Re: [PATCH v17 02/22] sfc: add cxl support

[Jonathan Cameron <Jonathan.Cameron@huawei.com>]

On Tue, 24 Jun 2025 15:13:35 +0100
<alejandro.lucero-palau@amd.com> wrote:

> From: Alejandro Lucero <alucerop@amd.com>
> 
> Add CXL initialization based on new CXL API for accel drivers and make
> it dependent on kernel CXL configuration.
> 
> Signed-off-by: Alejandro Lucero <alucerop@amd.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Acked-by: Edward Cree <ecree.xilinx@gmail.com>
> Reviewed-by: Alison Schofield <alison.schofield@intel.com>

Hi Alejandro,

I think I'm missing something with respect to the relative life times.
Throwing one devm_ call into the middle of a probe is normally a recipe
for at least hard to read code, if not actual bugs.  It should be done
with care and accompanied by at least a comment.

Jonathan

> ---
>  drivers/net/ethernet/sfc/Kconfig      |  9 +++++
>  drivers/net/ethernet/sfc/Makefile     |  1 +
>  drivers/net/ethernet/sfc/efx.c        | 15 +++++++-
>  drivers/net/ethernet/sfc/efx_cxl.c    | 55 +++++++++++++++++++++++++++
>  drivers/net/ethernet/sfc/efx_cxl.h    | 40 +++++++++++++++++++
>  drivers/net/ethernet/sfc/net_driver.h | 10 +++++
>  6 files changed, 129 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/net/ethernet/sfc/efx_cxl.c
>  create mode 100644 drivers/net/ethernet/sfc/efx_cxl.h
> 
> diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
> index c4c43434f314..979f2801e2a8 100644
> --- a/drivers/net/ethernet/sfc/Kconfig
> +++ b/drivers/net/ethernet/sfc/Kconfig
> @@ -66,6 +66,15 @@ config SFC_MCDI_LOGGING
>  	  Driver-Interface) commands and responses, allowing debugging of
>  	  driver/firmware interaction.  The tracing is actually enabled by
>  	  a sysfs file 'mcdi_logging' under the PCI device.
> +config SFC_CXL
> +	bool "Solarflare SFC9100-family CXL support"
> +	depends on SFC && CXL_BUS >= SFC
> +	default SFC
> +	help
> +	  This enables SFC CXL support if the kernel is configuring CXL for
> +	  using CTPIO with CXL.mem. The SFC device with CXL support and
> +	  with a CXL-aware firmware can be used for minimizing latencies
> +	  when sending through CTPIO.
>  
>  source "drivers/net/ethernet/sfc/falcon/Kconfig"
>  source "drivers/net/ethernet/sfc/siena/Kconfig"
> diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
> index d99039ec468d..bb0f1891cde6 100644
> --- a/drivers/net/ethernet/sfc/Makefile
> +++ b/drivers/net/ethernet/sfc/Makefile
> @@ -13,6 +13,7 @@ sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \
>                             mae.o tc.o tc_bindings.o tc_counters.o \
>                             tc_encap_actions.o tc_conntrack.o
>  
> +sfc-$(CONFIG_SFC_CXL)	+= efx_cxl.o
>  obj-$(CONFIG_SFC)	+= sfc.o
>  
>  obj-$(CONFIG_SFC_FALCON) += falcon/
> diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
> index 112e55b98ed3..537668278375 100644
> --- a/drivers/net/ethernet/sfc/efx.c
> +++ b/drivers/net/ethernet/sfc/efx.c
> @@ -34,6 +34,7 @@
>  #include "selftest.h"
>  #include "sriov.h"
>  #include "efx_devlink.h"
> +#include "efx_cxl.h"
>  
>  #include "mcdi_port_common.h"
>  #include "mcdi_pcol.h"
> @@ -981,12 +982,15 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
>  	efx_pci_remove_main(efx);
>  
>  	efx_fini_io(efx);
> +
> +	probe_data = container_of(efx, struct efx_probe_data, efx);
> +	efx_cxl_exit(probe_data);
> +
>  	pci_dbg(efx->pci_dev, "shutdown successful\n");
>  
>  	efx_fini_devlink_and_unlock(efx);
>  	efx_fini_struct(efx);
>  	free_netdev(efx->net_dev);
> -	probe_data = container_of(efx, struct efx_probe_data, efx);
>  	kfree(probe_data);
>  };
>  
> @@ -1190,6 +1194,15 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
>  	if (rc)
>  		goto fail2;
>  
> +	/* A successful cxl initialization implies a CXL region created to be
> +	 * used for PIO buffers. If there is no CXL support, or initialization
> +	 * fails, efx_cxl_pio_initialised will be false and legacy PIO buffers
> +	 * defined at specific PCI BAR regions will be used.
> +	 */
> +	rc = efx_cxl_init(probe_data);
> +	if (rc)
> +		pci_err(pci_dev, "CXL initialization failed with error %d\n", rc);
> +
>  	rc = efx_pci_probe_post_io(efx);
>  	if (rc) {
>  		/* On failure, retry once immediately.
> diff --git a/drivers/net/ethernet/sfc/efx_cxl.c b/drivers/net/ethernet/sfc/efx_cxl.c
> new file mode 100644
> index 000000000000..f1db7284dee8
> --- /dev/null
> +++ b/drivers/net/ethernet/sfc/efx_cxl.c
> @@ -0,0 +1,55 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/****************************************************************************
> + *
> + * Driver for AMD network controllers and boards
> + * Copyright (C) 2025, Advanced Micro Devices, Inc.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms of the GNU General Public License version 2 as published
> + * by the Free Software Foundation, incorporated herein by reference.
> + */
> +
> +#include <cxl/pci.h>
> +#include <linux/pci.h>
> +
> +#include "net_driver.h"
> +#include "efx_cxl.h"
> +
> +#define EFX_CTPIO_BUFFER_SIZE	SZ_256M
> +
> +int efx_cxl_init(struct efx_probe_data *probe_data)
> +{
> +	struct efx_nic *efx = &probe_data->efx;
> +	struct pci_dev *pci_dev = efx->pci_dev;
> +	struct efx_cxl *cxl;
> +	u16 dvsec;
> +
> +	probe_data->cxl_pio_initialised = false;
> +
> +	dvsec = pci_find_dvsec_capability(pci_dev, PCI_VENDOR_ID_CXL,
> +					  CXL_DVSEC_PCIE_DEVICE);
> +	if (!dvsec)
> +		return 0;
> +
> +	pci_dbg(pci_dev, "CXL_DVSEC_PCIE_DEVICE capability found\n");
> +
> +	/* Create a cxl_dev_state embedded in the cxl struct using cxl core api
> +	 * specifying no mbox available.
> +	 */
> +	cxl = devm_cxl_dev_state_create(&pci_dev->dev, CXL_DEVTYPE_DEVMEM,
> +					pci_dev->dev.id, dvsec, struct efx_cxl,
> +					cxlds, false);

The life time of this will outlast everything else in the efx driver.
Is that definitely safe to do?  Mostly from a reviewability and difficulty
of reasoning we avoid such late releasing of resources.

Perhaps add to the comment before this call what you are doing to ensure that
it is fine to release this after everything in efx_pci_remove()

Or wrap it up in a devres group and release that group in efx_cxl_exit().

See devres_open_group(), devres_release_group()


> +
> +	if (!cxl)
> +		return -ENOMEM;
> +
> +	probe_data->cxl = cxl;
> +
> +	return 0;
> +}
> +
> +void efx_cxl_exit(struct efx_probe_data *probe_data)
> +{
> +}
> +
> +MODULE_IMPORT_NS("CXL");
> diff --git a/drivers/net/ethernet/sfc/efx_cxl.h b/drivers/net/ethernet/sfc/efx_cxl.h
> new file mode 100644
> index 000000000000..961639cef692
> --- /dev/null
> +++ b/drivers/net/ethernet/sfc/efx_cxl.h
> @@ -0,0 +1,40 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/****************************************************************************
> + * Driver for AMD network controllers and boards
> + * Copyright (C) 2025, Advanced Micro Devices, Inc.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms of the GNU General Public License version 2 as published
> + * by the Free Software Foundation, incorporated herein by reference.
> + */
> +
> +#ifndef EFX_CXL_H
> +#define EFX_CXL_H
> +
> +#ifdef CONFIG_SFC_CXL
> +
> +#include <cxl/cxl.h>
> +
> +struct cxl_root_decoder;
> +struct cxl_port;
> +struct cxl_endpoint_decoder;
> +struct cxl_region;
> +struct efx_probe_data;
> +
> +struct efx_cxl {
> +	struct cxl_dev_state cxlds;
> +	struct cxl_memdev *cxlmd;
> +	struct cxl_root_decoder *cxlrd;
> +	struct cxl_port *endpoint;
> +	struct cxl_endpoint_decoder *cxled;
> +	struct cxl_region *efx_region;
> +	void __iomem *ctpio_cxl;
> +};
> +
> +int efx_cxl_init(struct efx_probe_data *probe_data);
> +void efx_cxl_exit(struct efx_probe_data *probe_data);
> +#else
> +static inline int efx_cxl_init(struct efx_probe_data *probe_data) { return 0; }
> +static inline void efx_cxl_exit(struct efx_probe_data *probe_data) {}
> +#endif
> +#endif
> diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
> index 5c0f306fb019..0e685b8a9980 100644
> --- a/drivers/net/ethernet/sfc/net_driver.h
> +++ b/drivers/net/ethernet/sfc/net_driver.h
> @@ -1199,14 +1199,24 @@ struct efx_nic {
>  	atomic_t n_rx_noskb_drops;
>  };
>  
> +#ifdef CONFIG_SFC_CXL
> +struct efx_cxl;
> +#endif
> +
>  /**
>   * struct efx_probe_data - State after hardware probe
>   * @pci_dev: The PCI device
>   * @efx: Efx NIC details
> + * @cxl: details of related cxl objects
> + * @cxl_pio_initialised: cxl initialization outcome.
>   */
>  struct efx_probe_data {
>  	struct pci_dev *pci_dev;
>  	struct efx_nic efx;
> +#ifdef CONFIG_SFC_CXL
> +	struct efx_cxl *cxl;
> +	bool cxl_pio_initialised;
> +#endif
>  };
>  
>  static inline struct efx_nic *efx_netdev_priv(struct net_device *dev)