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/i915/gvt/gtt.h | 297 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 297 insertions(+) create mode 100644 drivers/gpu/drm/i915/gvt/gtt.h (limited to 'drivers/gpu/drm/i915/gvt/gtt.h') diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h new file mode 100644 index 000000000..a3b0f59ec --- /dev/null +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -0,0 +1,297 @@ +/* + * Copyright(c) 2011-2016 Intel Corporation. All rights reserved. + * + * 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 (including the next + * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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. + * + * Authors: + * Zhi Wang + * Zhenyu Wang + * Xiao Zheng + * + * Contributors: + * Min He + * Bing Niu + * + */ + +#ifndef _GVT_GTT_H_ +#define _GVT_GTT_H_ + +#include +#include +#include +#include + +#include "gt/intel_gtt.h" + +struct intel_gvt; +struct intel_vgpu; +struct intel_vgpu_mm; + +#define I915_GTT_PAGE_SHIFT 12 + +#define INTEL_GVT_INVALID_ADDR (~0UL) + +struct intel_gvt_gtt_entry { + u64 val64; + int type; +}; + +struct intel_gvt_gtt_pte_ops { + int (*get_entry)(void *pt, + struct intel_gvt_gtt_entry *e, + unsigned long index, + bool hypervisor_access, + unsigned long gpa, + struct intel_vgpu *vgpu); + int (*set_entry)(void *pt, + struct intel_gvt_gtt_entry *e, + unsigned long index, + bool hypervisor_access, + unsigned long gpa, + struct intel_vgpu *vgpu); + bool (*test_present)(struct intel_gvt_gtt_entry *e); + void (*clear_present)(struct intel_gvt_gtt_entry *e); + void (*set_present)(struct intel_gvt_gtt_entry *e); + bool (*test_pse)(struct intel_gvt_gtt_entry *e); + void (*clear_pse)(struct intel_gvt_gtt_entry *e); + bool (*test_ips)(struct intel_gvt_gtt_entry *e); + void (*clear_ips)(struct intel_gvt_gtt_entry *e); + bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e); + void (*clear_64k_splited)(struct intel_gvt_gtt_entry *e); + void (*set_64k_splited)(struct intel_gvt_gtt_entry *e); + void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn); + unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e); +}; + +struct intel_gvt_gtt_gma_ops { + unsigned long (*gma_to_ggtt_pte_index)(unsigned long gma); + unsigned long (*gma_to_pte_index)(unsigned long gma); + unsigned long (*gma_to_pde_index)(unsigned long gma); + unsigned long (*gma_to_l3_pdp_index)(unsigned long gma); + unsigned long (*gma_to_l4_pdp_index)(unsigned long gma); + unsigned long (*gma_to_pml4_index)(unsigned long gma); +}; + +struct intel_gvt_gtt { + const struct intel_gvt_gtt_pte_ops *pte_ops; + const struct intel_gvt_gtt_gma_ops *gma_ops; + int (*mm_alloc_page_table)(struct intel_vgpu_mm *mm); + void (*mm_free_page_table)(struct intel_vgpu_mm *mm); + struct list_head oos_page_use_list_head; + struct list_head oos_page_free_list_head; + struct mutex ppgtt_mm_lock; + struct list_head ppgtt_mm_lru_list_head; + + struct page *scratch_page; + unsigned long scratch_mfn; +}; + +enum intel_gvt_gtt_type { + GTT_TYPE_INVALID = 0, + + GTT_TYPE_GGTT_PTE, + + GTT_TYPE_PPGTT_PTE_4K_ENTRY, + GTT_TYPE_PPGTT_PTE_64K_ENTRY, + GTT_TYPE_PPGTT_PTE_2M_ENTRY, + GTT_TYPE_PPGTT_PTE_1G_ENTRY, + + GTT_TYPE_PPGTT_PTE_ENTRY, + + GTT_TYPE_PPGTT_PDE_ENTRY, + GTT_TYPE_PPGTT_PDP_ENTRY, + GTT_TYPE_PPGTT_PML4_ENTRY, + + GTT_TYPE_PPGTT_ROOT_ENTRY, + + GTT_TYPE_PPGTT_ROOT_L3_ENTRY, + GTT_TYPE_PPGTT_ROOT_L4_ENTRY, + + GTT_TYPE_PPGTT_ENTRY, + + GTT_TYPE_PPGTT_PTE_PT, + GTT_TYPE_PPGTT_PDE_PT, + GTT_TYPE_PPGTT_PDP_PT, + GTT_TYPE_PPGTT_PML4_PT, + + GTT_TYPE_MAX, +}; + +enum intel_gvt_mm_type { + INTEL_GVT_MM_GGTT, + INTEL_GVT_MM_PPGTT, +}; + +#define GVT_RING_CTX_NR_PDPS GEN8_3LVL_PDPES + +struct intel_gvt_partial_pte { + unsigned long offset; + u64 data; + struct list_head list; +}; + +struct intel_vgpu_mm { + enum intel_gvt_mm_type type; + struct intel_vgpu *vgpu; + + struct kref ref; + atomic_t pincount; + + union { + struct { + enum intel_gvt_gtt_type root_entry_type; + /* + * The 4 PDPs in ring context. For 48bit addressing, + * only PDP0 is valid and point to PML4. For 32it + * addressing, all 4 are used as true PDPs. + */ + u64 guest_pdps[GVT_RING_CTX_NR_PDPS]; + u64 shadow_pdps[GVT_RING_CTX_NR_PDPS]; + bool shadowed; + + struct list_head list; + struct list_head lru_list; + struct list_head link; /* possible LRI shadow mm list */ + } ppgtt_mm; + struct { + void *virtual_ggtt; + /* Save/restore for PM */ + u64 *host_ggtt_aperture; + u64 *host_ggtt_hidden; + struct list_head partial_pte_list; + } ggtt_mm; + }; +}; + +struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu, + enum intel_gvt_gtt_type root_entry_type, u64 pdps[]); + +static inline void intel_vgpu_mm_get(struct intel_vgpu_mm *mm) +{ + kref_get(&mm->ref); +} + +void _intel_vgpu_mm_release(struct kref *mm_ref); + +static inline void intel_vgpu_mm_put(struct intel_vgpu_mm *mm) +{ + kref_put(&mm->ref, _intel_vgpu_mm_release); +} + +static inline void intel_vgpu_destroy_mm(struct intel_vgpu_mm *mm) +{ + intel_vgpu_mm_put(mm); +} + +struct intel_vgpu_guest_page; + +struct intel_vgpu_scratch_pt { + struct page *page; + unsigned long page_mfn; +}; + +struct intel_vgpu_gtt { + struct intel_vgpu_mm *ggtt_mm; + unsigned long active_ppgtt_mm_bitmap; + struct list_head ppgtt_mm_list_head; + struct radix_tree_root spt_tree; + struct list_head oos_page_list_head; + struct list_head post_shadow_list_head; + struct intel_vgpu_scratch_pt scratch_pt[GTT_TYPE_MAX]; +}; + +int intel_vgpu_init_gtt(struct intel_vgpu *vgpu); +void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu); +void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old); +void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu); + +int intel_gvt_init_gtt(struct intel_gvt *gvt); +void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu); +void intel_gvt_clean_gtt(struct intel_gvt *gvt); + +struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu, + int page_table_level, + void *root_entry); + +struct intel_vgpu_oos_page { + struct intel_vgpu_ppgtt_spt *spt; + struct list_head list; + struct list_head vm_list; + int id; + void *mem; +}; + +#define GTT_ENTRY_NUM_IN_ONE_PAGE 512 + +/* Represent a vgpu shadow page table. */ +struct intel_vgpu_ppgtt_spt { + atomic_t refcount; + struct intel_vgpu *vgpu; + + struct { + enum intel_gvt_gtt_type type; + bool pde_ips; /* for 64KB PTEs */ + void *vaddr; + struct page *page; + unsigned long mfn; + } shadow_page; + + struct { + enum intel_gvt_gtt_type type; + bool pde_ips; /* for 64KB PTEs */ + unsigned long gfn; + unsigned long write_cnt; + struct intel_vgpu_oos_page *oos_page; + } guest_page; + + DECLARE_BITMAP(post_shadow_bitmap, GTT_ENTRY_NUM_IN_ONE_PAGE); + struct list_head post_shadow_list; +}; + +int intel_vgpu_sync_oos_pages(struct intel_vgpu *vgpu); + +int intel_vgpu_flush_post_shadow(struct intel_vgpu *vgpu); + +int intel_vgpu_pin_mm(struct intel_vgpu_mm *mm); + +void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm); + +unsigned long intel_vgpu_gma_to_gpa(struct intel_vgpu_mm *mm, + unsigned long gma); + +struct intel_vgpu_mm *intel_vgpu_find_ppgtt_mm(struct intel_vgpu *vgpu, + u64 pdps[]); + +struct intel_vgpu_mm *intel_vgpu_get_ppgtt_mm(struct intel_vgpu *vgpu, + enum intel_gvt_gtt_type root_entry_type, u64 pdps[]); + +int intel_vgpu_put_ppgtt_mm(struct intel_vgpu *vgpu, u64 pdps[]); + +int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, + unsigned int off, void *p_data, unsigned int bytes); + +int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, + unsigned int off, void *p_data, unsigned int bytes); + +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu); +void intel_gvt_restore_ggtt(struct intel_gvt *gvt); + +#endif /* _GVT_GTT_H_ */ -- cgit v1.2.3