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

Pull perf fixes from Ingo Molnar:
 "On the kernel side there's two x86 PMU driver fixes and a uprobes fix,
  plus on the tooling side there's a number of fixes and some late
  updates"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  perf sched timehist: Fix invalid period calculation
  perf sched timehist: Remove hardcoded 'comm_width' check at print_summary
  perf sched timehist: Enlarge default 'comm_width'
  perf sched timehist: Honour 'comm_width' when aligning the headers
  perf/x86: Fix overlap counter scheduling bug
  perf/x86/pebs: Fix handling of PEBS buffer overflows
  samples/bpf: Move open_raw_sock to separate header
  samples/bpf: Remove perf_event_open() declaration
  samples/bpf: Be consistent with bpf_load_program bpf_insn parameter
  tools lib bpf: Add bpf_prog_{attach,detach}
  samples/bpf: Switch over to libbpf
  perf diff: Do not overwrite valid build id
  perf annotate: Don't throw error for zero length symbols
  perf bench futex: Fix lock-pi help string
  perf trace: Check if MAP_32BIT is defined (again)
  samples/bpf: Make perf_event_read() static
  uprobes: Fix uprobes on MIPS, allow for a cache flush after ixol breakpoint creation
  samples/bpf: Make samples more libbpf-centric
  tools lib bpf: Add flags to bpf_create_map()
  tools lib bpf: use __u32 from linux/types.h
  ...

27 files changed, 865 insertions, 405 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9e5fc168c8a3..0eb0e87dbe9f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,6 +73,8 @@ enum bpf_cmd {
 	BPF_PROG_LOAD,
 	BPF_OBJ_PIN,
 	BPF_OBJ_GET,
+	BPF_PROG_ATTACH,
+	BPF_PROG_DETACH,
 };
 
 enum bpf_map_type {
@@ -85,6 +87,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_ARRAY,
 	BPF_MAP_TYPE_STACK_TRACE,
 	BPF_MAP_TYPE_CGROUP_ARRAY,
+	BPF_MAP_TYPE_LRU_HASH,
+	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 };
 
 enum bpf_prog_type {
@@ -95,8 +99,23 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SCHED_ACT,
 	BPF_PROG_TYPE_TRACEPOINT,
 	BPF_PROG_TYPE_XDP,
+	BPF_PROG_TYPE_PERF_EVENT,
+	BPF_PROG_TYPE_CGROUP_SKB,
+	BPF_PROG_TYPE_CGROUP_SOCK,
+	BPF_PROG_TYPE_LWT_IN,
+	BPF_PROG_TYPE_LWT_OUT,
+	BPF_PROG_TYPE_LWT_XMIT,
 };
 
+enum bpf_attach_type {
+	BPF_CGROUP_INET_INGRESS,
+	BPF_CGROUP_INET_EGRESS,
+	BPF_CGROUP_INET_SOCK_CREATE,
+	__MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -105,6 +124,13 @@ enum bpf_prog_type {
 #define BPF_EXIST	2 /* update existing element */
 
 #define BPF_F_NO_PREALLOC	(1U << 0)
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+#define BPF_F_NO_COMMON_LRU	(1U << 1)
 
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
@@ -140,243 +166,327 @@ union bpf_attr {
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+		__u32		target_fd;	/* container object to attach to */
+		__u32		attach_bpf_fd;	/* eBPF program to attach */
+		__u32		attach_type;
+	};
 } __attribute__((aligned(8)));
 
+/* BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(&map, &key)
+ *     Return: Map value or NULL
+ *
+ * int bpf_map_update_elem(&map, &key, &value, flags)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_map_delete_elem(&map, &key)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_probe_read(void *dst, int size, void *src)
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_ktime_get_ns(void)
+ *     Return: current ktime
+ *
+ * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
+ *     Return: length of buffer written or negative error
+ *
+ * u32 bpf_prandom_u32(void)
+ *     Return: random value
+ *
+ * u32 bpf_raw_smp_processor_id(void)
+ *     Return: SMP processor ID
+ *
+ * int bpf_skb_store_bytes(skb, offset, from, len, flags)
+ *     store bytes into packet
+ *     @skb: pointer to skb
+ *     @offset: offset within packet from skb->mac_header
+ *     @from: pointer where to copy bytes from
+ *     @len: number of bytes to store into packet
+ *     @flags: bit 0 - if true, recompute skb->csum
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_l3_csum_replace(skb, offset, from, to, flags)
+ *     recompute IP checksum
+ *     @skb: pointer to skb
+ *     @offset: offset within packet where IP checksum is located
+ *     @from: old value of header field
+ *     @to: new value of header field
+ *     @flags: bits 0-3 - size of header field
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_l4_csum_replace(skb, offset, from, to, flags)
+ *     recompute TCP/UDP checksum
+ *     @skb: pointer to skb
+ *     @offset: offset within packet where TCP/UDP checksum is located
+ *     @from: old value of header field
+ *     @to: new value of header field
+ *     @flags: bits 0-3 - size of header field
+ *             bit 4 - is pseudo header
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_tail_call(ctx, prog_array_map, index)
+ *     jump into another BPF program
+ *     @ctx: context pointer passed to next program
+ *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+ *     @index: index inside array that selects specific program to run
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_clone_redirect(skb, ifindex, flags)
+ *     redirect to another netdev
+ *     @skb: pointer to skb
+ *     @ifindex: ifindex of the net device
+ *     @flags: bit 0 - if set, redirect to ingress instead of egress
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ *     Return: current->tgid << 32 | current->pid
+ *
+ * u64 bpf_get_current_uid_gid(void)
+ *     Return: current_gid << 32 | current_uid
+ *
+ * int bpf_get_current_comm(char *buf, int size_of_buf)
+ *     stores current->comm into buf
+ *     Return: 0 on success or negative error
+ *
+ * u32 bpf_get_cgroup_classid(skb)
+ *     retrieve a proc's classid
+ *     @skb: pointer to skb
+ *     Return: classid if != 0
+ *
+ * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_vlan_pop(skb)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_get_tunnel_key(skb, key, size, flags)
+ * int bpf_skb_set_tunnel_key(skb, key, size, flags)
+ *     retrieve or populate tunnel metadata
+ *     @skb: pointer to skb
+ *     @key: pointer to 'struct bpf_tunnel_key'
+ *     @size: size of 'struct bpf_tunnel_key'
+ *     @flags: room for future extensions
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_perf_event_read(&map, index)
+ *     Return: Number events read or error code
+ *
+ * int bpf_redirect(ifindex, flags)
+ *     redirect to another netdev
+ *     @ifindex: ifindex of the net device
+ *     @flags: bit 0 - if set, redirect to ingress instead of egress
+ *             other bits - reserved
+ *     Return: TC_ACT_REDIRECT
+ *
+ * u32 bpf_get_route_realm(skb)
+ *     retrieve a dst's tclassid
+ *     @skb: pointer to skb
+ *     Return: realm if != 0
+ *
+ * int bpf_perf_event_output(ctx, map, index, data, size)
+ *     output perf raw sample
+ *     @ctx: struct pt_regs*
+ *     @map: pointer to perf_event_array map
+ *     @index: index of event in the map
+ *     @data: data on stack to be output as raw data
+ *     @size: size of data
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_get_stackid(ctx, map, flags)
+ *     walk user or kernel stack and return id
+ *     @ctx: struct pt_regs*
+ *     @map: pointer to stack_trace map
+ *     @flags: bits 0-7 - numer of stack frames to skip
+ *             bit 8 - collect user stack instead of kernel
+ *             bit 9 - compare stacks by hash only
+ *             bit 10 - if two different stacks hash into the same stackid
+ *                      discard old
+ *             other bits - reserved
+ *     Return: >= 0 stackid on success or negative error
+ *
+ * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
+ *     calculate csum diff
+ *     @from: raw from buffer
+ *     @from_size: length of from buffer
+ *     @to: raw to buffer
+ *     @to_size: length of to buffer
+ *     @seed: optional seed
+ *     Return: csum result or negative error code
+ *
+ * int bpf_skb_get_tunnel_opt(skb, opt, size)
+ *     retrieve tunnel options metadata
+ *     @skb: pointer to skb
+ *     @opt: pointer to raw tunnel option data
+ *     @size: size of @opt
+ *     Return: option size
+ *
+ * int bpf_skb_set_tunnel_opt(skb, opt, size)
+ *     populate tunnel options metadata
+ *     @skb: pointer to skb
+ *     @opt: pointer to raw tunnel option data
+ *     @size: size of @opt
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_proto(skb, proto, flags)
+ *     Change protocol of the skb. Currently supported is v4 -> v6,
+ *     v6 -> v4 transitions. The helper will also resize the skb. eBPF
+ *     program is expected to fill the new headers via skb_store_bytes
+ *     and lX_csum_replace.
+ *     @skb: pointer to skb
+ *     @proto: new skb->protocol type
+ *     @flags: reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_type(skb, type)
+ *     Change packet type of skb.
+ *     @skb: pointer to skb
+ *     @type: new skb->pkt_type type
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_under_cgroup(skb, map, index)
+ *     Check cgroup2 membership of skb
+ *     @skb: pointer to skb
+ *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ *     @index: index of the cgroup in the bpf_map
+ *     Return:
+ *       == 0 skb failed the cgroup2 descendant test
+ *       == 1 skb succeeded the cgroup2 descendant test
+ *        < 0 error
+ *
+ * u32 bpf_get_hash_recalc(skb)
+ *     Retrieve and possibly recalculate skb->hash.
+ *     @skb: pointer to skb
+ *     Return: hash
+ *
+ * u64 bpf_get_current_task(void)
+ *     Returns current task_struct
+ *     Return: current
+ *
+ * int bpf_probe_write_user(void *dst, void *src, int len)
+ *     safely attempt to write to a location
+ *     @dst: destination address in userspace
+ *     @src: source address on stack
+ *     @len: number of bytes to copy
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_current_task_under_cgroup(map, index)
+ *     Check cgroup2 membership of current task
+ *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ *     @index: index of the cgroup in the bpf_map
+ *     Return:
+ *       == 0 current failed the cgroup2 descendant test
+ *       == 1 current succeeded the cgroup2 descendant test
+ *        < 0 error
+ *
+ * int bpf_skb_change_tail(skb, len, flags)
+ *     The helper will resize the skb to the given new size, to be used f.e.
+ *     with control messages.
+ *     @skb: pointer to skb
+ *     @len: new skb length
+ *     @flags: reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_pull_data(skb, len)
+ *     The helper will pull in non-linear data in case the skb is non-linear
+ *     and not all of len are part of the linear section. Only needed for
+ *     read/write with direct packet access.
+ *     @skb: pointer to skb
+ *     @len: len to make read/writeable
+ *     Return: 0 on success or negative error
+ *
+ * s64 bpf_csum_update(skb, csum)
+ *     Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
+ *     @skb: pointer to skb
+ *     @csum: csum to add
+ *     Return: csum on success or negative error
+ *
+ * void bpf_set_hash_invalid(skb)
+ *     Invalidate current skb->hash.
+ *     @skb: pointer to skb
+ *
+ * int bpf_get_numa_node_id()
+ *     Return: Id of current NUMA node.
+ *
+ * int bpf_skb_change_head()
+ *     Grows headroom of skb and adjusts MAC header offset accordingly.
+ *     Will extends/reallocae as required automatically.
+ *     May change skb data pointer and will thus invalidate any check
+ *     performed for direct packet access.
+ *     @skb: pointer to skb
+ *     @len: length of header to be pushed in front
+ *     @flags: Flags (unused for now)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ *     Adjust the xdp_md.data by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data
+ *     Return: 0 on success or negative on error
+ */
+#define __BPF_FUNC_MAPPER(FN)		\
+	FN(unspec),			\
+	FN(map_lookup_elem),		\
+	FN(map_update_elem),		\
+	FN(map_delete_elem),		\
+	FN(probe_read),			\
+	FN(ktime_get_ns),		\
+	FN(trace_printk),		\
+	FN(get_prandom_u32),		\
+	FN(get_smp_processor_id),	\
+	FN(skb_store_bytes),		\
+	FN(l3_csum_replace),		\
+	FN(l4_csum_replace),		\
+	FN(tail_call),			\
+	FN(clone_redirect),		\
+	FN(get_current_pid_tgid),	\
+	FN(get_current_uid_gid),	\
+	FN(get_current_comm),		\
+	FN(get_cgroup_classid),		\
+	FN(skb_vlan_push),		\
+	FN(skb_vlan_pop),		\
+	FN(skb_get_tunnel_key),		\
+	FN(skb_set_tunnel_key),		\
+	FN(perf_event_read),		\
+	FN(redirect),			\
+	FN(get_route_realm),		\
+	FN(perf_event_output),		\
+	FN(skb_load_bytes),		\
+	FN(get_stackid),		\
+	FN(csum_diff),			\
+	FN(skb_get_tunnel_opt),		\
+	FN(skb_set_tunnel_opt),		\
+	FN(skb_change_proto),		\
+	FN(skb_change_type),		\
+	FN(skb_under_cgroup),		\
+	FN(get_hash_recalc),		\
+	FN(get_current_task),		\
+	FN(probe_write_user),		\
+	FN(current_task_under_cgroup),	\
+	FN(skb_change_tail),		\
+	FN(skb_pull_data),		\
+	FN(csum_update),		\
+	FN(set_hash_invalid),		\
+	FN(get_numa_node_id),		\
+	FN(skb_change_head),		\
+	FN(xdp_adjust_head),
+
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
  */
+#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
 enum bpf_func_id {
-	BPF_FUNC_unspec,
-	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
-	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
-	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
-	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
-	BPF_FUNC_ktime_get_ns,    /* u64 bpf_ktime_get_ns(void) */
-	BPF_FUNC_trace_printk,    /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
-	BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
-	BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
-
-	/**
-	 * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
-	 * @skb: pointer to skb
-	 * @offset: offset within packet from skb->mac_header
-	 * @from: pointer where to copy bytes from
-	 * @len: number of bytes to store into packet
-	 * @flags: bit 0 - if true, recompute skb->csum
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_skb_store_bytes,
-
-	/**
-	 * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
-	 * @skb: pointer to skb
-	 * @offset: offset within packet where IP checksum is located
-	 * @from: old value of header field
-	 * @to: new value of header field
-	 * @flags: bits 0-3 - size of header field
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_l3_csum_replace,
-
-	/**
-	 * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
-	 * @skb: pointer to skb
-	 * @offset: offset within packet where TCP/UDP checksum is located
-	 * @from: old value of header field
-	 * @to: new value of header field
-	 * @flags: bits 0-3 - size of header field
-	 *         bit 4 - is pseudo header
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_l4_csum_replace,
-
-	/**
-	 * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
-	 * @ctx: context pointer passed to next program
-	 * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
-	 * @index: index inside array that selects specific program to run
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_tail_call,
-
-	/**
-	 * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
-	 * @skb: pointer to skb
-	 * @ifindex: ifindex of the net device
-	 * @flags: bit 0 - if set, redirect to ingress instead of egress
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_clone_redirect,
-
-	/**
-	 * u64 bpf_get_current_pid_tgid(void)
-	 * Return: current->tgid << 32 | current->pid
-	 */
-	BPF_FUNC_get_current_pid_tgid,
-
-	/**
-	 * u64 bpf_get_current_uid_gid(void)
-	 * Return: current_gid << 32 | current_uid
-	 */
-	BPF_FUNC_get_current_uid_gid,
-
-	/**
-	 * bpf_get_current_comm(char *buf, int size_of_buf)
-	 * stores current->comm into buf
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_get_current_comm,
-
-	/**
-	 * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
-	 * @skb: pointer to skb
-	 * Return: classid if != 0
-	 */
-	BPF_FUNC_get_cgroup_classid,
-	BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
-	BPF_FUNC_skb_vlan_pop,  /* bpf_skb_vlan_pop(skb) */
-
-	/**
-	 * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
-	 * retrieve or populate tunnel metadata
-	 * @skb: pointer to skb
-	 * @key: pointer to 'struct bpf_tunnel_key'
-	 * @size: size of 'struct bpf_tunnel_key'
-	 * @flags: room for future extensions
-	 * Retrun: 0 on success
-	 */
-	BPF_FUNC_skb_get_tunnel_key,
-	BPF_FUNC_skb_set_tunnel_key,
-	BPF_FUNC_perf_event_read,	/* u64 bpf_perf_event_read(&map, index) */
-	/**
-	 * bpf_redirect(ifindex, flags) - redirect to another netdev
-	 * @ifindex: ifindex of the net device
-	 * @flags: bit 0 - if set, redirect to ingress instead of egress
-	 *         other bits - reserved
-	 * Return: TC_ACT_REDIRECT
-	 */
-	BPF_FUNC_redirect,
-
-	/**
-	 * bpf_get_route_realm(skb) - retrieve a dst's tclassid
-	 * @skb: pointer to skb
-	 * Return: realm if != 0
-	 */
-	BPF_FUNC_get_route_realm,
-
-	/**
-	 * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
-	 * @ctx: struct pt_regs*
-	 * @map: pointer to perf_event_array map
-	 * @index: index of event in the map
-	 * @data: data on stack to be output as raw data
-	 * @size: size of data
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_perf_event_output,
-	BPF_FUNC_skb_load_bytes,
-
-	/**
-	 * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
-	 * @ctx: struct pt_regs*
-	 * @map: pointer to stack_trace map
-	 * @flags: bits 0-7 - numer of stack frames to skip
-	 *         bit 8 - collect user stack instead of kernel
-	 *         bit 9 - compare stacks by hash only
-	 *         bit 10 - if two different stacks hash into the same stackid
-	 *                  discard old
-	 *         other bits - reserved
-	 * Return: >= 0 stackid on success or negative error
-	 */
-	BPF_FUNC_get_stackid,
-
-	/**
-	 * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
-	 * @from: raw from buffer
-	 * @from_size: length of from buffer
-	 * @to: raw to buffer
-	 * @to_size: length of to buffer
-	 * @seed: optional seed
-	 * Return: csum result
-	 */
-	BPF_FUNC_csum_diff,
-
-	/**
-	 * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
-	 * retrieve or populate tunnel options metadata
-	 * @skb: pointer to skb
-	 * @opt: pointer to raw tunnel option data
-	 * @size: size of @opt
-	 * Return: 0 on success for set, option size for get
-	 */
-	BPF_FUNC_skb_get_tunnel_opt,
-	BPF_FUNC_skb_set_tunnel_opt,
-
-	/**
-	 * bpf_skb_change_proto(skb, proto, flags)
-	 * Change protocol of the skb. Currently supported is
-	 * v4 -> v6, v6 -> v4 transitions. The helper will also
-	 * resize the skb. eBPF program is expected to fill the
-	 * new headers via skb_store_bytes and lX_csum_replace.
-	 * @skb: pointer to skb
-	 * @proto: new skb->protocol type
-	 * @flags: reserved
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_skb_change_proto,
-
-	/**
-	 * bpf_skb_change_type(skb, type)
-	 * Change packet type of skb.
-	 * @skb: pointer to skb
-	 * @type: new skb->pkt_type type
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_skb_change_type,
-
-	/**
-	 * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb
-	 * @skb: pointer to skb
-	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
-	 * @index: index of the cgroup in the bpf_map
-	 * Return:
-	 *   == 0 skb failed the cgroup2 descendant test
-	 *   == 1 skb succeeded the cgroup2 descendant test
-	 *    < 0 error
-	 */
-	BPF_FUNC_skb_under_cgroup,
-
-	/**
-	 * bpf_get_hash_recalc(skb)
-	 * Retrieve and possibly recalculate skb->hash.
-	 * @skb: pointer to skb
-	 * Return: hash
-	 */
-	BPF_FUNC_get_hash_recalc,
-
-	/**
-	 * u64 bpf_get_current_task(void)
-	 * Returns current task_struct
-	 * Return: current
-	 */
-	BPF_FUNC_get_current_task,
-
-	/**
-	 * bpf_probe_write_user(void *dst, void *src, int len)
-	 * safely attempt to write to a location
-	 * @dst: destination address in userspace
-	 * @src: source address on stack
-	 * @len: number of bytes to copy
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_probe_write_user,
-
+	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
 	__BPF_FUNC_MAX_ID,
 };
+#undef __BPF_ENUM_FN
 
 /* All flags used by eBPF helper functions, placed here. */
 
@@ -450,6 +560,31 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+	BPF_OK = 0,
+	/* 1 reserved */
+	BPF_DROP = 2,
+	/* 3-6 reserved */
+	BPF_REDIRECT = 7,
+	/* >127 are reserved for prog type specific return codes */
+};
+
+struct bpf_sock {
+	__u32 bound_dev_if;
+	__u32 family;
+	__u32 type;
+	__u32 protocol;
+};
+
+#define XDP_PACKET_HEADROOM 256
+
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
  * return codes are reserved for future use. Unknown return codes will result
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 8143536b462a..3ddb58a36d3c 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -54,7 +54,7 @@ static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 }
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
-		   int value_size, int max_entries)
+		   int value_size, int max_entries, __u32 map_flags)
 {
 	union bpf_attr attr;
 
@@ -64,13 +64,14 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 	attr.key_size = key_size;
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf, size_t log_buf_sz)
+		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
 {
 	int fd;
 	union bpf_attr attr;
@@ -98,7 +99,7 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 }
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags)
+			__u64 flags)
 {
 	union bpf_attr attr;
 
@@ -166,3 +167,26 @@ int bpf_obj_get(const char *pathname)
 
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
 }
+
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	   = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type   = type;
+
+	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	 = target_fd;
+	attr.attach_type = type;
+
+	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 253c3dbb06b4..a2f9853dd882 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,22 +24,25 @@
 #include <linux/bpf.h>
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries);
+		   int max_entries, __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf,
+		     __u32 kern_version, char *log_buf,
 		     size_t log_buf_sz);
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags);
+			__u64 flags);
 
 int bpf_map_lookup_elem(int fd, void *key, void *value);
 int bpf_map_delete_elem(int fd, void *key);
 int bpf_map_get_next_key(int fd, void *key, void *next_key);
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2e974593f3e8..84e6b35da4bd 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -854,7 +854,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 		*pfd = bpf_create_map(def->type,
 				      def->key_size,
 				      def->value_size,
-				      def->max_entries);
+				      def->max_entries,
+				      0);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 7775b1eb2bee..76173969ab80 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist'
 --migrations::
 	Show migration events.
 
+-I::
+--idle-hist::
+	Show idle-related events only.
+
 --time::
 	Only analyze samples within given time window: <start>,<stop>. Times
 	have the format seconds.microseconds. If start is not given (i.e., time
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e5af38eede17..8fc24824705e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -201,6 +201,7 @@ goals := $(filter-out all sub-make, $(MAKECMDGOALS))
 $(goals) all: sub-make
 
 sub-make: fixdep
+	@./check-headers.sh
 	$(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals)
 
 else # force_fixdep
@@ -404,99 +405,6 @@ export JEVENTS
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): prepare FORCE
-	@(test -f ../../include/uapi/linux/perf_event.h && ( \
-        (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
-        || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/linux/hash.h && ( \
-        (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
-        || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
-        (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
-        || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
-        (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/required-features.h && ( \
-        (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
-        (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/lib/memcpy_64.S && ( \
-        (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
-        || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/lib/memset_64.S && ( \
-        (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
-        || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
-        (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
-        (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/__fls.h && ( \
-        (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/fls.h && ( \
-        (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/fls64.h && ( \
-        (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/linux/coresight-pmu.h && ( \
-	(diff -B ../include/linux/coresight-pmu.h ../../include/linux/coresight-pmu.h >/dev/null) \
-	|| echo "Warning: tools/include/linux/coresight-pmu.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/asm-generic/mman-common.h && ( \
-	(diff -B ../include/uapi/asm-generic/mman-common.h ../../include/uapi/asm-generic/mman-common.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/asm-generic/mman.h && ( \
-	(diff -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>$$" ../include/uapi/asm-generic/mman.h ../../include/uapi/asm-generic/mman.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/asm-generic/mman.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/linux/mman.h && ( \
-	(diff -B -I "^#include <\(uapi/\)*asm/mman.h>$$" ../include/uapi/linux/mman.h ../../include/uapi/linux/mman.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(JEVENTS_IN): FORCE
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 465012b320ee..6d9d6c40a916 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -48,7 +48,7 @@ static const struct option options[] = {
 };
 
 static const char * const bench_futex_lock_pi_usage[] = {
-	"perf bench futex requeue <options>",
+	"perf bench futex lock-pi <options>",
 	NULL
 };
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 4b419631753d..f8ca7a4ebabc 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -208,7 +208,7 @@ static void compute_stats(struct c2c_hist_entry *c2c_he,
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel __maybe_unused,
+				struct perf_evsel *evsel,
 				struct machine *machine)
 {
 	struct c2c_hists *c2c_hists = &c2c.hists;
@@ -379,7 +379,7 @@ static int symbol_width(struct hists *hists, struct sort_entry *se)
 
 static int c2c_width(struct perf_hpp_fmt *fmt,
 		     struct perf_hpp *hpp __maybe_unused,
-		     struct hists *hists __maybe_unused)
+		     struct hists *hists)
 {
 	struct c2c_fmt *c2c_fmt;
 	struct c2c_dimension *dim;
@@ -1127,7 +1127,7 @@ MEAN_ENTRY(mean_lcl_entry,  lcl_hitm);
 MEAN_ENTRY(mean_load_entry, load);
 
 static int
-cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cpucnt_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;
@@ -1141,7 +1141,7 @@ cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;
@@ -1155,7 +1155,7 @@ cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_empty_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		   struct hist_entry *he)
 {
 	int width = c2c_width(fmt, hpp, he->hists);
@@ -1779,7 +1779,6 @@ static int c2c_hists__init(struct c2c_hists *hists,
 	return hpp_list__parse(&hists->list, NULL, sort);
 }
 
-__maybe_unused
 static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 			     const char *output,
 			     const char *sort)
@@ -2658,7 +2657,7 @@ out:
 	return err;
 }
 
-static int parse_record_events(const struct option *opt __maybe_unused,
+static int parse_record_events(const struct option *opt,
 			       const char *str, int unset __maybe_unused)
 {
 	bool *event_set = (bool *) opt->value;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d1ce29be560e..cd7bc4d104e2 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
-	OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"),
+	OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_END()
 	};
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fa26865364b6..74d6a035133a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1687,6 +1687,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	/* Enable ignoring missing threads when -u option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d2afbe4a240d..06cc759a4597 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -648,7 +648,7 @@ report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
 }
 
 static int
-parse_branch_mode(const struct option *opt __maybe_unused,
+parse_branch_mode(const struct option *opt,
 		  const char *str __maybe_unused, int unset)
 {
 	int *branch_mode = opt->value;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 1a3f1be93372..d53e706a6f17 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -200,6 +200,7 @@ struct perf_sched {
 	/* options for timehist command */
 	bool		summary;
 	bool		summary_only;
+	bool		idle_hist;
 	bool		show_callchain;
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
@@ -230,6 +231,15 @@ struct evsel_runtime {
 	u32 ncpu;       /* highest cpu slot allocated */
 };
 
+/* per cpu idle time data */
+struct idle_thread_runtime {
+	struct thread_runtime	tr;
+	struct thread		*last_thread;
+	struct rb_root		sorted_root;
+	struct callchain_root	callchain;
+	struct callchain_cursor	cursor;
+};
+
 /* track idle times per cpu */
 static struct thread **idle_threads;
 static int idle_max_cpu;
@@ -1765,7 +1775,7 @@ static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu)
 	return r->last_time[cpu];
 }
 
-static int comm_width = 20;
+static int comm_width = 30;
 
 static char *timehist_get_commstr(struct thread *thread)
 {
@@ -1807,7 +1817,7 @@ static void timehist_header(struct perf_sched *sched)
 		printf(" ");
 	}
 
-	printf(" %-20s  %9s  %9s  %9s",
+	printf(" %-*s  %9s  %9s  %9s", comm_width,
 		"task name", "wait time", "sch delay", "run time");
 
 	printf("\n");
@@ -1820,7 +1830,8 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	printf(" %-20s  %9s  %9s  %9s\n", "[tid/pid]", "(msec)", "(msec)", "(msec)");
+	printf(" %-*s  %9s  %9s  %9s\n", comm_width,
+	       "[tid/pid]", "(msec)", "(msec)", "(msec)");
 
 	/*
 	 * separator
@@ -1830,7 +1841,7 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %.*s ", ncpus, graph_dotted_line);
 
-	printf(" %.20s  %.9s  %.9s  %.9s",
+	printf(" %.*s  %.9s  %.9s  %.9s", comm_width,
 		graph_dotted_line, graph_dotted_line, graph_dotted_line,
 		graph_dotted_line);
 
@@ -1939,39 +1950,40 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 	r->total_run_time += r->dt_run;
 }
 
-static bool is_idle_sample(struct perf_sched *sched,
-			   struct perf_sample *sample,
-			   struct perf_evsel *evsel,
-			   struct machine *machine)
+static bool is_idle_sample(struct perf_sample *sample,
+			   struct perf_evsel *evsel)
 {
-	struct thread *thread;
-	struct callchain_cursor *cursor = &callchain_cursor;
-
 	/* pid 0 == swapper == idle task */
-	if (sample->pid == 0)
-		return true;
+	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
+		return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
 
-	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) {
-		if (perf_evsel__intval(evsel, sample, "prev_pid") == 0)
-			return true;
-	}
+	return sample->pid == 0;
+}
+
+static void save_task_callchain(struct perf_sched *sched,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct callchain_cursor *cursor = &callchain_cursor;
+	struct thread *thread;
 
 	/* want main thread for process - has maps */
 	thread = machine__findnew_thread(machine, sample->pid, sample->pid);
 	if (thread == NULL) {
 		pr_debug("Failed to get thread for pid %d.\n", sample->pid);
-		return false;
+		return;
 	}
 
 	if (!symbol_conf.use_callchain || sample->callchain == NULL)
-		return false;
+		return;
 
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, sched->max_stack + 2) != 0) {
 		if (verbose)
 			error("Failed to resolve callchain. Skipping\n");
 
-		return false;
+		return;
 	}
 
 	callchain_cursor_commit(cursor);
@@ -1994,8 +2006,24 @@ static bool is_idle_sample(struct perf_sched *sched,
 
 		callchain_cursor_advance(cursor);
 	}
+}
+
+static int init_idle_thread(struct thread *thread)
+{
+	struct idle_thread_runtime *itr;
+
+	thread__set_comm(thread, idle_comm, 0);
+
+	itr = zalloc(sizeof(*itr));
+	if (itr == NULL)
+		return -ENOMEM;
 
-	return false;
+	init_stats(&itr->tr.run_stats);
+	callchain_init(&itr->callchain);
+	callchain_cursor_reset(&itr->cursor);
+	thread__set_priv(thread, itr);
+
+	return 0;
 }
 
 /*
@@ -2004,7 +2032,7 @@ static bool is_idle_sample(struct perf_sched *sched,
  */
 static int init_idle_threads(int ncpu)
 {
-	int i;
+	int i, ret;
 
 	idle_threads = zalloc(ncpu * sizeof(struct thread *));
 	if (!idle_threads)
@@ -2018,7 +2046,9 @@ static int init_idle_threads(int ncpu)
 		if (idle_threads[i] == NULL)
 			return -ENOMEM;
 
-		thread__set_comm(idle_threads[i], idle_comm, 0);
+		ret = init_idle_thread(idle_threads[i]);
+		if (ret < 0)
+			return ret;
 	}
 
 	return 0;
@@ -2065,14 +2095,23 @@ static struct thread *get_idle_thread(int cpu)
 		idle_threads[cpu] = thread__new(0, 0);
 
 		if (idle_threads[cpu]) {
-			idle_threads[cpu]->tid = 0;
-			thread__set_comm(idle_threads[cpu], idle_comm, 0);
+			if (init_idle_thread(idle_threads[cpu]) < 0)
+				return NULL;
 		}
 	}
 
 	return idle_threads[cpu];
 }
 
+static void save_idle_callchain(struct idle_thread_runtime *itr,
+				struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
+		return;
+
+	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
+}
+
 /*
  * handle runtime stats saved per thread
  */
@@ -2111,7 +2150,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 {
 	struct thread *thread;
 
-	if (is_idle_sample(sched, sample, evsel, machine)) {
+	if (is_idle_sample(sample, evsel)) {
 		thread = get_idle_thread(sample->cpu);
 		if (thread == NULL)
 			pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
@@ -2124,13 +2163,37 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			pr_debug("Failed to get thread for tid %d. skipping sample.\n",
 				 sample->tid);
 		}
+
+		save_task_callchain(sched, sample, evsel, machine);
+		if (sched->idle_hist) {
+			struct thread *idle;
+			struct idle_thread_runtime *itr;
+
+			idle = get_idle_thread(sample->cpu);
+			if (idle == NULL) {
+				pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+				return NULL;
+			}
+
+			itr = thread__priv(idle);
+			if (itr == NULL)
+				return NULL;
+
+			itr->last_thread = thread;
+
+			/* copy task callchain when entering to idle */
+			if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+				save_idle_callchain(itr, sample);
+		}
 	}
 
 	return thread;
 }
 
 static bool timehist_skip_sample(struct perf_sched *sched,
-				 struct thread *thread)
+				 struct thread *thread,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample)
 {
 	bool rc = false;
 
@@ -2139,10 +2202,19 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 		sched->skipped_samples++;
 	}
 
+	if (sched->idle_hist) {
+		if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+			rc = true;
+		else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
+			 perf_evsel__intval(evsel, sample, "next_pid") != 0)
+			rc = true;
+	}
+
 	return rc;
 }
 
 static void timehist_print_wakeup_event(struct perf_sched *sched,
+					struct perf_evsel *evsel,
 					struct perf_sample *sample,
 					struct machine *machine,
 					struct thread *awakened)
@@ -2155,8 +2227,8 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
 		return;
 
 	/* show wakeup unless both awakee and awaker are filtered */
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, awakened)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, awakened, evsel, sample)) {
 		return;
 	}
 
@@ -2201,7 +2273,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool,
 	/* show wakeups if requested */
 	if (sched->show_wakeups &&
 	    !perf_time__skip_sample(&sched->ptime, sample->time))
-		timehist_print_wakeup_event(sched, sample, machine, thread);
+		timehist_print_wakeup_event(sched, evsel, sample, machine, thread);
 
 	return 0;
 }
@@ -2228,8 +2300,8 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 	if (thread == NULL)
 		return;
 
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, migrated)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, migrated, evsel, sample)) {
 		return;
 	}
 
@@ -2314,7 +2386,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		goto out;
 	}
 
-	if (timehist_skip_sample(sched, thread))
+	if (timehist_skip_sample(sched, thread, evsel, sample))
 		goto out;
 
 	tr = thread__get_runtime(thread);
@@ -2333,7 +2405,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	if (ptime->start && ptime->start > t)
 		goto out;
 
-	if (ptime->start > tprev)
+	if (tprev && ptime->start > tprev)
 		tprev = ptime->start;
 
 	/*
@@ -2350,7 +2422,39 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			t = ptime->end;
 	}
 
-	timehist_update_runtime_stats(tr, t, tprev);
+	if (!sched->idle_hist || thread->tid == 0) {
+		timehist_update_runtime_stats(tr, t, tprev);
+
+		if (sched->idle_hist) {
+			struct idle_thread_runtime *itr = (void *)tr;
+			struct thread_runtime *last_tr;
+
+			BUG_ON(thread->tid != 0);
+
+			if (itr->last_thread == NULL)
+				goto out;
+
+			/* add current idle time as last thread's runtime */
+			last_tr = thread__get_runtime(itr->last_thread);
+			if (last_tr == NULL)
+				goto out;
+
+			timehist_update_runtime_stats(last_tr, t, tprev);
+			/*
+			 * remove delta time of last thread as it's not updated
+			 * and otherwise it will show an invalid value next
+			 * time.  we only care total run time and run stat.
+			 */
+			last_tr->dt_run = 0;
+			last_tr->dt_wait = 0;
+			last_tr->dt_delay = 0;
+
+			if (itr->cursor.nr)
+				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
+
+			itr->last_thread = NULL;
+		}
+	}
 
 	if (!sched->summary_only)
 		timehist_print_sample(sched, sample, &al, thread, t);
@@ -2457,6 +2561,60 @@ static int show_deadthread_runtime(struct thread *t, void *priv)
 	return __show_thread_runtime(t, priv);
 }
 
+static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+	const char *sep = " <- ";
+	struct callchain_list *chain;
+	size_t ret = 0;
+	char bf[1024];
+	bool first;
+
+	if (node == NULL)
+		return 0;
+
+	ret = callchain__fprintf_folded(fp, node->parent);
+	first = (ret == 0);
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->ms.sym && chain->ms.sym->ignore)
+			continue;
+		ret += fprintf(fp, "%s%s", first ? "" : sep,
+			       callchain_list__sym_name(chain, bf, sizeof(bf),
+							false));
+		first = false;
+	}
+
+	return ret;
+}
+
+static size_t timehist_print_idlehist_callchain(struct rb_root *root)
+{
+	size_t ret = 0;
+	FILE *fp = stdout;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(root);
+
+	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
+	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
+	       graph_dotted_line);
+
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		rb_node = rb_next(rb_node);
+
+		ret += fprintf(fp, "  ");
+		print_sched_time(chain->hit, 12);
+		ret += 16;  /* print_sched_time returns 2nd arg + 4 */
+		ret += fprintf(fp, " %8d  ", chain->count);
+		ret += callchain__fprintf_folded(fp, chain);
+		ret += fprintf(fp, "\n");
+	}
+
+	return ret;
+}
+
 static void timehist_print_summary(struct perf_sched *sched,
 				   struct perf_session *session)
 {
@@ -2469,12 +2627,15 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	memset(&totals, 0, sizeof(totals));
 
-	if (comm_width < 30)
-		comm_width = 30;
-
-	printf("\nRuntime summary\n");
-	printf("%*s  parent   sched-in  ", comm_width, "comm");
-	printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
+	if (sched->idle_hist) {
+		printf("\nIdle-time summary\n");
+		printf("%*s  parent  sched-out  ", comm_width, "comm");
+		printf("  idle-time   min-idle    avg-idle    max-idle  stddev  migrations\n");
+	} else {
+		printf("\nRuntime summary\n");
+		printf("%*s  parent   sched-in  ", comm_width, "comm");
+		printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
+	}
 	printf("%*s            (count)  ", comm_width, "");
 	printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
 	printf("%.117s\n", graph_dotted_line);
@@ -2490,7 +2651,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 		printf("<no terminated tasks>\n");
 
 	/* CPU idle stats not tracked when samples were skipped */
-	if (sched->skipped_samples)
+	if (sched->skipped_samples && !sched->idle_hist)
 		return;
 
 	printf("\nIdle stats:\n");
@@ -2509,6 +2670,35 @@ static void timehist_print_summary(struct perf_sched *sched,
 			printf("    CPU %2d idle entire time window\n", i);
 	}
 
+	if (sched->idle_hist && symbol_conf.use_callchain) {
+		callchain_param.mode  = CHAIN_FOLDED;
+		callchain_param.value = CCVAL_PERIOD;
+
+		callchain_register_param(&callchain_param);
+
+		printf("\nIdle stats by callchain:\n");
+		for (i = 0; i < idle_max_cpu; ++i) {
+			struct idle_thread_runtime *itr;
+
+			t = idle_threads[i];
+			if (!t)
+				continue;
+
+			itr = thread__priv(t);
+			if (itr == NULL)
+				continue;
+
+			callchain_param.sort(&itr->sorted_root, &itr->callchain,
+					     0, &callchain_param);
+
+			printf("  CPU %2d:", i);
+			print_sched_time(itr->tr.total_run_time, 6);
+			printf(" msec\n");
+			timehist_print_idlehist_callchain(&itr->sorted_root);
+			printf("\n");
+		}
+	}
+
 	printf("\n"
 	       "    Total number of unique tasks: %" PRIu64 "\n"
 	       "Total number of context switches: %" PRIu64 "\n"
@@ -3036,6 +3226,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
 	OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
 	OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
+	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
 	OPT_PARENT(sched_options)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 688dea7cb08f..a02f2e965628 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2195,7 +2195,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+int process_stat_config_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_session *session __maybe_unused)
 {
@@ -2238,7 +2238,7 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+int process_thread_map_event(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_session *session __maybe_unused)
 {
@@ -2257,7 +2257,7 @@ int process_thread_map_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+int process_cpu_map_event(struct perf_tool *tool,
 			  union perf_event *event,
 			  struct perf_session *session __maybe_unused)
 {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
new file mode 100755
index 000000000000..c747bfd7f14d
--- /dev/null
+++ b/tools/perf/check-headers.sh
@@ -0,0 +1,59 @@
+#!/bin/sh
+
+HEADERS='
+include/uapi/linux/perf_event.h
+include/linux/hash.h
+include/uapi/linux/hw_breakpoint.h
+arch/x86/include/asm/disabled-features.h
+arch/x86/include/asm/required-features.h
+arch/x86/include/asm/cpufeatures.h
+arch/arm/include/uapi/asm/perf_regs.h
+arch/arm64/include/uapi/asm/perf_regs.h
+arch/powerpc/include/uapi/asm/perf_regs.h
+arch/x86/include/uapi/asm/perf_regs.h
+arch/x86/include/uapi/asm/kvm.h
+arch/x86/include/uapi/asm/kvm_perf.h
+arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/vmx.h
+arch/powerpc/include/uapi/asm/kvm.h
+arch/s390/include/uapi/asm/kvm.h
+arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/sie.h
+arch/arm/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/kvm.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
+include/asm-generic/bitops/__fls.h
+include/asm-generic/bitops/fls.h
+include/asm-generic/bitops/fls64.h
+include/linux/coresight-pmu.h
+include/uapi/asm-generic/mman-common.h
+'
+
+check () {
+  file=$1
+  opts=
+
+  shift
+  while [ -n "$*" ]; do
+    opts="$opts \"$1\""
+    shift
+  done
+
+  cmd="diff $opts ../$file ../../$file > /dev/null"
+
+  test -f ../../$file &&
+  eval $cmd || echo "Warning: $file differs from kernel" >&2
+}
+
+
+# simple diff check
+for i in $HEADERS; do
+  check $i -B
+done
+
+# diff with extra ignore lines
+check arch/x86/lib/memcpy_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check arch/x86/lib/memset_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
+check include/uapi/linux/mman.h       -B -I "^#include <\(uapi/\)*asm/mman.h>"
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 9a0236a4cf95..1c27d947c2fe 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -55,6 +55,7 @@ struct record_opts {
 	bool	     all_user;
 	bool	     tail_synthesize;
 	bool	     overwrite;
+	bool	     ignore_missing_thread;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 23605202d4a1..a77dcc0d24e3 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -186,6 +186,10 @@ static struct test generic_tests[] = {
 		.func = test__thread_map_synthesize,
 	},
 	{
+		.desc = "Remove thread map",
+		.func = test__thread_map_remove,
+	},
+	{
 		.desc = "Synthesize cpu map",
 		.func = test__cpu_map_synthesize,
 	},
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 0d7b251305af..a512f0c8ff5b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -80,6 +80,7 @@ const char *test__bpf_subtest_get_desc(int subtest);
 int test__bpf_subtest_get_nr(void);
 int test_session_topology(int subtest);
 int test__thread_map_synthesize(int subtest);
+int test__thread_map_remove(int subtest);
 int test__cpu_map_synthesize(int subtest);
 int test__synthesize_stat_config(int subtest);
 int test__synthesize_stat(int subtest);
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index cee2a2cdc933..a4a4b4625ac3 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,3 +1,4 @@
+#include <stdlib.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/prctl.h>
@@ -93,3 +94,46 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
 
 	return 0;
 }
+
+int test__thread_map_remove(int subtest __maybe_unused)
+{
+	struct thread_map *threads;
+	char *str;
+	int i;
+
+	TEST_ASSERT_VAL("failed to allocate map string",
+			asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
+
+	threads = thread_map__new_str(str, NULL, 0);
+
+	TEST_ASSERT_VAL("failed to allocate thread_map",
+			threads);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to remove thread",
+			!thread_map__remove(threads, 0));
+
+	TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to remove thread",
+			!thread_map__remove(threads, 0));
+
+	TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to not remove thread",
+			thread_map__remove(threads, 0));
+
+	for (i = 0; i < threads->nr; i++)
+		free(threads->map[i].comm);
+
+	free(threads);
+	return 0;
+}
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index fd710ab33684..af1cfde6b97b 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -42,7 +42,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
+#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ec7a30fad149..ba36aac340bc 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -215,7 +215,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			ui_browser__set_color(browser, color);
 		if (dl->ins.ops && dl->ins.ops->scnprintf) {
 			if (ins__is_jump(&dl->ins)) {
-				bool fwd = dl->ops.target.offset > (u64)dl->offset;
+				bool fwd = dl->ops.target.offset > dl->offset;
 
 				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
 								    SLSMG_UARROW_CHAR);
@@ -245,7 +245,8 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
 {
 	if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins)
 	    || !disasm_line__has_offset(dl)
-	    || dl->ops.target.offset >= symbol__size(sym))
+	    || dl->ops.target.offset < 0
+	    || dl->ops.target.offset >= (s64)symbol__size(sym))
 		return false;
 
 	return true;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ea7e0de4b9c1..06cc04e5806a 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -223,13 +223,19 @@ bool ins__is_call(const struct ins *ins)
 static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused)
 {
 	const char *s = strchr(ops->raw, '+');
+	const char *c = strchr(ops->raw, ',');
 
-	ops->target.addr = strtoull(ops->raw, NULL, 16);
+	if (c++ != NULL)
+		ops->target.addr = strtoull(c, NULL, 16);
+	else
+		ops->target.addr = strtoull(ops->raw, NULL, 16);
 
-	if (s++ != NULL)
+	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
-	else
-		ops->target.offset = UINT64_MAX;
+		ops->target.offset_avail = true;
+	} else {
+		ops->target.offset_avail = false;
+	}
 
 	return 0;
 }
@@ -237,7 +243,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	if (!ops->target.addr)
+	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
 	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
@@ -641,7 +647,8 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr < sym->start || addr >= sym->end) {
+	if ((addr < sym->start || addr >= sym->end) &&
+	    (addr != sym->end || sym->start != sym->end)) {
 		pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n",
 		       __func__, __LINE__, sym->name, sym->start, addr, sym->end);
 		return -ERANGE;
@@ -1205,9 +1212,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 	if (dl == NULL)
 		return -1;
 
-	if (dl->ops.target.offset == UINT64_MAX)
+	if (!disasm_line__has_offset(dl)) {
 		dl->ops.target.offset = dl->ops.target.addr -
 					map__rip_2objdump(map, sym->start);
+		dl->ops.target.offset_avail = true;
+	}
 
 	/* kcore has no symbols, so add the call target name */
 	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) {
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 87e4cadc5d27..09776b5af991 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -24,7 +24,8 @@ struct ins_operands {
 		char	*raw;
 		char	*name;
 		u64	addr;
-		u64	offset;
+		s64	offset;
+		bool	offset_avail;
 	} target;
 	union {
 		struct {
@@ -68,7 +69,7 @@ struct disasm_line {
 
 static inline bool disasm_line__has_offset(const struct disasm_line *dl)
 {
-	return dl->ops.target.offset != UINT64_MAX;
+	return dl->ops.target.offset_avail;
 }
 
 void disasm_line__free(struct disasm_line *dl);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b2365a63db45..04e536ae4d88 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -990,6 +990,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	 * it overloads any global configuration.
 	 */
 	apply_config_terms(evsel, opts);
+
+	evsel->ignore_missing_thread = opts->ignore_missing_thread;
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -1419,6 +1421,33 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
 	return fprintf(fp, "  %-32s %s\n", name, val);
 }
 
+static bool ignore_missing_thread(struct perf_evsel *evsel,
+				  struct thread_map *threads,
+				  int thread, int err)
+{
+	if (!evsel->ignore_missing_thread)
+		return false;
+
+	/* The system wide setup does not work with threads. */
+	if (evsel->system_wide)
+		return false;
+
+	/* The -ESRCH is perf event syscall errno for pid's not found. */
+	if (err != -ESRCH)
+		return false;
+
+	/* If there's only one thread, let it fail. */
+	if (threads->nr == 1)
+		return false;
+
+	if (thread_map__remove(threads, thread))
+		return false;
+
+	pr_warning("WARNING: Ignored open failure for pid %d\n",
+		   thread_map__pid(threads, thread));
+	return true;
+}
+
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
@@ -1474,7 +1503,7 @@ retry_sample_id:
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
-			int group_fd;
+			int fd, group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
 				pid = thread_map__pid(threads, thread);
@@ -1484,21 +1513,37 @@ retry_open:
 			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
 				  pid, cpus->map[cpu], group_fd, flags);
 
-			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
-								     pid,
-								     cpus->map[cpu],
-								     group_fd, flags);
-			if (FD(evsel, cpu, thread) < 0) {
+			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
+						 group_fd, flags);
+
+			FD(evsel, cpu, thread) = fd;
+
+			if (fd < 0) {
 				err = -errno;
+
+				if (ignore_missing_thread(evsel, threads, thread, err)) {
+					/*
+					 * We just removed 1 thread, so take a step
+					 * back on thread index and lower the upper
+					 * nthreads limit.
+					 */
+					nthreads--;
+					thread--;
+
+					/* ... and pretend like nothing have happened. */
+					err = 0;
+					continue;
+				}
+
 				pr_debug2("\nsys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
 
-			pr_debug2(" = %d\n", FD(evsel, cpu, thread));
+			pr_debug2(" = %d\n", fd);
 
 			if (evsel->bpf_fd >= 0) {
-				int evt_fd = FD(evsel, cpu, thread);
+				int evt_fd = fd;
 				int bpf_fd = evsel->bpf_fd;
 
 				err = ioctl(evt_fd,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6abb89cd27f9..06ef6f29efa1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -120,6 +120,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			ignore_missing_thread;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index df2482b2ba45..dc93940de351 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1459,7 +1459,8 @@ int dso__load(struct dso *dso, struct map *map)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (is_regular_file(dso->long_name) &&
+	if (!dso->has_build_id &&
+	    is_regular_file(dso->long_name) &&
 	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 40585f5b7027..f9eab200fd75 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -448,3 +448,25 @@ bool thread_map__has(struct thread_map *threads, pid_t pid)
 
 	return false;
 }
+
+int thread_map__remove(struct thread_map *threads, int idx)
+{
+	int i;
+
+	if (threads->nr < 1)
+		return -EINVAL;
+
+	if (idx >= threads->nr)
+		return -EINVAL;
+
+	/*
+	 * Free the 'idx' item and shift the rest up.
+	 */
+	free(threads->map[idx].comm);
+
+	for (i = idx; i < threads->nr - 1; i++)
+		threads->map[i] = threads->map[i + 1];
+
+	threads->nr--;
+	return 0;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index bd3b971588da..ea0ef08c6303 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -58,4 +58,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread)
 
 void thread_map__read_comms(struct thread_map *threads);
 bool thread_map__has(struct thread_map *threads, pid_t pid);
+int thread_map__remove(struct thread_map *threads, int idx);
 #endif	/* __PERF_THREAD_MAP_H */