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/cavium-octeon/csrc-octeon.c | 214 ++++++++++++++++++++++++++++++++++ 1 file changed, 214 insertions(+) create mode 100644 arch/mips/cavium-octeon/csrc-octeon.c (limited to 'arch/mips/cavium-octeon/csrc-octeon.c') diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c new file mode 100644 index 000000000..124817609 --- /dev/null +++ b/arch/mips/cavium-octeon/csrc-octeon.c @@ -0,0 +1,214 @@ +/* + * 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) 2007 by Ralf Baechle + * Copyright (C) 2009, 2012 Cavium, Inc. + */ +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include +#include +#include + +static u64 f; +static u64 rdiv; +static u64 sdiv; +static u64 octeon_udelay_factor; +static u64 octeon_ndelay_factor; + +void __init octeon_setup_delays(void) +{ + octeon_udelay_factor = octeon_get_clock_rate() / 1000000; + /* + * For __ndelay we divide by 2^16, so the factor is multiplied + * by the same amount. + */ + octeon_ndelay_factor = (octeon_udelay_factor * 0x10000ull) / 1000ull; + + preset_lpj = octeon_get_clock_rate() / HZ; + + if (current_cpu_type() == CPU_CAVIUM_OCTEON2) { + union cvmx_mio_rst_boot rst_boot; + + rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT); + rdiv = rst_boot.s.c_mul; /* CPU clock */ + sdiv = rst_boot.s.pnr_mul; /* I/O clock */ + f = (0x8000000000000000ull / sdiv) * 2; + } else if (current_cpu_type() == CPU_CAVIUM_OCTEON3) { + union cvmx_rst_boot rst_boot; + + rst_boot.u64 = cvmx_read_csr(CVMX_RST_BOOT); + rdiv = rst_boot.s.c_mul; /* CPU clock */ + sdiv = rst_boot.s.pnr_mul; /* I/O clock */ + f = (0x8000000000000000ull / sdiv) * 2; + } + +} + +/* + * Set the current core's cvmcount counter to the value of the + * IPD_CLK_COUNT. We do this on all cores as they are brought + * on-line. This allows for a read from a local cpu register to + * access a synchronized counter. + * + * On CPU_CAVIUM_OCTEON2 the IPD_CLK_COUNT is scaled by rdiv/sdiv. + */ +void octeon_init_cvmcount(void) +{ + u64 clk_reg; + unsigned long flags; + unsigned loops = 2; + + clk_reg = octeon_has_feature(OCTEON_FEATURE_FPA3) ? + CVMX_FPA_CLK_COUNT : CVMX_IPD_CLK_COUNT; + + /* Clobber loops so GCC will not unroll the following while loop. */ + asm("" : "+r" (loops)); + + local_irq_save(flags); + /* + * Loop several times so we are executing from the cache, + * which should give more deterministic timing. + */ + while (loops--) { + u64 clk_count = cvmx_read_csr(clk_reg); + if (rdiv != 0) { + clk_count *= rdiv; + if (f != 0) { + asm("dmultu\t%[cnt],%[f]\n\t" + "mfhi\t%[cnt]" + : [cnt] "+r" (clk_count) + : [f] "r" (f) + : "hi", "lo"); + } + } + write_c0_cvmcount(clk_count); + } + local_irq_restore(flags); +} + +static u64 octeon_cvmcount_read(struct clocksource *cs) +{ + return read_c0_cvmcount(); +} + +static struct clocksource clocksource_mips = { + .name = "OCTEON_CVMCOUNT", + .read = octeon_cvmcount_read, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +unsigned long long notrace sched_clock(void) +{ + /* 64-bit arithmatic can overflow, so use 128-bit. */ + u64 t1, t2, t3; + unsigned long long rv; + u64 mult = clocksource_mips.mult; + u64 shift = clocksource_mips.shift; + u64 cnt = read_c0_cvmcount(); + + asm ( + "dmultu\t%[cnt],%[mult]\n\t" + "nor\t%[t1],$0,%[shift]\n\t" + "mfhi\t%[t2]\n\t" + "mflo\t%[t3]\n\t" + "dsll\t%[t2],%[t2],1\n\t" + "dsrlv\t%[rv],%[t3],%[shift]\n\t" + "dsllv\t%[t1],%[t2],%[t1]\n\t" + "or\t%[rv],%[t1],%[rv]\n\t" + : [rv] "=&r" (rv), [t1] "=&r" (t1), [t2] "=&r" (t2), [t3] "=&r" (t3) + : [cnt] "r" (cnt), [mult] "r" (mult), [shift] "r" (shift) + : "hi", "lo"); + return rv; +} + +void __init plat_time_init(void) +{ + clocksource_mips.rating = 300; + clocksource_register_hz(&clocksource_mips, octeon_get_clock_rate()); +} + +void __udelay(unsigned long us) +{ + u64 cur, end, inc; + + cur = read_c0_cvmcount(); + + inc = us * octeon_udelay_factor; + end = cur + inc; + + while (end > cur) + cur = read_c0_cvmcount(); +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long ns) +{ + u64 cur, end, inc; + + cur = read_c0_cvmcount(); + + inc = ((ns * octeon_ndelay_factor) >> 16); + end = cur + inc; + + while (end > cur) + cur = read_c0_cvmcount(); +} +EXPORT_SYMBOL(__ndelay); + +void __delay(unsigned long loops) +{ + u64 cur, end; + + cur = read_c0_cvmcount(); + end = cur + loops; + + while (end > cur) + cur = read_c0_cvmcount(); +} +EXPORT_SYMBOL(__delay); + + +/** + * octeon_io_clk_delay - wait for a given number of io clock cycles to pass. + * + * We scale the wait by the clock ratio, and then wait for the + * corresponding number of core clocks. + * + * @count: The number of clocks to wait. + */ +void octeon_io_clk_delay(unsigned long count) +{ + u64 cur, end; + + cur = read_c0_cvmcount(); + if (rdiv != 0) { + end = count * rdiv; + if (f != 0) { + asm("dmultu\t%[cnt],%[f]\n\t" + "mfhi\t%[cnt]" + : [cnt] "+r" (end) + : [f] "r" (f) + : "hi", "lo"); + } + end = cur + end; + } else { + end = cur + count; + } + while (end > cur) + cur = read_c0_cvmcount(); +} +EXPORT_SYMBOL(octeon_io_clk_delay); -- cgit v1.2.3