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/sparc/kernel/wuf.S | 313 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 313 insertions(+) create mode 100644 arch/sparc/kernel/wuf.S (limited to 'arch/sparc/kernel/wuf.S') diff --git a/arch/sparc/kernel/wuf.S b/arch/sparc/kernel/wuf.S new file mode 100644 index 000000000..1a4ca490e --- /dev/null +++ b/arch/sparc/kernel/wuf.S @@ -0,0 +1,313 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * wuf.S: Window underflow trap handler for the Sparc. + * + * Copyright (C) 1995 David S. Miller + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Just like the overflow handler we define macros for registers + * with fixed meanings in this routine. + */ +#define t_psr l0 +#define t_pc l1 +#define t_npc l2 +#define t_wim l3 +/* Don't touch the above registers or else you die horribly... */ + +/* Now macros for the available scratch registers in this routine. */ +#define twin_tmp1 l4 +#define twin_tmp2 l5 + +#define curptr g6 + + .text + .align 4 + + /* The trap entry point has executed the following: + * + * rd %psr, %l0 + * rd %wim, %l3 + * b fill_window_entry + * andcc %l0, PSR_PS, %g0 + */ + + /* Datum current_thread_info->uwinmask contains at all times a bitmask + * where if any user windows are active, at least one bit will + * be set in to mask. If no user windows are active, the bitmask + * will be all zeroes. + */ + + /* To get an idea of what has just happened to cause this + * trap take a look at this diagram: + * + * 1 2 3 4 <-- Window number + * ---------- + * T O W I <-- Symbolic name + * + * O == the window that execution was in when + * the restore was attempted + * + * T == the trap itself has save'd us into this + * window + * + * W == this window is the one which is now invalid + * and must be made valid plus loaded from the + * stack + * + * I == this window will be the invalid one when we + * are done and return from trap if successful + */ + + /* BEGINNING OF PATCH INSTRUCTIONS */ + + /* On 7-window Sparc the boot code patches fnwin_patch1 + * with the following instruction. + */ + .globl fnwin_patch1_7win, fnwin_patch2_7win +fnwin_patch1_7win: srl %t_wim, 6, %twin_tmp2 +fnwin_patch2_7win: and %twin_tmp1, 0x7f, %twin_tmp1 + /* END OF PATCH INSTRUCTIONS */ + + .globl fill_window_entry, fnwin_patch1, fnwin_patch2 +fill_window_entry: + /* LOCATION: Window 'T' */ + + /* Compute what the new %wim is going to be if we retrieve + * the proper window off of the stack. + */ + sll %t_wim, 1, %twin_tmp1 +fnwin_patch1: srl %t_wim, 7, %twin_tmp2 + or %twin_tmp1, %twin_tmp2, %twin_tmp1 +fnwin_patch2: and %twin_tmp1, 0xff, %twin_tmp1 + + wr %twin_tmp1, 0x0, %wim /* Make window 'I' invalid */ + + andcc %t_psr, PSR_PS, %g0 + be fwin_from_user + restore %g0, %g0, %g0 /* Restore to window 'O' */ + + /* Trapped from kernel, we trust that the kernel does not + * 'over restore' sorta speak and just grab the window + * from the stack and return. Easy enough. + */ +fwin_from_kernel: + /* LOCATION: Window 'O' */ + + restore %g0, %g0, %g0 + + /* LOCATION: Window 'W' */ + + LOAD_WINDOW(sp) /* Load it up */ + + /* Spin the wheel... */ + save %g0, %g0, %g0 + save %g0, %g0, %g0 + /* I'd like to buy a vowel please... */ + + /* LOCATION: Window 'T' */ + + /* Now preserve the condition codes in %psr, pause, and + * return from trap. This is the simplest case of all. + */ + wr %t_psr, 0x0, %psr + WRITE_PAUSE + + jmp %t_pc + rett %t_npc + +fwin_from_user: + /* LOCATION: Window 'O' */ + + restore %g0, %g0, %g0 /* Restore to window 'W' */ + + /* LOCATION: Window 'W' */ + + /* Branch to the stack validation routine */ + b srmmu_fwin_stackchk + andcc %sp, 0x7, %g0 + +#define STACK_OFFSET (THREAD_SIZE - TRACEREG_SZ - STACKFRAME_SZ) + +fwin_user_stack_is_bolixed: + /* LOCATION: Window 'W' */ + + /* Place a pt_regs frame on the kernel stack, save back + * to the trap window and call c-code to deal with this. + */ + LOAD_CURRENT(l4, l5) + + sethi %hi(STACK_OFFSET), %l5 + or %l5, %lo(STACK_OFFSET), %l5 + add %l4, %l5, %l5 + + /* Store globals into pt_regs frame. */ + STORE_PT_GLOBALS(l5) + STORE_PT_YREG(l5, g3) + + /* Save current in a global while we change windows. */ + mov %l4, %curptr + + save %g0, %g0, %g0 + + /* LOCATION: Window 'O' */ + + rd %psr, %g3 /* Read %psr in live user window */ + mov %fp, %g4 /* Save bogus frame pointer. */ + + save %g0, %g0, %g0 + + /* LOCATION: Window 'T' */ + + sethi %hi(STACK_OFFSET), %l5 + or %l5, %lo(STACK_OFFSET), %l5 + add %curptr, %l5, %sp + + /* Build rest of pt_regs. */ + STORE_PT_INS(sp) + STORE_PT_PRIV(sp, t_psr, t_pc, t_npc) + + /* re-set trap time %wim value */ + wr %t_wim, 0x0, %wim + + /* Fix users window mask and buffer save count. */ + mov 0x1, %g5 + sll %g5, %g3, %g5 + st %g5, [%curptr + TI_UWINMASK] ! one live user window still + st %g0, [%curptr + TI_W_SAVED] ! no windows in the buffer + + wr %t_psr, PSR_ET, %psr ! enable traps + nop + call window_underflow_fault + mov %g4, %o0 + + b ret_trap_entry + clr %l6 + +fwin_user_stack_is_ok: + /* LOCATION: Window 'W' */ + + /* The users stack area is kosher and mapped, load the + * window and fall through to the finish up routine. + */ + LOAD_WINDOW(sp) + + /* Round and round she goes... */ + save %g0, %g0, %g0 /* Save to window 'O' */ + save %g0, %g0, %g0 /* Save to window 'T' */ + /* Where she'll trap nobody knows... */ + + /* LOCATION: Window 'T' */ + +fwin_user_finish_up: + /* LOCATION: Window 'T' */ + + wr %t_psr, 0x0, %psr + WRITE_PAUSE + + jmp %t_pc + rett %t_npc + + /* Here come the architecture specific checks for stack. + * mappings. Note that unlike the window overflow handler + * we only need to check whether the user can read from + * the appropriate addresses. Also note that we are in + * an invalid window which will be loaded, and this means + * that until we actually load the window up we are free + * to use any of the local registers contained within. + * + * On success these routine branch to fwin_user_stack_is_ok + * if the area at %sp is user readable and the window still + * needs to be loaded, else fwin_user_finish_up if the + * routine has done the loading itself. On failure (bogus + * user stack) the routine shall branch to the label called + * fwin_user_stack_is_bolixed. + * + * Contrary to the arch-specific window overflow stack + * check routines in wof.S, these routines are free to use + * any of the local registers they want to as this window + * does not belong to anyone at this point, however the + * outs and ins are still verboten as they are part of + * 'someone elses' window possibly. + */ + + .globl srmmu_fwin_stackchk +srmmu_fwin_stackchk: + /* LOCATION: Window 'W' */ + + /* Caller did 'andcc %sp, 0x7, %g0' */ + bne fwin_user_stack_is_bolixed + sethi %hi(PAGE_OFFSET), %l5 + + /* Check if the users stack is in kernel vma, then our + * trial and error technique below would succeed for + * the 'wrong' reason. + */ + mov AC_M_SFSR, %l4 + cmp %l5, %sp + bleu fwin_user_stack_is_bolixed +LEON_PI( lda [%l4] ASI_LEON_MMUREGS, %g0) ! clear fault status +SUN_PI_( lda [%l4] ASI_M_MMUREGS, %g0) ! clear fault status + + /* The technique is, turn off faults on this processor, + * just let the load rip, then check the sfsr to see if + * a fault did occur. Then we turn on fault traps again + * and branch conditionally based upon what happened. + */ +LEON_PI(lda [%g0] ASI_LEON_MMUREGS, %l5) ! read mmu-ctrl reg +SUN_PI_(lda [%g0] ASI_M_MMUREGS, %l5) ! read mmu-ctrl reg + or %l5, 0x2, %l5 ! turn on no-fault bit +LEON_PI(sta %l5, [%g0] ASI_LEON_MMUREGS) ! store it +SUN_PI_(sta %l5, [%g0] ASI_M_MMUREGS) ! store it + + /* Cross fingers and go for it. */ + LOAD_WINDOW(sp) + + /* A penny 'saved'... */ + save %g0, %g0, %g0 + save %g0, %g0, %g0 + /* Is a BADTRAP earned... */ + + /* LOCATION: Window 'T' */ + +LEON_PI(lda [%g0] ASI_LEON_MMUREGS, %twin_tmp1) ! load mmu-ctrl again +SUN_PI_(lda [%g0] ASI_M_MMUREGS, %twin_tmp1) ! load mmu-ctrl again + andn %twin_tmp1, 0x2, %twin_tmp1 ! clear no-fault bit +LEON_PI(sta %twin_tmp1, [%g0] ASI_LEON_MMUREGS) ! store it +SUN_PI_(sta %twin_tmp1, [%g0] ASI_M_MMUREGS) ! store it + + mov AC_M_SFAR, %twin_tmp2 +LEON_PI(lda [%twin_tmp2] ASI_LEON_MMUREGS, %g0) ! read fault address +SUN_PI_(lda [%twin_tmp2] ASI_M_MMUREGS, %g0) ! read fault address + + mov AC_M_SFSR, %twin_tmp2 +LEON_PI(lda [%twin_tmp2] ASI_LEON_MMUREGS, %twin_tmp2) ! read fault status +SUN_PI_(lda [%twin_tmp2] ASI_M_MMUREGS, %twin_tmp2) ! read fault status + andcc %twin_tmp2, 0x2, %g0 ! did fault occur? + + bne 1f ! yep, cleanup + nop + + wr %t_psr, 0x0, %psr + nop + b fwin_user_finish_up + 0x4 + nop + + /* Did I ever tell you about my window lobotomy? + * anyways... fwin_user_stack_is_bolixed expects + * to be in window 'W' so make it happy or else + * we watchdog badly. + */ +1: + restore %g0, %g0, %g0 + b fwin_user_stack_is_bolixed ! oh well + restore %g0, %g0, %g0 -- cgit v1.2.3