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/platforms/pasemi/iommu.c | 267 ++++++++++++++++++++++++++++++++++ 1 file changed, 267 insertions(+) create mode 100644 arch/powerpc/platforms/pasemi/iommu.c (limited to 'arch/powerpc/platforms/pasemi/iommu.c') diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c new file mode 100644 index 000000000..0a38663d4 --- /dev/null +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2005-2008, PA Semi, Inc + * + * Maintained by: Olof Johansson + */ + +#undef DEBUG + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "pasemi.h" + +#define IOBMAP_PAGE_SHIFT 12 +#define IOBMAP_PAGE_SIZE (1 << IOBMAP_PAGE_SHIFT) +#define IOBMAP_PAGE_MASK (IOBMAP_PAGE_SIZE - 1) + +#define IOB_BASE 0xe0000000 +#define IOB_SIZE 0x3000 +/* Configuration registers */ +#define IOBCAP_REG 0x40 +#define IOBCOM_REG 0x100 +/* Enable IOB address translation */ +#define IOBCOM_ATEN 0x00000100 + +/* Address decode configuration register */ +#define IOB_AD_REG 0x14c +/* IOBCOM_AD_REG fields */ +#define IOB_AD_VGPRT 0x00000e00 +#define IOB_AD_VGAEN 0x00000100 +/* Direct mapping settings */ +#define IOB_AD_MPSEL_MASK 0x00000030 +#define IOB_AD_MPSEL_B38 0x00000000 +#define IOB_AD_MPSEL_B40 0x00000010 +#define IOB_AD_MPSEL_B42 0x00000020 +/* Translation window size / enable */ +#define IOB_AD_TRNG_MASK 0x00000003 +#define IOB_AD_TRNG_256M 0x00000000 +#define IOB_AD_TRNG_2G 0x00000001 +#define IOB_AD_TRNG_128G 0x00000003 + +#define IOB_TABLEBASE_REG 0x154 + +/* Base of the 64 4-byte L1 registers */ +#define IOB_XLT_L1_REGBASE 0x2b00 + +/* Register to invalidate TLB entries */ +#define IOB_AT_INVAL_TLB_REG 0x2d00 + +/* The top two bits of the level 1 entry contains valid and type flags */ +#define IOBMAP_L1E_V 0x40000000 +#define IOBMAP_L1E_V_B 0x80000000 + +/* For big page entries, the bottom two bits contains flags */ +#define IOBMAP_L1E_BIG_CACHED 0x00000002 +#define IOBMAP_L1E_BIG_PRIORITY 0x00000001 + +/* For regular level 2 entries, top 2 bits contain valid and cache flags */ +#define IOBMAP_L2E_V 0x80000000 +#define IOBMAP_L2E_V_CACHED 0xc0000000 + +static void __iomem *iob; +static u32 iob_l1_emptyval; +static u32 iob_l2_emptyval; +static u32 *iob_l2_base; + +static struct iommu_table iommu_table_iobmap; +static int iommu_table_iobmap_inited; + +static int iobmap_build(struct iommu_table *tbl, long index, + long npages, unsigned long uaddr, + enum dma_data_direction direction, + unsigned long attrs) +{ + u32 *ip; + u32 rpn; + unsigned long bus_addr; + + pr_debug("iobmap: build at: %lx, %lx, addr: %lx\n", index, npages, uaddr); + + bus_addr = (tbl->it_offset + index) << IOBMAP_PAGE_SHIFT; + + ip = ((u32 *)tbl->it_base) + index; + + while (npages--) { + rpn = __pa(uaddr) >> IOBMAP_PAGE_SHIFT; + + *(ip++) = IOBMAP_L2E_V | rpn; + /* invalidate tlb, can be optimized more */ + out_le32(iob+IOB_AT_INVAL_TLB_REG, bus_addr >> 14); + + uaddr += IOBMAP_PAGE_SIZE; + bus_addr += IOBMAP_PAGE_SIZE; + } + return 0; +} + + +static void iobmap_free(struct iommu_table *tbl, long index, + long npages) +{ + u32 *ip; + unsigned long bus_addr; + + pr_debug("iobmap: free at: %lx, %lx\n", index, npages); + + bus_addr = (tbl->it_offset + index) << IOBMAP_PAGE_SHIFT; + + ip = ((u32 *)tbl->it_base) + index; + + while (npages--) { + *(ip++) = iob_l2_emptyval; + /* invalidate tlb, can be optimized more */ + out_le32(iob+IOB_AT_INVAL_TLB_REG, bus_addr >> 14); + bus_addr += IOBMAP_PAGE_SIZE; + } +} + +static struct iommu_table_ops iommu_table_iobmap_ops = { + .set = iobmap_build, + .clear = iobmap_free +}; + +static void iommu_table_iobmap_setup(void) +{ + pr_debug(" -> %s\n", __func__); + iommu_table_iobmap.it_busno = 0; + iommu_table_iobmap.it_offset = 0; + iommu_table_iobmap.it_page_shift = IOBMAP_PAGE_SHIFT; + + /* it_size is in number of entries */ + iommu_table_iobmap.it_size = + 0x80000000 >> iommu_table_iobmap.it_page_shift; + + /* Initialize the common IOMMU code */ + iommu_table_iobmap.it_base = (unsigned long)iob_l2_base; + iommu_table_iobmap.it_index = 0; + /* XXXOJN tune this to avoid IOB cache invals. + * Should probably be 8 (64 bytes) + */ + iommu_table_iobmap.it_blocksize = 4; + iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops; + if (!iommu_init_table(&iommu_table_iobmap, 0, 0, 0)) + panic("Failed to initialize iommu table"); + + pr_debug(" <- %s\n", __func__); +} + + + +static void pci_dma_bus_setup_pasemi(struct pci_bus *bus) +{ + pr_debug("pci_dma_bus_setup, bus %p, bus->self %p\n", bus, bus->self); + + if (!iommu_table_iobmap_inited) { + iommu_table_iobmap_inited = 1; + iommu_table_iobmap_setup(); + } +} + + +static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) +{ + pr_debug("pci_dma_dev_setup, dev %p (%s)\n", dev, pci_name(dev)); + +#if !defined(CONFIG_PPC_PASEMI_IOMMU_DMA_FORCE) + /* For non-LPAR environment, don't translate anything for the DMA + * engine. The exception to this is if the user has enabled + * CONFIG_PPC_PASEMI_IOMMU_DMA_FORCE at build time. + */ + if (dev->vendor == 0x1959 && dev->device == 0xa007 && + !firmware_has_feature(FW_FEATURE_LPAR)) { + dev->dev.dma_ops = NULL; + /* + * Set the coherent DMA mask to prevent the iommu + * being used unnecessarily + */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(44); + return; + } +#endif + + set_iommu_table_base(&dev->dev, &iommu_table_iobmap); +} + +static int __init iob_init(struct device_node *dn) +{ + unsigned long tmp; + u32 regword; + int i; + + pr_debug(" -> %s\n", __func__); + + /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */ + iob_l2_base = memblock_alloc_try_nid_raw(1UL << 21, 1UL << 21, + MEMBLOCK_LOW_LIMIT, 0x80000000, + NUMA_NO_NODE); + if (!iob_l2_base) + panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%x\n", + __func__, 1UL << 21, 1UL << 21, 0x80000000); + + pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base); + + /* Allocate a spare page to map all invalid IOTLB pages. */ + tmp = memblock_phys_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); + if (!tmp) + panic("IOBMAP: Cannot allocate spare page!"); + /* Empty l1 is marked invalid */ + iob_l1_emptyval = 0; + /* Empty l2 is mapped to dummy page */ + iob_l2_emptyval = IOBMAP_L2E_V | (tmp >> IOBMAP_PAGE_SHIFT); + + iob = ioremap(IOB_BASE, IOB_SIZE); + if (!iob) + panic("IOBMAP: Cannot map registers!"); + + /* setup direct mapping of the L1 entries */ + for (i = 0; i < 64; i++) { + /* Each L1 covers 32MB, i.e. 8K entries = 32K of ram */ + regword = IOBMAP_L1E_V | (__pa(iob_l2_base + i*0x2000) >> 12); + out_le32(iob+IOB_XLT_L1_REGBASE+i*4, regword); + } + + /* set 2GB translation window, based at 0 */ + regword = in_le32(iob+IOB_AD_REG); + regword &= ~IOB_AD_TRNG_MASK; + regword |= IOB_AD_TRNG_2G; + out_le32(iob+IOB_AD_REG, regword); + + /* Enable translation */ + regword = in_le32(iob+IOBCOM_REG); + regword |= IOBCOM_ATEN; + out_le32(iob+IOBCOM_REG, regword); + + pr_debug(" <- %s\n", __func__); + + return 0; +} + + +/* These are called very early. */ +void __init iommu_init_early_pasemi(void) +{ + int iommu_off; + +#ifndef CONFIG_PPC_PASEMI_IOMMU + iommu_off = 1; +#else + iommu_off = of_chosen && + of_get_property(of_chosen, "linux,iommu-off", NULL); +#endif + if (iommu_off) + return; + + iob_init(NULL); + + pasemi_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pasemi; + pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi; + set_pci_dma_ops(&dma_iommu_ops); +} -- cgit v1.2.3