struct drm_i915_gem_object *obj;
};
-#define I915_READ_TAIL(ring) I915_READ(RING_TAIL((ring)->mmio_base))
-#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
+#define I915_READ_TAIL(engine) I915_READ(RING_TAIL((engine)->mmio_base))
+#define I915_WRITE_TAIL(engine, val) I915_WRITE(RING_TAIL((engine)->mmio_base), val)
-#define I915_READ_START(ring) I915_READ(RING_START((ring)->mmio_base))
-#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
+#define I915_READ_START(engine) I915_READ(RING_START((engine)->mmio_base))
+#define I915_WRITE_START(engine, val) I915_WRITE(RING_START((engine)->mmio_base), val)
-#define I915_READ_HEAD(ring) I915_READ(RING_HEAD((ring)->mmio_base))
-#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
+#define I915_READ_HEAD(engine) I915_READ(RING_HEAD((engine)->mmio_base))
+#define I915_WRITE_HEAD(engine, val) I915_WRITE(RING_HEAD((engine)->mmio_base), val)
-#define I915_READ_CTL(ring) I915_READ(RING_CTL((ring)->mmio_base))
-#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
+#define I915_READ_CTL(engine) I915_READ(RING_CTL((engine)->mmio_base))
+#define I915_WRITE_CTL(engine, val) I915_WRITE(RING_CTL((engine)->mmio_base), val)
-#define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
-#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
+#define I915_READ_IMR(engine) I915_READ(RING_IMR((engine)->mmio_base))
+#define I915_WRITE_IMR(engine, val) I915_WRITE(RING_IMR((engine)->mmio_base), val)
-#define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base))
-#define I915_WRITE_MODE(ring, val) I915_WRITE(RING_MI_MODE((ring)->mmio_base), val)
+#define I915_READ_MODE(engine) I915_READ(RING_MI_MODE((engine)->mmio_base))
+#define I915_WRITE_MODE(engine, val) I915_WRITE(RING_MI_MODE((engine)->mmio_base), val)
/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
* do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
-#define GEN8_RING_SEMAPHORE_INIT(e) do { \
- if (!dev_priv->semaphore_obj) { \
- break; \
- } \
- (e)->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET((e), RCS); \
- (e)->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET((e), VCS); \
- (e)->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET((e), BCS); \
- (e)->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET((e), VECS); \
- (e)->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET((e), VCS2); \
- (e)->semaphore.signal_ggtt[(e)->id] = MI_SEMAPHORE_SYNC_INVALID; \
- } while(0)
-
-enum intel_ring_hangcheck_action {
+enum intel_engine_hangcheck_action {
HANGCHECK_IDLE = 0,
HANGCHECK_WAIT,
HANGCHECK_ACTIVE,
#define HANGCHECK_SCORE_RING_HUNG 31
-struct intel_ring_hangcheck {
+struct intel_engine_hangcheck {
u64 acthd;
+ unsigned long user_interrupts;
u32 seqno;
- unsigned user_interrupts;
int score;
- enum intel_ring_hangcheck_action action;
+ enum intel_engine_hangcheck_action action;
int deadlock;
u32 instdone[I915_NUM_INSTDONE_REG];
};
-struct intel_ringbuffer {
+struct intel_ring {
struct drm_i915_gem_object *obj;
- void __iomem *virtual_start;
+ void *vaddr;
struct i915_vma *vma;
struct intel_engine_cs *engine;
int space;
int size;
int effective_size;
- int reserved_size;
- int reserved_tail;
- bool reserved_in_use;
/** We track the position of the requests in the ring buffer, and
* when each is retired we increment last_retired_head as the GPU
u32 last_retired_head;
};
-struct intel_context;
+struct i915_gem_context;
struct drm_i915_reg_table;
/*
struct drm_i915_gem_object *obj;
};
-struct intel_engine_cs {
+struct drm_i915_gem_request;
+
+struct intel_engine_cs {
+ struct drm_i915_private *i915;
const char *name;
enum intel_engine_id {
RCS = 0,
#define I915_NUM_ENGINES 5
#define _VCS(n) (VCS + (n))
unsigned int exec_id;
- unsigned int guc_id;
+ unsigned int hw_id;
+ unsigned int guc_id; /* XXX same as hw_id? */
+ u64 fence_context;
u32 mmio_base;
- struct drm_device *dev;
- struct intel_ringbuffer *buffer;
+ unsigned int irq_shift;
+ struct intel_ring *buffer;
struct list_head buffers;
+ /* Rather than have every client wait upon all user interrupts,
+ * with the herd waking after every interrupt and each doing the
+ * heavyweight seqno dance, we delegate the task (of being the
+ * bottom-half of the user interrupt) to the first client. After
+ * every interrupt, we wake up one client, who does the heavyweight
+ * coherent seqno read and either goes back to sleep (if incomplete),
+ * or wakes up all the completed clients in parallel, before then
+ * transferring the bottom-half status to the next client in the queue.
+ *
+ * Compared to walking the entire list of waiters in a single dedicated
+ * bottom-half, we reduce the latency of the first waiter by avoiding
+ * a context switch, but incur additional coherent seqno reads when
+ * following the chain of request breadcrumbs. Since it is most likely
+ * that we have a single client waiting on each seqno, then reducing
+ * the overhead of waking that client is much preferred.
+ */
+ struct intel_breadcrumbs {
+ struct task_struct *irq_seqno_bh; /* bh for user interrupts */
+ unsigned long irq_wakeups;
+ bool irq_posted;
+
+ spinlock_t lock; /* protects the lists of requests */
+ struct rb_root waiters; /* sorted by retirement, priority */
+ struct rb_root signals; /* sorted by retirement */
+ struct intel_wait *first_wait; /* oldest waiter by retirement */
+ struct task_struct *signaler; /* used for fence signalling */
+ struct drm_i915_gem_request *first_signal;
+ struct timer_list fake_irq; /* used after a missed interrupt */
+
+ bool irq_enabled : 1;
+ bool rpm_wakelock : 1;
+ } breadcrumbs;
+
/*
* A pool of objects to use as shadow copies of client batch buffers
* when the command parser is enabled. Prevents the client from
struct intel_hw_status_page status_page;
struct i915_ctx_workarounds wa_ctx;
- unsigned irq_refcount; /* protected by dev_priv->irq_lock */
- u32 irq_enable_mask; /* bitmask to enable ring interrupt */
- struct drm_i915_gem_request *trace_irq_req;
- bool __must_check (*irq_get)(struct intel_engine_cs *ring);
- void (*irq_put)(struct intel_engine_cs *ring);
+ u32 irq_keep_mask; /* always keep these interrupts */
+ u32 irq_enable_mask; /* bitmask to enable ring interrupt */
+ void (*irq_enable)(struct intel_engine_cs *engine);
+ void (*irq_disable)(struct intel_engine_cs *engine);
- int (*init_hw)(struct intel_engine_cs *ring);
+ int (*init_hw)(struct intel_engine_cs *engine);
int (*init_context)(struct drm_i915_gem_request *req);
- void (*write_tail)(struct intel_engine_cs *ring,
- u32 value);
- int __must_check (*flush)(struct drm_i915_gem_request *req,
- u32 invalidate_domains,
- u32 flush_domains);
- int (*add_request)(struct drm_i915_gem_request *req);
+ int (*emit_flush)(struct drm_i915_gem_request *request,
+ u32 mode);
+#define EMIT_INVALIDATE BIT(0)
+#define EMIT_FLUSH BIT(1)
+#define EMIT_BARRIER (EMIT_INVALIDATE | EMIT_FLUSH)
+ int (*emit_bb_start)(struct drm_i915_gem_request *req,
+ u64 offset, u32 length,
+ unsigned int dispatch_flags);
+#define I915_DISPATCH_SECURE BIT(0)
+#define I915_DISPATCH_PINNED BIT(1)
+#define I915_DISPATCH_RS BIT(2)
+ int (*emit_request)(struct drm_i915_gem_request *req);
+ void (*submit_request)(struct drm_i915_gem_request *req);
/* 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
* seen value is good enough. Note that the seqno will always be
* monotonic, even if not coherent.
*/
- void (*irq_seqno_barrier)(struct intel_engine_cs *ring);
- u32 (*get_seqno)(struct intel_engine_cs *ring);
- void (*set_seqno)(struct intel_engine_cs *ring,
- u32 seqno);
- int (*dispatch_execbuffer)(struct drm_i915_gem_request *req,
- u64 offset, u32 length,
- unsigned dispatch_flags);
-#define I915_DISPATCH_SECURE 0x1
-#define I915_DISPATCH_PINNED 0x2
-#define I915_DISPATCH_RS 0x4
- void (*cleanup)(struct intel_engine_cs *ring);
+ void (*irq_seqno_barrier)(struct intel_engine_cs *engine);
+ void (*cleanup)(struct intel_engine_cs *engine);
/* GEN8 signal/wait table - never trust comments!
* signal to signal to signal to signal to signal to
};
/* AKA wait() */
- int (*sync_to)(struct drm_i915_gem_request *to_req,
- struct intel_engine_cs *from,
- u32 seqno);
- int (*signal)(struct drm_i915_gem_request *signaller_req,
- /* num_dwords needed by caller */
- unsigned int num_dwords);
+ int (*sync_to)(struct drm_i915_gem_request *req,
+ struct drm_i915_gem_request *signal);
+ int (*signal)(struct drm_i915_gem_request *req);
} semaphore;
/* Execlists */
struct tasklet_struct irq_tasklet;
spinlock_t execlist_lock; /* used inside tasklet, use spin_lock_bh */
struct list_head execlist_queue;
- struct list_head execlist_retired_req_list;
unsigned int fw_domains;
unsigned int next_context_status_buffer;
unsigned int idle_lite_restore_wa;
bool disable_lite_restore_wa;
u32 ctx_desc_template;
- u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
- int (*emit_request)(struct drm_i915_gem_request *request);
- int (*emit_flush)(struct drm_i915_gem_request *request,
- u32 invalidate_domains,
- u32 flush_domains);
- int (*emit_bb_start)(struct drm_i915_gem_request *req,
- u64 offset, unsigned dispatch_flags);
/**
* List of objects currently involved in rendering from the
* inspecting request list.
*/
u32 last_submitted_seqno;
- unsigned user_interrupts;
-
- bool gpu_caches_dirty;
-
- wait_queue_head_t irq_queue;
- struct intel_context *last_context;
+ struct i915_gem_context *last_context;
- struct intel_ring_hangcheck hangcheck;
+ struct intel_engine_hangcheck hangcheck;
struct {
struct drm_i915_gem_object *obj;
u32 gtt_offset;
- volatile u32 *cpu_page;
} scratch;
bool needs_cmd_parser;
/*
* Table of commands the command parser needs to know about
- * for this ring.
+ * for this engine.
*/
DECLARE_HASHTABLE(cmd_hash, I915_CMD_HASH_ORDER);
* Returns the bitmask for the length field of the specified command.
* Return 0 for an unrecognized/invalid command.
*
- * If the command parser finds an entry for a command in the ring's
+ * If the command parser finds an entry for a command in the engine's
* cmd_tables, it gets the command's length based on the table entry.
- * If not, it calls this function to determine the per-ring length field
- * encoding for the command (i.e. certain opcode ranges use certain bits
- * to encode the command length in the header).
+ * If not, it calls this function to determine the per-engine length
+ * field encoding for the command (i.e. different opcode ranges use
+ * certain bits to encode the command length in the header).
*/
u32 (*get_cmd_length_mask)(u32 cmd_header);
};
static inline bool
-intel_engine_initialized(struct intel_engine_cs *engine)
+intel_engine_initialized(const struct intel_engine_cs *engine)
{
- return engine->dev != NULL;
+ return engine->i915 != NULL;
}
static inline unsigned
-intel_engine_flag(struct intel_engine_cs *engine)
+intel_engine_flag(const struct intel_engine_cs *engine)
{
return 1 << engine->id;
}
static inline u32
-intel_ring_sync_index(struct intel_engine_cs *engine,
- struct intel_engine_cs *other)
+intel_engine_sync_index(struct intel_engine_cs *engine,
+ struct intel_engine_cs *other)
{
int idx;
#define I915_GEM_HWS_SCRATCH_INDEX 0x40
#define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
-struct intel_ringbuffer *
-intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size);
-int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
- struct intel_ringbuffer *ringbuf);
-void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
-void intel_ringbuffer_free(struct intel_ringbuffer *ring);
+struct intel_ring *
+intel_engine_create_ring(struct intel_engine_cs *engine, int size);
+int intel_ring_pin(struct intel_ring *ring);
+void intel_ring_unpin(struct intel_ring *ring);
+void intel_ring_free(struct intel_ring *ring);
-void intel_stop_engine(struct intel_engine_cs *engine);
-void intel_cleanup_engine(struct intel_engine_cs *engine);
+void intel_engine_stop(struct intel_engine_cs *engine);
+void intel_engine_cleanup(struct intel_engine_cs *engine);
int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request);
int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
-static inline void intel_ring_emit(struct intel_engine_cs *engine,
- u32 data)
+
+static inline void intel_ring_emit(struct intel_ring *ring, u32 data)
{
- struct intel_ringbuffer *ringbuf = engine->buffer;
- iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
- ringbuf->tail += 4;
+ *(uint32_t *)(ring->vaddr + ring->tail) = data;
+ ring->tail += 4;
}
-static inline void intel_ring_emit_reg(struct intel_engine_cs *engine,
- i915_reg_t reg)
+
+static inline void intel_ring_emit_reg(struct intel_ring *ring, i915_reg_t reg)
{
- intel_ring_emit(engine, i915_mmio_reg_offset(reg));
+ intel_ring_emit(ring, i915_mmio_reg_offset(reg));
}
-static inline void intel_ring_advance(struct intel_engine_cs *engine)
+
+static inline void intel_ring_advance(struct intel_ring *ring)
{
- struct intel_ringbuffer *ringbuf = engine->buffer;
- ringbuf->tail &= ringbuf->size - 1;
+ /* Dummy function.
+ *
+ * This serves as a placeholder in the code so that the reader
+ * can compare against the preceding intel_ring_begin() and
+ * check that the number of dwords emitted matches the space
+ * reserved for the command packet (i.e. the value passed to
+ * intel_ring_begin()).
+ */
+}
+
+static inline u32 intel_ring_offset(struct intel_ring *ring, u32 value)
+{
+ /* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
+ return value & (ring->size - 1);
}
+
int __intel_ring_space(int head, int tail, int size);
-void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
-int intel_ring_space(struct intel_ringbuffer *ringbuf);
-bool intel_engine_stopped(struct intel_engine_cs *engine);
+void intel_ring_update_space(struct intel_ring *ring);
int __must_check intel_engine_idle(struct intel_engine_cs *engine);
-void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno);
-int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
-int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
+void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno);
+int intel_init_pipe_control(struct intel_engine_cs *engine, int size);
void intel_fini_pipe_control(struct intel_engine_cs *engine);
-int intel_init_pipe_control(struct intel_engine_cs *engine);
-int intel_init_render_ring_buffer(struct drm_device *dev);
-int intel_init_bsd_ring_buffer(struct drm_device *dev);
-int intel_init_bsd2_ring_buffer(struct drm_device *dev);
-int intel_init_blt_ring_buffer(struct drm_device *dev);
-int intel_init_vebox_ring_buffer(struct drm_device *dev);
+void intel_engine_setup_common(struct intel_engine_cs *engine);
+int intel_engine_init_common(struct intel_engine_cs *engine);
+void intel_engine_cleanup_common(struct intel_engine_cs *engine);
-u64 intel_ring_get_active_head(struct intel_engine_cs *engine);
+int intel_init_render_ring_buffer(struct intel_engine_cs *engine);
+int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
+int intel_init_bsd2_ring_buffer(struct intel_engine_cs *engine);
+int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
+int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine);
-int init_workarounds_ring(struct intel_engine_cs *engine);
-
-static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
+u64 intel_engine_get_active_head(struct intel_engine_cs *engine);
+static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine)
{
- return ringbuf->tail;
+ return intel_read_status_page(engine, I915_GEM_HWS_INDEX);
}
+int init_workarounds_ring(struct intel_engine_cs *engine);
+
/*
* Arbitrary size for largest possible 'add request' sequence. The code paths
* are complex and variable. Empirical measurement shows that the worst case
- * is ILK at 136 words. Reserving too much is better than reserving too little
- * as that allows for corner cases that might have been missed. So the figure
- * has been rounded up to 160 words.
+ * is BDW at 192 bytes (6 + 6 + 36 dwords), then ILK at 136 bytes. However,
+ * we need to allocate double the largest single packet within that emission
+ * to account for tail wraparound (so 6 + 6 + 72 dwords for BDW).
*/
-#define MIN_SPACE_FOR_ADD_REQUEST 160
+#define MIN_SPACE_FOR_ADD_REQUEST 336
-/*
- * Reserve space in the ring to guarantee that the i915_add_request() call
- * will always have sufficient room to do its stuff. The request creation
- * code calls this automatically.
- */
-void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size);
-/* Cancel the reservation, e.g. because the request is being discarded. */
-void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf);
-/* Use the reserved space - for use by i915_add_request() only. */
-void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf);
-/* Finish with the reserved space - for use by i915_add_request() only. */
-void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf);
-
-/* Legacy ringbuffer specific portion of reservation code: */
-int intel_ring_reserve_space(struct drm_i915_gem_request *request);
+static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
+{
+ return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR;
+}
+
+/* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
+struct intel_wait {
+ struct rb_node node;
+ struct task_struct *tsk;
+ u32 seqno;
+};
+
+struct intel_signal_node {
+ struct rb_node node;
+ struct intel_wait wait;
+};
+
+int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
+
+static inline void intel_wait_init(struct intel_wait *wait, u32 seqno)
+{
+ wait->tsk = current;
+ wait->seqno = seqno;
+}
+
+static inline bool intel_wait_complete(const struct intel_wait *wait)
+{
+ return RB_EMPTY_NODE(&wait->node);
+}
+
+bool intel_engine_add_wait(struct intel_engine_cs *engine,
+ struct intel_wait *wait);
+void intel_engine_remove_wait(struct intel_engine_cs *engine,
+ struct intel_wait *wait);
+void intel_engine_enable_signaling(struct drm_i915_gem_request *request);
+
+static inline bool intel_engine_has_waiter(struct intel_engine_cs *engine)
+{
+ return READ_ONCE(engine->breadcrumbs.irq_seqno_bh);
+}
+
+static inline bool intel_engine_wakeup(struct intel_engine_cs *engine)
+{
+ bool wakeup = false;
+ struct task_struct *tsk = READ_ONCE(engine->breadcrumbs.irq_seqno_bh);
+ /* Note that for this not to dangerously chase a dangling pointer,
+ * the caller is responsible for ensure that the task remain valid for
+ * wake_up_process() i.e. that the RCU grace period cannot expire.
+ *
+ * Also note that tsk is likely to be in !TASK_RUNNING state so an
+ * early test for tsk->state != TASK_RUNNING before wake_up_process()
+ * is unlikely to be beneficial.
+ */
+ if (tsk)
+ wakeup = wake_up_process(tsk);
+ return wakeup;
+}
+
+void intel_engine_enable_fake_irq(struct intel_engine_cs *engine);
+void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
+unsigned int intel_kick_waiters(struct drm_i915_private *i915);
+unsigned int intel_kick_signalers(struct drm_i915_private *i915);
#endif /* _INTEL_RINGBUFFER_H_ */
projects / karo-tx-linux.git / blobdiff