UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Revert "drm/i915: Avoid using PIPE_CONTROL on Ironlake" 

Restore PIPE_CONTROL once again just for Ironlake, as it appears that
MI_USER_INTERRUPT does not have the same coherency guarantees, that is
on Ironlake the interrupt following a GPU write is not guaranteed to
arrive after the write is coherent from the CPU, as it does on the
other generations.

Reported-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reported-by: Shuang He <shuang.he@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=32402
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This commit is contained in:
Chris Wilson 2010-12-15 09:56:50 +00:00
parent 1b894b5924
commit c6df541c00
2 changed files with 162 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
drivers/gpu/drm/i915/i915_irq.c
View File

@ -349,7 +349,7 @@ static irqreturn_t ironlake_irq_handler(struct drm_device *dev)
READ_BREADCRUMB(dev_priv);
}
if (gt_iir & GT_USER_INTERRUPT)
if (gt_iir & (GT_USER_INTERRUPT | GT_PIPE_NOTIFY))
notify_ring(dev, &dev_priv->ring[RCS]);
if (gt_iir & bsd_usr_interrupt)
notify_ring(dev, &dev_priv->ring[VCS]);
@ -1558,6 +1558,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
else
render_irqs =
GT_USER_INTERRUPT |
GT_PIPE_NOTIFY |
GT_BSD_USER_INTERRUPT;
I915_WRITE(GTIER, render_irqs);
POSTING_READ(GTIER);

162
drivers/gpu/drm/i915/intel_ringbuffer.c
View File

@ -209,6 +209,78 @@ static int init_ring_common(struct intel_ring_buffer *ring)
return 0;
}
/*
* 965+ support PIPE_CONTROL commands, which provide finer grained control
* over cache flushing.
*/
struct pipe_control {
struct drm_i915_gem_object *obj;
volatile u32 *cpu_page;
u32 gtt_offset;
};
static int
init_pipe_control(struct intel_ring_buffer *ring)
{
struct pipe_control *pc;
struct drm_i915_gem_object *obj;
int ret;
if (ring->private)
return 0;
pc = kmalloc(sizeof(*pc), GFP_KERNEL);
if (!pc)
return -ENOMEM;
obj = i915_gem_alloc_object(ring->dev, 4096);
if (obj == NULL) {
DRM_ERROR("Failed to allocate seqno page\n");
ret = -ENOMEM;
goto err;
}
obj->agp_type = AGP_USER_CACHED_MEMORY;
ret = i915_gem_object_pin(obj, 4096, true);
if (ret)
goto err_unref;
pc->gtt_offset = obj->gtt_offset;
pc->cpu_page = kmap(obj->pages[0]);
if (pc->cpu_page == NULL)
goto err_unpin;
pc->obj = obj;
ring->private = pc;
return 0;
err_unpin:
i915_gem_object_unpin(obj);
err_unref:
drm_gem_object_unreference(&obj->base);
err:
kfree(pc);
return ret;
}
static void
cleanup_pipe_control(struct intel_ring_buffer *ring)
{
struct pipe_control *pc = ring->private;
struct drm_i915_gem_object *obj;
if (!ring->private)
return;
obj = pc->obj;
kunmap(obj->pages[0]);
i915_gem_object_unpin(obj);
drm_gem_object_unreference(&obj->base);
kfree(pc);
ring->private = NULL;
}
static int init_render_ring(struct intel_ring_buffer *ring)
{
struct drm_device *dev = ring->dev;
@ -222,9 +294,24 @@ static int init_render_ring(struct intel_ring_buffer *ring)
I915_WRITE(MI_MODE, mode);
}
if (INTEL_INFO(dev)->gen >= 6) {
} else if (IS_GEN5(dev)) {
ret = init_pipe_control(ring);
if (ret)
return ret;
}
return ret;
}
static void render_ring_cleanup(struct intel_ring_buffer *ring)
{
if (!ring->private)
return;
cleanup_pipe_control(ring);
}
static void
update_semaphore(struct intel_ring_buffer *ring, int i, u32 seqno)
{
@ -299,6 +386,65 @@ intel_ring_sync(struct intel_ring_buffer *ring,
return 0;
}
#define PIPE_CONTROL_FLUSH(ring__, addr__) \
do { \
intel_ring_emit(ring__, GFX_OP_PIPE_CONTROL | PIPE_CONTROL_QW_WRITE | \
PIPE_CONTROL_DEPTH_STALL | 2); \
intel_ring_emit(ring__, (addr__) | PIPE_CONTROL_GLOBAL_GTT); \
intel_ring_emit(ring__, 0); \
intel_ring_emit(ring__, 0); \
} while (0)
static int
pc_render_add_request(struct intel_ring_buffer *ring,
u32 *result)
{
struct drm_device *dev = ring->dev;
u32 seqno = i915_gem_get_seqno(dev);
struct pipe_control *pc = ring->private;
u32 scratch_addr = pc->gtt_offset + 128;
int ret;
/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
* incoherent with writes to memory, i.e. completely fubar,
* so we need to use PIPE_NOTIFY instead.
*
* However, we also need to workaround the qword write
* incoherence by flushing the 6 PIPE_NOTIFY buffers out to
* memory before requesting an interrupt.
*/
ret = intel_ring_begin(ring, 32);
if (ret)
return ret;
intel_ring_emit(ring, GFX_OP_PIPE_CONTROL | PIPE_CONTROL_QW_WRITE |
PIPE_CONTROL_WC_FLUSH | PIPE_CONTROL_TC_FLUSH);
intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
intel_ring_emit(ring, seqno);
intel_ring_emit(ring, 0);
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 128; /* write to separate cachelines */
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 128;
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 128;
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 128;
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 128;
PIPE_CONTROL_FLUSH(ring, scratch_addr);
intel_ring_emit(ring, GFX_OP_PIPE_CONTROL | PIPE_CONTROL_QW_WRITE |
PIPE_CONTROL_WC_FLUSH | PIPE_CONTROL_TC_FLUSH |
PIPE_CONTROL_NOTIFY);
intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
intel_ring_emit(ring, seqno);
intel_ring_emit(ring, 0);
intel_ring_advance(ring);
*result = seqno;
return 0;
}
static int
render_ring_add_request(struct intel_ring_buffer *ring,
u32 *result)
@ -327,6 +473,13 @@ ring_get_seqno(struct intel_ring_buffer *ring)
return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
}
static u32
pc_render_get_seqno(struct intel_ring_buffer *ring)
{
struct pipe_control *pc = ring->private;
return pc->cpu_page[0];
}
static bool
render_ring_get_irq(struct intel_ring_buffer *ring)
{
@ -342,7 +495,7 @@ render_ring_get_irq(struct intel_ring_buffer *ring)
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (HAS_PCH_SPLIT(dev))
ironlake_enable_graphics_irq(dev_priv,
GT_USER_INTERRUPT);
GT_PIPE_NOTIFY | GT_USER_INTERRUPT);
else
i915_enable_irq(dev_priv, I915_USER_INTERRUPT);
spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
@ -363,7 +516,8 @@ render_ring_put_irq(struct intel_ring_buffer *ring)
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (HAS_PCH_SPLIT(dev))
ironlake_disable_graphics_irq(dev_priv,
GT_USER_INTERRUPT);
GT_USER_INTERRUPT |
GT_PIPE_NOTIFY);
else
i915_disable_irq(dev_priv, I915_USER_INTERRUPT);
spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
@ -776,6 +930,7 @@ static const struct intel_ring_buffer render_ring = {
.irq_get = render_ring_get_irq,
.irq_put = render_ring_put_irq,
.dispatch_execbuffer = render_ring_dispatch_execbuffer,
.cleanup = render_ring_cleanup,
};
/* ring buffer for bit-stream decoder */
@ -1010,6 +1165,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
*ring = render_ring;
if (INTEL_INFO(dev)->gen >= 6) {
ring->add_request = gen6_add_request;
} else if (IS_GEN5(dev)) {
ring->add_request = pc_render_add_request;
ring->get_seqno = pc_render_get_seqno;
}
if (!I915_NEED_GFX_HWS(dev)) {