drm/msm: introduce msm_fence_context

Better encapsulate the per-timeline stuff into fence-context.  For now
there is just a single fence-context, but eventually we'll also have one
per-CRTC to enable fully explicit fencing.

Signed-off-by: Rob Clark <robdclark@gmail.com>
This commit is contained in:
Rob Clark 2016-03-15 17:22:13 -04:00
parent 340faef241
commit ca762a8ae7
9 changed files with 108 additions and 78 deletions

View File

@ -121,7 +121,7 @@ void adreno_recover(struct msm_gpu *gpu)
gpu->rb->cur = gpu->rb->start;
/* reset completed fence seqno, just discard anything pending: */
adreno_gpu->memptrs->fence = gpu->submitted_fence;
adreno_gpu->memptrs->fence = gpu->fctx->last_fence;
adreno_gpu->memptrs->rptr = 0;
adreno_gpu->memptrs->wptr = 0;
@ -254,7 +254,7 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
adreno_gpu->rev.patchid);
seq_printf(m, "fence: %d/%d\n", adreno_gpu->memptrs->fence,
gpu->submitted_fence);
gpu->fctx->last_fence);
seq_printf(m, "rptr: %d\n", get_rptr(adreno_gpu));
seq_printf(m, "wptr: %d\n", adreno_gpu->memptrs->wptr);
seq_printf(m, "rb wptr: %d\n", get_wptr(gpu->rb));
@ -295,7 +295,7 @@ void adreno_dump_info(struct msm_gpu *gpu)
adreno_gpu->rev.patchid);
printk("fence: %d/%d\n", adreno_gpu->memptrs->fence,
gpu->submitted_fence);
gpu->fctx->last_fence);
printk("rptr: %d\n", get_rptr(adreno_gpu));
printk("wptr: %d\n", adreno_gpu->memptrs->wptr);
printk("rb wptr: %d\n", get_wptr(gpu->rb));

View File

@ -18,6 +18,7 @@
#include "msm_drv.h"
#include "msm_kms.h"
#include "msm_gem.h"
#include "msm_gpu.h" /* temporary */
#include "msm_fence.h"
struct msm_commit {
@ -202,6 +203,7 @@ int msm_atomic_check(struct drm_device *dev,
int msm_atomic_commit(struct drm_device *dev,
struct drm_atomic_state *state, bool nonblock)
{
struct msm_drm_private *priv = dev->dev_private;
int nplanes = dev->mode_config.num_total_plane;
int ncrtcs = dev->mode_config.num_crtc;
ktime_t timeout;
@ -276,15 +278,16 @@ int msm_atomic_commit(struct drm_device *dev,
* current layout.
*/
if (nonblock) {
msm_queue_fence_cb(dev, &c->fence_cb, c->fence);
if (nonblock && priv->gpu) {
msm_queue_fence_cb(priv->gpu->fctx, &c->fence_cb, c->fence);
return 0;
}
timeout = ktime_add_ms(ktime_get(), 1000);
/* uninterruptible wait */
msm_wait_fence(dev, c->fence, &timeout, false);
if (priv->gpu)
msm_wait_fence(priv->gpu->fctx, c->fence, &timeout, false);
complete_commit(c);

View File

@ -339,11 +339,9 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
dev->dev_private = priv;
priv->wq = alloc_ordered_workqueue("msm", 0);
init_waitqueue_head(&priv->fence_event);
init_waitqueue_head(&priv->pending_crtcs_event);
INIT_LIST_HEAD(&priv->inactive_list);
INIT_LIST_HEAD(&priv->fence_cbs);
INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
INIT_WORK(&priv->vblank_ctrl.work, vblank_ctrl_worker);
spin_lock_init(&priv->vblank_ctrl.lock);
@ -647,6 +645,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct msm_drm_private *priv = dev->dev_private;
struct drm_msm_wait_fence *args = data;
ktime_t timeout = to_ktime(args->timeout);
@ -655,7 +654,10 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
return -EINVAL;
}
return msm_wait_fence(dev, args->fence, &timeout, true);
if (!priv->gpu)
return 0;
return msm_wait_fence(priv->gpu->fctx, args->fence, &timeout, true);
}
static const struct drm_ioctl_desc msm_ioctls[] = {

View File

@ -49,6 +49,7 @@ struct msm_mmu;
struct msm_rd_state;
struct msm_perf_state;
struct msm_gem_submit;
struct msm_fence_context;
struct msm_fence_cb;
#define NUM_DOMAINS 2 /* one for KMS, then one per gpu core (?) */
@ -101,9 +102,6 @@ struct msm_drm_private {
struct drm_fb_helper *fbdev;
uint32_t next_fence, completed_fence;
wait_queue_head_t fence_event;
struct msm_rd_state *rd;
struct msm_perf_state *perf;
@ -112,9 +110,6 @@ struct msm_drm_private {
struct workqueue_struct *wq;
/* callbacks deferred until bo is inactive: */
struct list_head fence_cbs;
/* crtcs pending async atomic updates: */
uint32_t pending_crtcs;
wait_queue_head_t pending_crtcs_event;
@ -194,8 +189,6 @@ int msm_gem_prime_pin(struct drm_gem_object *obj);
void msm_gem_prime_unpin(struct drm_gem_object *obj);
void *msm_gem_vaddr_locked(struct drm_gem_object *obj);
void *msm_gem_vaddr(struct drm_gem_object *obj);
int msm_gem_queue_inactive_cb(struct drm_gem_object *obj,
struct msm_fence_cb *cb);
void msm_gem_move_to_active(struct drm_gem_object *obj,
struct msm_gpu *gpu, bool write, uint32_t fence);
void msm_gem_move_to_inactive(struct drm_gem_object *obj);

View File

@ -15,49 +15,68 @@
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/fence.h>
#include "msm_drv.h"
#include "msm_fence.h"
#include "msm_gpu.h"
static inline bool fence_completed(struct drm_device *dev, uint32_t fence)
struct msm_fence_context *
msm_fence_context_alloc(struct drm_device *dev, const char *name)
{
struct msm_drm_private *priv = dev->dev_private;
return (int32_t)(priv->completed_fence - fence) >= 0;
struct msm_fence_context *fctx;
fctx = kzalloc(sizeof(*fctx), GFP_KERNEL);
if (!fctx)
return ERR_PTR(-ENOMEM);
fctx->dev = dev;
fctx->name = name;
init_waitqueue_head(&fctx->event);
INIT_LIST_HEAD(&fctx->fence_cbs);
return fctx;
}
int msm_wait_fence(struct drm_device *dev, uint32_t fence,
ktime_t *timeout , bool interruptible)
void msm_fence_context_free(struct msm_fence_context *fctx)
{
kfree(fctx);
}
static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fence)
{
return (int32_t)(fctx->completed_fence - fence) >= 0;
}
int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
ktime_t *timeout, bool interruptible)
{
struct msm_drm_private *priv = dev->dev_private;
int ret;
if (!priv->gpu)
return 0;
if (fence > priv->gpu->submitted_fence) {
DRM_ERROR("waiting on invalid fence: %u (of %u)\n",
fence, priv->gpu->submitted_fence);
if (fence > fctx->last_fence) {
DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n",
fctx->name, fence, fctx->last_fence);
return -EINVAL;
}
if (!timeout) {
/* no-wait: */
ret = fence_completed(dev, fence) ? 0 : -EBUSY;
ret = fence_completed(fctx, fence) ? 0 : -EBUSY;
} else {
unsigned long remaining_jiffies = timeout_to_jiffies(timeout);
if (interruptible)
ret = wait_event_interruptible_timeout(priv->fence_event,
fence_completed(dev, fence),
ret = wait_event_interruptible_timeout(fctx->event,
fence_completed(fctx, fence),
remaining_jiffies);
else
ret = wait_event_timeout(priv->fence_event,
fence_completed(dev, fence),
ret = wait_event_timeout(fctx->event,
fence_completed(fctx, fence),
remaining_jiffies);
if (ret == 0) {
DBG("timeout waiting for fence: %u (completed: %u)",
fence, priv->completed_fence);
fence, fctx->completed_fence);
ret = -ETIMEDOUT;
} else if (ret != -ERESTARTSYS) {
ret = 0;
@ -67,50 +86,50 @@ int msm_wait_fence(struct drm_device *dev, uint32_t fence,
return ret;
}
int msm_queue_fence_cb(struct drm_device *dev,
int msm_queue_fence_cb(struct msm_fence_context *fctx,
struct msm_fence_cb *cb, uint32_t fence)
{
struct msm_drm_private *priv = dev->dev_private;
struct msm_drm_private *priv = fctx->dev->dev_private;
int ret = 0;
mutex_lock(&dev->struct_mutex);
mutex_lock(&fctx->dev->struct_mutex);
if (!list_empty(&cb->work.entry)) {
ret = -EINVAL;
} else if (fence > priv->completed_fence) {
} else if (fence > fctx->completed_fence) {
cb->fence = fence;
list_add_tail(&cb->work.entry, &priv->fence_cbs);
list_add_tail(&cb->work.entry, &fctx->fence_cbs);
} else {
queue_work(priv->wq, &cb->work);
}
mutex_unlock(&dev->struct_mutex);
mutex_unlock(&fctx->dev->struct_mutex);
return ret;
}
/* called from workqueue */
void msm_update_fence(struct drm_device *dev, uint32_t fence)
void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
{
struct msm_drm_private *priv = dev->dev_private;
struct msm_drm_private *priv = fctx->dev->dev_private;
mutex_lock(&dev->struct_mutex);
priv->completed_fence = max(fence, priv->completed_fence);
mutex_lock(&fctx->dev->struct_mutex);
fctx->completed_fence = max(fence, fctx->completed_fence);
while (!list_empty(&priv->fence_cbs)) {
while (!list_empty(&fctx->fence_cbs)) {
struct msm_fence_cb *cb;
cb = list_first_entry(&priv->fence_cbs,
cb = list_first_entry(&fctx->fence_cbs,
struct msm_fence_cb, work.entry);
if (cb->fence > priv->completed_fence)
if (cb->fence > fctx->completed_fence)
break;
list_del_init(&cb->work.entry);
queue_work(priv->wq, &cb->work);
}
mutex_unlock(&dev->struct_mutex);
mutex_unlock(&fctx->dev->struct_mutex);
wake_up_all(&priv->fence_event);
wake_up_all(&fctx->event);
}
void __msm_fence_worker(struct work_struct *work)

View File

@ -20,6 +20,21 @@
#include "msm_drv.h"
struct msm_fence_context {
struct drm_device *dev;
const char *name;
/* last_fence == completed_fence --> no pending work */
uint32_t last_fence; /* last assigned fence */
uint32_t completed_fence; /* last completed fence */
wait_queue_head_t event;
/* callbacks deferred until bo is inactive: */
struct list_head fence_cbs;
};
struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
const char *name);
void msm_fence_context_free(struct msm_fence_context *fctx);
/* callback from wq once fence has passed: */
struct msm_fence_cb {
struct work_struct work;
@ -34,10 +49,10 @@ void __msm_fence_worker(struct work_struct *work);
(_cb)->func = _func; \
} while (0)
int msm_wait_fence(struct drm_device *dev, uint32_t fence,
int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
ktime_t *timeout, bool interruptible);
int msm_queue_fence_cb(struct drm_device *dev,
int msm_queue_fence_cb(struct msm_fence_context *fctx,
struct msm_fence_cb *cb, uint32_t fence);
void msm_update_fence(struct drm_device *dev, uint32_t fence);
void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
#endif

View File

@ -411,18 +411,6 @@ void *msm_gem_vaddr(struct drm_gem_object *obj)
return ret;
}
/* setup callback for when bo is no longer busy..
* TODO probably want to differentiate read vs write..
*/
int msm_gem_queue_inactive_cb(struct drm_gem_object *obj,
struct msm_fence_cb *cb)
{
struct msm_gem_object *msm_obj = to_msm_bo(obj);
uint32_t fence = msm_gem_fence(msm_obj,
MSM_PREP_READ | MSM_PREP_WRITE);
return msm_queue_fence_cb(obj->dev, cb, fence);
}
void msm_gem_move_to_active(struct drm_gem_object *obj,
struct msm_gpu *gpu, bool write, uint32_t fence)
{
@ -454,6 +442,7 @@ void msm_gem_move_to_inactive(struct drm_gem_object *obj)
int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
{
struct drm_device *dev = obj->dev;
struct msm_drm_private *priv = dev->dev_private;
struct msm_gem_object *msm_obj = to_msm_bo(obj);
int ret = 0;
@ -463,7 +452,8 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
if (op & MSM_PREP_NOSYNC)
timeout = NULL;
ret = msm_wait_fence(dev, fence, timeout, true);
if (priv->gpu)
ret = msm_wait_fence(priv->gpu->fctx, fence, timeout, true);
}
/* TODO cache maintenance */

View File

@ -313,7 +313,7 @@ static void hangcheck_handler(unsigned long data)
if (fence != gpu->hangcheck_fence) {
/* some progress has been made.. ya! */
gpu->hangcheck_fence = fence;
} else if (fence < gpu->submitted_fence) {
} else if (fence < gpu->fctx->last_fence) {
/* no progress and not done.. hung! */
gpu->hangcheck_fence = fence;
dev_err(dev->dev, "%s: hangcheck detected gpu lockup!\n",
@ -321,12 +321,12 @@ static void hangcheck_handler(unsigned long data)
dev_err(dev->dev, "%s: completed fence: %u\n",
gpu->name, fence);
dev_err(dev->dev, "%s: submitted fence: %u\n",
gpu->name, gpu->submitted_fence);
gpu->name, gpu->fctx->last_fence);
queue_work(priv->wq, &gpu->recover_work);
}
/* if still more pending work, reset the hangcheck timer: */
if (gpu->submitted_fence > gpu->hangcheck_fence)
if (gpu->fctx->last_fence > gpu->hangcheck_fence)
hangcheck_timer_reset(gpu);
/* workaround for missing irq: */
@ -474,7 +474,7 @@ static void retire_worker(struct work_struct *work)
struct drm_device *dev = gpu->dev;
uint32_t fence = gpu->funcs->last_fence(gpu);
msm_update_fence(gpu->dev, fence);
msm_update_fence(gpu->fctx, fence);
mutex_lock(&dev->struct_mutex);
retire_submits(gpu, fence);
@ -502,9 +502,7 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
WARN_ON(!mutex_is_locked(&dev->struct_mutex));
submit->fence = ++priv->next_fence;
gpu->submitted_fence = submit->fence;
submit->fence = ++gpu->fctx->last_fence;
inactive_cancel(gpu);
@ -512,8 +510,6 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
msm_rd_dump_submit(submit);
gpu->submitted_fence = submit->fence;
update_sw_cntrs(gpu);
for (i = 0; i < submit->nr_bos; i++) {
@ -574,6 +570,12 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
gpu->funcs = funcs;
gpu->name = name;
gpu->inactive = true;
gpu->fctx = msm_fence_context_alloc(drm, name);
if (IS_ERR(gpu->fctx)) {
ret = PTR_ERR(gpu->fctx);
gpu->fctx = NULL;
goto fail;
}
INIT_LIST_HEAD(&gpu->active_list);
INIT_WORK(&gpu->retire_work, retire_worker);
@ -694,4 +696,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
if (gpu->mmu)
gpu->mmu->funcs->destroy(gpu->mmu);
if (gpu->fctx)
msm_fence_context_free(gpu->fctx);
}

View File

@ -22,6 +22,7 @@
#include <linux/regulator/consumer.h>
#include "msm_drv.h"
#include "msm_fence.h"
#include "msm_ringbuffer.h"
struct msm_gem_submit;
@ -77,13 +78,15 @@ struct msm_gpu {
const struct msm_gpu_perfcntr *perfcntrs;
uint32_t num_perfcntrs;
/* ringbuffer: */
struct msm_ringbuffer *rb;
uint32_t rb_iova;
/* list of GEM active objects: */
struct list_head active_list;
uint32_t submitted_fence;
/* fencing: */
struct msm_fence_context *fctx;
/* is gpu powered/active? */
int active_cnt;
@ -125,7 +128,7 @@ struct msm_gpu {
static inline bool msm_gpu_active(struct msm_gpu *gpu)
{
return gpu->submitted_fence > gpu->funcs->last_fence(gpu);
return gpu->fctx->last_fence > gpu->funcs->last_fence(gpu);
}
/* Perf-Counters: