DIV_ROUND_UP(size, NUM_BYTES_PER_CCS_BYTE) : 0;
}
+bool xe_device_mem_access_ongoing(struct xe_device *xe)
+{
+ if (xe_pm_read_callback_task(xe) != NULL)
+ return true;
+
+ return atomic_read(&xe->mem_access.ref);
+}
+
+void xe_device_assert_mem_access(struct xe_device *xe)
+{
+ XE_WARN_ON(!xe_device_mem_access_ongoing(xe));
+}
+
bool xe_device_mem_access_get_if_ongoing(struct xe_device *xe)
{
- return atomic_inc_not_zero(&xe->mem_access.ref);
+ bool active;
+
+ if (xe_pm_read_callback_task(xe) == current)
+ return true;
+
+ active = xe_pm_runtime_get_if_active(xe);
+ if (active) {
+ int ref = atomic_inc_return(&xe->mem_access.ref);
+
+ XE_WARN_ON(ref == S32_MAX);
+ }
+
+ return active;
}
void xe_device_mem_access_get(struct xe_device *xe)
{
- bool resumed = xe_pm_runtime_resume_if_suspended(xe);
- int ref = atomic_inc_return(&xe->mem_access.ref);
-
- if (ref == 1)
- xe->mem_access.hold_rpm = xe_pm_runtime_get_if_active(xe);
+ int ref;
+
+ /*
+ * This looks racy, but should be fine since the pm_callback_task only
+ * transitions from NULL -> current (and back to NULL again), during the
+ * runtime_resume() or runtime_suspend() callbacks, for which there can
+ * only be a single one running for our device. We only need to prevent
+ * recursively calling the runtime_get or runtime_put from those
+ * callbacks, as well as preventing triggering any access_ongoing
+ * asserts.
+ */
+ if (xe_pm_read_callback_task(xe) == current)
+ return;
- /* The usage counter increased if device was immediately resumed */
- if (resumed)
- xe_pm_runtime_put(xe);
+ xe_pm_runtime_get(xe);
+ ref = atomic_inc_return(&xe->mem_access.ref);
XE_WARN_ON(ref == S32_MAX);
}
void xe_device_mem_access_put(struct xe_device *xe)
{
- bool hold = xe->mem_access.hold_rpm;
- int ref = atomic_dec_return(&xe->mem_access.ref);
+ int ref;
+
+ if (xe_pm_read_callback_task(xe) == current)
+ return;
- if (!ref && hold)
- xe_pm_runtime_put(xe);
+ ref = atomic_dec_return(&xe->mem_access.ref);
+ xe_pm_runtime_put(xe);
XE_WARN_ON(ref < 0);
}
bool xe_device_mem_access_get_if_ongoing(struct xe_device *xe);
void xe_device_mem_access_put(struct xe_device *xe);
-static inline bool xe_device_mem_access_ongoing(struct xe_device *xe)
-{
- return atomic_read(&xe->mem_access.ref);
-}
-
-static inline void xe_device_assert_mem_access(struct xe_device *xe)
-{
- XE_WARN_ON(!xe_device_mem_access_ongoing(xe));
-}
+void xe_device_assert_mem_access(struct xe_device *xe);
+bool xe_device_mem_access_ongoing(struct xe_device *xe);
static inline bool xe_device_in_fault_mode(struct xe_device *xe)
{
struct {
/** @ref: ref count of memory accesses */
atomic_t ref;
- /** @hold_rpm: need to put rpm ref back at the end */
- bool hold_rpm;
} mem_access;
/** @d3cold: Encapsulate d3cold related stuff */
struct mutex lock;
} d3cold;
+ /**
+ * @pm_callback_task: Track the active task that is running in either
+ * the runtime_suspend or runtime_resume callbacks.
+ */
+ struct task_struct *pm_callback_task;
+
/* For pcode */
struct mutex sb_lock;
#include "xe_guc.h"
#include "xe_guc_submit.h"
#include "xe_map.h"
+#include "xe_pm.h"
#include "xe_trace.h"
/* Used when a CT send wants to block and / or receive data */
void xe_guc_ct_fast_path(struct xe_guc_ct *ct)
{
struct xe_device *xe = ct_to_xe(ct);
+ bool ongoing;
int len;
- if (!xe_device_mem_access_get_if_ongoing(xe))
+ ongoing = xe_device_mem_access_get_if_ongoing(ct_to_xe(ct));
+ if (!ongoing && xe_pm_read_callback_task(ct_to_xe(ct)) == NULL)
return;
spin_lock(&ct->fast_lock);
} while (len > 0);
spin_unlock(&ct->fast_lock);
- xe_device_mem_access_put(xe);
+ if (ongoing)
+ xe_device_mem_access_put(xe);
}
/* Returns less than zero on error, 0 on done, 1 on more available */
static void g2h_worker_func(struct work_struct *w)
{
struct xe_guc_ct *ct = container_of(w, struct xe_guc_ct, g2h_worker);
+ bool ongoing;
int ret;
- xe_device_mem_access_get(ct_to_xe(ct));
+ /*
+ * Normal users must always hold mem_access.ref around CT calls. However
+ * during the runtime pm callbacks we rely on CT to talk to the GuC, but
+ * at this stage we can't rely on mem_access.ref and even the
+ * callback_task will be different than current. For such cases we just
+ * need to ensure we always process the responses from any blocking
+ * ct_send requests or where we otherwise expect some response when
+ * initiated from those callbacks (which will need to wait for the below
+ * dequeue_one_g2h()). The dequeue_one_g2h() will gracefully fail if
+ * the device has suspended to the point that the CT communication has
+ * been disabled.
+ *
+ * If we are inside the runtime pm callback, we can be the only task
+ * still issuing CT requests (since that requires having the
+ * mem_access.ref). It seems like it might in theory be possible to
+ * receive unsolicited events from the GuC just as we are
+ * suspending-resuming, but those will currently anyway be lost when
+ * eventually exiting from suspend, hence no need to wake up the device
+ * here. If we ever need something stronger than get_if_ongoing() then
+ * we need to be careful with blocking the pm callbacks from getting CT
+ * responses, if the worker here is blocked on those callbacks
+ * completing, creating a deadlock.
+ */
+ ongoing = xe_device_mem_access_get_if_ongoing(ct_to_xe(ct));
+ if (!ongoing && xe_pm_read_callback_task(ct_to_xe(ct)) == NULL)
+ return;
+
do {
mutex_lock(&ct->lock);
ret = dequeue_one_g2h(ct);
kick_reset(ct);
}
} while (ret == 1);
- xe_device_mem_access_put(ct_to_xe(ct));
+
+ if (ongoing)
+ xe_device_mem_access_put(ct_to_xe(ct));
}
static void guc_ctb_snapshot_capture(struct xe_device *xe, struct guc_ctb *ctb,
pm_runtime_forbid(dev);
}
+static void xe_pm_write_callback_task(struct xe_device *xe,
+ struct task_struct *task)
+{
+ WRITE_ONCE(xe->pm_callback_task, task);
+
+ /*
+ * Just in case it's somehow possible for our writes to be reordered to
+ * the extent that something else re-uses the task written in
+ * pm_callback_task. For example after returning from the callback, but
+ * before the reordered write that resets pm_callback_task back to NULL.
+ */
+ smp_mb(); /* pairs with xe_pm_read_callback_task */
+}
+
+struct task_struct *xe_pm_read_callback_task(struct xe_device *xe)
+{
+ smp_mb(); /* pairs with xe_pm_write_callback_task */
+
+ return READ_ONCE(xe->pm_callback_task);
+}
+
int xe_pm_runtime_suspend(struct xe_device *xe)
{
struct xe_gt *gt;
u8 id;
- int err;
+ int err = 0;
- if (xe->d3cold.allowed) {
- if (xe_device_mem_access_ongoing(xe))
- return -EBUSY;
+ if (xe->d3cold.allowed && xe_device_mem_access_ongoing(xe))
+ return -EBUSY;
+
+ /* Disable access_ongoing asserts and prevent recursive pm calls */
+ xe_pm_write_callback_task(xe, current);
+ if (xe->d3cold.allowed) {
err = xe_bo_evict_all(xe);
if (err)
- return err;
+ goto out;
}
for_each_gt(gt, xe, id) {
err = xe_gt_suspend(gt);
if (err)
- return err;
+ goto out;
}
xe_irq_suspend(xe);
-
- return 0;
+out:
+ xe_pm_write_callback_task(xe, NULL);
+ return err;
}
int xe_pm_runtime_resume(struct xe_device *xe)
{
struct xe_gt *gt;
u8 id;
- int err;
+ int err = 0;
+
+ /* Disable access_ongoing asserts and prevent recursive pm calls */
+ xe_pm_write_callback_task(xe, current);
/*
* It can be possible that xe has allowed d3cold but other pcie devices
for_each_gt(gt, xe, id) {
err = xe_pcode_init(gt);
if (err)
- return err;
+ goto out;
}
/*
*/
err = xe_bo_restore_kernel(xe);
if (err)
- return err;
+ goto out;
}
xe_irq_resume(xe);
if (xe->d3cold.allowed && xe->d3cold.power_lost) {
err = xe_bo_restore_user(xe);
if (err)
- return err;
+ goto out;
}
-
- return 0;
+out:
+ xe_pm_write_callback_task(xe, NULL);
+ return err;
}
int xe_pm_runtime_get(struct xe_device *xe)
return pm_runtime_put_autosuspend(xe->drm.dev);
}
-/* Return true if resume operation happened and usage count was increased */
-bool xe_pm_runtime_resume_if_suspended(struct xe_device *xe)
-{
- /* In case we are suspended we need to immediately wake up */
- if (pm_runtime_suspended(xe->drm.dev))
- return !pm_runtime_resume_and_get(xe->drm.dev);
-
- return false;
-}
-
int xe_pm_runtime_get_if_active(struct xe_device *xe)
{
- WARN_ON(pm_runtime_suspended(xe->drm.dev));
return pm_runtime_get_if_active(xe->drm.dev, true);
}
int xe_pm_runtime_resume(struct xe_device *xe);
int xe_pm_runtime_get(struct xe_device *xe);
int xe_pm_runtime_put(struct xe_device *xe);
-bool xe_pm_runtime_resume_if_suspended(struct xe_device *xe);
int xe_pm_runtime_get_if_active(struct xe_device *xe);
void xe_pm_assert_unbounded_bridge(struct xe_device *xe);
int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold);
void xe_pm_d3cold_allowed_toggle(struct xe_device *xe);
+struct task_struct *xe_pm_read_callback_task(struct xe_device *xe);
#endif
projects / linux.git / commitdiff