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/mips/kernel/scall64-o32.S | 221 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 221 insertions(+) create mode 100644 arch/mips/kernel/scall64-o32.S (limited to 'arch/mips/kernel/scall64-o32.S') diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S new file mode 100644 index 000000000..d3c2616cb --- /dev/null +++ b/arch/mips/kernel/scall64-o32.S @@ -0,0 +1,221 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1995 - 2000, 2001 by Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2001 MIPS Technologies, Inc. + * Copyright (C) 2004 Thiemo Seufer + * + * Hairy, the userspace application uses a different argument passing + * convention than the kernel, so we have to translate things from o32 + * to ABI64 calling convention. 64-bit syscalls are also processed + * here for now. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + .align 5 +NESTED(handle_sys, PT_SIZE, sp) + .set noat + SAVE_SOME + TRACE_IRQS_ON_RELOAD + STI + .set at + ld t1, PT_EPC(sp) # skip syscall on return + + dsubu t0, v0, __NR_O32_Linux # check syscall number + sltiu t0, t0, __NR_O32_Linux_syscalls + daddiu t1, 4 # skip to next instruction + sd t1, PT_EPC(sp) + beqz t0, not_o32_scall +#if 0 + SAVE_ALL + move a1, v0 + ASM_PRINT("Scall %ld\n") + RESTORE_ALL +#endif + + /* We don't want to stumble over broken sign extensions from + userland. O32 does never use the upper half. */ + sll a0, a0, 0 + sll a1, a1, 0 + sll a2, a2, 0 + sll a3, a3, 0 + + sd a3, PT_R26(sp) # save a3 for syscall restarting + + /* + * More than four arguments. Try to deal with it by copying the + * stack arguments from the user stack to the kernel stack. + * This Sucks (TM). + * + * We intentionally keep the kernel stack a little below the top of + * userspace so we don't have to do a slower byte accurate check here. + */ + ld t0, PT_R29(sp) # get old user stack pointer + daddu t1, t0, 32 + bltz t1, bad_stack + +load_a4: lw a4, 16(t0) # argument #5 from usp +load_a5: lw a5, 20(t0) # argument #6 from usp +load_a6: lw a6, 24(t0) # argument #7 from usp +load_a7: lw a7, 28(t0) # argument #8 from usp +loads_done: + + .section __ex_table,"a" + PTR_WD load_a4, bad_stack_a4 + PTR_WD load_a5, bad_stack_a5 + PTR_WD load_a6, bad_stack_a6 + PTR_WD load_a7, bad_stack_a7 + .previous + + li t1, _TIF_WORK_SYSCALL_ENTRY + LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? + and t0, t1, t0 + bnez t0, trace_a_syscall + +syscall_common: + dsll t0, v0, 3 # offset into table + ld t2, (sys32_call_table - (__NR_O32_Linux * 8))(t0) + + jalr t2 # Do The Real Thing (TM) + + li t0, -EMAXERRNO - 1 # error? + sltu t0, t0, v0 + sd t0, PT_R7(sp) # set error flag + beqz t0, 1f + + ld t1, PT_R2(sp) # syscall number + dnegu v0 # error + sd t1, PT_R0(sp) # save it for syscall restarting +1: sd v0, PT_R2(sp) # result + +o32_syscall_exit: + j syscall_exit_partial + +/* ------------------------------------------------------------------------ */ + +trace_a_syscall: + SAVE_STATIC + sd a4, PT_R8(sp) # Save argument registers + sd a5, PT_R9(sp) + sd a6, PT_R10(sp) + sd a7, PT_R11(sp) # For indirect syscalls + + move a0, sp + /* + * absolute syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + * note: NR_syscall is the first O32 syscall but the macro is + * only defined when compiling with -mabi=32 (CONFIG_32BIT) + * therefore __NR_O32_Linux is used (4000) + */ + .set push + .set reorder + subu t1, v0, __NR_O32_Linux + move a1, v0 + bnez t1, 1f /* __NR_syscall at offset 0 */ + ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ + .set pop + +1: jal syscall_trace_enter + + bltz v0, 1f # seccomp failed? Skip syscall + + RESTORE_STATIC + ld v0, PT_R2(sp) # Restore syscall (maybe modified) + ld a0, PT_R4(sp) # Restore argument registers + ld a1, PT_R5(sp) + ld a2, PT_R6(sp) + ld a3, PT_R7(sp) + ld a4, PT_R8(sp) + ld a5, PT_R9(sp) + ld a6, PT_R10(sp) + ld a7, PT_R11(sp) # For indirect syscalls + + dsubu t0, v0, __NR_O32_Linux # check (new) syscall number + sltiu t0, t0, __NR_O32_Linux_syscalls + beqz t0, not_o32_scall + + j syscall_common + +1: j syscall_exit + +/* ------------------------------------------------------------------------ */ + + /* + * The stackpointer for a call with more than 4 arguments is bad. + */ +bad_stack: + li v0, EFAULT + sd v0, PT_R2(sp) + li t0, 1 # set error flag + sd t0, PT_R7(sp) + j o32_syscall_exit + +bad_stack_a4: + li a4, 0 + b load_a5 + +bad_stack_a5: + li a5, 0 + b load_a6 + +bad_stack_a6: + li a6, 0 + b load_a7 + +bad_stack_a7: + li a7, 0 + b loads_done + +not_o32_scall: + /* + * This is not an o32 compatibility syscall, pass it on + * to the 64-bit syscall handlers. + */ +#ifdef CONFIG_MIPS32_N32 + j handle_sysn32 +#else + j handle_sys64 +#endif + END(handle_sys) + +LEAF(sys32_syscall) + subu t0, a0, __NR_O32_Linux # check syscall number + sltiu v0, t0, __NR_O32_Linux_syscalls + beqz t0, einval # do not recurse + dsll t1, t0, 3 + beqz v0, einval + ld t2, sys32_call_table(t1) # syscall routine + + move a0, a1 # shift argument registers + move a1, a2 + move a2, a3 + move a3, a4 + move a4, a5 + move a5, a6 + move a6, a7 + jr t2 + /* Unreached */ + +einval: li v0, -ENOSYS + jr ra + END(sys32_syscall) + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) +#define __SYSCALL(nr, entry) PTR_WD entry + .align 3 + .type sys32_call_table,@object +EXPORT(sys32_call_table) +#include -- cgit v1.2.3