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/include/asm/paca.h | 305 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 305 insertions(+) create mode 100644 arch/powerpc/include/asm/paca.h (limited to 'arch/powerpc/include/asm/paca.h') diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h new file mode 100644 index 000000000..09f1790d0 --- /dev/null +++ b/arch/powerpc/include/asm/paca.h @@ -0,0 +1,305 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This control block defines the PACA which defines the processor + * specific data for each logical processor on the system. + * There are some pointers defined that are utilized by PLIC. + * + * C 2001 PPC 64 Team, IBM Corp + */ +#ifndef _ASM_POWERPC_PACA_H +#define _ASM_POWERPC_PACA_H +#ifdef __KERNEL__ + +#ifdef CONFIG_PPC64 + +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_PPC_BOOK3E_64 +#include +#else +#include +#endif +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include +#endif +#include +#include +#include +#include +#include + +#include + +register struct paca_struct *local_paca asm("r13"); + +#if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP) +extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */ +/* + * Add standard checks that preemption cannot occur when using get_paca(): + * otherwise the paca_struct it points to may be the wrong one just after. + */ +#define get_paca() ((void) debug_smp_processor_id(), local_paca) +#else +#define get_paca() local_paca +#endif + +#ifdef CONFIG_PPC_PSERIES +#define get_lppaca() (get_paca()->lppaca_ptr) +#endif + +#define get_slb_shadow() (get_paca()->slb_shadow_ptr) + +struct task_struct; +struct rtas_args; + +/* + * Defines the layout of the paca. + * + * This structure is not directly accessed by firmware or the service + * processor. + */ +struct paca_struct { +#ifdef CONFIG_PPC_PSERIES + /* + * Because hw_cpu_id, unlike other paca fields, is accessed + * routinely from other CPUs (from the IRQ code), we stick to + * read-only (after boot) fields in the first cacheline to + * avoid cacheline bouncing. + */ + + struct lppaca *lppaca_ptr; /* Pointer to LpPaca for PLIC */ +#endif /* CONFIG_PPC_PSERIES */ + + /* + * MAGIC: the spinlock functions in arch/powerpc/lib/locks.c + * load lock_token and paca_index with a single lwz + * instruction. They must travel together and be properly + * aligned. + */ +#ifdef __BIG_ENDIAN__ + u16 lock_token; /* Constant 0x8000, used in locks */ + u16 paca_index; /* Logical processor number */ +#else + u16 paca_index; /* Logical processor number */ + u16 lock_token; /* Constant 0x8000, used in locks */ +#endif + + u64 kernel_toc; /* Kernel TOC address */ + u64 kernelbase; /* Base address of kernel */ + u64 kernel_msr; /* MSR while running in kernel */ + void *emergency_sp; /* pointer to emergency stack */ + u64 data_offset; /* per cpu data offset */ + s16 hw_cpu_id; /* Physical processor number */ + u8 cpu_start; /* At startup, processor spins until */ + /* this becomes non-zero. */ + u8 kexec_state; /* set when kexec down has irqs off */ +#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU + struct slb_shadow *slb_shadow_ptr; +#endif + struct dtl_entry *dispatch_log; + struct dtl_entry *dispatch_log_end; +#endif + u64 dscr_default; /* per-CPU default DSCR */ + +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * Now, starting in cacheline 2, the exception save areas + */ + /* used for most interrupts/exceptions */ + u64 exgen[EX_SIZE] __attribute__((aligned(0x80))); + +#ifdef CONFIG_PPC_64S_HASH_MMU + /* SLB related definitions */ + u16 vmalloc_sllp; + u8 slb_cache_ptr; + u8 stab_rr; /* stab/slb round-robin counter */ +#ifdef CONFIG_DEBUG_VM + u8 in_kernel_slb_handler; +#endif + u32 slb_used_bitmap; /* Bitmaps for first 32 SLB entries. */ + u32 slb_kern_bitmap; + u32 slb_cache[SLB_CACHE_ENTRIES]; +#endif +#endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BOOK3E_64 + u64 exgen[8] __aligned(0x40); + /* Keep pgd in the same cacheline as the start of extlb */ + pgd_t *pgd __aligned(0x40); /* Current PGD */ + pgd_t *kernel_pgd; /* Kernel PGD */ + + /* Shared by all threads of a core -- points to tcd of first thread */ + struct tlb_core_data *tcd_ptr; + + /* + * We can have up to 3 levels of reentrancy in the TLB miss handler, + * in each of four exception levels (normal, crit, mcheck, debug). + */ + u64 extlb[12][EX_TLB_SIZE / sizeof(u64)]; + u64 exmc[8]; /* used for machine checks */ + u64 excrit[8]; /* used for crit interrupts */ + u64 exdbg[8]; /* used for debug interrupts */ + + /* Kernel stack pointers for use by special exceptions */ + void *mc_kstack; + void *crit_kstack; + void *dbg_kstack; + + struct tlb_core_data tcd; +#endif /* CONFIG_PPC_BOOK3E_64 */ + +#ifdef CONFIG_PPC_64S_HASH_MMU + unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; + unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE]; +#endif + + /* + * then miscellaneous read-write fields + */ + struct task_struct *__current; /* Pointer to current */ + u64 kstack; /* Saved Kernel stack addr */ + u64 saved_r1; /* r1 save for RTAS calls or PM or EE=0 */ + u64 saved_msr; /* MSR saved here by enter_rtas */ +#ifdef CONFIG_PPC64 + u64 exit_save_r1; /* Syscall/interrupt R1 save */ +#endif +#ifdef CONFIG_PPC_BOOK3E_64 + u16 trap_save; /* Used when bad stack is encountered */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + u8 hsrr_valid; /* HSRRs set for HRFID */ + u8 srr_valid; /* SRRs set for RFID */ +#endif + u8 irq_soft_mask; /* mask for irq soft masking */ + u8 irq_happened; /* irq happened while soft-disabled */ + u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + u8 pmcregs_in_use; /* pseries puts this in lppaca */ +#endif + u64 sprg_vdso; /* Saved user-visible sprg */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u64 tm_scratch; /* TM scratch area for reclaim */ +#endif + +#ifdef CONFIG_PPC_POWERNV + /* PowerNV idle fields */ + /* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */ + unsigned long idle_state; + union { + /* P7/P8 specific fields */ + struct { + /* PNV_THREAD_RUNNING/NAP/SLEEP */ + u8 thread_idle_state; + /* Mask to denote subcore sibling threads */ + u8 subcore_sibling_mask; + }; + + /* P9 specific fields */ + struct { +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* The PSSCR value that the kernel requested before going to stop */ + u64 requested_psscr; + /* Flag to request this thread not to stop */ + atomic_t dont_stop; +#endif + }; + }; +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Non-maskable exceptions that are not performance critical */ + u64 exnmi[EX_SIZE]; /* used for system reset (nmi) */ + u64 exmc[EX_SIZE]; /* used for machine checks */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* Exclusive stacks for system reset and machine check exception. */ + void *nmi_emergency_sp; + void *mc_emergency_sp; + + u16 in_nmi; /* In nmi handler */ + + /* + * Flag to check whether we are in machine check early handler + * and already using emergency stack. + */ + u16 in_mce; + u8 hmi_event_available; /* HMI event is available */ + u8 hmi_p9_special_emu; /* HMI P9 special emulation */ + u32 hmi_irqs; /* HMI irq stat */ +#endif + u8 ftrace_enabled; /* Hard disable ftrace */ + + /* Stuff for accurate time accounting */ + struct cpu_accounting_data accounting; + u64 dtl_ridx; /* read index in dispatch log */ + struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ + +#ifdef CONFIG_KVM_BOOK3S_HANDLER +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE + /* We use this to store guest state in */ + struct kvmppc_book3s_shadow_vcpu shadow_vcpu; +#endif + struct kvmppc_host_state kvm_hstate; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for + * more details + */ + struct sibling_subcore_state *sibling_subcore_state; +#endif +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * rfi fallback flush must be in its own cacheline to prevent + * other paca data leaking into the L1d + */ + u64 exrfi[EX_SIZE] __aligned(0x80); + void *rfi_flush_fallback_area; + u64 l1d_flush_size; +#endif +#ifdef CONFIG_PPC_PSERIES + u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ +#endif /* CONFIG_PPC_PSERIES */ + +#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU + /* Capture SLB related old contents in MCE handler. */ + struct slb_entry *mce_faulty_slbs; + u16 slb_save_cache_ptr; +#endif +#endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_STACKPROTECTOR + unsigned long canary; +#endif +#ifdef CONFIG_MMIOWB + struct mmiowb_state mmiowb_state; +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + struct mce_info *mce_info; + u8 mce_pending_irq_work; +#endif /* CONFIG_PPC_BOOK3S_64 */ +} ____cacheline_aligned; + +extern void copy_mm_to_paca(struct mm_struct *mm); +extern struct paca_struct **paca_ptrs; +extern void initialise_paca(struct paca_struct *new_paca, int cpu); +extern void setup_paca(struct paca_struct *new_paca); +extern void allocate_paca_ptrs(void); +extern void allocate_paca(int cpu); +extern void free_unused_pacas(void); + +#else /* CONFIG_PPC64 */ + +static inline void allocate_paca_ptrs(void) { } +static inline void allocate_paca(int cpu) { } +static inline void free_unused_pacas(void) { } + +#endif /* CONFIG_PPC64 */ + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_PACA_H */ -- cgit v1.2.3