diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2019-02-08 15:37:03 +0000 |
---|---|---|
committer | Chris Wilson <chris@chris-wilson.co.uk> | 2019-02-08 16:47:32 +0000 |
commit | 2caffbf1176256cc4f8d4e5c3c524fc689cb9876 (patch) | |
tree | 03bb0b9e29b61ae6886c84308cea1a446eb469eb /drivers/gpu/drm/i915/i915_debugfs.c | |
parent | 7ae1940014ef77e6389ca95a5a75273c9c4ea31f (diff) | |
download | linux-2caffbf1176256cc4f8d4e5c3c524fc689cb9876.tar.bz2 |
drm/i915: Revoke mmaps and prevent access to fence registers across reset
Previously, we were able to rely on the recursive properties of
struct_mutex to allow us to serialise revoking mmaps and reacquiring the
FENCE registers with them being clobbered over a global device reset.
I then proceeded to throw out the baby with the bath water in order to
pursue a struct_mutex-less reset.
Perusing LWN for alternative strategies, the dilemma on how to serialise
access to a global resource on one side was answered by
https://lwn.net/Articles/202847/ -- Sleepable RCU:
1 int readside(void) {
2 int idx;
3 rcu_read_lock();
4 if (nomoresrcu) {
5 rcu_read_unlock();
6 return -EINVAL;
7 }
8 idx = srcu_read_lock(&ss);
9 rcu_read_unlock();
10 /* SRCU read-side critical section. */
11 srcu_read_unlock(&ss, idx);
12 return 0;
13 }
14
15 void cleanup(void)
16 {
17 nomoresrcu = 1;
18 synchronize_rcu();
19 synchronize_srcu(&ss);
20 cleanup_srcu_struct(&ss);
21 }
No more worrying about stop_machine, just an uber-complex mutex,
optimised for reads, with the overhead pushed to the rare reset path.
However, we do run the risk of a deadlock as we allocate underneath the
SRCU read lock, and the allocation may require a GPU reset, causing a
dependency cycle via the in-flight requests. We resolve that by declaring
the driver wedged and cancelling all in-flight rendering.
v2: Use expedited rcu barriers to match our earlier timing
characteristics.
v3: Try to annotate locking contexts for sparse
v4: Reduce selftest lock duration to avoid a reset deadlock with fences
v5: s/srcu/reset_backoff_srcu/
v6: Remove more stale comments
Testcase: igt/gem_mmap_gtt/hang
Fixes: eb8d0f5af4ec ("drm/i915: Remove GPU reset dependence on struct_mutex")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190208153708.20023-2-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/i915_debugfs.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_debugfs.c | 12 |
1 files changed, 3 insertions, 9 deletions
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 53ec81a4e5f1..98a793d047ec 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1280,14 +1280,11 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) intel_wakeref_t wakeref; enum intel_engine_id id; + seq_printf(m, "Reset flags: %lx\n", dev_priv->gpu_error.flags); if (test_bit(I915_WEDGED, &dev_priv->gpu_error.flags)) - seq_puts(m, "Wedged\n"); + seq_puts(m, "\tWedged\n"); if (test_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags)) - seq_puts(m, "Reset in progress: struct_mutex backoff\n"); - if (waitqueue_active(&dev_priv->gpu_error.wait_queue)) - seq_puts(m, "Waiter holding struct mutex\n"); - if (waitqueue_active(&dev_priv->gpu_error.reset_queue)) - seq_puts(m, "struct_mutex blocked for reset\n"); + seq_puts(m, "\tDevice (global) reset in progress\n"); if (!i915_modparams.enable_hangcheck) { seq_puts(m, "Hangcheck disabled\n"); @@ -3872,9 +3869,6 @@ i915_wedged_set(void *data, u64 val) * while it is writing to 'i915_wedged' */ - if (i915_reset_backoff(&i915->gpu_error)) - return -EAGAIN; - i915_handle_error(i915, val, I915_ERROR_CAPTURE, "Manually set wedged engine mask = %llx", val); return 0; |