a71d8d9452
By recording the location of every request in the ringbuffer, we know that in order to retire the request the GPU must have finished reading it and so the GPU head is now beyond the tail of the request. We can therefore provide a conservative estimate of where the GPU is reading from in order to avoid having to read back the ring buffer registers when polling for space upon starting a new write into the ringbuffer. A secondary effect is that this allows us to convert intel_ring_buffer_wait() to use i915_wait_request() and so consolidate upon the single function to handle the complicated task of waiting upon the GPU. A necessary precaution is that we need to make that wait uninterruptible to match the existing conditions as all the callers of intel_ring_begin() have not been audited to handle ERESTARTSYS correctly. By using a conservative estimate for the head, and always processing all outstanding requests first, we prevent a race condition between using the estimate and direct reads of I915_RING_HEAD which could result in the value of the head going backwards, and the tail overflowing once again. We are also careful to mark any request that we skip over in order to free space in ring as consumed which provides a self-consistency check. Given sufficient abuse, such as a set of unthrottled GPU bound cairo-traces, avoiding the use of I915_RING_HEAD gives a 10-20% boost on Sandy Bridge (i5-2520m): firefox-paintball 18927ms -> 15646ms: 1.21x speedup firefox-fishtank 12563ms -> 11278ms: 1.11x speedup which is a mild consolation for the performance those traces achieved from exploiting the buggy autoreported head. v2: Add a few more comments and make request->tail a conservative estimate as suggested by Daniel Vetter. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> [danvet: resolve conflicts with retirement defering and the lack of the autoreport head removal (that will go in through -fixes).] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
220 lines
6.4 KiB
C
220 lines
6.4 KiB
C
#ifndef _INTEL_RINGBUFFER_H_
|
|
#define _INTEL_RINGBUFFER_H_
|
|
|
|
struct intel_hw_status_page {
|
|
u32 __iomem *page_addr;
|
|
unsigned int gfx_addr;
|
|
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_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_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_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_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_NOPID(ring) I915_READ(RING_NOPID((ring)->mmio_base))
|
|
#define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
|
|
#define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
|
|
|
|
struct intel_ring_buffer {
|
|
const char *name;
|
|
enum intel_ring_id {
|
|
RCS = 0x0,
|
|
VCS,
|
|
BCS,
|
|
} id;
|
|
#define I915_NUM_RINGS 3
|
|
u32 mmio_base;
|
|
void __iomem *virtual_start;
|
|
struct drm_device *dev;
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
u32 head;
|
|
u32 tail;
|
|
int space;
|
|
int size;
|
|
int effective_size;
|
|
struct intel_hw_status_page status_page;
|
|
|
|
/** We track the position of the requests in the ring buffer, and
|
|
* when each is retired we increment last_retired_head as the GPU
|
|
* must have finished processing the request and so we know we
|
|
* can advance the ringbuffer up to that position.
|
|
*
|
|
* last_retired_head is set to -1 after the value is consumed so
|
|
* we can detect new retirements.
|
|
*/
|
|
u32 last_retired_head;
|
|
|
|
spinlock_t irq_lock;
|
|
u32 irq_refcount;
|
|
u32 irq_mask;
|
|
u32 irq_seqno; /* last seq seem at irq time */
|
|
u32 trace_irq_seqno;
|
|
u32 waiting_seqno;
|
|
u32 sync_seqno[I915_NUM_RINGS-1];
|
|
bool __must_check (*irq_get)(struct intel_ring_buffer *ring);
|
|
void (*irq_put)(struct intel_ring_buffer *ring);
|
|
|
|
int (*init)(struct intel_ring_buffer *ring);
|
|
|
|
void (*write_tail)(struct intel_ring_buffer *ring,
|
|
u32 value);
|
|
int __must_check (*flush)(struct intel_ring_buffer *ring,
|
|
u32 invalidate_domains,
|
|
u32 flush_domains);
|
|
int (*add_request)(struct intel_ring_buffer *ring,
|
|
u32 *seqno);
|
|
u32 (*get_seqno)(struct intel_ring_buffer *ring);
|
|
int (*dispatch_execbuffer)(struct intel_ring_buffer *ring,
|
|
u32 offset, u32 length);
|
|
void (*cleanup)(struct intel_ring_buffer *ring);
|
|
int (*sync_to)(struct intel_ring_buffer *ring,
|
|
struct intel_ring_buffer *to,
|
|
u32 seqno);
|
|
|
|
u32 semaphore_register[3]; /*our mbox written by others */
|
|
u32 signal_mbox[2]; /* mboxes this ring signals to */
|
|
/**
|
|
* List of objects currently involved in rendering from the
|
|
* ringbuffer.
|
|
*
|
|
* Includes buffers having the contents of their GPU caches
|
|
* flushed, not necessarily primitives. last_rendering_seqno
|
|
* represents when the rendering involved will be completed.
|
|
*
|
|
* A reference is held on the buffer while on this list.
|
|
*/
|
|
struct list_head active_list;
|
|
|
|
/**
|
|
* List of breadcrumbs associated with GPU requests currently
|
|
* outstanding.
|
|
*/
|
|
struct list_head request_list;
|
|
|
|
/**
|
|
* List of objects currently pending a GPU write flush.
|
|
*
|
|
* All elements on this list will belong to either the
|
|
* active_list or flushing_list, last_rendering_seqno can
|
|
* be used to differentiate between the two elements.
|
|
*/
|
|
struct list_head gpu_write_list;
|
|
|
|
/**
|
|
* Do we have some not yet emitted requests outstanding?
|
|
*/
|
|
u32 outstanding_lazy_request;
|
|
|
|
wait_queue_head_t irq_queue;
|
|
drm_local_map_t map;
|
|
|
|
void *private;
|
|
};
|
|
|
|
static inline unsigned
|
|
intel_ring_flag(struct intel_ring_buffer *ring)
|
|
{
|
|
return 1 << ring->id;
|
|
}
|
|
|
|
static inline u32
|
|
intel_ring_sync_index(struct intel_ring_buffer *ring,
|
|
struct intel_ring_buffer *other)
|
|
{
|
|
int idx;
|
|
|
|
/*
|
|
* cs -> 0 = vcs, 1 = bcs
|
|
* vcs -> 0 = bcs, 1 = cs,
|
|
* bcs -> 0 = cs, 1 = vcs.
|
|
*/
|
|
|
|
idx = (other - ring) - 1;
|
|
if (idx < 0)
|
|
idx += I915_NUM_RINGS;
|
|
|
|
return idx;
|
|
}
|
|
|
|
static inline u32
|
|
intel_read_status_page(struct intel_ring_buffer *ring,
|
|
int reg)
|
|
{
|
|
return ioread32(ring->status_page.page_addr + reg);
|
|
}
|
|
|
|
/**
|
|
* Reads a dword out of the status page, which is written to from the command
|
|
* queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or
|
|
* MI_STORE_DATA_IMM.
|
|
*
|
|
* The following dwords have a reserved meaning:
|
|
* 0x00: ISR copy, updated when an ISR bit not set in the HWSTAM changes.
|
|
* 0x04: ring 0 head pointer
|
|
* 0x05: ring 1 head pointer (915-class)
|
|
* 0x06: ring 2 head pointer (915-class)
|
|
* 0x10-0x1b: Context status DWords (GM45)
|
|
* 0x1f: Last written status offset. (GM45)
|
|
*
|
|
* The area from dword 0x20 to 0x3ff is available for driver usage.
|
|
*/
|
|
#define READ_HWSP(dev_priv, reg) intel_read_status_page(LP_RING(dev_priv), reg)
|
|
#define READ_BREADCRUMB(dev_priv) READ_HWSP(dev_priv, I915_BREADCRUMB_INDEX)
|
|
#define I915_GEM_HWS_INDEX 0x20
|
|
#define I915_BREADCRUMB_INDEX 0x21
|
|
|
|
void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
|
|
|
|
int __must_check intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n);
|
|
static inline int intel_wait_ring_idle(struct intel_ring_buffer *ring)
|
|
{
|
|
return intel_wait_ring_buffer(ring, ring->size - 8);
|
|
}
|
|
|
|
int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
|
|
|
|
static inline void intel_ring_emit(struct intel_ring_buffer *ring,
|
|
u32 data)
|
|
{
|
|
iowrite32(data, ring->virtual_start + ring->tail);
|
|
ring->tail += 4;
|
|
}
|
|
|
|
void intel_ring_advance(struct intel_ring_buffer *ring);
|
|
|
|
u32 intel_ring_get_seqno(struct intel_ring_buffer *ring);
|
|
|
|
int intel_init_render_ring_buffer(struct drm_device *dev);
|
|
int intel_init_bsd_ring_buffer(struct drm_device *dev);
|
|
int intel_init_blt_ring_buffer(struct drm_device *dev);
|
|
|
|
u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
|
|
void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
|
|
|
|
static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
|
|
{
|
|
return ring->tail;
|
|
}
|
|
|
|
static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno)
|
|
{
|
|
if (ring->trace_irq_seqno == 0 && ring->irq_get(ring))
|
|
ring->trace_irq_seqno = seqno;
|
|
}
|
|
|
|
/* DRI warts */
|
|
int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size);
|
|
|
|
#endif /* _INTEL_RINGBUFFER_H_ */
|