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/amd/amdgpu/amdgpu_vm.h | 535 +++++++++++++++++++++++++++++++++ 1 file changed, 535 insertions(+) create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h new file mode 100644 index 000000000..094bb4807 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -0,0 +1,535 @@ +/* + * Copyright 2016 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. + * + * Authors: Christian König + */ +#ifndef __AMDGPU_VM_H__ +#define __AMDGPU_VM_H__ + +#include +#include +#include +#include +#include +#include +#include + +#include "amdgpu_sync.h" +#include "amdgpu_ring.h" +#include "amdgpu_ids.h" + +struct amdgpu_bo_va; +struct amdgpu_job; +struct amdgpu_bo_list_entry; +struct amdgpu_bo_vm; + +/* + * GPUVM handling + */ + +/* Maximum number of PTEs the hardware can write with one command */ +#define AMDGPU_VM_MAX_UPDATE_SIZE 0x3FFFF + +/* number of entries in page table */ +#define AMDGPU_VM_PTE_COUNT(adev) (1 << (adev)->vm_manager.block_size) + +#define AMDGPU_PTE_VALID (1ULL << 0) +#define AMDGPU_PTE_SYSTEM (1ULL << 1) +#define AMDGPU_PTE_SNOOPED (1ULL << 2) + +/* RV+ */ +#define AMDGPU_PTE_TMZ (1ULL << 3) + +/* VI only */ +#define AMDGPU_PTE_EXECUTABLE (1ULL << 4) + +#define AMDGPU_PTE_READABLE (1ULL << 5) +#define AMDGPU_PTE_WRITEABLE (1ULL << 6) + +#define AMDGPU_PTE_FRAG(x) ((x & 0x1fULL) << 7) + +/* TILED for VEGA10, reserved for older ASICs */ +#define AMDGPU_PTE_PRT (1ULL << 51) + +/* PDE is handled as PTE for VEGA10 */ +#define AMDGPU_PDE_PTE (1ULL << 54) + +#define AMDGPU_PTE_LOG (1ULL << 55) + +/* PTE is handled as PDE for VEGA10 (Translate Further) */ +#define AMDGPU_PTE_TF (1ULL << 56) + +/* MALL noalloc for sienna_cichlid, reserved for older ASICs */ +#define AMDGPU_PTE_NOALLOC (1ULL << 58) + +/* PDE Block Fragment Size for VEGA10 */ +#define AMDGPU_PDE_BFS(a) ((uint64_t)a << 59) + + +/* For GFX9 */ +#define AMDGPU_PTE_MTYPE_VG10(a) ((uint64_t)(a) << 57) +#define AMDGPU_PTE_MTYPE_VG10_MASK AMDGPU_PTE_MTYPE_VG10(3ULL) + +#define AMDGPU_MTYPE_NC 0 +#define AMDGPU_MTYPE_CC 2 + +#define AMDGPU_PTE_DEFAULT_ATC (AMDGPU_PTE_SYSTEM \ + | AMDGPU_PTE_SNOOPED \ + | AMDGPU_PTE_EXECUTABLE \ + | AMDGPU_PTE_READABLE \ + | AMDGPU_PTE_WRITEABLE \ + | AMDGPU_PTE_MTYPE_VG10(AMDGPU_MTYPE_CC)) + +/* gfx10 */ +#define AMDGPU_PTE_MTYPE_NV10(a) ((uint64_t)(a) << 48) +#define AMDGPU_PTE_MTYPE_NV10_MASK AMDGPU_PTE_MTYPE_NV10(7ULL) + +/* How to program VM fault handling */ +#define AMDGPU_VM_FAULT_STOP_NEVER 0 +#define AMDGPU_VM_FAULT_STOP_FIRST 1 +#define AMDGPU_VM_FAULT_STOP_ALWAYS 2 + +/* Reserve 4MB VRAM for page tables */ +#define AMDGPU_VM_RESERVED_VRAM (8ULL << 20) + +/* max number of VMHUB */ +#define AMDGPU_MAX_VMHUBS 3 +#define AMDGPU_GFXHUB_0 0 +#define AMDGPU_MMHUB_0 1 +#define AMDGPU_MMHUB_1 2 + +/* Reserve 2MB at top/bottom of address space for kernel use */ +#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20) + +/* See vm_update_mode */ +#define AMDGPU_VM_USE_CPU_FOR_GFX (1 << 0) +#define AMDGPU_VM_USE_CPU_FOR_COMPUTE (1 << 1) + +/* VMPT level enumerate, and the hiberachy is: + * PDB2->PDB1->PDB0->PTB + */ +enum amdgpu_vm_level { + AMDGPU_VM_PDB2, + AMDGPU_VM_PDB1, + AMDGPU_VM_PDB0, + AMDGPU_VM_PTB +}; + +/* base structure for tracking BO usage in a VM */ +struct amdgpu_vm_bo_base { + /* constant after initialization */ + struct amdgpu_vm *vm; + struct amdgpu_bo *bo; + + /* protected by bo being reserved */ + struct amdgpu_vm_bo_base *next; + + /* protected by spinlock */ + struct list_head vm_status; + + /* protected by the BO being reserved */ + bool moved; +}; + +/* provided by hw blocks that can write ptes, e.g., sdma */ +struct amdgpu_vm_pte_funcs { + /* number of dw to reserve per operation */ + unsigned copy_pte_num_dw; + + /* copy pte entries from GART */ + void (*copy_pte)(struct amdgpu_ib *ib, + uint64_t pe, uint64_t src, + unsigned count); + + /* write pte one entry at a time with addr mapping */ + void (*write_pte)(struct amdgpu_ib *ib, uint64_t pe, + uint64_t value, unsigned count, + uint32_t incr); + /* for linear pte/pde updates without addr mapping */ + void (*set_pte_pde)(struct amdgpu_ib *ib, + uint64_t pe, + uint64_t addr, unsigned count, + uint32_t incr, uint64_t flags); +}; + +struct amdgpu_task_info { + char process_name[TASK_COMM_LEN]; + char task_name[TASK_COMM_LEN]; + pid_t pid; + pid_t tgid; +}; + +/** + * struct amdgpu_vm_update_params + * + * Encapsulate some VM table update parameters to reduce + * the number of function parameters + * + */ +struct amdgpu_vm_update_params { + + /** + * @adev: amdgpu device we do this update for + */ + struct amdgpu_device *adev; + + /** + * @vm: optional amdgpu_vm we do this update for + */ + struct amdgpu_vm *vm; + + /** + * @immediate: if changes should be made immediately + */ + bool immediate; + + /** + * @unlocked: true if the root BO is not locked + */ + bool unlocked; + + /** + * @pages_addr: + * + * DMA addresses to use for mapping + */ + dma_addr_t *pages_addr; + + /** + * @job: job to used for hw submission + */ + struct amdgpu_job *job; + + /** + * @num_dw_left: number of dw left for the IB + */ + unsigned int num_dw_left; + + /** + * @table_freed: return true if page table is freed when updating + */ + bool table_freed; +}; + +struct amdgpu_vm_update_funcs { + int (*map_table)(struct amdgpu_bo_vm *bo); + int (*prepare)(struct amdgpu_vm_update_params *p, struct dma_resv *resv, + enum amdgpu_sync_mode sync_mode); + int (*update)(struct amdgpu_vm_update_params *p, + struct amdgpu_bo_vm *bo, uint64_t pe, uint64_t addr, + unsigned count, uint32_t incr, uint64_t flags); + int (*commit)(struct amdgpu_vm_update_params *p, + struct dma_fence **fence); +}; + +struct amdgpu_vm { + /* tree of virtual addresses mapped */ + struct rb_root_cached va; + + /* Lock to prevent eviction while we are updating page tables + * use vm_eviction_lock/unlock(vm) + */ + struct mutex eviction_lock; + bool evicting; + unsigned int saved_flags; + + /* Lock to protect vm_bo add/del/move on all lists of vm */ + spinlock_t status_lock; + + /* BOs who needs a validation */ + struct list_head evicted; + + /* PT BOs which relocated and their parent need an update */ + struct list_head relocated; + + /* per VM BOs moved, but not yet updated in the PT */ + struct list_head moved; + + /* All BOs of this VM not currently in the state machine */ + struct list_head idle; + + /* regular invalidated BOs, but not yet updated in the PT */ + struct list_head invalidated; + + /* BO mappings freed, but not yet updated in the PT */ + struct list_head freed; + + /* BOs which are invalidated, has been updated in the PTs */ + struct list_head done; + + /* PT BOs scheduled to free and fill with zero if vm_resv is not hold */ + struct list_head pt_freed; + struct work_struct pt_free_work; + + /* contains the page directory */ + struct amdgpu_vm_bo_base root; + struct dma_fence *last_update; + + /* Scheduler entities for page table updates */ + struct drm_sched_entity immediate; + struct drm_sched_entity delayed; + + /* Last finished delayed update */ + atomic64_t tlb_seq; + struct dma_fence *last_tlb_flush; + + /* Last unlocked submission to the scheduler entities */ + struct dma_fence *last_unlocked; + + unsigned int pasid; + bool reserved_vmid[AMDGPU_MAX_VMHUBS]; + + /* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */ + bool use_cpu_for_update; + + /* Functions to use for VM table updates */ + const struct amdgpu_vm_update_funcs *update_funcs; + + /* Flag to indicate ATS support from PTE for GFX9 */ + bool pte_support_ats; + + /* Up to 128 pending retry page faults */ + DECLARE_KFIFO(faults, u64, 128); + + /* Points to the KFD process VM info */ + struct amdkfd_process_info *process_info; + + /* List node in amdkfd_process_info.vm_list_head */ + struct list_head vm_list_node; + + /* Valid while the PD is reserved or fenced */ + uint64_t pd_phys_addr; + + /* Some basic info about the task */ + struct amdgpu_task_info task_info; + + /* Store positions of group of BOs */ + struct ttm_lru_bulk_move lru_bulk_move; + /* Flag to indicate if VM is used for compute */ + bool is_compute_context; +}; + +struct amdgpu_vm_manager { + /* Handling of VMIDs */ + struct amdgpu_vmid_mgr id_mgr[AMDGPU_MAX_VMHUBS]; + unsigned int first_kfd_vmid; + bool concurrent_flush; + + /* Handling of VM fences */ + u64 fence_context; + unsigned seqno[AMDGPU_MAX_RINGS]; + + uint64_t max_pfn; + uint32_t num_level; + uint32_t block_size; + uint32_t fragment_size; + enum amdgpu_vm_level root_level; + /* vram base address for page table entry */ + u64 vram_base_offset; + /* vm pte handling */ + const struct amdgpu_vm_pte_funcs *vm_pte_funcs; + struct drm_gpu_scheduler *vm_pte_scheds[AMDGPU_MAX_RINGS]; + unsigned vm_pte_num_scheds; + struct amdgpu_ring *page_fault; + + /* partial resident texture handling */ + spinlock_t prt_lock; + atomic_t num_prt_users; + + /* controls how VM page tables are updated for Graphics and Compute. + * BIT0[= 0] Graphics updated by SDMA [= 1] by CPU + * BIT1[= 0] Compute updated by SDMA [= 1] by CPU + */ + int vm_update_mode; + + /* PASID to VM mapping, will be used in interrupt context to + * look up VM of a page fault + */ + struct xarray pasids; +}; + +struct amdgpu_bo_va_mapping; + +#define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count))) +#define amdgpu_vm_write_pte(adev, ib, pe, value, count, incr) ((adev)->vm_manager.vm_pte_funcs->write_pte((ib), (pe), (value), (count), (incr))) +#define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags))) + +extern const struct amdgpu_vm_update_funcs amdgpu_vm_cpu_funcs; +extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs; + +void amdgpu_vm_manager_init(struct amdgpu_device *adev); +void amdgpu_vm_manager_fini(struct amdgpu_device *adev); + +int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, + u32 pasid); + +long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout); +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm); +int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, + struct list_head *validated, + struct amdgpu_bo_list_entry *entry); +bool amdgpu_vm_ready(struct amdgpu_vm *vm); +int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, + int (*callback)(void *p, struct amdgpu_bo *bo), + void *param); +int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync); +int amdgpu_vm_update_pdes(struct amdgpu_device *adev, + struct amdgpu_vm *vm, bool immediate); +int amdgpu_vm_clear_freed(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct dma_fence **fence); +int amdgpu_vm_handle_moved(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, + struct amdgpu_vm *vm, struct amdgpu_bo *bo); +int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm, + bool immediate, bool unlocked, bool flush_tlb, + struct dma_resv *resv, uint64_t start, uint64_t last, + uint64_t flags, uint64_t offset, uint64_t vram_base, + struct ttm_resource *res, dma_addr_t *pages_addr, + struct dma_fence **fence); +int amdgpu_vm_bo_update(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + bool clear); +bool amdgpu_vm_evictable(struct amdgpu_bo *bo); +void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, + struct amdgpu_bo *bo, bool evicted); +uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr); +struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +int amdgpu_vm_bo_map(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr, uint64_t offset, + uint64_t size, uint64_t flags); +int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr, uint64_t offset, + uint64_t size, uint64_t flags); +int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr); +int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + uint64_t saddr, uint64_t size); +struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm, + uint64_t addr); +void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket); +void amdgpu_vm_bo_del(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va); +void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, + uint32_t fragment_size_default, unsigned max_level, + unsigned max_bits); +int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, + struct amdgpu_job *job); +void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev); + +void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, + struct amdgpu_task_info *task_info); +bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, + uint64_t addr, bool write_fault); + +void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); + +void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, + uint64_t *gtt_mem, uint64_t *cpu_mem); + +int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct amdgpu_bo_vm *vmbo, bool immediate); +int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, + int level, bool immediate, struct amdgpu_bo_vm **vmbo); +void amdgpu_vm_pt_free_root(struct amdgpu_device *adev, struct amdgpu_vm *vm); +bool amdgpu_vm_pt_is_root_clean(struct amdgpu_device *adev, + struct amdgpu_vm *vm); + +int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params, + struct amdgpu_vm_bo_base *entry); +int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, + uint64_t start, uint64_t end, + uint64_t dst, uint64_t flags); +void amdgpu_vm_pt_free_work(struct work_struct *work); + +#if defined(CONFIG_DEBUG_FS) +void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m); +#endif + +/** + * amdgpu_vm_tlb_seq - return tlb flush sequence number + * @vm: the amdgpu_vm structure to query + * + * Returns the tlb flush sequence number which indicates that the VM TLBs needs + * to be invalidated whenever the sequence number change. + */ +static inline uint64_t amdgpu_vm_tlb_seq(struct amdgpu_vm *vm) +{ + unsigned long flags; + spinlock_t *lock; + + /* + * Workaround to stop racing between the fence signaling and handling + * the cb. The lock is static after initially setting it up, just make + * sure that the dma_fence structure isn't freed up. + */ + rcu_read_lock(); + lock = vm->last_tlb_flush->lock; + rcu_read_unlock(); + + spin_lock_irqsave(lock, flags); + spin_unlock_irqrestore(lock, flags); + + return atomic64_read(&vm->tlb_seq); +} + +/* + * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS + * happens while holding this lock anywhere to prevent deadlocks when + * an MMU notifier runs in reclaim-FS context. + */ +static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm) +{ + mutex_lock(&vm->eviction_lock); + vm->saved_flags = memalloc_noreclaim_save(); +} + +static inline bool amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm) +{ + if (mutex_trylock(&vm->eviction_lock)) { + vm->saved_flags = memalloc_noreclaim_save(); + return true; + } + return false; +} + +static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm) +{ + memalloc_noreclaim_restore(vm->saved_flags); + mutex_unlock(&vm->eviction_lock); +} + +#endif -- cgit v1.2.3