From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- arch/xtensa/kernel/coprocessor.S | 302 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 302 insertions(+) create mode 100644 arch/xtensa/kernel/coprocessor.S (limited to 'arch/xtensa/kernel/coprocessor.S') diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S new file mode 100644 index 000000000..ef33e76e0 --- /dev/null +++ b/arch/xtensa/kernel/coprocessor.S @@ -0,0 +1,302 @@ +/* + * arch/xtensa/kernel/coprocessor.S + * + * Xtensa processor configuration-specific table of coprocessor and + * other custom register layout information. + * + * 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) 2003 - 2007 Tensilica Inc. + */ + + +#include +#include +#include +#include +#include +#include + +/* + * Rules for coprocessor state manipulation on SMP: + * + * - a task may have live coprocessors only on one CPU. + * + * - whether coprocessor context of task T is live on some CPU is + * denoted by T's thread_info->cpenable. + * + * - non-zero thread_info->cpenable means that thread_info->cp_owner_cpu + * is valid in the T's thread_info. Zero thread_info->cpenable means that + * coprocessor context is valid in the T's thread_info. + * + * - if a coprocessor context of task T is live on CPU X, only CPU X changes + * T's thread_info->cpenable, cp_owner_cpu and coprocessor save area. + * This is done by making sure that for the task T with live coprocessor + * on CPU X cpenable SR is 0 when T runs on any other CPU Y. + * When fast_coprocessor exception is taken on CPU Y it goes to the + * C-level do_coprocessor that uses IPI to make CPU X flush T's coprocessors. + */ + +#if XTENSA_HAVE_COPROCESSORS + +/* + * Macros for lazy context switch. + */ + +#define SAVE_CP_REGS(x) \ + .if XTENSA_HAVE_COPROCESSOR(x); \ + .align 4; \ + .Lsave_cp_regs_cp##x: \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ + ret; \ + .endif + +#define LOAD_CP_REGS(x) \ + .if XTENSA_HAVE_COPROCESSOR(x); \ + .align 4; \ + .Lload_cp_regs_cp##x: \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ + ret; \ + .endif + +#define CP_REGS_TAB(x) \ + .if XTENSA_HAVE_COPROCESSOR(x); \ + .long .Lsave_cp_regs_cp##x; \ + .long .Lload_cp_regs_cp##x; \ + .else; \ + .long 0, 0; \ + .endif; \ + .long THREAD_XTREGS_CP##x + +#define CP_REGS_TAB_SAVE 0 +#define CP_REGS_TAB_LOAD 4 +#define CP_REGS_TAB_OFFSET 8 + + __XTENSA_HANDLER + + SAVE_CP_REGS(0) + SAVE_CP_REGS(1) + SAVE_CP_REGS(2) + SAVE_CP_REGS(3) + SAVE_CP_REGS(4) + SAVE_CP_REGS(5) + SAVE_CP_REGS(6) + SAVE_CP_REGS(7) + + LOAD_CP_REGS(0) + LOAD_CP_REGS(1) + LOAD_CP_REGS(2) + LOAD_CP_REGS(3) + LOAD_CP_REGS(4) + LOAD_CP_REGS(5) + LOAD_CP_REGS(6) + LOAD_CP_REGS(7) + + .align 4 +.Lcp_regs_jump_table: + CP_REGS_TAB(0) + CP_REGS_TAB(1) + CP_REGS_TAB(2) + CP_REGS_TAB(3) + CP_REGS_TAB(4) + CP_REGS_TAB(5) + CP_REGS_TAB(6) + CP_REGS_TAB(7) + +/* + * Entry condition: + * + * a0: trashed, original value saved on stack (PT_AREG0) + * a1: a1 + * a2: new stack pointer, original in DEPC + * a3: a3 + * depc: a2, original value saved on stack (PT_DEPC) + * excsave_1: dispatch table + * + * PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC + * < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception + */ + +ENTRY(fast_coprocessor) + + s32i a3, a2, PT_AREG3 + +#ifdef CONFIG_SMP + /* + * Check if any coprocessor context is live on another CPU + * and if so go through the C-level coprocessor exception handler + * to flush it to memory. + */ + GET_THREAD_INFO (a0, a2) + l32i a3, a0, THREAD_CPENABLE + beqz a3, .Lload_local + + /* + * Pairs with smp_wmb in local_coprocessor_release_all + * and with both memws below. + */ + memw + l32i a3, a0, THREAD_CPU + l32i a0, a0, THREAD_CP_OWNER_CPU + beq a0, a3, .Lload_local + + rsr a0, ps + l32i a3, a2, PT_AREG3 + bbci.l a0, PS_UM_BIT, 1f + call0 user_exception +1: call0 kernel_exception +#endif + + /* Save remaining registers a1-a3 and SAR */ + +.Lload_local: + rsr a3, sar + s32i a1, a2, PT_AREG1 + s32i a3, a2, PT_SAR + mov a1, a2 + rsr a2, depc + s32i a2, a1, PT_AREG2 + + /* The hal macros require up to 4 temporary registers. We use a3..a6. */ + + s32i a4, a1, PT_AREG4 + s32i a5, a1, PT_AREG5 + s32i a6, a1, PT_AREG6 + s32i a7, a1, PT_AREG7 + s32i a8, a1, PT_AREG8 + s32i a9, a1, PT_AREG9 + s32i a10, a1, PT_AREG10 + + /* Find coprocessor number. Subtract first CP EXCCAUSE from EXCCAUSE */ + + rsr a3, exccause + addi a3, a3, -EXCCAUSE_COPROCESSOR0_DISABLED + + /* Set corresponding CPENABLE bit -> (sar:cp-index, a3: 1<