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/gpu/drm/omapdrm/tcm-sita.c | 250 +++++++++++++++++++++++++++++++++++++ 1 file changed, 250 insertions(+) create mode 100644 drivers/gpu/drm/omapdrm/tcm-sita.c (limited to 'drivers/gpu/drm/omapdrm/tcm-sita.c') diff --git a/drivers/gpu/drm/omapdrm/tcm-sita.c b/drivers/gpu/drm/omapdrm/tcm-sita.c new file mode 100644 index 000000000..fde0208ec --- /dev/null +++ b/drivers/gpu/drm/omapdrm/tcm-sita.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SImple Tiler Allocator (SiTA): 2D and 1D allocation(reservation) algorithm + * + * Authors: Ravi Ramachandra , + * Lajos Molnar + * Andy Gross + * + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ + */ +#include +#include +#include +#include +#include +#include +#include +#include "tcm.h" + +static unsigned long mask[8]; +/* + * pos position in bitmap + * w width in slots + * h height in slots + * map ptr to bitmap + * stride slots in a row + */ +static void free_slots(unsigned long pos, u16 w, u16 h, + unsigned long *map, u16 stride) +{ + int i; + + for (i = 0; i < h; i++, pos += stride) + bitmap_clear(map, pos, w); +} + +/* + * w width in slots + * pos ptr to position + * map ptr to bitmap + * num_bits number of bits in bitmap + */ +static int r2l_b2t_1d(u16 w, unsigned long *pos, unsigned long *map, + size_t num_bits) +{ + unsigned long search_count = 0; + unsigned long bit; + bool area_found = false; + + *pos = num_bits - w; + + while (search_count < num_bits) { + bit = find_next_bit(map, num_bits, *pos); + + if (bit - *pos >= w) { + /* found a long enough free area */ + bitmap_set(map, *pos, w); + area_found = true; + break; + } + + search_count = num_bits - bit + w; + *pos = bit - w; + } + + return (area_found) ? 0 : -ENOMEM; +} + +/* + * w = width in slots + * h = height in slots + * a = align in slots (mask, 2^n-1, 0 is unaligned) + * offset = offset in bytes from 4KiB + * pos = position in bitmap for buffer + * map = bitmap ptr + * num_bits = size of bitmap + * stride = bits in one row of container + */ +static int l2r_t2b(u16 w, u16 h, u16 a, s16 offset, + unsigned long *pos, unsigned long slot_bytes, + unsigned long *map, size_t num_bits, size_t slot_stride) +{ + int i; + unsigned long index; + bool area_free = false; + unsigned long slots_per_band = PAGE_SIZE / slot_bytes; + unsigned long bit_offset = (offset > 0) ? offset / slot_bytes : 0; + unsigned long curr_bit = bit_offset; + + /* reset alignment to 1 if we are matching a specific offset */ + /* adjust alignment - 1 to get to the format expected in bitmaps */ + a = (offset > 0) ? 0 : a - 1; + + /* FIXME Return error if slots_per_band > stride */ + + while (curr_bit < num_bits) { + *pos = bitmap_find_next_zero_area(map, num_bits, curr_bit, w, + a); + + /* skip forward if we are not at right offset */ + if (bit_offset > 0 && (*pos % slots_per_band != bit_offset)) { + curr_bit = ALIGN(*pos, slots_per_band) + bit_offset; + continue; + } + + /* skip forward to next row if we overlap end of row */ + if ((*pos % slot_stride) + w > slot_stride) { + curr_bit = ALIGN(*pos, slot_stride) + bit_offset; + continue; + } + + /* TODO: Handle overlapping 4K boundaries */ + + /* break out of look if we will go past end of container */ + if ((*pos + slot_stride * h) > num_bits) + break; + + /* generate mask that represents out matching pattern */ + bitmap_clear(mask, 0, slot_stride); + bitmap_set(mask, (*pos % BITS_PER_LONG), w); + + /* assume the area is free until we find an overlap */ + area_free = true; + + /* check subsequent rows to see if complete area is free */ + for (i = 1; i < h; i++) { + index = *pos / BITS_PER_LONG + i * 8; + if (bitmap_intersects(&map[index], mask, + (*pos % BITS_PER_LONG) + w)) { + area_free = false; + break; + } + } + + if (area_free) + break; + + /* go forward past this match */ + if (bit_offset > 0) + curr_bit = ALIGN(*pos, slots_per_band) + bit_offset; + else + curr_bit = *pos + a + 1; + } + + if (area_free) { + /* set area as in-use. iterate over rows */ + for (i = 0, index = *pos; i < h; i++, index += slot_stride) + bitmap_set(map, index, w); + } + + return (area_free) ? 0 : -ENOMEM; +} + +static s32 sita_reserve_1d(struct tcm *tcm, u32 num_slots, + struct tcm_area *area) +{ + unsigned long pos; + int ret; + + spin_lock(&(tcm->lock)); + ret = r2l_b2t_1d(num_slots, &pos, tcm->bitmap, tcm->map_size); + if (!ret) { + area->p0.x = pos % tcm->width; + area->p0.y = pos / tcm->width; + area->p1.x = (pos + num_slots - 1) % tcm->width; + area->p1.y = (pos + num_slots - 1) / tcm->width; + } + spin_unlock(&(tcm->lock)); + + return ret; +} + +static s32 sita_reserve_2d(struct tcm *tcm, u16 h, u16 w, u16 align, + s16 offset, u16 slot_bytes, + struct tcm_area *area) +{ + unsigned long pos; + int ret; + + spin_lock(&(tcm->lock)); + ret = l2r_t2b(w, h, align, offset, &pos, slot_bytes, tcm->bitmap, + tcm->map_size, tcm->width); + + if (!ret) { + area->p0.x = pos % tcm->width; + area->p0.y = pos / tcm->width; + area->p1.x = area->p0.x + w - 1; + area->p1.y = area->p0.y + h - 1; + } + spin_unlock(&(tcm->lock)); + + return ret; +} + +static void sita_deinit(struct tcm *tcm) +{ + kfree(tcm); +} + +static s32 sita_free(struct tcm *tcm, struct tcm_area *area) +{ + unsigned long pos; + u16 w, h; + + pos = area->p0.x + area->p0.y * tcm->width; + if (area->is2d) { + w = area->p1.x - area->p0.x + 1; + h = area->p1.y - area->p0.y + 1; + } else { + w = area->p1.x + area->p1.y * tcm->width - pos + 1; + h = 1; + } + + spin_lock(&(tcm->lock)); + free_slots(pos, w, h, tcm->bitmap, tcm->width); + spin_unlock(&(tcm->lock)); + return 0; +} + +struct tcm *sita_init(u16 width, u16 height) +{ + struct tcm *tcm; + size_t map_size = BITS_TO_LONGS(width*height) * sizeof(unsigned long); + + if (width == 0 || height == 0) + return NULL; + + tcm = kzalloc(sizeof(*tcm) + map_size, GFP_KERNEL); + if (!tcm) + goto error; + + /* Updating the pointers to SiTA implementation APIs */ + tcm->height = height; + tcm->width = width; + tcm->reserve_2d = sita_reserve_2d; + tcm->reserve_1d = sita_reserve_1d; + tcm->free = sita_free; + tcm->deinit = sita_deinit; + + spin_lock_init(&tcm->lock); + tcm->bitmap = (unsigned long *)(tcm + 1); + bitmap_clear(tcm->bitmap, 0, width*height); + + tcm->map_size = width*height; + + return tcm; + +error: + return NULL; +} -- cgit v1.2.3