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/powerpc/kernel/stacktrace.c | 228 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+) create mode 100644 arch/powerpc/kernel/stacktrace.c (limited to 'arch/powerpc/kernel/stacktrace.c') diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c new file mode 100644 index 000000000..5de8597ea --- /dev/null +++ b/arch/powerpc/kernel/stacktrace.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Stack trace utility functions etc. + * + * Copyright 2008 Christoph Hellwig, IBM Corp. + * Copyright 2018 SUSE Linux GmbH + * Copyright 2018 Nick Piggin, Michael Ellerman, IBM Corp. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +void __no_sanitize_address arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) +{ + unsigned long sp; + + if (regs && !consume_entry(cookie, regs->nip)) + return; + + if (regs) + sp = regs->gpr[1]; + else if (task == current) + sp = current_stack_frame(); + else + sp = task->thread.ksp; + + for (;;) { + unsigned long *stack = (unsigned long *) sp; + unsigned long newsp, ip; + + if (!validate_sp(sp, task)) + return; + + newsp = stack[0]; + ip = stack[STACK_FRAME_LR_SAVE]; + + if (!consume_entry(cookie, ip)) + return; + + sp = newsp; + } +} + +/* + * This function returns an error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task) +{ + unsigned long sp; + unsigned long newsp; + unsigned long stack_page = (unsigned long)task_stack_page(task); + unsigned long stack_end; + int graph_idx = 0; + bool firstframe; + + stack_end = stack_page + THREAD_SIZE; + if (!is_idle_task(task)) { + /* + * For user tasks, this is the SP value loaded on + * kernel entry, see "PACAKSAVE(r13)" in _switch() and + * system_call_common(). + * + * Likewise for non-swapper kernel threads, + * this also happens to be the top of the stack + * as setup by copy_thread(). + * + * Note that stack backlinks are not properly setup by + * copy_thread() and thus, a forked task() will have + * an unreliable stack trace until it's been + * _switch()'ed to for the first time. + */ + stack_end -= STACK_USER_INT_FRAME_SIZE; + } else { + /* + * idle tasks have a custom stack layout, + * c.f. cpu_idle_thread_init(). + */ + stack_end -= STACK_FRAME_MIN_SIZE; + } + + if (task == current) + sp = current_stack_frame(); + else + sp = task->thread.ksp; + + if (sp < stack_page + sizeof(struct thread_struct) || + sp > stack_end - STACK_FRAME_MIN_SIZE) { + return -EINVAL; + } + + for (firstframe = true; sp != stack_end; + firstframe = false, sp = newsp) { + unsigned long *stack = (unsigned long *) sp; + unsigned long ip; + + /* sanity check: ABI requires SP to be aligned 16 bytes. */ + if (sp & 0xF) + return -EINVAL; + + newsp = stack[0]; + /* Stack grows downwards; unwinder may only go up. */ + if (newsp <= sp) + return -EINVAL; + + if (newsp != stack_end && + newsp > stack_end - STACK_FRAME_MIN_SIZE) { + return -EINVAL; /* invalid backlink, too far up. */ + } + + /* + * We can only trust the bottom frame's backlink, the + * rest of the frame may be uninitialized, continue to + * the next. + */ + if (firstframe) + continue; + + /* Mark stacktraces with exception frames as unreliable. */ + if (sp <= stack_end - STACK_INT_FRAME_SIZE && + stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) { + return -EINVAL; + } + + /* Examine the saved LR: it must point into kernel code. */ + ip = stack[STACK_FRAME_LR_SAVE]; + if (!__kernel_text_address(ip)) + return -EINVAL; + + /* + * FIXME: IMHO these tests do not belong in + * arch-dependent code, they are generic. + */ + ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack); +#ifdef CONFIG_KPROBES + /* + * Mark stacktraces with kretprobed functions on them + * as unreliable. + */ + if (ip == (unsigned long)__kretprobe_trampoline) + return -EINVAL; +#endif + + if (!consume_entry(cookie, ip)) + return -EINVAL; + } + return 0; +} + +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) +static void handle_backtrace_ipi(struct pt_regs *regs) +{ + nmi_cpu_backtrace(regs); +} + +static void raise_backtrace_ipi(cpumask_t *mask) +{ + struct paca_struct *p; + unsigned int cpu; + u64 delay_us; + + for_each_cpu(cpu, mask) { + if (cpu == smp_processor_id()) { + handle_backtrace_ipi(NULL); + continue; + } + + delay_us = 5 * USEC_PER_SEC; + + if (smp_send_safe_nmi_ipi(cpu, handle_backtrace_ipi, delay_us)) { + // Now wait up to 5s for the other CPU to do its backtrace + while (cpumask_test_cpu(cpu, mask) && delay_us) { + udelay(1); + delay_us--; + } + + // Other CPU cleared itself from the mask + if (delay_us) + continue; + } + + p = paca_ptrs[cpu]; + + cpumask_clear_cpu(cpu, mask); + + pr_warn("CPU %d didn't respond to backtrace IPI, inspecting paca.\n", cpu); + if (!virt_addr_valid(p)) { + pr_warn("paca pointer appears corrupt? (%px)\n", p); + continue; + } + + pr_warn("irq_soft_mask: 0x%02x in_mce: %d in_nmi: %d", + p->irq_soft_mask, p->in_mce, p->in_nmi); + + if (virt_addr_valid(p->__current)) + pr_cont(" current: %d (%s)\n", p->__current->pid, + p->__current->comm); + else + pr_cont(" current pointer corrupt? (%px)\n", p->__current); + + pr_warn("Back trace of paca->saved_r1 (0x%016llx) (possibly stale):\n", p->saved_r1); + show_stack(p->__current, (unsigned long *)p->saved_r1, KERN_WARNING); + } +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); +} +#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ -- cgit v1.2.3