diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_drv.h')
-rw-r--r-- | drivers/gpu/drm/i915/i915_drv.h | 1218 |
1 files changed, 553 insertions, 665 deletions
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 21f9390..4dd307e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -61,6 +61,7 @@ #include "i915_gem.h" #include "i915_gem_gtt.h" #include "i915_gem_render_state.h" +#include "i915_gem_request.h" #include "intel_gvt.h" @@ -69,7 +70,7 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20160711" +#define DRIVER_DATE "20160919" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@ -401,7 +402,7 @@ struct drm_i915_file_private { unsigned boosts; } rps; - unsigned int bsd_ring; + unsigned int bsd_engine; }; /* Used by dp and fdi links */ @@ -431,8 +432,6 @@ void intel_link_compute_m_n(int bpp, int nlanes, #define DRIVER_MINOR 6 #define DRIVER_PATCHLEVEL 0 -#define WATCH_LISTS 0 - struct opregion_header; struct opregion_acpi; struct opregion_swsci; @@ -456,15 +455,21 @@ struct intel_opregion { struct intel_overlay; struct intel_overlay_error_state; -#define I915_FENCE_REG_NONE -1 -#define I915_MAX_NUM_FENCES 32 -/* 32 fences + sign bit for FENCE_REG_NONE */ -#define I915_MAX_NUM_FENCE_BITS 6 - struct drm_i915_fence_reg { - struct list_head lru_list; - struct drm_i915_gem_object *obj; + struct list_head link; + struct drm_i915_private *i915; + struct i915_vma *vma; int pin_count; + int id; + /** + * Whether the tiling parameters for the currently + * associated fence register have changed. Note that + * for the purposes of tracking tiling changes we also + * treat the unfenced register, the register slot that + * the object occupies whilst it executes a fenced + * command (such as BLT on gen2/3), as a "fence". + */ + bool dirty; }; struct sdvo_device_mapping { @@ -476,130 +481,6 @@ struct sdvo_device_mapping { u8 ddc_pin; }; -struct intel_display_error_state; - -struct drm_i915_error_state { - struct kref ref; - struct timeval time; - - char error_msg[128]; - bool simulated; - int iommu; - u32 reset_count; - u32 suspend_count; - - /* Generic register state */ - u32 eir; - u32 pgtbl_er; - u32 ier; - u32 gtier[4]; - u32 ccid; - u32 derrmr; - u32 forcewake; - u32 error; /* gen6+ */ - u32 err_int; /* gen7 */ - u32 fault_data0; /* gen8, gen9 */ - u32 fault_data1; /* gen8, gen9 */ - u32 done_reg; - u32 gac_eco; - u32 gam_ecochk; - u32 gab_ctl; - u32 gfx_mode; - u32 extra_instdone[I915_NUM_INSTDONE_REG]; - u64 fence[I915_MAX_NUM_FENCES]; - struct intel_overlay_error_state *overlay; - struct intel_display_error_state *display; - struct drm_i915_error_object *semaphore_obj; - - struct drm_i915_error_ring { - bool valid; - /* Software tracked state */ - bool waiting; - int num_waiters; - int hangcheck_score; - enum intel_ring_hangcheck_action hangcheck_action; - int num_requests; - - /* our own tracking of ring head and tail */ - u32 cpu_ring_head; - u32 cpu_ring_tail; - - u32 last_seqno; - u32 semaphore_seqno[I915_NUM_ENGINES - 1]; - - /* Register state */ - u32 start; - u32 tail; - u32 head; - u32 ctl; - u32 hws; - u32 ipeir; - u32 ipehr; - u32 instdone; - u32 bbstate; - u32 instpm; - u32 instps; - u32 seqno; - u64 bbaddr; - u64 acthd; - u32 fault_reg; - u64 faddr; - u32 rc_psmi; /* sleep state */ - u32 semaphore_mboxes[I915_NUM_ENGINES - 1]; - - struct drm_i915_error_object { - int page_count; - u64 gtt_offset; - u32 *pages[0]; - } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page; - - struct drm_i915_error_object *wa_ctx; - - struct drm_i915_error_request { - long jiffies; - u32 seqno; - u32 tail; - } *requests; - - struct drm_i915_error_waiter { - char comm[TASK_COMM_LEN]; - pid_t pid; - u32 seqno; - } *waiters; - - struct { - u32 gfx_mode; - union { - u64 pdp[4]; - u32 pp_dir_base; - }; - } vm_info; - - pid_t pid; - char comm[TASK_COMM_LEN]; - } ring[I915_NUM_ENGINES]; - - struct drm_i915_error_buffer { - u32 size; - u32 name; - u32 rseqno[I915_NUM_ENGINES], wseqno; - u64 gtt_offset; - u32 read_domains; - u32 write_domain; - s32 fence_reg:I915_MAX_NUM_FENCE_BITS; - s32 pinned:2; - u32 tiling:2; - u32 dirty:1; - u32 purgeable:1; - u32 userptr:1; - s32 ring:4; - u32 cache_level:3; - } **active_bo, **pinned_bo; - - u32 *active_bo_count, *pinned_bo_count; - u32 vm_count; -}; - struct intel_connector; struct intel_encoder; struct intel_crtc_state; @@ -629,8 +510,12 @@ struct drm_i915_display_funcs { struct intel_initial_plane_config *); int (*crtc_compute_clock)(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); - void (*crtc_enable)(struct drm_crtc *crtc); - void (*crtc_disable)(struct drm_crtc *crtc); + void (*crtc_enable)(struct intel_crtc_state *pipe_config, + struct drm_atomic_state *old_state); + void (*crtc_disable)(struct intel_crtc_state *old_crtc_state, + struct drm_atomic_state *old_state); + void (*update_crtcs)(struct drm_atomic_state *state, + unsigned int *crtc_vblank_mask); void (*audio_codec_enable)(struct drm_connector *connector, struct intel_encoder *encoder, const struct drm_display_mode *adjusted_mode); @@ -694,8 +579,6 @@ struct intel_uncore_funcs { uint16_t val, bool trace); void (*mmio_writel)(struct drm_i915_private *dev_priv, i915_reg_t r, uint32_t val, bool trace); - void (*mmio_writeq)(struct drm_i915_private *dev_priv, i915_reg_t r, - uint64_t val, bool trace); }; struct intel_uncore { @@ -756,7 +639,7 @@ struct intel_csr { func(is_i915g) sep \ func(is_i945gm) sep \ func(is_g33) sep \ - func(need_gfx_hws) sep \ + func(hws_needs_physical) sep \ func(is_g4x) sep \ func(is_pineview) sep \ func(is_broadwater) sep \ @@ -771,6 +654,19 @@ struct intel_csr { func(is_kabylake) sep \ func(is_preliminary) sep \ func(has_fbc) sep \ + func(has_psr) sep \ + func(has_runtime_pm) sep \ + func(has_csr) sep \ + func(has_resource_streamer) sep \ + func(has_rc6) sep \ + func(has_rc6p) sep \ + func(has_dp_mst) sep \ + func(has_gmbus_irq) sep \ + func(has_hw_contexts) sep \ + func(has_logical_ring_contexts) sep \ + func(has_l3_dpf) sep \ + func(has_gmch_display) sep \ + func(has_guc) sep \ func(has_pipe_cxsr) sep \ func(has_hotplug) sep \ func(cursor_needs_physical) sep \ @@ -786,6 +682,24 @@ struct intel_csr { #define DEFINE_FLAG(name) u8 name:1 #define SEP_SEMICOLON ; +struct sseu_dev_info { + u8 slice_mask; + u8 subslice_mask; + u8 eu_total; + u8 eu_per_subslice; + u8 min_eu_in_pool; + /* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */ + u8 subslice_7eu[3]; + u8 has_slice_pg:1; + u8 has_subslice_pg:1; + u8 has_eu_pg:1; +}; + +static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu) +{ + return hweight8(sseu->slice_mask) * hweight8(sseu->subslice_mask); +} + struct intel_device_info { u32 display_mmio_offset; u16 device_id; @@ -794,7 +708,9 @@ struct intel_device_info { u8 gen; u16 gen_mask; u8 ring_mask; /* Rings supported by the HW */ + u8 num_rings; DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON); + u16 ddb_size; /* in blocks */ /* Register offsets for the various display pipes and transcoders */ int pipe_offsets[I915_MAX_TRANSCODERS]; int trans_offsets[I915_MAX_TRANSCODERS]; @@ -802,17 +718,7 @@ struct intel_device_info { int cursor_offsets[I915_MAX_PIPES]; /* Slice/subslice/EU info */ - u8 slice_total; - u8 subslice_total; - u8 subslice_per_slice; - u8 eu_total; - u8 eu_per_subslice; - u8 min_eu_in_pool; - /* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */ - u8 subslice_7eu[3]; - u8 has_slice_pg:1; - u8 has_subslice_pg:1; - u8 has_eu_pg:1; + struct sseu_dev_info sseu; struct color_luts { u16 degamma_lut_size; @@ -823,6 +729,134 @@ struct intel_device_info { #undef DEFINE_FLAG #undef SEP_SEMICOLON +struct intel_display_error_state; + +struct drm_i915_error_state { + struct kref ref; + struct timeval time; + + char error_msg[128]; + bool simulated; + int iommu; + u32 reset_count; + u32 suspend_count; + struct intel_device_info device_info; + + /* Generic register state */ + u32 eir; + u32 pgtbl_er; + u32 ier; + u32 gtier[4]; + u32 ccid; + u32 derrmr; + u32 forcewake; + u32 error; /* gen6+ */ + u32 err_int; /* gen7 */ + u32 fault_data0; /* gen8, gen9 */ + u32 fault_data1; /* gen8, gen9 */ + u32 done_reg; + u32 gac_eco; + u32 gam_ecochk; + u32 gab_ctl; + u32 gfx_mode; + u32 extra_instdone[I915_NUM_INSTDONE_REG]; + u64 fence[I915_MAX_NUM_FENCES]; + struct intel_overlay_error_state *overlay; + struct intel_display_error_state *display; + struct drm_i915_error_object *semaphore; + + struct drm_i915_error_engine { + int engine_id; + /* Software tracked state */ + bool waiting; + int num_waiters; + int hangcheck_score; + enum intel_engine_hangcheck_action hangcheck_action; + struct i915_address_space *vm; + int num_requests; + + /* our own tracking of ring head and tail */ + u32 cpu_ring_head; + u32 cpu_ring_tail; + + u32 last_seqno; + u32 semaphore_seqno[I915_NUM_ENGINES - 1]; + + /* Register state */ + u32 start; + u32 tail; + u32 head; + u32 ctl; + u32 mode; + u32 hws; + u32 ipeir; + u32 ipehr; + u32 instdone; + u32 bbstate; + u32 instpm; + u32 instps; + u32 seqno; + u64 bbaddr; + u64 acthd; + u32 fault_reg; + u64 faddr; + u32 rc_psmi; /* sleep state */ + u32 semaphore_mboxes[I915_NUM_ENGINES - 1]; + + struct drm_i915_error_object { + int page_count; + u64 gtt_offset; + u64 gtt_size; + u32 *pages[0]; + } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page; + + struct drm_i915_error_object *wa_ctx; + + struct drm_i915_error_request { + long jiffies; + pid_t pid; + u32 seqno; + u32 head; + u32 tail; + } *requests; + + struct drm_i915_error_waiter { + char comm[TASK_COMM_LEN]; + pid_t pid; + u32 seqno; + } *waiters; + + struct { + u32 gfx_mode; + union { + u64 pdp[4]; + u32 pp_dir_base; + }; + } vm_info; + + pid_t pid; + char comm[TASK_COMM_LEN]; + } engine[I915_NUM_ENGINES]; + + struct drm_i915_error_buffer { + u32 size; + u32 name; + u32 rseqno[I915_NUM_ENGINES], wseqno; + u64 gtt_offset; + u32 read_domains; + u32 write_domain; + s32 fence_reg:I915_MAX_NUM_FENCE_BITS; + u32 tiling:2; + u32 dirty:1; + u32 purgeable:1; + u32 userptr:1; + s32 engine:4; + u32 cache_level:3; + } *active_bo[I915_NUM_ENGINES], *pinned_bo; + u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count; + struct i915_address_space *active_vm[I915_NUM_ENGINES]; +}; + enum i915_cache_level { I915_CACHE_NONE = 0, I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */ @@ -879,22 +913,23 @@ struct i915_gem_context { struct drm_i915_private *i915; struct drm_i915_file_private *file_priv; struct i915_hw_ppgtt *ppgtt; + struct pid *pid; struct i915_ctx_hang_stats hang_stats; - /* Unique identifier for this context, used by the hw for tracking */ unsigned long flags; #define CONTEXT_NO_ZEROMAP BIT(0) #define CONTEXT_NO_ERROR_CAPTURE BIT(1) - unsigned hw_id; + + /* Unique identifier for this context, used by the hw for tracking */ + unsigned int hw_id; u32 user_handle; u32 ggtt_alignment; struct intel_context { - struct drm_i915_gem_object *state; - struct intel_ringbuffer *ringbuf; - struct i915_vma *lrc_vma; + struct i915_vma *state; + struct intel_ring *ring; uint32_t *lrc_reg_state; u64 lrc_desc; int pin_count; @@ -908,6 +943,7 @@ struct i915_gem_context { struct list_head link; u8 remap_slice; + bool closed:1; }; enum fb_op_origin { @@ -1061,13 +1097,6 @@ struct intel_gmbus { struct i915_suspend_saved_registers { u32 saveDSPARB; - u32 saveLVDS; - u32 savePP_ON_DELAYS; - u32 savePP_OFF_DELAYS; - u32 savePP_ON; - u32 savePP_OFF; - u32 savePP_CONTROL; - u32 savePP_DIVISOR; u32 saveFBC_CONTROL; u32 saveCACHE_MODE_0; u32 saveMI_ARB_STATE; @@ -1156,6 +1185,7 @@ struct intel_gen6_power_mgmt { bool interrupts_enabled; u32 pm_iir; + /* PM interrupt bits that should never be masked */ u32 pm_intr_keep; /* Frequencies are stored in potentially platform dependent multiples. @@ -1173,6 +1203,7 @@ struct intel_gen6_power_mgmt { u8 max_freq_softlimit; /* Max frequency permitted by the driver */ u8 max_freq; /* Maximum frequency, RP0 if not overclocking */ u8 min_freq; /* AKA RPn. Minimum frequency */ + u8 boost_freq; /* Frequency to request when wait boosting */ u8 idle_freq; /* Frequency to request when we are idle */ u8 efficient_freq; /* AKA RPe. Pre-determined balanced frequency */ u8 rp1_freq; /* "less than" RP0 power/freqency */ @@ -1190,11 +1221,9 @@ struct intel_gen6_power_mgmt { bool client_boost; bool enabled; - struct delayed_work delayed_resume_work; + struct delayed_work autoenable_work; unsigned boosts; - struct intel_rps_client semaphores, mmioflips; - /* manual wa residency calculations */ struct intel_rps_ei up_ei, down_ei; @@ -1319,7 +1348,6 @@ struct i915_gem_mm { struct notifier_block oom_notifier; struct notifier_block vmap_notifier; struct shrinker shrinker; - bool shrinker_no_lock_stealing; /** LRU list of objects with fence regs on them. */ struct list_head fence_list; @@ -1331,7 +1359,7 @@ struct i915_gem_mm { bool interruptible; /* the indicator for dispatch video commands on two BSD rings */ - unsigned int bsd_ring_dispatch_index; + atomic_t bsd_engine_dispatch_index; /** Bit 6 swizzling required for X tiling */ uint32_t bit_6_swizzle_x; @@ -1379,9 +1407,10 @@ struct i915_gpu_error { * State variable controlling the reset flow and count * * This is a counter which gets incremented when reset is triggered, - * and again when reset has been handled. So odd values (lowest bit set) - * means that reset is in progress and even values that - * (reset_counter >> 1):th reset was successfully completed. + * + * Before the reset commences, the I915_RESET_IN_PROGRESS bit is set + * meaning that any waiters holding onto the struct_mutex should + * relinquish the lock immediately in order for the reset to start. * * If reset is not completed succesfully, the I915_WEDGE bit is * set meaning that hardware is terminally sour and there is no @@ -1396,10 +1425,11 @@ struct i915_gpu_error { * naturally enforces the correct ordering between the bail-out of the * waiter and the gpu reset work code. */ - atomic_t reset_counter; + unsigned long reset_count; -#define I915_RESET_IN_PROGRESS_FLAG 1 -#define I915_WEDGED (1 << 31) + unsigned long flags; +#define I915_RESET_IN_PROGRESS 0 +#define I915_WEDGED (BITS_PER_LONG - 1) /** * Waitqueue to signal when a hang is detected. Used to for waiters @@ -1670,7 +1700,7 @@ struct intel_pipe_crc { }; struct i915_frontbuffer_tracking { - struct mutex lock; + spinlock_t lock; /* * Tracking bits for delayed frontbuffer flushing du to gpu activity or @@ -1705,18 +1735,6 @@ struct i915_virtual_gpu { bool active; }; -struct i915_execbuffer_params { - struct drm_device *dev; - struct drm_file *file; - uint32_t dispatch_flags; - uint32_t args_batch_start_offset; - uint64_t batch_obj_vm_offset; - struct intel_engine_cs *engine; - struct drm_i915_gem_object *batch_obj; - struct i915_gem_context *ctx; - struct drm_i915_gem_request *request; -}; - /* used in computing the new watermarks state */ struct intel_wm_config { unsigned int num_pipes_active; @@ -1763,13 +1781,15 @@ struct drm_i915_private { uint32_t psr_mmio_base; + uint32_t pps_mmio_base; + wait_queue_head_t gmbus_wait_queue; struct pci_dev *bridge_dev; struct i915_gem_context *kernel_context; struct intel_engine_cs engine[I915_NUM_ENGINES]; - struct drm_i915_gem_object *semaphore_obj; - uint32_t last_seqno, next_seqno; + struct i915_vma *semaphore; + u32 next_seqno; struct drm_dma_handle *status_page_dmah; struct resource mch_res; @@ -1854,6 +1874,7 @@ struct drm_i915_private { enum modeset_restore modeset_restore; struct mutex modeset_restore_lock; struct drm_atomic_state *modeset_restore_state; + struct drm_modeset_acquire_ctx reset_ctx; struct list_head vm_list; /* Global list of all address spaces */ struct i915_ggtt ggtt; /* VM representing the global address space */ @@ -1962,6 +1983,13 @@ struct drm_i915_private { struct i915_suspend_saved_registers regfile; struct vlv_s0ix_state vlv_s0ix_state; + enum { + I915_SKL_SAGV_UNKNOWN = 0, + I915_SKL_SAGV_DISABLED, + I915_SKL_SAGV_ENABLED, + I915_SKL_SAGV_NOT_CONTROLLED + } skl_sagv_status; + struct { /* * Raw watermark latency values: @@ -2016,12 +2044,8 @@ struct drm_i915_private { /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */ struct { - int (*execbuf_submit)(struct i915_execbuffer_params *params, - struct drm_i915_gem_execbuffer2 *args, - struct list_head *vmas); - int (*init_engines)(struct drm_device *dev); + void (*resume)(struct drm_i915_private *); void (*cleanup_engine)(struct intel_engine_cs *engine); - void (*stop_engine)(struct intel_engine_cs *engine); /** * Is the GPU currently considered idle, or busy executing @@ -2068,9 +2092,9 @@ static inline struct drm_i915_private *to_i915(const struct drm_device *dev) return container_of(dev, struct drm_i915_private, drm); } -static inline struct drm_i915_private *dev_to_i915(struct device *dev) +static inline struct drm_i915_private *kdev_to_i915(struct device *kdev) { - return to_i915(dev_get_drvdata(dev)); + return to_i915(dev_get_drvdata(kdev)); } static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc) @@ -2093,13 +2117,16 @@ static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc) for_each_if (((id__) = (engine__)->id, \ intel_engine_initialized(engine__))) +#define __mask_next_bit(mask) ({ \ + int __idx = ffs(mask) - 1; \ + mask &= ~BIT(__idx); \ + __idx; \ +}) + /* Iterator over subset of engines selected by mask */ -#define for_each_engine_masked(engine__, dev_priv__, mask__) \ - for ((engine__) = &(dev_priv__)->engine[0]; \ - (engine__) < &(dev_priv__)->engine[I915_NUM_ENGINES]; \ - (engine__)++) \ - for_each_if (((mask__) & intel_engine_flag(engine__)) && \ - intel_engine_initialized(engine__)) +#define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \ + for (tmp__ = mask__ & INTEL_INFO(dev_priv__)->ring_mask; \ + tmp__ ? (engine__ = &(dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : 0; ) enum hdmi_force_audio { HDMI_AUDIO_OFF_DVI = -2, /* no aux data for HDMI-DVI converter */ @@ -2144,8 +2171,6 @@ struct drm_i915_gem_object_ops { */ #define INTEL_MAX_SPRITE_BITS_PER_PIPE 5 #define INTEL_FRONTBUFFER_BITS_PER_PIPE 8 -#define INTEL_FRONTBUFFER_BITS \ - (INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES) #define INTEL_FRONTBUFFER_PRIMARY(pipe) \ (1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))) #define INTEL_FRONTBUFFER_CURSOR(pipe) \ @@ -2169,18 +2194,21 @@ struct drm_i915_gem_object { struct drm_mm_node *stolen; struct list_head global_list; - struct list_head engine_list[I915_NUM_ENGINES]; /** Used in execbuf to temporarily hold a ref */ struct list_head obj_exec_link; struct list_head batch_pool_link; + unsigned long flags; /** * This is set if the object is on the active lists (has pending * rendering and so a non-zero seqno), and is not set if it i s on * inactive (ready to be unbound) list. */ - unsigned int active:I915_NUM_ENGINES; +#define I915_BO_ACTIVE_SHIFT 0 +#define I915_BO_ACTIVE_MASK ((1 << I915_NUM_ENGINES) - 1) +#define __I915_BO_ACTIVE(bo) \ + ((READ_ONCE((bo)->flags) >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK) /** * This is set if the object has been written to since last bound @@ -2189,37 +2217,11 @@ struct drm_i915_gem_object { unsigned int dirty:1; /** - * Fence register bits (if any) for this object. Will be set - * as needed when mapped into the GTT. - * Protected by dev->struct_mutex. - */ - signed int fence_reg:I915_MAX_NUM_FENCE_BITS; - - /** * Advice: are the backing pages purgeable? */ unsigned int madv:2; /** - * Current tiling mode for the object. - */ - unsigned int tiling_mode:2; - /** - * Whether the tiling parameters for the currently associated fence - * register have changed. Note that for the purposes of tracking - * tiling changes we also treat the unfenced register, the register - * slot that the object occupies whilst it executes a fenced - * command (such as BLT on gen2/3), as a "fence". - */ - unsigned int fence_dirty:1; - - /** - * Is the object at the current location in the gtt mappable and - * fenceable? Used to avoid costly recalculations. - */ - unsigned int map_and_fenceable:1; - - /** * Whether the current gtt mapping needs to be mappable (and isn't just * mappable by accident). Track pin and fault separate for a more * accurate mappable working set. @@ -2234,9 +2236,17 @@ struct drm_i915_gem_object { unsigned int cache_level:3; unsigned int cache_dirty:1; - unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS; + atomic_t frontbuffer_bits; + unsigned int frontbuffer_ggtt_origin; /* write once */ + + /** Current tiling stride for the object, if it's tiled. */ + unsigned int tiling_and_stride; +#define FENCE_MINIMUM_STRIDE 128 /* See i915_tiling_ok() */ +#define TILING_MASK (FENCE_MINIMUM_STRIDE-1) +#define STRIDE_MASK (~TILING_MASK) - unsigned int has_wc_mmap; + /** Count of VMA actually bound by this object */ + unsigned int bind_count; unsigned int pin_display; struct sg_table *pages; @@ -2256,14 +2266,9 @@ struct drm_i915_gem_object { * requests on one ring where the write request is older than the * read request. This allows for the CPU to read from an active * buffer by only waiting for the write to complete. - * */ - struct drm_i915_gem_request *last_read_req[I915_NUM_ENGINES]; - struct drm_i915_gem_request *last_write_req; - /** Breadcrumb of last fenced GPU access to the buffer. */ - struct drm_i915_gem_request *last_fenced_req; - - /** Current tiling stride for the object, if it's tiled. */ - uint32_t stride; + */ + struct i915_gem_active last_read[I915_NUM_ENGINES]; + struct i915_gem_active last_write; /** References from framebuffers, locks out tiling changes. */ unsigned long framebuffer_references; @@ -2287,7 +2292,56 @@ struct drm_i915_gem_object { } userptr; }; }; -#define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) + +static inline struct drm_i915_gem_object * +to_intel_bo(struct drm_gem_object *gem) +{ + /* Assert that to_intel_bo(NULL) == NULL */ + BUILD_BUG_ON(offsetof(struct drm_i915_gem_object, base)); + + return container_of(gem, struct drm_i915_gem_object, base); +} + +static inline struct drm_i915_gem_object * +i915_gem_object_lookup(struct drm_file *file, u32 handle) +{ + return to_intel_bo(drm_gem_object_lookup(file, handle)); +} + +__deprecated +extern struct drm_gem_object * +drm_gem_object_lookup(struct drm_file *file, u32 handle); + +__attribute__((nonnull)) +static inline struct drm_i915_gem_object * +i915_gem_object_get(struct drm_i915_gem_object *obj) +{ + drm_gem_object_reference(&obj->base); + return obj; +} + +__deprecated +extern void drm_gem_object_reference(struct drm_gem_object *); + +__attribute__((nonnull)) +static inline void +i915_gem_object_put(struct drm_i915_gem_object *obj) +{ + drm_gem_object_unreference(&obj->base); +} + +__deprecated +extern void drm_gem_object_unreference(struct drm_gem_object *); + +__attribute__((nonnull)) +static inline void +i915_gem_object_put_unlocked(struct drm_i915_gem_object *obj) +{ + drm_gem_object_unreference_unlocked(&obj->base); +} + +__deprecated +extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *); static inline bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) @@ -2295,6 +2349,67 @@ i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) return obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE; } +static inline unsigned long +i915_gem_object_get_active(const struct drm_i915_gem_object *obj) +{ + return (obj->flags >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK; +} + +static inline bool +i915_gem_object_is_active(const struct drm_i915_gem_object *obj) +{ + return i915_gem_object_get_active(obj); +} + +static inline void +i915_gem_object_set_active(struct drm_i915_gem_object *obj, int engine) +{ + obj->flags |= BIT(engine + I915_BO_ACTIVE_SHIFT); +} + +static inline void +i915_gem_object_clear_active(struct drm_i915_gem_object *obj, int engine) +{ + obj->flags &= ~BIT(engine + I915_BO_ACTIVE_SHIFT); +} + +static inline bool +i915_gem_object_has_active_engine(const struct drm_i915_gem_object *obj, + int engine) +{ + return obj->flags & BIT(engine + I915_BO_ACTIVE_SHIFT); +} + +static inline unsigned int +i915_gem_object_get_tiling(struct drm_i915_gem_object *obj) +{ + return obj->tiling_and_stride & TILING_MASK; +} + +static inline bool +i915_gem_object_is_tiled(struct drm_i915_gem_object *obj) +{ + return i915_gem_object_get_tiling(obj) != I915_TILING_NONE; +} + +static inline unsigned int +i915_gem_object_get_stride(struct drm_i915_gem_object *obj) +{ + return obj->tiling_and_stride & STRIDE_MASK; +} + +static inline struct i915_vma *i915_vma_get(struct i915_vma *vma) +{ + i915_gem_object_get(vma->obj); + return vma; +} + +static inline void i915_vma_put(struct i915_vma *vma) +{ + lockdep_assert_held(&vma->vm->dev->struct_mutex); + i915_gem_object_put(vma->obj); +} + /* * Optimised SGL iterator for GEM objects */ @@ -2365,171 +2480,6 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg) (((__iter).curr += PAGE_SIZE) < (__iter).max) || \ ((__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0)) -/** - * Request queue structure. - * - * The request queue allows us to note sequence numbers that have been emitted - * and may be associated with active buffers to be retired. - * - * By keeping this list, we can avoid having to do questionable sequence - * number comparisons on buffer last_read|write_seqno. It also allows an - * emission time to be associated with the request for tracking how far ahead - * of the GPU the submission is. - * - * The requests are reference counted, so upon creation they should have an - * initial reference taken using kref_init - */ -struct drm_i915_gem_request { - struct kref ref; - - /** On Which ring this request was generated */ - struct drm_i915_private *i915; - struct intel_engine_cs *engine; - struct intel_signal_node signaling; - - /** GEM sequence number associated with the previous request, - * when the HWS breadcrumb is equal to this the GPU is processing - * this request. - */ - u32 previous_seqno; - - /** GEM sequence number associated with this request, - * when the HWS breadcrumb is equal or greater than this the GPU - * has finished processing this request. - */ - u32 seqno; - - /** Position in the ringbuffer of the start of the request */ - u32 head; - - /** - * Position in the ringbuffer of the start of the postfix. - * This is required to calculate the maximum available ringbuffer - * space without overwriting the postfix. - */ - u32 postfix; - - /** Position in the ringbuffer of the end of the whole request */ - u32 tail; - - /** Preallocate space in the ringbuffer for the emitting the request */ - u32 reserved_space; - - /** - * Context and ring buffer related to this request - * Contexts are refcounted, so when this request is associated with a - * context, we must increment the context's refcount, to guarantee that - * it persists while any request is linked to it. Requests themselves - * are also refcounted, so the request will only be freed when the last - * reference to it is dismissed, and the code in - * i915_gem_request_free() will then decrement the refcount on the - * context. - */ - struct i915_gem_context *ctx; - struct intel_ringbuffer *ringbuf; - - /** - * Context related to the previous request. - * As the contexts are accessed by the hardware until the switch is - * completed to a new context, the hardware may still be writing - * to the context object after the breadcrumb is visible. We must - * not unpin/unbind/prune that object whilst still active and so - * we keep the previous context pinned until the following (this) - * request is retired. - */ - struct i915_gem_context *previous_context; - - /** Batch buffer related to this request if any (used for - error state dump only) */ - struct drm_i915_gem_object *batch_obj; - - /** Time at which this request was emitted, in jiffies. */ - unsigned long emitted_jiffies; - - /** global list entry for this request */ - struct list_head list; - - struct drm_i915_file_private *file_priv; - /** file_priv list entry for this request */ - struct list_head client_list; - - /** process identifier submitting this request */ - struct pid *pid; - - /** - * The ELSP only accepts two elements at a time, so we queue - * context/tail pairs on a given queue (ring->execlist_queue) until the - * hardware is available. The queue serves a double purpose: we also use - * it to keep track of the up to 2 contexts currently in the hardware - * (usually one in execution and the other queued up by the GPU): We - * only remove elements from the head of the queue when the hardware - * informs us that an element has been completed. - * - * All accesses to the queue are mediated by a spinlock - * (ring->execlist_lock). - */ - - /** Execlist link in the submission queue.*/ - struct list_head execlist_link; - - /** Execlists no. of times this request has been sent to the ELSP */ - int elsp_submitted; - - /** Execlists context hardware id. */ - unsigned ctx_hw_id; -}; - -struct drm_i915_gem_request * __must_check -i915_gem_request_alloc(struct intel_engine_cs *engine, - struct i915_gem_context *ctx); -void i915_gem_request_free(struct kref *req_ref); -int i915_gem_request_add_to_client(struct drm_i915_gem_request *req, - struct drm_file *file); - -static inline uint32_t -i915_gem_request_get_seqno(struct drm_i915_gem_request *req) -{ - return req ? req->seqno : 0; -} - -static inline struct intel_engine_cs * -i915_gem_request_get_engine(struct drm_i915_gem_request *req) -{ - return req ? req->engine : NULL; -} - -static inline struct drm_i915_gem_request * -i915_gem_request_reference(struct drm_i915_gem_request *req) -{ - if (req) - kref_get(&req->ref); - return req; -} - -static inline void -i915_gem_request_unreference(struct drm_i915_gem_request *req) -{ - kref_put(&req->ref, i915_gem_request_free); -} - -static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst, - struct drm_i915_gem_request *src) -{ - if (src) - i915_gem_request_reference(src); - - if (*pdst) - i915_gem_request_unreference(*pdst); - - *pdst = src; -} - -/* - * XXX: i915_gem_request_completed should be here but currently needs the - * definition of i915_seqno_passed() which is below. It will be moved in - * a later patch when the call to i915_seqno_passed() is obsoleted... - */ - /* * A command that requires special handling by the command parser. */ @@ -2617,8 +2567,9 @@ struct drm_i915_cmd_descriptor { /* * A table of commands requiring special handling by the command parser. * - * Each ring has an array of tables. Each table consists of an array of command - * descriptors, which must be sorted with command opcodes in ascending order. + * Each engine has an array of tables. Each table consists of an array of + * command descriptors, which must be sorted with command opcodes in + * ascending order. */ struct drm_i915_cmd_table { const struct drm_i915_cmd_descriptor *table; @@ -2636,7 +2587,7 @@ struct drm_i915_cmd_table { BUILD_BUG(); \ __p; \ }) -#define INTEL_INFO(p) (&__I915__(p)->info) +#define INTEL_INFO(p) (&__I915__(p)->info) #define INTEL_GEN(p) (INTEL_INFO(p)->gen) #define INTEL_DEVID(p) (INTEL_INFO(p)->device_id) @@ -2803,10 +2754,10 @@ struct drm_i915_cmd_table { #define HAS_EDRAM(dev) (!!(__I915__(dev)->edram_cap & EDRAM_ENABLED)) #define HAS_WT(dev) ((IS_HASWELL(dev) || IS_BROADWELL(dev)) && \ HAS_EDRAM(dev)) -#define I915_NEED_GFX_HWS(dev) (INTEL_INFO(dev)->need_gfx_hws) +#define HWS_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->hws_needs_physical) -#define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6) -#define HAS_LOGICAL_RING_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 8) +#define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->has_hw_contexts) +#define HAS_LOGICAL_RING_CONTEXTS(dev) (INTEL_INFO(dev)->has_logical_ring_contexts) #define USES_PPGTT(dev) (i915.enable_ppgtt) #define USES_FULL_PPGTT(dev) (i915.enable_ppgtt >= 2) #define USES_FULL_48BIT_PPGTT(dev) (i915.enable_ppgtt == 3) @@ -2830,7 +2781,7 @@ struct drm_i915_cmd_table { * interrupt source and so prevents the other device from working properly. */ #define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5) -#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5) +#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->has_gmbus_irq) /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte * rows, which changed the alignment requirements and fence programming. @@ -2846,38 +2797,27 @@ struct drm_i915_cmd_table { #define HAS_IPS(dev) (IS_HSW_ULT(dev) || IS_BROADWELL(dev)) -#define HAS_DP_MST(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev) || \ - INTEL_INFO(dev)->gen >= 9) +#define HAS_DP_MST(dev) (INTEL_INFO(dev)->has_dp_mst) #define HAS_DDI(dev) (INTEL_INFO(dev)->has_ddi) #define HAS_FPGA_DBG_UNCLAIMED(dev) (INTEL_INFO(dev)->has_fpga_dbg) -#define HAS_PSR(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev) || \ - IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev) || \ - IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) -#define HAS_RUNTIME_PM(dev) (IS_GEN6(dev) || IS_HASWELL(dev) || \ - IS_BROADWELL(dev) || IS_VALLEYVIEW(dev) || \ - IS_CHERRYVIEW(dev) || IS_SKYLAKE(dev) || \ - IS_KABYLAKE(dev) || IS_BROXTON(dev)) -#define HAS_RC6(dev) (INTEL_INFO(dev)->gen >= 6) -#define HAS_RC6p(dev) (IS_GEN6(dev) || IS_IVYBRIDGE(dev)) - -#define HAS_CSR(dev) (IS_GEN9(dev)) +#define HAS_PSR(dev) (INTEL_INFO(dev)->has_psr) +#define HAS_RUNTIME_PM(dev) (INTEL_INFO(dev)->has_runtime_pm) +#define HAS_RC6(dev) (INTEL_INFO(dev)->has_rc6) +#define HAS_RC6p(dev) (INTEL_INFO(dev)->has_rc6p) + +#define HAS_CSR(dev) (INTEL_INFO(dev)->has_csr) /* * For now, anything with a GuC requires uCode loading, and then supports * command submission once loaded. But these are logically independent * properties, so we have separate macros to test them. */ -#define HAS_GUC(dev) (IS_GEN9(dev)) +#define HAS_GUC(dev) (INTEL_INFO(dev)->has_guc) #define HAS_GUC_UCODE(dev) (HAS_GUC(dev)) #define HAS_GUC_SCHED(dev) (HAS_GUC(dev)) -#define HAS_RESOURCE_STREAMER(dev) (IS_HASWELL(dev) || \ - INTEL_INFO(dev)->gen >= 8) - -#define HAS_CORE_RING_FREQ(dev) (INTEL_INFO(dev)->gen >= 6 && \ - !IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) && \ - !IS_BROXTON(dev)) +#define HAS_RESOURCE_STREAMER(dev) (INTEL_INFO(dev)->has_resource_streamer) #define HAS_POOLED_EU(dev) (INTEL_INFO(dev)->has_pooled_eu) @@ -2905,11 +2845,10 @@ struct drm_i915_cmd_table { #define HAS_PCH_NOP(dev) (INTEL_PCH_TYPE(dev) == PCH_NOP) #define HAS_PCH_SPLIT(dev) (INTEL_PCH_TYPE(dev) != PCH_NONE) -#define HAS_GMCH_DISPLAY(dev) (INTEL_INFO(dev)->gen < 5 || \ - IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) +#define HAS_GMCH_DISPLAY(dev) (INTEL_INFO(dev)->has_gmch_display) /* DPF == dynamic parity feature */ -#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) +#define HAS_L3_DPF(dev) (INTEL_INFO(dev)->has_l3_dpf) #define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev)) #define GT_FREQUENCY_MULTIPLIER 50 @@ -2930,7 +2869,9 @@ extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state); extern int i915_resume_switcheroo(struct drm_device *dev); int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, - int enable_ppgtt); + int enable_ppgtt); + +bool intel_sanitize_semaphores(struct drm_i915_private *dev_priv, int value); /* i915_drv.c */ void __printf(3, 4) @@ -2946,7 +2887,7 @@ extern long i915_compat_ioctl(struct file *filp, unsigned int cmd, #endif extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask); extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv); -extern int i915_reset(struct drm_i915_private *dev_priv); +extern void i915_reset(struct drm_i915_private *dev_priv); extern int intel_guc_reset(struct drm_i915_private *dev_priv); extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine); extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv); @@ -3107,11 +3048,6 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -void i915_gem_execbuffer_move_to_active(struct list_head *vmas, - struct drm_i915_gem_request *req); -int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, - struct drm_i915_gem_execbuffer2 *args, - struct list_head *vmas); int i915_gem_execbuffer(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_execbuffer2(struct drm_device *dev, void *data, @@ -3150,47 +3086,28 @@ struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev, size_t size); struct drm_i915_gem_object *i915_gem_object_create_from_data( struct drm_device *dev, const void *data, size_t size); +void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file); void i915_gem_free_object(struct drm_gem_object *obj); -void i915_gem_vma_destroy(struct i915_vma *vma); - -/* Flags used by pin/bind&friends. */ -#define PIN_MAPPABLE (1<<0) -#define PIN_NONBLOCK (1<<1) -#define PIN_GLOBAL (1<<2) -#define PIN_OFFSET_BIAS (1<<3) -#define PIN_USER (1<<4) -#define PIN_UPDATE (1<<5) -#define PIN_ZONE_4G (1<<6) -#define PIN_HIGH (1<<7) -#define PIN_OFFSET_FIXED (1<<8) -#define PIN_OFFSET_MASK (~4095) -int __must_check -i915_gem_object_pin(struct drm_i915_gem_object *obj, - struct i915_address_space *vm, - uint32_t alignment, - uint64_t flags); -int __must_check + +struct i915_vma * __must_check i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, const struct i915_ggtt_view *view, - uint32_t alignment, - uint64_t flags); + u64 size, + u64 alignment, + u64 flags); int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags); void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); -/* - * BEWARE: Do not use the function below unless you can _absolutely_ - * _guarantee_ VMA in question is _not in use_ anywhere. - */ -int __must_check __i915_vma_unbind_no_wait(struct i915_vma *vma); +void i915_vma_close(struct i915_vma *vma); +void i915_vma_destroy(struct i915_vma *vma); + +int i915_gem_object_unbind(struct drm_i915_gem_object *obj); int i915_gem_object_put_pages(struct drm_i915_gem_object *obj); void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); -int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, - int *needs_clflush); - int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj); static inline int __sg_page_count(struct scatterlist *sg) @@ -3250,13 +3167,20 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) obj->pages_pin_count--; } +enum i915_map_type { + I915_MAP_WB = 0, + I915_MAP_WC, +}; + /** * i915_gem_object_pin_map - return a contiguous mapping of the entire object * @obj - the object to map into kernel address space + * @type - the type of mapping, used to select pgprot_t * * Calls i915_gem_object_pin_pages() to prevent reaping of the object's * pages and then returns a contiguous mapping of the backing storage into - * the kernel address space. + * the kernel address space. Based on the @type of mapping, the PTE will be + * set to either WriteBack or WriteCombine (via pgprot_t). * * The caller must hold the struct_mutex, and is responsible for calling * i915_gem_object_unpin_map() when the mapping is no longer required. @@ -3264,7 +3188,8 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) * Returns the pointer through which to access the mapped object, or an * ERR_PTR() on error. */ -void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj); +void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj, + enum i915_map_type type); /** * i915_gem_object_unpin_map - releases an earlier mapping @@ -3283,122 +3208,73 @@ static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); } +int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, + unsigned int *needs_clflush); +int i915_gem_obj_prepare_shmem_write(struct drm_i915_gem_object *obj, + unsigned int *needs_clflush); +#define CLFLUSH_BEFORE 0x1 +#define CLFLUSH_AFTER 0x2 +#define CLFLUSH_FLAGS (CLFLUSH_BEFORE | CLFLUSH_AFTER) + +static inline void +i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj) +{ + i915_gem_object_unpin_pages(obj); +} + int __must_check i915_mutex_lock_interruptible(struct drm_device *dev); -int i915_gem_object_sync(struct drm_i915_gem_object *obj, - struct intel_engine_cs *to, - struct drm_i915_gem_request **to_req); void i915_vma_move_to_active(struct i915_vma *vma, - struct drm_i915_gem_request *req); + struct drm_i915_gem_request *req, + unsigned int flags); int i915_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, struct drm_mode_create_dumb *args); int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev, uint32_t handle, uint64_t *offset); +int i915_gem_mmap_gtt_version(void); void i915_gem_track_fb(struct drm_i915_gem_object *old, struct drm_i915_gem_object *new, unsigned frontbuffer_bits); -/** - * Returns true if seq1 is later than seq2. - */ -static inline bool -i915_seqno_passed(uint32_t seq1, uint32_t seq2) -{ - return (int32_t)(seq1 - seq2) >= 0; -} - -static inline bool i915_gem_request_started(const struct drm_i915_gem_request *req) -{ - return i915_seqno_passed(intel_engine_get_seqno(req->engine), - req->previous_seqno); -} - -static inline bool i915_gem_request_completed(const struct drm_i915_gem_request *req) -{ - return i915_seqno_passed(intel_engine_get_seqno(req->engine), - req->seqno); -} - -bool __i915_spin_request(const struct drm_i915_gem_request *request, - int state, unsigned long timeout_us); -static inline bool i915_spin_request(const struct drm_i915_gem_request *request, - int state, unsigned long timeout_us) -{ - return (i915_gem_request_started(request) && - __i915_spin_request(request, state, timeout_us)); -} - -int __must_check i915_gem_get_seqno(struct drm_i915_private *dev_priv, u32 *seqno); int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno); struct drm_i915_gem_request * i915_gem_find_active_request(struct intel_engine_cs *engine); void i915_gem_retire_requests(struct drm_i915_private *dev_priv); -void i915_gem_retire_requests_ring(struct intel_engine_cs *engine); - -static inline u32 i915_reset_counter(struct i915_gpu_error *error) -{ - return atomic_read(&error->reset_counter); -} - -static inline bool __i915_reset_in_progress(u32 reset) -{ - return unlikely(reset & I915_RESET_IN_PROGRESS_FLAG); -} - -static inline bool __i915_reset_in_progress_or_wedged(u32 reset) -{ - return unlikely(reset & (I915_RESET_IN_PROGRESS_FLAG | I915_WEDGED)); -} - -static inline bool __i915_terminally_wedged(u32 reset) -{ - return unlikely(reset & I915_WEDGED); -} static inline bool i915_reset_in_progress(struct i915_gpu_error *error) { - return __i915_reset_in_progress(i915_reset_counter(error)); + return unlikely(test_bit(I915_RESET_IN_PROGRESS, &error->flags)); } -static inline bool i915_reset_in_progress_or_wedged(struct i915_gpu_error *error) +static inline bool i915_terminally_wedged(struct i915_gpu_error *error) { - return __i915_reset_in_progress_or_wedged(i915_reset_counter(error)); + return unlikely(test_bit(I915_WEDGED, &error->flags)); } -static inline bool i915_terminally_wedged(struct i915_gpu_error *error) +static inline bool i915_reset_in_progress_or_wedged(struct i915_gpu_error *error) { - return __i915_terminally_wedged(i915_reset_counter(error)); + return i915_reset_in_progress(error) | i915_terminally_wedged(error); } static inline u32 i915_reset_count(struct i915_gpu_error *error) { - return ((i915_reset_counter(error) & ~I915_WEDGED) + 1) / 2; + return READ_ONCE(error->reset_count); } -void i915_gem_reset(struct drm_device *dev); +void i915_gem_reset(struct drm_i915_private *dev_priv); +void i915_gem_set_wedged(struct drm_i915_private *dev_priv); bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force); int __must_check i915_gem_init(struct drm_device *dev); -int i915_gem_init_engines(struct drm_device *dev); int __must_check i915_gem_init_hw(struct drm_device *dev); void i915_gem_init_swizzling(struct drm_device *dev); void i915_gem_cleanup_engines(struct drm_device *dev); -int __must_check i915_gem_wait_for_idle(struct drm_i915_private *dev_priv); +int __must_check i915_gem_wait_for_idle(struct drm_i915_private *dev_priv, + unsigned int flags); int __must_check i915_gem_suspend(struct drm_device *dev); -void __i915_add_request(struct drm_i915_gem_request *req, - struct drm_i915_gem_object *batch_obj, - bool flush_caches); -#define i915_add_request(req) \ - __i915_add_request(req, NULL, true) -#define i915_add_request_no_flush(req) \ - __i915_add_request(req, NULL, false) -int __i915_wait_request(struct drm_i915_gem_request *req, - bool interruptible, - s64 *timeout, - struct intel_rps_client *rps); -int __must_check i915_wait_request(struct drm_i915_gem_request *req); +void i915_gem_resume(struct drm_device *dev); int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf); int __must_check i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj, @@ -3408,22 +3284,20 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write); int __must_check i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write); -int __must_check +struct i915_vma * __must_check i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, const struct i915_ggtt_view *view); -void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj, - const struct i915_ggtt_view *view); +void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma); int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align); int i915_gem_open(struct drm_device *dev, struct drm_file *file); void i915_gem_release(struct drm_device *dev, struct drm_file *file); -uint32_t -i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode); -uint32_t -i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size, - int tiling_mode, bool fenced); +u64 i915_gem_get_ggtt_size(struct drm_i915_private *dev_priv, u64 size, + int tiling_mode); +u64 i915_gem_get_ggtt_alignment(struct drm_i915_private *dev_priv, u64 size, + int tiling_mode, bool fenced); int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); @@ -3434,86 +3308,82 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags); -u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, - const struct i915_ggtt_view *view); -u64 i915_gem_obj_offset(struct drm_i915_gem_object *o, - struct i915_address_space *vm); -static inline u64 -i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o) -{ - return i915_gem_obj_ggtt_offset_view(o, &i915_ggtt_view_normal); -} - -bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o); -bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o, - const struct i915_ggtt_view *view); -bool i915_gem_obj_bound(struct drm_i915_gem_object *o, - struct i915_address_space *vm); - struct i915_vma * i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, - struct i915_address_space *vm); -struct i915_vma * -i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj, - const struct i915_ggtt_view *view); + struct i915_address_space *vm, + const struct i915_ggtt_view *view); struct i915_vma * i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj, - struct i915_address_space *vm); -struct i915_vma * -i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj, - const struct i915_ggtt_view *view); - -static inline struct i915_vma * -i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj) -{ - return i915_gem_obj_to_ggtt_view(obj, &i915_ggtt_view_normal); -} -bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj); + struct i915_address_space *vm, + const struct i915_ggtt_view *view); -/* Some GGTT VM helpers */ static inline struct i915_hw_ppgtt * i915_vm_to_ppgtt(struct i915_address_space *vm) { return container_of(vm, struct i915_hw_ppgtt, base); } +static inline struct i915_vma * +i915_gem_object_to_ggtt(struct drm_i915_gem_object *obj, + const struct i915_ggtt_view *view) +{ + return i915_gem_obj_to_vma(obj, &to_i915(obj->base.dev)->ggtt.base, view); +} -static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj) +static inline unsigned long +i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o, + const struct i915_ggtt_view *view) { - return i915_gem_obj_ggtt_bound_view(obj, &i915_ggtt_view_normal); + return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view)); } -unsigned long -i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj); +/* i915_gem_fence.c */ +int __must_check i915_vma_get_fence(struct i915_vma *vma); +int __must_check i915_vma_put_fence(struct i915_vma *vma); -static inline int __must_check -i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj, - uint32_t alignment, - unsigned flags) +/** + * i915_vma_pin_fence - pin fencing state + * @vma: vma to pin fencing for + * + * This pins the fencing state (whether tiled or untiled) to make sure the + * vma (and its object) is ready to be used as a scanout target. Fencing + * status must be synchronize first by calling i915_vma_get_fence(): + * + * The resulting fence pin reference must be released again with + * i915_vma_unpin_fence(). + * + * Returns: + * + * True if the vma has a fence, false otherwise. + */ +static inline bool +i915_vma_pin_fence(struct i915_vma *vma) { - struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; - - return i915_gem_object_pin(obj, &ggtt->base, - alignment, flags | PIN_GLOBAL); + if (vma->fence) { + vma->fence->pin_count++; + return true; + } else + return false; } -void i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj, - const struct i915_ggtt_view *view); +/** + * i915_vma_unpin_fence - unpin fencing state + * @vma: vma to unpin fencing for + * + * This releases the fence pin reference acquired through + * i915_vma_pin_fence. It will handle both objects with and without an + * attached fence correctly, callers do not need to distinguish this. + */ static inline void -i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj) +i915_vma_unpin_fence(struct i915_vma *vma) { - i915_gem_object_ggtt_unpin_view(obj, &i915_ggtt_view_normal); + if (vma->fence) { + GEM_BUG_ON(vma->fence->pin_count <= 0); + vma->fence->pin_count--; + } } -/* i915_gem_fence.c */ -int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj); -int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj); - -bool i915_gem_object_pin_fence(struct drm_i915_gem_object *obj); -void i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj); - void i915_gem_restore_fences(struct drm_device *dev); void i915_gem_detect_bit_6_swizzle(struct drm_device *dev); @@ -3524,10 +3394,10 @@ void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj); int __must_check i915_gem_context_init(struct drm_device *dev); void i915_gem_context_lost(struct drm_i915_private *dev_priv); void i915_gem_context_fini(struct drm_device *dev); -void i915_gem_context_reset(struct drm_device *dev); int i915_gem_context_open(struct drm_device *dev, struct drm_file *file); void i915_gem_context_close(struct drm_device *dev, struct drm_file *file); int i915_switch_context(struct drm_i915_gem_request *req); +int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv); void i915_gem_context_free(struct kref *ctx_ref); struct drm_i915_gem_object * i915_gem_alloc_context_obj(struct drm_device *dev, size_t size); @@ -3548,12 +3418,14 @@ i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id) return ctx; } -static inline void i915_gem_context_reference(struct i915_gem_context *ctx) +static inline struct i915_gem_context * +i915_gem_context_get(struct i915_gem_context *ctx) { kref_get(&ctx->ref); + return ctx; } -static inline void i915_gem_context_unreference(struct i915_gem_context *ctx) +static inline void i915_gem_context_put(struct i915_gem_context *ctx) { lockdep_assert_held(&ctx->i915->drm.struct_mutex); kref_put(&ctx->ref, i915_gem_context_free); @@ -3576,13 +3448,10 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data, struct drm_file *file); /* i915_gem_evict.c */ -int __must_check i915_gem_evict_something(struct drm_device *dev, - struct i915_address_space *vm, - int min_size, - unsigned alignment, +int __must_check i915_gem_evict_something(struct i915_address_space *vm, + u64 min_size, u64 alignment, unsigned cache_level, - unsigned long start, - unsigned long end, + u64 start, u64 end, unsigned flags); int __must_check i915_gem_evict_for_vma(struct i915_vma *target); int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); @@ -3590,6 +3459,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); /* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv) { + wmb(); if (INTEL_GEN(dev_priv) < 6) intel_gtt_chipset_flush(); } @@ -3634,28 +3504,21 @@ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_objec struct drm_i915_private *dev_priv = to_i915(obj->base.dev); return dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 && - obj->tiling_mode != I915_TILING_NONE; + i915_gem_object_is_tiled(obj); } -/* i915_gem_debug.c */ -#if WATCH_LISTS -int i915_verify_lists(struct drm_device *dev); -#else -#define i915_verify_lists(dev) 0 -#endif - /* i915_debugfs.c */ #ifdef CONFIG_DEBUG_FS int i915_debugfs_register(struct drm_i915_private *dev_priv); void i915_debugfs_unregister(struct drm_i915_private *dev_priv); int i915_debugfs_connector_add(struct drm_connector *connector); -void intel_display_crc_init(struct drm_device *dev); +void intel_display_crc_init(struct drm_i915_private *dev_priv); #else static inline int i915_debugfs_register(struct drm_i915_private *dev_priv) {return 0;} static inline void i915_debugfs_unregister(struct drm_i915_private *dev_priv) {} static inline int i915_debugfs_connector_add(struct drm_connector *connector) { return 0; } -static inline void intel_display_crc_init(struct drm_device *dev) {} +static inline void intel_display_crc_init(struct drm_i915_private *dev_priv) {} #endif /* i915_gpu_error.c */ @@ -3684,23 +3547,23 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); /* i915_cmd_parser.c */ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); -int i915_cmd_parser_init_ring(struct intel_engine_cs *engine); -void i915_cmd_parser_fini_ring(struct intel_engine_cs *engine); -bool i915_needs_cmd_parser(struct intel_engine_cs *engine); -int i915_parse_cmds(struct intel_engine_cs *engine, - struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, - u32 batch_start_offset, - u32 batch_len, - bool is_master); +void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); +void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); +bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine); +int intel_engine_cmd_parser(struct intel_engine_cs *engine, + struct drm_i915_gem_object *batch_obj, + struct drm_i915_gem_object *shadow_batch_obj, + u32 batch_start_offset, + u32 batch_len, + bool is_master); /* i915_suspend.c */ extern int i915_save_state(struct drm_device *dev); extern int i915_restore_state(struct drm_device *dev); /* i915_sysfs.c */ -void i915_setup_sysfs(struct drm_device *dev_priv); -void i915_teardown_sysfs(struct drm_device *dev_priv); +void i915_setup_sysfs(struct drm_i915_private *dev_priv); +void i915_teardown_sysfs(struct drm_i915_private *dev_priv); /* intel_i2c.c */ extern int intel_setup_gmbus(struct drm_device *dev); @@ -3800,7 +3663,6 @@ extern void intel_set_rps(struct drm_i915_private *dev_priv, u8 val); extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable); -extern bool i915_semaphore_is_enabled(struct drm_i915_private *dev_priv); int i915_reg_read_ioctl(struct drm_device *dev, void *data, struct drm_file *file); @@ -3878,9 +3740,16 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val); * will be implemented using 2 32-bit writes in an arbitrary order with * an arbitrary delay between them. This can cause the hardware to * act upon the intermediate value, possibly leading to corruption and - * machine death. You have been warned. + * machine death. For this reason we do not support I915_WRITE64, or + * dev_priv->uncore.funcs.mmio_writeq. + * + * When reading a 64-bit value as two 32-bit values, the delay may cause + * the two reads to mismatch, e.g. a timestamp overflowing. Also note that + * occasionally a 64-bit register does not actualy support a full readq + * and must be read using two 32-bit reads. + * + * You have been warned. */ -#define I915_WRITE64(reg, val) dev_priv->uncore.funcs.mmio_writeq(dev_priv, (reg), (val), true) #define I915_READ64(reg) dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true) #define I915_READ64_2x32(lower_reg, upper_reg) ({ \ @@ -3923,7 +3792,7 @@ __raw_write(64, q) #undef __raw_write /* These are untraced mmio-accessors that are only valid to be used inside - * criticial sections inside IRQ handlers where forcewake is explicitly + * critical sections inside IRQ handlers where forcewake is explicitly * controlled. * Think twice, and think again, before using these. * Note: Should only be used between intel_uncore_forcewake_irqlock() and @@ -3995,7 +3864,9 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms) schedule_timeout_uninterruptible(remaining_jiffies); } } -static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req) + +static inline bool +__i915_request_irq_complete(struct drm_i915_gem_request *req) { struct intel_engine_cs *engine = req->engine; @@ -4017,7 +3888,7 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req) * is woken. */ if (engine->irq_seqno_barrier && - READ_ONCE(engine->breadcrumbs.irq_seqno_bh) == current && + rcu_access_pointer(engine->breadcrumbs.irq_seqno_bh) == current && cmpxchg_relaxed(&engine->breadcrumbs.irq_posted, 1, 0)) { struct task_struct *tsk; @@ -4042,7 +3913,7 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req) * irq_posted == false but we are still running). */ rcu_read_lock(); - tsk = READ_ONCE(engine->breadcrumbs.irq_seqno_bh); + tsk = rcu_dereference(engine->breadcrumbs.irq_seqno_bh); if (tsk && tsk != current) /* Note that if the bottom-half is changed as we * are sending the wake-up, the new bottom-half will @@ -4057,18 +3928,35 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req) return true; } - /* We need to check whether any gpu reset happened in between - * the request being submitted and now. If a reset has occurred, - * the seqno will have been advance past ours and our request - * is complete. If we are in the process of handling a reset, - * the request is effectively complete as the rendering will - * be discarded, but we need to return in order to drop the - * struct_mutex. - */ - if (i915_reset_in_progress(&req->i915->gpu_error)) - return true; - return false; } +void i915_memcpy_init_early(struct drm_i915_private *dev_priv); +bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len); + +/* i915_mm.c */ +int remap_io_mapping(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, unsigned long size, + struct io_mapping *iomap); + +#define ptr_mask_bits(ptr) ({ \ + unsigned long __v = (unsigned long)(ptr); \ + (typeof(ptr))(__v & PAGE_MASK); \ +}) + +#define ptr_unpack_bits(ptr, bits) ({ \ + unsigned long __v = (unsigned long)(ptr); \ + (bits) = __v & ~PAGE_MASK; \ + (typeof(ptr))(__v & PAGE_MASK); \ +}) + +#define ptr_pack_bits(ptr, bits) \ + ((typeof(ptr))((unsigned long)(ptr) | (bits))) + +#define fetch_and_zero(ptr) ({ \ + typeof(*ptr) __T = *(ptr); \ + *(ptr) = (typeof(*ptr))0; \ + __T; \ +}) + #endif |