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(). ... --- tools/testing/selftests/rseq/rseq.h | 384 ++++++++++++++++++++++++++++++++++++ 1 file changed, 384 insertions(+) create mode 100644 tools/testing/selftests/rseq/rseq.h (limited to 'tools/testing/selftests/rseq/rseq.h') diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h new file mode 100644 index 000000000..d7364ea4d --- /dev/null +++ b/tools/testing/selftests/rseq/rseq.h @@ -0,0 +1,384 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * rseq.h + * + * (C) Copyright 2016-2018 - Mathieu Desnoyers + */ + +#ifndef RSEQ_H +#define RSEQ_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "rseq-abi.h" +#include "compiler.h" + +#ifndef rseq_sizeof_field +#define rseq_sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +#ifndef rseq_offsetofend +#define rseq_offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + rseq_sizeof_field(TYPE, MEMBER)) +#endif + +/* + * Empty code injection macros, override when testing. + * It is important to consider that the ASM injection macros need to be + * fully reentrant (e.g. do not modify the stack). + */ +#ifndef RSEQ_INJECT_ASM +#define RSEQ_INJECT_ASM(n) +#endif + +#ifndef RSEQ_INJECT_C +#define RSEQ_INJECT_C(n) +#endif + +#ifndef RSEQ_INJECT_INPUT +#define RSEQ_INJECT_INPUT +#endif + +#ifndef RSEQ_INJECT_CLOBBER +#define RSEQ_INJECT_CLOBBER +#endif + +#ifndef RSEQ_INJECT_FAILED +#define RSEQ_INJECT_FAILED +#endif + +#include "rseq-thread-pointer.h" + +/* Offset from the thread pointer to the rseq area. */ +extern ptrdiff_t rseq_offset; + +/* + * Size of the registered rseq area. 0 if the registration was + * unsuccessful. + */ +extern unsigned int rseq_size; + +/* Flags used during rseq registration. */ +extern unsigned int rseq_flags; + +/* + * rseq feature size supported by the kernel. 0 if the registration was + * unsuccessful. + */ +extern unsigned int rseq_feature_size; + +enum rseq_mo { + RSEQ_MO_RELAXED = 0, + RSEQ_MO_CONSUME = 1, /* Unused */ + RSEQ_MO_ACQUIRE = 2, /* Unused */ + RSEQ_MO_RELEASE = 3, + RSEQ_MO_ACQ_REL = 4, /* Unused */ + RSEQ_MO_SEQ_CST = 5, /* Unused */ +}; + +enum rseq_percpu_mode { + RSEQ_PERCPU_CPU_ID = 0, + RSEQ_PERCPU_MM_CID = 1, +}; + +static inline struct rseq_abi *rseq_get_abi(void) +{ + return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); +} + +#define rseq_likely(x) __builtin_expect(!!(x), 1) +#define rseq_unlikely(x) __builtin_expect(!!(x), 0) +#define rseq_barrier() __asm__ __volatile__("" : : : "memory") + +#define RSEQ_ACCESS_ONCE(x) (*(__volatile__ __typeof__(x) *)&(x)) +#define RSEQ_WRITE_ONCE(x, v) __extension__ ({ RSEQ_ACCESS_ONCE(x) = (v); }) +#define RSEQ_READ_ONCE(x) RSEQ_ACCESS_ONCE(x) + +#define __rseq_str_1(x) #x +#define __rseq_str(x) __rseq_str_1(x) + +#define rseq_log(fmt, args...) \ + fprintf(stderr, fmt "(in %s() at " __FILE__ ":" __rseq_str(__LINE__)"\n", \ + ## args, __func__) + +#define rseq_bug(fmt, args...) \ + do { \ + rseq_log(fmt, ##args); \ + abort(); \ + } while (0) + +#if defined(__x86_64__) || defined(__i386__) +#include +#elif defined(__ARMEL__) +#include +#elif defined (__AARCH64EL__) +#include +#elif defined(__PPC__) +#include +#elif defined(__mips__) +#include +#elif defined(__s390__) +#include +#elif defined(__riscv) +#include +#else +#error unsupported target +#endif + +/* + * Register rseq for the current thread. This needs to be called once + * by any thread which uses restartable sequences, before they start + * using restartable sequences, to ensure restartable sequences + * succeed. A restartable sequence executed from a non-registered + * thread will always fail. + */ +int rseq_register_current_thread(void); + +/* + * Unregister rseq for current thread. + */ +int rseq_unregister_current_thread(void); + +/* + * Restartable sequence fallback for reading the current CPU number. + */ +int32_t rseq_fallback_current_cpu(void); + +/* + * Restartable sequence fallback for reading the current node number. + */ +int32_t rseq_fallback_current_node(void); + +/* + * Values returned can be either the current CPU number, -1 (rseq is + * uninitialized), or -2 (rseq initialization has failed). + */ +static inline int32_t rseq_current_cpu_raw(void) +{ + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id); +} + +/* + * Returns a possible CPU number, which is typically the current CPU. + * The returned CPU number can be used to prepare for an rseq critical + * section, which will confirm whether the cpu number is indeed the + * current one, and whether rseq is initialized. + * + * The CPU number returned by rseq_cpu_start should always be validated + * by passing it to a rseq asm sequence, or by comparing it to the + * return value of rseq_current_cpu_raw() if the rseq asm sequence + * does not need to be invoked. + */ +static inline uint32_t rseq_cpu_start(void) +{ + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start); +} + +static inline uint32_t rseq_current_cpu(void) +{ + int32_t cpu; + + cpu = rseq_current_cpu_raw(); + if (rseq_unlikely(cpu < 0)) + cpu = rseq_fallback_current_cpu(); + return cpu; +} + +static inline bool rseq_node_id_available(void) +{ + return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, node_id); +} + +/* + * Current NUMA node number. + */ +static inline uint32_t rseq_current_node_id(void) +{ + assert(rseq_node_id_available()); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->node_id); +} + +static inline bool rseq_mm_cid_available(void) +{ + return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, mm_cid); +} + +static inline uint32_t rseq_current_mm_cid(void) +{ + return RSEQ_ACCESS_ONCE(rseq_get_abi()->mm_cid); +} + +static inline void rseq_clear_rseq_cs(void) +{ + RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); +} + +/* + * rseq_prepare_unload() should be invoked by each thread executing a rseq + * critical section at least once between their last critical section and + * library unload of the library defining the rseq critical section (struct + * rseq_cs) or the code referred to by the struct rseq_cs start_ip and + * post_commit_offset fields. This also applies to use of rseq in code + * generated by JIT: rseq_prepare_unload() should be invoked at least once by + * each thread executing a rseq critical section before reclaim of the memory + * holding the struct rseq_cs or reclaim of the code pointed to by struct + * rseq_cs start_ip and post_commit_offset fields. + */ +static inline void rseq_prepare_unload(void) +{ + rseq_clear_rseq_cs(); +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t newv, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_storev_relaxed_cpu_id(v, expect, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_storev_relaxed_mm_cid(v, expect, newv, cpu); + } + return -1; +} + +/* + * Compare @v against @expectnot. When it does _not_ match, load @v + * into @load, and store the content of *@v + voffp into @v. + */ +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expectnot, long voffp, intptr_t *load, + int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpnev_storeoffp_load_relaxed_cpu_id(v, expectnot, voffp, load, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpnev_storeoffp_load_relaxed_mm_cid(v, expectnot, voffp, load, cpu); + } + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t count, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_addv_relaxed_cpu_id(v, count, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_addv_relaxed_mm_cid(v, count, cpu); + } + return -1; +} + +#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV +/* + * pval = *(ptr+off) + * *pval += inc; + */ +static inline __attribute__((always_inline)) +int rseq_offset_deref_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *ptr, long off, intptr_t inc, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_offset_deref_addv_relaxed_cpu_id(ptr, off, inc, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_offset_deref_addv_relaxed_mm_cid(ptr, off, inc, cpu); + } + return -1; +} +#endif + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + switch (rseq_mo) { + case RSEQ_MO_RELAXED: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trystorev_storev_relaxed_cpu_id(v, expect, v2, newv2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trystorev_storev_relaxed_mm_cid(v, expect, v2, newv2, newv, cpu); + } + return -1; + case RSEQ_MO_RELEASE: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trystorev_storev_release_cpu_id(v, expect, v2, newv2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trystorev_storev_release_mm_cid(v, expect, v2, newv2, newv, cpu); + } + return -1; + default: + return -1; + } +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_cmpeqv_storev_relaxed_cpu_id(v, expect, v2, expect2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_cmpeqv_storev_relaxed_mm_cid(v, expect, v2, expect2, newv, cpu); + } + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + switch (rseq_mo) { + case RSEQ_MO_RELAXED: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trymemcpy_storev_relaxed_cpu_id(v, expect, dst, src, len, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trymemcpy_storev_relaxed_mm_cid(v, expect, dst, src, len, newv, cpu); + } + return -1; + case RSEQ_MO_RELEASE: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trymemcpy_storev_release_cpu_id(v, expect, dst, src, len, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trymemcpy_storev_release_mm_cid(v, expect, dst, src, len, newv, cpu); + } + return -1; + default: + return -1; + } +} + +#endif /* RSEQ_H_ */ -- cgit v1.2.3