public inbox for dmaengine@vger.kernel.org
 help / color / mirror / Atom feed
From: "Köry Maincent" <kory.maincent@bootlin.com>
To: Cai Huoqing <cai.huoqing@linux.dev>,
	Manivannan Sadhasivam <mani@kernel.org>,
	Serge Semin <fancer.lancer@gmail.com>,
	Vinod Koul <vkoul@kernel.org>,
	Gustavo Pimentel <Gustavo.Pimentel@synopsys.com>,
	dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Thomas Petazzoni <thomas.petazzoni@bootlin.com>,
	Gustavo Pimentel <gustavo.pimentel@synopsys.com>,
	Herve Codina <herve.codina@bootlin.com>,
	Kory Maincent <kory.maincent@bootlin.com>
Subject: [PATCH 7/9] dmaengine: dw-edma: eDMA: Add memory barrier before starting the DMA transfer in remote setup
Date: Fri,  9 Jun 2023 10:16:52 +0200	[thread overview]
Message-ID: <20230609081654.330857-8-kory.maincent@bootlin.com> (raw)
In-Reply-To: <20230609081654.330857-1-kory.maincent@bootlin.com>

From: Kory Maincent <kory.maincent@bootlin.com>

The Linked list element and pointer are not stored in the same memory as
the eDMA controller register. If the doorbell register is toggled before
the full write of the linked list a race condition error can appears.
In remote setup we can only use a readl to the memory to assured the full
write has occurred.

Fixes: 7e4b8a4fbe2c ("dmaengine: Add Synopsys eDMA IP version 0 support")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
---
 drivers/dma/dw-edma/dw-edma-v0-core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index b38786f0ad79..2e872d6f2c04 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -412,6 +412,15 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
 	}
+
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		/* Make sure Linked List has been written.
+		 * Linux memory barriers don't cater for what's required here.
+		 * What's required is what's here - a read of the linked
+		 * list region.
+		 */
+		readl(chunk->ll_region.vaddr.io);
+
 	/* Doorbell */
 	SET_RW_32(dw, chan->dir, doorbell,
 		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
-- 
2.25.1


  parent reply	other threads:[~2023-06-09  8:17 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-09  8:16 [PATCH 0/9] Fix support of dw-edma HDMA NATIVE IP in remote setup Köry Maincent
2023-06-09  8:16 ` [PATCH 1/9] dmaengine: dw-edma: Fix the ch_count hdma callback Köry Maincent
2023-06-18 21:07   ` Serge Semin
2023-06-19 18:07     ` Köry Maincent
2023-06-09  8:16 ` [PATCH 2/9] dmaengine: dw-edma: Typos fixes Köry Maincent
2023-06-18 21:15   ` Serge Semin
2023-06-09  8:16 ` [PATCH 3/9] dmaengine: dw-edma: Add HDMA remote interrupt configuration Köry Maincent
2023-06-18 21:48   ` Serge Semin
2023-06-19 18:16     ` Köry Maincent
2023-06-20  9:32       ` Serge Semin
2023-06-09  8:16 ` [PATCH 4/9] dmaengine: dw-edma: HDMA: Add memory barrier before starting the DMA transfer in remote setup Köry Maincent
2023-06-19 17:02   ` Serge Semin
2023-06-19 18:32     ` Köry Maincent
2023-06-20 11:45       ` Serge Semin
2023-06-20 13:30         ` Köry Maincent
2023-06-21  9:45           ` Serge Semin
2023-06-21 13:19             ` Köry Maincent
2023-06-21 15:56               ` Serge Semin
2023-06-22 15:12                 ` Köry Maincent
2023-06-22 16:22                   ` Serge Semin
2023-09-12  8:52                     ` Köry Maincent
2023-09-25 16:06                       ` Serge Semin
2023-06-09  8:16 ` [PATCH 5/9] dmaengine: dw-edma: HDMA: Fix possible race condition " Köry Maincent
2023-06-19 17:15   ` Serge Semin
2023-06-19 18:41     ` Köry Maincent
2023-06-20 12:07       ` Serge Semin
2023-06-20 13:35         ` Köry Maincent
2023-06-09  8:16 ` [PATCH 6/9] dmaengine: dw-edma: HDMA: Fix possible race condition in local setup Köry Maincent
2023-06-09  8:16 ` Köry Maincent [this message]
2023-06-09  8:16 ` [PATCH 8/9] dmaengine: dw-edma: eDMA: Fix possible race condition in remote setup Köry Maincent
2023-06-09  8:16 ` [PATCH 9/9] dmaengine: dw-edma: eDMA: Fix possible race condition in local setup Köry Maincent
2023-06-12  8:59 ` [PATCH 0/9] Fix support of dw-edma HDMA NATIVE IP in remote setup Köry Maincent
2023-06-12 16:48   ` Serge Semin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230609081654.330857-8-kory.maincent@bootlin.com \
    --to=kory.maincent@bootlin.com \
    --cc=Gustavo.Pimentel@synopsys.com \
    --cc=cai.huoqing@linux.dev \
    --cc=dmaengine@vger.kernel.org \
    --cc=fancer.lancer@gmail.com \
    --cc=herve.codina@bootlin.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mani@kernel.org \
    --cc=thomas.petazzoni@bootlin.com \
    --cc=vkoul@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox