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/arm/kernel/tcm.c | 435 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 435 insertions(+) create mode 100644 arch/arm/kernel/tcm.c (limited to 'arch/arm/kernel/tcm.c') diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c new file mode 100644 index 000000000..d3a85f01b --- /dev/null +++ b/arch/arm/kernel/tcm.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008-2009 ST-Ericsson AB + * TCM memory handling for ARM systems + * + * Author: Linus Walleij + * Author: Rickard Andersson + */ +#include +#include +#include +#include +#include +#include +#include /* memcpy */ +#include +#include +#include +#include +#include +#include + +#define TCMTR_FORMAT_MASK 0xe0000000U + +static struct gen_pool *tcm_pool; +static bool dtcm_present; +static bool itcm_present; + +/* TCM section definitions from the linker */ +extern char __itcm_start, __sitcm_text, __eitcm_text; +extern char __dtcm_start, __sdtcm_data, __edtcm_data; + +/* These will be increased as we run */ +static u32 dtcm_end = DTCM_OFFSET; +static u32 itcm_end = ITCM_OFFSET; + +/* + * TCM memory resources + */ +static struct resource dtcm_res = { + .name = "DTCM RAM", + .start = DTCM_OFFSET, + .end = DTCM_OFFSET, + .flags = IORESOURCE_MEM +}; + +static struct resource itcm_res = { + .name = "ITCM RAM", + .start = ITCM_OFFSET, + .end = ITCM_OFFSET, + .flags = IORESOURCE_MEM +}; + +static struct map_desc dtcm_iomap[] __initdata = { + { + .virtual = DTCM_OFFSET, + .pfn = __phys_to_pfn(DTCM_OFFSET), + .length = 0, + .type = MT_MEMORY_RW_DTCM + } +}; + +static struct map_desc itcm_iomap[] __initdata = { + { + .virtual = ITCM_OFFSET, + .pfn = __phys_to_pfn(ITCM_OFFSET), + .length = 0, + .type = MT_MEMORY_RWX_ITCM, + } +}; + +/* + * Allocate a chunk of TCM memory + */ +void *tcm_alloc(size_t len) +{ + unsigned long vaddr; + + if (!tcm_pool) + return NULL; + + vaddr = gen_pool_alloc(tcm_pool, len); + if (!vaddr) + return NULL; + + return (void *) vaddr; +} +EXPORT_SYMBOL(tcm_alloc); + +/* + * Free a chunk of TCM memory + */ +void tcm_free(void *addr, size_t len) +{ + gen_pool_free(tcm_pool, (unsigned long) addr, len); +} +EXPORT_SYMBOL(tcm_free); + +bool tcm_dtcm_present(void) +{ + return dtcm_present; +} +EXPORT_SYMBOL(tcm_dtcm_present); + +bool tcm_itcm_present(void) +{ + return itcm_present; +} +EXPORT_SYMBOL(tcm_itcm_present); + +static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks, + u32 *offset) +{ + const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128, + 256, 512, 1024, -1, -1, -1, -1 }; + u32 tcm_region; + int tcm_size; + + /* + * If there are more than one TCM bank of this type, + * select the TCM bank to operate on in the TCM selection + * register. + */ + if (banks > 1) + asm("mcr p15, 0, %0, c9, c2, 0" + : /* No output operands */ + : "r" (bank)); + + /* Read the special TCM region register c9, 0 */ + if (!type) + asm("mrc p15, 0, %0, c9, c1, 0" + : "=r" (tcm_region)); + else + asm("mrc p15, 0, %0, c9, c1, 1" + : "=r" (tcm_region)); + + tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f]; + if (tcm_size < 0) { + pr_err("CPU: %sTCM%d of unknown size\n", + type ? "I" : "D", bank); + return -EINVAL; + } else if (tcm_size > 32) { + pr_err("CPU: %sTCM%d larger than 32k found\n", + type ? "I" : "D", bank); + return -EINVAL; + } else { + pr_info("CPU: found %sTCM%d %dk @ %08x, %senabled\n", + type ? "I" : "D", + bank, + tcm_size, + (tcm_region & 0xfffff000U), + (tcm_region & 1) ? "" : "not "); + } + + /* Not much fun you can do with a size 0 bank */ + if (tcm_size == 0) + return 0; + + /* Force move the TCM bank to where we want it, enable */ + tcm_region = *offset | (tcm_region & 0x00000ffeU) | 1; + + if (!type) + asm("mcr p15, 0, %0, c9, c1, 0" + : /* No output operands */ + : "r" (tcm_region)); + else + asm("mcr p15, 0, %0, c9, c1, 1" + : /* No output operands */ + : "r" (tcm_region)); + + /* Increase offset */ + *offset += (tcm_size << 10); + + pr_info("CPU: moved %sTCM%d %dk to %08x, enabled\n", + type ? "I" : "D", + bank, + tcm_size, + (tcm_region & 0xfffff000U)); + return 0; +} + +/* + * When we are running in the non-secure world and the secure world + * has not explicitly given us access to the TCM we will get an + * undefined error when reading the TCM region register in the + * setup_tcm_bank function (above). + * + * There are two variants of this register read that we need to trap, + * the read for the data TCM and the read for the instruction TCM: + * c0370628: ee196f11 mrc 15, 0, r6, cr9, cr1, {0} + * c0370674: ee196f31 mrc 15, 0, r6, cr9, cr1, {1} + * + * Our undef hook mask explicitly matches all fields of the encoded + * instruction other than the destination register. The mask also + * only allows operand 2 to have the values 0 or 1. + * + * The undefined hook is defined as __init and __initdata, and therefore + * must be removed before tcm_init returns. + * + * In this particular case (MRC with ARM condition code ALways) the + * Thumb-2 and ARM instruction encoding are identical, so this hook + * will work on a Thumb-2 kernel. + * + * See A8.8.107, DDI0406C_C ARM Architecture Reference Manual, Encoding + * T1/A1 for the bit-by-bit details. + * + * mrc p15, 0, XX, c9, c1, 0 + * mrc p15, 0, XX, c9, c1, 1 + * | | | | | | | +---- opc2 0|1 = 000|001 + * | | | | | | +------- CRm 0 = 0001 + * | | | | | +----------- CRn 0 = 1001 + * | | | | +--------------- Rt ? = ???? + * | | | +------------------- opc1 0 = 000 + * | | +----------------------- coproc 15 = 1111 + * | +-------------------------- condition ALways = 1110 + * +----------------------------- instruction MRC = 1110 + * + * Encoding this as per A8.8.107 of DDI0406C, Encoding T1/A1, yields: + * 1111 1111 1111 1111 0000 1111 1101 1111 Required Mask + * 1110 1110 0001 1001 ???? 1111 0001 0001 mrc p15, 0, XX, c9, c1, 0 + * 1110 1110 0001 1001 ???? 1111 0011 0001 mrc p15, 0, XX, c9, c1, 1 + * [ ] [ ] [ ]| [ ] [ ] [ ] [ ]| +--- CRm + * | | | | | | | | +----- SBO + * | | | | | | | +------- opc2 + * | | | | | | +----------- coproc + * | | | | | +---------------- Rt + * | | | | +--------------------- CRn + * | | | +------------------------- SBO + * | | +--------------------------- opc1 + * | +------------------------------- instruction + * +------------------------------------ condition + */ +#define TCM_REGION_READ_MASK 0xffff0fdf +#define TCM_REGION_READ_INSTR 0xee190f11 +#define DEST_REG_SHIFT 12 +#define DEST_REG_MASK 0xf + +static int __init tcm_handler(struct pt_regs *regs, unsigned int instr) +{ + regs->uregs[(instr >> DEST_REG_SHIFT) & DEST_REG_MASK] = 0; + regs->ARM_pc += 4; + return 0; +} + +static struct undef_hook tcm_hook __initdata = { + .instr_mask = TCM_REGION_READ_MASK, + .instr_val = TCM_REGION_READ_INSTR, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = tcm_handler +}; + +/* + * This initializes the TCM memory + */ +void __init tcm_init(void) +{ + u32 tcm_status; + u8 dtcm_banks; + u8 itcm_banks; + size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data; + size_t itcm_code_sz = &__eitcm_text - &__sitcm_text; + char *start; + char *end; + char *ram; + int ret; + int i; + + /* + * Prior to ARMv5 there is no TCM, and trying to read the status + * register will hang the processor. + */ + if (cpu_architecture() < CPU_ARCH_ARMv5) { + if (dtcm_code_sz || itcm_code_sz) + pr_info("CPU TCM: %u bytes of DTCM and %u bytes of " + "ITCM code compiled in, but no TCM present " + "in pre-v5 CPU\n", dtcm_code_sz, itcm_code_sz); + return; + } + + tcm_status = read_cpuid_tcmstatus(); + + /* + * This code only supports v6-compatible TCMTR implementations. + */ + if (tcm_status & TCMTR_FORMAT_MASK) + return; + + dtcm_banks = (tcm_status >> 16) & 0x03; + itcm_banks = (tcm_status & 0x03); + + register_undef_hook(&tcm_hook); + + /* Values greater than 2 for D/ITCM banks are "reserved" */ + if (dtcm_banks > 2) + dtcm_banks = 0; + if (itcm_banks > 2) + itcm_banks = 0; + + /* Setup DTCM if present */ + if (dtcm_banks > 0) { + for (i = 0; i < dtcm_banks; i++) { + ret = setup_tcm_bank(0, i, dtcm_banks, &dtcm_end); + if (ret) + goto unregister; + } + /* This means you compiled more code than fits into DTCM */ + if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) { + pr_info("CPU DTCM: %u bytes of code compiled to " + "DTCM but only %lu bytes of DTCM present\n", + dtcm_code_sz, (dtcm_end - DTCM_OFFSET)); + goto no_dtcm; + } + /* + * This means that the DTCM sizes were 0 or the DTCM banks + * were inaccessible due to TrustZone configuration. + */ + if (!(dtcm_end - DTCM_OFFSET)) + goto no_dtcm; + dtcm_res.end = dtcm_end - 1; + request_resource(&iomem_resource, &dtcm_res); + dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET; + iotable_init(dtcm_iomap, 1); + /* Copy data from RAM to DTCM */ + start = &__sdtcm_data; + end = &__edtcm_data; + ram = &__dtcm_start; + memcpy(start, ram, dtcm_code_sz); + pr_debug("CPU DTCM: copied data from %p - %p\n", + start, end); + dtcm_present = true; + } else if (dtcm_code_sz) { + pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no " + "DTCM banks present in CPU\n", dtcm_code_sz); + } + +no_dtcm: + /* Setup ITCM if present */ + if (itcm_banks > 0) { + for (i = 0; i < itcm_banks; i++) { + ret = setup_tcm_bank(1, i, itcm_banks, &itcm_end); + if (ret) + goto unregister; + } + /* This means you compiled more code than fits into ITCM */ + if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) { + pr_info("CPU ITCM: %u bytes of code compiled to " + "ITCM but only %lu bytes of ITCM present\n", + itcm_code_sz, (itcm_end - ITCM_OFFSET)); + goto unregister; + } + /* + * This means that the ITCM sizes were 0 or the ITCM banks + * were inaccessible due to TrustZone configuration. + */ + if (!(itcm_end - ITCM_OFFSET)) + goto unregister; + itcm_res.end = itcm_end - 1; + request_resource(&iomem_resource, &itcm_res); + itcm_iomap[0].length = itcm_end - ITCM_OFFSET; + iotable_init(itcm_iomap, 1); + /* Copy code from RAM to ITCM */ + start = &__sitcm_text; + end = &__eitcm_text; + ram = &__itcm_start; + memcpy(start, ram, itcm_code_sz); + pr_debug("CPU ITCM: copied code from %p - %p\n", + start, end); + itcm_present = true; + } else if (itcm_code_sz) { + pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no " + "ITCM banks present in CPU\n", itcm_code_sz); + } + +unregister: + unregister_undef_hook(&tcm_hook); +} + +/* + * This creates the TCM memory pool and has to be done later, + * during the core_initicalls, since the allocator is not yet + * up and running when the first initialization runs. + */ +static int __init setup_tcm_pool(void) +{ + u32 dtcm_pool_start = (u32) &__edtcm_data; + u32 itcm_pool_start = (u32) &__eitcm_text; + int ret; + + /* + * Set up malloc pool, 2^2 = 4 bytes granularity since + * the TCM is sometimes just 4 KiB. NB: pages and cache + * line alignments does not matter in TCM! + */ + tcm_pool = gen_pool_create(2, -1); + + pr_debug("Setting up TCM memory pool\n"); + + /* Add the rest of DTCM to the TCM pool */ + if (dtcm_present) { + if (dtcm_pool_start < dtcm_end) { + ret = gen_pool_add(tcm_pool, dtcm_pool_start, + dtcm_end - dtcm_pool_start, -1); + if (ret) { + pr_err("CPU DTCM: could not add DTCM " \ + "remainder to pool!\n"); + return ret; + } + pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \ + "the TCM memory pool\n", + dtcm_end - dtcm_pool_start, + dtcm_pool_start); + } + } + + /* Add the rest of ITCM to the TCM pool */ + if (itcm_present) { + if (itcm_pool_start < itcm_end) { + ret = gen_pool_add(tcm_pool, itcm_pool_start, + itcm_end - itcm_pool_start, -1); + if (ret) { + pr_err("CPU ITCM: could not add ITCM " \ + "remainder to pool!\n"); + return ret; + } + pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \ + "the TCM memory pool\n", + itcm_end - itcm_pool_start, + itcm_pool_start); + } + } + return 0; +} + +core_initcall(setup_tcm_pool); -- cgit v1.2.3