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, 908 insertions, 0 deletions

diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
new file mode 100644
index 000000000..0216ff24c
--- /dev/null
+++ b/arch/mips/kernel/branch.c
@@ -0,0 +1,908 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1996, 97, 2000, 2001 by Ralf Baechle
+ * Copyright (C) 2001 MIPS Technologies, Inc.
+ */
+#include <linux/kernel.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/export.h>
+#include <asm/branch.h>
+#include <asm/cpu.h>
+#include <asm/cpu-features.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
+#include <asm/inst.h>
+#include <asm/mips-r2-to-r6-emul.h>
+#include <asm/ptrace.h>
+#include <linux/uaccess.h>
+
+#include "probes-common.h"
+
+/*
+ * Calculate and return exception PC in case of branch delay slot
+ * for microMIPS and MIPS16e. It does not clear the ISA mode bit.
+ */
+int __isa_exception_epc(struct pt_regs *regs)
+{
+	unsigned short inst;
+	long epc = regs->cp0_epc;
+
+	/* Calculate exception PC in branch delay slot. */
+	if (__get_user(inst, (u16 __user *) msk_isa16_mode(epc))) {
+		/* This should never happen because delay slot was checked. */
+		force_sig(SIGSEGV);
+		return epc;
+	}
+	if (cpu_has_mips16) {
+		union mips16e_instruction inst_mips16e;
+
+		inst_mips16e.full = inst;
+		if (inst_mips16e.ri.opcode == MIPS16e_jal_op)
+			epc += 4;
+		else
+			epc += 2;
+	} else if (mm_insn_16bit(inst))
+		epc += 2;
+	else
+		epc += 4;
+
+	return epc;
+}
+
+/* (microMIPS) Convert 16-bit register encoding to 32-bit register encoding. */
+static const unsigned int reg16to32map[8] = {16, 17, 2, 3, 4, 5, 6, 7};
+
+int __mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
+		       unsigned long *contpc)
+{
+	union mips_instruction insn = (union mips_instruction)dec_insn.insn;
+	int __maybe_unused bc_false = 0;
+
+	if (!cpu_has_mmips)
+		return 0;
+
+	switch (insn.mm_i_format.opcode) {
+	case mm_pool32a_op:
+		if ((insn.mm_i_format.simmediate & MM_POOL32A_MINOR_MASK) ==
+		    mm_pool32axf_op) {
+			switch (insn.mm_i_format.simmediate >>
+				MM_POOL32A_MINOR_SHIFT) {
+			case mm_jalr_op:
+			case mm_jalrhb_op:
+			case mm_jalrs_op:
+			case mm_jalrshb_op:
+				if (insn.mm_i_format.rt != 0)	/* Not mm_jr */
+					regs->regs[insn.mm_i_format.rt] =
+						regs->cp0_epc +
+						dec_insn.pc_inc +
+						dec_insn.next_pc_inc;
+				*contpc = regs->regs[insn.mm_i_format.rs];
+				return 1;
+			}
+		}
+		break;
+	case mm_pool32i_op:
+		switch (insn.mm_i_format.rt) {
+		case mm_bltzals_op:
+		case mm_bltzal_op:
+			regs->regs[31] = regs->cp0_epc +
+				dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+			fallthrough;
+		case mm_bltz_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] < 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_bgezals_op:
+		case mm_bgezal_op:
+			regs->regs[31] = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			fallthrough;
+		case mm_bgez_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] >= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_blez_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_bgtz_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+#ifdef CONFIG_MIPS_FP_SUPPORT
+		case mm_bc2f_op:
+		case mm_bc1f_op: {
+			unsigned int fcr31;
+			unsigned int bit;
+
+			bc_false = 1;
+			fallthrough;
+		case mm_bc2t_op:
+		case mm_bc1t_op:
+			preempt_disable();
+			if (is_fpu_owner())
+			        fcr31 = read_32bit_cp1_register(CP1_STATUS);
+			else
+				fcr31 = current->thread.fpu.fcr31;
+			preempt_enable();
+
+			if (bc_false)
+				fcr31 = ~fcr31;
+
+			bit = (insn.mm_i_format.rs >> 2);
+			bit += (bit != 0);
+			bit += 23;
+			if (fcr31 & (1 << bit))
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc + dec_insn.next_pc_inc;
+			return 1;
+		}
+#endif /* CONFIG_MIPS_FP_SUPPORT */
+		}
+		break;
+	case mm_pool16c_op:
+		switch (insn.mm_i_format.rt) {
+		case mm_jalr16_op:
+		case mm_jalrs16_op:
+			regs->regs[31] = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+			fallthrough;
+		case mm_jr16_op:
+			*contpc = regs->regs[insn.mm_i_format.rs];
+			return 1;
+		}
+		break;
+	case mm_beqz16_op:
+		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] == 0)
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_b1_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_bnez16_op:
+		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0)
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_b1_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_b16_op:
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			 (insn.mm_b0_format.simmediate << 1);
+		return 1;
+	case mm_beq32_op:
+		if (regs->regs[insn.mm_i_format.rs] ==
+		    regs->regs[insn.mm_i_format.rt])
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_i_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+		return 1;
+	case mm_bne32_op:
+		if (regs->regs[insn.mm_i_format.rs] !=
+		    regs->regs[insn.mm_i_format.rt])
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_i_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_jalx32_op:
+		regs->regs[31] = regs->cp0_epc +
+			dec_insn.pc_inc + dec_insn.next_pc_inc;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc;
+		*contpc >>= 28;
+		*contpc <<= 28;
+		*contpc |= (insn.j_format.target << 2);
+		return 1;
+	case mm_jals32_op:
+	case mm_jal32_op:
+		regs->regs[31] = regs->cp0_epc +
+			dec_insn.pc_inc + dec_insn.next_pc_inc;
+		fallthrough;
+	case mm_j32_op:
+		*contpc = regs->cp0_epc + dec_insn.pc_inc;
+		*contpc >>= 27;
+		*contpc <<= 27;
+		*contpc |= (insn.j_format.target << 1);
+		set_isa16_mode(*contpc);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Compute return address and emulate branch in microMIPS mode after an
+ * exception only. It does not handle compact branches/jumps and cannot
+ * be used in interrupt context. (Compact branches/jumps do not cause
+ * exceptions.)
+ */
+int __microMIPS_compute_return_epc(struct pt_regs *regs)
+{
+	u16 __user *pc16;
+	u16 halfword;
+	unsigned int word;
+	unsigned long contpc;
+	struct mm_decoded_insn mminsn = { 0 };
+
+	mminsn.micro_mips_mode = 1;
+
+	/* This load never faults. */
+	pc16 = (unsigned short __user *)msk_isa16_mode(regs->cp0_epc);
+	__get_user(halfword, pc16);
+	pc16++;
+	contpc = regs->cp0_epc + 2;
+	word = ((unsigned int)halfword << 16);
+	mminsn.pc_inc = 2;
+
+	if (!mm_insn_16bit(halfword)) {
+		__get_user(halfword, pc16);
+		pc16++;
+		contpc = regs->cp0_epc + 4;
+		mminsn.pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.insn = word;
+
+	if (get_user(halfword, pc16))
+		goto sigsegv;
+	mminsn.next_pc_inc = 2;
+	word = ((unsigned int)halfword << 16);
+
+	if (!mm_insn_16bit(halfword)) {
+		pc16++;
+		if (get_user(halfword, pc16))
+			goto sigsegv;
+		mminsn.next_pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.next_insn = word;
+
+	mm_isBranchInstr(regs, mminsn, &contpc);
+
+	regs->cp0_epc = contpc;
+
+	return 0;
+
+sigsegv:
+	force_sig(SIGSEGV);
+	return -EFAULT;
+}
+
+/*
+ * Compute return address and emulate branch in MIPS16e mode after an
+ * exception only. It does not handle compact branches/jumps and cannot
+ * be used in interrupt context. (Compact branches/jumps do not cause
+ * exceptions.)
+ */
+int __MIPS16e_compute_return_epc(struct pt_regs *regs)
+{
+	u16 __user *addr;
+	union mips16e_instruction inst;
+	u16 inst2;
+	u32 fullinst;
+	long epc;
+
+	epc = regs->cp0_epc;
+
+	/* Read the instruction. */
+	addr = (u16 __user *)msk_isa16_mode(epc);
+	if (__get_user(inst.full, addr)) {
+		force_sig(SIGSEGV);
+		return -EFAULT;
+	}
+
+	switch (inst.ri.opcode) {
+	case MIPS16e_extend_op:
+		regs->cp0_epc += 4;
+		return 0;
+
+		/*
+		 *  JAL and JALX in MIPS16e mode
+		 */
+	case MIPS16e_jal_op:
+		addr += 1;
+		if (__get_user(inst2, addr)) {
+			force_sig(SIGSEGV);
+			return -EFAULT;
+		}
+		fullinst = ((unsigned)inst.full << 16) | inst2;
+		regs->regs[31] = epc + 6;
+		epc += 4;
+		epc >>= 28;
+		epc <<= 28;
+		/*
+		 * JAL:5 X:1 TARGET[20-16]:5 TARGET[25:21]:5 TARGET[15:0]:16
+		 *
+		 * ......TARGET[15:0].................TARGET[20:16]...........
+		 * ......TARGET[25:21]
+		 */
+		epc |=
+		    ((fullinst & 0xffff) << 2) | ((fullinst & 0x3e00000) >> 3) |
+		    ((fullinst & 0x1f0000) << 7);
+		if (!inst.jal.x)
+			set_isa16_mode(epc);	/* Set ISA mode bit. */
+		regs->cp0_epc = epc;
+		return 0;
+
+		/*
+		 *  J(AL)R(C)
+		 */
+	case MIPS16e_rr_op:
+		if (inst.rr.func == MIPS16e_jr_func) {
+
+			if (inst.rr.ra)
+				regs->cp0_epc = regs->regs[31];
+			else
+				regs->cp0_epc =
+				    regs->regs[reg16to32[inst.rr.rx]];
+
+			if (inst.rr.l) {
+				if (inst.rr.nd)
+					regs->regs[31] = epc + 2;
+				else
+					regs->regs[31] = epc + 4;
+			}
+			return 0;
+		}
+		break;
+	}
+
+	/*
+	 * All other cases have no branch delay slot and are 16-bits.
+	 * Branches do not cause an exception.
+	 */
+	regs->cp0_epc += 2;
+
+	return 0;
+}
+
+/**
+ * __compute_return_epc_for_insn - Computes the return address and do emulate
+ *				    branch simulation, if required.
+ *
+ * @regs:	Pointer to pt_regs
+ * @insn:	branch instruction to decode
+ * Return:	-EFAULT on error and forces SIGILL, and on success
+ *		returns 0 or BRANCH_LIKELY_TAKEN as appropriate after
+ *		evaluating the branch.
+ *
+ * MIPS R6 Compact branches and forbidden slots:
+ *	Compact branches do not throw exceptions because they do
+ *	not have delay slots. The forbidden slot instruction ($PC+4)
+ *	is only executed if the branch was not taken. Otherwise the
+ *	forbidden slot is skipped entirely. This means that the
+ *	only possible reason to be here because of a MIPS R6 compact
+ *	branch instruction is that the forbidden slot has thrown one.
+ *	In that case the branch was not taken, so the EPC can be safely
+ *	set to EPC + 8.
+ */
+int __compute_return_epc_for_insn(struct pt_regs *regs,
+				   union mips_instruction insn)
+{
+	long epc = regs->cp0_epc;
+	unsigned int dspcontrol;
+	int ret = 0;
+
+	switch (insn.i_format.opcode) {
+	/*
+	 * jr and jalr are in r_format format.
+	 */
+	case spec_op:
+		switch (insn.r_format.func) {
+		case jalr_op:
+			regs->regs[insn.r_format.rd] = epc + 8;
+			fallthrough;
+		case jr_op:
+			if (NO_R6EMU && insn.r_format.func == jr_op)
+				goto sigill_r2r6;
+			regs->cp0_epc = regs->regs[insn.r_format.rs];
+			break;
+		}
+		break;
+
+	/*
+	 * This group contains:
+	 * bltz_op, bgez_op, bltzl_op, bgezl_op,
+	 * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
+	 */
+	case bcond_op:
+		switch (insn.i_format.rt) {
+		case bltzl_op:
+			if (NO_R6EMU)
+				goto sigill_r2r6;
+			fallthrough;
+		case bltz_op:
+			if ((long)regs->regs[insn.i_format.rs] < 0) {
+				epc = epc + 4 + (insn.i_format.simmediate << 2);
+				if (insn.i_format.rt == bltzl_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
+				epc += 8;
+			regs->cp0_epc = epc;
+			break;
+
+		case bgezl_op:
+			if (NO_R6EMU)
+				goto sigill_r2r6;
+			fallthrough;
+		case bgez_op:
+			if ((long)regs->regs[insn.i_format.rs] >= 0) {
+				epc = epc + 4 + (insn.i_format.simmediate << 2);
+				if (insn.i_format.rt == bgezl_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
+				epc += 8;
+			regs->cp0_epc = epc;
+			break;
+
+		case bltzal_op:
+		case bltzall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bltzall_op))
+				goto sigill_r2r6;
+			regs->regs[31] = epc + 8;
+			/*
+			 * OK we are here either because we hit a NAL
+			 * instruction or because we are emulating an
+			 * old bltzal{,l} one. Let's figure out what the
+			 * case really is.
+			 */
+			if (!insn.i_format.rs) {
+				/*
+				 * NAL or BLTZAL with rs == 0
+				 * Doesn't matter if we are R6 or not. The
+				 * result is the same
+				 */
+				regs->cp0_epc += 4 +
+					(insn.i_format.simmediate << 2);
+				break;
+			}
+			/* Now do the real thing for non-R6 BLTZAL{,L} */
+			if ((long)regs->regs[insn.i_format.rs] < 0) {
+				epc = epc + 4 + (insn.i_format.simmediate << 2);
+				if (insn.i_format.rt == bltzall_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
+				epc += 8;
+			regs->cp0_epc = epc;
+			break;
+
+		case bgezal_op:
+		case bgezall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bgezall_op))
+				goto sigill_r2r6;
+			regs->regs[31] = epc + 8;
+			/*
+			 * OK we are here either because we hit a BAL
+			 * instruction or because we are emulating an
+			 * old bgezal{,l} one. Let's figure out what the
+			 * case really is.
+			 */
+			if (!insn.i_format.rs) {
+				/*
+				 * BAL or BGEZAL with rs == 0
+				 * Doesn't matter if we are R6 or not. The
+				 * result is the same
+				 */
+				regs->cp0_epc += 4 +
+					(insn.i_format.simmediate << 2);
+				break;
+			}
+			/* Now do the real thing for non-R6 BGEZAL{,L} */
+			if ((long)regs->regs[insn.i_format.rs] >= 0) {
+				epc = epc + 4 + (insn.i_format.simmediate << 2);
+				if (insn.i_format.rt == bgezall_op)
+					ret = BRANCH_LIKELY_TAKEN;
+			} else
+				epc += 8;
+			regs->cp0_epc = epc;
+			break;
+
+		case bposge32_op:
+			if (!cpu_has_dsp)
+				goto sigill_dsp;
+
+			dspcontrol = rddsp(0x01);
+
+			if (dspcontrol >= 32) {
+				epc = epc + 4 + (insn.i_format.simmediate << 2);
+			} else
+				epc += 8;
+			regs->cp0_epc = epc;
+			break;
+		}
+		break;
+
+	/*
+	 * These are unconditional and in j_format.
+	 */
+	case jalx_op:
+	case jal_op:
+		regs->regs[31] = regs->cp0_epc + 8;
+		fallthrough;
+	case j_op:
+		epc += 4;
+		epc >>= 28;
+		epc <<= 28;
+		epc |= (insn.j_format.target << 2);
+		regs->cp0_epc = epc;
+		if (insn.i_format.opcode == jalx_op)
+			set_isa16_mode(regs->cp0_epc);
+		break;
+
+	/*
+	 * These are conditional and in i_format.
+	 */
+	case beql_op:
+		if (NO_R6EMU)
+			goto sigill_r2r6;
+		fallthrough;
+	case beq_op:
+		if (regs->regs[insn.i_format.rs] ==
+		    regs->regs[insn.i_format.rt]) {
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+			if (insn.i_format.opcode == beql_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+
+	case bnel_op:
+		if (NO_R6EMU)
+			goto sigill_r2r6;
+		fallthrough;
+	case bne_op:
+		if (regs->regs[insn.i_format.rs] !=
+		    regs->regs[insn.i_format.rt]) {
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+			if (insn.i_format.opcode == bnel_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+
+	case blezl_op: /* not really i_format */
+		if (!insn.i_format.rt && NO_R6EMU)
+			goto sigill_r2r6;
+		fallthrough;
+	case blez_op:
+		/*
+		 * Compact branches for R6 for the
+		 * blez and blezl opcodes.
+		 * BLEZ  | rs = 0 | rt != 0  == BLEZALC
+		 * BLEZ  | rs = rt != 0      == BGEZALC
+		 * BLEZ  | rs != 0 | rt != 0 == BGEUC
+		 * BLEZL | rs = 0 | rt != 0  == BLEZC
+		 * BLEZL | rs = rt != 0      == BGEZC
+		 * BLEZL | rs != 0 | rt != 0 == BGEC
+		 *
+		 * For real BLEZ{,L}, rt is always 0.
+		 */
+
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			     (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = epc + 4;
+			regs->cp0_epc += 8;
+			break;
+		}
+		/* rt field assumed to be zero */
+		if ((long)regs->regs[insn.i_format.rs] <= 0) {
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+			if (insn.i_format.opcode == blezl_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+
+	case bgtzl_op:
+		if (!insn.i_format.rt && NO_R6EMU)
+			goto sigill_r2r6;
+		fallthrough;
+	case bgtz_op:
+		/*
+		 * Compact branches for R6 for the
+		 * bgtz and bgtzl opcodes.
+		 * BGTZ  | rs = 0 | rt != 0  == BGTZALC
+		 * BGTZ  | rs = rt != 0      == BLTZALC
+		 * BGTZ  | rs != 0 | rt != 0 == BLTUC
+		 * BGTZL | rs = 0 | rt != 0  == BGTZC
+		 * BGTZL | rs = rt != 0      == BLTZC
+		 * BGTZL | rs != 0 | rt != 0 == BLTC
+		 *
+		 * *ZALC varint for BGTZ &&& rt != 0
+		 * For real GTZ{,L}, rt is always 0.
+		 */
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			    (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = epc + 4;
+			regs->cp0_epc += 8;
+			break;
+		}
+
+		/* rt field assumed to be zero */
+		if ((long)regs->regs[insn.i_format.rs] > 0) {
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+			if (insn.i_format.opcode == bgtzl_op)
+				ret = BRANCH_LIKELY_TAKEN;
+		} else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+
+#ifdef CONFIG_MIPS_FP_SUPPORT
+	/*
+	 * And now the FPA/cp1 branch instructions.
+	 */
+	case cop1_op: {
+		unsigned int bit, fcr31, reg;
+
+		if (cpu_has_mips_r6 &&
+		    ((insn.i_format.rs == bc1eqz_op) ||
+		     (insn.i_format.rs == bc1nez_op))) {
+			if (!init_fp_ctx(current))
+				lose_fpu(1);
+			reg = insn.i_format.rt;
+			bit = get_fpr32(&current->thread.fpu.fpr[reg], 0) & 0x1;
+			if (insn.i_format.rs == bc1eqz_op)
+				bit = !bit;
+			own_fpu(1);
+			if (bit)
+				epc = epc + 4 +
+					(insn.i_format.simmediate << 2);
+			else
+				epc += 8;
+			regs->cp0_epc = epc;
+
+			break;
+		} else {
+
+			preempt_disable();
+			if (is_fpu_owner())
+			        fcr31 = read_32bit_cp1_register(CP1_STATUS);
+			else
+				fcr31 = current->thread.fpu.fcr31;
+			preempt_enable();
+
+			bit = (insn.i_format.rt >> 2);
+			bit += (bit != 0);
+			bit += 23;
+			switch (insn.i_format.rt & 3) {
+			case 0: /* bc1f */
+			case 2: /* bc1fl */
+				if (~fcr31 & (1 << bit)) {
+					epc = epc + 4 +
+						(insn.i_format.simmediate << 2);
+					if (insn.i_format.rt == 2)
+						ret = BRANCH_LIKELY_TAKEN;
+				} else
+					epc += 8;
+				regs->cp0_epc = epc;
+				break;
+
+			case 1: /* bc1t */
+			case 3: /* bc1tl */
+				if (fcr31 & (1 << bit)) {
+					epc = epc + 4 +
+						(insn.i_format.simmediate << 2);
+					if (insn.i_format.rt == 3)
+						ret = BRANCH_LIKELY_TAKEN;
+				} else
+					epc += 8;
+				regs->cp0_epc = epc;
+				break;
+			}
+			break;
+		}
+	}
+#endif /* CONFIG_MIPS_FP_SUPPORT */
+
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+	case lwc2_op: /* This is bbit0 on Octeon */
+		if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
+		     == 0)
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+	case ldc2_op: /* This is bbit032 on Octeon */
+		if ((regs->regs[insn.i_format.rs] &
+		    (1ull<<(insn.i_format.rt+32))) == 0)
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+	case swc2_op: /* This is bbit1 on Octeon */
+		if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+	case sdc2_op: /* This is bbit132 on Octeon */
+		if (regs->regs[insn.i_format.rs] &
+		    (1ull<<(insn.i_format.rt+32)))
+			epc = epc + 4 + (insn.i_format.simmediate << 2);
+		else
+			epc += 8;
+		regs->cp0_epc = epc;
+		break;
+#else
+	case bc6_op:
+		/* Only valid for MIPS R6 */
+		if (!cpu_has_mips_r6)
+			goto sigill_r6;
+		regs->cp0_epc += 8;
+		break;
+	case balc6_op:
+		if (!cpu_has_mips_r6)
+			goto sigill_r6;
+		/* Compact branch: BALC */
+		regs->regs[31] = epc + 4;
+		epc += 4 + (insn.i_format.simmediate << 2);
+		regs->cp0_epc = epc;
+		break;
+	case pop66_op:
+		if (!cpu_has_mips_r6)
+			goto sigill_r6;
+		/* Compact branch: BEQZC || JIC */
+		regs->cp0_epc += 8;
+		break;
+	case pop76_op:
+		if (!cpu_has_mips_r6)
+			goto sigill_r6;
+		/* Compact branch: BNEZC || JIALC */
+		if (!insn.i_format.rs) {
+			/* JIALC: set $31/ra */
+			regs->regs[31] = epc + 4;
+		}
+		regs->cp0_epc += 8;
+		break;
+#endif
+	case pop10_op:
+	case pop30_op:
+		/* Only valid for MIPS R6 */
+		if (!cpu_has_mips_r6)
+			goto sigill_r6;
+		/*
+		 * Compact branches:
+		 * bovc, beqc, beqzalc, bnvc, bnec, bnezlac
+		 */
+		if (insn.i_format.rt && !insn.i_format.rs)
+			regs->regs[31] = epc + 4;
+		regs->cp0_epc += 8;
+		break;
+	}
+
+	return ret;
+
+sigill_dsp:
+	pr_debug("%s: DSP branch but not DSP ASE - sending SIGILL.\n",
+		 current->comm);
+	force_sig(SIGILL);
+	return -EFAULT;
+sigill_r2r6:
+	pr_debug("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n",
+		 current->comm);
+	force_sig(SIGILL);
+	return -EFAULT;
+sigill_r6:
+	pr_debug("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n",
+		 current->comm);
+	force_sig(SIGILL);
+	return -EFAULT;
+}
+EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn);
+
+int __compute_return_epc(struct pt_regs *regs)
+{
+	unsigned int __user *addr;
+	long epc;
+	union mips_instruction insn;
+
+	epc = regs->cp0_epc;
+	if (epc & 3)
+		goto unaligned;
+
+	/*
+	 * Read the instruction
+	 */
+	addr = (unsigned int __user *) epc;
+	if (__get_user(insn.word, addr)) {
+		force_sig(SIGSEGV);
+		return -EFAULT;
+	}
+
+	return __compute_return_epc_for_insn(regs, insn);
+
+unaligned:
+	printk("%s: unaligned epc - sending SIGBUS.\n", current->comm);
+	force_sig(SIGBUS);
+	return -EFAULT;
+}
+
+#if (defined CONFIG_KPROBES) || (defined CONFIG_UPROBES)
+
+int __insn_is_compact_branch(union mips_instruction insn)
+{
+	if (!cpu_has_mips_r6)
+		return 0;
+
+	switch (insn.i_format.opcode) {
+	case blezl_op:
+	case bgtzl_op:
+	case blez_op:
+	case bgtz_op:
+		/*
+		 * blez[l] and bgtz[l] opcodes with non-zero rt
+		 * are MIPS R6 compact branches
+		 */
+		if (insn.i_format.rt)
+			return 1;
+		break;
+	case bc6_op:
+	case balc6_op:
+	case pop10_op:
+	case pop30_op:
+	case pop66_op:
+	case pop76_op:
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__insn_is_compact_branch);
+
+#endif  /* CONFIG_KPROBES || CONFIG_UPROBES */