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, 501 insertions, 0 deletions

diff --git a/kernel/profile.c b/kernel/profile.c
new file mode 100644
index 000000000..8a77769bc
--- /dev/null
+++ b/kernel/profile.c
@@ -0,0 +1,501 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/kernel/profile.c
+ *  Simple profiling. Manages a direct-mapped profile hit count buffer,
+ *  with configurable resolution, support for restricting the cpus on
+ *  which profiling is done, and switching between cpu time and
+ *  schedule() calls via kernel command line parameters passed at boot.
+ *
+ *  Scheduler profiling support, Arjan van de Ven and Ingo Molnar,
+ *	Red Hat, July 2004
+ *  Consolidation of architecture support code for profiling,
+ *	Nadia Yvette Chambers, Oracle, July 2004
+ *  Amortized hit count accounting via per-cpu open-addressed hashtables
+ *	to resolve timer interrupt livelocks, Nadia Yvette Chambers,
+ *	Oracle, 2004
+ */
+
+#include <linux/export.h>
+#include <linux/profile.h>
+#include <linux/memblock.h>
+#include <linux/notifier.h>
+#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/cpu.h>
+#include <linux/highmem.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/sched/stat.h>
+
+#include <asm/sections.h>
+#include <asm/irq_regs.h>
+#include <asm/ptrace.h>
+
+struct profile_hit {
+	u32 pc, hits;
+};
+#define PROFILE_GRPSHIFT	3
+#define PROFILE_GRPSZ		(1 << PROFILE_GRPSHIFT)
+#define NR_PROFILE_HIT		(PAGE_SIZE/sizeof(struct profile_hit))
+#define NR_PROFILE_GRP		(NR_PROFILE_HIT/PROFILE_GRPSZ)
+
+static atomic_t *prof_buffer;
+static unsigned long prof_len;
+static unsigned short int prof_shift;
+
+int prof_on __read_mostly;
+EXPORT_SYMBOL_GPL(prof_on);
+
+static cpumask_var_t prof_cpu_mask;
+#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
+static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
+static DEFINE_PER_CPU(int, cpu_profile_flip);
+static DEFINE_MUTEX(profile_flip_mutex);
+#endif /* CONFIG_SMP */
+
+int profile_setup(char *str)
+{
+	static const char schedstr[] = "schedule";
+	static const char sleepstr[] = "sleep";
+	static const char kvmstr[] = "kvm";
+	const char *select = NULL;
+	int par;
+
+	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
+#ifdef CONFIG_SCHEDSTATS
+		force_schedstat_enabled();
+		prof_on = SLEEP_PROFILING;
+		select = sleepstr;
+#else
+		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
+#endif /* CONFIG_SCHEDSTATS */
+	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
+		prof_on = SCHED_PROFILING;
+		select = schedstr;
+	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
+		prof_on = KVM_PROFILING;
+		select = kvmstr;
+	} else if (get_option(&str, &par)) {
+		prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+		prof_on = CPU_PROFILING;
+		pr_info("kernel profiling enabled (shift: %u)\n",
+			prof_shift);
+	}
+
+	if (select) {
+		if (str[strlen(select)] == ',')
+			str += strlen(select) + 1;
+		if (get_option(&str, &par))
+			prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+		pr_info("kernel %s profiling enabled (shift: %u)\n",
+			select, prof_shift);
+	}
+
+	return 1;
+}
+__setup("profile=", profile_setup);
+
+
+int __ref profile_init(void)
+{
+	int buffer_bytes;
+	if (!prof_on)
+		return 0;
+
+	/* only text is profiled */
+	prof_len = (_etext - _stext) >> prof_shift;
+
+	if (!prof_len) {
+		pr_warn("profiling shift: %u too large\n", prof_shift);
+		prof_on = 0;
+		return -EINVAL;
+	}
+
+	buffer_bytes = prof_len*sizeof(atomic_t);
+
+	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(prof_cpu_mask, cpu_possible_mask);
+
+	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = alloc_pages_exact(buffer_bytes,
+					GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = vzalloc(buffer_bytes);
+	if (prof_buffer)
+		return 0;
+
+	free_cpumask_var(prof_cpu_mask);
+	return -ENOMEM;
+}
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
+/*
+ * Each cpu has a pair of open-addressed hashtables for pending
+ * profile hits. read_profile() IPI's all cpus to request them
+ * to flip buffers and flushes their contents to prof_buffer itself.
+ * Flip requests are serialized by the profile_flip_mutex. The sole
+ * use of having a second hashtable is for avoiding cacheline
+ * contention that would otherwise happen during flushes of pending
+ * profile hits required for the accuracy of reported profile hits
+ * and so resurrect the interrupt livelock issue.
+ *
+ * The open-addressed hashtables are indexed by profile buffer slot
+ * and hold the number of pending hits to that profile buffer slot on
+ * a cpu in an entry. When the hashtable overflows, all pending hits
+ * are accounted to their corresponding profile buffer slots with
+ * atomic_add() and the hashtable emptied. As numerous pending hits
+ * may be accounted to a profile buffer slot in a hashtable entry,
+ * this amortizes a number of atomic profile buffer increments likely
+ * to be far larger than the number of entries in the hashtable,
+ * particularly given that the number of distinct profile buffer
+ * positions to which hits are accounted during short intervals (e.g.
+ * several seconds) is usually very small. Exclusion from buffer
+ * flipping is provided by interrupt disablement (note that for
+ * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from
+ * process context).
+ * The hash function is meant to be lightweight as opposed to strong,
+ * and was vaguely inspired by ppc64 firmware-supported inverted
+ * pagetable hash functions, but uses a full hashtable full of finite
+ * collision chains, not just pairs of them.
+ *
+ * -- nyc
+ */
+static void __profile_flip_buffers(void *unused)
+{
+	int cpu = smp_processor_id();
+
+	per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu);
+}
+
+static void profile_flip_buffers(void)
+{
+	int i, j, cpu;
+
+	mutex_lock(&profile_flip_mutex);
+	j = per_cpu(cpu_profile_flip, get_cpu());
+	put_cpu();
+	on_each_cpu(__profile_flip_buffers, NULL, 1);
+	for_each_online_cpu(cpu) {
+		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j];
+		for (i = 0; i < NR_PROFILE_HIT; ++i) {
+			if (!hits[i].hits) {
+				if (hits[i].pc)
+					hits[i].pc = 0;
+				continue;
+			}
+			atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
+			hits[i].hits = hits[i].pc = 0;
+		}
+	}
+	mutex_unlock(&profile_flip_mutex);
+}
+
+static void profile_discard_flip_buffers(void)
+{
+	int i, cpu;
+
+	mutex_lock(&profile_flip_mutex);
+	i = per_cpu(cpu_profile_flip, get_cpu());
+	put_cpu();
+	on_each_cpu(__profile_flip_buffers, NULL, 1);
+	for_each_online_cpu(cpu) {
+		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i];
+		memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit));
+	}
+	mutex_unlock(&profile_flip_mutex);
+}
+
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
+{
+	unsigned long primary, secondary, flags, pc = (unsigned long)__pc;
+	int i, j, cpu;
+	struct profile_hit *hits;
+
+	pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1);
+	i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
+	secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
+	cpu = get_cpu();
+	hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)];
+	if (!hits) {
+		put_cpu();
+		return;
+	}
+	/*
+	 * We buffer the global profiler buffer into a per-CPU
+	 * queue and thus reduce the number of global (and possibly
+	 * NUMA-alien) accesses. The write-queue is self-coalescing:
+	 */
+	local_irq_save(flags);
+	do {
+		for (j = 0; j < PROFILE_GRPSZ; ++j) {
+			if (hits[i + j].pc == pc) {
+				hits[i + j].hits += nr_hits;
+				goto out;
+			} else if (!hits[i + j].hits) {
+				hits[i + j].pc = pc;
+				hits[i + j].hits = nr_hits;
+				goto out;
+			}
+		}
+		i = (i + secondary) & (NR_PROFILE_HIT - 1);
+	} while (i != primary);
+
+	/*
+	 * Add the current hit(s) and flush the write-queue out
+	 * to the global buffer:
+	 */
+	atomic_add(nr_hits, &prof_buffer[pc]);
+	for (i = 0; i < NR_PROFILE_HIT; ++i) {
+		atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
+		hits[i].pc = hits[i].hits = 0;
+	}
+out:
+	local_irq_restore(flags);
+	put_cpu();
+}
+
+static int profile_dead_cpu(unsigned int cpu)
+{
+	struct page *page;
+	int i;
+
+	if (cpumask_available(prof_cpu_mask))
+		cpumask_clear_cpu(cpu, prof_cpu_mask);
+
+	for (i = 0; i < 2; i++) {
+		if (per_cpu(cpu_profile_hits, cpu)[i]) {
+			page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]);
+			per_cpu(cpu_profile_hits, cpu)[i] = NULL;
+			__free_page(page);
+		}
+	}
+	return 0;
+}
+
+static int profile_prepare_cpu(unsigned int cpu)
+{
+	int i, node = cpu_to_mem(cpu);
+	struct page *page;
+
+	per_cpu(cpu_profile_flip, cpu) = 0;
+
+	for (i = 0; i < 2; i++) {
+		if (per_cpu(cpu_profile_hits, cpu)[i])
+			continue;
+
+		page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		if (!page) {
+			profile_dead_cpu(cpu);
+			return -ENOMEM;
+		}
+		per_cpu(cpu_profile_hits, cpu)[i] = page_address(page);
+
+	}
+	return 0;
+}
+
+static int profile_online_cpu(unsigned int cpu)
+{
+	if (cpumask_available(prof_cpu_mask))
+		cpumask_set_cpu(cpu, prof_cpu_mask);
+
+	return 0;
+}
+
+#else /* !CONFIG_SMP */
+#define profile_flip_buffers()		do { } while (0)
+#define profile_discard_flip_buffers()	do { } while (0)
+
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
+{
+	unsigned long pc;
+	pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift;
+	atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]);
+}
+#endif /* !CONFIG_SMP */
+
+void profile_hits(int type, void *__pc, unsigned int nr_hits)
+{
+	if (prof_on != type || !prof_buffer)
+		return;
+	do_profile_hits(type, __pc, nr_hits);
+}
+EXPORT_SYMBOL_GPL(profile_hits);
+
+void profile_tick(int type)
+{
+	struct pt_regs *regs = get_irq_regs();
+
+	if (!user_mode(regs) && cpumask_available(prof_cpu_mask) &&
+	    cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
+		profile_hit(type, (void *)profile_pc(regs));
+}
+
+#ifdef CONFIG_PROC_FS
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+
+static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask));
+	return 0;
+}
+
+static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, prof_cpu_mask_proc_show, NULL);
+}
+
+static ssize_t prof_cpu_mask_proc_write(struct file *file,
+	const char __user *buffer, size_t count, loff_t *pos)
+{
+	cpumask_var_t new_value;
+	int err;
+
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
+		return -ENOMEM;
+
+	err = cpumask_parse_user(buffer, count, new_value);
+	if (!err) {
+		cpumask_copy(prof_cpu_mask, new_value);
+		err = count;
+	}
+	free_cpumask_var(new_value);
+	return err;
+}
+
+static const struct proc_ops prof_cpu_mask_proc_ops = {
+	.proc_open	= prof_cpu_mask_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= prof_cpu_mask_proc_write,
+};
+
+void create_prof_cpu_mask(void)
+{
+	/* create /proc/irq/prof_cpu_mask */
+	proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops);
+}
+
+/*
+ * This function accesses profiling information. The returned data is
+ * binary: the sampling step and the actual contents of the profile
+ * buffer. Use of the program readprofile is recommended in order to
+ * get meaningful info out of these data.
+ */
+static ssize_t
+read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long p = *ppos;
+	ssize_t read;
+	char *pnt;
+	unsigned long sample_step = 1UL << prof_shift;
+
+	profile_flip_buffers();
+	if (p >= (prof_len+1)*sizeof(unsigned int))
+		return 0;
+	if (count > (prof_len+1)*sizeof(unsigned int) - p)
+		count = (prof_len+1)*sizeof(unsigned int) - p;
+	read = 0;
+
+	while (p < sizeof(unsigned int) && count > 0) {
+		if (put_user(*((char *)(&sample_step)+p), buf))
+			return -EFAULT;
+		buf++; p++; count--; read++;
+	}
+	pnt = (char *)prof_buffer + p - sizeof(atomic_t);
+	if (copy_to_user(buf, (void *)pnt, count))
+		return -EFAULT;
+	read += count;
+	*ppos += read;
+	return read;
+}
+
+/* default is to not implement this call */
+int __weak setup_profiling_timer(unsigned mult)
+{
+	return -EINVAL;
+}
+
+/*
+ * Writing to /proc/profile resets the counters
+ *
+ * Writing a 'profiling multiplier' value into it also re-sets the profiling
+ * interrupt frequency, on architectures that support this.
+ */
+static ssize_t write_profile(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+#ifdef CONFIG_SMP
+	if (count == sizeof(int)) {
+		unsigned int multiplier;
+
+		if (copy_from_user(&multiplier, buf, sizeof(int)))
+			return -EFAULT;
+
+		if (setup_profiling_timer(multiplier))
+			return -EINVAL;
+	}
+#endif
+	profile_discard_flip_buffers();
+	memset(prof_buffer, 0, prof_len * sizeof(atomic_t));
+	return count;
+}
+
+static const struct proc_ops profile_proc_ops = {
+	.proc_read	= read_profile,
+	.proc_write	= write_profile,
+	.proc_lseek	= default_llseek,
+};
+
+int __ref create_proc_profile(void)
+{
+	struct proc_dir_entry *entry;
+#ifdef CONFIG_SMP
+	enum cpuhp_state online_state;
+#endif
+
+	int err = 0;
+
+	if (!prof_on)
+		return 0;
+#ifdef CONFIG_SMP
+	err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE",
+				profile_prepare_cpu, profile_dead_cpu);
+	if (err)
+		return err;
+
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE",
+				profile_online_cpu, NULL);
+	if (err < 0)
+		goto err_state_prep;
+	online_state = err;
+	err = 0;
+#endif
+	entry = proc_create("profile", S_IWUSR | S_IRUGO,
+			    NULL, &profile_proc_ops);
+	if (!entry)
+		goto err_state_onl;
+	proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
+
+	return err;
+err_state_onl:
+#ifdef CONFIG_SMP
+	cpuhp_remove_state(online_state);
+err_state_prep:
+	cpuhp_remove_state(CPUHP_PROFILE_PREPARE);
+#endif
+	return err;
+}
+subsys_initcall(create_proc_profile);
+#endif /* CONFIG_PROC_FS */