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/arm64/kernel/vmlinux.lds.S | 389 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 389 insertions(+) create mode 100644 arch/arm64/kernel/vmlinux.lds.S (limited to 'arch/arm64/kernel/vmlinux.lds.S') diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S new file mode 100644 index 000000000..b9202c2ee --- /dev/null +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -0,0 +1,389 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * ld script to make ARM Linux kernel + * taken from the i386 version by Russell King + * Written by Martin Mares + */ + +#include +#ifdef CONFIG_KVM +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + __start___kvm_ex_table = .; \ + *(__kvm_ex_table) \ + __stop___kvm_ex_table = .; + +#define HYPERVISOR_DATA_SECTIONS \ + HYP_SECTION_NAME(.rodata) : { \ + . = ALIGN(PAGE_SIZE); \ + __hyp_rodata_start = .; \ + *(HYP_SECTION_NAME(.data..ro_after_init)) \ + *(HYP_SECTION_NAME(.rodata)) \ + . = ALIGN(PAGE_SIZE); \ + __hyp_rodata_end = .; \ + } + +#define HYPERVISOR_PERCPU_SECTION \ + . = ALIGN(PAGE_SIZE); \ + HYP_SECTION_NAME(.data..percpu) : { \ + *(HYP_SECTION_NAME(.data..percpu)) \ + } + +#define HYPERVISOR_RELOC_SECTION \ + .hyp.reloc : ALIGN(4) { \ + __hyp_reloc_begin = .; \ + *(.hyp.reloc) \ + __hyp_reloc_end = .; \ + } + +#define BSS_FIRST_SECTIONS \ + __hyp_bss_start = .; \ + *(HYP_SECTION_NAME(.bss)) \ + . = ALIGN(PAGE_SIZE); \ + __hyp_bss_end = .; + +/* + * We require that __hyp_bss_start and __bss_start are aligned, and enforce it + * with an assertion. But the BSS_SECTION macro places an empty .sbss section + * between them, which can in some cases cause the linker to misalign them. To + * work around the issue, force a page alignment for __bss_start. + */ +#define SBSS_ALIGN PAGE_SIZE +#else /* CONFIG_KVM */ +#define HYPERVISOR_EXTABLE +#define HYPERVISOR_DATA_SECTIONS +#define HYPERVISOR_PERCPU_SECTION +#define HYPERVISOR_RELOC_SECTION +#define SBSS_ALIGN 0 +#endif + +#define RO_EXCEPTION_TABLE_ALIGN 4 +#define RUNTIME_DISCARD_EXIT + +#include +#include +#include +#include +#include +#include + +#include "image.h" + +OUTPUT_ARCH(aarch64) +ENTRY(_text) + +jiffies = jiffies_64; + +#define HYPERVISOR_TEXT \ + . = ALIGN(PAGE_SIZE); \ + __hyp_idmap_text_start = .; \ + *(.hyp.idmap.text) \ + __hyp_idmap_text_end = .; \ + __hyp_text_start = .; \ + *(.hyp.text) \ + HYPERVISOR_EXTABLE \ + . = ALIGN(PAGE_SIZE); \ + __hyp_text_end = .; + +#define IDMAP_TEXT \ + . = ALIGN(SZ_4K); \ + __idmap_text_start = .; \ + *(.idmap.text) \ + __idmap_text_end = .; + +#ifdef CONFIG_HIBERNATION +#define HIBERNATE_TEXT \ + ALIGN_FUNCTION(); \ + __hibernate_exit_text_start = .; \ + *(.hibernate_exit.text) \ + __hibernate_exit_text_end = .; +#else +#define HIBERNATE_TEXT +#endif + +#ifdef CONFIG_KEXEC_CORE +#define KEXEC_TEXT \ + ALIGN_FUNCTION(); \ + __relocate_new_kernel_start = .; \ + *(.kexec_relocate.text) \ + __relocate_new_kernel_end = .; +#else +#define KEXEC_TEXT +#endif + +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +#define TRAMP_TEXT \ + . = ALIGN(PAGE_SIZE); \ + __entry_tramp_text_start = .; \ + *(.entry.tramp.text) \ + . = ALIGN(PAGE_SIZE); \ + __entry_tramp_text_end = .; \ + *(.entry.tramp.rodata) +#else +#define TRAMP_TEXT +#endif + +#ifdef CONFIG_UNWIND_TABLES +#define UNWIND_DATA_SECTIONS \ + .eh_frame : { \ + __eh_frame_start = .; \ + *(.eh_frame) \ + __eh_frame_end = .; \ + } +#else +#define UNWIND_DATA_SECTIONS +#endif + +/* + * The size of the PE/COFF section that covers the kernel image, which + * runs from _stext to _edata, must be a round multiple of the PE/COFF + * FileAlignment, which we set to its minimum value of 0x200. '_stext' + * itself is 4 KB aligned, so padding out _edata to a 0x200 aligned + * boundary should be sufficient. + */ +PECOFF_FILE_ALIGNMENT = 0x200; + +#ifdef CONFIG_EFI +#define PECOFF_EDATA_PADDING \ + .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } +#else +#define PECOFF_EDATA_PADDING +#endif + +SECTIONS +{ + /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + */ + DISCARDS + /DISCARD/ : { + *(.interp .dynamic) + *(.dynsym .dynstr .hash .gnu.hash) + } + + . = KIMAGE_VADDR; + + .head.text : { + _text = .; + HEAD_TEXT + } + .text : ALIGN(SEGMENT_ALIGN) { /* Real text segment */ + _stext = .; /* Text and read-only data */ + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT + ENTRY_TEXT + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + HYPERVISOR_TEXT + *(.gnu.warning) + . = ALIGN(16); + *(.got) /* Global offset table */ + } + + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the lazy dispatch entries. + */ + .got.plt : { *(.got.plt) } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, + "Unexpected GOT/PLT entries detected!") + + . = ALIGN(SEGMENT_ALIGN); + _etext = .; /* End of text section */ + + /* everything from this point to __init_begin will be marked RO NX */ + RO_DATA(PAGE_SIZE) + + HYPERVISOR_DATA_SECTIONS + + /* code sections that are never executed via the kernel mapping */ + .rodata.text : { + TRAMP_TEXT + HIBERNATE_TEXT + KEXEC_TEXT + IDMAP_TEXT + . = ALIGN(PAGE_SIZE); + } + + idmap_pg_dir = .; + . += PAGE_SIZE; + +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + tramp_pg_dir = .; + . += PAGE_SIZE; +#endif + + reserved_pg_dir = .; + . += PAGE_SIZE; + + swapper_pg_dir = .; + . += PAGE_SIZE; + + . = ALIGN(SEGMENT_ALIGN); + __init_begin = .; + __inittext_begin = .; + + INIT_TEXT_SECTION(8) + + __exittext_begin = .; + .exit.text : { + EXIT_TEXT + } + __exittext_end = .; + + . = ALIGN(4); + .altinstructions : { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } + + UNWIND_DATA_SECTIONS + + . = ALIGN(SEGMENT_ALIGN); + __inittext_end = .; + __initdata_begin = .; + + init_idmap_pg_dir = .; + . += INIT_IDMAP_DIR_SIZE; + init_idmap_pg_end = .; + + .init.data : { + INIT_DATA + INIT_SETUP(16) + INIT_CALLS + CON_INITCALL + INIT_RAM_FS + *(.init.altinstructions .init.bss) /* from the EFI stub */ + } + .exit.data : { + EXIT_DATA + } + + PERCPU_SECTION(L1_CACHE_BYTES) + HYPERVISOR_PERCPU_SECTION + + HYPERVISOR_RELOC_SECTION + + .rela.dyn : ALIGN(8) { + __rela_start = .; + *(.rela .rela*) + __rela_end = .; + } + + .relr.dyn : ALIGN(8) { + __relr_start = .; + *(.relr.dyn) + __relr_end = .; + } + + . = ALIGN(SEGMENT_ALIGN); + __initdata_end = .; + __init_end = .; + + _data = .; + _sdata = .; + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) + + /* + * Data written with the MMU off but read with the MMU on requires + * cache lines to be invalidated, discarding up to a Cache Writeback + * Granule (CWG) of data from the cache. Keep the section that + * requires this type of maintenance to be in its own Cache Writeback + * Granule (CWG) area so the cache maintenance operations don't + * interfere with adjacent data. + */ + .mmuoff.data.write : ALIGN(SZ_2K) { + __mmuoff_data_start = .; + *(.mmuoff.data.write) + } + . = ALIGN(SZ_2K); + .mmuoff.data.read : { + *(.mmuoff.data.read) + __mmuoff_data_end = .; + } + + PECOFF_EDATA_PADDING + __pecoff_data_rawsize = ABSOLUTE(. - __initdata_begin); + _edata = .; + + BSS_SECTION(SBSS_ALIGN, 0, 0) + + . = ALIGN(PAGE_SIZE); + init_pg_dir = .; + . += INIT_DIR_SIZE; + init_pg_end = .; + + . = ALIGN(SEGMENT_ALIGN); + __pecoff_data_size = ABSOLUTE(. - __initdata_begin); + _end = .; + + STABS_DEBUG + DWARF_DEBUG + ELF_DETAILS + + HEAD_SYMBOLS + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .plt : { + *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") + + .data.rel.ro : { *(.data.rel.ro) } + ASSERT(SIZEOF(.data.rel.ro) == 0, "Unexpected RELRO detected!") +} + +#include "image-vars.h" + +/* + * The HYP init code and ID map text can't be longer than a page each. The + * former is page-aligned, but the latter may not be with 16K or 64K pages, so + * it should also not cross a page boundary. + */ +ASSERT(__hyp_idmap_text_end - __hyp_idmap_text_start <= PAGE_SIZE, + "HYP init code too big") +ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, + "ID map text too big or misaligned") +#ifdef CONFIG_HIBERNATION +ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K, + "Hibernate exit text is bigger than 4 KiB") +ASSERT(__hibernate_exit_text_start == swsusp_arch_suspend_exit, + "Hibernate exit text does not start with swsusp_arch_suspend_exit") +#endif +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, + "Entry trampoline text too big") +#endif +#ifdef CONFIG_KVM +ASSERT(__hyp_bss_start == __bss_start, "HYP and Host BSS are misaligned") +#endif +/* + * If padding is applied before .head.text, virt<->phys conversions will fail. + */ +ASSERT(_text == KIMAGE_VADDR, "HEAD is misaligned") + +ASSERT(swapper_pg_dir - reserved_pg_dir == RESERVED_SWAPPER_OFFSET, + "RESERVED_SWAPPER_OFFSET is wrong!") + +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET, + "TRAMP_SWAPPER_OFFSET is wrong!") +#endif + +#ifdef CONFIG_KEXEC_CORE +/* kexec relocation code should fit into one KEXEC_CONTROL_PAGE_SIZE */ +ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K, + "kexec relocation code is bigger than 4 KiB") +ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken") +ASSERT(__relocate_new_kernel_start == arm64_relocate_new_kernel, + "kexec control page does not start with arm64_relocate_new_kernel") +#endif -- cgit v1.2.3