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/drivers/chan_kern.c | 570 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 570 insertions(+) create mode 100644 arch/um/drivers/chan_kern.c (limited to 'arch/um/drivers/chan_kern.c') diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c new file mode 100644 index 000000000..26a702a06 --- /dev/null +++ b/arch/um/drivers/chan_kern.c @@ -0,0 +1,570 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{linux.intel,addtoit}.com) + */ + +#include +#include +#include +#include "chan.h" +#include +#include + +#ifdef CONFIG_NOCONFIG_CHAN +static void *not_configged_init(char *str, int device, + const struct chan_opts *opts) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return NULL; +} + +static int not_configged_open(int input, int output, int primary, void *data, + char **dev_out) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return -ENODEV; +} + +static void not_configged_close(int fd, void *data) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); +} + +static int not_configged_read(int fd, char *c_out, void *data) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return -EIO; +} + +static int not_configged_write(int fd, const char *buf, int len, void *data) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return -EIO; +} + +static int not_configged_console_write(int fd, const char *buf, int len) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return -EIO; +} + +static int not_configged_window_size(int fd, void *data, unsigned short *rows, + unsigned short *cols) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); + return -ENODEV; +} + +static void not_configged_free(void *data) +{ + printk(KERN_ERR "Using a channel type which is configured out of " + "UML\n"); +} + +static const struct chan_ops not_configged_ops = { + .init = not_configged_init, + .open = not_configged_open, + .close = not_configged_close, + .read = not_configged_read, + .write = not_configged_write, + .console_write = not_configged_console_write, + .window_size = not_configged_window_size, + .free = not_configged_free, + .winch = 0, +}; +#endif /* CONFIG_NOCONFIG_CHAN */ + +static int open_one_chan(struct chan *chan) +{ + int fd, err; + + if (chan->opened) + return 0; + + if (chan->ops->open == NULL) + fd = 0; + else fd = (*chan->ops->open)(chan->input, chan->output, chan->primary, + chan->data, &chan->dev); + if (fd < 0) + return fd; + + err = os_set_fd_block(fd, 0); + if (err) { + (*chan->ops->close)(fd, chan->data); + return err; + } + + chan->fd = fd; + + chan->opened = 1; + return 0; +} + +static int open_chan(struct list_head *chans) +{ + struct list_head *ele; + struct chan *chan; + int ret, err = 0; + + list_for_each(ele, chans) { + chan = list_entry(ele, struct chan, list); + ret = open_one_chan(chan); + if (chan->primary) + err = ret; + } + return err; +} + +void chan_enable_winch(struct chan *chan, struct tty_port *port) +{ + if (chan && chan->primary && chan->ops->winch) + register_winch(chan->fd, port); +} + +static void line_timer_cb(struct work_struct *work) +{ + struct line *line = container_of(work, struct line, task.work); + + if (!line->throttled) + chan_interrupt(line, line->read_irq); +} + +int enable_chan(struct line *line) +{ + struct list_head *ele; + struct chan *chan; + int err; + + INIT_DELAYED_WORK(&line->task, line_timer_cb); + + list_for_each(ele, &line->chan_list) { + chan = list_entry(ele, struct chan, list); + err = open_one_chan(chan); + if (err) { + if (chan->primary) + goto out_close; + + continue; + } + + if (chan->enabled) + continue; + err = line_setup_irq(chan->fd, chan->input, chan->output, line, + chan); + if (err) + goto out_close; + + chan->enabled = 1; + } + + return 0; + + out_close: + close_chan(line); + return err; +} + +/* Items are added in IRQ context, when free_irq can't be called, and + * removed in process context, when it can. + * This handles interrupt sources which disappear, and which need to + * be permanently disabled. This is discovered in IRQ context, but + * the freeing of the IRQ must be done later. + */ +static DEFINE_SPINLOCK(irqs_to_free_lock); +static LIST_HEAD(irqs_to_free); + +void free_irqs(void) +{ + struct chan *chan; + LIST_HEAD(list); + struct list_head *ele; + unsigned long flags; + + spin_lock_irqsave(&irqs_to_free_lock, flags); + list_splice_init(&irqs_to_free, &list); + spin_unlock_irqrestore(&irqs_to_free_lock, flags); + + list_for_each(ele, &list) { + chan = list_entry(ele, struct chan, free_list); + + if (chan->input && chan->enabled) + um_free_irq(chan->line->read_irq, chan); + if (chan->output && chan->enabled) + um_free_irq(chan->line->write_irq, chan); + chan->enabled = 0; + } +} + +static void close_one_chan(struct chan *chan, int delay_free_irq) +{ + unsigned long flags; + + if (!chan->opened) + return; + + if (delay_free_irq) { + spin_lock_irqsave(&irqs_to_free_lock, flags); + list_add(&chan->free_list, &irqs_to_free); + spin_unlock_irqrestore(&irqs_to_free_lock, flags); + } else { + if (chan->input && chan->enabled) + um_free_irq(chan->line->read_irq, chan); + if (chan->output && chan->enabled) + um_free_irq(chan->line->write_irq, chan); + chan->enabled = 0; + } + if (chan->ops->close != NULL) + (*chan->ops->close)(chan->fd, chan->data); + + chan->opened = 0; + chan->fd = -1; +} + +void close_chan(struct line *line) +{ + struct chan *chan; + + /* Close in reverse order as open in case more than one of them + * refers to the same device and they save and restore that device's + * state. Then, the first one opened will have the original state, + * so it must be the last closed. + */ + list_for_each_entry_reverse(chan, &line->chan_list, list) { + close_one_chan(chan, 0); + } +} + +void deactivate_chan(struct chan *chan, int irq) +{ + if (chan && chan->enabled) + deactivate_fd(chan->fd, irq); +} + +int write_chan(struct chan *chan, const char *buf, int len, + int write_irq) +{ + int n, ret = 0; + + if (len == 0 || !chan || !chan->ops->write) + return 0; + + n = chan->ops->write(chan->fd, buf, len, chan->data); + if (chan->primary) { + ret = n; + } + return ret; +} + +int console_write_chan(struct chan *chan, const char *buf, int len) +{ + int n, ret = 0; + + if (!chan || !chan->ops->console_write) + return 0; + + n = chan->ops->console_write(chan->fd, buf, len); + if (chan->primary) + ret = n; + return ret; +} + +int console_open_chan(struct line *line, struct console *co) +{ + int err; + + err = open_chan(&line->chan_list); + if (err) + return err; + + printk(KERN_INFO "Console initialized on /dev/%s%d\n", co->name, + co->index); + return 0; +} + +int chan_window_size(struct line *line, unsigned short *rows_out, + unsigned short *cols_out) +{ + struct chan *chan; + + chan = line->chan_in; + if (chan && chan->primary) { + if (chan->ops->window_size == NULL) + return 0; + return chan->ops->window_size(chan->fd, chan->data, + rows_out, cols_out); + } + chan = line->chan_out; + if (chan && chan->primary) { + if (chan->ops->window_size == NULL) + return 0; + return chan->ops->window_size(chan->fd, chan->data, + rows_out, cols_out); + } + return 0; +} + +static void free_one_chan(struct chan *chan) +{ + list_del(&chan->list); + + close_one_chan(chan, 0); + + if (chan->ops->free != NULL) + (*chan->ops->free)(chan->data); + + if (chan->primary && chan->output) + ignore_sigio_fd(chan->fd); + kfree(chan); +} + +static void free_chan(struct list_head *chans) +{ + struct list_head *ele, *next; + struct chan *chan; + + list_for_each_safe(ele, next, chans) { + chan = list_entry(ele, struct chan, list); + free_one_chan(chan); + } +} + +static int one_chan_config_string(struct chan *chan, char *str, int size, + char **error_out) +{ + int n = 0; + + if (chan == NULL) { + CONFIG_CHUNK(str, size, n, "none", 1); + return n; + } + + CONFIG_CHUNK(str, size, n, chan->ops->type, 0); + + if (chan->dev == NULL) { + CONFIG_CHUNK(str, size, n, "", 1); + return n; + } + + CONFIG_CHUNK(str, size, n, ":", 0); + CONFIG_CHUNK(str, size, n, chan->dev, 0); + + return n; +} + +static int chan_pair_config_string(struct chan *in, struct chan *out, + char *str, int size, char **error_out) +{ + int n; + + n = one_chan_config_string(in, str, size, error_out); + str += n; + size -= n; + + if (in == out) { + CONFIG_CHUNK(str, size, n, "", 1); + return n; + } + + CONFIG_CHUNK(str, size, n, ",", 1); + n = one_chan_config_string(out, str, size, error_out); + str += n; + size -= n; + CONFIG_CHUNK(str, size, n, "", 1); + + return n; +} + +int chan_config_string(struct line *line, char *str, int size, + char **error_out) +{ + struct chan *in = line->chan_in, *out = line->chan_out; + + if (in && !in->primary) + in = NULL; + if (out && !out->primary) + out = NULL; + + return chan_pair_config_string(in, out, str, size, error_out); +} + +struct chan_type { + char *key; + const struct chan_ops *ops; +}; + +static const struct chan_type chan_table[] = { + { "fd", &fd_ops }, + +#ifdef CONFIG_NULL_CHAN + { "null", &null_ops }, +#else + { "null", ¬_configged_ops }, +#endif + +#ifdef CONFIG_PORT_CHAN + { "port", &port_ops }, +#else + { "port", ¬_configged_ops }, +#endif + +#ifdef CONFIG_PTY_CHAN + { "pty", &pty_ops }, + { "pts", &pts_ops }, +#else + { "pty", ¬_configged_ops }, + { "pts", ¬_configged_ops }, +#endif + +#ifdef CONFIG_TTY_CHAN + { "tty", &tty_ops }, +#else + { "tty", ¬_configged_ops }, +#endif + +#ifdef CONFIG_XTERM_CHAN + { "xterm", &xterm_ops }, +#else + { "xterm", ¬_configged_ops }, +#endif +}; + +static struct chan *parse_chan(struct line *line, char *str, int device, + const struct chan_opts *opts, char **error_out) +{ + const struct chan_type *entry; + const struct chan_ops *ops; + struct chan *chan; + void *data; + int i; + + ops = NULL; + data = NULL; + for(i = 0; i < ARRAY_SIZE(chan_table); i++) { + entry = &chan_table[i]; + if (!strncmp(str, entry->key, strlen(entry->key))) { + ops = entry->ops; + str += strlen(entry->key); + break; + } + } + if (ops == NULL) { + *error_out = "No match for configured backends"; + return NULL; + } + + data = (*ops->init)(str, device, opts); + if (data == NULL) { + *error_out = "Configuration failed"; + return NULL; + } + + chan = kmalloc(sizeof(*chan), GFP_ATOMIC); + if (chan == NULL) { + *error_out = "Memory allocation failed"; + return NULL; + } + *chan = ((struct chan) { .list = LIST_HEAD_INIT(chan->list), + .free_list = + LIST_HEAD_INIT(chan->free_list), + .line = line, + .primary = 1, + .input = 0, + .output = 0, + .opened = 0, + .enabled = 0, + .fd = -1, + .ops = ops, + .data = data }); + return chan; +} + +int parse_chan_pair(char *str, struct line *line, int device, + const struct chan_opts *opts, char **error_out) +{ + struct list_head *chans = &line->chan_list; + struct chan *new; + char *in, *out; + + if (!list_empty(chans)) { + line->chan_in = line->chan_out = NULL; + free_chan(chans); + INIT_LIST_HEAD(chans); + } + + if (!str) + return 0; + + out = strchr(str, ','); + if (out != NULL) { + in = str; + *out = '\0'; + out++; + new = parse_chan(line, in, device, opts, error_out); + if (new == NULL) + return -1; + + new->input = 1; + list_add(&new->list, chans); + line->chan_in = new; + + new = parse_chan(line, out, device, opts, error_out); + if (new == NULL) + return -1; + + list_add(&new->list, chans); + new->output = 1; + line->chan_out = new; + } + else { + new = parse_chan(line, str, device, opts, error_out); + if (new == NULL) + return -1; + + list_add(&new->list, chans); + new->input = 1; + new->output = 1; + line->chan_in = line->chan_out = new; + } + return 0; +} + +void chan_interrupt(struct line *line, int irq) +{ + struct tty_port *port = &line->port; + struct chan *chan = line->chan_in; + int err; + char c; + + if (!chan || !chan->ops->read) + goto out; + + do { + if (!tty_buffer_request_room(port, 1)) { + schedule_delayed_work(&line->task, 1); + goto out; + } + err = chan->ops->read(chan->fd, &c, chan->data); + if (err > 0) + tty_insert_flip_char(port, c, TTY_NORMAL); + } while (err > 0); + + if (err == -EIO) { + if (chan->primary) { + tty_port_tty_hangup(&line->port, false); + if (line->chan_out != chan) + close_one_chan(line->chan_out, 1); + } + close_one_chan(chan, 1); + if (chan->primary) + return; + } + out: + tty_flip_buffer_push(port); +} -- cgit v1.2.3