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/infiniband/core/umem.c | 317 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 317 insertions(+) create mode 100644 drivers/infiniband/core/umem.c (limited to 'drivers/infiniband/core/umem.c') diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c new file mode 100644 index 000000000..755a9c57d --- /dev/null +++ b/drivers/infiniband/core/umem.c @@ -0,0 +1,317 @@ +/* + * Copyright (c) 2005 Topspin Communications. All rights reserved. + * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005 Mellanox Technologies. All rights reserved. + * Copyright (c) 2020 Intel Corporation. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "uverbs.h" + +static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty) +{ + bool make_dirty = umem->writable && dirty; + struct scatterlist *sg; + unsigned int i; + + if (dirty) + ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt, + DMA_BIDIRECTIONAL, 0); + + for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) + unpin_user_page_range_dirty_lock(sg_page(sg), + DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty); + + sg_free_append_table(&umem->sgt_append); +} + +/** + * ib_umem_find_best_pgsz - Find best HW page size to use for this MR + * + * @umem: umem struct + * @pgsz_bitmap: bitmap of HW supported page sizes + * @virt: IOVA + * + * This helper is intended for HW that support multiple page + * sizes but can do only a single page size in an MR. + * + * Returns 0 if the umem requires page sizes not supported by + * the driver to be mapped. Drivers always supporting PAGE_SIZE + * or smaller will never see a 0 result. + */ +unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, + unsigned long pgsz_bitmap, + unsigned long virt) +{ + struct scatterlist *sg; + unsigned long va, pgoff; + dma_addr_t mask; + int i; + + if (umem->is_odp) { + unsigned int page_size = BIT(to_ib_umem_odp(umem)->page_shift); + + /* ODP must always be self consistent. */ + if (!(pgsz_bitmap & page_size)) + return 0; + return page_size; + } + + /* rdma_for_each_block() has a bug if the page size is smaller than the + * page size used to build the umem. For now prevent smaller page sizes + * from being returned. + */ + pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); + + umem->iova = va = virt; + /* The best result is the smallest page size that results in the minimum + * number of required pages. Compute the largest page size that could + * work based on VA address bits that don't change. + */ + mask = pgsz_bitmap & + GENMASK(BITS_PER_LONG - 1, + bits_per((umem->length - 1 + virt) ^ virt)); + /* offset into first SGL */ + pgoff = umem->address & ~PAGE_MASK; + + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { + /* Walk SGL and reduce max page size if VA/PA bits differ + * for any address. + */ + mask |= (sg_dma_address(sg) + pgoff) ^ va; + va += sg_dma_len(sg) - pgoff; + /* Except for the last entry, the ending iova alignment sets + * the maximum possible page size as the low bits of the iova + * must be zero when starting the next chunk. + */ + if (i != (umem->sgt_append.sgt.nents - 1)) + mask |= va; + pgoff = 0; + } + + /* The mask accumulates 1's in each position where the VA and physical + * address differ, thus the length of trailing 0 is the largest page + * size that can pass the VA through to the physical. + */ + if (mask) + pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0); + return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0; +} +EXPORT_SYMBOL(ib_umem_find_best_pgsz); + +/** + * ib_umem_get - Pin and DMA map userspace memory. + * + * @device: IB device to connect UMEM + * @addr: userspace virtual address to start at + * @size: length of region to pin + * @access: IB_ACCESS_xxx flags for memory being pinned + */ +struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, + size_t size, int access) +{ + struct ib_umem *umem; + struct page **page_list; + unsigned long lock_limit; + unsigned long new_pinned; + unsigned long cur_base; + unsigned long dma_attr = 0; + struct mm_struct *mm; + unsigned long npages; + int pinned, ret; + unsigned int gup_flags = FOLL_LONGTERM; + + /* + * If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if (((addr + size) < addr) || + PAGE_ALIGN(addr + size) < (addr + size)) + return ERR_PTR(-EINVAL); + + if (!can_do_mlock()) + return ERR_PTR(-EPERM); + + if (access & IB_ACCESS_ON_DEMAND) + return ERR_PTR(-EOPNOTSUPP); + + umem = kzalloc(sizeof(*umem), GFP_KERNEL); + if (!umem) + return ERR_PTR(-ENOMEM); + umem->ibdev = device; + umem->length = size; + umem->address = addr; + /* + * Drivers should call ib_umem_find_best_pgsz() to set the iova + * correctly. + */ + umem->iova = addr; + umem->writable = ib_access_writable(access); + umem->owning_mm = mm = current->mm; + mmgrab(mm); + + page_list = (struct page **) __get_free_page(GFP_KERNEL); + if (!page_list) { + ret = -ENOMEM; + goto umem_kfree; + } + + npages = ib_umem_num_pages(umem); + if (npages == 0 || npages > UINT_MAX) { + ret = -EINVAL; + goto out; + } + + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + new_pinned = atomic64_add_return(npages, &mm->pinned_vm); + if (new_pinned > lock_limit && !capable(CAP_IPC_LOCK)) { + atomic64_sub(npages, &mm->pinned_vm); + ret = -ENOMEM; + goto out; + } + + cur_base = addr & PAGE_MASK; + + if (umem->writable) + gup_flags |= FOLL_WRITE; + + while (npages) { + cond_resched(); + pinned = pin_user_pages_fast(cur_base, + min_t(unsigned long, npages, + PAGE_SIZE / + sizeof(struct page *)), + gup_flags, page_list); + if (pinned < 0) { + ret = pinned; + goto umem_release; + } + + cur_base += pinned * PAGE_SIZE; + npages -= pinned; + ret = sg_alloc_append_table_from_pages( + &umem->sgt_append, page_list, pinned, 0, + pinned << PAGE_SHIFT, ib_dma_max_seg_size(device), + npages, GFP_KERNEL); + if (ret) { + unpin_user_pages_dirty_lock(page_list, pinned, 0); + goto umem_release; + } + } + + if (access & IB_ACCESS_RELAXED_ORDERING) + dma_attr |= DMA_ATTR_WEAK_ORDERING; + + ret = ib_dma_map_sgtable_attrs(device, &umem->sgt_append.sgt, + DMA_BIDIRECTIONAL, dma_attr); + if (ret) + goto umem_release; + goto out; + +umem_release: + __ib_umem_release(device, umem, 0); + atomic64_sub(ib_umem_num_pages(umem), &mm->pinned_vm); +out: + free_page((unsigned long) page_list); +umem_kfree: + if (ret) { + mmdrop(umem->owning_mm); + kfree(umem); + } + return ret ? ERR_PTR(ret) : umem; +} +EXPORT_SYMBOL(ib_umem_get); + +/** + * ib_umem_release - release memory pinned with ib_umem_get + * @umem: umem struct to release + */ +void ib_umem_release(struct ib_umem *umem) +{ + if (!umem) + return; + if (umem->is_dmabuf) + return ib_umem_dmabuf_release(to_ib_umem_dmabuf(umem)); + if (umem->is_odp) + return ib_umem_odp_release(to_ib_umem_odp(umem)); + + __ib_umem_release(umem->ibdev, umem, 1); + + atomic64_sub(ib_umem_num_pages(umem), &umem->owning_mm->pinned_vm); + mmdrop(umem->owning_mm); + kfree(umem); +} +EXPORT_SYMBOL(ib_umem_release); + +/* + * Copy from the given ib_umem's pages to the given buffer. + * + * umem - the umem to copy from + * offset - offset to start copying from + * dst - destination buffer + * length - buffer length + * + * Returns 0 on success, or an error code. + */ +int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, + size_t length) +{ + size_t end = offset + length; + int ret; + + if (offset > umem->length || length > umem->length - offset) { + pr_err("%s not in range. offset: %zd umem length: %zd end: %zd\n", + __func__, offset, umem->length, end); + return -EINVAL; + } + + ret = sg_pcopy_to_buffer(umem->sgt_append.sgt.sgl, + umem->sgt_append.sgt.orig_nents, dst, length, + offset + ib_umem_offset(umem)); + + if (ret < 0) + return ret; + else if (ret != length) + return -EINVAL; + else + return 0; +} +EXPORT_SYMBOL(ib_umem_copy_from); -- cgit v1.2.3