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(). ... --- net/rds/info.c | 242 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 242 insertions(+) create mode 100644 net/rds/info.c (limited to 'net/rds/info.c') diff --git a/net/rds/info.c b/net/rds/info.c new file mode 100644 index 000000000..b6b46a821 --- /dev/null +++ b/net/rds/info.c @@ -0,0 +1,242 @@ +/* + * Copyright (c) 2006 Oracle. 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 "rds.h" + +/* + * This file implements a getsockopt() call which copies a set of fixed + * sized structs into a user-specified buffer as a means of providing + * read-only information about RDS. + * + * For a given information source there are a given number of fixed sized + * structs at a given time. The structs are only copied if the user-specified + * buffer is big enough. The destination pages that make up the buffer + * are pinned for the duration of the copy. + * + * This gives us the following benefits: + * + * - simple implementation, no copy "position" across multiple calls + * - consistent snapshot of an info source + * - atomic copy works well with whatever locking info source has + * - one portable tool to get rds info across implementations + * - long-lived tool can get info without allocating + * + * at the following costs: + * + * - info source copy must be pinned, may be "large" + */ + +struct rds_info_iterator { + struct page **pages; + void *addr; + unsigned long offset; +}; + +static DEFINE_SPINLOCK(rds_info_lock); +static rds_info_func rds_info_funcs[RDS_INFO_LAST - RDS_INFO_FIRST + 1]; + +void rds_info_register_func(int optname, rds_info_func func) +{ + int offset = optname - RDS_INFO_FIRST; + + BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST); + + spin_lock(&rds_info_lock); + BUG_ON(rds_info_funcs[offset]); + rds_info_funcs[offset] = func; + spin_unlock(&rds_info_lock); +} +EXPORT_SYMBOL_GPL(rds_info_register_func); + +void rds_info_deregister_func(int optname, rds_info_func func) +{ + int offset = optname - RDS_INFO_FIRST; + + BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST); + + spin_lock(&rds_info_lock); + BUG_ON(rds_info_funcs[offset] != func); + rds_info_funcs[offset] = NULL; + spin_unlock(&rds_info_lock); +} +EXPORT_SYMBOL_GPL(rds_info_deregister_func); + +/* + * Typically we hold an atomic kmap across multiple rds_info_copy() calls + * because the kmap is so expensive. This must be called before using blocking + * operations while holding the mapping and as the iterator is torn down. + */ +void rds_info_iter_unmap(struct rds_info_iterator *iter) +{ + if (iter->addr) { + kunmap_atomic(iter->addr); + iter->addr = NULL; + } +} + +/* + * get_user_pages() called flush_dcache_page() on the pages for us. + */ +void rds_info_copy(struct rds_info_iterator *iter, void *data, + unsigned long bytes) +{ + unsigned long this; + + while (bytes) { + if (!iter->addr) + iter->addr = kmap_atomic(*iter->pages); + + this = min(bytes, PAGE_SIZE - iter->offset); + + rdsdebug("page %p addr %p offset %lu this %lu data %p " + "bytes %lu\n", *iter->pages, iter->addr, + iter->offset, this, data, bytes); + + memcpy(iter->addr + iter->offset, data, this); + + data += this; + bytes -= this; + iter->offset += this; + + if (iter->offset == PAGE_SIZE) { + kunmap_atomic(iter->addr); + iter->addr = NULL; + iter->offset = 0; + iter->pages++; + } + } +} +EXPORT_SYMBOL_GPL(rds_info_copy); + +/* + * @optval points to the userspace buffer that the information snapshot + * will be copied into. + * + * @optlen on input is the size of the buffer in userspace. @optlen + * on output is the size of the requested snapshot in bytes. + * + * This function returns -errno if there is a failure, particularly -ENOSPC + * if the given userspace buffer was not large enough to fit the snapshot. + * On success it returns the positive number of bytes of each array element + * in the snapshot. + */ +int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval, + int __user *optlen) +{ + struct rds_info_iterator iter; + struct rds_info_lengths lens; + unsigned long nr_pages = 0; + unsigned long start; + rds_info_func func; + struct page **pages = NULL; + int ret; + int len; + int total; + + if (get_user(len, optlen)) { + ret = -EFAULT; + goto out; + } + + /* check for all kinds of wrapping and the like */ + start = (unsigned long)optval; + if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) { + ret = -EINVAL; + goto out; + } + + /* a 0 len call is just trying to probe its length */ + if (len == 0) + goto call_func; + + nr_pages = (PAGE_ALIGN(start + len) - (start & PAGE_MASK)) + >> PAGE_SHIFT; + + pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) { + ret = -ENOMEM; + goto out; + } + ret = pin_user_pages_fast(start, nr_pages, FOLL_WRITE, pages); + if (ret != nr_pages) { + if (ret > 0) + nr_pages = ret; + else + nr_pages = 0; + ret = -EAGAIN; /* XXX ? */ + goto out; + } + + rdsdebug("len %d nr_pages %lu\n", len, nr_pages); + +call_func: + func = rds_info_funcs[optname - RDS_INFO_FIRST]; + if (!func) { + ret = -ENOPROTOOPT; + goto out; + } + + iter.pages = pages; + iter.addr = NULL; + iter.offset = start & (PAGE_SIZE - 1); + + func(sock, len, &iter, &lens); + BUG_ON(lens.each == 0); + + total = lens.nr * lens.each; + + rds_info_iter_unmap(&iter); + + if (total > len) { + len = total; + ret = -ENOSPC; + } else { + len = total; + ret = lens.each; + } + + if (put_user(len, optlen)) + ret = -EFAULT; + +out: + if (pages) + unpin_user_pages(pages, nr_pages); + kfree(pages); + + return ret; +} -- cgit v1.2.3