Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Lorenzo Bianconi <lorenzo@kernel.org>
To: Chris Scott <gilroyscott1970@gmail.com>
Cc: netdev@vger.kernel.org, andrew+netdev@lunn.ch,
	davem@davemloft.net, edumazet@kernel.org, kuba@kernel.org,
	pabeni@redhat.com, robh@kernel.org, krzk+dt@kernel.org,
	conor+dt@kernel.org, matthias.bgg@gmail.com,
	angelogioacchino.delregno@collabora.com,
	devicetree@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-mediatek@lists.infradead.org, pawlik.dan@gmail.com,
	zhengping.zhang@airoha.com
Subject: Re: [RFC net-next 2/3] net: airoha: npu: attach a coherent pool in the NPU window
Date: Mon, 26 Oct 2026 08:48:24 +0100	[thread overview]
Message-ID: <at8FyOLeaMlpS7mR@lore-desk> (raw)
In-Reply-To: <20261024154150.45733-3-gilroyscott1970@gmail.com>

[-- Attachment #1: Type: text/plain, Size: 4109 bytes --]

> The EN7581 NPU can only address host DRAM at 0x80000000-0xbfffffff;
> higher addresses alias the lower 1 GiB. The coherent buffers allocated
> on the NPU device are all shared with the NPU: since mt76 uses the NPU
> device as dma_dev, these are the NPU TX/RX descriptor rings, the HW-RRO
> ba_bitmap/addr_elem/msdu_pg/session buffers and the NPU TXD buffers.
> On a 2 GiB board nothing keeps them below 0xc0000000; they normally
> land there only because of early-boot allocation order. With low DRAM
> reserved away on W1700K the SoC hangs right after mt7996 firmware load.
> 
> If the NPU node has an optional "dma" reserved-memory region, attach it
> as the device coherent pool so all of these come from the window. The
> next patch moves the mailbox buffers to coherent memory as well.
> 
> Unlike a restricted-dma-pool this leaves streaming mappings alone.
> Packet buffers are passed through to the WiFi DMA engine: on W1700K
> with 96% of TX skbs and ~20% of RX page_pool buffers above 0xc0000000,
> host-path traffic and sha256 file round-trips stay intact, at the same
> throughput as without a pool, whereas a restricted-dma-pool (swiotlb
> bouncing) costs ~22% of host-path TX.
> 
> A device coherent pool has no fallback once full; mt76 and the mailbox
> use ~10.7 MiB with MT7996, so the DT region should be 16 MiB.
> 
> This patch was written with the help of Claude (Anthropic, claude-
> opus-5-5).
> 
> Link: https://lore.kernel.org/r/atCRsquzA1UxSpCc@mediatek.com
> Tested-by: Daniel Pawlik <pawlik.dan@gmail.com>
> Signed-off-by: Chris Scott <gilroyscott1970@gmail.com>
> ---
>  drivers/net/ethernet/airoha/airoha_npu.c | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
> index 4d3195eb00..069fd60680 100644
> --- a/drivers/net/ethernet/airoha/airoha_npu.c
> +++ b/drivers/net/ethernet/airoha/airoha_npu.c
> @@ -693,6 +693,11 @@ static const struct regmap_config regmap_config = {
>  	.disable_locking	= true,
>  };
>  
> +static void airoha_npu_rmem_release(void *data)
> +{
> +	of_reserved_mem_device_release(data);
> +}
> +
>  static int airoha_npu_probe(struct platform_device *pdev)
>  {
>  	struct device *dev = &pdev->dev;
> @@ -776,6 +781,19 @@ static int airoha_npu_probe(struct platform_device *pdev)
>  	if (err)
>  		return err;
>  
> +	if (of_property_match_string(dev->of_node, "memory-region-names",
> +				     "dma") >= 0) {
> +		err = of_reserved_mem_device_init_by_name(dev, dev->of_node,
> +							  "dma");
> +		if (err)
> +			return err;
> +
> +		err = devm_add_action_or_reset(dev, airoha_npu_rmem_release,
> +					       dev);
> +		if (err)
> +			return err;
> +	}

nit: what about creating a dedicated routine for both firmware and dma
memory regions. Something like:

diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
index 4d3195eb00f7..9c9c754f82c7 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.c
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -693,6 +693,23 @@ static const struct regmap_config regmap_config = {
 	.disable_locking	= true,
 };
 
+static int airoha_npu_reserve_mem_region(struct device *dev,
+					 struct resource *res)
+{
+	int err;
+
+	err = of_reserved_mem_region_to_resource(dev->of_node, 0, res);
+	if (err)
+		return err;
+
+	if (of_property_match_string(dev->of_node, "memory-region-names",
+				     "dma" >= 0)) {
+		...
+	}
+
+	return 0;
+}
+
 static int airoha_npu_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -729,7 +746,7 @@ static int airoha_npu_probe(struct platform_device *pdev)
 	if (IS_ERR(npu->regmap))
 		return PTR_ERR(npu->regmap);
 
-	err = of_reserved_mem_region_to_resource(dev->of_node, 0, &res);
+	err = airoha_npu_reserve_mem_region(dev, &res);
 	if (err)
 		return err;
 

Regards,
Lorenzo

> +
>  	err = airoha_npu_run_firmware(dev, base, &res);
>  	if (err)
>  		return err;
> -- 
> 2.53.0
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

  reply	other threads:[~2026-10-26  7:49 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-24 15:41 [RFC net-next 0/3] net: airoha: npu: keep NPU-shared DMA buffers in the NPU window Chris Scott
2026-10-24 15:41 ` [RFC net-next 1/3] dt-bindings: net: airoha: npu: add DMA pool memory region Chris Scott
2026-10-24 15:41 ` [RFC net-next 2/3] net: airoha: npu: attach a coherent pool in the NPU window Chris Scott
2026-10-26  7:48   ` Lorenzo Bianconi [this message]
2026-10-27  5:10     ` Chris Scott
2026-10-24 15:41 ` [RFC net-next 3/3] net: airoha: npu: use coherent memory for mailbox messages Chris Scott
2026-10-26  7:50   ` Lorenzo Bianconi

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=at8FyOLeaMlpS7mR@lore-desk \
    --to=lorenzo@kernel.org \
    --cc=andrew+netdev@lunn.ch \
    --cc=angelogioacchino.delregno@collabora.com \
    --cc=conor+dt@kernel.org \
    --cc=davem@davemloft.net \
    --cc=devicetree@vger.kernel.org \
    --cc=edumazet@kernel.org \
    --cc=gilroyscott1970@gmail.com \
    --cc=krzk+dt@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mediatek@lists.infradead.org \
    --cc=matthias.bgg@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=pawlik.dan@gmail.com \
    --cc=robh@kernel.org \
    --cc=zhengping.zhang@airoha.com \
    /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