Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 818 insertions, 0 deletions

diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
new file mode 100644
index 000000000..330aee1c1
--- /dev/null
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -0,0 +1,818 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace task wakeup timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ *
+ *  Copyright (C) 2004-2006 Ingo Molnar
+ *  Copyright (C) 2004 Nadia Yvette Chambers
+ */
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
+#include <trace/events/sched.h>
+#include "trace.h"
+
+static struct trace_array	*wakeup_trace;
+static int __read_mostly	tracer_enabled;
+
+static struct task_struct	*wakeup_task;
+static int			wakeup_cpu;
+static int			wakeup_current_cpu;
+static unsigned			wakeup_prio = -1;
+static bool			wakeup_rt;
+static bool			wakeup_dl;
+static bool			tracing_dl;
+
+static arch_spinlock_t wakeup_lock =
+	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+static void wakeup_reset(struct trace_array *tr);
+static void __wakeup_reset(struct trace_array *tr);
+static int start_func_tracer(struct trace_array *tr, int graph);
+static void stop_func_tracer(struct trace_array *tr, int graph);
+
+static int save_flags;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+# define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH)
+#else
+# define is_graph(tr) false
+#endif
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static bool function_enabled;
+
+/*
+ * Prologue for the wakeup function tracers.
+ *
+ * Returns 1 if it is OK to continue, and preemption
+ *            is disabled and data->disabled is incremented.
+ *         0 if the trace is to be ignored, and preemption
+ *            is not disabled and data->disabled is
+ *            kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
+ */
+static int
+func_prolog_preempt_disable(struct trace_array *tr,
+			    struct trace_array_cpu **data,
+			    unsigned int *trace_ctx)
+{
+	long disabled;
+	int cpu;
+
+	if (likely(!wakeup_task))
+		return 0;
+
+	*trace_ctx = tracing_gen_ctx();
+	preempt_disable_notrace();
+
+	cpu = raw_smp_processor_id();
+	if (cpu != wakeup_current_cpu)
+		goto out_enable;
+
+	*data = per_cpu_ptr(tr->array_buffer.data, cpu);
+	disabled = atomic_inc_return(&(*data)->disabled);
+	if (unlikely(disabled != 1))
+		goto out;
+
+	return 1;
+
+out:
+	atomic_dec(&(*data)->disabled);
+
+out_enable:
+	preempt_enable_notrace();
+	return 0;
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+static int wakeup_display_graph(struct trace_array *tr, int set)
+{
+	if (!(is_graph(tr) ^ set))
+		return 0;
+
+	stop_func_tracer(tr, !set);
+
+	wakeup_reset(wakeup_trace);
+	tr->max_latency = 0;
+
+	return start_func_tracer(tr, set);
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned int trace_ctx;
+	int ret = 0;
+
+	if (ftrace_graph_ignore_func(trace))
+		return 0;
+	/*
+	 * Do not trace a function if it's filtered by set_graph_notrace.
+	 * Make the index of ret stack negative to indicate that it should
+	 * ignore further functions.  But it needs its own ret stack entry
+	 * to recover the original index in order to continue tracing after
+	 * returning from the function.
+	 */
+	if (ftrace_graph_notrace_addr(trace->func))
+		return 1;
+
+	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
+		return 0;
+
+	ret = __trace_graph_entry(tr, trace, trace_ctx);
+	atomic_dec(&data->disabled);
+	preempt_enable_notrace();
+
+	return ret;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned int trace_ctx;
+
+	ftrace_graph_addr_finish(trace);
+
+	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
+		return;
+
+	__trace_graph_return(tr, trace, trace_ctx);
+	atomic_dec(&data->disabled);
+
+	preempt_enable_notrace();
+	return;
+}
+
+static struct fgraph_ops fgraph_wakeup_ops = {
+	.entryfunc = &wakeup_graph_entry,
+	.retfunc = &wakeup_graph_return,
+};
+
+static void wakeup_trace_open(struct trace_iterator *iter)
+{
+	if (is_graph(iter->tr))
+		graph_trace_open(iter);
+}
+
+static void wakeup_trace_close(struct trace_iterator *iter)
+{
+	if (iter->private)
+		graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \
+			    TRACE_GRAPH_PRINT_CPU |  \
+			    TRACE_GRAPH_PRINT_REL_TIME | \
+			    TRACE_GRAPH_PRINT_DURATION | \
+			    TRACE_GRAPH_PRINT_OVERHEAD | \
+			    TRACE_GRAPH_PRINT_IRQS)
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	/*
+	 * In graph mode call the graph tracer output function,
+	 * otherwise go with the TRACE_FN event handler
+	 */
+	if (is_graph(iter->tr))
+		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_print_header(struct seq_file *s)
+{
+	if (is_graph(wakeup_trace))
+		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+	else
+		trace_default_header(s);
+}
+#endif /* else CONFIG_FUNCTION_GRAPH_TRACER */
+
+/*
+ * wakeup uses its own tracer function to keep the overhead down:
+ */
+static void
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+		   struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	unsigned int trace_ctx;
+
+	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
+		return;
+
+	local_irq_save(flags);
+	trace_function(tr, ip, parent_ip, trace_ctx);
+	local_irq_restore(flags);
+
+	atomic_dec(&data->disabled);
+	preempt_enable_notrace();
+}
+
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
+{
+	int ret;
+
+	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+	if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION)))
+		return 0;
+
+	if (graph)
+		ret = register_ftrace_graph(&fgraph_wakeup_ops);
+	else
+		ret = register_ftrace_function(tr->ops);
+
+	if (!ret)
+		function_enabled = true;
+
+	return ret;
+}
+
+static void unregister_wakeup_function(struct trace_array *tr, int graph)
+{
+	if (!function_enabled)
+		return;
+
+	if (graph)
+		unregister_ftrace_graph(&fgraph_wakeup_ops);
+	else
+		unregister_ftrace_function(tr->ops);
+
+	function_enabled = false;
+}
+
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	if (!(mask & TRACE_ITER_FUNCTION))
+		return 0;
+
+	if (set)
+		register_wakeup_function(tr, is_graph(tr), 1);
+	else
+		unregister_wakeup_function(tr, is_graph(tr));
+	return 1;
+}
+#else /* CONFIG_FUNCTION_TRACER */
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
+{
+	return 0;
+}
+static void unregister_wakeup_function(struct trace_array *tr, int graph) { }
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	return 0;
+}
+#endif /* else CONFIG_FUNCTION_TRACER */
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter) { }
+static void wakeup_trace_close(struct trace_iterator *iter) { }
+
+static void wakeup_print_header(struct seq_file *s)
+{
+	trace_default_header(s);
+}
+#endif /* !CONFIG_FUNCTION_GRAPH_TRACER */
+
+static void
+__trace_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long parent_ip,
+		 unsigned int trace_ctx)
+{
+	if (is_graph(tr))
+		trace_graph_function(tr, ip, parent_ip, trace_ctx);
+	else
+		trace_function(tr, ip, parent_ip, trace_ctx);
+}
+
+static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
+{
+	struct tracer *tracer = tr->current_trace;
+
+	if (wakeup_function_set(tr, mask, set))
+		return 0;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (mask & TRACE_ITER_DISPLAY_GRAPH)
+		return wakeup_display_graph(tr, set);
+#endif
+
+	return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_func_tracer(struct trace_array *tr, int graph)
+{
+	int ret;
+
+	ret = register_wakeup_function(tr, graph, 0);
+
+	if (!ret && tracing_is_enabled())
+		tracer_enabled = 1;
+	else
+		tracer_enabled = 0;
+
+	return ret;
+}
+
+static void stop_func_tracer(struct trace_array *tr, int graph)
+{
+	tracer_enabled = 0;
+
+	unregister_wakeup_function(tr, graph);
+}
+
+/*
+ * Should this new latency be reported/recorded?
+ */
+static bool report_latency(struct trace_array *tr, u64 delta)
+{
+	if (tracing_thresh) {
+		if (delta < tracing_thresh)
+			return false;
+	} else {
+		if (delta <= tr->max_latency)
+			return false;
+	}
+	return true;
+}
+
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
+{
+	if (task != wakeup_task)
+		return;
+
+	wakeup_current_cpu = cpu;
+}
+
+static void
+tracing_sched_switch_trace(struct trace_array *tr,
+			   struct task_struct *prev,
+			   struct task_struct *next,
+			   unsigned int trace_ctx)
+{
+	struct trace_event_call *call = &event_context_switch;
+	struct trace_buffer *buffer = tr->array_buffer.buffer;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+					  sizeof(*entry), trace_ctx);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= prev->pid;
+	entry->prev_prio		= prev->prio;
+	entry->prev_state		= task_state_index(prev);
+	entry->next_pid			= next->pid;
+	entry->next_prio		= next->prio;
+	entry->next_state		= task_state_index(next);
+	entry->next_cpu	= task_cpu(next);
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+}
+
+static void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned int trace_ctx)
+{
+	struct trace_event_call *call = &event_wakeup;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+	struct trace_buffer *buffer = tr->array_buffer.buffer;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+					  sizeof(*entry), trace_ctx);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= curr->pid;
+	entry->prev_prio		= curr->prio;
+	entry->prev_state		= task_state_index(curr);
+	entry->next_pid			= wakee->pid;
+	entry->next_prio		= wakee->prio;
+	entry->next_state		= task_state_index(wakee);
+	entry->next_cpu			= task_cpu(wakee);
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+}
+
+static void notrace
+probe_wakeup_sched_switch(void *ignore, bool preempt,
+			  struct task_struct *prev, struct task_struct *next,
+			  unsigned int prev_state)
+{
+	struct trace_array_cpu *data;
+	u64 T0, T1, delta;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	unsigned int trace_ctx;
+
+	tracing_record_cmdline(prev);
+
+	if (unlikely(!tracer_enabled))
+		return;
+
+	/*
+	 * When we start a new trace, we set wakeup_task to NULL
+	 * and then set tracer_enabled = 1. We want to make sure
+	 * that another CPU does not see the tracer_enabled = 1
+	 * and the wakeup_task with an older task, that might
+	 * actually be the same as next.
+	 */
+	smp_rmb();
+
+	if (next != wakeup_task)
+		return;
+
+	/* disable local data, not wakeup_cpu data */
+	cpu = raw_smp_processor_id();
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	if (likely(disabled != 1))
+		goto out;
+
+	local_irq_save(flags);
+	trace_ctx = tracing_gen_ctx_flags(flags);
+
+	arch_spin_lock(&wakeup_lock);
+
+	/* We could race with grabbing wakeup_lock */
+	if (unlikely(!tracer_enabled || next != wakeup_task))
+		goto out_unlock;
+
+	/* The task we are waiting for is waking up */
+	data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu);
+
+	__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, trace_ctx);
+	tracing_sched_switch_trace(wakeup_trace, prev, next, trace_ctx);
+	__trace_stack(wakeup_trace, trace_ctx, 0);
+
+	T0 = data->preempt_timestamp;
+	T1 = ftrace_now(cpu);
+	delta = T1-T0;
+
+	if (!report_latency(wakeup_trace, delta))
+		goto out_unlock;
+
+	if (likely(!is_tracing_stopped())) {
+		wakeup_trace->max_latency = delta;
+		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu, NULL);
+	}
+
+out_unlock:
+	__wakeup_reset(wakeup_trace);
+	arch_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
+out:
+	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+}
+
+static void __wakeup_reset(struct trace_array *tr)
+{
+	wakeup_cpu = -1;
+	wakeup_prio = -1;
+	tracing_dl = false;
+
+	if (wakeup_task)
+		put_task_struct(wakeup_task);
+
+	wakeup_task = NULL;
+}
+
+static void wakeup_reset(struct trace_array *tr)
+{
+	unsigned long flags;
+
+	tracing_reset_online_cpus(&tr->array_buffer);
+
+	local_irq_save(flags);
+	arch_spin_lock(&wakeup_lock);
+	__wakeup_reset(tr);
+	arch_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
+}
+
+static void
+probe_wakeup(void *ignore, struct task_struct *p)
+{
+	struct trace_array_cpu *data;
+	int cpu = smp_processor_id();
+	long disabled;
+	unsigned int trace_ctx;
+
+	if (likely(!tracer_enabled))
+		return;
+
+	tracing_record_cmdline(p);
+	tracing_record_cmdline(current);
+
+	/*
+	 * Semantic is like this:
+	 *  - wakeup tracer handles all tasks in the system, independently
+	 *    from their scheduling class;
+	 *  - wakeup_rt tracer handles tasks belonging to sched_dl and
+	 *    sched_rt class;
+	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
+	 */
+	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
+		return;
+
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	if (unlikely(disabled != 1))
+		goto out;
+
+	trace_ctx = tracing_gen_ctx();
+
+	/* interrupts should be off from try_to_wake_up */
+	arch_spin_lock(&wakeup_lock);
+
+	/* check for races. */
+	if (!tracer_enabled || tracing_dl ||
+	    (!dl_task(p) && p->prio >= wakeup_prio))
+		goto out_locked;
+
+	/* reset the trace */
+	__wakeup_reset(wakeup_trace);
+
+	wakeup_cpu = task_cpu(p);
+	wakeup_current_cpu = wakeup_cpu;
+	wakeup_prio = p->prio;
+
+	/*
+	 * Once you start tracing a -deadline task, don't bother tracing
+	 * another task until the first one wakes up.
+	 */
+	if (dl_task(p))
+		tracing_dl = true;
+	else
+		tracing_dl = false;
+
+	wakeup_task = get_task_struct(p);
+
+	data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu);
+	data->preempt_timestamp = ftrace_now(cpu);
+	tracing_sched_wakeup_trace(wakeup_trace, p, current, trace_ctx);
+	__trace_stack(wakeup_trace, trace_ctx, 0);
+
+	/*
+	 * We must be careful in using CALLER_ADDR2. But since wake_up
+	 * is not called by an assembly function  (where as schedule is)
+	 * it should be safe to use it here.
+	 */
+	__trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, trace_ctx);
+
+out_locked:
+	arch_spin_unlock(&wakeup_lock);
+out:
+	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+}
+
+static void start_wakeup_tracer(struct trace_array *tr)
+{
+	int ret;
+
+	ret = register_trace_sched_wakeup(probe_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup\n");
+		return;
+	}
+
+	ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup_new\n");
+		goto fail_deprobe;
+	}
+
+	ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+	if (ret) {
+		pr_info("sched trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_switch\n");
+		goto fail_deprobe_wake_new;
+	}
+
+	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_migrate_task\n");
+		goto fail_deprobe_sched_switch;
+	}
+
+	wakeup_reset(tr);
+
+	/*
+	 * Don't let the tracer_enabled = 1 show up before
+	 * the wakeup_task is reset. This may be overkill since
+	 * wakeup_reset does a spin_unlock after setting the
+	 * wakeup_task to NULL, but I want to be safe.
+	 * This is a slow path anyway.
+	 */
+	smp_wmb();
+
+	if (start_func_tracer(tr, is_graph(tr)))
+		printk(KERN_ERR "failed to start wakeup tracer\n");
+
+	return;
+fail_deprobe_sched_switch:
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+fail_deprobe_wake_new:
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+fail_deprobe:
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
+}
+
+static void stop_wakeup_tracer(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+	stop_func_tracer(tr, is_graph(tr));
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
+	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
+}
+
+static bool wakeup_busy;
+
+static int __wakeup_tracer_init(struct trace_array *tr)
+{
+	save_flags = tr->trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
+
+	tr->max_latency = 0;
+	wakeup_trace = tr;
+	ftrace_init_array_ops(tr, wakeup_tracer_call);
+	start_wakeup_tracer(tr);
+
+	wakeup_busy = true;
+	return 0;
+}
+
+static int wakeup_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = false;
+	wakeup_rt = false;
+	return __wakeup_tracer_init(tr);
+}
+
+static int wakeup_rt_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = false;
+	wakeup_rt = true;
+	return __wakeup_tracer_init(tr);
+}
+
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = true;
+	wakeup_rt = false;
+	return __wakeup_tracer_init(tr);
+}
+
+static void wakeup_tracer_reset(struct trace_array *tr)
+{
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
+	stop_wakeup_tracer(tr);
+	/* make sure we put back any tasks we are tracing */
+	wakeup_reset(tr);
+
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	ftrace_reset_array_ops(tr);
+	wakeup_busy = false;
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+	wakeup_reset(tr);
+	tracer_enabled = 1;
+}
+
+static void wakeup_tracer_stop(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+}
+
+static struct tracer wakeup_tracer __read_mostly =
+{
+	.name		= "wakeup",
+	.init		= wakeup_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+static struct tracer wakeup_rt_tracer __read_mostly =
+{
+	.name		= "wakeup_rt",
+	.init		= wakeup_rt_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+	.name		= "wakeup_dl",
+	.init		= wakeup_dl_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+__init static int init_wakeup_tracer(void)
+{
+	int ret;
+
+	ret = register_tracer(&wakeup_tracer);
+	if (ret)
+		return ret;
+
+	ret = register_tracer(&wakeup_rt_tracer);
+	if (ret)
+		return ret;
+
+	ret = register_tracer(&wakeup_dl_tracer);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+core_initcall(init_wakeup_tracer);