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(). ... --- drivers/gpu/drm/msm/msm_iommu.c | 408 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 408 insertions(+) create mode 100644 drivers/gpu/drm/msm/msm_iommu.c (limited to 'drivers/gpu/drm/msm/msm_iommu.c') diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c new file mode 100644 index 000000000..c2507582e --- /dev/null +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2013 Red Hat + * Author: Rob Clark + */ + +#include +#include +#include "msm_drv.h" +#include "msm_mmu.h" + +struct msm_iommu { + struct msm_mmu base; + struct iommu_domain *domain; + atomic_t pagetables; +}; + +#define to_msm_iommu(x) container_of(x, struct msm_iommu, base) + +struct msm_iommu_pagetable { + struct msm_mmu base; + struct msm_mmu *parent; + struct io_pgtable_ops *pgtbl_ops; + unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ + phys_addr_t ttbr; + u32 asid; +}; +static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu) +{ + return container_of(mmu, struct msm_iommu_pagetable, base); +} + +/* based on iommu_pgsize() in iommu.c: */ +static size_t calc_pgsize(struct msm_iommu_pagetable *pagetable, + unsigned long iova, phys_addr_t paddr, + size_t size, size_t *count) +{ + unsigned int pgsize_idx, pgsize_idx_next; + unsigned long pgsizes; + size_t offset, pgsize, pgsize_next; + unsigned long addr_merge = paddr | iova; + + /* Page sizes supported by the hardware and small enough for @size */ + pgsizes = pagetable->pgsize_bitmap & GENMASK(__fls(size), 0); + + /* Constrain the page sizes further based on the maximum alignment */ + if (likely(addr_merge)) + pgsizes &= GENMASK(__ffs(addr_merge), 0); + + /* Make sure we have at least one suitable page size */ + BUG_ON(!pgsizes); + + /* Pick the biggest page size remaining */ + pgsize_idx = __fls(pgsizes); + pgsize = BIT(pgsize_idx); + if (!count) + return pgsize; + + /* Find the next biggest support page size, if it exists */ + pgsizes = pagetable->pgsize_bitmap & ~GENMASK(pgsize_idx, 0); + if (!pgsizes) + goto out_set_count; + + pgsize_idx_next = __ffs(pgsizes); + pgsize_next = BIT(pgsize_idx_next); + + /* + * There's no point trying a bigger page size unless the virtual + * and physical addresses are similarly offset within the larger page. + */ + if ((iova ^ paddr) & (pgsize_next - 1)) + goto out_set_count; + + /* Calculate the offset to the next page size alignment boundary */ + offset = pgsize_next - (addr_merge & (pgsize_next - 1)); + + /* + * If size is big enough to accommodate the larger page, reduce + * the number of smaller pages. + */ + if (offset + pgsize_next <= size) + size = offset; + +out_set_count: + *count = size >> pgsize_idx; + return pgsize; +} + +static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova, + size_t size) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct io_pgtable_ops *ops = pagetable->pgtbl_ops; + + while (size) { + size_t unmapped, pgsize, count; + + pgsize = calc_pgsize(pagetable, iova, iova, size, &count); + + unmapped = ops->unmap_pages(ops, iova, pgsize, count, NULL); + if (!unmapped) + break; + + iova += unmapped; + size -= unmapped; + } + + iommu_flush_iotlb_all(to_msm_iommu(pagetable->parent)->domain); + + return (size == 0) ? 0 : -EINVAL; +} + +static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova, + struct sg_table *sgt, size_t len, int prot) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct io_pgtable_ops *ops = pagetable->pgtbl_ops; + struct scatterlist *sg; + u64 addr = iova; + unsigned int i; + + for_each_sgtable_sg(sgt, sg, i) { + size_t size = sg->length; + phys_addr_t phys = sg_phys(sg); + + while (size) { + size_t pgsize, count, mapped = 0; + int ret; + + pgsize = calc_pgsize(pagetable, addr, phys, size, &count); + + ret = ops->map_pages(ops, addr, phys, pgsize, count, + prot, GFP_KERNEL, &mapped); + + /* map_pages could fail after mapping some of the pages, + * so update the counters before error handling. + */ + phys += mapped; + addr += mapped; + size -= mapped; + + if (ret) { + msm_iommu_pagetable_unmap(mmu, iova, addr - iova); + return -EINVAL; + } + } + } + + return 0; +} + +static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct msm_iommu *iommu = to_msm_iommu(pagetable->parent); + struct adreno_smmu_priv *adreno_smmu = + dev_get_drvdata(pagetable->parent->dev); + + /* + * If this is the last attached pagetable for the parent, + * disable TTBR0 in the arm-smmu driver + */ + if (atomic_dec_return(&iommu->pagetables) == 0) + adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); + + free_io_pgtable_ops(pagetable->pgtbl_ops); + kfree(pagetable); +} + +int msm_iommu_pagetable_params(struct msm_mmu *mmu, + phys_addr_t *ttbr, int *asid) +{ + struct msm_iommu_pagetable *pagetable; + + if (mmu->type != MSM_MMU_IOMMU_PAGETABLE) + return -EINVAL; + + pagetable = to_pagetable(mmu); + + if (ttbr) + *ttbr = pagetable->ttbr; + + if (asid) + *asid = pagetable->asid; + + return 0; +} + +struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + + return &iommu->domain->geometry; +} + +static const struct msm_mmu_funcs pagetable_funcs = { + .map = msm_iommu_pagetable_map, + .unmap = msm_iommu_pagetable_unmap, + .destroy = msm_iommu_pagetable_destroy, +}; + +static void msm_iommu_tlb_flush_all(void *cookie) +{ +} + +static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ +} + +static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) +{ +} + +static const struct iommu_flush_ops null_tlb_ops = { + .tlb_flush_all = msm_iommu_tlb_flush_all, + .tlb_flush_walk = msm_iommu_tlb_flush_walk, + .tlb_add_page = msm_iommu_tlb_add_page, +}; + +static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg); + +struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev); + struct msm_iommu *iommu = to_msm_iommu(parent); + struct msm_iommu_pagetable *pagetable; + const struct io_pgtable_cfg *ttbr1_cfg = NULL; + struct io_pgtable_cfg ttbr0_cfg; + int ret; + + /* Get the pagetable configuration from the domain */ + if (adreno_smmu->cookie) + ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); + if (!ttbr1_cfg) + return ERR_PTR(-ENODEV); + + /* + * Defer setting the fault handler until we have a valid adreno_smmu + * to avoid accidentially installing a GPU specific fault handler for + * the display's iommu + */ + iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + + pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); + if (!pagetable) + return ERR_PTR(-ENOMEM); + + msm_mmu_init(&pagetable->base, parent->dev, &pagetable_funcs, + MSM_MMU_IOMMU_PAGETABLE); + + /* Clone the TTBR1 cfg as starting point for TTBR0 cfg: */ + ttbr0_cfg = *ttbr1_cfg; + + /* The incoming cfg will have the TTBR1 quirk enabled */ + ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; + ttbr0_cfg.tlb = &null_tlb_ops; + + pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, + &ttbr0_cfg, iommu->domain); + + if (!pagetable->pgtbl_ops) { + kfree(pagetable); + return ERR_PTR(-ENOMEM); + } + + /* + * If this is the first pagetable that we've allocated, send it back to + * the arm-smmu driver as a trigger to set up TTBR0 + */ + if (atomic_inc_return(&iommu->pagetables) == 1) { + /* Enable stall on iommu fault: */ + adreno_smmu->set_stall(adreno_smmu->cookie, true); + + ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); + if (ret) { + free_io_pgtable_ops(pagetable->pgtbl_ops); + kfree(pagetable); + return ERR_PTR(ret); + } + } + + /* Needed later for TLB flush */ + pagetable->parent = parent; + pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; + pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; + + /* + * TODO we would like each set of page tables to have a unique ASID + * to optimize TLB invalidation. But iommu_flush_iotlb_all() will + * end up flushing the ASID used for TTBR1 pagetables, which is not + * what we want. So for now just use the same ASID as TTBR1. + */ + pagetable->asid = 0; + + return &pagetable->base; +} + +static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg) +{ + struct msm_iommu *iommu = arg; + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev); + struct adreno_smmu_fault_info info, *ptr = NULL; + + if (adreno_smmu->get_fault_info) { + adreno_smmu->get_fault_info(adreno_smmu->cookie, &info); + ptr = &info; + } + + if (iommu->base.handler) + return iommu->base.handler(iommu->base.arg, iova, flags, ptr); + + pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags); + return 0; +} + +static void msm_iommu_resume_translation(struct msm_mmu *mmu) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev); + + adreno_smmu->resume_translation(adreno_smmu->cookie, true); +} + +static void msm_iommu_detach(struct msm_mmu *mmu) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + + iommu_detach_device(iommu->domain, mmu->dev); +} + +static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, + struct sg_table *sgt, size_t len, int prot) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + size_t ret; + + /* The arm-smmu driver expects the addresses to be sign extended */ + if (iova & BIT_ULL(48)) + iova |= GENMASK_ULL(63, 49); + + ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot); + WARN_ON(!ret); + + return (ret == len) ? 0 : -EINVAL; +} + +static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + + if (iova & BIT_ULL(48)) + iova |= GENMASK_ULL(63, 49); + + iommu_unmap(iommu->domain, iova, len); + + return 0; +} + +static void msm_iommu_destroy(struct msm_mmu *mmu) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + iommu_domain_free(iommu->domain); + kfree(iommu); +} + +static const struct msm_mmu_funcs funcs = { + .detach = msm_iommu_detach, + .map = msm_iommu_map, + .unmap = msm_iommu_unmap, + .destroy = msm_iommu_destroy, + .resume_translation = msm_iommu_resume_translation, +}; + +struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) +{ + struct iommu_domain *domain; + struct msm_iommu *iommu; + int ret; + + domain = iommu_domain_alloc(dev->bus); + if (!domain) + return NULL; + + iommu_set_pgtable_quirks(domain, quirks); + + iommu = kzalloc(sizeof(*iommu), GFP_KERNEL); + if (!iommu) { + iommu_domain_free(domain); + return ERR_PTR(-ENOMEM); + } + + iommu->domain = domain; + msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); + + atomic_set(&iommu->pagetables, 0); + + ret = iommu_attach_device(iommu->domain, dev); + if (ret) { + iommu_domain_free(domain); + kfree(iommu); + return ERR_PTR(ret); + } + + return &iommu->base; +} -- cgit v1.2.3