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/dump.c | 479 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 479 insertions(+) create mode 100644 arch/arm/mm/dump.c (limited to 'arch/arm/mm/dump.c') diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c new file mode 100644 index 000000000..059eb4cdc --- /dev/null +++ b/arch/arm/mm/dump.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Debug helper to dump the current kernel pagetables of the system + * so that we can see what the various memory ranges are set to. + * + * Derived from x86 implementation: + * (C) Copyright 2008 Intel Corporation + * + * Author: Arjan van de Ven + */ +#include +#include +#include +#include + +#include +#include +#include +#include + +static struct addr_marker address_markers[] = { +#ifdef CONFIG_KASAN + { KASAN_SHADOW_START, "Kasan shadow start"}, + { KASAN_SHADOW_END, "Kasan shadow end"}, +#endif + { MODULES_VADDR, "Modules" }, + { PAGE_OFFSET, "Kernel Mapping" }, + { 0, "vmalloc() Area" }, + { FDT_FIXED_BASE, "FDT Area" }, + { FIXADDR_START, "Fixmap Area" }, + { VECTORS_BASE, "Vectors" }, + { VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" }, + { -1, NULL }, +}; + +#define pt_dump_seq_printf(m, fmt, args...) \ +({ \ + if (m) \ + seq_printf(m, fmt, ##args); \ +}) + +#define pt_dump_seq_puts(m, fmt) \ +({ \ + if (m) \ + seq_printf(m, fmt); \ +}) + +struct pg_state { + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned level; + u64 current_prot; + bool check_wx; + unsigned long wx_pages; + const char *current_domain; +}; + +struct prot_bits { + u64 mask; + u64 val; + const char *set; + const char *clear; + bool ro_bit; + bool nx_bit; +}; + +static const struct prot_bits pte_bits[] = { + { + .mask = L_PTE_USER, + .val = L_PTE_USER, + .set = "USR", + .clear = " ", + }, { + .mask = L_PTE_RDONLY, + .val = L_PTE_RDONLY, + .set = "ro", + .clear = "RW", + .ro_bit = true, + }, { + .mask = L_PTE_XN, + .val = L_PTE_XN, + .set = "NX", + .clear = "x ", + .nx_bit = true, + }, { + .mask = L_PTE_SHARED, + .val = L_PTE_SHARED, + .set = "SHD", + .clear = " ", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_UNCACHED, + .set = "SO/UNCACHED", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_BUFFERABLE, + .set = "MEM/BUFFERABLE/WC", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITETHROUGH, + .set = "MEM/CACHED/WT", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITEBACK, + .set = "MEM/CACHED/WBRA", +#ifndef CONFIG_ARM_LPAE + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_MINICACHE, + .set = "MEM/MINICACHE", +#endif + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITEALLOC, + .set = "MEM/CACHED/WBWA", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_SHARED, + .set = "DEV/SHARED", +#ifndef CONFIG_ARM_LPAE + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_NONSHARED, + .set = "DEV/NONSHARED", +#endif + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_WC, + .set = "DEV/WC", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_CACHED, + .set = "DEV/CACHED", + }, +}; + +static const struct prot_bits section_bits[] = { +#ifdef CONFIG_ARM_LPAE + { + .mask = PMD_SECT_USER, + .val = PMD_SECT_USER, + .set = "USR", + }, { + .mask = L_PMD_SECT_RDONLY | PMD_SECT_AP2, + .val = L_PMD_SECT_RDONLY | PMD_SECT_AP2, + .set = "ro", + .clear = "RW", + .ro_bit = true, +#elif __LINUX_ARM_ARCH__ >= 6 + { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_APX | PMD_SECT_AP_WRITE, + .set = " ro", + .ro_bit = true, + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_WRITE, + .set = " RW", + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ, + .set = "USR ro", + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .set = "USR RW", +#else /* ARMv4/ARMv5 */ + /* These are approximate */ + { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = 0, + .set = " ro", + .ro_bit = true, + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_WRITE, + .set = " RW", + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ, + .set = "USR ro", + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .set = "USR RW", +#endif + }, { + .mask = PMD_SECT_XN, + .val = PMD_SECT_XN, + .set = "NX", + .clear = "x ", + .nx_bit = true, + }, { + .mask = PMD_SECT_S, + .val = PMD_SECT_S, + .set = "SHD", + .clear = " ", + }, +}; + +struct pg_level { + const char *name; + const struct prot_bits *bits; + size_t num; + u64 mask; + const struct prot_bits *ro_bit; + const struct prot_bits *nx_bit; +}; + +static struct pg_level pg_level[] = { + { + }, { /* pgd */ + }, { /* p4d */ + }, { /* pud */ + }, { /* pmd */ + .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", + .bits = section_bits, + .num = ARRAY_SIZE(section_bits), + }, { /* pte */ + .name = "PTE", + .bits = pte_bits, + .num = ARRAY_SIZE(pte_bits), + }, +}; + +static void dump_prot(struct pg_state *st, const struct prot_bits *bits, size_t num) +{ + unsigned i; + + for (i = 0; i < num; i++, bits++) { + const char *s; + + if ((st->current_prot & bits->mask) == bits->val) + s = bits->set; + else + s = bits->clear; + + if (s) + pt_dump_seq_printf(st->seq, " %s", s); + } +} + +static void note_prot_wx(struct pg_state *st, unsigned long addr) +{ + if (!st->check_wx) + return; + if ((st->current_prot & pg_level[st->level].ro_bit->mask) == + pg_level[st->level].ro_bit->val) + return; + if ((st->current_prot & pg_level[st->level].nx_bit->mask) == + pg_level[st->level].nx_bit->val) + return; + + WARN_ONCE(1, "arm/mm: Found insecure W+X mapping at address %pS\n", + (void *)st->start_address); + + st->wx_pages += (addr - st->start_address) / PAGE_SIZE; +} + +static void note_page(struct pg_state *st, unsigned long addr, + unsigned int level, u64 val, const char *domain) +{ + static const char units[] = "KMGTPE"; + u64 prot = val & pg_level[level].mask; + + if (!st->level) { + st->level = level; + st->current_prot = prot; + st->current_domain = domain; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } else if (prot != st->current_prot || level != st->level || + domain != st->current_domain || + addr >= st->marker[1].start_address) { + const char *unit = units; + unsigned long delta; + + if (st->current_prot) { + note_prot_wx(st, addr); + pt_dump_seq_printf(st->seq, "0x%08lx-0x%08lx ", + st->start_address, addr); + + delta = (addr - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); + if (st->current_domain) + pt_dump_seq_printf(st->seq, " %s", + st->current_domain); + if (pg_level[st->level].bits) + dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num); + pt_dump_seq_printf(st->seq, "\n"); + } + + if (addr >= st->marker[1].start_address) { + st->marker++; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", + st->marker->name); + } + st->start_address = addr; + st->current_prot = prot; + st->current_domain = domain; + st->level = level; + } +} + +static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start, + const char *domain) +{ + pte_t *pte = pte_offset_kernel(pmd, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + addr = start + i * PAGE_SIZE; + note_page(st, addr, 5, pte_val(*pte), domain); + } +} + +static const char *get_domain_name(pmd_t *pmd) +{ +#ifndef CONFIG_ARM_LPAE + switch (pmd_val(*pmd) & PMD_DOMAIN_MASK) { + case PMD_DOMAIN(DOMAIN_KERNEL): + return "KERNEL "; + case PMD_DOMAIN(DOMAIN_USER): + return "USER "; + case PMD_DOMAIN(DOMAIN_IO): + return "IO "; + case PMD_DOMAIN(DOMAIN_VECTORS): + return "VECTORS"; + default: + return "unknown"; + } +#endif + return NULL; +} + +static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +{ + pmd_t *pmd = pmd_offset(pud, 0); + unsigned long addr; + unsigned i; + const char *domain; + + for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + addr = start + i * PMD_SIZE; + domain = get_domain_name(pmd); + if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd)) + note_page(st, addr, 4, pmd_val(*pmd), domain); + else + walk_pte(st, pmd, addr, domain); + + if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1])) { + addr += SECTION_SIZE; + pmd++; + domain = get_domain_name(pmd); + note_page(st, addr, 4, pmd_val(*pmd), domain); + } + } +} + +static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start) +{ + pud_t *pud = pud_offset(p4d, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + addr = start + i * PUD_SIZE; + if (!pud_none(*pud)) { + walk_pmd(st, pud, addr); + } else { + note_page(st, addr, 3, pud_val(*pud), NULL); + } + } +} + +static void walk_p4d(struct pg_state *st, pgd_t *pgd, unsigned long start) +{ + p4d_t *p4d = p4d_offset(pgd, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_P4D; i++, p4d++) { + addr = start + i * P4D_SIZE; + if (!p4d_none(*p4d)) { + walk_pud(st, p4d, addr); + } else { + note_page(st, addr, 2, p4d_val(*p4d), NULL); + } + } +} + +static void walk_pgd(struct pg_state *st, struct mm_struct *mm, + unsigned long start) +{ + pgd_t *pgd = pgd_offset(mm, 0UL); + unsigned i; + unsigned long addr; + + for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + addr = start + i * PGDIR_SIZE; + if (!pgd_none(*pgd)) { + walk_p4d(st, pgd, addr); + } else { + note_page(st, addr, 1, pgd_val(*pgd), NULL); + } + } +} + +void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) +{ + struct pg_state st = { + .seq = m, + .marker = info->markers, + .check_wx = false, + }; + + walk_pgd(&st, info->mm, info->base_addr); + note_page(&st, 0, 0, 0, NULL); +} + +static void __init ptdump_initialize(void) +{ + unsigned i, j; + + for (i = 0; i < ARRAY_SIZE(pg_level); i++) + if (pg_level[i].bits) + for (j = 0; j < pg_level[i].num; j++) { + pg_level[i].mask |= pg_level[i].bits[j].mask; + if (pg_level[i].bits[j].ro_bit) + pg_level[i].ro_bit = &pg_level[i].bits[j]; + if (pg_level[i].bits[j].nx_bit) + pg_level[i].nx_bit = &pg_level[i].bits[j]; + } +#ifdef CONFIG_KASAN + address_markers[4].start_address = VMALLOC_START; +#else + address_markers[2].start_address = VMALLOC_START; +#endif +} + +static struct ptdump_info kernel_ptdump_info = { + .mm = &init_mm, + .markers = address_markers, + .base_addr = 0, +}; + +void ptdump_check_wx(void) +{ + struct pg_state st = { + .seq = NULL, + .marker = (struct addr_marker[]) { + { 0, NULL}, + { -1, NULL}, + }, + .check_wx = true, + }; + + walk_pgd(&st, &init_mm, 0); + note_page(&st, 0, 0, 0, NULL); + if (st.wx_pages) + pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", + st.wx_pages); + else + pr_info("Checked W+X mappings: passed, no W+X pages found\n"); +} + +static int __init ptdump_init(void) +{ + ptdump_initialize(); + ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); + return 0; +} +__initcall(ptdump_init); -- cgit v1.2.3