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, 895 insertions, 0 deletions

diff --git a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c
new file mode 100644
index 000000000..f75739bba
--- /dev/null
+++ b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c
@@ -0,0 +1,895 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * perf events self profiling example test case for hw breakpoints.
+ *
+ * This tests perf PERF_TYPE_BREAKPOINT parameters
+ * 1) tests all variants of the break on read/write flags
+ * 2) tests exclude_user == 0 and 1
+ * 3) test array matches (if DAWR is supported))
+ * 4) test different numbers of breakpoints matches
+ *
+ * Configure this breakpoint, then read and write the data a number of
+ * times. Then check the output count from perf is as expected.
+ *
+ * Based on:
+ *   http://ozlabs.org/~anton/junkcode/perf_events_example1.c
+ *
+ * Copyright (C) 2018 Michael Neuling, IBM Corporation.
+ */
+
+#define _GNU_SOURCE
+
+#include <unistd.h>
+#include <assert.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/wait.h>
+#include <sys/ptrace.h>
+#include <sys/resource.h>
+#include <sys/sysinfo.h>
+#include <asm/ptrace.h>
+#include <elf.h>
+#include <pthread.h>
+#include <sys/syscall.h>
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
+#include "utils.h"
+
+#ifndef PPC_DEBUG_FEATURE_DATA_BP_ARCH_31
+#define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31	0x20
+#endif
+
+#define MAX_LOOPS 10000
+
+#define DAWR_LENGTH_MAX ((0x3f + 1) * 8)
+
+int nprocs;
+
+static volatile int a = 10;
+static volatile int b = 10;
+static volatile char c[512 + 8] __attribute__((aligned(512)));
+
+static void perf_event_attr_set(struct perf_event_attr *attr,
+				__u32 type, __u64 addr, __u64 len,
+				bool exclude_user)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type           = PERF_TYPE_BREAKPOINT;
+	attr->size           = sizeof(struct perf_event_attr);
+	attr->bp_type        = type;
+	attr->bp_addr        = addr;
+	attr->bp_len         = len;
+	attr->exclude_kernel = 1;
+	attr->exclude_hv     = 1;
+	attr->exclude_guest  = 1;
+	attr->exclude_user   = exclude_user;
+	attr->disabled       = 1;
+}
+
+static int
+perf_process_event_open_exclude_user(__u32 type, __u64 addr, __u64 len, bool exclude_user)
+{
+	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, exclude_user);
+	return syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
+}
+
+static int perf_process_event_open(__u32 type, __u64 addr, __u64 len)
+{
+	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, 0);
+	return syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
+}
+
+static int perf_cpu_event_open(long cpu, __u32 type, __u64 addr, __u64 len)
+{
+	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, 0);
+	return syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0);
+}
+
+static void close_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		close(fd[i]);
+}
+
+static unsigned long read_fds(int *fd, int n)
+{
+	int i;
+	unsigned long c = 0;
+	unsigned long count = 0;
+	size_t res;
+
+	for (i = 0; i < n; i++) {
+		res = read(fd[i], &c, sizeof(c));
+		assert(res == sizeof(unsigned long long));
+		count += c;
+	}
+	return count;
+}
+
+static void reset_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_RESET);
+}
+
+static void enable_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_ENABLE);
+}
+
+static void disable_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_DISABLE);
+}
+
+static int perf_systemwide_event_open(int *fd, __u32 type, __u64 addr, __u64 len)
+{
+	int i, ncpus, cpu, ret = 0;
+	struct rlimit rlim;
+	cpu_set_t *mask;
+	size_t size;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim)) {
+		perror("getrlimit");
+		return -1;
+	}
+	rlim.rlim_cur = 65536;
+	if (setrlimit(RLIMIT_NOFILE, &rlim)) {
+		perror("setrlimit");
+		return -1;
+	}
+
+	ncpus = get_nprocs_conf();
+	size = CPU_ALLOC_SIZE(ncpus);
+	mask = CPU_ALLOC(ncpus);
+	if (!mask) {
+		perror("malloc");
+		return -1;
+	}
+
+	CPU_ZERO_S(size, mask);
+
+	if (sched_getaffinity(0, size, mask)) {
+		perror("sched_getaffinity");
+		ret = -1;
+		goto done;
+	}
+
+	for (i = 0, cpu = 0; i < nprocs && cpu < ncpus; cpu++) {
+		if (!CPU_ISSET_S(cpu, size, mask))
+			continue;
+		fd[i] = perf_cpu_event_open(cpu, type, addr, len);
+		if (fd[i] < 0) {
+			perror("perf_systemwide_event_open");
+			close_fds(fd, i);
+			ret = fd[i];
+			goto done;
+		}
+		i++;
+	}
+
+	if (i < nprocs) {
+		printf("Error: Number of online cpus reduced since start of test: %d < %d\n", i, nprocs);
+		close_fds(fd, i);
+		ret = -1;
+	}
+
+done:
+	CPU_FREE(mask);
+	return ret;
+}
+
+static inline bool breakpoint_test(int len)
+{
+	int fd;
+
+	/* bp_addr can point anywhere but needs to be aligned */
+	fd = perf_process_event_open(HW_BREAKPOINT_R, (__u64)(&fd) & 0xfffffffffffff800, len);
+	if (fd < 0)
+		return false;
+	close(fd);
+	return true;
+}
+
+static inline bool perf_breakpoint_supported(void)
+{
+	return breakpoint_test(4);
+}
+
+static inline bool dawr_supported(void)
+{
+	return breakpoint_test(DAWR_LENGTH_MAX);
+}
+
+static int runtestsingle(int readwriteflag, int exclude_user, int arraytest)
+{
+	int i,j;
+	size_t res;
+	unsigned long long breaks, needed;
+	int readint;
+	int readintarraybig[2*DAWR_LENGTH_MAX/sizeof(int)];
+	int *readintalign;
+	volatile int *ptr;
+	int break_fd;
+	int loop_num = MAX_LOOPS - (rand() % 100); /* provide some variability */
+	volatile int *k;
+	__u64 len;
+
+	/* align to 0x400 boundary as required by DAWR */
+	readintalign = (int *)(((unsigned long)readintarraybig + 0x7ff) &
+			       0xfffffffffffff800);
+
+	ptr = &readint;
+	if (arraytest)
+		ptr = &readintalign[0];
+
+	len = arraytest ? DAWR_LENGTH_MAX : sizeof(int);
+	break_fd = perf_process_event_open_exclude_user(readwriteflag, (__u64)ptr,
+							len, exclude_user);
+	if (break_fd < 0) {
+		perror("perf_process_event_open_exclude_user");
+		exit(1);
+	}
+
+	/* start counters */
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+
+	/* Test a bunch of reads and writes */
+	k = &readint;
+	for (i = 0; i < loop_num; i++) {
+		if (arraytest)
+			k = &(readintalign[i % (DAWR_LENGTH_MAX/sizeof(int))]);
+
+		j = *k;
+		*k = j;
+	}
+
+	/* stop counters */
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+
+	/* read and check counters */
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	/* we read and write each loop, so subtract the ones we are counting */
+	needed = 0;
+	if (readwriteflag & HW_BREAKPOINT_R)
+		needed += loop_num;
+	if (readwriteflag & HW_BREAKPOINT_W)
+		needed += loop_num;
+	needed = needed * (1 - exclude_user);
+	printf("TESTED: addr:0x%lx brks:% 8lld loops:% 8i rw:%i !user:%i array:%i\n",
+	       (unsigned long int)ptr, breaks, loop_num, readwriteflag, exclude_user, arraytest);
+	if (breaks != needed) {
+		printf("FAILED: 0x%lx brks:%lld needed:%lli %i %i %i\n\n",
+		       (unsigned long int)ptr, breaks, needed, loop_num, readwriteflag, exclude_user);
+		return 1;
+	}
+	close(break_fd);
+
+	return 0;
+}
+
+static int runtest_dar_outside(void)
+{
+	void *target;
+	volatile __u16 temp16;
+	volatile __u64 temp64;
+	int break_fd;
+	unsigned long long breaks;
+	int fail = 0;
+	size_t res;
+
+	target = malloc(8);
+	if (!target) {
+		perror("malloc failed");
+		exit(EXIT_FAILURE);
+	}
+
+	/* watch middle half of target array */
+	break_fd = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)(target + 2), 4);
+	if (break_fd < 0) {
+		free(target);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Shouldn't hit. */
+	ioctl(break_fd, PERF_EVENT_IOC_RESET);
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+	temp16 = *((__u16 *)target);
+	*((__u16 *)target) = temp16;
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	if (breaks == 0) {
+		printf("TESTED: No overlap\n");
+	} else {
+		printf("FAILED: No overlap: %lld != 0\n", breaks);
+		fail = 1;
+	}
+
+	/* Hit */
+	ioctl(break_fd, PERF_EVENT_IOC_RESET);
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+	temp16 = *((__u16 *)(target + 1));
+	*((__u16 *)(target + 1)) = temp16;
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	if (breaks == 2) {
+		printf("TESTED: Partial overlap\n");
+	} else {
+		printf("FAILED: Partial overlap: %lld != 2\n", breaks);
+		fail = 1;
+	}
+
+	/* Hit */
+	ioctl(break_fd, PERF_EVENT_IOC_RESET);
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+	temp16 = *((__u16 *)(target + 5));
+	*((__u16 *)(target + 5)) = temp16;
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	if (breaks == 2) {
+		printf("TESTED: Partial overlap\n");
+	} else {
+		printf("FAILED: Partial overlap: %lld != 2\n", breaks);
+		fail = 1;
+	}
+
+	/* Shouldn't Hit */
+	ioctl(break_fd, PERF_EVENT_IOC_RESET);
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+	temp16 = *((__u16 *)(target + 6));
+	*((__u16 *)(target + 6)) = temp16;
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	if (breaks == 0) {
+		printf("TESTED: No overlap\n");
+	} else {
+		printf("FAILED: No overlap: %lld != 0\n", breaks);
+		fail = 1;
+	}
+
+	/* Hit */
+	ioctl(break_fd, PERF_EVENT_IOC_RESET);
+	ioctl(break_fd, PERF_EVENT_IOC_ENABLE);
+	temp64 = *((__u64 *)target);
+	*((__u64 *)target) = temp64;
+	ioctl(break_fd, PERF_EVENT_IOC_DISABLE);
+	res = read(break_fd, &breaks, sizeof(unsigned long long));
+	assert(res == sizeof(unsigned long long));
+	if (breaks == 2) {
+		printf("TESTED: Full overlap\n");
+	} else {
+		printf("FAILED: Full overlap: %lld != 2\n", breaks);
+		fail = 1;
+	}
+
+	free(target);
+	close(break_fd);
+	return fail;
+}
+
+static void multi_dawr_workload(void)
+{
+	a += 10;
+	b += 10;
+	c[512 + 1] += 'a';
+}
+
+static int test_process_multi_diff_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, diff addr";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&b, (__u64)sizeof(b));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_same_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, same addr";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_diff_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, diff addr, one is RO, other is WO";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_R, (__u64)&b, (__u64)sizeof(b));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_same_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, same addr, one is RO, other is WO";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_R, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_diff_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, diff addr";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret)
+		exit(EXIT_FAILURE);
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_RW, (__u64)&b, (__u64)sizeof(b));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_same_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, same addr";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret)
+		exit(EXIT_FAILURE);
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_diff_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, diff addr, one is RO, other is WO";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (ret)
+		exit(EXIT_FAILURE);
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_R, (__u64)&b, (__u64)sizeof(b));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_same_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, same addr, one is RO, other is WO";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (ret)
+		exit(EXIT_FAILURE);
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_R, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int runtest_multi_dawr(void)
+{
+	int ret = 0;
+
+	ret |= test_process_multi_diff_addr();
+	ret |= test_process_multi_same_addr();
+	ret |= test_process_multi_diff_addr_ro_wo();
+	ret |= test_process_multi_same_addr_ro_wo();
+	ret |= test_syswide_multi_diff_addr();
+	ret |= test_syswide_multi_same_addr();
+	ret |= test_syswide_multi_diff_addr_ro_wo();
+	ret |= test_syswide_multi_same_addr_ro_wo();
+
+	return ret;
+}
+
+static int runtest_unaligned_512bytes(void)
+{
+	unsigned long long breaks = 0;
+	int fd;
+	char *desc = "Process specific, 512 bytes, unaligned";
+	__u64 addr = (__u64)&c + 8;
+	size_t res;
+
+	fd = perf_process_event_open(HW_BREAKPOINT_RW, addr, 512);
+	if (fd < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd, &breaks, sizeof(breaks));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd);
+
+	if (breaks != 2) {
+		printf("FAILED: %s: %lld != 2\n", desc, breaks);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+/* There is no perf api to find number of available watchpoints. Use ptrace. */
+static int get_nr_wps(bool *arch_31)
+{
+	struct ppc_debug_info dbginfo;
+	int child_pid;
+
+	child_pid = fork();
+	if (!child_pid) {
+		int ret = ptrace(PTRACE_TRACEME, 0, NULL, 0);
+		if (ret) {
+			perror("PTRACE_TRACEME failed\n");
+			exit(EXIT_FAILURE);
+		}
+		kill(getpid(), SIGUSR1);
+
+		sleep(1);
+		exit(EXIT_SUCCESS);
+	}
+
+	wait(NULL);
+	if (ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo)) {
+		perror("Can't get breakpoint info");
+		exit(EXIT_FAILURE);
+	}
+
+	*arch_31 = !!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_ARCH_31);
+	return dbginfo.num_data_bps;
+}
+
+static int runtest(void)
+{
+	int rwflag;
+	int exclude_user;
+	int ret;
+	bool dawr = dawr_supported();
+	bool arch_31 = false;
+	int nr_wps = get_nr_wps(&arch_31);
+
+	/*
+	 * perf defines rwflag as two bits read and write and at least
+	 * one must be set.  So range 1-3.
+	 */
+	for (rwflag = 1 ; rwflag < 4; rwflag++) {
+		for (exclude_user = 0 ; exclude_user < 2; exclude_user++) {
+			ret = runtestsingle(rwflag, exclude_user, 0);
+			if (ret)
+				return ret;
+
+			/* if we have the dawr, we can do an array test */
+			if (!dawr)
+				continue;
+			ret = runtestsingle(rwflag, exclude_user, 1);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = runtest_dar_outside();
+	if (ret)
+		return ret;
+
+	if (dawr && nr_wps > 1) {
+		nprocs = get_nprocs();
+		ret = runtest_multi_dawr();
+		if (ret)
+			return ret;
+	}
+
+	if (dawr && arch_31)
+		ret = runtest_unaligned_512bytes();
+
+	return ret;
+}
+
+
+static int perf_hwbreak(void)
+{
+	srand ( time(NULL) );
+
+	SKIP_IF(!perf_breakpoint_supported());
+
+	return runtest();
+}
+
+int main(int argc, char *argv[], char **envp)
+{
+	return test_harness(perf_hwbreak, "perf_hwbreak");
+}