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/media/pci/cx18/cx18-queue.c | 428 ++++++++++++++++++++++++++++++++++++ 1 file changed, 428 insertions(+) create mode 100644 drivers/media/pci/cx18/cx18-queue.c (limited to 'drivers/media/pci/cx18/cx18-queue.c') diff --git a/drivers/media/pci/cx18/cx18-queue.c b/drivers/media/pci/cx18/cx18-queue.c new file mode 100644 index 000000000..013694bfc --- /dev/null +++ b/drivers/media/pci/cx18/cx18-queue.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * cx18 buffer queues + * + * Derived from ivtv-queue.c + * + * Copyright (C) 2007 Hans Verkuil + * Copyright (C) 2008 Andy Walls + */ + +#include "cx18-driver.h" +#include "cx18-queue.h" +#include "cx18-streams.h" +#include "cx18-scb.h" +#include "cx18-io.h" + +void cx18_buf_swap(struct cx18_buffer *buf) +{ + int i; + + for (i = 0; i < buf->bytesused; i += 4) + swab32s((u32 *)(buf->buf + i)); +} + +void _cx18_mdl_swap(struct cx18_mdl *mdl) +{ + struct cx18_buffer *buf; + + list_for_each_entry(buf, &mdl->buf_list, list) { + if (buf->bytesused == 0) + break; + cx18_buf_swap(buf); + } +} + +void cx18_queue_init(struct cx18_queue *q) +{ + INIT_LIST_HEAD(&q->list); + atomic_set(&q->depth, 0); + q->bytesused = 0; +} + +struct cx18_queue *_cx18_enqueue(struct cx18_stream *s, struct cx18_mdl *mdl, + struct cx18_queue *q, int to_front) +{ + /* clear the mdl if it is not to be enqueued to the full queue */ + if (q != &s->q_full) { + mdl->bytesused = 0; + mdl->readpos = 0; + mdl->m_flags = 0; + mdl->skipped = 0; + mdl->curr_buf = NULL; + } + + /* q_busy is restricted to a max buffer count imposed by firmware */ + if (q == &s->q_busy && + atomic_read(&q->depth) >= CX18_MAX_FW_MDLS_PER_STREAM) + q = &s->q_free; + + spin_lock(&q->lock); + + if (to_front) + list_add(&mdl->list, &q->list); /* LIFO */ + else + list_add_tail(&mdl->list, &q->list); /* FIFO */ + q->bytesused += mdl->bytesused - mdl->readpos; + atomic_inc(&q->depth); + + spin_unlock(&q->lock); + return q; +} + +struct cx18_mdl *cx18_dequeue(struct cx18_stream *s, struct cx18_queue *q) +{ + struct cx18_mdl *mdl = NULL; + + spin_lock(&q->lock); + if (!list_empty(&q->list)) { + mdl = list_first_entry(&q->list, struct cx18_mdl, list); + list_del_init(&mdl->list); + q->bytesused -= mdl->bytesused - mdl->readpos; + mdl->skipped = 0; + atomic_dec(&q->depth); + } + spin_unlock(&q->lock); + return mdl; +} + +static void _cx18_mdl_update_bufs_for_cpu(struct cx18_stream *s, + struct cx18_mdl *mdl) +{ + struct cx18_buffer *buf; + u32 buf_size = s->buf_size; + u32 bytesused = mdl->bytesused; + + list_for_each_entry(buf, &mdl->buf_list, list) { + buf->readpos = 0; + if (bytesused >= buf_size) { + buf->bytesused = buf_size; + bytesused -= buf_size; + } else { + buf->bytesused = bytesused; + bytesused = 0; + } + cx18_buf_sync_for_cpu(s, buf); + } +} + +static inline void cx18_mdl_update_bufs_for_cpu(struct cx18_stream *s, + struct cx18_mdl *mdl) +{ + struct cx18_buffer *buf; + + if (list_is_singular(&mdl->buf_list)) { + buf = list_first_entry(&mdl->buf_list, struct cx18_buffer, + list); + buf->bytesused = mdl->bytesused; + buf->readpos = 0; + cx18_buf_sync_for_cpu(s, buf); + } else { + _cx18_mdl_update_bufs_for_cpu(s, mdl); + } +} + +struct cx18_mdl *cx18_queue_get_mdl(struct cx18_stream *s, u32 id, + u32 bytesused) +{ + struct cx18 *cx = s->cx; + struct cx18_mdl *mdl; + struct cx18_mdl *tmp; + struct cx18_mdl *ret = NULL; + LIST_HEAD(sweep_up); + + /* + * We don't have to acquire multiple q locks here, because we are + * serialized by the single threaded work handler. + * MDLs from the firmware will thus remain in order as + * they are moved from q_busy to q_full or to the dvb ring buffer. + */ + spin_lock(&s->q_busy.lock); + list_for_each_entry_safe(mdl, tmp, &s->q_busy.list, list) { + /* + * We should find what the firmware told us is done, + * right at the front of the queue. If we don't, we likely have + * missed an mdl done message from the firmware. + * Once we skip an mdl repeatedly, relative to the size of + * q_busy, we have high confidence we've missed it. + */ + if (mdl->id != id) { + mdl->skipped++; + if (mdl->skipped >= atomic_read(&s->q_busy.depth)-1) { + /* mdl must have fallen out of rotation */ + CX18_WARN("Skipped %s, MDL %d, %d times - it must have dropped out of rotation\n", + s->name, mdl->id, + mdl->skipped); + /* Sweep it up to put it back into rotation */ + list_move_tail(&mdl->list, &sweep_up); + atomic_dec(&s->q_busy.depth); + } + continue; + } + /* + * We pull the desired mdl off of the queue here. Something + * will have to put it back on a queue later. + */ + list_del_init(&mdl->list); + atomic_dec(&s->q_busy.depth); + ret = mdl; + break; + } + spin_unlock(&s->q_busy.lock); + + /* + * We found the mdl for which we were looking. Get it ready for + * the caller to put on q_full or in the dvb ring buffer. + */ + if (ret != NULL) { + ret->bytesused = bytesused; + ret->skipped = 0; + /* 0'ed readpos, m_flags & curr_buf when mdl went on q_busy */ + cx18_mdl_update_bufs_for_cpu(s, ret); + if (s->type != CX18_ENC_STREAM_TYPE_TS) + set_bit(CX18_F_M_NEED_SWAP, &ret->m_flags); + } + + /* Put any mdls the firmware is ignoring back into normal rotation */ + list_for_each_entry_safe(mdl, tmp, &sweep_up, list) { + list_del_init(&mdl->list); + cx18_enqueue(s, mdl, &s->q_free); + } + return ret; +} + +/* Move all mdls of a queue, while flushing the mdl */ +static void cx18_queue_flush(struct cx18_stream *s, + struct cx18_queue *q_src, struct cx18_queue *q_dst) +{ + struct cx18_mdl *mdl; + + /* It only makes sense to flush to q_free or q_idle */ + if (q_src == q_dst || q_dst == &s->q_full || q_dst == &s->q_busy) + return; + + spin_lock(&q_src->lock); + spin_lock(&q_dst->lock); + while (!list_empty(&q_src->list)) { + mdl = list_first_entry(&q_src->list, struct cx18_mdl, list); + list_move_tail(&mdl->list, &q_dst->list); + mdl->bytesused = 0; + mdl->readpos = 0; + mdl->m_flags = 0; + mdl->skipped = 0; + mdl->curr_buf = NULL; + atomic_inc(&q_dst->depth); + } + cx18_queue_init(q_src); + spin_unlock(&q_src->lock); + spin_unlock(&q_dst->lock); +} + +void cx18_flush_queues(struct cx18_stream *s) +{ + cx18_queue_flush(s, &s->q_busy, &s->q_free); + cx18_queue_flush(s, &s->q_full, &s->q_free); +} + +/* + * Note, s->buf_pool is not protected by a lock, + * the stream better not have *anything* going on when calling this + */ +void cx18_unload_queues(struct cx18_stream *s) +{ + struct cx18_queue *q_idle = &s->q_idle; + struct cx18_mdl *mdl; + struct cx18_buffer *buf; + + /* Move all MDLS to q_idle */ + cx18_queue_flush(s, &s->q_busy, q_idle); + cx18_queue_flush(s, &s->q_full, q_idle); + cx18_queue_flush(s, &s->q_free, q_idle); + + /* Reset MDL id's and move all buffers back to the stream's buf_pool */ + spin_lock(&q_idle->lock); + list_for_each_entry(mdl, &q_idle->list, list) { + while (!list_empty(&mdl->buf_list)) { + buf = list_first_entry(&mdl->buf_list, + struct cx18_buffer, list); + list_move_tail(&buf->list, &s->buf_pool); + buf->bytesused = 0; + buf->readpos = 0; + } + mdl->id = s->mdl_base_idx; /* reset id to a "safe" value */ + /* all other mdl fields were cleared by cx18_queue_flush() */ + } + spin_unlock(&q_idle->lock); +} + +/* + * Note, s->buf_pool is not protected by a lock, + * the stream better not have *anything* going on when calling this + */ +void cx18_load_queues(struct cx18_stream *s) +{ + struct cx18 *cx = s->cx; + struct cx18_mdl *mdl; + struct cx18_buffer *buf; + int mdl_id; + int i; + u32 partial_buf_size; + + /* + * Attach buffers to MDLs, give the MDLs ids, and add MDLs to q_free + * Excess MDLs are left on q_idle + * Excess buffers are left in buf_pool and/or on an MDL in q_idle + */ + mdl_id = s->mdl_base_idx; + for (mdl = cx18_dequeue(s, &s->q_idle), i = s->bufs_per_mdl; + mdl != NULL && i == s->bufs_per_mdl; + mdl = cx18_dequeue(s, &s->q_idle)) { + + mdl->id = mdl_id; + + for (i = 0; i < s->bufs_per_mdl; i++) { + if (list_empty(&s->buf_pool)) + break; + + buf = list_first_entry(&s->buf_pool, struct cx18_buffer, + list); + list_move_tail(&buf->list, &mdl->buf_list); + + /* update the firmware's MDL array with this buffer */ + cx18_writel(cx, buf->dma_handle, + &cx->scb->cpu_mdl[mdl_id + i].paddr); + cx18_writel(cx, s->buf_size, + &cx->scb->cpu_mdl[mdl_id + i].length); + } + + if (i == s->bufs_per_mdl) { + /* + * The encoder doesn't honor s->mdl_size. So in the + * case of a non-integral number of buffers to meet + * mdl_size, we lie about the size of the last buffer + * in the MDL to get the encoder to really only send + * us mdl_size bytes per MDL transfer. + */ + partial_buf_size = s->mdl_size % s->buf_size; + if (partial_buf_size) { + cx18_writel(cx, partial_buf_size, + &cx->scb->cpu_mdl[mdl_id + i - 1].length); + } + cx18_enqueue(s, mdl, &s->q_free); + } else { + /* Not enough buffers for this MDL; we won't use it */ + cx18_push(s, mdl, &s->q_idle); + } + mdl_id += i; + } +} + +void _cx18_mdl_sync_for_device(struct cx18_stream *s, struct cx18_mdl *mdl) +{ + int dma = s->dma; + u32 buf_size = s->buf_size; + struct pci_dev *pci_dev = s->cx->pci_dev; + struct cx18_buffer *buf; + + list_for_each_entry(buf, &mdl->buf_list, list) + dma_sync_single_for_device(&pci_dev->dev, buf->dma_handle, + buf_size, dma); +} + +int cx18_stream_alloc(struct cx18_stream *s) +{ + struct cx18 *cx = s->cx; + int i; + + if (s->buffers == 0) + return 0; + + CX18_DEBUG_INFO("Allocate %s stream: %d x %d buffers (%d.%02d kB total)\n", + s->name, s->buffers, s->buf_size, + s->buffers * s->buf_size / 1024, + (s->buffers * s->buf_size * 100 / 1024) % 100); + + if (((char __iomem *)&cx->scb->cpu_mdl[cx->free_mdl_idx + s->buffers] - + (char __iomem *)cx->scb) > SCB_RESERVED_SIZE) { + unsigned bufsz = (((char __iomem *)cx->scb) + SCB_RESERVED_SIZE - + ((char __iomem *)cx->scb->cpu_mdl)); + + CX18_ERR("Too many buffers, cannot fit in SCB area\n"); + CX18_ERR("Max buffers = %zu\n", + bufsz / sizeof(struct cx18_mdl_ent)); + return -ENOMEM; + } + + s->mdl_base_idx = cx->free_mdl_idx; + + /* allocate stream buffers and MDLs */ + for (i = 0; i < s->buffers; i++) { + struct cx18_mdl *mdl; + struct cx18_buffer *buf; + + /* 1 MDL per buffer to handle the worst & also default case */ + mdl = kzalloc(sizeof(struct cx18_mdl), GFP_KERNEL|__GFP_NOWARN); + if (mdl == NULL) + break; + + buf = kzalloc(sizeof(struct cx18_buffer), + GFP_KERNEL|__GFP_NOWARN); + if (buf == NULL) { + kfree(mdl); + break; + } + + buf->buf = kmalloc(s->buf_size, GFP_KERNEL|__GFP_NOWARN); + if (buf->buf == NULL) { + kfree(mdl); + kfree(buf); + break; + } + + INIT_LIST_HEAD(&mdl->list); + INIT_LIST_HEAD(&mdl->buf_list); + mdl->id = s->mdl_base_idx; /* a somewhat safe value */ + cx18_enqueue(s, mdl, &s->q_idle); + + INIT_LIST_HEAD(&buf->list); + buf->dma_handle = dma_map_single(&s->cx->pci_dev->dev, + buf->buf, s->buf_size, + s->dma); + cx18_buf_sync_for_cpu(s, buf); + list_add_tail(&buf->list, &s->buf_pool); + } + if (i == s->buffers) { + cx->free_mdl_idx += s->buffers; + return 0; + } + CX18_ERR("Couldn't allocate buffers for %s stream\n", s->name); + cx18_stream_free(s); + return -ENOMEM; +} + +void cx18_stream_free(struct cx18_stream *s) +{ + struct cx18_mdl *mdl; + struct cx18_buffer *buf; + struct cx18 *cx = s->cx; + + CX18_DEBUG_INFO("Deallocating buffers for %s stream\n", s->name); + + /* move all buffers to buf_pool and all MDLs to q_idle */ + cx18_unload_queues(s); + + /* empty q_idle */ + while ((mdl = cx18_dequeue(s, &s->q_idle))) + kfree(mdl); + + /* empty buf_pool */ + while (!list_empty(&s->buf_pool)) { + buf = list_first_entry(&s->buf_pool, struct cx18_buffer, list); + list_del_init(&buf->list); + + dma_unmap_single(&s->cx->pci_dev->dev, buf->dma_handle, + s->buf_size, s->dma); + kfree(buf->buf); + kfree(buf); + } +} -- cgit v1.2.3