gpu: nvgpu: add per-channel refcounting

Add reference counting for channels, and wait for reference count to
get to 0 in gk20a_channel_free() before actually freeing the channel.
Also, change free channel tracking a bit by employing a list of free
channels, which simplifies the procedure of finding available channels
with reference counting.

Each use of a channel must have a reference taken before use or held
by the caller. Taking a reference of a wild channel pointer may fail, if
the channel is either not opened or in a process of being closed. Also,
add safeguards for protecting accidental use of closed channels,
specifically, by setting ch->g = NULL in channel free. This will make it
obvious if freed channel is attempted to be used.

The last user of a channel might be the deferred interrupt handler,
so wait for deferred interrupts to be processed twice in the channel
free procedure: once for providing last notifications to the channel
and once to make sure there are no stale pointers left after referencing
to the channel has been denied.

Finally, fix some races in channel and TSG force reset IOCTL path,
by pausing the channel scheduler in gk20a_fifo_recover_ch() and
gk20a_fifo_recover_tsg(), while the affected engines have been identified,
the appropriate MMU faults triggered, and the MMU faults handled. In this
case, make sure that the MMU fault does not attempt to query the hardware
about the failing channel or TSG ids. This should make channel recovery
more safe also in the regular (i.e., not in the interrupt handler) context.

Bug 1530226
Bug 1597493
Bug 1625901
Bug 200076344
Bug 200071810

Change-Id: Ib274876908e18219c64ea41e50ca443df81d957b
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: http://git-master/r/448463
(cherry picked from commit 3f03aeae64ef2af4829e06f5f63062e8ebd21353)
Reviewed-on: http://git-master/r/755147
Reviewed-by: Automatic_Commit_Validation_User

1 files changed, 26 insertions, 6 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.h b/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
index f022fe36..2ea5b4be 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
@@ -19,12 +19,13 @@
 #define CHANNEL_GK20A_H
 
 #include <linux/log2.h>
-#include <linux/slab.h>
-#include <linux/wait.h>
 #include <linux/mutex.h>
-#include <uapi/linux/nvgpu.h>
 #include <linux/poll.h>
+#include <linux/semaphore.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <uapi/linux/nvgpu.h>
 
 struct gk20a;
 struct gr_gk20a;
@@ -77,8 +78,15 @@ struct channel_gk20a_poll_events {
 
 /* this is the priv element of struct nvhost_channel */
 struct channel_gk20a {
-        struct gk20a *g;
-        bool in_use;
+        struct gk20a *g; /* set only when channel is active */
+
+        struct list_head free_chs;
+
+        spinlock_t ref_obtain_lock;
+        bool referenceable;
+        atomic_t ref_count;
+        wait_queue_head_t ref_count_dec_wq;
+
         int hw_chid;
         bool bound;
         bool first_init;
@@ -171,7 +179,10 @@ static inline bool gk20a_channel_as_bound(struct channel_gk20a *ch)
 }
 int channel_gk20a_commit_va(struct channel_gk20a *c);
 int gk20a_init_channel_support(struct gk20a *, u32 chid);
-void gk20a_free_channel(struct channel_gk20a *ch, bool finish);
+
+/* must be inside gk20a_busy()..gk20a_idle() */
+void gk20a_channel_close(struct channel_gk20a *ch);
+
 bool gk20a_channel_update_and_check_timeout(struct channel_gk20a *ch,
                                             u32 timeout_delta_ms);
 void gk20a_disable_channel(struct channel_gk20a *ch,
@@ -202,6 +213,15 @@ void gk20a_channel_event(struct channel_gk20a *ch);
 
 void gk20a_init_channel(struct gpu_ops *gops);
 
+/* returns ch if reference was obtained */
+struct channel_gk20a *__must_check _gk20a_channel_get(struct channel_gk20a *ch,
+                                                      const char *caller);
+#define gk20a_channel_get(ch) _gk20a_channel_get(ch, __func__)
+
+
+void _gk20a_channel_put(struct channel_gk20a *ch, const char *caller);
+#define gk20a_channel_put(ch) _gk20a_channel_put(ch, __func__)
+
 int gk20a_wait_channel_idle(struct channel_gk20a *ch);
 struct channel_gk20a *gk20a_open_new_channel(struct gk20a *g);
 struct channel_gk20a *gk20a_open_new_channel_with_cb(struct gk20a *g,