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(). ... --- arch/um/os-Linux/umid.c | 408 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 408 insertions(+) create mode 100644 arch/um/os-Linux/umid.c (limited to 'arch/um/os-Linux/umid.c') diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c new file mode 100644 index 000000000..7a1abb829 --- /dev/null +++ b/arch/um/os-Linux/umid.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define UML_DIR "~/.uml/" + +#define UMID_LEN 64 + +/* Changed by set_umid, which is run early in boot */ +static char umid[UMID_LEN] = { 0 }; + +/* Changed by set_uml_dir and make_uml_dir, which are run early in boot */ +static char *uml_dir = UML_DIR; + +static int __init make_uml_dir(void) +{ + char dir[512] = { '\0' }; + int len, err; + + if (*uml_dir == '~') { + char *home = getenv("HOME"); + + err = -ENOENT; + if (home == NULL) { + printk(UM_KERN_ERR + "%s: no value in environment for $HOME\n", + __func__); + goto err; + } + strlcpy(dir, home, sizeof(dir)); + uml_dir++; + } + strlcat(dir, uml_dir, sizeof(dir)); + len = strlen(dir); + if (len > 0 && dir[len - 1] != '/') + strlcat(dir, "/", sizeof(dir)); + + err = -ENOMEM; + uml_dir = malloc(strlen(dir) + 1); + if (uml_dir == NULL) { + printk(UM_KERN_ERR "%s : malloc failed, errno = %d\n", + __func__, errno); + goto err; + } + strcpy(uml_dir, dir); + + if ((mkdir(uml_dir, 0777) < 0) && (errno != EEXIST)) { + printk(UM_KERN_ERR "Failed to mkdir '%s': %s\n", + uml_dir, strerror(errno)); + err = -errno; + goto err_free; + } + return 0; + +err_free: + free(uml_dir); +err: + uml_dir = NULL; + return err; +} + +/* + * Unlinks the files contained in @dir and then removes @dir. + * Doesn't handle directory trees, so it's not like rm -rf, but almost such. We + * ignore ENOENT errors for anything (they happen, strangely enough - possibly + * due to races between multiple dying UML threads). + */ +static int remove_files_and_dir(char *dir) +{ + DIR *directory; + struct dirent *ent; + int len; + char file[256]; + int ret; + + directory = opendir(dir); + if (directory == NULL) { + if (errno != ENOENT) + return -errno; + else + return 0; + } + + while ((ent = readdir(directory)) != NULL) { + if (!strcmp(ent->d_name, ".") || !strcmp(ent->d_name, "..")) + continue; + len = strlen(dir) + strlen("/") + strlen(ent->d_name) + 1; + if (len > sizeof(file)) { + ret = -E2BIG; + goto out; + } + + sprintf(file, "%s/%s", dir, ent->d_name); + if (unlink(file) < 0 && errno != ENOENT) { + ret = -errno; + goto out; + } + } + + if (rmdir(dir) < 0 && errno != ENOENT) { + ret = -errno; + goto out; + } + + ret = 0; +out: + closedir(directory); + return ret; +} + +/* + * This says that there isn't already a user of the specified directory even if + * there are errors during the checking. This is because if these errors + * happen, the directory is unusable by the pre-existing UML, so we might as + * well take it over. This could happen either by + * the existing UML somehow corrupting its umid directory + * something other than UML sticking stuff in the directory + * this boot racing with a shutdown of the other UML + * In any of these cases, the directory isn't useful for anything else. + * + * Boolean return: 1 if in use, 0 otherwise. + */ +static inline int is_umdir_used(char *dir) +{ + char pid[sizeof("nnnnnnnnn")], *end, *file; + int fd, p, n, err; + size_t filelen = strlen(dir) + sizeof("/pid") + 1; + + file = malloc(filelen); + if (!file) + return -ENOMEM; + + snprintf(file, filelen, "%s/pid", dir); + + fd = open(file, O_RDONLY); + if (fd < 0) { + fd = -errno; + if (fd != -ENOENT) { + printk(UM_KERN_ERR "is_umdir_used : couldn't open pid " + "file '%s', err = %d\n", file, -fd); + } + goto out; + } + + err = 0; + n = read(fd, pid, sizeof(pid)); + if (n < 0) { + printk(UM_KERN_ERR "is_umdir_used : couldn't read pid file " + "'%s', err = %d\n", file, errno); + goto out_close; + } else if (n == 0) { + printk(UM_KERN_ERR "is_umdir_used : couldn't read pid file " + "'%s', 0-byte read\n", file); + goto out_close; + } + + p = strtoul(pid, &end, 0); + if (end == pid) { + printk(UM_KERN_ERR "is_umdir_used : couldn't parse pid file " + "'%s', errno = %d\n", file, errno); + goto out_close; + } + + if ((kill(p, 0) == 0) || (errno != ESRCH)) { + printk(UM_KERN_ERR "umid \"%s\" is already in use by pid %d\n", + umid, p); + return 1; + } + +out_close: + close(fd); +out: + free(file); + return 0; +} + +/* + * Try to remove the directory @dir unless it's in use. + * Precondition: @dir exists. + * Returns 0 for success, < 0 for failure in removal or if the directory is in + * use. + */ +static int umdir_take_if_dead(char *dir) +{ + int ret; + if (is_umdir_used(dir)) + return -EEXIST; + + ret = remove_files_and_dir(dir); + if (ret) { + printk(UM_KERN_ERR "is_umdir_used - remove_files_and_dir " + "failed with err = %d\n", ret); + } + return ret; +} + +static void __init create_pid_file(void) +{ + char pid[sizeof("nnnnnnnnn")], *file; + int fd, n; + + n = strlen(uml_dir) + UMID_LEN + sizeof("/pid"); + file = malloc(n); + if (!file) + return; + + if (umid_file_name("pid", file, n)) + goto out; + + fd = open(file, O_RDWR | O_CREAT | O_EXCL, 0644); + if (fd < 0) { + printk(UM_KERN_ERR "Open of machine pid file \"%s\" failed: " + "%s\n", file, strerror(errno)); + goto out; + } + + snprintf(pid, sizeof(pid), "%d\n", getpid()); + n = write(fd, pid, strlen(pid)); + if (n != strlen(pid)) + printk(UM_KERN_ERR "Write of pid file failed - err = %d\n", + errno); + + close(fd); +out: + free(file); +} + +int __init set_umid(char *name) +{ + if (strlen(name) > UMID_LEN - 1) + return -E2BIG; + + strlcpy(umid, name, sizeof(umid)); + + return 0; +} + +/* Changed in make_umid, which is called during early boot */ +static int umid_setup = 0; + +static int __init make_umid(void) +{ + int fd, err; + char tmp[256]; + + if (umid_setup) + return 0; + + make_uml_dir(); + + if (*umid == '\0') { + strlcpy(tmp, uml_dir, sizeof(tmp)); + strlcat(tmp, "XXXXXX", sizeof(tmp)); + fd = mkstemp(tmp); + if (fd < 0) { + printk(UM_KERN_ERR "make_umid - mkstemp(%s) failed: " + "%s\n", tmp, strerror(errno)); + err = -errno; + goto err; + } + + close(fd); + + set_umid(&tmp[strlen(uml_dir)]); + + /* + * There's a nice tiny little race between this unlink and + * the mkdir below. It'd be nice if there were a mkstemp + * for directories. + */ + if (unlink(tmp)) { + err = -errno; + goto err; + } + } + + snprintf(tmp, sizeof(tmp), "%s%s", uml_dir, umid); + err = mkdir(tmp, 0777); + if (err < 0) { + err = -errno; + if (err != -EEXIST) + goto err; + + if (umdir_take_if_dead(tmp) < 0) + goto err; + + err = mkdir(tmp, 0777); + } + if (err) { + err = -errno; + printk(UM_KERN_ERR "Failed to create '%s' - err = %d\n", umid, + errno); + goto err; + } + + umid_setup = 1; + + create_pid_file(); + + err = 0; + err: + return err; +} + +static int __init make_umid_init(void) +{ + if (!make_umid()) + return 0; + + /* + * If initializing with the given umid failed, then try again with + * a random one. + */ + printk(UM_KERN_ERR "Failed to initialize umid \"%s\", trying with a " + "random umid\n", umid); + *umid = '\0'; + make_umid(); + + return 0; +} + +__initcall(make_umid_init); + +int __init umid_file_name(char *name, char *buf, int len) +{ + int n, err; + + err = make_umid(); + if (err) + return err; + + n = snprintf(buf, len, "%s%s/%s", uml_dir, umid, name); + if (n >= len) { + printk(UM_KERN_ERR "umid_file_name : buffer too short\n"); + return -E2BIG; + } + + return 0; +} + +char *get_umid(void) +{ + return umid; +} + +static int __init set_uml_dir(char *name, int *add) +{ + if (*name == '\0') { + os_warn("uml_dir can't be an empty string\n"); + return 0; + } + + if (name[strlen(name) - 1] == '/') { + uml_dir = name; + return 0; + } + + uml_dir = malloc(strlen(name) + 2); + if (uml_dir == NULL) { + os_warn("Failed to malloc uml_dir - error = %d\n", errno); + + /* + * Return 0 here because do_initcalls doesn't look at + * the return value. + */ + return 0; + } + sprintf(uml_dir, "%s/", name); + + return 0; +} + +__uml_setup("uml_dir=", set_uml_dir, +"uml_dir=\n" +" The location to place the pid and umid files.\n\n" +); + +static void remove_umid_dir(void) +{ + char *dir, err; + + dir = malloc(strlen(uml_dir) + UMID_LEN + 1); + if (!dir) + return; + + sprintf(dir, "%s%s", uml_dir, umid); + err = remove_files_and_dir(dir); + if (err) + os_warn("%s - remove_files_and_dir failed with err = %d\n", + __func__, err); + + free(dir); +} + +__uml_exitcall(remove_umid_dir); -- cgit v1.2.3