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(). ... --- block/blk-ioc.c | 457 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 457 insertions(+) create mode 100644 block/blk-ioc.c (limited to 'block/blk-ioc.c') diff --git a/block/blk-ioc.c b/block/blk-ioc.c new file mode 100644 index 000000000..63fc02042 --- /dev/null +++ b/block/blk-ioc.c @@ -0,0 +1,457 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Functions related to io context handling + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "blk.h" +#include "blk-mq-sched.h" + +/* + * For io context allocations + */ +static struct kmem_cache *iocontext_cachep; + +#ifdef CONFIG_BLK_ICQ +/** + * get_io_context - increment reference count to io_context + * @ioc: io_context to get + * + * Increment reference count to @ioc. + */ +static void get_io_context(struct io_context *ioc) +{ + BUG_ON(atomic_long_read(&ioc->refcount) <= 0); + atomic_long_inc(&ioc->refcount); +} + +static void icq_free_icq_rcu(struct rcu_head *head) +{ + struct io_cq *icq = container_of(head, struct io_cq, __rcu_head); + + kmem_cache_free(icq->__rcu_icq_cache, icq); +} + +/* + * Exit an icq. Called with ioc locked for blk-mq, and with both ioc + * and queue locked for legacy. + */ +static void ioc_exit_icq(struct io_cq *icq) +{ + struct elevator_type *et = icq->q->elevator->type; + + if (icq->flags & ICQ_EXITED) + return; + + if (et->ops.exit_icq) + et->ops.exit_icq(icq); + + icq->flags |= ICQ_EXITED; +} + +static void ioc_exit_icqs(struct io_context *ioc) +{ + struct io_cq *icq; + + spin_lock_irq(&ioc->lock); + hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) + ioc_exit_icq(icq); + spin_unlock_irq(&ioc->lock); +} + +/* + * Release an icq. Called with ioc locked for blk-mq, and with both ioc + * and queue locked for legacy. + */ +static void ioc_destroy_icq(struct io_cq *icq) +{ + struct io_context *ioc = icq->ioc; + struct request_queue *q = icq->q; + struct elevator_type *et = q->elevator->type; + + lockdep_assert_held(&ioc->lock); + + radix_tree_delete(&ioc->icq_tree, icq->q->id); + hlist_del_init(&icq->ioc_node); + list_del_init(&icq->q_node); + + /* + * Both setting lookup hint to and clearing it from @icq are done + * under queue_lock. If it's not pointing to @icq now, it never + * will. Hint assignment itself can race safely. + */ + if (rcu_access_pointer(ioc->icq_hint) == icq) + rcu_assign_pointer(ioc->icq_hint, NULL); + + ioc_exit_icq(icq); + + /* + * @icq->q might have gone away by the time RCU callback runs + * making it impossible to determine icq_cache. Record it in @icq. + */ + icq->__rcu_icq_cache = et->icq_cache; + icq->flags |= ICQ_DESTROYED; + call_rcu(&icq->__rcu_head, icq_free_icq_rcu); +} + +/* + * Slow path for ioc release in put_io_context(). Performs double-lock + * dancing to unlink all icq's and then frees ioc. + */ +static void ioc_release_fn(struct work_struct *work) +{ + struct io_context *ioc = container_of(work, struct io_context, + release_work); + spin_lock_irq(&ioc->lock); + + while (!hlist_empty(&ioc->icq_list)) { + struct io_cq *icq = hlist_entry(ioc->icq_list.first, + struct io_cq, ioc_node); + struct request_queue *q = icq->q; + + if (spin_trylock(&q->queue_lock)) { + ioc_destroy_icq(icq); + spin_unlock(&q->queue_lock); + } else { + /* Make sure q and icq cannot be freed. */ + rcu_read_lock(); + + /* Re-acquire the locks in the correct order. */ + spin_unlock(&ioc->lock); + spin_lock(&q->queue_lock); + spin_lock(&ioc->lock); + + /* + * The icq may have been destroyed when the ioc lock + * was released. + */ + if (!(icq->flags & ICQ_DESTROYED)) + ioc_destroy_icq(icq); + + spin_unlock(&q->queue_lock); + rcu_read_unlock(); + } + } + + spin_unlock_irq(&ioc->lock); + + kmem_cache_free(iocontext_cachep, ioc); +} + +/* + * Releasing icqs requires reverse order double locking and we may already be + * holding a queue_lock. Do it asynchronously from a workqueue. + */ +static bool ioc_delay_free(struct io_context *ioc) +{ + unsigned long flags; + + spin_lock_irqsave(&ioc->lock, flags); + if (!hlist_empty(&ioc->icq_list)) { + queue_work(system_power_efficient_wq, &ioc->release_work); + spin_unlock_irqrestore(&ioc->lock, flags); + return true; + } + spin_unlock_irqrestore(&ioc->lock, flags); + return false; +} + +/** + * ioc_clear_queue - break any ioc association with the specified queue + * @q: request_queue being cleared + * + * Walk @q->icq_list and exit all io_cq's. + */ +void ioc_clear_queue(struct request_queue *q) +{ + LIST_HEAD(icq_list); + + spin_lock_irq(&q->queue_lock); + list_splice_init(&q->icq_list, &icq_list); + spin_unlock_irq(&q->queue_lock); + + rcu_read_lock(); + while (!list_empty(&icq_list)) { + struct io_cq *icq = + list_entry(icq_list.next, struct io_cq, q_node); + + spin_lock_irq(&icq->ioc->lock); + if (!(icq->flags & ICQ_DESTROYED)) + ioc_destroy_icq(icq); + spin_unlock_irq(&icq->ioc->lock); + } + rcu_read_unlock(); +} +#else /* CONFIG_BLK_ICQ */ +static inline void ioc_exit_icqs(struct io_context *ioc) +{ +} +static inline bool ioc_delay_free(struct io_context *ioc) +{ + return false; +} +#endif /* CONFIG_BLK_ICQ */ + +/** + * put_io_context - put a reference of io_context + * @ioc: io_context to put + * + * Decrement reference count of @ioc and release it if the count reaches + * zero. + */ +void put_io_context(struct io_context *ioc) +{ + BUG_ON(atomic_long_read(&ioc->refcount) <= 0); + if (atomic_long_dec_and_test(&ioc->refcount) && !ioc_delay_free(ioc)) + kmem_cache_free(iocontext_cachep, ioc); +} +EXPORT_SYMBOL_GPL(put_io_context); + +/* Called by the exiting task */ +void exit_io_context(struct task_struct *task) +{ + struct io_context *ioc; + + task_lock(task); + ioc = task->io_context; + task->io_context = NULL; + task_unlock(task); + + if (atomic_dec_and_test(&ioc->active_ref)) { + ioc_exit_icqs(ioc); + put_io_context(ioc); + } +} + +static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) +{ + struct io_context *ioc; + + ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, + node); + if (unlikely(!ioc)) + return NULL; + + atomic_long_set(&ioc->refcount, 1); + atomic_set(&ioc->active_ref, 1); +#ifdef CONFIG_BLK_ICQ + spin_lock_init(&ioc->lock); + INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); + INIT_HLIST_HEAD(&ioc->icq_list); + INIT_WORK(&ioc->release_work, ioc_release_fn); +#endif + ioc->ioprio = IOPRIO_DEFAULT; + + return ioc; +} + +int set_task_ioprio(struct task_struct *task, int ioprio) +{ + int err; + const struct cred *cred = current_cred(), *tcred; + + rcu_read_lock(); + tcred = __task_cred(task); + if (!uid_eq(tcred->uid, cred->euid) && + !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); + return -EPERM; + } + rcu_read_unlock(); + + err = security_task_setioprio(task, ioprio); + if (err) + return err; + + task_lock(task); + if (unlikely(!task->io_context)) { + struct io_context *ioc; + + task_unlock(task); + + ioc = alloc_io_context(GFP_ATOMIC, NUMA_NO_NODE); + if (!ioc) + return -ENOMEM; + + task_lock(task); + if (task->flags & PF_EXITING) { + kmem_cache_free(iocontext_cachep, ioc); + goto out; + } + if (task->io_context) + kmem_cache_free(iocontext_cachep, ioc); + else + task->io_context = ioc; + } + task->io_context->ioprio = ioprio; +out: + task_unlock(task); + return 0; +} +EXPORT_SYMBOL_GPL(set_task_ioprio); + +int __copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + struct io_context *ioc = current->io_context; + + /* + * Share io context with parent, if CLONE_IO is set + */ + if (clone_flags & CLONE_IO) { + atomic_inc(&ioc->active_ref); + tsk->io_context = ioc; + } else if (ioprio_valid(ioc->ioprio)) { + tsk->io_context = alloc_io_context(GFP_KERNEL, NUMA_NO_NODE); + if (!tsk->io_context) + return -ENOMEM; + tsk->io_context->ioprio = ioc->ioprio; + } + + return 0; +} + +#ifdef CONFIG_BLK_ICQ +/** + * ioc_lookup_icq - lookup io_cq from ioc + * @q: the associated request_queue + * + * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called + * with @q->queue_lock held. + */ +struct io_cq *ioc_lookup_icq(struct request_queue *q) +{ + struct io_context *ioc = current->io_context; + struct io_cq *icq; + + lockdep_assert_held(&q->queue_lock); + + /* + * icq's are indexed from @ioc using radix tree and hint pointer, + * both of which are protected with RCU. All removals are done + * holding both q and ioc locks, and we're holding q lock - if we + * find a icq which points to us, it's guaranteed to be valid. + */ + rcu_read_lock(); + icq = rcu_dereference(ioc->icq_hint); + if (icq && icq->q == q) + goto out; + + icq = radix_tree_lookup(&ioc->icq_tree, q->id); + if (icq && icq->q == q) + rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ + else + icq = NULL; +out: + rcu_read_unlock(); + return icq; +} +EXPORT_SYMBOL(ioc_lookup_icq); + +/** + * ioc_create_icq - create and link io_cq + * @q: request_queue of interest + * + * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they + * will be created using @gfp_mask. + * + * The caller is responsible for ensuring @ioc won't go away and @q is + * alive and will stay alive until this function returns. + */ +static struct io_cq *ioc_create_icq(struct request_queue *q) +{ + struct io_context *ioc = current->io_context; + struct elevator_type *et = q->elevator->type; + struct io_cq *icq; + + /* allocate stuff */ + icq = kmem_cache_alloc_node(et->icq_cache, GFP_ATOMIC | __GFP_ZERO, + q->node); + if (!icq) + return NULL; + + if (radix_tree_maybe_preload(GFP_ATOMIC) < 0) { + kmem_cache_free(et->icq_cache, icq); + return NULL; + } + + icq->ioc = ioc; + icq->q = q; + INIT_LIST_HEAD(&icq->q_node); + INIT_HLIST_NODE(&icq->ioc_node); + + /* lock both q and ioc and try to link @icq */ + spin_lock_irq(&q->queue_lock); + spin_lock(&ioc->lock); + + if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { + hlist_add_head(&icq->ioc_node, &ioc->icq_list); + list_add(&icq->q_node, &q->icq_list); + if (et->ops.init_icq) + et->ops.init_icq(icq); + } else { + kmem_cache_free(et->icq_cache, icq); + icq = ioc_lookup_icq(q); + if (!icq) + printk(KERN_ERR "cfq: icq link failed!\n"); + } + + spin_unlock(&ioc->lock); + spin_unlock_irq(&q->queue_lock); + radix_tree_preload_end(); + return icq; +} + +struct io_cq *ioc_find_get_icq(struct request_queue *q) +{ + struct io_context *ioc = current->io_context; + struct io_cq *icq = NULL; + + if (unlikely(!ioc)) { + ioc = alloc_io_context(GFP_ATOMIC, q->node); + if (!ioc) + return NULL; + + task_lock(current); + if (current->io_context) { + kmem_cache_free(iocontext_cachep, ioc); + ioc = current->io_context; + } else { + current->io_context = ioc; + } + + get_io_context(ioc); + task_unlock(current); + } else { + get_io_context(ioc); + + spin_lock_irq(&q->queue_lock); + icq = ioc_lookup_icq(q); + spin_unlock_irq(&q->queue_lock); + } + + if (!icq) { + icq = ioc_create_icq(q); + if (!icq) { + put_io_context(ioc); + return NULL; + } + } + return icq; +} +EXPORT_SYMBOL_GPL(ioc_find_get_icq); +#endif /* CONFIG_BLK_ICQ */ + +static int __init blk_ioc_init(void) +{ + iocontext_cachep = kmem_cache_create("blkdev_ioc", + sizeof(struct io_context), 0, SLAB_PANIC, NULL); + return 0; +} +subsys_initcall(blk_ioc_init); -- cgit v1.2.3