1
0
Fork 0
alistair23-linux/drivers/gpu/drm/amd/amdgpu/amdgpu.h

1371 lines
40 KiB
C
Raw Normal View History

/*
* Copyright 2008 Advanced Micro Devices, Inc.
* Copyright 2008 Red Hat Inc.
* Copyright 2009 Jerome Glisse.
*
* 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: Dave Airlie
* Alex Deucher
* Jerome Glisse
*/
#ifndef __AMDGPU_H__
#define __AMDGPU_H__
#ifdef pr_fmt
#undef pr_fmt
#endif
#define pr_fmt(fmt) "amdgpu: " fmt
#ifdef dev_fmt
#undef dev_fmt
#endif
#define dev_fmt(fmt) "amdgpu: " fmt
#include "amdgpu_ctx.h"
#include <linux/atomic.h>
#include <linux/wait.h>
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/rbtree.h>
#include <linux/hashtable.h>
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
#include <linux/dma-fence.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <drm/ttm/ttm_bo_api.h>
#include <drm/ttm/ttm_bo_driver.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_execbuf_util.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_gem.h>
#include <drm/drm_ioctl.h>
#include <drm/gpu_scheduler.h>
#include <kgd_kfd_interface.h>
#include "dm_pp_interface.h"
#include "kgd_pp_interface.h"
#include "amd_shared.h"
#include "amdgpu_mode.h"
#include "amdgpu_ih.h"
#include "amdgpu_irq.h"
#include "amdgpu_ucode.h"
#include "amdgpu_ttm.h"
#include "amdgpu_psp.h"
#include "amdgpu_gds.h"
#include "amdgpu_sync.h"
#include "amdgpu_ring.h"
#include "amdgpu_vm.h"
#include "amdgpu_dpm.h"
#include "amdgpu_acp.h"
#include "amdgpu_uvd.h"
#include "amdgpu_vce.h"
#include "amdgpu_vcn.h"
#include "amdgpu_jpeg.h"
#include "amdgpu_mn.h"
#include "amdgpu_gmc.h"
#include "amdgpu_gfx.h"
#include "amdgpu_sdma.h"
#include "amdgpu_nbio.h"
#include "amdgpu_hdp.h"
#include "amdgpu_dm.h"
#include "amdgpu_virt.h"
#include "amdgpu_csa.h"
#include "amdgpu_gart.h"
#include "amdgpu_debugfs.h"
#include "amdgpu_job.h"
#include "amdgpu_bo_list.h"
#include "amdgpu_gem.h"
#include "amdgpu_doorbell.h"
#include "amdgpu_amdkfd.h"
#include "amdgpu_smu.h"
2019-06-20 09:18:50 -06:00
#include "amdgpu_discovery.h"
#include "amdgpu_mes.h"
#include "amdgpu_umc.h"
#include "amdgpu_mmhub.h"
#include "amdgpu_gfxhub.h"
#include "amdgpu_df.h"
#include "amdgpu_smuio.h"
#include "amdgpu_hdp.h"
#define MAX_GPU_INSTANCE 16
struct amdgpu_gpu_instance
{
struct amdgpu_device *adev;
int mgpu_fan_enabled;
};
struct amdgpu_mgpu_info
{
struct amdgpu_gpu_instance gpu_ins[MAX_GPU_INSTANCE];
struct mutex mutex;
uint32_t num_gpu;
uint32_t num_dgpu;
uint32_t num_apu;
};
#define AMDGPU_MAX_TIMEOUT_PARAM_LENGTH 256
/*
* Modules parameters.
*/
extern int amdgpu_modeset;
extern int amdgpu_vram_limit;
extern int amdgpu_vis_vram_limit;
extern int amdgpu_gart_size;
extern int amdgpu_gtt_size;
drm/amdgpu: throttle buffer migrations at CS using a fixed MBps limit (v2) The old mechanism used a per-submission limit that didn't take previous submissions within the same time frame into account. It also filled VRAM slowly when VRAM usage dropped due to a big eviction or buffer deallocation. This new method establishes a configurable MBps limit that is obeyed when VRAM usage is very high. When VRAM usage is not very high, it gives the driver the freedom to fill it quickly. The result is more consistent performance. It can't keep the BO move rate low if lots of evictions are happening due to VRAM fragmentation, or if a big buffer is being migrated. The amdgpu.moverate parameter can be used to set a non-default limit. Measurements can be done to find out which amdgpu.moverate setting gives the best results. Mainly APUs and cards with small VRAM will benefit from this. For F1 2015, anything with 2 GB VRAM or less will benefit. Some benchmark results - F1 2015 (Tonga 2GB): Limit MinFPS AvgFPS Old code: 14 32.6 128 MB/s: 28 41 64 MB/s: 15.5 43 32 MB/s: 28.7 43.4 8 MB/s: 27.8 44.4 8 MB/s: 21.9 42.8 (different run) Random drops in Min FPS can still occur (due to fragmented VRAM?), but the average FPS is much better. 8 MB/s is probably a good limit for this game & the current VRAM management. The random FPS drops are still to be tackled. v2: use a spinlock Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-08-17 15:49:27 -06:00
extern int amdgpu_moverate;
extern int amdgpu_benchmarking;
extern int amdgpu_testing;
extern int amdgpu_audio;
extern int amdgpu_disp_priority;
extern int amdgpu_hw_i2c;
extern int amdgpu_pcie_gen2;
extern int amdgpu_msi;
extern char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
extern int amdgpu_dpm;
extern int amdgpu_fw_load_type;
extern int amdgpu_aspm;
extern int amdgpu_runtime_pm;
extern uint amdgpu_ip_block_mask;
extern int amdgpu_bapm;
extern int amdgpu_deep_color;
extern int amdgpu_vm_size;
extern int amdgpu_vm_block_size;
extern int amdgpu_vm_fragment_size;
extern int amdgpu_vm_fault_stop;
extern int amdgpu_vm_debug;
extern int amdgpu_vm_update_mode;
extern int amdgpu_exp_hw_support;
extern int amdgpu_dc;
extern int amdgpu_sched_jobs;
extern int amdgpu_sched_hw_submission;
extern uint amdgpu_pcie_gen_cap;
extern uint amdgpu_pcie_lane_cap;
extern uint amdgpu_cg_mask;
extern uint amdgpu_pg_mask;
extern uint amdgpu_sdma_phase_quantum;
extern char *amdgpu_disable_cu;
extern char *amdgpu_virtual_display;
extern uint amdgpu_pp_feature_mask;
extern uint amdgpu_force_long_training;
extern int amdgpu_job_hang_limit;
extern int amdgpu_lbpw;
extern int amdgpu_compute_multipipe;
extern int amdgpu_gpu_recovery;
extern int amdgpu_emu_mode;
extern uint amdgpu_smu_memory_pool_size;
extern uint amdgpu_dc_feature_mask;
extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dm_abm_level;
extern int amdgpu_backlight;
extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
extern int amdgpu_bad_page_threshold;
extern int amdgpu_async_gfx_ring;
extern int amdgpu_mcbp;
extern int amdgpu_discovery;
extern int amdgpu_mes;
extern int amdgpu_noretry;
extern int amdgpu_force_asic_type;
#ifdef CONFIG_HSA_AMD
extern int sched_policy;
extern bool debug_evictions;
extern bool no_system_mem_limit;
#else
static const int __maybe_unused sched_policy = KFD_SCHED_POLICY_HWS;
static const bool __maybe_unused debug_evictions; /* = false */
static const bool __maybe_unused no_system_mem_limit;
#endif
extern int amdgpu_tmz;
extern int amdgpu_reset_method;
#ifdef CONFIG_DRM_AMDGPU_SI
extern int amdgpu_si_support;
#endif
#ifdef CONFIG_DRM_AMDGPU_CIK
extern int amdgpu_cik_support;
#endif
extern int amdgpu_num_kcq;
#define AMDGPU_VM_MAX_NUM_CTX 4096
#define AMDGPU_SG_THRESHOLD (256*1024*1024)
#define AMDGPU_DEFAULT_GTT_SIZE_MB 3072ULL /* 3GB by default */
#define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000
#define AMDGPU_MAX_USEC_TIMEOUT 100000 /* 100 ms */
#define AMDGPU_FENCE_JIFFIES_TIMEOUT (HZ / 2)
#define AMDGPU_DEBUGFS_MAX_COMPONENTS 32
#define AMDGPUFB_CONN_LIMIT 4
#define AMDGPU_BIOS_NUM_SCRATCH 16
#define AMDGPU_VBIOS_VGA_ALLOCATION (9 * 1024 * 1024) /* reserve 8MB for vga emulator and 1 MB for FB */
/* hard reset data */
#define AMDGPU_ASIC_RESET_DATA 0x39d5e86b
/* reset flags */
#define AMDGPU_RESET_GFX (1 << 0)
#define AMDGPU_RESET_COMPUTE (1 << 1)
#define AMDGPU_RESET_DMA (1 << 2)
#define AMDGPU_RESET_CP (1 << 3)
#define AMDGPU_RESET_GRBM (1 << 4)
#define AMDGPU_RESET_DMA1 (1 << 5)
#define AMDGPU_RESET_RLC (1 << 6)
#define AMDGPU_RESET_SEM (1 << 7)
#define AMDGPU_RESET_IH (1 << 8)
#define AMDGPU_RESET_VMC (1 << 9)
#define AMDGPU_RESET_MC (1 << 10)
#define AMDGPU_RESET_DISPLAY (1 << 11)
#define AMDGPU_RESET_UVD (1 << 12)
#define AMDGPU_RESET_VCE (1 << 13)
#define AMDGPU_RESET_VCE1 (1 << 14)
/* max cursor sizes (in pixels) */
#define CIK_CURSOR_WIDTH 128
#define CIK_CURSOR_HEIGHT 128
struct amdgpu_device;
struct amdgpu_ib;
struct amdgpu_cs_parser;
struct amdgpu_job;
struct amdgpu_irq_src;
struct amdgpu_fpriv;
struct amdgpu_bo_va_mapping;
struct amdgpu_atif;
struct kfd_vm_fault_info;
struct amdgpu_hive_info;
enum amdgpu_cp_irq {
AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP = 0,
AMDGPU_CP_IRQ_GFX_ME0_PIPE1_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE1_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE2_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE3_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC2_PIPE0_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC2_PIPE1_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC2_PIPE2_EOP,
AMDGPU_CP_IRQ_COMPUTE_MEC2_PIPE3_EOP,
AMDGPU_CP_IRQ_LAST
};
enum amdgpu_thermal_irq {
AMDGPU_THERMAL_IRQ_LOW_TO_HIGH = 0,
AMDGPU_THERMAL_IRQ_HIGH_TO_LOW,
AMDGPU_THERMAL_IRQ_LAST
};
enum amdgpu_kiq_irq {
AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
AMDGPU_CP_KIQ_IRQ_LAST
};
#define MAX_KIQ_REG_WAIT 5000 /* in usecs, 5ms */
#define MAX_KIQ_REG_BAILOUT_INTERVAL 5 /* in msecs, 5ms */
#define MAX_KIQ_REG_TRY 1000
int amdgpu_device_ip_set_clockgating_state(void *dev,
enum amd_ip_block_type block_type,
enum amd_clockgating_state state);
int amdgpu_device_ip_set_powergating_state(void *dev,
enum amd_ip_block_type block_type,
enum amd_powergating_state state);
void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
u32 *flags);
int amdgpu_device_ip_wait_for_idle(struct amdgpu_device *adev,
enum amd_ip_block_type block_type);
bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
enum amd_ip_block_type block_type);
#define AMDGPU_MAX_IP_NUM 16
struct amdgpu_ip_block_status {
bool valid;
bool sw;
bool hw;
bool late_initialized;
bool hang;
};
struct amdgpu_ip_block_version {
const enum amd_ip_block_type type;
const u32 major;
const u32 minor;
const u32 rev;
const struct amd_ip_funcs *funcs;
};
#define HW_REV(_Major, _Minor, _Rev) \
((((uint32_t) (_Major)) << 16) | ((uint32_t) (_Minor) << 8) | ((uint32_t) (_Rev)))
struct amdgpu_ip_block {
struct amdgpu_ip_block_status status;
const struct amdgpu_ip_block_version *version;
};
int amdgpu_device_ip_block_version_cmp(struct amdgpu_device *adev,
enum amd_ip_block_type type,
u32 major, u32 minor);
struct amdgpu_ip_block *
amdgpu_device_ip_get_ip_block(struct amdgpu_device *adev,
enum amd_ip_block_type type);
int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
const struct amdgpu_ip_block_version *ip_block_version);
/*
* BIOS.
*/
bool amdgpu_get_bios(struct amdgpu_device *adev);
bool amdgpu_read_bios(struct amdgpu_device *adev);
/*
* Clocks
*/
#define AMDGPU_MAX_PPLL 3
struct amdgpu_clock {
struct amdgpu_pll ppll[AMDGPU_MAX_PPLL];
struct amdgpu_pll spll;
struct amdgpu_pll mpll;
/* 10 Khz units */
uint32_t default_mclk;
uint32_t default_sclk;
uint32_t default_dispclk;
uint32_t current_dispclk;
uint32_t dp_extclk;
uint32_t max_pixel_clock;
};
/* sub-allocation manager, it has to be protected by another lock.
* By conception this is an helper for other part of the driver
* like the indirect buffer or semaphore, which both have their
* locking.
*
* Principe is simple, we keep a list of sub allocation in offset
* order (first entry has offset == 0, last entry has the highest
* offset).
*
* When allocating new object we first check if there is room at
* the end total_size - (last_object_offset + last_object_size) >=
* alloc_size. If so we allocate new object there.
*
* When there is not enough room at the end, we start waiting for
* each sub object until we reach object_offset+object_size >=
* alloc_size, this object then become the sub object we return.
*
* Alignment can't be bigger than page size.
*
* Hole are not considered for allocation to keep things simple.
* Assumption is that there won't be hole (all object on same
* alignment).
*/
#define AMDGPU_SA_NUM_FENCE_LISTS 32
struct amdgpu_sa_manager {
wait_queue_head_t wq;
struct amdgpu_bo *bo;
struct list_head *hole;
struct list_head flist[AMDGPU_SA_NUM_FENCE_LISTS];
struct list_head olist;
unsigned size;
uint64_t gpu_addr;
void *cpu_ptr;
uint32_t domain;
uint32_t align;
};
/* sub-allocation buffer */
struct amdgpu_sa_bo {
struct list_head olist;
struct list_head flist;
struct amdgpu_sa_manager *manager;
unsigned soffset;
unsigned eoffset;
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
struct dma_fence *fence;
};
int amdgpu_fence_slab_init(void);
void amdgpu_fence_slab_fini(void);
/*
* IRQS.
*/
struct amdgpu_flip_work {
struct delayed_work flip_work;
struct work_struct unpin_work;
struct amdgpu_device *adev;
int crtc_id;
u32 target_vblank;
uint64_t base;
struct drm_pending_vblank_event *event;
struct amdgpu_bo *old_abo;
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
struct dma_fence *excl;
unsigned shared_count;
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
struct dma_fence **shared;
struct dma_fence_cb cb;
bool async;
};
/*
* CP & rings.
*/
struct amdgpu_ib {
struct amdgpu_sa_bo *sa_bo;
uint32_t length_dw;
uint64_t gpu_addr;
uint32_t *ptr;
uint32_t flags;
};
extern const struct drm_sched_backend_ops amdgpu_sched_ops;
/*
* file private structure
*/
struct amdgpu_fpriv {
struct amdgpu_vm vm;
struct amdgpu_bo_va *prt_va;
struct amdgpu_bo_va *csa_va;
struct mutex bo_list_lock;
struct idr bo_list_handles;
struct amdgpu_ctx_mgr ctx_mgr;
};
int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv);
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
unsigned size,
enum amdgpu_ib_pool_type pool,
struct amdgpu_ib *ib);
void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
struct dma_fence *f);
int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
struct amdgpu_ib *ibs, struct amdgpu_job *job,
struct dma_fence **f);
int amdgpu_ib_pool_init(struct amdgpu_device *adev);
void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
/*
* CS.
*/
struct amdgpu_cs_chunk {
uint32_t chunk_id;
uint32_t length_dw;
void *kdata;
};
struct amdgpu_cs_post_dep {
struct drm_syncobj *syncobj;
struct dma_fence_chain *chain;
u64 point;
};
struct amdgpu_cs_parser {
struct amdgpu_device *adev;
struct drm_file *filp;
struct amdgpu_ctx *ctx;
/* chunks */
unsigned nchunks;
struct amdgpu_cs_chunk *chunks;
/* scheduler job object */
struct amdgpu_job *job;
struct drm_sched_entity *entity;
/* buffer objects */
struct ww_acquire_ctx ticket;
struct amdgpu_bo_list *bo_list;
struct amdgpu_mn *mn;
struct amdgpu_bo_list_entry vm_pd;
struct list_head validated;
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 06:00:45 -06:00
struct dma_fence *fence;
uint64_t bytes_moved_threshold;
uint64_t bytes_moved_vis_threshold;
uint64_t bytes_moved;
uint64_t bytes_moved_vis;
/* user fence */
struct amdgpu_bo_list_entry uf_entry;
unsigned num_post_deps;
struct amdgpu_cs_post_dep *post_deps;
};
static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
uint32_t ib_idx, int idx)
{
return p->job->ibs[ib_idx].ptr[idx];
}
static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p,
uint32_t ib_idx, int idx,
uint32_t value)
{
p->job->ibs[ib_idx].ptr[idx] = value;
}
/*
* Writeback
*/
#define AMDGPU_MAX_WB 256 /* Reserve at most 256 WB slots for amdgpu-owned rings. */
struct amdgpu_wb {
struct amdgpu_bo *wb_obj;
volatile uint32_t *wb;
uint64_t gpu_addr;
u32 num_wb; /* Number of wb slots actually reserved for amdgpu. */
unsigned long used[DIV_ROUND_UP(AMDGPU_MAX_WB, BITS_PER_LONG)];
};
int amdgpu_device_wb_get(struct amdgpu_device *adev, u32 *wb);
void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb);
/*
* Benchmarking
*/
void amdgpu_benchmark(struct amdgpu_device *adev, int test_number);
/*
* Testing
*/
void amdgpu_test_moves(struct amdgpu_device *adev);
/*
* ASIC specific register table accessible by UMD
*/
struct amdgpu_allowed_register_entry {
uint32_t reg_offset;
bool grbm_indexed;
};
enum amd_reset_method {
AMD_RESET_METHOD_LEGACY = 0,
AMD_RESET_METHOD_MODE0,
AMD_RESET_METHOD_MODE1,
AMD_RESET_METHOD_MODE2,
AMD_RESET_METHOD_BACO,
AMD_RESET_METHOD_PCI,
};
/*
* ASIC specific functions.
*/
struct amdgpu_asic_funcs {
bool (*read_disabled_bios)(struct amdgpu_device *adev);
bool (*read_bios_from_rom)(struct amdgpu_device *adev,
u8 *bios, u32 length_bytes);
int (*read_register)(struct amdgpu_device *adev, u32 se_num,
u32 sh_num, u32 reg_offset, u32 *value);
void (*set_vga_state)(struct amdgpu_device *adev, bool state);
int (*reset)(struct amdgpu_device *adev);
enum amd_reset_method (*reset_method)(struct amdgpu_device *adev);
/* get the reference clock */
u32 (*get_xclk)(struct amdgpu_device *adev);
/* MM block clocks */
int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
/* static power management */
int (*get_pcie_lanes)(struct amdgpu_device *adev);
void (*set_pcie_lanes)(struct amdgpu_device *adev, int lanes);
/* get config memsize register */
u32 (*get_config_memsize)(struct amdgpu_device *adev);
/* flush hdp write queue */
void (*flush_hdp)(struct amdgpu_device *adev, struct amdgpu_ring *ring);
/* invalidate hdp read cache */
void (*invalidate_hdp)(struct amdgpu_device *adev,
struct amdgpu_ring *ring);
/* check if the asic needs a full reset of if soft reset will work */
bool (*need_full_reset)(struct amdgpu_device *adev);
/* initialize doorbell layout for specific asic*/
void (*init_doorbell_index)(struct amdgpu_device *adev);
/* PCIe bandwidth usage */
void (*get_pcie_usage)(struct amdgpu_device *adev, uint64_t *count0,
uint64_t *count1);
/* do we need to reset the asic at init time (e.g., kexec) */
bool (*need_reset_on_init)(struct amdgpu_device *adev);
/* PCIe replay counter */
uint64_t (*get_pcie_replay_count)(struct amdgpu_device *adev);
/* device supports BACO */
bool (*supports_baco)(struct amdgpu_device *adev);
/* pre asic_init quirks */
void (*pre_asic_init)(struct amdgpu_device *adev);
/* enter/exit umd stable pstate */
int (*update_umd_stable_pstate)(struct amdgpu_device *adev, bool enter);
};
/*
* IOCTL.
*/
int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
/* VRAM scratch page for HDP bug, default vram page */
struct amdgpu_vram_scratch {
struct amdgpu_bo *robj;
volatile uint32_t *ptr;
u64 gpu_addr;
};
/*
* ACPI
*/
struct amdgpu_atcs_functions {
bool get_ext_state;
bool pcie_perf_req;
bool pcie_dev_rdy;
bool pcie_bus_width;
};
struct amdgpu_atcs {
struct amdgpu_atcs_functions functions;
};
/*
* CGS
*/
struct cgs_device *amdgpu_cgs_create_device(struct amdgpu_device *adev);
void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
/*
* Core structure, functions and helpers.
*/
typedef uint32_t (*amdgpu_rreg_t)(struct amdgpu_device*, uint32_t);
typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
typedef uint64_t (*amdgpu_rreg64_t)(struct amdgpu_device*, uint32_t);
typedef void (*amdgpu_wreg64_t)(struct amdgpu_device*, uint32_t, uint64_t);
typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
struct amdgpu_mmio_remap {
u32 reg_offset;
resource_size_t bus_addr;
};
/* Define the HW IP blocks will be used in driver , add more if necessary */
enum amd_hw_ip_block_type {
GC_HWIP = 1,
HDP_HWIP,
SDMA0_HWIP,
SDMA1_HWIP,
SDMA2_HWIP,
SDMA3_HWIP,
SDMA4_HWIP,
SDMA5_HWIP,
SDMA6_HWIP,
SDMA7_HWIP,
MMHUB_HWIP,
ATHUB_HWIP,
NBIO_HWIP,
MP0_HWIP,
MP1_HWIP,
UVD_HWIP,
VCN_HWIP = UVD_HWIP,
JPEG_HWIP = VCN_HWIP,
VCE_HWIP,
DF_HWIP,
DCE_HWIP,
OSSSYS_HWIP,
SMUIO_HWIP,
PWR_HWIP,
NBIF_HWIP,
THM_HWIP,
CLK_HWIP,
UMC_HWIP,
RSMU_HWIP,
MAX_HWIP
};
#define HWIP_MAX_INSTANCE 8
struct amd_powerplay {
void *pp_handle;
const struct amd_pm_funcs *pp_funcs;
};
/* polaris10 kickers */
#define ASICID_IS_P20(did, rid) (((did == 0x67DF) && \
((rid == 0xE3) || \
(rid == 0xE4) || \
(rid == 0xE5) || \
(rid == 0xE7) || \
(rid == 0xEF))) || \
((did == 0x6FDF) && \
((rid == 0xE7) || \
(rid == 0xEF) || \
(rid == 0xFF))))
#define ASICID_IS_P30(did, rid) ((did == 0x67DF) && \
((rid == 0xE1) || \
(rid == 0xF7)))
/* polaris11 kickers */
#define ASICID_IS_P21(did, rid) (((did == 0x67EF) && \
((rid == 0xE0) || \
(rid == 0xE5))) || \
((did == 0x67FF) && \
((rid == 0xCF) || \
(rid == 0xEF) || \
(rid == 0xFF))))
#define ASICID_IS_P31(did, rid) ((did == 0x67EF) && \
((rid == 0xE2)))
/* polaris12 kickers */
#define ASICID_IS_P23(did, rid) (((did == 0x6987) && \
((rid == 0xC0) || \
(rid == 0xC1) || \
(rid == 0xC3) || \
(rid == 0xC7))) || \
((did == 0x6981) && \
((rid == 0x00) || \
(rid == 0x01) || \
(rid == 0x10))))
#define AMDGPU_RESET_MAGIC_NUM 64
#define AMDGPU_MAX_DF_PERFMONS 4
struct amdgpu_device {
struct device *dev;
struct pci_dev *pdev;
struct drm_device ddev;
#ifdef CONFIG_DRM_AMD_ACP
struct amdgpu_acp acp;
#endif
struct amdgpu_hive_info *hive;
/* ASIC */
enum amd_asic_type asic_type;
uint32_t family;
uint32_t rev_id;
uint32_t external_rev_id;
unsigned long flags;
unsigned long apu_flags;
int usec_timeout;
const struct amdgpu_asic_funcs *asic_funcs;
bool shutdown;
bool need_swiotlb;
bool accel_working;
struct notifier_block acpi_nb;
struct amdgpu_i2c_chan *i2c_bus[AMDGPU_MAX_I2C_BUS];
struct amdgpu_debugfs debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
unsigned debugfs_count;
#if defined(CONFIG_DEBUG_FS)
struct dentry *debugfs_preempt;
struct dentry *debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
#endif
struct amdgpu_atif *atif;
struct amdgpu_atcs atcs;
struct mutex srbm_mutex;
/* GRBM index mutex. Protects concurrent access to GRBM index */
struct mutex grbm_idx_mutex;
struct dev_pm_domain vga_pm_domain;
bool have_disp_power_ref;
bool have_atomics_support;
/* BIOS */
bool is_atom_fw;
uint8_t *bios;
uint32_t bios_size;
uint32_t bios_scratch_reg_offset;
uint32_t bios_scratch[AMDGPU_BIOS_NUM_SCRATCH];
/* Register/doorbell mmio */
resource_size_t rmmio_base;
resource_size_t rmmio_size;
void __iomem *rmmio;
/* protects concurrent MM_INDEX/DATA based register access */
spinlock_t mmio_idx_lock;
struct amdgpu_mmio_remap rmmio_remap;
/* protects concurrent SMC based register access */
spinlock_t smc_idx_lock;
amdgpu_rreg_t smc_rreg;
amdgpu_wreg_t smc_wreg;
/* protects concurrent PCIE register access */
spinlock_t pcie_idx_lock;
amdgpu_rreg_t pcie_rreg;
amdgpu_wreg_t pcie_wreg;
amdgpu_rreg_t pciep_rreg;
amdgpu_wreg_t pciep_wreg;
amdgpu_rreg64_t pcie_rreg64;
amdgpu_wreg64_t pcie_wreg64;
/* protects concurrent UVD register access */
spinlock_t uvd_ctx_idx_lock;
amdgpu_rreg_t uvd_ctx_rreg;
amdgpu_wreg_t uvd_ctx_wreg;
/* protects concurrent DIDT register access */
spinlock_t didt_idx_lock;
amdgpu_rreg_t didt_rreg;
amdgpu_wreg_t didt_wreg;
/* protects concurrent gc_cac register access */
spinlock_t gc_cac_idx_lock;
amdgpu_rreg_t gc_cac_rreg;
amdgpu_wreg_t gc_cac_wreg;
/* protects concurrent se_cac register access */
spinlock_t se_cac_idx_lock;
amdgpu_rreg_t se_cac_rreg;
amdgpu_wreg_t se_cac_wreg;
/* protects concurrent ENDPOINT (audio) register access */
spinlock_t audio_endpt_idx_lock;
amdgpu_block_rreg_t audio_endpt_rreg;
amdgpu_block_wreg_t audio_endpt_wreg;
void __iomem *rio_mem;
resource_size_t rio_mem_size;
struct amdgpu_doorbell doorbell;
/* clock/pll info */
struct amdgpu_clock clock;
/* MC */
struct amdgpu_gmc gmc;
struct amdgpu_gart gart;
dma_addr_t dummy_page_addr;
struct amdgpu_vm_manager vm_manager;
struct amdgpu_vmhub vmhub[AMDGPU_MAX_VMHUBS];
unsigned num_vmhubs;
/* memory management */
struct amdgpu_mman mman;
struct amdgpu_vram_scratch vram_scratch;
struct amdgpu_wb wb;
atomic64_t num_bytes_moved;
atomic64_t num_evictions;
atomic64_t num_vram_cpu_page_faults;
atomic_t gpu_reset_counter;
atomic_t vram_lost_counter;
drm/amdgpu: throttle buffer migrations at CS using a fixed MBps limit (v2) The old mechanism used a per-submission limit that didn't take previous submissions within the same time frame into account. It also filled VRAM slowly when VRAM usage dropped due to a big eviction or buffer deallocation. This new method establishes a configurable MBps limit that is obeyed when VRAM usage is very high. When VRAM usage is not very high, it gives the driver the freedom to fill it quickly. The result is more consistent performance. It can't keep the BO move rate low if lots of evictions are happening due to VRAM fragmentation, or if a big buffer is being migrated. The amdgpu.moverate parameter can be used to set a non-default limit. Measurements can be done to find out which amdgpu.moverate setting gives the best results. Mainly APUs and cards with small VRAM will benefit from this. For F1 2015, anything with 2 GB VRAM or less will benefit. Some benchmark results - F1 2015 (Tonga 2GB): Limit MinFPS AvgFPS Old code: 14 32.6 128 MB/s: 28 41 64 MB/s: 15.5 43 32 MB/s: 28.7 43.4 8 MB/s: 27.8 44.4 8 MB/s: 21.9 42.8 (different run) Random drops in Min FPS can still occur (due to fragmented VRAM?), but the average FPS is much better. 8 MB/s is probably a good limit for this game & the current VRAM management. The random FPS drops are still to be tackled. v2: use a spinlock Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-08-17 15:49:27 -06:00
/* data for buffer migration throttling */
struct {
spinlock_t lock;
s64 last_update_us;
s64 accum_us; /* accumulated microseconds */
s64 accum_us_vis; /* for visible VRAM */
drm/amdgpu: throttle buffer migrations at CS using a fixed MBps limit (v2) The old mechanism used a per-submission limit that didn't take previous submissions within the same time frame into account. It also filled VRAM slowly when VRAM usage dropped due to a big eviction or buffer deallocation. This new method establishes a configurable MBps limit that is obeyed when VRAM usage is very high. When VRAM usage is not very high, it gives the driver the freedom to fill it quickly. The result is more consistent performance. It can't keep the BO move rate low if lots of evictions are happening due to VRAM fragmentation, or if a big buffer is being migrated. The amdgpu.moverate parameter can be used to set a non-default limit. Measurements can be done to find out which amdgpu.moverate setting gives the best results. Mainly APUs and cards with small VRAM will benefit from this. For F1 2015, anything with 2 GB VRAM or less will benefit. Some benchmark results - F1 2015 (Tonga 2GB): Limit MinFPS AvgFPS Old code: 14 32.6 128 MB/s: 28 41 64 MB/s: 15.5 43 32 MB/s: 28.7 43.4 8 MB/s: 27.8 44.4 8 MB/s: 21.9 42.8 (different run) Random drops in Min FPS can still occur (due to fragmented VRAM?), but the average FPS is much better. 8 MB/s is probably a good limit for this game & the current VRAM management. The random FPS drops are still to be tackled. v2: use a spinlock Signed-off-by: Marek Olšák <marek.olsak@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-08-17 15:49:27 -06:00
u32 log2_max_MBps;
} mm_stats;
/* display */
bool enable_virtual_display;
struct amdgpu_mode_info mode_info;
/* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */
struct work_struct hotplug_work;
struct amdgpu_irq_src crtc_irq;
struct amdgpu_irq_src vline0_irq;
struct amdgpu_irq_src vupdate_irq;
struct amdgpu_irq_src pageflip_irq;
struct amdgpu_irq_src hpd_irq;
/* rings */
u64 fence_context;
unsigned num_rings;
struct amdgpu_ring *rings[AMDGPU_MAX_RINGS];
bool ib_pool_ready;
struct amdgpu_sa_manager ib_pools[AMDGPU_IB_POOL_MAX];
struct amdgpu_sched gpu_sched[AMDGPU_HW_IP_NUM][AMDGPU_RING_PRIO_MAX];
/* interrupts */
struct amdgpu_irq irq;
/* powerplay */
struct amd_powerplay powerplay;
bool pp_force_state_enabled;
/* smu */
struct smu_context smu;
/* dpm */
struct amdgpu_pm pm;
u32 cg_flags;
u32 pg_flags;
/* nbio */
struct amdgpu_nbio nbio;
/* hdp */
struct amdgpu_hdp hdp;
/* smuio */
struct amdgpu_smuio smuio;
/* mmhub */
struct amdgpu_mmhub mmhub;
/* gfxhub */
struct amdgpu_gfxhub gfxhub;
/* gfx */
struct amdgpu_gfx gfx;
/* sdma */
struct amdgpu_sdma sdma;
/* uvd */
struct amdgpu_uvd uvd;
/* vce */
struct amdgpu_vce vce;
/* vcn */
struct amdgpu_vcn vcn;
/* jpeg */
struct amdgpu_jpeg jpeg;
/* firmwares */
struct amdgpu_firmware firmware;
/* PSP */
struct psp_context psp;
/* GDS */
struct amdgpu_gds gds;
/* KFD */
struct amdgpu_kfd_dev kfd;
/* UMC */
struct amdgpu_umc umc;
/* display related functionality */
struct amdgpu_display_manager dm;
/* mes */
bool enable_mes;
struct amdgpu_mes mes;
/* df */
struct amdgpu_df df;
struct amdgpu_ip_block ip_blocks[AMDGPU_MAX_IP_NUM];
int num_ip_blocks;
struct mutex mn_lock;
DECLARE_HASHTABLE(mn_hash, 7);
/* tracking pinned memory */
atomic64_t vram_pin_size;
atomic64_t visible_pin_size;
atomic64_t gart_pin_size;
/* soc15 register offset based on ip, instance and segment */
uint32_t *reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
/* delayed work_func for deferring clockgating during resume */
struct delayed_work delayed_init_work;
struct amdgpu_virt virt;
/* link all shadow bo */
struct list_head shadow_list;
struct mutex shadow_list_lock;
/* record hw reset is performed */
bool has_hw_reset;
u8 reset_magic[AMDGPU_RESET_MAGIC_NUM];
/* s3/s4 mask */
bool in_suspend;
bool in_s3;
bool in_s4;
bool in_s0ix;
atomic_t in_gpu_reset;
enum pp_mp1_state mp1_state;
struct rw_semaphore reset_sem;
struct amdgpu_doorbell_index doorbell_index;
struct mutex notifier_lock;
int asic_reset_res;
struct work_struct xgmi_reset_work;
long gfx_timeout;
long sdma_timeout;
long video_timeout;
long compute_timeout;
uint64_t unique_id;
uint64_t df_perfmon_config_assign_mask[AMDGPU_MAX_DF_PERFMONS];
/* enable runtime pm on the device */
bool runpm;
bool in_runpm;
bool has_pr3;
drm/amdgpu: not remove sysfs if not create sysfs When load amdgpu failed before create pm_sysfs and ucode_sysfs, the pm_sysfs and ucode_sysfs should not be removed. Otherwise, there will be warning call trace just like below. [ 24.836386] [drm] VCE initialized successfully. [ 24.841352] amdgpu 0000:00:07.0: amdgpu_device_ip_init failed [ 25.370383] amdgpu 0000:00:07.0: Fatal error during GPU init [ 25.889575] [drm] amdgpu: finishing device. [ 26.069128] amdgpu 0000:00:07.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring kiq_2.1.0 test failed (-110) [ 26.070110] [drm:gfx_v9_0_hw_fini [amdgpu]] *ERROR* KCQ disable failed [ 26.200309] [TTM] Finalizing pool allocator [ 26.200314] [TTM] Finalizing DMA pool allocator [ 26.200349] [TTM] Zone kernel: Used memory at exit: 0 KiB [ 26.200351] [TTM] Zone dma32: Used memory at exit: 0 KiB [ 26.200353] [drm] amdgpu: ttm finalized [ 26.205329] ------------[ cut here ]------------ [ 26.205330] sysfs group 'fw_version' not found for kobject '0000:00:07.0' [ 26.205347] WARNING: CPU: 0 PID: 1228 at fs/sysfs/group.c:256 sysfs_remove_group+0x80/0x90 [ 26.205348] Modules linked in: amdgpu(OE+) gpu_sched(OE) ttm(OE) drm_kms_helper(OE) drm(OE) i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs lockd grace fscache binfmt_misc snd_hda_codec_generic ledtrig_audio crct10dif_pclmul snd_hda_intel crc32_pclmul snd_hda_codec ghash_clmulni_intel snd_hda_core snd_hwdep snd_pcm snd_timer input_leds snd joydev soundcore serio_raw pcspkr evbug aesni_intel aes_x86_64 crypto_simd cryptd mac_hid glue_helper sunrpc ip_tables x_tables autofs4 8139too psmouse 8139cp mii i2c_piix4 pata_acpi floppy [ 26.205369] CPU: 0 PID: 1228 Comm: modprobe Tainted: G OE 5.2.0-rc1 #1 [ 26.205370] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 26.205372] RIP: 0010:sysfs_remove_group+0x80/0x90 [ 26.205374] Code: e8 35 b9 ff ff 5b 41 5c 41 5d 5d c3 48 89 df e8 f6 b5 ff ff eb c6 49 8b 55 00 49 8b 34 24 48 c7 c7 48 7a 70 98 e8 60 63 d3 ff <0f> 0b eb d7 66 90 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 [ 26.205375] RSP: 0018:ffffbee242b0b908 EFLAGS: 00010282 [ 26.205376] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000006 [ 26.205377] RDX: 0000000000000007 RSI: 0000000000000092 RDI: ffff97ad6f817380 [ 26.205377] RBP: ffffbee242b0b920 R08: ffffffff98f520c4 R09: 00000000000002b3 [ 26.205378] R10: ffffbee242b0b8f8 R11: 00000000000002b3 R12: ffffffffc0e58240 [ 26.205379] R13: ffff97ad6d1fe0b0 R14: ffff97ad4db954c8 R15: ffff97ad4db7fff0 [ 26.205380] FS: 00007ff3d8a1c4c0(0000) GS:ffff97ad6f800000(0000) knlGS:0000000000000000 [ 26.205381] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 26.205381] CR2: 00007f9b2ef1df04 CR3: 000000042aab8001 CR4: 00000000003606f0 [ 26.205384] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 26.205385] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 26.205385] Call Trace: [ 26.205461] amdgpu_ucode_sysfs_fini+0x18/0x20 [amdgpu] [ 26.205518] amdgpu_device_fini+0x3b4/0x560 [amdgpu] [ 26.205573] amdgpu_driver_unload_kms+0x4f/0xa0 [amdgpu] [ 26.205623] amdgpu_driver_load_kms+0xcd/0x250 [amdgpu] [ 26.205637] drm_dev_register+0x12b/0x1c0 [drm] [ 26.205695] amdgpu_pci_probe+0x12a/0x1e0 [amdgpu] [ 26.205699] local_pci_probe+0x47/0xa0 [ 26.205701] pci_device_probe+0x106/0x1b0 [ 26.205704] really_probe+0x21a/0x3f0 [ 26.205706] driver_probe_device+0x11c/0x140 [ 26.205707] device_driver_attach+0x58/0x60 [ 26.205709] __driver_attach+0xc3/0x140 Signed-off-by: Yintian Tao <yttao@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Nirmoy Das <nirmoy.das@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-11-29 01:05:55 -07:00
bool pm_sysfs_en;
bool ucode_sysfs_en;
/* Chip product information */
char product_number[16];
char product_name[32];
char serial[20];
drm/amdgpu: Add autodump debugfs node for gpu reset v8 When GPU got timeout, it would notify an interested part of an opportunity to dump info before actual GPU reset. A usermode app would open 'autodump' node under debugfs system and poll() for readable/writable. When a GPU reset is due, amdgpu would notify usermode app through wait_queue_head and give it 10 minutes to dump info. After usermode app has done its work, this 'autodump' node is closed. On node closure, amdgpu gets to know the dump is done through the completion that is triggered in release(). There is no write or read callback because necessary info can be obtained through dmesg and umr. Messages back and forth between usermode app and amdgpu are unnecessary. v2: (1) changed 'registered' to 'app_listening' (2) add a mutex in open() to prevent race condition v3 (chk): grab the reset lock to avoid race in autodump_open, rename debugfs file to amdgpu_autodump, provide autodump_read as well, style and code cleanups v4: add 'bool app_listening' to differentiate situations, so that the node can be reopened; also, there is no need to wait for completion when no app is waiting for a dump. v5: change 'bool app_listening' to 'enum amdgpu_autodump_state' add 'app_state_mutex' for race conditions: (1)Only 1 user can open this file node (2)wait_dump() can only take effect after poll() executed. (3)eliminated the race condition between release() and wait_dump() v6: removed 'enum amdgpu_autodump_state' and 'app_state_mutex' removed state checking in amdgpu_debugfs_wait_dump Improve on top of version 3 so that the node can be reopened. v7: move reinit_completion into open() so that only one user can open it. v8: remove complete_all() from amdgpu_debugfs_wait_dump(). Signed-off-by: Jiange Zhao <Jiange.Zhao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-04-26 03:57:00 -06:00
struct amdgpu_autodump autodump;
atomic_t throttling_logging_enabled;
struct ratelimit_state throttling_logging_rs;
uint32_t ras_features;
bool in_pci_err_recovery;
struct pci_saved_state *pci_state;
};
static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
{
return container_of(ddev, struct amdgpu_device, ddev);
}
static inline struct drm_device *adev_to_drm(struct amdgpu_device *adev)
{
return &adev->ddev;
}
static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
{
return container_of(bdev, struct amdgpu_device, mman.bdev);
}
int amdgpu_device_init(struct amdgpu_device *adev,
uint32_t flags);
void amdgpu_device_fini(struct amdgpu_device *adev);
int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
uint32_t *buf, size_t size, bool write);
uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
uint32_t reg, uint32_t acc_flags);
void amdgpu_device_wreg(struct amdgpu_device *adev,
uint32_t reg, uint32_t v,
uint32_t acc_flags);
void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
uint32_t reg, uint32_t v);
void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset);
u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg);
void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v);
u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev,
u32 pcie_index, u32 pcie_data,
u32 reg_addr);
u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev,
u32 pcie_index, u32 pcie_data,
u32 reg_addr);
void amdgpu_device_indirect_wreg(struct amdgpu_device *adev,
u32 pcie_index, u32 pcie_data,
u32 reg_addr, u32 reg_data);
void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
u32 pcie_index, u32 pcie_data,
u32 reg_addr, u64 reg_data);
bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type);
bool amdgpu_device_has_dc_support(struct amdgpu_device *adev);
int emu_soc_asic_init(struct amdgpu_device *adev);
/*
* Registers read & write functions.
*/
#define AMDGPU_REGS_NO_KIQ (1<<1)
#define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
#define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
#define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg))
#define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v))
#define RREG8(reg) amdgpu_mm_rreg8(adev, (reg))
#define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v))
#define RREG32(reg) amdgpu_device_rreg(adev, (reg), 0)
#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_device_rreg(adev, (reg), 0))
#define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0)
#define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
#define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
#define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg))
#define WREG32_PCIE(reg, v) adev->pcie_wreg(adev, (reg), (v))
#define RREG32_PCIE_PORT(reg) adev->pciep_rreg(adev, (reg))
#define WREG32_PCIE_PORT(reg, v) adev->pciep_wreg(adev, (reg), (v))
#define RREG64_PCIE(reg) adev->pcie_rreg64(adev, (reg))
#define WREG64_PCIE(reg, v) adev->pcie_wreg64(adev, (reg), (v))
#define RREG32_SMC(reg) adev->smc_rreg(adev, (reg))
#define WREG32_SMC(reg, v) adev->smc_wreg(adev, (reg), (v))
#define RREG32_UVD_CTX(reg) adev->uvd_ctx_rreg(adev, (reg))
#define WREG32_UVD_CTX(reg, v) adev->uvd_ctx_wreg(adev, (reg), (v))
#define RREG32_DIDT(reg) adev->didt_rreg(adev, (reg))
#define WREG32_DIDT(reg, v) adev->didt_wreg(adev, (reg), (v))
#define RREG32_GC_CAC(reg) adev->gc_cac_rreg(adev, (reg))
#define WREG32_GC_CAC(reg, v) adev->gc_cac_wreg(adev, (reg), (v))
#define RREG32_SE_CAC(reg) adev->se_cac_rreg(adev, (reg))
#define WREG32_SE_CAC(reg, v) adev->se_cac_wreg(adev, (reg), (v))
#define RREG32_AUDIO_ENDPT(block, reg) adev->audio_endpt_rreg(adev, (block), (reg))
#define WREG32_AUDIO_ENDPT(block, reg, v) adev->audio_endpt_wreg(adev, (block), (reg), (v))
#define WREG32_P(reg, val, mask) \
do { \
uint32_t tmp_ = RREG32(reg); \
tmp_ &= (mask); \
tmp_ |= ((val) & ~(mask)); \
WREG32(reg, tmp_); \
} while (0)
#define WREG32_AND(reg, and) WREG32_P(reg, 0, and)
#define WREG32_OR(reg, or) WREG32_P(reg, or, ~(or))
#define WREG32_PLL_P(reg, val, mask) \
do { \
uint32_t tmp_ = RREG32_PLL(reg); \
tmp_ &= (mask); \
tmp_ |= ((val) & ~(mask)); \
WREG32_PLL(reg, tmp_); \
} while (0)
#define WREG32_SMC_P(_Reg, _Val, _Mask) \
do { \
u32 tmp = RREG32_SMC(_Reg); \
tmp &= (_Mask); \
tmp |= ((_Val) & ~(_Mask)); \
WREG32_SMC(_Reg, tmp); \
} while (0)
#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_device_rreg((adev), (reg), false))
#define RREG32_IO(reg) amdgpu_io_rreg(adev, (reg))
#define WREG32_IO(reg, v) amdgpu_io_wreg(adev, (reg), (v))
#define REG_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
#define REG_FIELD_MASK(reg, field) reg##__##field##_MASK
#define REG_SET_FIELD(orig_val, reg, field, field_val) \
(((orig_val) & ~REG_FIELD_MASK(reg, field)) | \
(REG_FIELD_MASK(reg, field) & ((field_val) << REG_FIELD_SHIFT(reg, field))))
#define REG_GET_FIELD(value, reg, field) \
(((value) & REG_FIELD_MASK(reg, field)) >> REG_FIELD_SHIFT(reg, field))
#define WREG32_FIELD(reg, field, val) \
WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
#define WREG32_FIELD_OFFSET(reg, offset, field, val) \
WREG32(mm##reg + offset, (RREG32(mm##reg + offset) & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
/*
* BIOS helpers.
*/
#define RBIOS8(i) (adev->bios[i])
#define RBIOS16(i) (RBIOS8(i) | (RBIOS8((i)+1) << 8))
#define RBIOS32(i) ((RBIOS16(i)) | (RBIOS16((i)+2) << 16))
/*
* ASICs macro.
*/
#define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
#define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
#define amdgpu_asic_reset_method(adev) (adev)->asic_funcs->reset_method((adev))
#define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
#define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
#define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
#define amdgpu_get_pcie_lanes(adev) (adev)->asic_funcs->get_pcie_lanes((adev))
#define amdgpu_set_pcie_lanes(adev, l) (adev)->asic_funcs->set_pcie_lanes((adev), (l))
#define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev))
#define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
#define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
#define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v)))
#define amdgpu_asic_get_config_memsize(adev) (adev)->asic_funcs->get_config_memsize((adev))
#define amdgpu_asic_flush_hdp(adev, r) \
((adev)->asic_funcs->flush_hdp ? (adev)->asic_funcs->flush_hdp((adev), (r)) : (adev)->hdp.funcs->flush_hdp((adev), (r)))
#define amdgpu_asic_invalidate_hdp(adev, r) \
((adev)->asic_funcs->invalidate_hdp ? (adev)->asic_funcs->invalidate_hdp((adev), (r)) : (adev)->hdp.funcs->invalidate_hdp((adev), (r)))
#define amdgpu_asic_need_full_reset(adev) (adev)->asic_funcs->need_full_reset((adev))
#define amdgpu_asic_init_doorbell_index(adev) (adev)->asic_funcs->init_doorbell_index((adev))
#define amdgpu_asic_get_pcie_usage(adev, cnt0, cnt1) ((adev)->asic_funcs->get_pcie_usage((adev), (cnt0), (cnt1)))
#define amdgpu_asic_need_reset_on_init(adev) (adev)->asic_funcs->need_reset_on_init((adev))
#define amdgpu_asic_get_pcie_replay_count(adev) ((adev)->asic_funcs->get_pcie_replay_count((adev)))
#define amdgpu_asic_supports_baco(adev) (adev)->asic_funcs->supports_baco((adev))
#define amdgpu_asic_pre_asic_init(adev) (adev)->asic_funcs->pre_asic_init((adev))
#define amdgpu_asic_update_umd_stable_pstate(adev, enter) \
((adev)->asic_funcs->update_umd_stable_pstate ? (adev)->asic_funcs->update_umd_stable_pstate((adev), (enter)) : 0)
#define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
/* Common functions */
bool amdgpu_device_has_job_running(struct amdgpu_device *adev);
bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
struct amdgpu_job* job);
void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
int amdgpu_device_pci_reset(struct amdgpu_device *adev);
bool amdgpu_device_need_post(struct amdgpu_device *adev);
void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
u64 num_vis_bytes);
int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev);
void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
const u32 *registers,
const u32 array_size);
bool amdgpu_device_supports_atpx(struct drm_device *dev);
bool amdgpu_device_supports_boco(struct drm_device *dev);
bool amdgpu_device_supports_baco(struct drm_device *dev);
bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
struct amdgpu_device *peer_adev);
int amdgpu_device_baco_enter(struct drm_device *dev);
int amdgpu_device_baco_exit(struct drm_device *dev);
/* atpx handler */
#if defined(CONFIG_VGA_SWITCHEROO)
void amdgpu_register_atpx_handler(void);
void amdgpu_unregister_atpx_handler(void);
bool amdgpu_has_atpx_dgpu_power_cntl(void);
bool amdgpu_is_atpx_hybrid(void);
bool amdgpu_atpx_dgpu_req_power_for_displays(void);
bool amdgpu_has_atpx(void);
#else
static inline void amdgpu_register_atpx_handler(void) {}
static inline void amdgpu_unregister_atpx_handler(void) {}
static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; }
static inline bool amdgpu_is_atpx_hybrid(void) { return false; }
static inline bool amdgpu_atpx_dgpu_req_power_for_displays(void) { return false; }
static inline bool amdgpu_has_atpx(void) { return false; }
#endif
#if defined(CONFIG_VGA_SWITCHEROO) && defined(CONFIG_ACPI)
void *amdgpu_atpx_get_dhandle(void);
#else
static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
#endif
/*
* KMS
*/
extern const struct drm_ioctl_desc amdgpu_ioctls_kms[];
extern const int amdgpu_max_kms_ioctl;
int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags);
void amdgpu_driver_unload_kms(struct drm_device *dev);
void amdgpu_driver_lastclose_kms(struct drm_device *dev);
int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
void amdgpu_driver_postclose_kms(struct drm_device *dev,
struct drm_file *file_priv);
int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc);
int amdgpu_enable_vblank_kms(struct drm_crtc *crtc);
void amdgpu_disable_vblank_kms(struct drm_crtc *crtc);
long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg);
int amdgpu_info_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp);
/*
* functions used by amdgpu_encoder.c
*/
struct amdgpu_afmt_acr {
u32 clock;
int n_32khz;
int cts_32khz;
int n_44_1khz;
int cts_44_1khz;
int n_48khz;
int cts_48khz;
};
struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock);
/* amdgpu_acpi.c */
#if defined(CONFIG_ACPI)
int amdgpu_acpi_init(struct amdgpu_device *adev);
void amdgpu_acpi_fini(struct amdgpu_device *adev);
bool amdgpu_acpi_is_pcie_performance_request_supported(struct amdgpu_device *adev);
int amdgpu_acpi_pcie_performance_request(struct amdgpu_device *adev,
u8 perf_req, bool advertise);
int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
void amdgpu_acpi_get_backlight_caps(struct amdgpu_device *adev,
struct amdgpu_dm_backlight_caps *caps);
bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev);
#else
static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
static inline bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { return false; }
#endif
int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
uint64_t addr, struct amdgpu_bo **bo,
struct amdgpu_bo_va_mapping **mapping);
#if defined(CONFIG_DRM_AMD_DC)
int amdgpu_dm_display_resume(struct amdgpu_device *adev );
#else
static inline int amdgpu_dm_display_resume(struct amdgpu_device *adev) { return 0; }
#endif
void amdgpu_register_gpu_instance(struct amdgpu_device *adev);
void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev);
pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev,
pci_channel_state_t state);
pci_ers_result_t amdgpu_pci_mmio_enabled(struct pci_dev *pdev);
pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev);
void amdgpu_pci_resume(struct pci_dev *pdev);
bool amdgpu_device_cache_pci_state(struct pci_dev *pdev);
bool amdgpu_device_load_pci_state(struct pci_dev *pdev);
#include "amdgpu_object.h"
static inline bool amdgpu_is_tmz(struct amdgpu_device *adev)
{
return adev->gmc.tmz_enabled;
}
static inline int amdgpu_in_reset(struct amdgpu_device *adev)
{
return atomic_read(&adev->in_gpu_reset);
}
#endif