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/mm/kasan_init.c | 300 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 300 insertions(+) create mode 100644 arch/arm/mm/kasan_init.c (limited to 'arch/arm/mm/kasan_init.c') diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c new file mode 100644 index 000000000..46d9f4a62 --- /dev/null +++ b/arch/arm/mm/kasan_init.c @@ -0,0 +1,300 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This file contains kasan initialization code for ARM. + * + * Copyright (c) 2018 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * Author: Linus Walleij + */ + +#define pr_fmt(fmt) "kasan: " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mm.h" + +static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); + +pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss; + +static __init void *kasan_alloc_block(size_t size) +{ + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_NOLEAKTRACE, NUMA_NO_NODE); +} + +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, + unsigned long end, bool early) +{ + unsigned long next; + pte_t *ptep = pte_offset_kernel(pmdp, addr); + + do { + pte_t entry; + void *p; + + next = addr + PAGE_SIZE; + + if (!early) { + if (!pte_none(READ_ONCE(*ptep))) + continue; + + p = kasan_alloc_block(PAGE_SIZE); + if (!p) { + panic("%s failed to allocate shadow page for address 0x%lx\n", + __func__, addr); + return; + } + memset(p, KASAN_SHADOW_INIT, PAGE_SIZE); + entry = pfn_pte(virt_to_pfn(p), + __pgprot(pgprot_val(PAGE_KERNEL))); + } else if (pte_none(READ_ONCE(*ptep))) { + /* + * The early shadow memory is mapping all KASan + * operations to one and the same page in memory, + * "kasan_early_shadow_page" so that the instrumentation + * will work on a scratch area until we can set up the + * proper KASan shadow memory. + */ + entry = pfn_pte(virt_to_pfn(kasan_early_shadow_page), + __pgprot(_L_PTE_DEFAULT | L_PTE_DIRTY | L_PTE_XN)); + } else { + /* + * Early shadow mappings are PMD_SIZE aligned, so if the + * first entry is already set, they must all be set. + */ + return; + } + + set_pte_at(&init_mm, addr, ptep, entry); + } while (ptep++, addr = next, addr != end); +} + +/* + * The pmd (page middle directory) is only used on LPAE + */ +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, + unsigned long end, bool early) +{ + unsigned long next; + pmd_t *pmdp = pmd_offset(pudp, addr); + + do { + if (pmd_none(*pmdp)) { + /* + * We attempt to allocate a shadow block for the PMDs + * used by the PTEs for this address if it isn't already + * allocated. + */ + void *p = early ? kasan_early_shadow_pte : + kasan_alloc_block(PAGE_SIZE); + + if (!p) { + panic("%s failed to allocate shadow block for address 0x%lx\n", + __func__, addr); + return; + } + pmd_populate_kernel(&init_mm, pmdp, p); + flush_pmd_entry(pmdp); + } + + next = pmd_addr_end(addr, end); + kasan_pte_populate(pmdp, addr, next, early); + } while (pmdp++, addr = next, addr != end); +} + +static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, + bool early) +{ + unsigned long next; + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + + pgdp = pgd_offset_k(addr); + + do { + /* + * Allocate and populate the shadow block of p4d folded into + * pud folded into pmd if it doesn't already exist + */ + if (!early && pgd_none(*pgdp)) { + void *p = kasan_alloc_block(PAGE_SIZE); + + if (!p) { + panic("%s failed to allocate shadow block for address 0x%lx\n", + __func__, addr); + return; + } + pgd_populate(&init_mm, pgdp, p); + } + + next = pgd_addr_end(addr, end); + /* + * We just immediately jump over the p4d and pud page + * directories since we believe ARM32 will never gain four + * nor five level page tables. + */ + p4dp = p4d_offset(pgdp, addr); + pudp = pud_offset(p4dp, addr); + + kasan_pmd_populate(pudp, addr, next, early); + } while (pgdp++, addr = next, addr != end); +} + +extern struct proc_info_list *lookup_processor_type(unsigned int); + +void __init kasan_early_init(void) +{ + struct proc_info_list *list; + + /* + * locate processor in the list of supported processor + * types. The linker builds this table for us from the + * entries in arch/arm/mm/proc-*.S + */ + list = lookup_processor_type(read_cpuid_id()); + if (list) { +#ifdef MULTI_CPU + processor = *list->proc; +#endif + } + + BUILD_BUG_ON((KASAN_SHADOW_END - (1UL << 29)) != KASAN_SHADOW_OFFSET); + /* + * We walk the page table and set all of the shadow memory to point + * to the scratch page. + */ + kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, true); +} + +static void __init clear_pgds(unsigned long start, + unsigned long end) +{ + for (; start && start < end; start += PMD_SIZE) + pmd_clear(pmd_off_k(start)); +} + +static int __init create_mapping(void *start, void *end) +{ + void *shadow_start, *shadow_end; + + shadow_start = kasan_mem_to_shadow(start); + shadow_end = kasan_mem_to_shadow(end); + + pr_info("Mapping kernel virtual memory block: %px-%px at shadow: %px-%px\n", + start, end, shadow_start, shadow_end); + + kasan_pgd_populate((unsigned long)shadow_start & PAGE_MASK, + PAGE_ALIGN((unsigned long)shadow_end), false); + return 0; +} + +void __init kasan_init(void) +{ + phys_addr_t pa_start, pa_end; + u64 i; + + /* + * We are going to perform proper setup of shadow memory. + * + * At first we should unmap early shadow (clear_pgds() call bellow). + * However, instrumented code can't execute without shadow memory. + * + * To keep the early shadow memory MMU tables around while setting up + * the proper shadow memory, we copy swapper_pg_dir (the initial page + * table) to tmp_pgd_table and use that to keep the early shadow memory + * mapped until the full shadow setup is finished. Then we swap back + * to the proper swapper_pg_dir. + */ + + memcpy(tmp_pgd_table, swapper_pg_dir, sizeof(tmp_pgd_table)); +#ifdef CONFIG_ARM_LPAE + /* We need to be in the same PGD or this won't work */ + BUILD_BUG_ON(pgd_index(KASAN_SHADOW_START) != + pgd_index(KASAN_SHADOW_END)); + memcpy(tmp_pmd_table, + (void*)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)), + sizeof(tmp_pmd_table)); + set_pgd(&tmp_pgd_table[pgd_index(KASAN_SHADOW_START)], + __pgd(__pa(tmp_pmd_table) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); +#endif + cpu_switch_mm(tmp_pgd_table, &init_mm); + local_flush_tlb_all(); + + clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (!IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START), + kasan_mem_to_shadow((void *)VMALLOC_END)); + + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_END), + kasan_mem_to_shadow((void *)-1UL) + 1); + + for_each_mem_range(i, &pa_start, &pa_end) { + void *start = __va(pa_start); + void *end = __va(pa_end); + + /* Do not attempt to shadow highmem */ + if (pa_start >= arm_lowmem_limit) { + pr_info("Skip highmem block at %pa-%pa\n", &pa_start, &pa_end); + continue; + } + if (pa_end > arm_lowmem_limit) { + pr_info("Truncating shadow for memory block at %pa-%pa to lowmem region at %pa\n", + &pa_start, &pa_end, &arm_lowmem_limit); + end = __va(arm_lowmem_limit); + } + if (start >= end) { + pr_info("Skipping invalid memory block %pa-%pa (virtual %p-%p)\n", + &pa_start, &pa_end, start, end); + continue; + } + + create_mapping(start, end); + } + + /* + * 1. The module global variables are in MODULES_VADDR ~ MODULES_END, + * so we need to map this area if CONFIG_KASAN_VMALLOC=n. With + * VMALLOC support KASAN will manage this region dynamically, + * refer to kasan_populate_vmalloc() and ARM's implementation of + * module_alloc(). + * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR + * ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't + * use kasan_populate_zero_shadow. + */ + if (!IS_ENABLED(CONFIG_KASAN_VMALLOC) && IS_ENABLED(CONFIG_MODULES)) + create_mapping((void *)MODULES_VADDR, (void *)(MODULES_END)); + create_mapping((void *)PKMAP_BASE, (void *)(PKMAP_BASE + PMD_SIZE)); + + /* + * KAsan may reuse the contents of kasan_early_shadow_pte directly, so + * we should make sure that it maps the zero page read-only. + */ + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte_at(&init_mm, KASAN_SHADOW_START + i*PAGE_SIZE, + &kasan_early_shadow_pte[i], + pfn_pte(virt_to_pfn(kasan_early_shadow_page), + __pgprot(pgprot_val(PAGE_KERNEL) + | L_PTE_RDONLY))); + + cpu_switch_mm(swapper_pg_dir, &init_mm); + local_flush_tlb_all(); + + memset(kasan_early_shadow_page, 0, PAGE_SIZE); + pr_info("Kernel address sanitizer initialized\n"); + init_task.kasan_depth = 0; +} -- cgit v1.2.3