/*
 * 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.
 *
 */

#ifndef __AMDGPU_TTM_H__
#define __AMDGPU_TTM_H__

#include <linux/dma-direction.h>
#include <drm/gpu_scheduler.h>
#include <drm/ttm/ttm_placement.h>
#include "amdgpu_vram_mgr.h"
#include "amdgpu_hmm.h"
#include "amdgpu_gmc.h"

#define AMDGPU_PL_GDS           (TTM_PL_PRIV + 0)
#define AMDGPU_PL_GWS           (TTM_PL_PRIV + 1)
#define AMDGPU_PL_OA            (TTM_PL_PRIV + 2)
#define AMDGPU_PL_PREEMPT       (TTM_PL_PRIV + 3)
#define AMDGPU_PL_DOORBELL      (TTM_PL_PRIV + 4)
#define AMDGPU_PL_MMIO_REMAP    (TTM_PL_PRIV + 5)
#define __AMDGPU_PL_NUM (TTM_PL_PRIV + 6)

#define AMDGPU_GTT_MAX_TRANSFER_SIZE    (1ULL << 22)

extern const struct attribute_group amdgpu_vram_mgr_attr_group;
extern const struct attribute_group amdgpu_gtt_mgr_attr_group;

struct hmm_range;

struct amdgpu_gtt_mgr {
        struct ttm_resource_manager manager;
        struct drm_mm mm;
        spinlock_t lock;
};

struct amdgpu_ttm_buffer_entity {
        struct drm_sched_entity base;
        struct mutex            lock;
        struct drm_mm_node      gart_node;
        u64                     gart_window_offs[2];
};

enum amdgpu_resv_region_id {
        AMDGPU_RESV_STOLEN_VGA,
        AMDGPU_RESV_STOLEN_EXTENDED,
        AMDGPU_RESV_STOLEN_RESERVED,
        AMDGPU_RESV_FW,
        AMDGPU_RESV_FW_EXTEND,
        AMDGPU_RESV_FW_VRAM_USAGE,
        AMDGPU_RESV_DRV_VRAM_USAGE,
        AMDGPU_RESV_MEM_TRAIN,
        AMDGPU_RESV_MAX
};

struct amdgpu_vram_resv {
        uint64_t                offset;
        uint64_t                size;
        struct amdgpu_bo        *bo;
        void                    *cpu_ptr;
        bool                    needs_cpu_map;
};

struct amdgpu_mman {
        struct ttm_device               bdev;
        struct ttm_pool                 *ttm_pools;
        bool                            initialized;
        void __iomem                    *aper_base_kaddr;

        /* buffer handling */
        const struct amdgpu_buffer_funcs        *buffer_funcs;
        struct drm_gpu_scheduler                *buffer_funcs_scheds[AMDGPU_MAX_RINGS];
        u32                                     num_buffer_funcs_scheds;
        bool                                    buffer_funcs_enabled;

        /* @default_entity: for workarounds, has no gart windows */
        struct amdgpu_ttm_buffer_entity default_entity;
        struct amdgpu_ttm_buffer_entity *clear_entities;
        atomic_t next_clear_entity;
        u32 num_clear_entities;
        struct amdgpu_ttm_buffer_entity move_entities[TTM_NUM_MOVE_FENCES];
        atomic_t next_move_entity;
        u32 num_move_entities;

        struct amdgpu_vram_mgr vram_mgr;
        struct amdgpu_gtt_mgr gtt_mgr;
        struct ttm_resource_manager preempt_mgr;

        bool                    keep_stolen_vga_memory;

        struct amdgpu_vram_resv         resv_region[AMDGPU_RESV_MAX];

        /* PAGE_SIZE'd BO for process memory r/w over SDMA. */
        struct amdgpu_bo        *sdma_access_bo;
        void                    *sdma_access_ptr;
};

struct amdgpu_copy_mem {
        struct ttm_buffer_object        *bo;
        struct ttm_resource             *mem;
        unsigned long                   offset;
};

#define AMDGPU_COPY_FLAGS_TMZ           (1 << 0)
#define AMDGPU_COPY_FLAGS_READ_DECOMPRESSED     (1 << 1)
#define AMDGPU_COPY_FLAGS_WRITE_COMPRESSED      (1 << 2)
#define AMDGPU_COPY_FLAGS_MAX_COMPRESSED_SHIFT          3
#define AMDGPU_COPY_FLAGS_MAX_COMPRESSED_MASK           0x03
#define AMDGPU_COPY_FLAGS_NUMBER_TYPE_SHIFT             5
#define AMDGPU_COPY_FLAGS_NUMBER_TYPE_MASK              0x07
#define AMDGPU_COPY_FLAGS_DATA_FORMAT_SHIFT             8
#define AMDGPU_COPY_FLAGS_DATA_FORMAT_MASK              0x3f
#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_SHIFT  14
#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_MASK   0x1

#define AMDGPU_COPY_FLAGS_SET(field, value) \
        (((__u32)(value) & AMDGPU_COPY_FLAGS_##field##_MASK) << AMDGPU_COPY_FLAGS_##field##_SHIFT)
#define AMDGPU_COPY_FLAGS_GET(value, field) \
        (((__u32)(value) >> AMDGPU_COPY_FLAGS_##field##_SHIFT) & AMDGPU_COPY_FLAGS_##field##_MASK)

int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size);
void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev);
int amdgpu_preempt_mgr_init(struct amdgpu_device *adev);
void amdgpu_preempt_mgr_fini(struct amdgpu_device *adev);
int amdgpu_vram_mgr_init(struct amdgpu_device *adev);
void amdgpu_vram_mgr_fini(struct amdgpu_device *adev);

bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem);
void amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr);

int amdgpu_gtt_mgr_alloc_entries(struct amdgpu_gtt_mgr *mgr,
                                 struct drm_mm_node *mm_node,
                                 u64 num_pages,
                                 enum drm_mm_insert_mode mode);
void amdgpu_gtt_mgr_free_entries(struct amdgpu_gtt_mgr *mgr,
                                 struct drm_mm_node *mm_node);
uint64_t amdgpu_preempt_mgr_usage(struct ttm_resource_manager *man);

u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
                              struct ttm_resource *mem,
                              u64 offset, u64 size,
                              struct device *dev,
                              enum dma_data_direction dir,
                              struct sg_table **sgt);
void amdgpu_vram_mgr_free_sgt(struct device *dev,
                              enum dma_data_direction dir,
                              struct sg_table *sgt);
uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr);
int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr,
                                  uint64_t start, uint64_t size);
int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
                                      uint64_t start);
void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev);

bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
                            struct ttm_resource *res);

void amdgpu_ttm_init_vram_resv(struct amdgpu_device *adev,
                                enum amdgpu_resv_region_id id,
                                uint64_t offset, uint64_t size,
                                bool needs_cpu_map);
int amdgpu_ttm_mark_vram_reserved(struct amdgpu_device *adev,
                                  enum amdgpu_resv_region_id id);
void amdgpu_ttm_unmark_vram_reserved(struct amdgpu_device *adev,
                                     enum amdgpu_resv_region_id id);

int amdgpu_ttm_init(struct amdgpu_device *adev);
void amdgpu_ttm_fini(struct amdgpu_device *adev);
void amdgpu_ttm_enable_buffer_funcs(struct amdgpu_device *adev);
void amdgpu_ttm_disable_buffer_funcs(struct amdgpu_device *adev);
int amdgpu_copy_buffer(struct amdgpu_device *adev,
                       struct amdgpu_ttm_buffer_entity *entity,
                       uint64_t src_offset,
                       uint64_t dst_offset, uint32_t byte_count,
                       struct dma_resv *resv,
                       struct dma_fence **fence,
                       bool vm_needs_flush, uint32_t copy_flags);
int amdgpu_ttm_clear_buffer(struct amdgpu_ttm_buffer_entity *entity,
                            struct amdgpu_bo *bo,
                            struct dma_resv *resv,
                            struct dma_fence **out_fence,
                            bool consider_clear_status,
                            u64 k_job_id);
struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev);

int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);

#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo,
                                 struct amdgpu_hmm_range *range);
#else
static inline int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo,
                                               struct amdgpu_hmm_range *range)
{
        return -EPERM;
}
#endif

/**
 * amdgpu_compute_gart_address() - Returns GART address of an entity's window
 * @gmc: The &struct amdgpu_gmc instance to use
 * @entity: The &struct amdgpu_ttm_buffer_entity owning the GART window
 * @index: The window to use (must be 0 or 1)
 */
static inline u64 amdgpu_compute_gart_address(struct amdgpu_gmc *gmc,
                                              struct amdgpu_ttm_buffer_entity *entity,
                                              int index)
{
        return gmc->gart_start + entity->gart_window_offs[index];
}

/**
 * amdgpu_gtt_node_to_byte_offset() - Returns a byte offset of a gtt node
 */
static inline u64 amdgpu_gtt_node_to_byte_offset(const struct drm_mm_node *gtt_node)
{
        return gtt_node->start * (u64)PAGE_SIZE;
}

void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct amdgpu_hmm_range *range);
int amdgpu_ttm_tt_get_userptr(const struct ttm_buffer_object *tbo,
                              uint64_t *user_addr);
int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
                              uint64_t addr, uint32_t flags);
bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm);
bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
                                  unsigned long end, unsigned long *userptr);
bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
                                       int *last_invalidated);
bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm);
bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem);
uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
                                 struct ttm_resource *mem);
int amdgpu_ttm_evict_resources(struct amdgpu_device *adev, int mem_type);

void amdgpu_ttm_debugfs_init(struct amdgpu_device *adev);

int amdgpu_ttm_mmio_remap_alloc_sgt(struct amdgpu_device *adev,
                                    struct ttm_resource *res,
                                    struct device *dev,
                                    enum dma_data_direction dir,
                                    struct sg_table **sgt);
void amdgpu_ttm_mmio_remap_free_sgt(struct device *dev,
                                    enum dma_data_direction dir,
                                    struct sg_table *sgt);

#endif