diff options
Diffstat (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.h')
| -rw-r--r-- | drivers/gpu/drm/i915/intel_ringbuffer.h | 184 |
1 files changed, 155 insertions, 29 deletions
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 6b2067f10824..2863d5a65187 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -8,6 +8,8 @@ #include "i915_gem_timeline.h" #include "i915_selftest.h" +struct drm_printer; + #define I915_CMD_HASH_ORDER 9 /* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill, @@ -185,6 +187,104 @@ struct i915_priolist { int priority; }; +/** + * struct intel_engine_execlists - execlist submission queue and port state + * + * The struct intel_engine_execlists represents the combined logical state of + * driver and the hardware state for execlist mode of submission. + */ +struct intel_engine_execlists { + /** + * @irq_tasklet: softirq tasklet for bottom handler + */ + struct tasklet_struct irq_tasklet; + + /** + * @default_priolist: priority list for I915_PRIORITY_NORMAL + */ + struct i915_priolist default_priolist; + + /** + * @no_priolist: priority lists disabled + */ + bool no_priolist; + + /** + * @port: execlist port states + * + * For each hardware ELSP (ExecList Submission Port) we keep + * track of the last request and the number of times we submitted + * that port to hw. We then count the number of times the hw reports + * a context completion or preemption. As only one context can + * be active on hw, we limit resubmission of context to port[0]. This + * is called Lite Restore, of the context. + */ + struct execlist_port { + /** + * @request_count: combined request and submission count + */ + struct drm_i915_gem_request *request_count; +#define EXECLIST_COUNT_BITS 2 +#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS) +#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS) +#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS) +#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS) +#define port_set(p, packed) ((p)->request_count = (packed)) +#define port_isset(p) ((p)->request_count) +#define port_index(p, execlists) ((p) - (execlists)->port) + + /** + * @context_id: context ID for port + */ + GEM_DEBUG_DECL(u32 context_id); + +#define EXECLIST_MAX_PORTS 2 + } port[EXECLIST_MAX_PORTS]; + + /** + * @active: is the HW active? We consider the HW as active after + * submitting any context for execution and until we have seen the + * last context completion event. After that, we do not expect any + * more events until we submit, and so can park the HW. + * + * As we have a small number of different sources from which we feed + * the HW, we track the state of each inside a single bitfield. + */ + unsigned int active; +#define EXECLISTS_ACTIVE_USER 0 +#define EXECLISTS_ACTIVE_PREEMPT 1 + + /** + * @port_mask: number of execlist ports - 1 + */ + unsigned int port_mask; + + /** + * @queue: queue of requests, in priority lists + */ + struct rb_root queue; + + /** + * @first: leftmost level in priority @queue + */ + struct rb_node *first; + + /** + * @fw_domains: forcewake domains for irq tasklet + */ + unsigned int fw_domains; + + /** + * @csb_head: context status buffer head + */ + unsigned int csb_head; + + /** + * @csb_use_mmio: access csb through mmio, instead of hwsp + */ + bool csb_use_mmio; +}; + #define INTEL_ENGINE_CS_MAX_NAME 8 struct intel_engine_cs { @@ -307,6 +407,14 @@ struct intel_engine_cs { void (*schedule)(struct drm_i915_gem_request *request, int priority); + /* + * Cancel all requests on the hardware, or queued for execution. + * This should only cancel the ready requests that have been + * submitted to the engine (via the engine->submit_request callback). + * This is called when marking the device as wedged. + */ + void (*cancel_requests)(struct intel_engine_cs *engine); + /* Some chipsets are not quite as coherent as advertised and need * an expensive kick to force a true read of the up-to-date seqno. * However, the up-to-date seqno is not always required and the last @@ -373,25 +481,7 @@ struct intel_engine_cs { u32 *(*signal)(struct drm_i915_gem_request *req, u32 *cs); } semaphore; - /* Execlists */ - struct tasklet_struct irq_tasklet; - struct i915_priolist default_priolist; - bool no_priolist; - struct execlist_port { - struct drm_i915_gem_request *request_count; -#define EXECLIST_COUNT_BITS 2 -#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS) -#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS) -#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS) -#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS) -#define port_set(p, packed) ((p)->request_count = (packed)) -#define port_isset(p) ((p)->request_count) -#define port_index(p, e) ((p) - (e)->execlist_port) - GEM_DEBUG_DECL(u32 context_id); - } execlist_port[2]; - struct rb_root execlist_queue; - struct rb_node *execlist_first; - unsigned int fw_domains; + struct intel_engine_execlists execlists; /* Contexts are pinned whilst they are active on the GPU. The last * context executed remains active whilst the GPU is idle - the @@ -444,6 +534,46 @@ struct intel_engine_cs { u32 (*get_cmd_length_mask)(u32 cmd_header); }; +static inline void +execlists_set_active(struct intel_engine_execlists *execlists, + unsigned int bit) +{ + __set_bit(bit, (unsigned long *)&execlists->active); +} + +static inline void +execlists_clear_active(struct intel_engine_execlists *execlists, + unsigned int bit) +{ + __clear_bit(bit, (unsigned long *)&execlists->active); +} + +static inline bool +execlists_is_active(const struct intel_engine_execlists *execlists, + unsigned int bit) +{ + return test_bit(bit, (unsigned long *)&execlists->active); +} + +static inline unsigned int +execlists_num_ports(const struct intel_engine_execlists * const execlists) +{ + return execlists->port_mask + 1; +} + +static inline void +execlists_port_complete(struct intel_engine_execlists * const execlists, + struct execlist_port * const port) +{ + const unsigned int m = execlists->port_mask; + + GEM_BUG_ON(port_index(port, execlists) != 0); + GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_USER)); + + memmove(port, port + 1, m * sizeof(struct execlist_port)); + memset(port + m, 0, sizeof(struct execlist_port)); +} + static inline unsigned int intel_engine_flag(const struct intel_engine_cs *engine) { @@ -497,6 +627,10 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value) #define I915_GEM_HWS_SCRATCH_INDEX 0x40 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT) +#define I915_HWS_CSB_BUF0_INDEX 0x10 +#define I915_HWS_CSB_WRITE_INDEX 0x1f +#define CNL_HWS_CSB_WRITE_INDEX 0x2f + struct intel_ring * intel_engine_create_ring(struct intel_engine_cs *engine, int size); int intel_ring_pin(struct intel_ring *ring, @@ -736,16 +870,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv); void intel_engines_mark_idle(struct drm_i915_private *i915); void intel_engines_reset_default_submission(struct drm_i915_private *i915); -static inline bool -__intel_engine_can_store_dword(unsigned int gen, unsigned int class) -{ - if (gen <= 2) - return false; /* uses physical not virtual addresses */ +bool intel_engine_can_store_dword(struct intel_engine_cs *engine); - if (gen == 6 && class == VIDEO_DECODE_CLASS) - return false; /* b0rked */ - - return true; -} +void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *p); #endif /* _INTEL_RINGBUFFER_H_ */ |