drm/i915: Flush TLBs before releasing backing store

commit 7938d61591d33394a21bdd7797a245b65428f44c upstream.

We need to flush TLBs before releasing backing store otherwise userspace
is able to encounter stale entries if a) it is not declaring access to
certain buffers and b) it races with the backing store release from a
such undeclared execution already executing on the GPU in parallel.

The approach taken is to mark any buffer objects which were ever bound
to the GPU and to trigger a serialized TLB flush when their backing
store is released.

Alternatively the flushing could be done on VMA unbind, at which point
we would be able to ascertain whether there is potential a parallel GPU
execution (which could race), but essentially it boils down to paying
the cost of TLB flushes potentially needlessly at VMA unbind time (when
the backing store is not known to be going away so not needed for
safety), versus potentially needlessly at backing store relase time
(since we at that point cannot tell whether there is anything executing
on the GPU which uses that object).

Thereforce simplicity of implementation has been chosen for now with
scope to benchmark and refine later as required.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reported-by: Sushma Venkatesh Reddy <sushma.venkatesh.reddy@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Dave Airlie <airlied@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 22 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index e072054adac5..e21c779cb487 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -724,7 +724,8 @@ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
 }
 
 static void __intel_uncore_forcewake_put(struct intel_uncore *uncore,
-					 enum forcewake_domains fw_domains)
+					 enum forcewake_domains fw_domains,
+					 bool delayed)
 {
 	struct intel_uncore_forcewake_domain *domain;
 	unsigned int tmp;
@@ -739,7 +740,11 @@ static void __intel_uncore_forcewake_put(struct intel_uncore *uncore,
 			continue;
 		}
 
-		fw_domains_put(uncore, domain->mask);
+		if (delayed &&
+		    !(domain->uncore->fw_domains_timer & domain->mask))
+			fw_domain_arm_timer(domain);
+		else
+			fw_domains_put(uncore, domain->mask);
 	}
 }
 
@@ -760,7 +765,20 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore,
 		return;
 
 	spin_lock_irqsave(&uncore->lock, irqflags);
-	__intel_uncore_forcewake_put(uncore, fw_domains);
+	__intel_uncore_forcewake_put(uncore, fw_domains, false);
+	spin_unlock_irqrestore(&uncore->lock, irqflags);
+}
+
+void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore,
+					enum forcewake_domains fw_domains)
+{
+	unsigned long irqflags;
+
+	if (!uncore->fw_get_funcs)
+		return;
+
+	spin_lock_irqsave(&uncore->lock, irqflags);
+	__intel_uncore_forcewake_put(uncore, fw_domains, true);
 	spin_unlock_irqrestore(&uncore->lock, irqflags);
 }
 
@@ -802,7 +820,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore,
 	if (!uncore->fw_get_funcs)
 		return;
 
-	__intel_uncore_forcewake_put(uncore, fw_domains);
+	__intel_uncore_forcewake_put(uncore, fw_domains, false);
 }
 
 void assert_forcewakes_inactive(struct intel_uncore *uncore)