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/misc_64.S | 497 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 497 insertions(+) create mode 100644 arch/powerpc/kernel/misc_64.S (limited to 'arch/powerpc/kernel/misc_64.S') diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S new file mode 100644 index 000000000..c39c07a4c --- /dev/null +++ b/arch/powerpc/kernel/misc_64.S @@ -0,0 +1,497 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This file contains miscellaneous low-level functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + .text + +_GLOBAL(__bswapdi2) +EXPORT_SYMBOL(__bswapdi2) + srdi r8,r3,32 + rlwinm r7,r3,8,0xffffffff + rlwimi r7,r3,24,0,7 + rlwinm r9,r8,8,0xffffffff + rlwimi r7,r3,24,16,23 + rlwimi r9,r8,24,0,7 + rlwimi r9,r8,24,16,23 + sldi r7,r7,32 + or r3,r7,r9 + blr + + +#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX +_GLOBAL(rmci_on) + sync + isync + li r3,0x100 + rldicl r3,r3,32,0 + mfspr r5,SPRN_HID4 + or r5,r5,r3 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + sync + blr + +_GLOBAL(rmci_off) + sync + isync + li r3,0x100 + rldicl r3,r3,32,0 + mfspr r5,SPRN_HID4 + andc r5,r5,r3 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + sync + blr +#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */ + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) + +/* + * Do an IO access in real mode + */ +_GLOBAL(real_readb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + mfspr r6,SPRN_HID4 + rldicl r5,r6,32,0 + ori r5,r5,0x100 + rldicl r5,r5,32,0 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + lbz r3,0(r3) + sync + mtspr SPRN_HID4,r6 + isync + slbia + isync + mtmsrd r7 + sync + isync + blr + + /* + * Do an IO access in real mode + */ +_GLOBAL(real_writeb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + mfspr r6,SPRN_HID4 + rldicl r5,r6,32,0 + ori r5,r5,0x100 + rldicl r5,r5,32,0 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + stb r3,0(r4) + sync + mtspr SPRN_HID4,r6 + isync + slbia + isync + mtmsrd r7 + sync + isync + blr +#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */ + +#ifdef CONFIG_PPC_PASEMI + +_GLOBAL(real_205_readb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + LBZCIX(R3,R0,R3) + isync + mtmsrd r7 + sync + isync + blr + +_GLOBAL(real_205_writeb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + STBCIX(R3,R0,R4) + isync + mtmsrd r7 + sync + isync + blr + +#endif /* CONFIG_PPC_PASEMI */ + + +#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE) +/* + * SCOM access functions for 970 (FX only for now) + * + * unsigned long scom970_read(unsigned int address); + * void scom970_write(unsigned int address, unsigned long value); + * + * The address passed in is the 24 bits register address. This code + * is 970 specific and will not check the status bits, so you should + * know what you are doing. + */ +_GLOBAL(scom970_read) + /* interrupts off */ + mfmsr r4 + ori r0,r4,MSR_EE + xori r0,r0,MSR_EE + mtmsrd r0,1 + + /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + * (including parity). On current CPUs they must be 0'd, + * and finally or in RW bit + */ + rlwinm r3,r3,8,0,15 + ori r3,r3,0x8000 + + /* do the actual scom read */ + sync + mtspr SPRN_SCOMC,r3 + isync + mfspr r3,SPRN_SCOMD + isync + mfspr r0,SPRN_SCOMC + isync + + /* XXX: fixup result on some buggy 970's (ouch ! we lost a bit, bah + * that's the best we can do). Not implemented yet as we don't use + * the scom on any of the bogus CPUs yet, but may have to be done + * ultimately + */ + + /* restore interrupts */ + mtmsrd r4,1 + blr + + +_GLOBAL(scom970_write) + /* interrupts off */ + mfmsr r5 + ori r0,r5,MSR_EE + xori r0,r0,MSR_EE + mtmsrd r0,1 + + /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + * (including parity). On current CPUs they must be 0'd. + */ + + rlwinm r3,r3,8,0,15 + + sync + mtspr SPRN_SCOMD,r4 /* write data */ + isync + mtspr SPRN_SCOMC,r3 /* write command */ + isync + mfspr 3,SPRN_SCOMC + isync + + /* restore interrupts */ + mtmsrd r5,1 + blr +#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */ + +/* kexec_wait(phys_cpu) + * + * wait for the flag to change, indicating this kernel is going away but + * the slave code for the next one is at addresses 0 to 100. + * + * This is used by all slaves, even those that did not find a matching + * paca in the secondary startup code. + * + * Physical (hardware) cpu id should be in r3. + */ +_GLOBAL(kexec_wait) + bcl 20,31,$+4 +1: mflr r5 + addi r5,r5,kexec_flag-1b + +99: HMT_LOW +#ifdef CONFIG_KEXEC_CORE /* use no memory without kexec */ + lwz r4,0(r5) + cmpwi 0,r4,0 + beq 99b +#ifdef CONFIG_PPC_BOOK3S_64 + li r10,0x60 + mfmsr r11 + clrrdi r11,r11,1 /* Clear MSR_LE */ + mtsrr0 r10 + mtsrr1 r11 + rfid +#else + /* Create TLB entry in book3e_secondary_core_init */ + li r4,0 + ba 0x60 +#endif +#endif + +/* this can be in text because we won't change it until we are + * running in real anyways + */ +kexec_flag: + .long 0 + + +#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_PPC_BOOK3E_64 +/* + * BOOK3E has no real MMU mode, so we have to setup the initial TLB + * for a core to identity map v:0 to p:0. This current implementation + * assumes that 1G is enough for kexec. + */ +kexec_create_tlb: + /* + * Invalidate all non-IPROT TLB entries to avoid any TLB conflict. + * IPROT TLB entries should be >= PAGE_OFFSET and thus not conflict. + */ + PPC_TLBILX_ALL(0,R0) + sync + isync + + mfspr r10,SPRN_TLB1CFG + andi. r10,r10,TLBnCFG_N_ENTRY /* Extract # entries */ + subi r10,r10,1 /* Last entry: no conflict with kernel text */ + lis r9,MAS0_TLBSEL(1)@h + rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */ + +/* Set up a temp identity mapping v:0 to p:0 and return to it. */ + mtspr SPRN_MAS0,r9 + + lis r9,(MAS1_VALID|MAS1_IPROT)@h + ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l + mtspr SPRN_MAS1,r9 + + LOAD_REG_IMMEDIATE(r9, 0x0 | MAS2_M_IF_NEEDED) + mtspr SPRN_MAS2,r9 + + LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX) + mtspr SPRN_MAS3,r9 + li r9,0 + mtspr SPRN_MAS7,r9 + + tlbwe + isync + blr +#endif + +/* kexec_smp_wait(void) + * + * call with interrupts off + * note: this is a terminal routine, it does not save lr + * + * get phys id from paca + * switch to real mode + * mark the paca as no longer used + * join other cpus in kexec_wait(phys_id) + */ +_GLOBAL(kexec_smp_wait) + lhz r3,PACAHWCPUID(r13) + bl real_mode + + li r4,KEXEC_STATE_REAL_MODE + stb r4,PACAKEXECSTATE(r13) + + b kexec_wait + +/* + * switch to real mode (turn mmu off) + * we use the early kernel trick that the hardware ignores bits + * 0 and 1 (big endian) of the effective address in real mode + * + * don't overwrite r3 here, it is live for kexec_wait above. + */ +SYM_FUNC_START_LOCAL(real_mode) /* assume normal blr return */ +#ifdef CONFIG_PPC_BOOK3E_64 + /* Create an identity mapping. */ + b kexec_create_tlb +#else +1: li r9,MSR_RI + li r10,MSR_DR|MSR_IR + mflr r11 /* return address to SRR0 */ + mfmsr r12 + andc r9,r12,r9 + andc r10,r12,r10 + + mtmsrd r9,1 + mtspr SPRN_SRR1,r10 + mtspr SPRN_SRR0,r11 + rfid +#endif +SYM_FUNC_END(real_mode) + +/* + * kexec_sequence(newstack, start, image, control, clear_all(), + copy_with_mmu_off) + * + * does the grungy work with stack switching and real mode switches + * also does simple calls to other code + */ + +_GLOBAL(kexec_sequence) + mflr r0 + std r0,16(r1) + + /* switch stacks to newstack -- &kexec_stack.stack */ + stdu r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r3) + mr r1,r3 + + li r0,0 + std r0,16(r1) + + /* save regs for local vars on new stack. + * yes, we won't go back, but ... + */ + std r31,-8(r1) + std r30,-16(r1) + std r29,-24(r1) + std r28,-32(r1) + std r27,-40(r1) + std r26,-48(r1) + std r25,-56(r1) + + stdu r1,-STACK_FRAME_MIN_SIZE-64(r1) + + /* save args into preserved regs */ + mr r31,r3 /* newstack (both) */ + mr r30,r4 /* start (real) */ + mr r29,r5 /* image (virt) */ + mr r28,r6 /* control, unused */ + mr r27,r7 /* clear_all() fn desc */ + mr r26,r8 /* copy_with_mmu_off */ + lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ + + /* disable interrupts, we are overwriting kernel data next */ +#ifdef CONFIG_PPC_BOOK3E_64 + wrteei 0 +#else + mfmsr r3 + rlwinm r3,r3,0,17,15 + mtmsrd r3,1 +#endif + + /* We need to turn the MMU off unless we are in hash mode + * under a hypervisor + */ + cmpdi r26,0 + beq 1f + bl real_mode +1: + /* copy dest pages, flush whole dest image */ + mr r3,r29 + bl kexec_copy_flush /* (image) */ + + /* turn off mmu now if not done earlier */ + cmpdi r26,0 + bne 1f + bl real_mode + + /* copy 0x100 bytes starting at start to 0 */ +1: li r3,0 + mr r4,r30 /* start, aka phys mem offset */ + li r5,0x100 + li r6,0 + bl copy_and_flush /* (dest, src, copy limit, start offset) */ +1: /* assume normal blr return */ + + /* release other cpus to the new kernel secondary start at 0x60 */ + mflr r5 + li r6,1 + stw r6,kexec_flag-1b(5) + + cmpdi r27,0 + beq 1f + + /* clear out hardware hash page table and tlb */ +#ifdef CONFIG_PPC64_ELF_ABI_V1 + ld r12,0(r27) /* deref function descriptor */ +#else + mr r12,r27 +#endif + mtctr r12 + bctrl /* mmu_hash_ops.hpte_clear_all(void); */ + +/* + * kexec image calling is: + * the first 0x100 bytes of the entry point are copied to 0 + * + * all slaves branch to slave = 0x60 (absolute) + * slave(phys_cpu_id); + * + * master goes to start = entry point + * start(phys_cpu_id, start, 0); + * + * + * a wrapper is needed to call existing kernels, here is an approximate + * description of one method: + * + * v2: (2.6.10) + * start will be near the boot_block (maybe 0x100 bytes before it?) + * it will have a 0x60, which will b to boot_block, where it will wait + * and 0 will store phys into struct boot-block and load r3 from there, + * copy kernel 0-0x100 and tell slaves to back down to 0x60 again + * + * v1: (2.6.9) + * boot block will have all cpus scanning device tree to see if they + * are the boot cpu ????? + * other device tree differences (prop sizes, va vs pa, etc)... + */ +1: mr r3,r25 # my phys cpu + mr r4,r30 # start, aka phys mem offset + mtlr 4 + li r5,0 + blr /* image->start(physid, image->start, 0); */ +#endif /* CONFIG_KEXEC_CORE */ -- cgit v1.2.3