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/arm/mach-hisi/platmcpm.c | 346 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 346 insertions(+) create mode 100644 arch/arm/mach-hisi/platmcpm.c (limited to 'arch/arm/mach-hisi/platmcpm.c') diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c new file mode 100644 index 000000000..258586e31 --- /dev/null +++ b/arch/arm/mach-hisi/platmcpm.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013-2014 Linaro Ltd. + * Copyright (c) 2013-2014 HiSilicon Limited. + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "core.h" + +/* bits definition in SC_CPU_RESET_REQ[x]/SC_CPU_RESET_DREQ[x] + * 1 -- unreset; 0 -- reset + */ +#define CORE_RESET_BIT(x) (1 << x) +#define NEON_RESET_BIT(x) (1 << (x + 4)) +#define CORE_DEBUG_RESET_BIT(x) (1 << (x + 9)) +#define CLUSTER_L2_RESET_BIT (1 << 8) +#define CLUSTER_DEBUG_RESET_BIT (1 << 13) + +/* + * bits definition in SC_CPU_RESET_STATUS[x] + * 1 -- reset status; 0 -- unreset status + */ +#define CORE_RESET_STATUS(x) (1 << x) +#define NEON_RESET_STATUS(x) (1 << (x + 4)) +#define CORE_DEBUG_RESET_STATUS(x) (1 << (x + 9)) +#define CLUSTER_L2_RESET_STATUS (1 << 8) +#define CLUSTER_DEBUG_RESET_STATUS (1 << 13) +#define CORE_WFI_STATUS(x) (1 << (x + 16)) +#define CORE_WFE_STATUS(x) (1 << (x + 20)) +#define CORE_DEBUG_ACK(x) (1 << (x + 24)) + +#define SC_CPU_RESET_REQ(x) (0x520 + (x << 3)) /* reset */ +#define SC_CPU_RESET_DREQ(x) (0x524 + (x << 3)) /* unreset */ +#define SC_CPU_RESET_STATUS(x) (0x1520 + (x << 3)) + +#define FAB_SF_MODE 0x0c +#define FAB_SF_INVLD 0x10 + +/* bits definition in FB_SF_INVLD */ +#define FB_SF_INVLD_START (1 << 8) + +#define HIP04_MAX_CLUSTERS 4 +#define HIP04_MAX_CPUS_PER_CLUSTER 4 + +#define POLL_MSEC 10 +#define TIMEOUT_MSEC 1000 + +static void __iomem *sysctrl, *fabric; +static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +static DEFINE_SPINLOCK(boot_lock); +static u32 fabric_phys_addr; +/* + * [0]: bootwrapper physical address + * [1]: bootwrapper size + * [2]: relocation address + * [3]: relocation size + */ +static u32 hip04_boot_method[4]; + +static bool hip04_cluster_is_down(unsigned int cluster) +{ + int i; + + for (i = 0; i < HIP04_MAX_CPUS_PER_CLUSTER; i++) + if (hip04_cpu_table[cluster][i]) + return false; + return true; +} + +static void hip04_set_snoop_filter(unsigned int cluster, unsigned int on) +{ + unsigned long data; + + if (!fabric) + BUG(); + data = readl_relaxed(fabric + FAB_SF_MODE); + if (on) + data |= 1 << cluster; + else + data &= ~(1 << cluster); + writel_relaxed(data, fabric + FAB_SF_MODE); + do { + cpu_relax(); + } while (data != readl_relaxed(fabric + FAB_SF_MODE)); +} + +static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle) +{ + unsigned int mpidr, cpu, cluster; + unsigned long data; + void __iomem *sys_dreq, *sys_status; + + mpidr = cpu_logical_map(l_cpu); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + if (!sysctrl) + return -ENODEV; + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + + spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; + + sys_dreq = sysctrl + SC_CPU_RESET_DREQ(cluster); + sys_status = sysctrl + SC_CPU_RESET_STATUS(cluster); + if (hip04_cluster_is_down(cluster)) { + data = CLUSTER_DEBUG_RESET_BIT; + writel_relaxed(data, sys_dreq); + do { + cpu_relax(); + data = readl_relaxed(sys_status); + } while (data & CLUSTER_DEBUG_RESET_STATUS); + hip04_set_snoop_filter(cluster, 1); + } + + data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \ + CORE_DEBUG_RESET_BIT(cpu); + writel_relaxed(data, sys_dreq); + do { + cpu_relax(); + } while (data == readl_relaxed(sys_status)); + + /* + * We may fail to power up core again without this delay. + * It's not mentioned in document. It's found by test. + */ + udelay(20); + + arch_send_wakeup_ipi_mask(cpumask_of(l_cpu)); + +out: + hip04_cpu_table[cluster][cpu]++; + spin_unlock_irq(&boot_lock); + + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static void hip04_cpu_die(unsigned int l_cpu) +{ + unsigned int mpidr, cpu, cluster; + bool last_man; + + mpidr = cpu_logical_map(l_cpu); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + spin_lock(&boot_lock); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { + /* A power_up request went ahead of us. */ + spin_unlock(&boot_lock); + return; + } else if (hip04_cpu_table[cluster][cpu] > 1) { + pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); + BUG(); + } + + last_man = hip04_cluster_is_down(cluster); + spin_unlock(&boot_lock); + if (last_man) { + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( + "mcr p15, 1, %0, c15, c0, 3 \n\t" + "isb \n\t" + "dsb " + : : "r" (0x400) ); + v7_exit_coherency_flush(all); + } else { + v7_exit_coherency_flush(louis); + } + + for (;;) + wfi(); +} + +static int hip04_cpu_kill(unsigned int l_cpu) +{ + unsigned int mpidr, cpu, cluster; + unsigned int data, tries, count; + + mpidr = cpu_logical_map(l_cpu); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + BUG_ON(cluster >= HIP04_MAX_CLUSTERS || + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; + spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) + goto err; + cpu_relax(); + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; + spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); + spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; + data = CORE_RESET_BIT(cpu) | NEON_RESET_BIT(cpu) | \ + CORE_DEBUG_RESET_BIT(cpu); + writel_relaxed(data, sysctrl + SC_CPU_RESET_REQ(cluster)); + for (tries = 0; tries < count; tries++) { + cpu_relax(); + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_RESET_STATUS(cpu)) + break; + } + if (tries >= count) + goto err; + if (hip04_cluster_is_down(cluster)) + hip04_set_snoop_filter(cluster, 0); + spin_unlock_irq(&boot_lock); + return 1; +err: + spin_unlock_irq(&boot_lock); + return 0; +} +#endif + +static const struct smp_operations hip04_smp_ops __initconst = { + .smp_boot_secondary = hip04_boot_secondary, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_die = hip04_cpu_die, + .cpu_kill = hip04_cpu_kill, +#endif +}; + +static bool __init hip04_cpu_table_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + if (cluster >= HIP04_MAX_CLUSTERS || + cpu >= HIP04_MAX_CPUS_PER_CLUSTER) { + pr_err("%s: boot CPU is out of bound!\n", __func__); + return false; + } + hip04_set_snoop_filter(cluster, 1); + hip04_cpu_table[cluster][cpu] = 1; + return true; +} + +static int __init hip04_smp_init(void) +{ + struct device_node *np, *np_sctl, *np_fab; + struct resource fab_res; + void __iomem *relocation; + int ret = -ENODEV; + + np = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-bootwrapper"); + if (!np) + goto err; + ret = of_property_read_u32_array(np, "boot-method", + &hip04_boot_method[0], 4); + if (ret) + goto err; + + ret = -ENODEV; + np_sctl = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl"); + if (!np_sctl) + goto err; + np_fab = of_find_compatible_node(NULL, NULL, "hisilicon,hip04-fabric"); + if (!np_fab) + goto err; + + ret = memblock_reserve(hip04_boot_method[0], hip04_boot_method[1]); + if (ret) + goto err; + + relocation = ioremap(hip04_boot_method[2], hip04_boot_method[3]); + if (!relocation) { + pr_err("failed to map relocation space\n"); + ret = -ENOMEM; + goto err_reloc; + } + sysctrl = of_iomap(np_sctl, 0); + if (!sysctrl) { + pr_err("failed to get sysctrl base\n"); + ret = -ENOMEM; + goto err_sysctrl; + } + ret = of_address_to_resource(np_fab, 0, &fab_res); + if (ret) { + pr_err("failed to get fabric base phys\n"); + goto err_fabric; + } + fabric_phys_addr = fab_res.start; + sync_cache_w(&fabric_phys_addr); + fabric = of_iomap(np_fab, 0); + if (!fabric) { + pr_err("failed to get fabric base\n"); + ret = -ENOMEM; + goto err_fabric; + } + + if (!hip04_cpu_table_init()) { + ret = -EINVAL; + goto err_table; + } + + /* + * Fill the instruction address that is used after secondary core + * out of reset. + */ + writel_relaxed(hip04_boot_method[0], relocation); + writel_relaxed(0xa5a5a5a5, relocation + 4); /* magic number */ + writel_relaxed(__pa_symbol(secondary_startup), relocation + 8); + writel_relaxed(0, relocation + 12); + iounmap(relocation); + + smp_set_ops(&hip04_smp_ops); + return ret; +err_table: + iounmap(fabric); +err_fabric: + iounmap(sysctrl); +err_sysctrl: + iounmap(relocation); +err_reloc: + memblock_phys_free(hip04_boot_method[0], hip04_boot_method[1]); +err: + return ret; +} +early_initcall(hip04_smp_init); -- cgit v1.2.3