aboutsummaryrefslogtreecommitdiff
path: root/arch/riscv/kernel/setup.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /arch/riscv/kernel/setup.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
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(). ...
Diffstat (limited to 'arch/riscv/kernel/setup.c')
-rw-r--r--arch/riscv/kernel/setup.c332
1 files changed, 332 insertions, 0 deletions
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000..86acd690d
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ * Chen Liqin <liqin.chen@sunplusct.com>
+ * Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2020 FORTH-ICS/CARV
+ * Nick Kossifidis <mick@ics.forth.gr>
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+#include <linux/smp.h>
+#include <linux/efi.h>
+#include <linux/crash_dump.h>
+
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/early_ioremap.h>
+#include <asm/pgtable.h>
+#include <asm/setup.h>
+#include <asm/set_memory.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+#include <asm/kasan.h>
+#include <asm/efi.h>
+
+#include "head.h"
+
+#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
+struct screen_info screen_info __section(".data") = {
+ .orig_video_lines = 30,
+ .orig_video_cols = 80,
+ .orig_video_mode = 0,
+ .orig_video_ega_bx = 0,
+ .orig_video_isVGA = 1,
+ .orig_video_points = 8
+};
+#endif
+
+/*
+ * The lucky hart to first increment this variable will boot the other cores.
+ * This is used before the kernel initializes the BSS so it can't be in the
+ * BSS.
+ */
+atomic_t hart_lottery __section(".sdata")
+#ifdef CONFIG_XIP_KERNEL
+= ATOMIC_INIT(0xC001BEEF)
+#endif
+;
+unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+/*
+ * Place kernel memory regions on the resource tree so that
+ * kexec-tools can retrieve them from /proc/iomem. While there
+ * also add "System RAM" regions for compatibility with other
+ * archs, and the rest of the known regions for completeness.
+ */
+static struct resource kimage_res = { .name = "Kernel image", };
+static struct resource code_res = { .name = "Kernel code", };
+static struct resource data_res = { .name = "Kernel data", };
+static struct resource rodata_res = { .name = "Kernel rodata", };
+static struct resource bss_res = { .name = "Kernel bss", };
+#ifdef CONFIG_CRASH_DUMP
+static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
+#endif
+
+static int __init add_resource(struct resource *parent,
+ struct resource *res)
+{
+ int ret = 0;
+
+ ret = insert_resource(parent, res);
+ if (ret < 0) {
+ pr_err("Failed to add a %s resource at %llx\n",
+ res->name, (unsigned long long) res->start);
+ return ret;
+ }
+
+ return 1;
+}
+
+static int __init add_kernel_resources(void)
+{
+ int ret = 0;
+
+ /*
+ * The memory region of the kernel image is continuous and
+ * was reserved on setup_bootmem, register it here as a
+ * resource, with the various segments of the image as
+ * child nodes.
+ */
+
+ code_res.start = __pa_symbol(_text);
+ code_res.end = __pa_symbol(_etext) - 1;
+ code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+ rodata_res.start = __pa_symbol(__start_rodata);
+ rodata_res.end = __pa_symbol(__end_rodata) - 1;
+ rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+ data_res.start = __pa_symbol(_data);
+ data_res.end = __pa_symbol(_edata) - 1;
+ data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+ bss_res.start = __pa_symbol(__bss_start);
+ bss_res.end = __pa_symbol(__bss_stop) - 1;
+ bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+ kimage_res.start = code_res.start;
+ kimage_res.end = bss_res.end;
+ kimage_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+ ret = add_resource(&iomem_resource, &kimage_res);
+ if (ret < 0)
+ return ret;
+
+ ret = add_resource(&kimage_res, &code_res);
+ if (ret < 0)
+ return ret;
+
+ ret = add_resource(&kimage_res, &rodata_res);
+ if (ret < 0)
+ return ret;
+
+ ret = add_resource(&kimage_res, &data_res);
+ if (ret < 0)
+ return ret;
+
+ ret = add_resource(&kimage_res, &bss_res);
+
+ return ret;
+}
+
+static void __init init_resources(void)
+{
+ struct memblock_region *region = NULL;
+ struct resource *res = NULL;
+ struct resource *mem_res = NULL;
+ size_t mem_res_sz = 0;
+ int num_resources = 0, res_idx = 0;
+ int ret = 0;
+
+ /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
+ num_resources = memblock.memory.cnt + memblock.reserved.cnt + 1;
+ res_idx = num_resources - 1;
+
+ mem_res_sz = num_resources * sizeof(*mem_res);
+ mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+ if (!mem_res)
+ panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
+
+ /*
+ * Start by adding the reserved regions, if they overlap
+ * with /memory regions, insert_resource later on will take
+ * care of it.
+ */
+ ret = add_kernel_resources();
+ if (ret < 0)
+ goto error;
+
+#ifdef CONFIG_KEXEC_CORE
+ if (crashk_res.start != crashk_res.end) {
+ ret = add_resource(&iomem_resource, &crashk_res);
+ if (ret < 0)
+ goto error;
+ }
+#endif
+
+#ifdef CONFIG_CRASH_DUMP
+ if (elfcorehdr_size > 0) {
+ elfcorehdr_res.start = elfcorehdr_addr;
+ elfcorehdr_res.end = elfcorehdr_addr + elfcorehdr_size - 1;
+ elfcorehdr_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ add_resource(&iomem_resource, &elfcorehdr_res);
+ }
+#endif
+
+ for_each_reserved_mem_region(region) {
+ res = &mem_res[res_idx--];
+
+ res->name = "Reserved";
+ res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE;
+ res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
+ res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
+
+ /*
+ * Ignore any other reserved regions within
+ * system memory.
+ */
+ if (memblock_is_memory(res->start)) {
+ /* Re-use this pre-allocated resource */
+ res_idx++;
+ continue;
+ }
+
+ ret = add_resource(&iomem_resource, res);
+ if (ret < 0)
+ goto error;
+ }
+
+ /* Add /memory regions to the resource tree */
+ for_each_mem_region(region) {
+ res = &mem_res[res_idx--];
+
+ if (unlikely(memblock_is_nomap(region))) {
+ res->name = "Reserved";
+ res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE;
+ } else {
+ res->name = "System RAM";
+ res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ }
+
+ res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
+ res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+
+ ret = add_resource(&iomem_resource, res);
+ if (ret < 0)
+ goto error;
+ }
+
+ /* Clean-up any unused pre-allocated resources */
+ if (res_idx >= 0)
+ memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
+ return;
+
+ error:
+ /* Better an empty resource tree than an inconsistent one */
+ release_child_resources(&iomem_resource);
+ memblock_free(mem_res, mem_res_sz);
+}
+
+
+static void __init parse_dtb(void)
+{
+ /* Early scan of device tree from init memory */
+ if (early_init_dt_scan(dtb_early_va)) {
+ const char *name = of_flat_dt_get_machine_name();
+
+ if (name) {
+ pr_info("Machine model: %s\n", name);
+ dump_stack_set_arch_desc("%s (DT)", name);
+ }
+ } else {
+ pr_err("No DTB passed to the kernel\n");
+ }
+
+#ifdef CONFIG_CMDLINE_FORCE
+ strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+ pr_info("Forcing kernel command line to: %s\n", boot_command_line);
+#endif
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+ parse_dtb();
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
+
+ *cmdline_p = boot_command_line;
+
+ early_ioremap_setup();
+ jump_label_init();
+ parse_early_param();
+
+ efi_init();
+ paging_init();
+#if IS_ENABLED(CONFIG_BUILTIN_DTB)
+ unflatten_and_copy_device_tree();
+#else
+ if (early_init_dt_verify(__va(XIP_FIXUP(dtb_early_pa))))
+ unflatten_device_tree();
+ else
+ pr_err("No DTB found in kernel mappings\n");
+#endif
+ early_init_fdt_scan_reserved_mem();
+ misc_mem_init();
+
+ init_resources();
+ sbi_init();
+
+#ifdef CONFIG_KASAN
+ kasan_init();
+#endif
+
+#ifdef CONFIG_SMP
+ setup_smp();
+#endif
+
+ riscv_init_cbom_blocksize();
+ riscv_fill_hwcap();
+ apply_boot_alternatives();
+}
+
+static int __init topology_init(void)
+{
+ int i, ret;
+
+ for_each_possible_cpu(i) {
+ struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+ cpu->hotpluggable = cpu_has_hotplug(i);
+ ret = register_cpu(cpu, i);
+ if (unlikely(ret))
+ pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
+ __func__, i, ret);
+ }
+
+ return 0;
+}
+subsys_initcall(topology_init);
+
+void free_initmem(void)
+{
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
+ set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx);
+ if (IS_ENABLED(CONFIG_64BIT))
+ set_kernel_memory(__init_begin, __init_end, set_memory_nx);
+ }
+
+ free_initmem_default(POISON_FREE_INITMEM);
+}