From 0a823e8fd4fd67726697854578f3584ee3a49b1d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 8 Nov 2018 08:17:38 +0000
Subject: [PATCH] drm/i915/execlists: Force write serialisation into context image vs execution
Git-commit: 0a823e8fd4fd67726697854578f3584ee3a49b1d
Patch-mainline: v4.20-rc3
No-fix: 987abd5c62f92ee4970b45aa077f47949974e615
References: bsc#1051510

Ensure that the writes into the context image are completed prior to the
register mmio to trigger execution. Although previously we were assured
by the SDM that all writes are flushed before an uncached memory
transaction (our mmio write to submit the context to HW for execution),
we have empirical evidence to believe that this is not actually the
case.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108656
References: https://bugs.freedesktop.org/show_bug.cgi?id=108315
References: https://bugs.freedesktop.org/show_bug.cgi?id=106887
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>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181108081740.25615-1-chris@chris-wilson.co.uk
Cc: stable@vger.kernel.org
(cherry picked from commit 987abd5c62f92ee4970b45aa077f47949974e615)

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/i915/intel_lrc.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -424,7 +424,8 @@ static u64 execlists_update_context(stru
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
 
-	/* True 32b PPGTT with dynamic page allocation: update PDP
+	/*
+	 * True 32b PPGTT with dynamic page allocation: update PDP
 	 * registers and point the unallocated PDPs to scratch page.
 	 * PML4 is allocated during ppgtt init, so this is not needed
 	 * in 48-bit mode.
@@ -432,6 +433,17 @@ static u64 execlists_update_context(stru
 	if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm))
 		execlists_update_context_pdps(ppgtt, reg_state);
 
+	/*
+	 * Make sure the context image is complete before we submit it to HW.
+	 *
+	 * Ostensibly, writes (including the WCB) should be flushed prior to
+	 * an uncached write such as our mmio register access, the empirical
+	 * evidence (esp. on Braswell) suggests that the WC write into memory
+	 * may not be visible to the HW prior to the completion of the UC
+	 * register write and that we may begin execution from the context
+	 * before its image is complete leading to invalid PD chasing.
+	 */
+	wmb();
 	return ce->lrc_desc;
 }