accel/ivpu: Force snooping for MMU writes

Set AW_SNOOP_OVERRIDE bit in VPU_37/40XX_HOST_IF_TCU_PTW_OVERRIDES
to force snooping for MMU write accesses (setting event queue events).

MMU event queue buffer is the only buffer written by MMU and
mapped as write-back which break cache coherency. Force write
transactions to be snooped solving the problem.
Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-2-jacek.lawrynowicz@linux.intel.com

drivers/accel/ivpu/ivpu_hw_37xx.c

@@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);

drivers/accel/ivpu/ivpu_hw_40xx.c

@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);

drivers/accel/ivpu/ivpu_mmu.c

@@ -560,7 +560,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -877,8 +876,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
 	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);