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(). ... --- .../drm/amd/amdkfd/kfd_device_queue_manager_vi.c | 256 +++++++++++++++++++++ 1 file changed, 256 insertions(+) create mode 100644 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c new file mode 100644 index 000000000..d7d45832d --- /dev/null +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright 2014-2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "kfd_device_queue_manager.h" +#include "gca/gfx_8_0_enum.h" +#include "gca/gfx_8_0_sh_mask.h" +#include "oss/oss_3_0_sh_mask.h" + +static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size); +static bool set_cache_memory_policy_vi_tonga(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size); +static int update_qpd_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd); +static int update_qpd_vi_tonga(struct device_queue_manager *dqm, + struct qcm_process_device *qpd); +static void init_sdma_vm(struct device_queue_manager *dqm, struct queue *q, + struct qcm_process_device *qpd); +static void init_sdma_vm_tonga(struct device_queue_manager *dqm, + struct queue *q, + struct qcm_process_device *qpd); + +void device_queue_manager_init_vi( + struct device_queue_manager_asic_ops *asic_ops) +{ + asic_ops->set_cache_memory_policy = set_cache_memory_policy_vi; + asic_ops->update_qpd = update_qpd_vi; + asic_ops->init_sdma_vm = init_sdma_vm; + asic_ops->mqd_manager_init = mqd_manager_init_vi; +} + +void device_queue_manager_init_vi_tonga( + struct device_queue_manager_asic_ops *asic_ops) +{ + asic_ops->set_cache_memory_policy = set_cache_memory_policy_vi_tonga; + asic_ops->update_qpd = update_qpd_vi_tonga; + asic_ops->init_sdma_vm = init_sdma_vm_tonga; + asic_ops->mqd_manager_init = mqd_manager_init_vi_tonga; +} + +static uint32_t compute_sh_mem_bases_64bit(unsigned int top_address_nybble) +{ + /* In 64-bit mode, we can only control the top 3 bits of the LDS, + * scratch and GPUVM apertures. + * The hardware fills in the remaining 59 bits according to the + * following pattern: + * LDS: X0000000'00000000 - X0000001'00000000 (4GB) + * Scratch: X0000001'00000000 - X0000002'00000000 (4GB) + * GPUVM: Y0010000'00000000 - Y0020000'00000000 (1TB) + * + * (where X/Y is the configurable nybble with the low-bit 0) + * + * LDS and scratch will have the same top nybble programmed in the + * top 3 bits of SH_MEM_BASES.PRIVATE_BASE. + * GPUVM can have a different top nybble programmed in the + * top 3 bits of SH_MEM_BASES.SHARED_BASE. + * We don't bother to support different top nybbles + * for LDS/Scratch and GPUVM. + */ + + WARN_ON((top_address_nybble & 1) || top_address_nybble > 0xE || + top_address_nybble == 0); + + return top_address_nybble << 12 | + (top_address_nybble << 12) << + SH_MEM_BASES__SHARED_BASE__SHIFT; +} + +static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size) +{ + uint32_t default_mtype; + uint32_t ape1_mtype; + + default_mtype = (default_policy == cache_policy_coherent) ? + MTYPE_CC : + MTYPE_NC; + + ape1_mtype = (alternate_policy == cache_policy_coherent) ? + MTYPE_CC : + MTYPE_NC; + + qpd->sh_mem_config = (qpd->sh_mem_config & + SH_MEM_CONFIG__ADDRESS_MODE_MASK) | + SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | + default_mtype << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | + ape1_mtype << SH_MEM_CONFIG__APE1_MTYPE__SHIFT | + SH_MEM_CONFIG__PRIVATE_ATC_MASK; + + return true; +} + +static bool set_cache_memory_policy_vi_tonga(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size) +{ + uint32_t default_mtype; + uint32_t ape1_mtype; + + default_mtype = (default_policy == cache_policy_coherent) ? + MTYPE_UC : + MTYPE_NC; + + ape1_mtype = (alternate_policy == cache_policy_coherent) ? + MTYPE_UC : + MTYPE_NC; + + qpd->sh_mem_config = + SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | + default_mtype << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | + ape1_mtype << SH_MEM_CONFIG__APE1_MTYPE__SHIFT; + + return true; +} + +static int update_qpd_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ + struct kfd_process_device *pdd; + unsigned int temp; + + pdd = qpd_to_pdd(qpd); + + /* check if sh_mem_config register already configured */ + if (qpd->sh_mem_config == 0) { + qpd->sh_mem_config = + SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | + MTYPE_CC << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | + MTYPE_CC << SH_MEM_CONFIG__APE1_MTYPE__SHIFT | + SH_MEM_CONFIG__PRIVATE_ATC_MASK; + + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + } + + if (qpd->pqm->process->is_32bit_user_mode) { + temp = get_sh_mem_bases_32(pdd); + qpd->sh_mem_bases = temp << SH_MEM_BASES__SHARED_BASE__SHIFT; + qpd->sh_mem_config |= SH_MEM_ADDRESS_MODE_HSA32 << + SH_MEM_CONFIG__ADDRESS_MODE__SHIFT; + } else { + temp = get_sh_mem_bases_nybble_64(pdd); + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); + qpd->sh_mem_config |= SH_MEM_ADDRESS_MODE_HSA64 << + SH_MEM_CONFIG__ADDRESS_MODE__SHIFT; + qpd->sh_mem_config |= 1 << + SH_MEM_CONFIG__PRIVATE_ATC__SHIFT; + } + + pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n", + qpd->pqm->process->is_32bit_user_mode, temp, qpd->sh_mem_bases); + + return 0; +} + +static int update_qpd_vi_tonga(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ + struct kfd_process_device *pdd; + unsigned int temp; + + pdd = qpd_to_pdd(qpd); + + /* check if sh_mem_config register already configured */ + if (qpd->sh_mem_config == 0) { + qpd->sh_mem_config = + SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | + MTYPE_UC << + SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | + MTYPE_UC << + SH_MEM_CONFIG__APE1_MTYPE__SHIFT; + + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + } + + /* On dGPU we're always in GPUVM64 addressing mode with 64-bit + * aperture addresses. + */ + temp = get_sh_mem_bases_nybble_64(pdd); + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); + + pr_debug("sh_mem_bases nybble: 0x%X and register 0x%X\n", + temp, qpd->sh_mem_bases); + + return 0; +} + +static void init_sdma_vm(struct device_queue_manager *dqm, struct queue *q, + struct qcm_process_device *qpd) +{ + uint32_t value = (1 << SDMA0_RLC0_VIRTUAL_ADDR__ATC__SHIFT); + + if (q->process->is_32bit_user_mode) + value |= (1 << SDMA0_RLC0_VIRTUAL_ADDR__PTR32__SHIFT) | + get_sh_mem_bases_32(qpd_to_pdd(qpd)); + else + value |= ((get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd))) << + SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE__SHIFT) & + SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE_MASK; + + q->properties.sdma_vm_addr = value; +} + +static void init_sdma_vm_tonga(struct device_queue_manager *dqm, + struct queue *q, + struct qcm_process_device *qpd) +{ + /* On dGPU we're always in GPUVM64 addressing mode with 64-bit + * aperture addresses. + */ + q->properties.sdma_vm_addr = + ((get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd))) << + SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE__SHIFT) & + SDMA0_RLC0_VIRTUAL_ADDR__SHARED_BASE_MASK; +} -- cgit v1.2.3