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