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/iommu/sprd-iommu.c | 555 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 555 insertions(+) create mode 100644 drivers/iommu/sprd-iommu.c (limited to 'drivers/iommu/sprd-iommu.c') diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c new file mode 100644 index 000000000..219bfa11f --- /dev/null +++ b/drivers/iommu/sprd-iommu.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Unisoc IOMMU driver + * + * Copyright (C) 2020 Unisoc, Inc. + * Author: Chunyan Zhang + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SPRD_IOMMU_PAGE_SHIFT 12 +#define SPRD_IOMMU_PAGE_SIZE SZ_4K + +#define SPRD_EX_CFG 0x0 +#define SPRD_IOMMU_VAOR_BYPASS BIT(4) +#define SPRD_IOMMU_GATE_EN BIT(1) +#define SPRD_IOMMU_EN BIT(0) +#define SPRD_EX_UPDATE 0x4 +#define SPRD_EX_FIRST_VPN 0x8 +#define SPRD_EX_VPN_RANGE 0xc +#define SPRD_EX_FIRST_PPN 0x10 +#define SPRD_EX_DEFAULT_PPN 0x14 + +#define SPRD_IOMMU_VERSION 0x0 +#define SPRD_VERSION_MASK GENMASK(15, 8) +#define SPRD_VERSION_SHIFT 0x8 +#define SPRD_VAU_CFG 0x4 +#define SPRD_VAU_UPDATE 0x8 +#define SPRD_VAU_AUTH_CFG 0xc +#define SPRD_VAU_FIRST_PPN 0x10 +#define SPRD_VAU_DEFAULT_PPN_RD 0x14 +#define SPRD_VAU_DEFAULT_PPN_WR 0x18 +#define SPRD_VAU_FIRST_VPN 0x1c +#define SPRD_VAU_VPN_RANGE 0x20 + +enum sprd_iommu_version { + SPRD_IOMMU_EX, + SPRD_IOMMU_VAU, +}; + +/* + * struct sprd_iommu_device - high-level sprd IOMMU device representation, + * including hardware information and configuration, also driver data, etc + * + * @ver: sprd IOMMU IP version + * @prot_page_va: protect page base virtual address + * @prot_page_pa: protect page base physical address, data would be + * written to here while translation fault + * @base: mapped base address for accessing registers + * @dev: pointer to basic device structure + * @iommu: IOMMU core representation + * @group: IOMMU group + * @eb: gate clock which controls IOMMU access + */ +struct sprd_iommu_device { + enum sprd_iommu_version ver; + u32 *prot_page_va; + dma_addr_t prot_page_pa; + void __iomem *base; + struct device *dev; + struct iommu_device iommu; + struct iommu_group *group; + struct clk *eb; +}; + +struct sprd_iommu_domain { + spinlock_t pgtlock; /* lock for page table */ + struct iommu_domain domain; + u32 *pgt_va; /* page table virtual address base */ + dma_addr_t pgt_pa; /* page table physical address base */ + struct sprd_iommu_device *sdev; +}; + +static const struct iommu_ops sprd_iommu_ops; + +static struct sprd_iommu_domain *to_sprd_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct sprd_iommu_domain, domain); +} + +static inline void +sprd_iommu_write(struct sprd_iommu_device *sdev, unsigned int reg, u32 val) +{ + writel_relaxed(val, sdev->base + reg); +} + +static inline u32 +sprd_iommu_read(struct sprd_iommu_device *sdev, unsigned int reg) +{ + return readl_relaxed(sdev->base + reg); +} + +static inline void +sprd_iommu_update_bits(struct sprd_iommu_device *sdev, unsigned int reg, + u32 mask, u32 shift, u32 val) +{ + u32 t = sprd_iommu_read(sdev, reg); + + t = (t & (~(mask << shift))) | ((val & mask) << shift); + sprd_iommu_write(sdev, reg, t); +} + +static inline int +sprd_iommu_get_version(struct sprd_iommu_device *sdev) +{ + int ver = (sprd_iommu_read(sdev, SPRD_IOMMU_VERSION) & + SPRD_VERSION_MASK) >> SPRD_VERSION_SHIFT; + + switch (ver) { + case SPRD_IOMMU_EX: + case SPRD_IOMMU_VAU: + return ver; + default: + return -EINVAL; + } +} + +static size_t +sprd_iommu_pgt_size(struct iommu_domain *domain) +{ + return ((domain->geometry.aperture_end - + domain->geometry.aperture_start + 1) >> + SPRD_IOMMU_PAGE_SHIFT) * sizeof(u32); +} + +static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) +{ + struct sprd_iommu_domain *dom; + + if (domain_type != IOMMU_DOMAIN_DMA && domain_type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + dom = kzalloc(sizeof(*dom), GFP_KERNEL); + if (!dom) + return NULL; + + spin_lock_init(&dom->pgtlock); + + dom->domain.geometry.aperture_start = 0; + dom->domain.geometry.aperture_end = SZ_256M - 1; + + return &dom->domain; +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + kfree(dom); +} + +static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) +{ + struct sprd_iommu_device *sdev = dom->sdev; + u32 val; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_FIRST_VPN; + else + reg = SPRD_VAU_FIRST_VPN; + + val = dom->domain.geometry.aperture_start >> SPRD_IOMMU_PAGE_SHIFT; + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_vpn_range(struct sprd_iommu_domain *dom) +{ + struct sprd_iommu_device *sdev = dom->sdev; + u32 val; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_VPN_RANGE; + else + reg = SPRD_VAU_VPN_RANGE; + + val = (dom->domain.geometry.aperture_end - + dom->domain.geometry.aperture_start) >> SPRD_IOMMU_PAGE_SHIFT; + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_first_ppn(struct sprd_iommu_domain *dom) +{ + u32 val = dom->pgt_pa >> SPRD_IOMMU_PAGE_SHIFT; + struct sprd_iommu_device *sdev = dom->sdev; + unsigned int reg; + + if (sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_FIRST_PPN; + else + reg = SPRD_VAU_FIRST_PPN; + + sprd_iommu_write(sdev, reg, val); +} + +static void sprd_iommu_default_ppn(struct sprd_iommu_device *sdev) +{ + u32 val = sdev->prot_page_pa >> SPRD_IOMMU_PAGE_SHIFT; + + if (sdev->ver == SPRD_IOMMU_EX) { + sprd_iommu_write(sdev, SPRD_EX_DEFAULT_PPN, val); + } else if (sdev->ver == SPRD_IOMMU_VAU) { + sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_RD, val); + sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_WR, val); + } +} + +static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) +{ + unsigned int reg_cfg; + u32 mask, val; + + if (sdev->ver == SPRD_IOMMU_EX) + reg_cfg = SPRD_EX_CFG; + else + reg_cfg = SPRD_VAU_CFG; + + mask = SPRD_IOMMU_EN | SPRD_IOMMU_GATE_EN; + val = en ? mask : 0; + sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); +} + +static int sprd_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev); + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + size_t pgt_size = sprd_iommu_pgt_size(domain); + + if (dom->sdev) + return -EINVAL; + + dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); + if (!dom->pgt_va) + return -ENOMEM; + + dom->sdev = sdev; + + sprd_iommu_first_ppn(dom); + sprd_iommu_first_vpn(dom); + sprd_iommu_vpn_range(dom); + sprd_iommu_default_ppn(sdev); + sprd_iommu_hw_en(sdev, true); + + return 0; +} + +static void sprd_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + struct sprd_iommu_device *sdev = dom->sdev; + size_t pgt_size = sprd_iommu_pgt_size(domain); + + if (!sdev) + return; + + dma_free_coherent(sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + sprd_iommu_hw_en(sdev, false); + dom->sdev = NULL; +} + +static int sprd_iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + size_t size = pgcount * SPRD_IOMMU_PAGE_SIZE; + unsigned long flags; + unsigned int i; + u32 *pgt_base_iova; + u32 pabase = (u32)paddr; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (!dom->sdev) { + pr_err("No sprd_iommu_device attached to the domain\n"); + return -EINVAL; + } + + if (iova < start || (iova + size) > (end + 1)) { + dev_err(dom->sdev->dev, "(iova(0x%lx) + size(%zx)) are not in the range!\n", + iova, size); + return -EINVAL; + } + + pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT); + + spin_lock_irqsave(&dom->pgtlock, flags); + for (i = 0; i < pgcount; i++) { + pgt_base_iova[i] = pabase >> SPRD_IOMMU_PAGE_SHIFT; + pabase += SPRD_IOMMU_PAGE_SIZE; + } + spin_unlock_irqrestore(&dom->pgtlock, flags); + + *mapped = size; + return 0; +} + +static size_t sprd_iommu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned long flags; + u32 *pgt_base_iova; + size_t size = pgcount * SPRD_IOMMU_PAGE_SIZE; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (iova < start || (iova + size) > (end + 1)) + return 0; + + pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT); + + spin_lock_irqsave(&dom->pgtlock, flags); + memset(pgt_base_iova, 0, pgcount * sizeof(u32)); + spin_unlock_irqrestore(&dom->pgtlock, flags); + + return size; +} + +static void sprd_iommu_sync_map(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned int reg; + + if (dom->sdev->ver == SPRD_IOMMU_EX) + reg = SPRD_EX_UPDATE; + else + reg = SPRD_VAU_UPDATE; + + /* clear IOMMU TLB buffer after page table updated */ + sprd_iommu_write(dom->sdev, reg, 0xffffffff); +} + +static void sprd_iommu_sync(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather) +{ + sprd_iommu_sync_map(domain, 0, 0); +} + +static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + unsigned long flags; + phys_addr_t pa; + unsigned long start = domain->geometry.aperture_start; + unsigned long end = domain->geometry.aperture_end; + + if (WARN_ON(iova < start || iova > end)) + return 0; + + spin_lock_irqsave(&dom->pgtlock, flags); + pa = *(dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT)); + pa = (pa << SPRD_IOMMU_PAGE_SHIFT) + ((iova - start) & (SPRD_IOMMU_PAGE_SIZE - 1)); + spin_unlock_irqrestore(&dom->pgtlock, flags); + + return pa; +} + +static struct iommu_device *sprd_iommu_probe_device(struct device *dev) +{ + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct sprd_iommu_device *sdev; + + if (!fwspec || fwspec->ops != &sprd_iommu_ops) + return ERR_PTR(-ENODEV); + + sdev = dev_iommu_priv_get(dev); + + return &sdev->iommu; +} + +static struct iommu_group *sprd_iommu_device_group(struct device *dev) +{ + struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev); + + return iommu_group_ref_get(sdev->group); +} + +static int sprd_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) +{ + struct platform_device *pdev; + + if (!dev_iommu_priv_get(dev)) { + pdev = of_find_device_by_node(args->np); + dev_iommu_priv_set(dev, platform_get_drvdata(pdev)); + platform_device_put(pdev); + } + + return 0; +} + + +static const struct iommu_ops sprd_iommu_ops = { + .domain_alloc = sprd_iommu_domain_alloc, + .probe_device = sprd_iommu_probe_device, + .device_group = sprd_iommu_device_group, + .of_xlate = sprd_iommu_of_xlate, + .pgsize_bitmap = SPRD_IOMMU_PAGE_SIZE, + .owner = THIS_MODULE, + .default_domain_ops = &(const struct iommu_domain_ops) { + .attach_dev = sprd_iommu_attach_device, + .detach_dev = sprd_iommu_detach_device, + .map_pages = sprd_iommu_map, + .unmap_pages = sprd_iommu_unmap, + .iotlb_sync_map = sprd_iommu_sync_map, + .iotlb_sync = sprd_iommu_sync, + .iova_to_phys = sprd_iommu_iova_to_phys, + .free = sprd_iommu_domain_free, + } +}; + +static const struct of_device_id sprd_iommu_of_match[] = { + { .compatible = "sprd,iommu-v1" }, + { }, +}; +MODULE_DEVICE_TABLE(of, sprd_iommu_of_match); + +/* + * Clock is not required, access to some of IOMMUs is controlled by gate + * clk, enabled clocks for that kind of IOMMUs before accessing. + * Return 0 for success or no clocks found. + */ +static int sprd_iommu_clk_enable(struct sprd_iommu_device *sdev) +{ + struct clk *eb; + + eb = devm_clk_get_optional(sdev->dev, NULL); + if (!eb) + return 0; + + if (IS_ERR(eb)) + return PTR_ERR(eb); + + sdev->eb = eb; + return clk_prepare_enable(eb); +} + +static void sprd_iommu_clk_disable(struct sprd_iommu_device *sdev) +{ + if (sdev->eb) + clk_disable_unprepare(sdev->eb); +} + +static int sprd_iommu_probe(struct platform_device *pdev) +{ + struct sprd_iommu_device *sdev; + struct device *dev = &pdev->dev; + void __iomem *base; + int ret; + + sdev = devm_kzalloc(dev, sizeof(*sdev), GFP_KERNEL); + if (!sdev) + return -ENOMEM; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) { + dev_err(dev, "Failed to get ioremap resource.\n"); + return PTR_ERR(base); + } + sdev->base = base; + + sdev->prot_page_va = dma_alloc_coherent(dev, SPRD_IOMMU_PAGE_SIZE, + &sdev->prot_page_pa, GFP_KERNEL); + if (!sdev->prot_page_va) + return -ENOMEM; + + platform_set_drvdata(pdev, sdev); + sdev->dev = dev; + + /* All the client devices are in the same iommu-group */ + sdev->group = iommu_group_alloc(); + if (IS_ERR(sdev->group)) { + ret = PTR_ERR(sdev->group); + goto free_page; + } + + ret = iommu_device_sysfs_add(&sdev->iommu, dev, NULL, dev_name(dev)); + if (ret) + goto put_group; + + ret = iommu_device_register(&sdev->iommu, &sprd_iommu_ops, dev); + if (ret) + goto remove_sysfs; + + ret = sprd_iommu_clk_enable(sdev); + if (ret) + goto unregister_iommu; + + ret = sprd_iommu_get_version(sdev); + if (ret < 0) { + dev_err(dev, "IOMMU version(%d) is invalid.\n", ret); + goto disable_clk; + } + sdev->ver = ret; + + return 0; + +disable_clk: + sprd_iommu_clk_disable(sdev); +unregister_iommu: + iommu_device_unregister(&sdev->iommu); +remove_sysfs: + iommu_device_sysfs_remove(&sdev->iommu); +put_group: + iommu_group_put(sdev->group); +free_page: + dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa); + return ret; +} + +static int sprd_iommu_remove(struct platform_device *pdev) +{ + struct sprd_iommu_device *sdev = platform_get_drvdata(pdev); + + dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa); + + iommu_group_put(sdev->group); + sdev->group = NULL; + + platform_set_drvdata(pdev, NULL); + iommu_device_sysfs_remove(&sdev->iommu); + iommu_device_unregister(&sdev->iommu); + + return 0; +} + +static struct platform_driver sprd_iommu_driver = { + .driver = { + .name = "sprd-iommu", + .of_match_table = sprd_iommu_of_match, + .suppress_bind_attrs = true, + }, + .probe = sprd_iommu_probe, + .remove = sprd_iommu_remove, +}; +module_platform_driver(sprd_iommu_driver); + +MODULE_DESCRIPTION("IOMMU driver for Unisoc SoCs"); +MODULE_ALIAS("platform:sprd-iommu"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3