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, 495 insertions, 0 deletions

diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
new file mode 100644
index 000000000..cb6a7dc02
--- /dev/null
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -0,0 +1,495 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter support for POWER9 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2013 Michael Ellerman, IBM Corporation.
+ * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
+ */
+
+#define pr_fmt(fmt)	"power9-pmu: " fmt
+
+#include "isa207-common.h"
+
+/*
+ * Raw event encoding for Power9:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   | | [ ]                       [ ] [      thresh_cmp     ]   [  thresh_ctl   ]
+ *   | |  |                         |                                     |
+ *   | |  *- IFM (Linux)            |	               thresh start/stop -*
+ *   | *- BHRB (Linux)              *sm
+ *   *- EBB (Linux)
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   [   ] [  sample ]   [cache]   [ pmc ]   [unit ]   []    m   [    pmcxsel    ]
+ *     |        |           |                          |     |
+ *     |        |           |                          |     *- mark
+ *     |        |           *- L1/L2/L3 cache_sel      |
+ *     |        |                                      |
+ *     |        *- sampling mode for marked events     *- combine
+ *     |
+ *     *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit    (PMCxUNIT)
+ * MMCR1[24]   = pmc1combine[0]
+ * MMCR1[25]   = pmc1combine[1]
+ * MMCR1[26]   = pmc2combine[0]
+ * MMCR1[27]   = pmc2combine[1]
+ * MMCR1[28]   = pmc3combine[0]
+ * MMCR1[29]   = pmc3combine[1]
+ * MMCR1[30]   = pmc4combine[0]
+ * MMCR1[31]   = pmc4combine[1]
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ *	MMCR1[20:27] = thresh_ctl
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ *	MMCR1[20:27] = thresh_ctl
+ * else
+ *	MMCRA[48:55] = thresh_ctl   (THRESH START/END)
+ *
+ * if thresh_sel:
+ *	MMCRA[45:47] = thresh_sel
+ *
+ * if thresh_cmp:
+ *	MMCRA[9:11] = thresh_cmp[0:2]
+ *	MMCRA[12:18] = thresh_cmp[3:9]
+ *
+ * MMCR1[16] = cache_sel[2]
+ * MMCR1[17] = cache_sel[3]
+ *
+ * if mark:
+ *	MMCRA[63]    = 1		(SAMPLE_ENABLE)
+ *	MMCRA[57:59] = sample[0:2]	(RAND_SAMP_ELIG)
+ *	MMCRA[61:62] = sample[3:4]	(RAND_SAMP_MODE)
+ *
+ * if EBB and BHRB:
+ *	MMCRA[32:33] = IFM
+ *
+ * MMCRA[SDAR_MODE]  = sm
+ */
+
+/*
+ * Some power9 event codes.
+ */
+#define EVENT(_name, _code)	_name = _code,
+
+enum {
+#include "power9-events-list.h"
+};
+
+#undef EVENT
+
+/* MMCRA IFM bits - POWER9 */
+#define POWER9_MMCRA_IFM1		0x0000000040000000UL
+#define POWER9_MMCRA_IFM2		0x0000000080000000UL
+#define POWER9_MMCRA_IFM3		0x00000000C0000000UL
+#define POWER9_MMCRA_BHRB_MASK		0x00000000C0000000UL
+
+extern u64 PERF_REG_EXTENDED_MASK;
+
+/* Nasty Power9 specific hack */
+#define PVR_POWER9_CUMULUS		0x00002000
+
+/* PowerISA v2.07 format attribute structure*/
+extern const struct attribute_group isa207_pmu_format_group;
+
+static int p9_dd21_bl_ev[] = {
+	PM_MRK_ST_DONE_L2,
+	PM_RADIX_PWC_L1_HIT,
+	PM_FLOP_CMPL,
+	PM_MRK_NTF_FIN,
+	PM_RADIX_PWC_L2_HIT,
+	PM_IFETCH_THROTTLE,
+	PM_MRK_L2_TM_ST_ABORT_SISTER,
+	PM_RADIX_PWC_L3_HIT,
+	PM_RUN_CYC_SMT2_MODE,
+	PM_TM_TX_PASS_RUN_INST,
+	PM_DISP_HELD_SYNC_HOLD,
+};
+
+static int p9_dd22_bl_ev[] = {
+	PM_DTLB_MISS_16G,
+	PM_DERAT_MISS_2M,
+	PM_DTLB_MISS_2M,
+	PM_MRK_DTLB_MISS_1G,
+	PM_DTLB_MISS_4K,
+	PM_DERAT_MISS_1G,
+	PM_MRK_DERAT_MISS_2M,
+	PM_MRK_DTLB_MISS_4K,
+	PM_MRK_DTLB_MISS_16G,
+	PM_DTLB_MISS_64K,
+	PM_MRK_DERAT_MISS_1G,
+	PM_MRK_DTLB_MISS_64K,
+	PM_DISP_HELD_SYNC_HOLD,
+	PM_DTLB_MISS_16M,
+	PM_DTLB_MISS_1G,
+	PM_MRK_DTLB_MISS_16M,
+};
+
+/* Table of alternatives, sorted by column 0 */
+static const unsigned int power9_event_alternatives[][MAX_ALT] = {
+	{ PM_BR_2PATH,			PM_BR_2PATH_ALT },
+	{ PM_INST_DISP,			PM_INST_DISP_ALT },
+	{ PM_RUN_CYC_ALT,               PM_RUN_CYC },
+	{ PM_LD_MISS_L1,                PM_LD_MISS_L1_ALT },
+	{ PM_RUN_INST_CMPL_ALT,         PM_RUN_INST_CMPL },
+};
+
+static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int num_alt = 0;
+
+	num_alt = isa207_get_alternatives(event, alt,
+					  ARRAY_SIZE(power9_event_alternatives), flags,
+					  power9_event_alternatives);
+
+	return num_alt;
+}
+
+static int power9_check_attr_config(struct perf_event *ev)
+{
+	u64 val;
+	u64 event = ev->attr.config;
+
+	val = (event >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
+	if (val == 0xC || isa3XX_check_attr_config(ev))
+		return -EINVAL;
+
+	return 0;
+}
+
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	PM_ICT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+GENERIC_EVENT_ATTR(branch-instructions,		PM_BR_CMPL);
+GENERIC_EVENT_ATTR(branch-misses,		PM_BR_MPRED_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		PM_LD_MISS_L1_FIN);
+GENERIC_EVENT_ATTR(mem-loads,			MEM_LOADS);
+GENERIC_EVENT_ATTR(mem-stores,			MEM_STORES);
+
+CACHE_EVENT_ATTR(L1-dcache-load-misses,		PM_LD_MISS_L1_FIN);
+CACHE_EVENT_ATTR(L1-dcache-loads,		PM_LD_REF_L1);
+CACHE_EVENT_ATTR(L1-dcache-prefetches,		PM_L1_PREF);
+CACHE_EVENT_ATTR(L1-dcache-store-misses,	PM_ST_MISS_L1);
+CACHE_EVENT_ATTR(L1-icache-load-misses,		PM_L1_ICACHE_MISS);
+CACHE_EVENT_ATTR(L1-icache-loads,		PM_INST_FROM_L1);
+CACHE_EVENT_ATTR(L1-icache-prefetches,		PM_IC_PREF_WRITE);
+CACHE_EVENT_ATTR(LLC-load-misses,		PM_DATA_FROM_L3MISS);
+CACHE_EVENT_ATTR(LLC-loads,			PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(LLC-prefetches,		PM_L3_PREF_ALL);
+CACHE_EVENT_ATTR(branch-load-misses,		PM_BR_MPRED_CMPL);
+CACHE_EVENT_ATTR(branch-loads,			PM_BR_CMPL);
+CACHE_EVENT_ATTR(dTLB-load-misses,		PM_DTLB_MISS);
+CACHE_EVENT_ATTR(iTLB-load-misses,		PM_ITLB_MISS);
+
+static struct attribute *power9_events_attr[] = {
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_ICT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_BR_CMPL),
+	GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+	GENERIC_EVENT_PTR(PM_LD_REF_L1),
+	GENERIC_EVENT_PTR(PM_LD_MISS_L1_FIN),
+	GENERIC_EVENT_PTR(MEM_LOADS),
+	GENERIC_EVENT_PTR(MEM_STORES),
+	CACHE_EVENT_PTR(PM_LD_MISS_L1_FIN),
+	CACHE_EVENT_PTR(PM_LD_REF_L1),
+	CACHE_EVENT_PTR(PM_L1_PREF),
+	CACHE_EVENT_PTR(PM_ST_MISS_L1),
+	CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+	CACHE_EVENT_PTR(PM_INST_FROM_L1),
+	CACHE_EVENT_PTR(PM_IC_PREF_WRITE),
+	CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+	CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+	CACHE_EVENT_PTR(PM_L3_PREF_ALL),
+	CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+	CACHE_EVENT_PTR(PM_BR_CMPL),
+	CACHE_EVENT_PTR(PM_DTLB_MISS),
+	CACHE_EVENT_PTR(PM_ITLB_MISS),
+	NULL
+};
+
+static const struct attribute_group power9_pmu_events_group = {
+	.name = "events",
+	.attrs = power9_events_attr,
+};
+
+PMU_FORMAT_ATTR(event,		"config:0-51");
+PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
+PMU_FORMAT_ATTR(mark,		"config:8");
+PMU_FORMAT_ATTR(combine,	"config:10-11");
+PMU_FORMAT_ATTR(unit,		"config:12-15");
+PMU_FORMAT_ATTR(pmc,		"config:16-19");
+PMU_FORMAT_ATTR(cache_sel,	"config:20-23");
+PMU_FORMAT_ATTR(sample_mode,	"config:24-28");
+PMU_FORMAT_ATTR(thresh_sel,	"config:29-31");
+PMU_FORMAT_ATTR(thresh_stop,	"config:32-35");
+PMU_FORMAT_ATTR(thresh_start,	"config:36-39");
+PMU_FORMAT_ATTR(thresh_cmp,	"config:40-49");
+PMU_FORMAT_ATTR(sdar_mode,	"config:50-51");
+
+static struct attribute *power9_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_pmcxsel.attr,
+	&format_attr_mark.attr,
+	&format_attr_combine.attr,
+	&format_attr_unit.attr,
+	&format_attr_pmc.attr,
+	&format_attr_cache_sel.attr,
+	&format_attr_sample_mode.attr,
+	&format_attr_thresh_sel.attr,
+	&format_attr_thresh_stop.attr,
+	&format_attr_thresh_start.attr,
+	&format_attr_thresh_cmp.attr,
+	&format_attr_sdar_mode.attr,
+	NULL,
+};
+
+static const struct attribute_group power9_pmu_format_group = {
+	.name = "format",
+	.attrs = power9_pmu_format_attr,
+};
+
+static struct attribute *power9_pmu_caps_attrs[] = {
+	NULL
+};
+
+static struct attribute_group power9_pmu_caps_group = {
+	.name  = "caps",
+	.attrs = power9_pmu_caps_attrs,
+};
+
+static const struct attribute_group *power9_pmu_attr_groups[] = {
+	&power9_pmu_format_group,
+	&power9_pmu_events_group,
+	&power9_pmu_caps_group,
+	NULL,
+};
+
+static int power9_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PM_ICT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BR_CMPL,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1_FIN,
+};
+
+static u64 power9_bhrb_filter_map(u64 branch_sample_type)
+{
+	u64 pmu_bhrb_filter = 0;
+
+	/* BHRB and regular PMU events share the same privilege state
+	 * filter configuration. BHRB is always recorded along with a
+	 * regular PMU event. As the privilege state filter is handled
+	 * in the basic PMC configuration of the accompanying regular
+	 * PMU event, we ignore any separate BHRB specific request.
+	 */
+
+	/* No branch filter requested */
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY)
+		return pmu_bhrb_filter;
+
+	/* Invalid branch filter options - HW does not support */
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+		pmu_bhrb_filter |= POWER9_MMCRA_IFM1;
+		return pmu_bhrb_filter;
+	}
+
+	/* Every thing else is unsupported */
+	return -1;
+}
+
+static void power9_config_bhrb(u64 pmu_bhrb_filter)
+{
+	pmu_bhrb_filter &= POWER9_MMCRA_BHRB_MASK;
+
+	/* Enable BHRB filter in PMU */
+	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
+}
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static u64 power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1_FIN,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BR_CMPL,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
+static struct power_pmu power9_pmu = {
+	.name			= "POWER9",
+	.n_counter		= MAX_PMU_COUNTERS,
+	.add_fields		= ISA207_ADD_FIELDS,
+	.test_adder		= ISA207_TEST_ADDER,
+	.group_constraint_mask	= CNST_CACHE_PMC4_MASK,
+	.group_constraint_val	= CNST_CACHE_PMC4_VAL,
+	.compute_mmcr		= isa207_compute_mmcr,
+	.config_bhrb		= power9_config_bhrb,
+	.bhrb_filter_map	= power9_bhrb_filter_map,
+	.get_constraint		= isa207_get_constraint,
+	.get_alternatives	= power9_get_alternatives,
+	.get_mem_data_src	= isa207_get_mem_data_src,
+	.get_mem_weight		= isa207_get_mem_weight,
+	.disable_pmc		= isa207_disable_pmc,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.n_generic		= ARRAY_SIZE(power9_generic_events),
+	.generic_events		= power9_generic_events,
+	.cache_events		= &power9_cache_events,
+	.attr_groups		= power9_pmu_attr_groups,
+	.bhrb_nr		= 32,
+	.capabilities           = PERF_PMU_CAP_EXTENDED_REGS,
+	.check_attr_config	= power9_check_attr_config,
+};
+
+int __init init_power9_pmu(void)
+{
+	int rc = 0;
+	unsigned int pvr = mfspr(SPRN_PVR);
+
+	if (PVR_VER(pvr) != PVR_POWER9)
+		return -ENODEV;
+
+	/* Blacklist events */
+	if (!(pvr & PVR_POWER9_CUMULUS)) {
+		if ((PVR_CFG(pvr) == 2) && (PVR_MIN(pvr) == 1)) {
+			power9_pmu.blacklist_ev = p9_dd21_bl_ev;
+			power9_pmu.n_blacklist_ev = ARRAY_SIZE(p9_dd21_bl_ev);
+		} else if ((PVR_CFG(pvr) == 2) && (PVR_MIN(pvr) == 2)) {
+			power9_pmu.blacklist_ev = p9_dd22_bl_ev;
+			power9_pmu.n_blacklist_ev = ARRAY_SIZE(p9_dd22_bl_ev);
+		}
+	}
+
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300;
+
+	rc = register_power_pmu(&power9_pmu);
+	if (rc)
+		return rc;
+
+	/* Tell userspace that EBB is supported */
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+	return 0;
+}