diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 7d48bd57b6ef..0a9c3be4817c 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -986,6 +986,9 @@ void intel_engine_init_ctx_wa(struct intel_engine_cs *engine)
 int intel_engine_emit_ctx_wa(struct i915_request *rq)
 {
 	struct i915_wa_list *wal = &rq->engine->ctx_wa_list;
+	struct intel_uncore *uncore = rq->engine->uncore;
+	enum forcewake_domains fw;
+	unsigned long flags;
 	struct i915_wa *wa;
 	unsigned int i;
 	u32 *cs;
@@ -1002,13 +1005,36 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
+	fw = wal_get_fw_for_rmw(uncore, wal);
+
+	intel_gt_mcr_lock(wal->gt, &flags);
+	spin_lock(&uncore->lock);
+	intel_uncore_forcewake_get__locked(uncore, fw);
+
 	*cs++ = MI_LOAD_REGISTER_IMM(wal->count);
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
+		u32 val;
+
+		/* Skip reading the register if it's not really needed */
+		if (wa->masked_reg || (wa->clr | wa->set) == U32_MAX) {
+			val = wa->set;
+		} else {
+			val = wa->is_mcr ?
+				intel_gt_mcr_read_any_fw(wal->gt, wa->mcr_reg) :
+				intel_uncore_read_fw(uncore, wa->reg);
+			val &= ~wa->clr;
+			val |= wa->set;
+		}
+
 		*cs++ = i915_mmio_reg_offset(wa->reg);
-		*cs++ = wa->set;
+		*cs++ = val;
 	}
 	*cs++ = MI_NOOP;
 
+	intel_uncore_forcewake_put__locked(uncore, fw);
+	spin_unlock(&uncore->lock);
+	intel_gt_mcr_unlock(wal->gt, flags);
+
 	intel_ring_advance(rq, cs);
 
 	ret = rq->engine->emit_flush(rq, EMIT_BARRIER);