[<prev] [next>] [day] [month] [year] [list]
Message-Id: <20190326184137.22354-1-oded.gabbay@gmail.com>
Date: Tue, 26 Mar 2019 20:41:37 +0200
From: Oded Gabbay <oded.gabbay@...il.com>
To: linux-kernel@...r.kernel.org
Cc: gregkh@...uxfoundation.org
Subject: [PATCH] habanalabs: do not limit credits of DMA #0
Because DMA #0 is now used by the user, remove the limitation of credits
from this channel. Without this patch, this channel is pretty much
unusable due to its very low bandwidth configuration.
Signed-off-by: Oded Gabbay <oded.gabbay@...il.com>
---
drivers/misc/habanalabs/goya/goya.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index ea979ebd62fb..3c509e19d69d 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -1688,12 +1688,11 @@ static void goya_init_golden_registers(struct hl_device *hdev)
/*
* Workaround for H2 #HW-23 bug
- * Set DMA max outstanding read requests to 240 on DMA CH 1. Set it
- * to 16 on KMD DMA
- * We need to limit only these DMAs because the user can only read
+ * Set DMA max outstanding read requests to 240 on DMA CH 1.
+ * This limitation is still large enough to not affect Gen4 bandwidth.
+ * We need to only limit that DMA channel because the user can only read
* from Host using DMA CH 1
*/
- WREG32(mmDMA_CH_0_CFG0, 0x0fff0010);
WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0);
goya->hw_cap_initialized |= HW_CAP_GOLDEN;
@@ -3693,7 +3692,7 @@ static int goya_validate_dma_pkt_mmu(struct hl_device *hdev,
* WA for HW-23.
* We can't allow user to read from Host using QMANs other than 1.
*/
- if (parser->hw_queue_id > GOYA_QUEUE_ID_DMA_1 &&
+ if (parser->hw_queue_id != GOYA_QUEUE_ID_DMA_1 &&
hl_mem_area_inside_range(le64_to_cpu(user_dma_pkt->src_addr),
le32_to_cpu(user_dma_pkt->tsize),
hdev->asic_prop.va_space_host_start_address,
--
2.17.1
Powered by blists - more mailing lists