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/x86/purgatory/.gitignore | 1 + arch/x86/purgatory/Makefile | 83 ++++++++++++++++++++++++++++ arch/x86/purgatory/entry64.S | 103 +++++++++++++++++++++++++++++++++++ arch/x86/purgatory/kexec-purgatory.S | 14 +++++ arch/x86/purgatory/purgatory.c | 59 ++++++++++++++++++++ arch/x86/purgatory/setup-x86_64.S | 59 ++++++++++++++++++++ arch/x86/purgatory/stack.S | 18 ++++++ 7 files changed, 337 insertions(+) create mode 100644 arch/x86/purgatory/.gitignore create mode 100644 arch/x86/purgatory/Makefile create mode 100644 arch/x86/purgatory/entry64.S create mode 100644 arch/x86/purgatory/kexec-purgatory.S create mode 100644 arch/x86/purgatory/purgatory.c create mode 100644 arch/x86/purgatory/setup-x86_64.S create mode 100644 arch/x86/purgatory/stack.S (limited to 'arch/x86/purgatory') diff --git a/arch/x86/purgatory/.gitignore b/arch/x86/purgatory/.gitignore new file mode 100644 index 000000000..d2be15006 --- /dev/null +++ b/arch/x86/purgatory/.gitignore @@ -0,0 +1 @@ +purgatory.chk diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile new file mode 100644 index 000000000..17f09dc26 --- /dev/null +++ b/arch/x86/purgatory/Makefile @@ -0,0 +1,83 @@ +# SPDX-License-Identifier: GPL-2.0 +OBJECT_FILES_NON_STANDARD := y + +purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string.o + +targets += $(purgatory-y) +PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) + +$(obj)/string.o: $(srctree)/arch/x86/boot/compressed/string.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE + $(call if_changed_rule,cc_o_c) + +CFLAGS_sha256.o := -D__DISABLE_EXPORTS + +# When linking purgatory.ro with -r unresolved symbols are not checked, +# also link a purgatory.chk binary without -r to check for unresolved symbols. +PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib +LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS) +LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS) +targets += purgatory.ro purgatory.chk + +# Sanitizer, etc. runtimes are unavailable and cannot be linked here. +GCOV_PROFILE := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +KCSAN_SANITIZE := n +KMSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +# These are adjustments to the compiler flags used for objects that +# make up the standalone purgatory.ro + +PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel +PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0 +PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING +PURGATORY_CFLAGS += -fno-stack-protector + +# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That +# in turn leaves some undefined symbols like __fentry__ in purgatory and not +# sure how to relocate those. +ifdef CONFIG_FUNCTION_TRACER +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_FTRACE) +endif + +ifdef CONFIG_STACKPROTECTOR +PURGATORY_CFLAGS_REMOVE += -fstack-protector +endif + +ifdef CONFIG_STACKPROTECTOR_STRONG +PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong +endif + +ifdef CONFIG_RETPOLINE +PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) +endif + +ifdef CONFIG_CFI_CLANG +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) +endif + +CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_sha256.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_sha256.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_string.o += $(PURGATORY_CFLAGS) + +AFLAGS_REMOVE_setup-x86_$(BITS).o += -Wa,-gdwarf-2 +AFLAGS_REMOVE_entry64.o += -Wa,-gdwarf-2 + +$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE + $(call if_changed,ld) + +$(obj)/purgatory.chk: $(obj)/purgatory.ro FORCE + $(call if_changed,ld) + +$(obj)/kexec-purgatory.o: $(obj)/purgatory.ro $(obj)/purgatory.chk + +obj-y += kexec-purgatory.o diff --git a/arch/x86/purgatory/entry64.S b/arch/x86/purgatory/entry64.S new file mode 100644 index 000000000..0b4390ce5 --- /dev/null +++ b/arch/x86/purgatory/entry64.S @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2003,2004 Eric Biederman (ebiederm@xmission.com) + * Copyright (C) 2014 Red Hat Inc. + + * Author(s): Vivek Goyal + * + * This code has been taken from kexec-tools. + */ + +#include + + .text + .balign 16 + .code64 + +SYM_CODE_START(entry64) + /* Setup a gdt that should be preserved */ + lgdt gdt(%rip) + + /* load the data segments */ + movl $0x18, %eax /* data segment */ + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + movl %eax, %fs + movl %eax, %gs + + /* Setup new stack */ + leaq stack_init(%rip), %rsp + pushq $0x10 /* CS */ + leaq new_cs_exit(%rip), %rax + pushq %rax + lretq +new_cs_exit: + + /* Load the registers */ + movq rax(%rip), %rax + movq rbx(%rip), %rbx + movq rcx(%rip), %rcx + movq rdx(%rip), %rdx + movq rsi(%rip), %rsi + movq rdi(%rip), %rdi + movq rsp(%rip), %rsp + movq rbp(%rip), %rbp + movq r8(%rip), %r8 + movq r9(%rip), %r9 + movq r10(%rip), %r10 + movq r11(%rip), %r11 + movq r12(%rip), %r12 + movq r13(%rip), %r13 + movq r14(%rip), %r14 + movq r15(%rip), %r15 + + /* Jump to the new code... */ + jmpq *rip(%rip) +SYM_CODE_END(entry64) + + .section ".rodata" + .balign 4 +SYM_DATA_START(entry64_regs) +rax: .quad 0x0 +rcx: .quad 0x0 +rdx: .quad 0x0 +rbx: .quad 0x0 +rsp: .quad 0x0 +rbp: .quad 0x0 +rsi: .quad 0x0 +rdi: .quad 0x0 +r8: .quad 0x0 +r9: .quad 0x0 +r10: .quad 0x0 +r11: .quad 0x0 +r12: .quad 0x0 +r13: .quad 0x0 +r14: .quad 0x0 +r15: .quad 0x0 +rip: .quad 0x0 +SYM_DATA_END(entry64_regs) + + /* GDT */ + .section ".rodata" + .balign 16 +SYM_DATA_START_LOCAL(gdt) + /* + * 0x00 unusable segment + * 0x08 unused + * so use them as gdt ptr + */ + .word gdt_end - gdt - 1 + .quad gdt + .word 0, 0, 0 + + /* 0x10 4GB flat code segment */ + .word 0xFFFF, 0x0000, 0x9A00, 0x00AF + + /* 0x18 4GB flat data segment */ + .word 0xFFFF, 0x0000, 0x9200, 0x00CF +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) + +SYM_DATA_START_LOCAL(stack) + .quad 0, 0 +SYM_DATA_END_LABEL(stack, SYM_L_LOCAL, stack_init) diff --git a/arch/x86/purgatory/kexec-purgatory.S b/arch/x86/purgatory/kexec-purgatory.S new file mode 100644 index 000000000..8530fe93b --- /dev/null +++ b/arch/x86/purgatory/kexec-purgatory.S @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + + .section .rodata, "a" + + .align 8 +kexec_purgatory: + .globl kexec_purgatory + .incbin "arch/x86/purgatory/purgatory.ro" +.Lkexec_purgatory_end: + + .align 8 +kexec_purgatory_size: + .globl kexec_purgatory_size + .quad .Lkexec_purgatory_end - kexec_purgatory diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c new file mode 100644 index 000000000..755813992 --- /dev/null +++ b/arch/x86/purgatory/purgatory.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * purgatory: Runs between two kernels + * + * Copyright (C) 2014 Red Hat Inc. + * + * Author: + * Vivek Goyal + */ + +#include +#include +#include +#include +#include + +#include "../boot/string.h" + +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory"); + +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory"); + +static int verify_sha256_digest(void) +{ + struct kexec_sha_region *ptr, *end; + u8 digest[SHA256_DIGEST_SIZE]; + struct sha256_state sctx; + + sha256_init(&sctx); + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) + sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); + + sha256_final(&sctx, digest); + + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) + return 1; + + return 0; +} + +void purgatory(void) +{ + int ret; + + ret = verify_sha256_digest(); + if (ret) { + /* loop forever */ + for (;;) + ; + } +} + +/* + * Defined in order to reuse memcpy() and memset() from + * arch/x86/boot/compressed/string.c + */ +void warn(const char *msg) {} diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S new file mode 100644 index 000000000..89d9e9e53 --- /dev/null +++ b/arch/x86/purgatory/setup-x86_64.S @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * purgatory: setup code + * + * Copyright (C) 2003,2004 Eric Biederman (ebiederm@xmission.com) + * Copyright (C) 2014 Red Hat Inc. + * + * This code has been taken from kexec-tools. + */ +#include +#include + + .text + .balign 16 + .code64 + +SYM_CODE_START(purgatory_start) + /* Load a gdt so I know what the segment registers are */ + lgdt gdt(%rip) + + /* load the data segments */ + movl $0x18, %eax /* data segment */ + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + movl %eax, %fs + movl %eax, %gs + + /* Setup a stack */ + leaq lstack_end(%rip), %rsp + + /* Call the C code */ + call purgatory + jmp entry64 +SYM_CODE_END(purgatory_start) + + .section ".rodata" + .balign 16 +SYM_DATA_START_LOCAL(gdt) + /* 0x00 unusable segment + * 0x08 unused + * so use them as the gdt ptr + */ + .word gdt_end - gdt - 1 + .quad gdt + .word 0, 0, 0 + + /* 0x10 4GB flat code segment */ + .word 0xFFFF, 0x0000, 0x9A00, 0x00AF + + /* 0x18 4GB flat data segment */ + .word 0xFFFF, 0x0000, 0x9200, 0x00CF +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) + + .bss + .balign 4096 +SYM_DATA_START_LOCAL(lstack) + .skip 4096 +SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end) diff --git a/arch/x86/purgatory/stack.S b/arch/x86/purgatory/stack.S new file mode 100644 index 000000000..1ef507ca5 --- /dev/null +++ b/arch/x86/purgatory/stack.S @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * purgatory: stack + * + * Copyright (C) 2014 Red Hat Inc. + */ + +#include + + /* A stack for the loaded kernel. + * Separate and in the data section so it can be prepopulated. + */ + .data + .balign 4096 + +SYM_DATA_START(stack) + .skip 4096 +SYM_DATA_END_LABEL(stack, SYM_L_GLOBAL, stack_end) -- cgit v1.2.3