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, 582 insertions, 0 deletions

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
new file mode 100644
index 000000000..5a48dba91
--- /dev/null
+++ b/kernel/trace/trace_stack.c
@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/security.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+
+#include "trace.h"
+
+#define STACK_TRACE_ENTRIES 500
+
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES];
+static unsigned stack_trace_index[STACK_TRACE_ENTRIES];
+
+static unsigned int stack_trace_nr_entries;
+static unsigned long stack_trace_max_size;
+static arch_spinlock_t stack_trace_max_lock =
+	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+DEFINE_PER_CPU(int, disable_stack_tracer);
+static DEFINE_MUTEX(stack_sysctl_mutex);
+
+int stack_tracer_enabled;
+
+static void print_max_stack(void)
+{
+	long i;
+	int size;
+
+	pr_emerg("        Depth    Size   Location    (%d entries)\n"
+			   "        -----    ----   --------\n",
+			   stack_trace_nr_entries);
+
+	for (i = 0; i < stack_trace_nr_entries; i++) {
+		if (i + 1 == stack_trace_nr_entries)
+			size = stack_trace_index[i];
+		else
+			size = stack_trace_index[i] - stack_trace_index[i+1];
+
+		pr_emerg("%3ld) %8d   %5d   %pS\n", i, stack_trace_index[i],
+				size, (void *)stack_dump_trace[i]);
+	}
+}
+
+/*
+ * The stack tracer looks for a maximum stack at each call from a function. It
+ * registers a callback from ftrace, and in that callback it examines the stack
+ * size. It determines the stack size from the variable passed in, which is the
+ * address of a local variable in the stack_trace_call() callback function.
+ * The stack size is calculated by the address of the local variable to the top
+ * of the current stack. If that size is smaller than the currently saved max
+ * stack size, nothing more is done.
+ *
+ * If the size of the stack is greater than the maximum recorded size, then the
+ * following algorithm takes place.
+ *
+ * For architectures (like x86) that store the function's return address before
+ * saving the function's local variables, the stack will look something like
+ * this:
+ *
+ *   [ top of stack ]
+ *    0: sys call entry frame
+ *   10: return addr to entry code
+ *   11: start of sys_foo frame
+ *   20: return addr to sys_foo
+ *   21: start of kernel_func_bar frame
+ *   30: return addr to kernel_func_bar
+ *   31: [ do trace stack here ]
+ *
+ * The save_stack_trace() is called returning all the functions it finds in the
+ * current stack. Which would be (from the bottom of the stack to the top):
+ *
+ *   return addr to kernel_func_bar
+ *   return addr to sys_foo
+ *   return addr to entry code
+ *
+ * Now to figure out how much each of these functions' local variable size is,
+ * a search of the stack is made to find these values. When a match is made, it
+ * is added to the stack_dump_trace[] array. The offset into the stack is saved
+ * in the stack_trace_index[] array. The above example would show:
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          30
+ *  return addr to sys_foo          |          20
+ *  return addr to entry            |          10
+ *
+ * The print_max_stack() function above, uses these values to print the size of
+ * each function's portion of the stack.
+ *
+ *  for (i = 0; i < nr_entries; i++) {
+ *     size = i == nr_entries - 1 ? stack_trace_index[i] :
+ *                    stack_trace_index[i] - stack_trace_index[i+1]
+ *     print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]);
+ *  }
+ *
+ * The above shows
+ *
+ *     depth size  location
+ *     ----- ----  --------
+ *  0    30   10   kernel_func_bar
+ *  1    20   10   sys_foo
+ *  2    10   10   entry code
+ *
+ * Now for architectures that might save the return address after the functions
+ * local variables (saving the link register before calling nested functions),
+ * this will cause the stack to look a little different:
+ *
+ * [ top of stack ]
+ *  0: sys call entry frame
+ * 10: start of sys_foo_frame
+ * 19: return addr to entry code << lr saved before calling kernel_func_bar
+ * 20: start of kernel_func_bar frame
+ * 29: return addr to sys_foo_frame << lr saved before calling next function
+ * 30: [ do trace stack here ]
+ *
+ * Although the functions returned by save_stack_trace() may be the same, the
+ * placement in the stack will be different. Using the same algorithm as above
+ * would yield:
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          30
+ *  return addr to sys_foo          |          29
+ *  return addr to entry            |          19
+ *
+ * Where the mapping is off by one:
+ *
+ *   kernel_func_bar stack frame size is 29 - 19 not 30 - 29!
+ *
+ * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the
+ * values in stack_trace_index[] are shifted by one to and the number of
+ * stack trace entries is decremented by one.
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          29
+ *  return addr to sys_foo          |          19
+ *
+ * Although the entry function is not displayed, the first function (sys_foo)
+ * will still include the stack size of it.
+ */
+static void check_stack(unsigned long ip, unsigned long *stack)
+{
+	unsigned long this_size, flags; unsigned long *p, *top, *start;
+	static int tracer_frame;
+	int frame_size = READ_ONCE(tracer_frame);
+	int i, x;
+
+	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
+	this_size = THREAD_SIZE - this_size;
+	/* Remove the frame of the tracer */
+	this_size -= frame_size;
+
+	if (this_size <= stack_trace_max_size)
+		return;
+
+	/* we do not handle interrupt stacks yet */
+	if (!object_is_on_stack(stack))
+		return;
+
+	/* Can't do this from NMI context (can cause deadlocks) */
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+	arch_spin_lock(&stack_trace_max_lock);
+
+	/* In case another CPU set the tracer_frame on us */
+	if (unlikely(!frame_size))
+		this_size -= tracer_frame;
+
+	/* a race could have already updated it */
+	if (this_size <= stack_trace_max_size)
+		goto out;
+
+	stack_trace_max_size = this_size;
+
+	stack_trace_nr_entries = stack_trace_save(stack_dump_trace,
+					       ARRAY_SIZE(stack_dump_trace) - 1,
+					       0);
+
+	/* Skip over the overhead of the stack tracer itself */
+	for (i = 0; i < stack_trace_nr_entries; i++) {
+		if (stack_dump_trace[i] == ip)
+			break;
+	}
+
+	/*
+	 * Some archs may not have the passed in ip in the dump.
+	 * If that happens, we need to show everything.
+	 */
+	if (i == stack_trace_nr_entries)
+		i = 0;
+
+	/*
+	 * Now find where in the stack these are.
+	 */
+	x = 0;
+	start = stack;
+	top = (unsigned long *)
+		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
+
+	/*
+	 * Loop through all the entries. One of the entries may
+	 * for some reason be missed on the stack, so we may
+	 * have to account for them. If they are all there, this
+	 * loop will only happen once. This code only takes place
+	 * on a new max, so it is far from a fast path.
+	 */
+	while (i < stack_trace_nr_entries) {
+		int found = 0;
+
+		stack_trace_index[x] = this_size;
+		p = start;
+
+		for (; p < top && i < stack_trace_nr_entries; p++) {
+			/*
+			 * The READ_ONCE_NOCHECK is used to let KASAN know that
+			 * this is not a stack-out-of-bounds error.
+			 */
+			if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
+				stack_dump_trace[x] = stack_dump_trace[i++];
+				this_size = stack_trace_index[x++] =
+					(top - p) * sizeof(unsigned long);
+				found = 1;
+				/* Start the search from here */
+				start = p + 1;
+				/*
+				 * We do not want to show the overhead
+				 * of the stack tracer stack in the
+				 * max stack. If we haven't figured
+				 * out what that is, then figure it out
+				 * now.
+				 */
+				if (unlikely(!tracer_frame)) {
+					tracer_frame = (p - stack) *
+						sizeof(unsigned long);
+					stack_trace_max_size -= tracer_frame;
+				}
+			}
+		}
+
+		if (!found)
+			i++;
+	}
+
+#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER
+	/*
+	 * Some archs will store the link register before calling
+	 * nested functions. This means the saved return address
+	 * comes after the local storage, and we need to shift
+	 * for that.
+	 */
+	if (x > 1) {
+		memmove(&stack_trace_index[0], &stack_trace_index[1],
+			sizeof(stack_trace_index[0]) * (x - 1));
+		x--;
+	}
+#endif
+
+	stack_trace_nr_entries = x;
+
+	if (task_stack_end_corrupted(current)) {
+		print_max_stack();
+		BUG();
+	}
+
+ out:
+	arch_spin_unlock(&stack_trace_max_lock);
+	local_irq_restore(flags);
+}
+
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
+static void
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+		 struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	unsigned long stack;
+
+	preempt_disable_notrace();
+
+	/* no atomic needed, we only modify this variable by this cpu */
+	__this_cpu_inc(disable_stack_tracer);
+	if (__this_cpu_read(disable_stack_tracer) != 1)
+		goto out;
+
+	/* If rcu is not watching, then save stack trace can fail */
+	if (!rcu_is_watching())
+		goto out;
+
+	ip += MCOUNT_INSN_SIZE;
+
+	check_stack(ip, &stack);
+
+ out:
+	__this_cpu_dec(disable_stack_tracer);
+	/* prevent recursion in schedule */
+	preempt_enable_notrace();
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+	.func = stack_trace_call,
+};
+
+static ssize_t
+stack_max_size_read(struct file *filp, char __user *ubuf,
+		    size_t count, loff_t *ppos)
+{
+	unsigned long *ptr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
+	if (r > sizeof(buf))
+		r = sizeof(buf);
+	return simple_read_from_buffer(ubuf, count, ppos, buf, r);
+}
+
+static ssize_t
+stack_max_size_write(struct file *filp, const char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	long *ptr = filp->private_data;
+	unsigned long val, flags;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, count, 10, &val);
+	if (ret)
+		return ret;
+
+	local_irq_save(flags);
+
+	/*
+	 * In case we trace inside arch_spin_lock() or after (NMI),
+	 * we will cause circular lock, so we also need to increase
+	 * the percpu disable_stack_tracer here.
+	 */
+	__this_cpu_inc(disable_stack_tracer);
+
+	arch_spin_lock(&stack_trace_max_lock);
+	*ptr = val;
+	arch_spin_unlock(&stack_trace_max_lock);
+
+	__this_cpu_dec(disable_stack_tracer);
+	local_irq_restore(flags);
+
+	return count;
+}
+
+static const struct file_operations stack_max_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= stack_max_size_read,
+	.write		= stack_max_size_write,
+	.llseek		= default_llseek,
+};
+
+static void *
+__next(struct seq_file *m, loff_t *pos)
+{
+	long n = *pos - 1;
+
+	if (n >= stack_trace_nr_entries)
+		return NULL;
+
+	m->private = (void *)n;
+	return &m->private;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return __next(m, pos);
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	local_irq_disable();
+
+	__this_cpu_inc(disable_stack_tracer);
+
+	arch_spin_lock(&stack_trace_max_lock);
+
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	return __next(m, pos);
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+	arch_spin_unlock(&stack_trace_max_lock);
+
+	__this_cpu_dec(disable_stack_tracer);
+
+	local_irq_enable();
+}
+
+static void trace_lookup_stack(struct seq_file *m, long i)
+{
+	unsigned long addr = stack_dump_trace[i];
+
+	seq_printf(m, "%pS\n", (void *)addr);
+}
+
+static void print_disabled(struct seq_file *m)
+{
+	seq_puts(m, "#\n"
+		 "#  Stack tracer disabled\n"
+		 "#\n"
+		 "# To enable the stack tracer, either add 'stacktrace' to the\n"
+		 "# kernel command line\n"
+		 "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n"
+		 "#\n");
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	long i;
+	int size;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(m, "        Depth    Size   Location"
+			   "    (%d entries)\n"
+			   "        -----    ----   --------\n",
+			   stack_trace_nr_entries);
+
+		if (!stack_tracer_enabled && !stack_trace_max_size)
+			print_disabled(m);
+
+		return 0;
+	}
+
+	i = *(long *)v;
+
+	if (i >= stack_trace_nr_entries)
+		return 0;
+
+	if (i + 1 == stack_trace_nr_entries)
+		size = stack_trace_index[i];
+	else
+		size = stack_trace_index[i] - stack_trace_index[i+1];
+
+	seq_printf(m, "%3ld) %8d   %5d   ", i, stack_trace_index[i], size);
+
+	trace_lookup_stack(m, i);
+
+	return 0;
+}
+
+static const struct seq_operations stack_trace_seq_ops = {
+	.start		= t_start,
+	.next		= t_next,
+	.stop		= t_stop,
+	.show		= t_show,
+};
+
+static int stack_trace_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	return seq_open(file, &stack_trace_seq_ops);
+}
+
+static const struct file_operations stack_trace_fops = {
+	.open		= stack_trace_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static int
+stack_trace_filter_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_ops *ops = inode->i_private;
+
+	/* Checks for tracefs lockdown */
+	return ftrace_regex_open(ops, FTRACE_ITER_FILTER,
+				 inode, file);
+}
+
+static const struct file_operations stack_trace_filter_fops = {
+	.open = stack_trace_filter_open,
+	.read = seq_read,
+	.write = ftrace_filter_write,
+	.llseek = tracing_lseek,
+	.release = ftrace_regex_release,
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+int
+stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+		   size_t *lenp, loff_t *ppos)
+{
+	int was_enabled;
+	int ret;
+
+	mutex_lock(&stack_sysctl_mutex);
+	was_enabled = !!stack_tracer_enabled;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write || (was_enabled == !!stack_tracer_enabled))
+		goto out;
+
+	if (stack_tracer_enabled)
+		register_ftrace_function(&trace_ops);
+	else
+		unregister_ftrace_function(&trace_ops);
+ out:
+	mutex_unlock(&stack_sysctl_mutex);
+	return ret;
+}
+
+static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata;
+
+static __init int enable_stacktrace(char *str)
+{
+	int len;
+
+	if ((len = str_has_prefix(str, "_filter=")))
+		strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
+
+	stack_tracer_enabled = 1;
+	return 1;
+}
+__setup("stacktrace", enable_stacktrace);
+
+static __init int stack_trace_init(void)
+{
+	int ret;
+
+	ret = tracing_init_dentry();
+	if (ret)
+		return 0;
+
+	trace_create_file("stack_max_size", TRACE_MODE_WRITE, NULL,
+			&stack_trace_max_size, &stack_max_size_fops);
+
+	trace_create_file("stack_trace", TRACE_MODE_READ, NULL,
+			NULL, &stack_trace_fops);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	trace_create_file("stack_trace_filter", TRACE_MODE_WRITE, NULL,
+			  &trace_ops, &stack_trace_filter_fops);
+#endif
+
+	if (stack_trace_filter_buf[0])
+		ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1);
+
+	if (stack_tracer_enabled)
+		register_ftrace_function(&trace_ops);
+
+	return 0;
+}
+
+device_initcall(stack_trace_init);