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/riscv/include/asm/pgtable-64.h | 377 ++++++++++++++++++++++++++++++++++++ 1 file changed, 377 insertions(+) create mode 100644 arch/riscv/include/asm/pgtable-64.h (limited to 'arch/riscv/include/asm/pgtable-64.h') diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h new file mode 100644 index 000000000..42a042c0e --- /dev/null +++ b/arch/riscv/include/asm/pgtable-64.h @@ -0,0 +1,377 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGTABLE_64_H +#define _ASM_RISCV_PGTABLE_64_H + +#include +#include +#include + +extern bool pgtable_l4_enabled; +extern bool pgtable_l5_enabled; + +#define PGDIR_SHIFT_L3 30 +#define PGDIR_SHIFT_L4 39 +#define PGDIR_SHIFT_L5 48 +#define PGDIR_SIZE_L3 (_AC(1, UL) << PGDIR_SHIFT_L3) + +#define PGDIR_SHIFT (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \ + (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)) +/* Size of region mapped by a page global directory */ +#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE - 1)) + +/* p4d is folded into pgd in case of 4-level page table */ +#define P4D_SHIFT_L3 30 +#define P4D_SHIFT_L4 39 +#define P4D_SHIFT_L5 39 +#define P4D_SHIFT (pgtable_l5_enabled ? P4D_SHIFT_L5 : \ + (pgtable_l4_enabled ? P4D_SHIFT_L4 : P4D_SHIFT_L3)) +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE - 1)) + +/* pud is folded into pgd in case of 3-level page table */ +#define PUD_SHIFT 30 +#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE - 1)) + +#define PMD_SHIFT 21 +/* Size of region mapped by a page middle directory */ +#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE - 1)) + +/* Page 4th Directory entry */ +typedef struct { + unsigned long p4d; +} p4d_t; + +#define p4d_val(x) ((x).p4d) +#define __p4d(x) ((p4d_t) { (x) }) +#define PTRS_PER_P4D (PAGE_SIZE / sizeof(p4d_t)) + +/* Page Upper Directory entry */ +typedef struct { + unsigned long pud; +} pud_t; + +#define pud_val(x) ((x).pud) +#define __pud(x) ((pud_t) { (x) }) +#define PTRS_PER_PUD (PAGE_SIZE / sizeof(pud_t)) + +/* Page Middle Directory entry */ +typedef struct { + unsigned long pmd; +} pmd_t; + +#define pmd_val(x) ((x).pmd) +#define __pmd(x) ((pmd_t) { (x) }) + +#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t)) + +/* + * rv64 PTE format: + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 + * N MT RSV PFN reserved for SW D A G U X W R V + */ +#define _PAGE_PFN_MASK GENMASK(53, 10) + +/* + * [62:61] Svpbmt Memory Type definitions: + * + * 00 - PMA Normal Cacheable, No change to implied PMA memory type + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory + * 11 - Rsvd Reserved for future standard use + */ +#define _PAGE_NOCACHE_SVPBMT (1UL << 61) +#define _PAGE_IO_SVPBMT (1UL << 62) +#define _PAGE_MTMASK_SVPBMT (_PAGE_NOCACHE_SVPBMT | _PAGE_IO_SVPBMT) + +/* + * [63:59] T-Head Memory Type definitions: + * + * 00000 - NC Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable + * 01110 - PMA Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable + * 10000 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable + */ +#define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) +#define _PAGE_NOCACHE_THEAD 0UL +#define _PAGE_IO_THEAD (1UL << 63) +#define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) + +static inline u64 riscv_page_mtmask(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_MTMASK); + return val; +} + +static inline u64 riscv_page_nocache(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_NOCACHE); + return val; +} + +static inline u64 riscv_page_io(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_IO); + return val; +} + +#define _PAGE_NOCACHE riscv_page_nocache() +#define _PAGE_IO riscv_page_io() +#define _PAGE_MTMASK riscv_page_mtmask() + +/* Set of bits to preserve across pte_modify() */ +#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_WRITE | _PAGE_EXEC | \ + _PAGE_USER | _PAGE_GLOBAL | \ + _PAGE_MTMASK)) + +static inline int pud_present(pud_t pud) +{ + return (pud_val(pud) & _PAGE_PRESENT); +} + +static inline int pud_none(pud_t pud) +{ + return (pud_val(pud) == 0); +} + +static inline int pud_bad(pud_t pud) +{ + return !pud_present(pud); +} + +#define pud_leaf pud_leaf +static inline int pud_leaf(pud_t pud) +{ + return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF); +} + +static inline int pud_user(pud_t pud) +{ + return pud_val(pud) & _PAGE_USER; +} + +static inline void set_pud(pud_t *pudp, pud_t pud) +{ + *pudp = pud; +} + +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, __pud(0)); +} + +static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot) +{ + return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +static inline unsigned long _pud_pfn(pud_t pud) +{ + return __page_val_to_pfn(pud_val(pud)); +} + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)pfn_to_virt(__page_val_to_pfn(pud_val(pud))); +} + +static inline struct page *pud_page(pud_t pud) +{ + return pfn_to_page(__page_val_to_pfn(pud_val(pud))); +} + +#define mm_p4d_folded mm_p4d_folded +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + if (pgtable_l5_enabled) + return false; + + return true; +} + +#define mm_pud_folded mm_pud_folded +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + if (pgtable_l4_enabled) + return false; + + return true; +} + +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) + +static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) +{ + unsigned long prot_val = pgprot_val(prot); + + ALT_THEAD_PMA(prot_val); + + return __pmd((pfn << _PAGE_PFN_SHIFT) | prot_val); +} + +static inline unsigned long _pmd_pfn(pmd_t pmd) +{ + return __page_val_to_pfn(pmd_val(pmd)); +} + +#define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) + +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e)) + +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e)) + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %016lx.\n", __FILE__, __LINE__, p4d_val(e)) + +static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + if (pgtable_l4_enabled) + *p4dp = p4d; + else + set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) }); +} + +static inline int p4d_none(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (p4d_val(p4d) == 0); + + return 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (p4d_val(p4d) & _PAGE_PRESENT); + + return 1; +} + +static inline int p4d_bad(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return !p4d_present(p4d); + + return 0; +} + +static inline void p4d_clear(p4d_t *p4d) +{ + if (pgtable_l4_enabled) + set_p4d(p4d, __p4d(0)); +} + +static inline p4d_t pfn_p4d(unsigned long pfn, pgprot_t prot) +{ + return __p4d((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +static inline unsigned long _p4d_pfn(p4d_t p4d) +{ + return __page_val_to_pfn(p4d_val(p4d)); +} + +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (pud_t *)pfn_to_virt(__page_val_to_pfn(p4d_val(p4d))); + + return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) }); +} +#define p4d_page_vaddr(p4d) ((unsigned long)p4d_pgtable(p4d)) + +static inline struct page *p4d_page(p4d_t p4d) +{ + return pfn_to_page(__page_val_to_pfn(p4d_val(p4d))); +} + +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +#define pud_offset pud_offset +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + if (pgtable_l4_enabled) + return p4d_pgtable(*p4d) + pud_index(address); + + return (pud_t *)p4d; +} + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (pgtable_l5_enabled) + *pgdp = pgd; + else + set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) }); +} + +static inline int pgd_none(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (pgd_val(pgd) == 0); + + return 0; +} + +static inline int pgd_present(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (pgd_val(pgd) & _PAGE_PRESENT); + + return 1; +} + +static inline int pgd_bad(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return !pgd_present(pgd); + + return 0; +} + +static inline void pgd_clear(pgd_t *pgd) +{ + if (pgtable_l5_enabled) + set_pgd(pgd, __pgd(0)); +} + +static inline p4d_t *pgd_pgtable(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (p4d_t *)pfn_to_virt(__page_val_to_pfn(pgd_val(pgd))); + + return (p4d_t *)p4d_pgtable((p4d_t) { pgd_val(pgd) }); +} +#define pgd_page_vaddr(pgd) ((unsigned long)pgd_pgtable(pgd)) + +static inline struct page *pgd_page(pgd_t pgd) +{ + return pfn_to_page(__page_val_to_pfn(pgd_val(pgd))); +} +#define pgd_page(pgd) pgd_page(pgd) + +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +#define p4d_offset p4d_offset +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + if (pgtable_l5_enabled) + return pgd_pgtable(*pgd) + p4d_index(address); + + return (p4d_t *)pgd; +} + +#endif /* _ASM_RISCV_PGTABLE_64_H */ -- cgit v1.2.3