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/dma-buf/dma-heap.c | 326 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 326 insertions(+) create mode 100644 drivers/dma-buf/dma-heap.c (limited to 'drivers/dma-buf/dma-heap.c') diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c new file mode 100644 index 000000000..c9e41e8a9 --- /dev/null +++ b/drivers/dma-buf/dma-heap.c @@ -0,0 +1,326 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Framework for userspace DMA-BUF allocations + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DEVNAME "dma_heap" + +#define NUM_HEAP_MINORS 128 + +/** + * struct dma_heap - represents a dmabuf heap in the system + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @heap_devt heap device node + * @list list head connecting to list of heaps + * @heap_cdev heap char device + * + * Represents a heap of memory from which buffers can be made. + */ +struct dma_heap { + const char *name; + const struct dma_heap_ops *ops; + void *priv; + dev_t heap_devt; + struct list_head list; + struct cdev heap_cdev; +}; + +static LIST_HEAD(heap_list); +static DEFINE_MUTEX(heap_list_lock); +static dev_t dma_heap_devt; +static struct class *dma_heap_class; +static DEFINE_XARRAY_ALLOC(dma_heap_minors); + +static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, + unsigned int fd_flags, + unsigned int heap_flags) +{ + struct dma_buf *dmabuf; + int fd; + + /* + * Allocations from all heaps have to begin + * and end on page boundaries. + */ + len = PAGE_ALIGN(len); + if (!len) + return -EINVAL; + + dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + fd = dma_buf_fd(dmabuf, fd_flags); + if (fd < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + } + return fd; +} + +static int dma_heap_open(struct inode *inode, struct file *file) +{ + struct dma_heap *heap; + + heap = xa_load(&dma_heap_minors, iminor(inode)); + if (!heap) { + pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); + return -ENODEV; + } + + /* instance data as context */ + file->private_data = heap; + nonseekable_open(inode, file); + + return 0; +} + +static long dma_heap_ioctl_allocate(struct file *file, void *data) +{ + struct dma_heap_allocation_data *heap_allocation = data; + struct dma_heap *heap = file->private_data; + int fd; + + if (heap_allocation->fd) + return -EINVAL; + + if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) + return -EINVAL; + + if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) + return -EINVAL; + + fd = dma_heap_buffer_alloc(heap, heap_allocation->len, + heap_allocation->fd_flags, + heap_allocation->heap_flags); + if (fd < 0) + return fd; + + heap_allocation->fd = fd; + + return 0; +} + +static unsigned int dma_heap_ioctl_cmds[] = { + DMA_HEAP_IOCTL_ALLOC, +}; + +static long dma_heap_ioctl(struct file *file, unsigned int ucmd, + unsigned long arg) +{ + char stack_kdata[128]; + char *kdata = stack_kdata; + unsigned int kcmd; + unsigned int in_size, out_size, drv_size, ksize; + int nr = _IOC_NR(ucmd); + int ret = 0; + + if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) + return -EINVAL; + + nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); + /* Get the kernel ioctl cmd that matches */ + kcmd = dma_heap_ioctl_cmds[nr]; + + /* Figure out the delta between user cmd size and kernel cmd size */ + drv_size = _IOC_SIZE(kcmd); + out_size = _IOC_SIZE(ucmd); + in_size = out_size; + if ((ucmd & kcmd & IOC_IN) == 0) + in_size = 0; + if ((ucmd & kcmd & IOC_OUT) == 0) + out_size = 0; + ksize = max(max(in_size, out_size), drv_size); + + /* If necessary, allocate buffer for ioctl argument */ + if (ksize > sizeof(stack_kdata)) { + kdata = kmalloc(ksize, GFP_KERNEL); + if (!kdata) + return -ENOMEM; + } + + if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { + ret = -EFAULT; + goto err; + } + + /* zero out any difference between the kernel/user structure size */ + if (ksize > in_size) + memset(kdata + in_size, 0, ksize - in_size); + + switch (kcmd) { + case DMA_HEAP_IOCTL_ALLOC: + ret = dma_heap_ioctl_allocate(file, kdata); + break; + default: + ret = -ENOTTY; + goto err; + } + + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) + ret = -EFAULT; +err: + if (kdata != stack_kdata) + kfree(kdata); + return ret; +} + +static const struct file_operations dma_heap_fops = { + .owner = THIS_MODULE, + .open = dma_heap_open, + .unlocked_ioctl = dma_heap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_heap_ioctl, +#endif +}; + +/** + * dma_heap_get_drvdata() - get per-subdriver data for the heap + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-subdriver data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap) +{ + return heap->priv; +} + +/** + * dma_heap_get_name() - get heap name + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The char* for the heap name. + */ +const char *dma_heap_get_name(struct dma_heap *heap) +{ + return heap->name; +} + +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) +{ + struct dma_heap *heap, *h, *err_ret; + struct device *dev_ret; + unsigned int minor; + int ret; + + if (!exp_info->name || !strcmp(exp_info->name, "")) { + pr_err("dma_heap: Cannot add heap without a name\n"); + return ERR_PTR(-EINVAL); + } + + if (!exp_info->ops || !exp_info->ops->allocate) { + pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); + return ERR_PTR(-EINVAL); + } + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return ERR_PTR(-ENOMEM); + + heap->name = exp_info->name; + heap->ops = exp_info->ops; + heap->priv = exp_info->priv; + + /* Find unused minor number */ + ret = xa_alloc(&dma_heap_minors, &minor, heap, + XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); + if (ret < 0) { + pr_err("dma_heap: Unable to get minor number for heap\n"); + err_ret = ERR_PTR(ret); + goto err0; + } + + /* Create device */ + heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); + + cdev_init(&heap->heap_cdev, &dma_heap_fops); + ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); + if (ret < 0) { + pr_err("dma_heap: Unable to add char device\n"); + err_ret = ERR_PTR(ret); + goto err1; + } + + dev_ret = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(dev_ret)) { + pr_err("dma_heap: Unable to create device\n"); + err_ret = ERR_CAST(dev_ret); + goto err2; + } + + mutex_lock(&heap_list_lock); + /* check the name is unique */ + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + err_ret = ERR_PTR(-EINVAL); + goto err3; + } + } + + /* Add heap to the list */ + list_add(&heap->list, &heap_list); + mutex_unlock(&heap_list_lock); + + return heap; + +err3: + device_destroy(dma_heap_class, heap->heap_devt); +err2: + cdev_del(&heap->heap_cdev); +err1: + xa_erase(&dma_heap_minors, minor); +err0: + kfree(heap); + return err_ret; +} + +static char *dma_heap_devnode(const struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); +} + +static int dma_heap_init(void) +{ + int ret; + + ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); + if (ret) + return ret; + + dma_heap_class = class_create(THIS_MODULE, DEVNAME); + if (IS_ERR(dma_heap_class)) { + unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); + return PTR_ERR(dma_heap_class); + } + dma_heap_class->devnode = dma_heap_devnode; + + return 0; +} +subsys_initcall(dma_heap_init); -- cgit v1.2.3