drm/i915: add i915_reset_count

reset_counter will be incremented twice per successful
reset. Odd values mean reset is in progress and even values
mean that reset has completed.

Reset status ioctl introduced in following commit
needs to deliver global reset count to userspace so
use reset_counter to derive the actual reset count
for the gpu

Note that reset in progress is enough to increment
the counter.

v2: wedged equals reset in progress (Daniel Vetter)

v3: Fixed stale comments (Damien Lespiau)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c546316ac649758dbea0edf400769ca904c9ee66..4c0f751d1c88031e505307e9822d3b79a464902b 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1069,34 +1069,30 @@ struct i915_gpu_error {
        unsigned long missed_irq_rings;
 
        /**
-        * State variable and reset counter controlling the reset flow
+        * State variable controlling the reset flow and count
         *
-        * Upper bits are for the reset counter.  This counter is used by the
-        * wait_seqno code to race-free noticed that a reset event happened and
-        * that it needs to restart the entire ioctl (since most likely the
-        * seqno it waited for won't ever signal anytime soon).
+        * This is a counter which gets incremented when reset is triggered,
+        * and again when reset has been handled. So odd values (lowest bit set)
+        * means that reset is in progress and even values that
+        * (reset_counter >> 1):th reset was successfully completed.
+        *
+        * If reset is not completed succesfully, the I915_WEDGE bit is
+        * set meaning that hardware is terminally sour and there is no
+        * recovery. All waiters on the reset_queue will be woken when
+        * that happens.
+        *
+        * This counter is used by the wait_seqno code to notice that reset
+        * event happened and it needs to restart the entire ioctl (since most
+        * likely the seqno it waited for won't ever signal anytime soon).
         *
         * This is important for lock-free wait paths, where no contended lock
         * naturally enforces the correct ordering between the bail-out of the
         * waiter and the gpu reset work code.
-        *
-        * Lowest bit controls the reset state machine: Set means a reset is in
-        * progress. This state will (presuming we don't have any bugs) decay
-        * into either unset (successful reset) or the special WEDGED value (hw
-        * terminally sour). All waiters on the reset_queue will be woken when
-        * that happens.
         */
        atomic_t reset_counter;
 
-       /**
-        * Special values/flags for reset_counter
-        *
-        * Note that the code relies on
-        *      I915_WEDGED & I915_RESET_IN_PROGRESS_FLAG
-        * being true.
-        */
 #define I915_RESET_IN_PROGRESS_FLAG    1
-#define I915_WEDGED                    0xffffffff
+#define I915_WEDGED                    (1 << 31)
 
        /**
         * Waitqueue to signal when the reset has completed. Used by clients
@@ -2046,12 +2042,17 @@ int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
 {
        return unlikely(atomic_read(&error->reset_counter)
-                       & I915_RESET_IN_PROGRESS_FLAG);
+                       & (I915_RESET_IN_PROGRESS_FLAG | I915_WEDGED));
 }
 
 static inline bool i915_terminally_wedged(struct i915_gpu_error *error)
 {
-       return atomic_read(&error->reset_counter) == I915_WEDGED;
+       return atomic_read(&error->reset_counter) & I915_WEDGED;
+}
+
+static inline u32 i915_reset_count(struct i915_gpu_error *error)
+{
+       return ((atomic_read(&error->reset_counter) & ~I915_WEDGED) + 1) / 2;
 }
 
 void i915_gem_reset(struct drm_device *dev);

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e14285bafbd45319ecf63a7d6d6263374e5f2793..19949e8b36c55e33299d71745c9b356e9cc65518 100644 (file)
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1781,7 +1781,7 @@ static void i915_error_work_func(struct work_struct *work)
                        kobject_uevent_env(&dev->primary->kdev.kobj,
                                           KOBJ_CHANGE, reset_done_event);
                } else {
-                       atomic_set(&error->reset_counter, I915_WEDGED);
+                       atomic_set_mask(I915_WEDGED, &error->reset_counter);
                }
 
                /*