Re: [PATCH v6 8/8] fs/resctrl: Introduce interface to modify io_alloc Capacity Bit Masks

[Reinette Chatre <reinette.chatre@intel.com>]

Hi Babu,

On 6/11/25 2:23 PM, Babu Moger wrote:
> "io_alloc" feature is a mechanism that enables direct insertion of data

""io_alloc" feature is a mechanism that enables" -> ""io_alloc" feature enables"

> from I/O devices into the L3 cache. By directly caching data from I/O

Drop L3

> devices rather than first storing the I/O data in DRAM, it reduces the
> demands on DRAM bandwidth and reduces latency to the processor consuming
> the I/O data.
> 
> "io_alloc" feature uses the highest CLOSID to route the traffic from I/O

How is the CLOSID related here?

> devices. Provide the interface to modify io_alloc CBMs (Capacity Bit Mask)
> when feature is enabled.
> 
> Signed-off-by: Babu Moger <babu.moger@amd.com>
> ---

...

> ---
>  Documentation/filesystems/resctrl.rst | 13 ++++
>  fs/resctrl/ctrlmondata.c              |  4 +-
>  fs/resctrl/internal.h                 |  2 +
>  fs/resctrl/rdtgroup.c                 | 89 ++++++++++++++++++++++++++-
>  4 files changed, 105 insertions(+), 3 deletions(-)
> 
> diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
> index b31748ec8c61..ae1157dcb4a3 100644
> --- a/Documentation/filesystems/resctrl.rst
> +++ b/Documentation/filesystems/resctrl.rst
> @@ -181,6 +181,19 @@ related to allocation:
>  			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
>  			0=ffff;1=ffff
>  
> +		CBM can be configured by writing to the interface.
> +
> +		Example::
> +
> +			# echo 1=FF > /sys/fs/resctrl/info/L3/io_alloc_cbm
> +			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
> +			0=ffff;1=00ff
> +
> +		When CDP is enabled, io_alloc directs traffic using the highest CLOSID
> +		linked to an L3CODE resource. Although CBMs can be accessed through
> +		either L3CODE or L3DATA resources, any updates to the schemata are
> +		always routed through L3CODE.

Please do not commit resctrl to this implementation by documenting it as part of
user interface. Could snippet about CDP I shared in patch 6 be placed here as
a replacement? Not the usage of *may* to keep implementation options open.

> +
>  
>  Memory bandwidth(MB) subdirectory contains the following files
>  with respect to allocation:
> diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
> index 6409637b4de6..f3e5e697945c 100644
> --- a/fs/resctrl/ctrlmondata.c
> +++ b/fs/resctrl/ctrlmondata.c
> @@ -148,8 +148,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
>   * Read one cache bit mask (hex). Check that it is valid for the current
>   * resource type.
>   */
> -static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
> -		     struct rdt_ctrl_domain *d)
> +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
> +	      struct rdt_ctrl_domain *d)
>  {
>  	enum rdtgrp_mode mode = data->mode;
>  	struct resctrl_staged_config *cfg;
> diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
> index 10a3188ffa54..755f23934295 100644
> --- a/fs/resctrl/internal.h
> +++ b/fs/resctrl/internal.h
> @@ -382,6 +382,8 @@ bool closid_allocated(unsigned int closid);
>  int resctrl_find_cleanest_closid(void);
>  void show_doms(struct seq_file *s, struct resctrl_schema *schema,
>  	       char *name, int closid);
> +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
> +	      struct rdt_ctrl_domain *d);
>  
>  #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
>  int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
> index 0c2d2cf4baa1..f6c44fae4b72 100644
> --- a/fs/resctrl/rdtgroup.c
> +++ b/fs/resctrl/rdtgroup.c
> @@ -2037,6 +2037,92 @@ static int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of,
>  	return ret;
>  }
>  
> +static int resctrl_io_alloc_parse_line(char *line,  struct rdt_resource *r,
> +				       struct resctrl_schema *s, u32 closid)
> +{
> +	struct rdt_parse_data data;
> +	struct rdt_ctrl_domain *d;
> +	char *dom = NULL, *id;
> +	unsigned long dom_id;
> +
> +next:
> +	if (!line || line[0] == '\0')
> +		return 0;
> +
> +	dom = strsep(&line, ";");
> +	id = strsep(&dom, "=");
> +	if (!dom || kstrtoul(id, 10, &dom_id)) {
> +		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
> +		return -EINVAL;
> +	}
> +
> +	dom = strim(dom);
> +	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +		if (d->hdr.id == dom_id) {
> +			data.buf = dom;
> +			data.mode = RDT_MODE_SHAREABLE;
> +			data.closid = closid;
> +			if (parse_cbm(&data, s, d))
> +				return -EINVAL;
> +			goto next;
> +		}
> +	}
> +	return -EINVAL;
> +}
> +
> +static ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of,
> +					  char *buf, size_t nbytes, loff_t off)
> +{
> +	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
> +	struct rdt_resource *r = s->res;
> +	u32 io_alloc_closid;
> +	int ret = 0;
> +
> +	/* Valid input requires a trailing newline */
> +	if (nbytes == 0 || buf[nbytes - 1] != '\n')
> +		return -EINVAL;
> +
> +	buf[nbytes - 1] = '\0';
> +
> +	if (!r->cache.io_alloc_capable) {
> +		rdt_last_cmd_puts("io_alloc feature is not supported on the resource\n");

rdt_last_cmd_puts() requires rdtgroup_mutex to be held.

> +		return -EINVAL;
> +	}
> +
> +	cpus_read_lock();
> +	mutex_lock(&rdtgroup_mutex);
> +
> +	rdt_last_cmd_clear();
> +	rdt_staged_configs_clear();
> +
> +	if (!resctrl_arch_get_io_alloc_enabled(r)) {
> +		rdt_last_cmd_puts("io_alloc feature is not enabled\n");
> +		ret = -EINVAL;
> +		goto cbm_write_out;

can just be "out"

> +	}
> +
> +	io_alloc_closid = resctrl_io_alloc_closid_get(r);
> +	if (io_alloc_closid < 0) {

Similar to other places, since this is preceded by resctrl_arch_get_io_alloc_enabled(r)
passing the io_alloc_closid has to be valid and can use proposed resctrl_io_alloc_closid()
helper to simplify the code.

> +		rdt_last_cmd_puts("Max CLOSID to support io_alloc is not available\n");
> +		ret = -EINVAL;
> +		goto cbm_write_out;
> +	}
> +
> +	ret = resctrl_io_alloc_parse_line(buf, r, resctrl_schema_io_alloc(s),
> +					  io_alloc_closid);

Here too I think both schemata needs to be updated.

> +	if (ret)
> +		goto cbm_write_out;
> +
> +	ret = resctrl_arch_update_domains(r, io_alloc_closid);
> +
> +cbm_write_out:
> +	rdt_staged_configs_clear();
> +	mutex_unlock(&rdtgroup_mutex);
> +	cpus_read_unlock();
> +
> +	return ret ?: nbytes;
> +}
> +
>  /* rdtgroup information files for one cache resource. */
>  static struct rftype res_common_files[] = {
>  	{
> @@ -2198,9 +2284,10 @@ static struct rftype res_common_files[] = {
>  	},
>  	{
>  		.name		= "io_alloc_cbm",
> -		.mode		= 0444,
> +		.mode		= 0644,
>  		.kf_ops		= &rdtgroup_kf_single_ops,
>  		.seq_show	= resctrl_io_alloc_cbm_show,
> +		.write		= resctrl_io_alloc_cbm_write,
>  	},
>  	{
>  		.name		= "mba_MBps_event",

Reinette