Message-ID: <25237d53-a93d-4c1f-a7a4-4b6ed03e10e4@oracle.com>
Date: Sat, 30 Aug 2025 01:02:21 +0530
From: ALOK TIWARI <alok.a.tiwari@...cle.com>
To: admiyo@...amperecomputing.com, Jeremy Kerr <jk@...econstruct.com.au>,
        Matt Johnston <matt@...econstruct.com.au>,
        Andrew Lunn <andrew+netdev@...n.ch>,
        "David S. Miller"
 <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>
Cc: netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
        Sudeep Holla <sudeep.holla@....com>,
        Jonathan Cameron <Jonathan.Cameron@...wei.com>,
        Huisong Li <lihuisong@...wei.com>
Subject: Re: [PATCH net-next v25 1/1] mctp pcc: Implement MCTP over PCC
 Transport



On 8/27/2025 10:18 AM, admiyo@...amperecomputing.com wrote:
> From: Adam Young <admiyo@...amperecomputing.com>
> 
> Implementation of network driver for
> Management Control Transport Protocol(MCTP)

it is Management Component Transport Protocol (see DMTF spec).

> over Platform Communication Channel(PCC)
> 
> DMTF DSP:0292
> https://urldefense.com/v3/__https://www.dmtf.org/sites/default/files/standards/documents/*__;Lw!!ACWV5N9M2RV99hQ!JkW80M1xGJjvaXd72o192mqV0uzOu511ibGTz-JCtmbsM_IrpuZ0jJeeQFOug5UHp8fNY1dX2Lk0_hPUUY__KokwgtE$
> DSP0292_1.0.0WIP50.pdf
> 
> MCTP devices are specified via ACPI by entries
> in DSDT/SDST and reference channels specified

SDST -> SSDT

> in the PCCT.  Messages are sent on a type 3 and
> received on a type 4 channel.  Communication with
> other devices use the PCC based doorbell mechanism;
> a shared memory segment with a corresponding
> interrupt and a memory register used to trigger
> remote interrupts.
> 
> This driver takes advantage of PCC mailbox buffer
> management. The data section of the struct sk_buff
> that contains the outgoing packet is sent to the mailbox,
> already properly formatted  as a PCC message.  The driver
> is also responsible for allocating a struct sk_buff that
> is then passed to the mailbox and used to record the
> data in the shared buffer. It maintains a list of both
> outging and incoming sk_buffs to match the data buffers

outging

> 
> When the Type 3 channel outbox receives a txdone response
> interrupt, it consumes the outgoing sk_buff, allowing
> it to be freed.
> 
> Bringing the interface up and down creates and frees
> the channel between the network driver and the mailbox
> driver. Freeing the channel also frees any packets that
> are cached in the mailbox ringbuffer.
> 
> Signed-off-by: Adam Young <admiyo@...amperecomputing.com>
> ---
>   MAINTAINERS                 |   5 +
>   drivers/net/mctp/Kconfig    |  13 ++
>   drivers/net/mctp/Makefile   |   1 +
>   drivers/net/mctp/mctp-pcc.c | 367 ++++++++++++++++++++++++++++++++++++
>   4 files changed, 386 insertions(+)
>   create mode 100644 drivers/net/mctp/mctp-pcc.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index bce96dd254b8..de359bddcb2f 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -14660,6 +14660,11 @@ F:	include/net/mctpdevice.h
>   F:	include/net/netns/mctp.h
>   F:	net/mctp/
>   
> +MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP) over PCC (MCTP-PCC) Driver
> +M:	Adam Young <admiyo@...amperecomputing.com>
> +S:	Maintained
> +F:	drivers/net/mctp/mctp-pcc.c
> +
>   MAPLE TREE
>   M:	Liam R. Howlett <Liam.Howlett@...cle.com>
>   L:	maple-tree@...ts.infradead.org
> diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig
> index cf325ab0b1ef..f69d0237f058 100644
> --- a/drivers/net/mctp/Kconfig
> +++ b/drivers/net/mctp/Kconfig
> @@ -57,6 +57,19 @@ config MCTP_TRANSPORT_USB
>   	  MCTP-over-USB interfaces are peer-to-peer, so each interface
>   	  represents a physical connection to one remote MCTP endpoint.
>   
> +config MCTP_TRANSPORT_PCC
> +	tristate "MCTP PCC transport"
> +	depends on ACPI
> +	help
> +	  Provides a driver to access MCTP devices over PCC transport,
> +	  A MCTP protocol network device is created via ACPI for each
> +	  entry in the DST/SDST that matches the identifier. The Platform

should be DSDT/SSDT ?

> +	  communication channels are selected from the corresponding
> +	  entries in the PCCT.
> +
> +	  Say y here if you need to connect to MCTP endpoints over PCC. To
> +	  compile as a module, use m; the module will be called mctp-pcc.
> +
>   endmenu
>   
>   endif
> diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile
> index c36006849a1e..2276f148df7c 100644
> --- a/drivers/net/mctp/Makefile
> +++ b/drivers/net/mctp/Makefile
> @@ -1,3 +1,4 @@
> +obj-$(CONFIG_MCTP_TRANSPORT_PCC) += mctp-pcc.o
>   obj-$(CONFIG_MCTP_SERIAL) += mctp-serial.o
>   obj-$(CONFIG_MCTP_TRANSPORT_I2C) += mctp-i2c.o
>   obj-$(CONFIG_MCTP_TRANSPORT_I3C) += mctp-i3c.o
> diff --git a/drivers/net/mctp/mctp-pcc.c b/drivers/net/mctp/mctp-pcc.c
> new file mode 100644
> index 000000000000..c6578b27c00c
> --- /dev/null
> +++ b/drivers/net/mctp/mctp-pcc.c
> @@ -0,0 +1,367 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * mctp-pcc.c - Driver for MCTP over PCC.
> + * Copyright (c) 2024-2025, Ampere Computing LLC
> + *
> + */
> +
> +/* Implementation of MCTP over PCC DMTF Specification DSP0256

DSP0256 vs DSP0292 mismatch

> + * https://urldefense.com/v3/__https://www.dmtf.org/sites/default/files/standards/documents/DSP0292_1.0.0WIP50.pdf__;!!ACWV5N9M2RV99hQ!JkW80M1xGJjvaXd72o192mqV0uzOu511ibGTz-JCtmbsM_IrpuZ0jJeeQFOug5UHp8fNY1dX2Lk0_hPUUY__EEa7amg$
> + */
> +
> +#include <linux/acpi.h>
> +#include <linux/if_arp.h>
> +#include <linux/init.h>
> +#include <linux/kernel.h>
> +#include <linux/mailbox_client.h>
> +#include <linux/module.h>
> +#include <linux/netdevice.h>
> +#include <linux/platform_device.h>
> +#include <linux/string.h>
> +#include <linux/skbuff.h>
> +#include <linux/hrtimer.h>
> +
> +#include <acpi/acpi_bus.h>
> +#include <acpi/acpi_drivers.h>
> +#include <acpi/acrestyp.h>
> +#include <acpi/actbl.h>
> +#include <net/mctp.h>
> +#include <net/mctpdevice.h>
> +#include <acpi/pcc.h>
> +
> +#define MCTP_SIGNATURE          "MCTP"
> +#define MCTP_SIGNATURE_LENGTH   (sizeof(MCTP_SIGNATURE) - 1)
> +#define MCTP_MIN_MTU            68
> +#define PCC_DWORD_TYPE          0x0c
> +
> +struct mctp_pcc_mailbox {
> +	u32 index;
> +	struct pcc_mbox_chan *chan;
> +	struct mbox_client client;
> +	struct sk_buff_head packets;
> +};
> +
> +/* The netdev structure. One of these per PCC adapter. */
> +struct mctp_pcc_ndev {
> +	struct net_device *ndev;
> +	struct acpi_device *acpi_device;
> +	struct mctp_pcc_mailbox inbox;
> +	struct mctp_pcc_mailbox outbox;
> +};
> +
> +static void *mctp_pcc_rx_alloc(struct mbox_client *c, int size)
> +{
> +	struct mctp_pcc_ndev *mctp_pcc_ndev;
> +	struct mctp_pcc_mailbox *box;
> +	struct sk_buff *skb;
> +
> +	mctp_pcc_ndev =	container_of(c, struct mctp_pcc_ndev, inbox.client);
> +	box = &mctp_pcc_ndev->inbox;
> +
> +	if (size > mctp_pcc_ndev->ndev->mtu)
> +		return NULL;
> +	skb = netdev_alloc_skb(mctp_pcc_ndev->ndev, size);
> +	if (!skb)
> +		return NULL;
> +	skb_put(skb, size);
> +	skb->protocol = htons(ETH_P_MCTP);
> +	skb_queue_head(&box->packets, skb);
> +
> +	return skb->data;
> +}
> +
> +static void mctp_pcc_client_rx_callback(struct mbox_client *c, void *buffer)
> +{
> +	struct mctp_pcc_ndev *mctp_pcc_ndev;
> +	struct sk_buff *curr_skb = NULL;
> +	struct pcc_header pcc_header;
> +	struct sk_buff *skb = NULL;
> +	struct mctp_skb_cb *cb;
> +
> +	mctp_pcc_ndev = container_of(c, struct mctp_pcc_ndev, inbox.client);
> +	if (!buffer) {
> +		dev_dstats_rx_dropped(mctp_pcc_ndev->ndev);
> +		return;
> +	}
> +
> +	spin_lock(&mctp_pcc_ndev->inbox.packets.lock);
> +	skb_queue_walk(&mctp_pcc_ndev->inbox.packets, curr_skb) {
> +		skb = curr_skb;
> +		if (skb->data != buffer)
> +			continue;
> +		__skb_unlink(skb, &mctp_pcc_ndev->inbox.packets);
> +		break;
> +	}
> +	spin_unlock(&mctp_pcc_ndev->inbox.packets.lock);
> +
> +	if (skb) {
> +		dev_dstats_rx_add(mctp_pcc_ndev->ndev, skb->len);
> +		skb_reset_mac_header(skb);
> +		skb_pull(skb, sizeof(pcc_header));
> +		skb_reset_network_header(skb);
> +		cb = __mctp_cb(skb);
> +		cb->halen = 0;
> +		netif_rx(skb);
> +	}
> +}
> +
> +static void mctp_pcc_tx_done(struct mbox_client *c, void *mssg, int r)
> +{
> +	struct mctp_pcc_ndev *mctp_pcc_ndev;
> +	struct mctp_pcc_mailbox *box;
> +	struct sk_buff *skb = NULL;
> +	struct sk_buff *curr_skb;
> +
> +	mctp_pcc_ndev = container_of(c, struct mctp_pcc_ndev, outbox.client);
> +	box = container_of(c, struct mctp_pcc_mailbox, client);
> +	spin_lock(&box->packets.lock);
> +	skb_queue_walk(&box->packets, curr_skb) {
> +		skb = curr_skb;
> +		if (skb->data == mssg) {
> +			__skb_unlink(skb, &box->packets);
> +			break;
> +		}
> +	}
> +	spin_unlock(&box->packets.lock);
> +
> +	if (skb)
> +		dev_consume_skb_any(skb);
> +}
> +
> +static netdev_tx_t mctp_pcc_tx(struct sk_buff *skb, struct net_device *ndev)
> +{
> +	struct mctp_pcc_ndev *mpnd = netdev_priv(ndev);
> +	struct pcc_header *pcc_header;
> +	int len = skb->len;
> +	int rc;
> +
> +	rc = skb_cow_head(skb, sizeof(*pcc_header));
> +	if (rc) {
> +		dev_dstats_tx_dropped(ndev);
> +		kfree_skb(skb);
> +		return NETDEV_TX_OK;
> +	}
> +
> +	pcc_header = skb_push(skb, sizeof(*pcc_header));
> +	pcc_header->signature = PCC_SIGNATURE | mpnd->outbox.index;
> +	pcc_header->flags = PCC_CMD_COMPLETION_NOTIFY;
> +	memcpy(&pcc_header->command, MCTP_SIGNATURE, MCTP_SIGNATURE_LENGTH);
> +	pcc_header->length = len + MCTP_SIGNATURE_LENGTH;
> +
> +	skb_queue_head(&mpnd->outbox.packets, skb);
> +
> +	rc = mbox_send_message(mpnd->outbox.chan->mchan, skb->data);
> +
> +	if (rc < 0) {
> +		skb_unlink(skb, &mpnd->outbox.packets);
> +		return NETDEV_TX_BUSY;
> +	}
> +
> +	dev_dstats_tx_add(ndev, len);
> +	return NETDEV_TX_OK;
> +}
> +
> +static void drain_packets(struct sk_buff_head *list)
> +{
> +	struct sk_buff *skb;
> +
> +	while (!skb_queue_empty(list)) {
> +		skb = skb_dequeue(list);
> +		dev_consume_skb_any(skb);
> +	}
> +}
> +
> +static int mctp_pcc_ndo_open(struct net_device *ndev)
> +{
> +	struct mctp_pcc_ndev *mctp_pcc_ndev =
> +	    netdev_priv(ndev);
> +	struct mctp_pcc_mailbox *outbox =
> +	    &mctp_pcc_ndev->outbox;
> +	struct mctp_pcc_mailbox *inbox =
> +	    &mctp_pcc_ndev->inbox;
> +	int mctp_pcc_mtu;
> +
> +	outbox->chan = pcc_mbox_request_channel(&outbox->client, outbox->index);
> +	if (IS_ERR(outbox->chan))
> +		return PTR_ERR(outbox->chan);
> +
> +	inbox->chan = pcc_mbox_request_channel(&inbox->client, inbox->index);
> +	if (IS_ERR(inbox->chan)) {
> +		pcc_mbox_free_channel(outbox->chan);
> +		return PTR_ERR(inbox->chan);
> +	}
> +
> +	mctp_pcc_ndev->inbox.chan->rx_alloc = mctp_pcc_rx_alloc;
> +	mctp_pcc_ndev->outbox.chan->manage_writes = true;
> +
> +	mctp_pcc_mtu = mctp_pcc_ndev->outbox.chan->shmem_size -
> +		sizeof(struct pcc_header);
> +	ndev->mtu = MCTP_MIN_MTU;
> +	ndev->max_mtu = mctp_pcc_mtu;
> +	ndev->min_mtu = MCTP_MIN_MTU;
> +
> +	return 0;
> +}
> +
> +static int mctp_pcc_ndo_stop(struct net_device *ndev)
> +{
> +	struct mctp_pcc_ndev *mctp_pcc_ndev =
> +	    netdev_priv(ndev);
> +	struct mctp_pcc_mailbox *outbox =
> +	    &mctp_pcc_ndev->outbox;
> +	struct mctp_pcc_mailbox *inbox =
> +	    &mctp_pcc_ndev->inbox;
> +
> +	pcc_mbox_free_channel(outbox->chan);
> +	pcc_mbox_free_channel(inbox->chan);
> +
> +	drain_packets(&mctp_pcc_ndev->outbox.packets);
> +	drain_packets(&mctp_pcc_ndev->inbox.packets);
> +	return 0;
> +}
> +
> +static const struct net_device_ops mctp_pcc_netdev_ops = {
> +	.ndo_open = mctp_pcc_ndo_open,
> +	.ndo_stop = mctp_pcc_ndo_stop,
> +	.ndo_start_xmit = mctp_pcc_tx,
> +
> +};
> +
> +static void mctp_pcc_setup(struct net_device *ndev)
> +{
> +	ndev->type = ARPHRD_MCTP;
> +	ndev->hard_header_len = 0;
> +	ndev->tx_queue_len = 0;
> +	ndev->flags = IFF_NOARP;
> +	ndev->netdev_ops = &mctp_pcc_netdev_ops;
> +	ndev->needs_free_netdev = true;
> +	ndev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
> +}
> +
> +struct mctp_pcc_lookup_context {
> +	int index;
> +	u32 inbox_index;
> +	u32 outbox_index;
> +};
> +
> +static acpi_status lookup_pcct_indices(struct acpi_resource *ares,
> +				       void *context)
> +{
> +	struct mctp_pcc_lookup_context *luc = context;
> +	struct acpi_resource_address32 *addr;
> +
> +	if (ares->type != PCC_DWORD_TYPE)
> +		return AE_OK;
> +
> +	addr = ACPI_CAST_PTR(struct acpi_resource_address32, &ares->data);
> +	switch (luc->index) {
> +	case 0:
> +		luc->outbox_index = addr[0].address.minimum;
> +		break;
> +	case 1:
> +		luc->inbox_index = addr[0].address.minimum;
> +		break;
> +	}
> +	luc->index++;
> +	return AE_OK;
> +}
> +
> +static void mctp_cleanup_netdev(void *data)
> +{
> +	struct net_device *ndev = data;
> +
> +	mctp_unregister_netdev(ndev);
> +}
> +
> +static int mctp_pcc_initialize_mailbox(struct device *dev,
> +				       struct mctp_pcc_mailbox *box, u32 index)
> +{
> +	box->index = index;
> +	skb_queue_head_init(&box->packets);
> +	box->client.dev = dev;
> +	return 0;
> +}
> +
> +static int mctp_pcc_driver_add(struct acpi_device *acpi_dev)
> +{
> +	struct mctp_pcc_lookup_context context = {0};
> +	struct mctp_pcc_ndev *mctp_pcc_ndev;
> +	struct device *dev = &acpi_dev->dev;
> +	struct net_device *ndev;
> +	acpi_handle dev_handle;
> +	acpi_status status;
> +	char name[32];
> +	int rc;
> +
> +	dev_dbg(dev, "Adding mctp_pcc device for HID %s\n",
> +		acpi_device_hid(acpi_dev));
> +	dev_handle = acpi_device_handle(acpi_dev);
> +	status = acpi_walk_resources(dev_handle, "_CRS", lookup_pcct_indices,
> +				     &context);
> +	if (!ACPI_SUCCESS(status)) {
> +		dev_err(dev, "FAILURE to lookup PCC indexes from CRS\n");

FAILURE to lookup -> failed to lookup

> +		return -EINVAL;
> +	}
> +
> +	snprintf(name, sizeof(name), "mctpipcc%d", context.inbox_index);

mctp_pcc%d ?

> +	ndev = alloc_netdev(sizeof(*mctp_pcc_ndev), name, NET_NAME_PREDICTABLE,
> +			    mctp_pcc_setup);
> +	if (!ndev)
> +		return -ENOMEM;
> +
> +	mctp_pcc_ndev = netdev_priv(ndev);
> +
> +	/* inbox initialization */
> +	rc = mctp_pcc_initialize_mailbox(dev, &mctp_pcc_ndev->inbox,
> +					 context.inbox_index);
> +	if (rc)
> +		goto free_netdev;
> +
> +	mctp_pcc_ndev->inbox.client.rx_callback = mctp_pcc_client_rx_callback;
> +
> +	/* outbox initialization */
> +	rc = mctp_pcc_initialize_mailbox(dev, &mctp_pcc_ndev->outbox,
> +					 context.outbox_index);
> +	if (rc)
> +		goto free_netdev;
> +
> +	mctp_pcc_ndev->outbox.client.tx_done = mctp_pcc_tx_done;
> +	mctp_pcc_ndev->acpi_device = acpi_dev;
> +	mctp_pcc_ndev->ndev = ndev;
> +	acpi_dev->driver_data = mctp_pcc_ndev;
> +
> +	/* ndev needs to be freed before the iomemory (mapped above) gets
> +	 * unmapped,  devm resources get freed in reverse to the order they
> +	 * are added.
> +	 */
> +	rc = mctp_register_netdev(ndev, NULL, MCTP_PHYS_BINDING_PCC);
> +	if (rc)
> +		goto free_netdev;
> +
> +	return devm_add_action_or_reset(dev, mctp_cleanup_netdev, ndev);
> +free_netdev:
> +	free_netdev(ndev);
> +	return rc;
> +}
> +
> +static const struct acpi_device_id mctp_pcc_device_ids[] = {
> +	{ "DMT0001" },
> +	{}
> +};
> +
> +static struct acpi_driver mctp_pcc_driver = {
> +	.name = "mctp_pcc",
> +	.class = "Unknown",
> +	.ids = mctp_pcc_device_ids,
> +	.ops = {
> +		.add = mctp_pcc_driver_add,
> +	},
> +};
> +
> +module_acpi_driver(mctp_pcc_driver);
> +
> +MODULE_DEVICE_TABLE(acpi, mctp_pcc_device_ids);
> +
> +MODULE_DESCRIPTION("MCTP PCC ACPI device");
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Adam Young <admiyo@...amperecomputing.com>");

Thanks,
Alok

Powered by blists - more mailing lists