can be used by
  * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the
@@ -340,14 +525,35 @@ static void kcov_fault_in_area(struct kcov *kcov)
 		READ_ONCE(area[offset]);
 }
 
+static inline bool kcov_check_handle(u64 handle, bool common_valid,
+				bool uncommon_valid, bool zero_valid)
+{
+	if (handle & ~(KCOV_SUBSYSTEM_MASK | KCOV_INSTANCE_MASK))
+		return false;
+	switch (handle & KCOV_SUBSYSTEM_MASK) {
+	case KCOV_SUBSYSTEM_COMMON:
+		return (handle & KCOV_INSTANCE_MASK) ?
+			common_valid : zero_valid;
+	case KCOV_SUBSYSTEM_USB:
+		return uncommon_valid;
+	default:
+		return false;
+	}
+	return false;
+}
+
 static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 			     unsigned long arg)
 {
 	struct task_struct *t;
 	unsigned long size, unused;
+	int mode, i;
+	struct kcov_remote_arg *remote_arg;
+	struct kcov_remote *remote;
 
 	switch (cmd) {
 	case KCOV_INIT_TRACE:
+		kcov_debug("KCOV_INIT_TRACE\n");
 		/*
 		 * Enable kcov in trace mode and setup buffer size.
 		 * Must happen before anything else.
@@ -366,6 +572,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		kcov->mode = KCOV_MODE_INIT;
 		return 0;
 	case KCOV_ENABLE:
+		kcov_debug("KCOV_ENABLE\n");
 		/*
 		 * Enable coverage for the current task.
 		 * At this point user must have been enabled trace mode,
@@ -378,29 +585,20 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		t = current;
 		if (kcov->t != NULL || t->kcov != NULL)
 			return -EBUSY;
-		if (arg == KCOV_TRACE_PC)
-			kcov->mode = KCOV_MODE_TRACE_PC;
-		else if (arg == KCOV_TRACE_CMP)
-#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
-			kcov->mode = KCOV_MODE_TRACE_CMP;
-#else
-		return -ENOTSUPP;
-#endif
-		else
-			return -EINVAL;
+		mode = kcov_get_mode(arg);
+		if (mode < 0)
+			return mode;
 		kcov_fault_in_area(kcov);
-		/* Cache in task struct for performance. */
-		t->kcov_size = kcov->size;
-		t->kcov_area = kcov->area;
-		/* See comment in check_kcov_mode(). */
-		barrier();
-		WRITE_ONCE(t->kcov_mode, kcov->mode);
+		kcov->mode = mode;
+		kcov_start(t, kcov->size, kcov->area, kcov->mode,
+				kcov->sequence);
 		t->kcov = kcov;
 		kcov->t = t;
-		/* This is put either in kcov_task_exit() or in KCOV_DISABLE. */
+		/* Put either in kcov_task_exit() or in KCOV_DISABLE. */
 		kcov_get(kcov);
 		return 0;
 	case KCOV_DISABLE:
+		kcov_debug("KCOV_DISABLE\n");
 		/* Disable coverage for the current task. */
 		unused = arg;
 		if (unused != 0 || current->kcov != kcov)
@@ -408,11 +606,65 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		t = current;
 		if (WARN_ON(kcov->t != t))
 			return -EINVAL;
-		kcov_task_init(t);
-		kcov->t = NULL;
-		kcov->mode = KCOV_MODE_INIT;
+		kcov_disable(t, kcov);
 		kcov_put(kcov);
 		return 0;
+	case KCOV_REMOTE_ENABLE:
+		kcov_debug("KCOV_REMOTE_ENABLE\n");
+		if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
+			return -EINVAL;
+		t = current;
+		if (kcov->t != NULL || t->kcov != NULL)
+			return -EBUSY;
+		remote_arg = (struct kcov_remote_arg *)arg;
+		mode = kcov_get_mode(remote_arg->trace_mode);
+		if (mode < 0)
+			return mode;
+		if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long))
+			return -EINVAL;
+		kcov->mode = mode;
+		t->kcov = kcov;
+		kcov->t = t;
+		kcov->remote = true;
+		kcov->remote_size = remote_arg->area_size;
+		spin_lock(&kcov_remote_lock);
+		for (i = 0; i < remote_arg->num_handles; i++) {
+			kcov_debug("handle %llx\n", remote_arg->handles[i]);
+			if (!kcov_check_handle(remote_arg->handles[i],
+						false, true, false)) {
+				spin_unlock(&kcov_remote_lock);
+				kcov_disable(t, kcov);
+				return -EINVAL;
+			}
+			remote = kcov_remote_add(kcov, remote_arg->handles[i]);
+			if (IS_ERR(remote)) {
+				spin_unlock(&kcov_remote_lock);
+				kcov_disable(t, kcov);
+				return PTR_ERR(remote);
+			}
+		}
+		if (remote_arg->common_handle) {
+			kcov_debug("common handle %llx\n",
+					remote_arg->common_handle);
+			if (!kcov_check_handle(remote_arg->common_handle,
+						true, false, false)) {
+				spin_unlock(&kcov_remote_lock);
+				kcov_disable(t, kcov);
+				return -EINVAL;
+			}
+			remote = kcov_remote_add(kcov,
+					remote_arg->common_handle);
+			if (IS_ERR(remote)) {
+				spin_unlock(&kcov_remote_lock);
+				kcov_disable(t, kcov);
+				return PTR_ERR(remote);
+			}
+			t->kcov_handle = remote_arg->common_handle;
+		}
+		spin_unlock(&kcov_remote_lock);
+		/* Put either in kcov_task_exit() or in KCOV_DISABLE. */
+		kcov_get(kcov);
+		return 0;
 	default:
 		return -ENOTTY;
 	}
@@ -422,11 +674,35 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
 	struct kcov *kcov;
 	int res;
+	struct kcov_remote_arg *remote_arg