Add drm/i915 backport for hangs

https://lore.kernel.org/stable/20191230111530.3750048-1-chris@chris-wilson.co.uk/

drm-i915-gt-Detect-if-we-miss-WaIdleLiteRestore.patch

@@ -0,0 +1,129 @@
+From 90de578c81e983b3d992ca3e1a7e5910c803abba Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Mon, 30 Dec 2019 11:15:30 +0000
+Subject: [PATCH] drm/i915/gt: Detect if we miss WaIdleLiteRestore
+
+In order to avoid confusing the HW, we must never submit an empty ring
+during lite-restore, that is we should always advance the RING_TAIL
+before submitting to stay ahead of the RING_HEAD.
+
+Normally this is prevented by keeping a couple of spare NOPs in the
+request->wa_tail so that on resubmission we can advance the tail. This
+relies on the request only being resubmitted once, which is the normal
+condition as it is seen once for ELSP[1] and then later in ELSP[0]. On
+preemption, the requests are unwound and the tail reset back to the
+normal end point (as we know the request is incomplete and therefore its
+RING_HEAD is even earlier).
+
+However, if this w/a should fail we would try and resubmit the request
+with the RING_TAIL already set to the location of this request's wa_tail
+potentially causing a GPU hang. We can spot when we do try and
+incorrectly resubmit without advancing the RING_TAIL and spare any
+embarrassment by forcing the context restore.
+
+In the case of preempt-to-busy, we leave the requests running on the HW
+while we unwind. As the ring is still live, we cannot rewind our
+rq->tail without forcing a reload so leave it set to rq->wa_tail and
+only force a reload if we resubmit after a lite-restore. (Normally, the
+forced reload will be a part of the preemption event.)
+
+Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
+Closes: https://gitlab.freedesktop.org/drm/intel/issues/673
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
+Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20191209023215.3519970-1-chris@chris-wilson.co.uk
+(cherry picked from commit 82c69bf58650e644c61aa2bf5100b63a1070fd2f)
+---
+ drivers/gpu/drm/i915/gt/intel_lrc.c | 42 ++++++++++++++---------------
+ 1 file changed, 20 insertions(+), 22 deletions(-)
+
+diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
+index d564bfcab6a3..49ce15553e7b 100644
+--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
++++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
+@@ -471,12 +471,6 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
+ 	return desc;
+ }
+ 
+-static void unwind_wa_tail(struct i915_request *rq)
+-{
+-	rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
+-	assert_ring_tail_valid(rq->ring, rq->tail);
+-}
+-
+ static struct i915_request *
+ __unwind_incomplete_requests(struct intel_engine_cs *engine)
+ {
+@@ -495,7 +489,6 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
+ 			continue; /* XXX */
+ 
+ 		__i915_request_unsubmit(rq);
+-		unwind_wa_tail(rq);
+ 
+ 		/*
+ 		 * Push the request back into the queue for later resubmission.
+@@ -650,13 +643,29 @@ execlists_schedule_out(struct i915_request *rq)
+ 	i915_request_put(rq);
+ }
+ 
+-static u64 execlists_update_context(const struct i915_request *rq)
++static u64 execlists_update_context(struct i915_request *rq)
+ {
+ 	struct intel_context *ce = rq->hw_context;
+-	u64 desc;
++	u64 desc = ce->lrc_desc;
++	u32 tail;
+ 
+-	ce->lrc_reg_state[CTX_RING_TAIL + 1] =
+-		intel_ring_set_tail(rq->ring, rq->tail);
++	/*
++	 * WaIdleLiteRestore:bdw,skl
++	 *
++	 * We should never submit the context with the same RING_TAIL twice
++	 * just in case we submit an empty ring, which confuses the HW.
++	 *
++	 * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of
++	 * the normal request to be able to always advance the RING_TAIL on
++	 * subsequent resubmissions (for lite restore). Should that fail us,
++	 * and we try and submit the same tail again, force the context
++	 * reload.
++	 */
++	tail = intel_ring_set_tail(rq->ring, rq->tail);
++	if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL + 1] == tail))
++		desc |= CTX_DESC_FORCE_RESTORE;
++	ce->lrc_reg_state[CTX_RING_TAIL + 1] = tail;
++	rq->tail = rq->wa_tail;
+ 
+ 	/*
+ 	 * Make sure the context image is complete before we submit it to HW.
+@@ -675,7 +684,6 @@ static u64 execlists_update_context(const struct i915_request *rq)
+ 	 */
+ 	mb();
+ 
+-	desc = ce->lrc_desc;
+ 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
+ 
+ 	return desc;
+@@ -1150,16 +1158,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
+ 			if (!list_is_last(&last->sched.link,
+ 					  &engine->active.requests))
+ 				return;
+-
+-			/*
+-			 * WaIdleLiteRestore:bdw,skl
+-			 * Apply the wa NOOPs to prevent
+-			 * ring:HEAD == rq:TAIL as we resubmit the
+-			 * request. See gen8_emit_fini_breadcrumb() for
+-			 * where we prepare the padding after the
+-			 * end of the request.
+-			 */
+-			last->tail = last->wa_tail;
+ 		}
+ 	}
+ 
+-- 
+2.24.1
+

kernel.spec

@@ -44,7 +44,7 @@ Summary: The Linux kernel
 # For non-released -rc kernels, this will be appended after the rcX and
 # gitX tags, so a 3 here would become part of release "0.rcX.gitX.3"
 #
-%global baserelease 100
+%global baserelease 101
 %global fedora_build %{baserelease}
 
 # base_sublevel is the kernel version we're starting with and patching
@@ -601,6 +601,9 @@ Patch610: 0001-tracing-Do-not-create-directories-if-lockdown-is-in-.patch
 # rhbz 1788653
 Patch611: tpm-handle-negative-priv--response_len-in-tpm_common_read.patch
 
+# https://gitlab.freedesktop.org/drm/intel/issues/673
+Patch531: drm-i915-gt-Detect-if-we-miss-WaIdleLiteRestore.patch
+
 # END OF PATCH DEFINITIONS
 
 %endif