Re: [RFC] drm/xe: Expose retired VRAM pages via drm-ras

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Thu, Sep 03, 2026 at 02:50:14PM +0530, Aravind Iddamsetty wrote:
> 
> On 31-08-2026 23:39, Rodrigo Vivi wrote:
> > Ccing AMD folks...
> >
> > AMD folks, I understand you have your sysfs for your 'uniras' in
> > production and already using your sysfs entries. But I would appreciate
> > if you guys can take a look to this drm-ras proposed API for the
> > memory page offline RAS related entry. Perhaps this is something that
> > you might want to align in the future. So, it would be good to design
> > something that is generic or flexible enough.
> >
> > On Mon, Aug 31, 2026 at 07:08:43PM +0530, Aravind Iddamsetty wrote:
> >
> > For a bit of context to AMD folks, I blocked Intel attempt to create
> > a sysfs for the memory page offlining feature because it was breaking
> > the sysfs rules and using a mixed fancy formatting.
> >
> > That solution apparently was inspired by the AMD's gpu_vram_bad_pages
> > where each record is  0x%08x : 0x%08x : %1s\n  — three different types
> > with decorative  :  separators. That's the "fancy formatting" clause.
> > And it's ASCII text stuffed into a binary attribute, so it gets neither
> > benefit: not parseable as a blob, not compliant as text.
> >
> > The rule for reference:
> > Documentation/filesystems/sysfs.rst:
> >
> > """
> > Attributes should be ASCII text files, preferably with only one value per file.
> > It is noted that it may not be efficient to contain only one value per file, so
> > it is socially acceptable to express an array of values of the same type.
> >
> > Mixing types, expressing multiple lines of data, and doing fancy formatting of
> > data is heavily frowned upon. Doing these things may get you publicly humiliated
> > and your code rewritten without notice.
> > """
> >
> >> The memory page offlining support tracks bad VRAM pages and currently
> >> only exposes them through debugfs (vram_bad_pages), which is not a
> >> stable ABI. Add a proper userspace interface on top of it using the
> >> drm-ras generic netlink family.
> > After considering every other API and placement for this infrastructure,
> > I agree that the drm-ras netlink is the one that aligns better wit the
> > need of the mem page offline flows and semantics.
> >
> > But I have a few doubts about some of the choices below.
> >
> >> Introduce a new node type DRM_RAS_NODE_TYPE_RETIRED_RESOURCES which
> >> enumerates hardware resources that have been permanently taken out of
> >> service. The node type is designed to be extensible: each entry carries
> >> a resource-type discriminator plus a type-specific nested attribute, so
> >> future resource types can be added without touching existing consumers.
> >> VRAM pages are the first supported type, reported via the vram-page nest
> >> as {address, size} with a retirement status
> >> (retired/pending/failed).
> > I understand that your goal of creating this retired-resources is to
> > make this generic and easy to extend.
> > And this aligns with the goal and original design of the drm-ras itself,
> > which is be extensible by definition from day 0.
> >
> > However, I'm afraid that in this case here I couldn't think of other
> > kind of 'resources' that we would want to 'retire' at runtime. So,
> > I'm afraid that this is forcing the user-space to go one extra level without
> > a good reason.
> >
> > What about a new drm-ras node that is simply 'bad-vram-pages' or even better:
> > 'memory-offline' ?!
> in future if there are any repairable resources like memory, fabric if
> they support sparings performed through in field repair those can be
> exposed via this interface so designed it to be generic.

ack

> >
> >> Two operations are added on the node:
> >>  - GET_RETIRED_RESOURCES: dump the list of retired resources.
> >>  - GET_RETIRED_RESOURCES_INFO: dump per-type limits and occupancy
> >>    (max/offlined/queued counts), e.g. the FW-provided maximum number of
> >>    pages that can be offlined.
> >>
> >> Eg:
> >> $ sudo ./tools/net/ynl/pyynl/cli.py \
> >>      --spec Documentation/netlink/specs/drm_ras.yaml \
> >>      --dump list-nodes
> >>
> >> [{'device-name': '0000:03:00.0', 'node-id': 0, 'node-name':'correctable-errors', 'node-type': 'error-counter'},
> >>  {'device-name': '0000:03:00.0', 'node-id': 1, 'node-name':'uncorrectable-errors', 'node-type': 'error-counter'},
> >>  {'device-name': '0000:03:00.0', 'node-id': 2, 'node-name':'vram-retired-pages', 'node-type': 'retired-resources'}]
> >>
> >> $ sudo ./tools/net/ynl/pyynl/cli.py --spec \
> >> Documentation/netlink/specs/drm_ras.yaml  --dump  get-retired-resources \
> >> --json '{"node-id": 2}'
> >>
> >> [{'node-id': 2, 'status': 'retired', 'type': 'vram-page', 'vram-page': {'address': 12807041024, 'size': 4096}}]
> > I'm confused here, isn't status such as 'retired' a per-page attribute?
> > Why isn't it inside the vram-page itself?
> >
> > $ sudo ynl --dump get-memory-offline --json '{"node-id": 2}'
> >
> > [{'node-id': 2,
> >   'page': [{'address': 12807041024, 'size': 4096,  'status': 'offlined'},
> >            {'address': 12807045120, 'size': 4096,  'status': 'offlined'},
> >            {'address': 12812345344, 'size': 4096,  'status': 'pending'},
> >            {'address': 12898765312, 'size': 65536, 'status': 'failed'}]}]
> >
> >
> > Although I doubt we would get different page sizes here, I believe this is
> > generic and matches better with AMD's current sysfs needs.
> 
> the status is still a per entry I just had  type to indicate what is the
> resource may be that confused, i will drop the type here as its obvious,
> and also make the format simpler like you suggested
> 
> ./tools/net/ynl/pyynl/cli.py --spec
> Documentation/netlink/specs/drm_ras.yaml  --dump  get-retired-resources
> --json '{"node-id": 2}'
> [{'node-id': 2, 'status': 'retired', 'type': 'vram-page', 'vram-page':
> {'address': 22451773440, 'size': 4096}},
>  {'node-id': 2, 'status': 'retired', 'type': 'vram-page', 'vram-page':
> {'address': 22451777536, 'size': 4096}}]
> 
> new format to be:
> 
> {'node-id': 2, 'address': 0x2a4b000, 'size': 4096, 'status': 'retired'}
> {'node-id': 2, 'address': 0x2a4c000, 'size': 4096, 'status': 'pending'}

cool, thanks

> 
> >
> >
> >> $ sudo ./tools/net/ynl/pyynl/cli.py --spec \
> >> Documentation/netlink/specs/drm_ras.yaml  --dump \
> >> get-retired-resources-info --json '{"node-id": 2}'
> >>
> >> [{'max-count': 100, 'node-id': 2, 'offlined-count': 1, 'queued-count': 0, 'type': 'vram-page'}]
> >>
> >> This change is built on top of and depends on the memory page offline
> >> patch series [1]
> >>
> >> [1] https://lore.kernel.org/all/20260831064942.315720-17-tejas.upadhyay@intel.com/
> >>
> >> Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
> >> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> >> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> >> Cc: Riana Tauro <riana.tauro@intel.com>
> >> Cc: Raag Jadav <raag.jadav@intel.com>
> >> Cc: Joshua Santhosh Ranjan <joshua.santosh.ranjan@intel.com>
> >> Cc: Ashwin Kumar Kulkarni <ashwin.kumar.kulkarni@intel.com>
> >> Cc: Pratik Bari <pratik.bari@intel.com>
> >>
> >> Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@linux.intel.com>
> >> Assisted-by: Copilot:claude-opus-4.8
> >>
> >> ---
> >>  Documentation/netlink/specs/drm_ras.yaml | 131 +++++++++++++-
> >>  drivers/gpu/drm/drm_ras.c                | 221 ++++++++++++++++++++++-
> >>  drivers/gpu/drm/drm_ras_nl.c             |  24 +++
> >>  drivers/gpu/drm/drm_ras_nl.h             |   4 +
> >>  drivers/gpu/drm/xe/xe_drm_ras.c          |  81 +++++++++
> >>  drivers/gpu/drm/xe/xe_drm_ras_types.h    |   3 +
> >>  drivers/gpu/drm/xe/xe_ttm_vram_mgr.c     | 134 ++++++++++++++
> >>  drivers/gpu/drm/xe/xe_ttm_vram_mgr.h     |   5 +
> >>  include/drm/drm_ras.h                    |  87 +++++++++
> >>  include/uapi/drm/drm_ras.h               |  63 ++++++-
> >>  10 files changed, 742 insertions(+), 11 deletions(-)
> >>
> >> diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
> > Btw, this doesn't apply on recent drm-tip. There were some changes to this spec
> > merged recently. Please do a v2 in a recent drm-tip/
> sure will fix and respin
> >
> >> index 8aed3d4515e5..37fe297eeb2e 100644
> >> --- a/Documentation/netlink/specs/drm_ras.yaml
> >> +++ b/Documentation/netlink/specs/drm_ras.yaml
> >> @@ -16,11 +16,34 @@ definitions:
> >>      type: enum
> >>      name: node-type
> >>      value-start: 1
> >> -    entries: [error-counter]
> >> +    entries: [error-counter, retired-resources]
> >>      doc: >-
> >> -         Type of the node. Currently, only error-counter nodes are
> >> -         supported, which expose reliability counters for a hardware/software
> >> -         component.
> >> +         Type of the node.
> >> +         error-counter nodes expose reliability counters for a
> >> +         hardware/software component. retired-resources nodes enumerate
> >> +         hardware resources (e.g. VRAM pages) that have been permanently
> >> +         taken out of service.
> >> +  -
> >> +    type: enum
> >> +    name: retired-resource-status
> >> +    value-start: 0
> >> +    entries: [retired, pending, failed]
> >> +    doc: >-
> >> +         Status of a retired resource entry. retired means the resource is
> >> +         permanently reserved and out of service; pending means retirement is
> >> +         queued but the reservation is not yet complete; failed means the
> >> +         reservation failed and the resource may still be in use.
> >> +  -
> >> +    type: enum
> >> +    name: retired-resource-type
> >> +    value-start: 1
> >> +    entries: [vram-page]
> >> +    doc: >-
> >> +         Type of a retired resource entry. The type selects which type-specific
> >> +         nested attribute is present. New hardware resource types can be added
> >> +         here, each carrying its own nested attribute set, without affecting
> >> +         existing types. vram-page describes a VRAM page by device address and
> >> +         size.
> >>  
> >>  attribute-sets:
> >>    -
> >> @@ -96,6 +119,66 @@ attribute-sets:
> >>          name: error-value
> >>          type: u32
> >>          doc: Current value of the error counter.
> >> +  -
> >> +    name: retired-resource-attrs
> >> +    attributes:
> >> +      -
> >> +        name: node-id
> >> +        type: u32
> >> +        doc: Node ID targeted by this retired resource operation.
> >> +      -
> >> +        name: type
> >> +        type: u32
> >> +        doc: Type of the retired resource, selects the type-specific nest.
> >> +        enum: retired-resource-type
> >> +      -
> >> +        name: status
> >> +        type: u32
> >> +        doc: Retirement status of the resource.
> >> +        enum: retired-resource-status
> >> +      -
> >> +        name: vram-page
> >> +        type: nest
> >> +        nested-attributes: vram-page-attrs
> >> +        doc: Type-specific payload present when type is vram-page.
> >> +  -
> >> +    name: vram-page-attrs
> >> +    attributes:
> >> +      -
> >> +        name: address
> >> +        type: u64
> >> +        doc: Device address of the retired VRAM page (e.g. DPA).
> >> +      -
> >> +        name: size
> >> +        type: u64
> >> +        doc: Size of the retired VRAM page in bytes.
> >> +      -
> >> +        name: pad
> >> +        type: pad
> >> +  -
> >> +    name: retired-resource-info-attrs
> >> +    attributes:
> >> +      -
> >> +        name: node-id
> >> +        type: u32
> >> +        doc: Node ID targeted by this retired resource info operation.
> >> +      -
> >> +        name: type
> >> +        type: u32
> >> +        doc: Resource type this info entry describes.
> >> +        enum: retired-resource-type
> >> +      -
> >> +        name: max-count
> >> +        type: u32
> >> +        doc: Maximum resources of this type that can be retired.
> >> +      -
> >> +        name: offlined-count
> >> +        type: u32
> >> +        doc: Resources of this type currently retired and out of service.
> >> +      -
> >> +        name: queued-count
> >> +        type: u32
> >> +        doc: Resources of this type queued for retirement (pending or failed).
> >>  
> >>  operations:
> >>    list:
> >> @@ -167,6 +250,46 @@ operations:
> >>            - error-id
> >>            - error-name
> >>            - error-value
> >> +    -
> >> +      name: get-retired-resources
> >> +      doc: >-
> >> +           Enumerate the resources (e.g. VRAM pages) that a retired-resources
> >> +           node has taken out of service. Each entry includes a type, a
> >> +           retirement status and one type-specific nested attribute selected by
> >> +           the type. User space must obtain the node ID from list-nodes first.
> >> +      attribute-set: retired-resource-attrs
> >> +      flags: [admin-perm]
> >> +      dump:
> >> +        request:
> >> +          attributes:
> >> +            - node-id
> >> +        reply:
> >> +          attributes:
> >> +            - node-id
> >> +            - type
> >> +            - status
> >> +            - vram-page
> >> +    -
> >> +      name: get-retired-resources-info
> >> +      doc: >-
> >> +           Enumerate per-type retired resource limits and current occupancy for
> >> +           a retired-resources node: for each resource type the node tracks, the
> >> +           maximum number of resources that can be retired and the current
> >> +           retired and queued counts. User space must obtain the node ID from
> >> +           list-nodes first.
> >> +      attribute-set: retired-resource-info-attrs
> >> +      flags: [admin-perm]
> >> +      dump:
> >> +        request:
> >> +          attributes:
> >> +            - node-id
> >> +        reply:
> >> +          attributes:
> >> +            - node-id
> >> +            - type
> >> +            - max-count
> >> +            - offlined-count
> >> +            - queued-count
> >>  
> >>  mcast-groups:
> >>    list:
> >> diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> >> index 39155fb514de..a708fec7b68f 100644
> >> --- a/drivers/gpu/drm/drm_ras.c
> >> +++ b/drivers/gpu/drm/drm_ras.c
> >> @@ -56,7 +56,6 @@
> >>   * Node type:
> >>   *
> >>   * - ERROR_COUNTER:
> >> - *     + Currently, only error counters are supported.
> >>   *     + The driver must implement the query_error_counter() callback to provide
> >>   *       the name and the value of the error counter.
> >>   *     + The driver must provide a error_counter_range.last value informing the
> >> @@ -67,6 +66,13 @@
> >>   *       driver must return -ENOENT to the query_error_counter as an indication
> >>   *       that the ID should be skipped and not listed in the netlink API.
> >>   *
> >> + * - RETIRED_RESOURCES:
> >> + *     + Enumerates hardware resources (e.g. VRAM pages) permanently taken out
> >> + *       of service.
> >> + *     + The driver must implement the query_retired_resource() callback, which
> >> + *       is called with an incrementing index and returns -ENOENT once the last
> >> + *       entry has been reported.
> >> + *
> >>   * Netlink handlers:
> >>   *
> >>   * - drm_ras_nl_list_nodes_dumpit(): Implements the LIST_NODES
> >> @@ -77,6 +83,9 @@
> >>   *   operation, fetching a counter value from a specific node.
> >>   * - drm_ras_nl_clear_error_counter_doit(): Implements the CLEAR_ERROR_COUNTER doit
> >>   *   operation, clearing a counter value from a specific node.
> >> + * - drm_ras_nl_get_retired_resources_dumpit(): Implements the
> >> + *   GET_RETIRED_RESOURCES dumpit operation, enumerating retired resources of a
> >> + *   specific node.
> >>   */
> >>  
> >>  static DEFINE_XARRAY_ALLOC(drm_ras_xa);
> >> @@ -87,6 +96,8 @@ static DEFINE_XARRAY_ALLOC(drm_ras_xa);
> >>  struct drm_ras_ctx {
> >>  	/* Which xarray id to restart the dump from */
> >>  	unsigned long restart;
> >> +	/* Ordering-key cursor for retired-resource dumps (inclusive lower bound) */
> >> +	u64 cursor;
> >>  };
> >>  
> >>  /**
> >> @@ -456,6 +467,197 @@ int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
> >>  	return node->clear_error_counter(node, error_id);
> >>  }
> >>  
> >> +static int msg_put_retired_resource(struct sk_buff *skb, u32 node_id,
> >> +				    const struct drm_ras_retired_resource *res)
> >> +{
> >> +	struct nlattr *nest;
> >> +
> >> +	if (nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID, node_id) ||
> >> +	    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_ATTRS_TYPE, res->type) ||
> >> +	    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_ATTRS_STATUS, res->status))
> >> +		return -EMSGSIZE;
> >> +
> >> +	switch (res->type) {
> >> +	case DRM_RAS_RETIRED_RESOURCE_TYPE_VRAM_PAGE:
> >> +		nest = nla_nest_start(skb,
> >> +				      DRM_RAS_A_RETIRED_RESOURCE_ATTRS_VRAM_PAGE);
> >> +		if (!nest)
> >> +			return -EMSGSIZE;
> >> +
> >> +		if (nla_put_u64_64bit(skb, DRM_RAS_A_VRAM_PAGE_ATTRS_ADDRESS,
> >> +				      res->vram_page.address,
> >> +				      DRM_RAS_A_VRAM_PAGE_ATTRS_PAD) ||
> >> +		    nla_put_u64_64bit(skb, DRM_RAS_A_VRAM_PAGE_ATTRS_SIZE,
> >> +				      res->vram_page.size,
> >> +				      DRM_RAS_A_VRAM_PAGE_ATTRS_PAD)) {
> >> +			nla_nest_cancel(skb, nest);
> >> +			return -EMSGSIZE;
> >> +		}
> >> +
> >> +		nla_nest_end(skb, nest);
> >> +		break;
> >> +	default:
> >> +		/* Unknown type: common attributes were still reported. */
> >> +		break;
> >> +	}
> >> +
> >> +	return 0;
> >> +}
> >> +
> >> +/**
> >> + * drm_ras_nl_get_retired_resources_dumpit() - Dump retired resources of a node
> >> + * @skb: Netlink message buffer
> >> + * @cb: Callback context for multi-part dumps
> >> + *
> >> + * Iterates over all retired resources of a %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES
> >> + * node and appends their attributes to the given netlink message buffer. Each
> >> + * entry carries a common type and status, plus one type-specific nested
> >> + * attribute selected by the type. Uses @cb->ctx to store an ordering-key cursor
> >> + * so multi-part dumps resume by key rather than position, staying correct if
> >> + * the list changes concurrently between message parts.
> >> + *
> >> + * Return: 0 if all entries fit in @skb, number of bytes added to @skb if
> >> + *          the buffer filled up (requires multi-part continuation), or
> >> + *          a negative error code on failure.
> >> + */
> >> +int drm_ras_nl_get_retired_resources_dumpit(struct sk_buff *skb,
> >> +					    struct netlink_callback *cb)
> >> +{
> >> +	const struct genl_info *info = genl_info_dump(cb);
> >> +	struct drm_ras_ctx *ctx = (void *)cb->ctx;
> >> +	struct drm_ras_retired_resource res;
> >> +	struct drm_ras_node *node;
> >> +	struct nlattr *hdr;
> >> +	u32 node_id;
> >> +	u64 cursor;
> >> +	int ret = 0;
> >> +
> >> +	if (!info->attrs ||
> >> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID))
> >> +		return -EINVAL;
> >> +
> >> +	node_id = nla_get_u32(info->attrs[DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID]);
> >> +
> >> +	node = xa_load(&drm_ras_xa, node_id);
> >> +	if (!node || node->type != DRM_RAS_NODE_TYPE_RETIRED_RESOURCES ||
> >> +	    !node->query_retired_resource)
> >> +		return -ENOENT;
> >> +
> >> +	cursor = ctx->cursor;
> >> +	for (;;) {
> >> +		memset(&res, 0, sizeof(res));
> >> +		ret = node->query_retired_resource(node, cursor, &res);
> >> +		/* -ENOENT marks the end of the list. */
> >> +		if (ret == -ENOENT) {
> >> +			ret = 0;
> >> +			break;
> >> +		}
> >> +		if (ret)
> >> +			return ret;
> >> +
> >> +		hdr = genlmsg_iput(skb, info);
> >> +		if (!hdr) {
> >> +			ret = -EMSGSIZE;
> >> +			break;
> >> +		}
> >> +
> >> +		ret = msg_put_retired_resource(skb, node_id, &res);
> >> +		if (ret) {
> >> +			genlmsg_cancel(skb, hdr);
> >> +			break;
> >> +		}
> >> +
> >> +		genlmsg_end(skb, hdr);
> >> +		/* Advance past this entry; keys are unique. */
> >> +		cursor = res.key + 1;
> >> +	}
> >> +
> >> +	/* On buffer-full the current entry was not emitted; resume at it. */
> >> +	if (ret == -EMSGSIZE)
> >> +		ctx->cursor = cursor;
> >> +
> >> +	return ret;
> >> +}
> >> +
> >> +/**
> >> + * drm_ras_nl_get_retired_resources_info_dumpit() - Dump node retired limits
> >> + * @skb: Netlink message buffer
> >> + * @cb: Callback context for multi-part dumps
> >> + *
> >> + * Reports per-type limits and current occupancy for a
> >> + * %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES node. Each entry carries the resource
> >> + * type, the maximum number of resources of that type that can be retired, and
> >> + * the current retired and queued counts. A node that tracks several resource
> >> + * types reports one entry per type. Uses @cb->ctx to track the next type index
> >> + * in case the buffer fills up, allowing multi-part dump support.
> >> + *
> >> + * Return: 0 if all entries fit in @skb, number of bytes added to @skb if
> >> + *          the buffer filled up (requires multi-part continuation), or
> >> + *          a negative error code on failure.
> >> + */
> >> +int drm_ras_nl_get_retired_resources_info_dumpit(struct sk_buff *skb,
> >> +						 struct netlink_callback *cb)
> >> +{
> >> +	const struct genl_info *info = genl_info_dump(cb);
> >> +	struct drm_ras_ctx *ctx = (void *)cb->ctx;
> >> +	struct drm_ras_retired_info rinfo;
> >> +	struct drm_ras_node *node;
> >> +	struct nlattr *hdr;
> >> +	u32 node_id, index;
> >> +	int ret = 0;
> >> +
> >> +	if (!info->attrs ||
> >> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID))
> >> +		return -EINVAL;
> >> +
> >> +	node_id = nla_get_u32(info->attrs[DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID]);
> >> +
> >> +	node = xa_load(&drm_ras_xa, node_id);
> >> +	if (!node || node->type != DRM_RAS_NODE_TYPE_RETIRED_RESOURCES ||
> >> +	    !node->query_retired_info)
> >> +		return -ENOENT;
> >> +
> >> +	for (index = ctx->restart; ; index++) {
> >> +		memset(&rinfo, 0, sizeof(rinfo));
> >> +		ret = node->query_retired_info(node, index, &rinfo);
> >> +		/* -ENOENT marks the end of the type list. */
> >> +		if (ret == -ENOENT) {
> >> +			ret = 0;
> >> +			break;
> >> +		}
> >> +		if (ret)
> >> +			return ret;
> >> +
> >> +		hdr = genlmsg_iput(skb, info);
> >> +		if (!hdr) {
> >> +			ret = -EMSGSIZE;
> >> +			break;
> >> +		}
> >> +
> >> +		if (nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID,
> >> +				node_id) ||
> >> +		    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_TYPE,
> >> +				rinfo.type) ||
> >> +		    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_MAX_COUNT,
> >> +				rinfo.max_count) ||
> >> +		    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_OFFLINED_COUNT,
> >> +				rinfo.offlined_count) ||
> >> +		    nla_put_u32(skb, DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_QUEUED_COUNT,
> >> +				rinfo.queued_count)) {
> >> +			genlmsg_cancel(skb, hdr);
> >> +			ret = -EMSGSIZE;
> >> +			break;
> >> +		}
> >> +
> >> +		genlmsg_end(skb, hdr);
> >> +	}
> >> +
> >> +	if (ret == -EMSGSIZE)
> >> +		ctx->restart = index;
> >> +
> >> +	return ret;
> >> +}
> >> +
> >>  /**
> >>   * drm_ras_node_register() - Register a new RAS node
> >>   * @node: Node structure to register
> >> @@ -470,15 +672,24 @@ int drm_ras_node_register(struct drm_ras_node *node)
> >>  	if (!node->device_name || !node->node_name)
> >>  		return -EINVAL;
> >>  
> >> -	/* Currently, only Error Counter Endpoints are supported */
> >> -	if (node->type != DRM_RAS_NODE_TYPE_ERROR_COUNTER)
> >> -		return -EINVAL;
> >> -
> >>  	/* Mandatory entries for Error Counter Node */
> >>  	if (node->type == DRM_RAS_NODE_TYPE_ERROR_COUNTER &&
> >>  	    (!node->error_counter_range.last || !node->query_error_counter))
> >>  		return -EINVAL;
> >>  
> >> +	/* Mandatory entries for Retired Resources Node */
> >> +	if (node->type == DRM_RAS_NODE_TYPE_RETIRED_RESOURCES &&
> >> +	    !node->query_retired_resource)
> >> +		return -EINVAL;
> >> +
> >> +	switch (node->type) {
> >> +	case DRM_RAS_NODE_TYPE_ERROR_COUNTER:
> >> +	case DRM_RAS_NODE_TYPE_RETIRED_RESOURCES:
> >> +		break;
> >> +	default:
> >> +		return -EINVAL;
> >> +	}
> >> +
> >>  	return xa_alloc(&drm_ras_xa, &node->id, node, xa_limit_32b, GFP_KERNEL);
> >>  }
> >>  EXPORT_SYMBOL(drm_ras_node_register);
> >> diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
> >> index 9d3123cc9f9c..b194d065ec48 100644
> >> --- a/drivers/gpu/drm/drm_ras_nl.c
> >> +++ b/drivers/gpu/drm/drm_ras_nl.c
> >> @@ -28,6 +28,16 @@ static const struct nla_policy drm_ras_clear_error_counter_nl_policy[DRM_RAS_A_E
> >>  	[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, },
> >>  };
> >>  
> >> +/* DRM_RAS_CMD_GET_RETIRED_RESOURCES - dump */
> >> +static const struct nla_policy drm_ras_get_retired_resources_nl_policy[DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID + 1] = {
> >> +	[DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID] = { .type = NLA_U32, },
> >> +};
> >> +
> >> +/* DRM_RAS_CMD_GET_RETIRED_RESOURCES_INFO - dump */
> >> +static const struct nla_policy drm_ras_get_retired_resources_info_nl_policy[DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID + 1] = {
> >> +	[DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID] = { .type = NLA_U32, },
> >> +};
> >> +
> >>  /* Ops table for drm_ras */
> >>  static const struct genl_split_ops drm_ras_nl_ops[] = {
> >>  	{
> >> @@ -56,6 +66,20 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
> >>  		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
> >>  		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
> >>  	},
> >> +	{
> >> +		.cmd		= DRM_RAS_CMD_GET_RETIRED_RESOURCES,
> >> +		.dumpit		= drm_ras_nl_get_retired_resources_dumpit,
> >> +		.policy		= drm_ras_get_retired_resources_nl_policy,
> >> +		.maxattr	= DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID,
> >> +		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
> >> +	},
> >> +	{
> >> +		.cmd		= DRM_RAS_CMD_GET_RETIRED_RESOURCES_INFO,
> >> +		.dumpit		= drm_ras_nl_get_retired_resources_info_dumpit,
> >> +		.policy		= drm_ras_get_retired_resources_info_nl_policy,
> >> +		.maxattr	= DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID,
> >> +		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
> >> +	},
> >>  };
> >>  
> >>  static const struct genl_multicast_group drm_ras_nl_mcgrps[] = {
> >> diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
> >> index 03ec275aca92..c46f2b4a6e8a 100644
> >> --- a/drivers/gpu/drm/drm_ras_nl.h
> >> +++ b/drivers/gpu/drm/drm_ras_nl.h
> >> @@ -20,6 +20,10 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
> >>  					struct netlink_callback *cb);
> >>  int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
> >>  					struct genl_info *info);
> >> +int drm_ras_nl_get_retired_resources_dumpit(struct sk_buff *skb,
> >> +					    struct netlink_callback *cb);
> >> +int drm_ras_nl_get_retired_resources_info_dumpit(struct sk_buff *skb,
> >> +						 struct netlink_callback *cb);
> >>  
> >>  enum {
> >>  	DRM_RAS_NLGRP_ERROR_REPORT,
> >> diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
> >> index 78184b6ea7d4..11ddd12a42e2 100644
> >> --- a/drivers/gpu/drm/xe/xe_drm_ras.c
> >> +++ b/drivers/gpu/drm/xe/xe_drm_ras.c
> >> @@ -12,6 +12,7 @@
> >>  #include "xe_device_types.h"
> >>  #include "xe_drm_ras.h"
> >>  #include "xe_ras.h"
> >> +#include "xe_ttm_vram_mgr.h"
> >>  
> >>  static const char * const error_components[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES;
> >>  static const char * const error_severity[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES;
> >> @@ -154,6 +155,79 @@ static void cleanup_node(struct drm_device *drm, void *node)
> >>  	cleanup_node_param(node);
> >>  }
> >>  
> >> +static int query_retired_resource(struct drm_ras_node *node, u64 cursor,
> >> +				  struct drm_ras_retired_resource *res)
> >> +{
> >> +	struct xe_device *xe = node->priv;
> >> +	int ret;
> >> +
> >> +	ret = xe_ttm_vram_get_retired_page(xe, cursor, &res->vram_page.address,
> >> +					   &res->vram_page.size, &res->status);
> >> +	if (ret)
> >> +		return ret;
> >> +
> >> +	res->type = DRM_RAS_RETIRED_RESOURCE_TYPE_VRAM_PAGE;
> >> +	res->key = res->vram_page.address;
> >> +
> >> +	return 0;
> >> +}
> >> +
> >> +static int query_retired_info(struct drm_ras_node *node, u32 index,
> >> +			      struct drm_ras_retired_info *info)
> >> +{
> >> +	struct xe_device *xe = node->priv;
> >> +
> >> +	/* This node currently tracks a single resource type: VRAM pages. */
> >> +	if (index > 0)
> >> +		return -ENOENT;
> >> +
> >> +	info->type = DRM_RAS_RETIRED_RESOURCE_TYPE_VRAM_PAGE;
> >> +	xe_ttm_vram_get_retired_info(xe, &info->max_count, &info->offlined_count,
> >> +				     &info->queued_count);
> >> +
> >> +	return 0;
> >> +}
> >> +
> >> +static int register_retired_node(struct xe_device *xe)
> >> +{
> >> +	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> >> +	struct xe_drm_ras *ras = &xe->ras;
> >> +	struct drm_ras_node *node;
> >> +	const char *device_name;
> >> +	int ret;
> >> +
> >> +	/* Retired VRAM pages are only tracked on platforms with page offline */
> >> +	if (xe->info.platform != XE_CRESCENTISLAND)
> >> +		return 0;
> >> +
> >> +	node = drmm_kzalloc(&xe->drm, sizeof(*node), GFP_KERNEL);
> >> +	if (!node)
> >> +		return -ENOMEM;
> >> +
> >> +	device_name = kasprintf(GFP_KERNEL, "%04x:%02x:%02x.%d",
> >> +				pci_domain_nr(pdev->bus), pdev->bus->number,
> >> +				PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
> >> +	if (!device_name)
> >> +		return -ENOMEM;
> >> +
> >> +	node->device_name = device_name;
> >> +	node->node_name = "vram-retired-pages";
> >> +	node->type = DRM_RAS_NODE_TYPE_RETIRED_RESOURCES;
> >> +	node->query_retired_resource = query_retired_resource;
> >> +	node->query_retired_info = query_retired_info;
> >> +	node->priv = xe;
> >> +
> >> +	ret = drm_ras_node_register(node);
> >> +	if (ret) {
> >> +		cleanup_node_param(node);
> >> +		return ret;
> >> +	}
> >> +
> >> +	ras->retired_node = node;
> >> +
> >> +	return drmm_add_action_or_reset(&xe->drm, cleanup_node, node);
> >> +}
> >> +
> >>  static int register_nodes(struct xe_device *xe)
> >>  {
> >>  	struct xe_drm_ras *ras = &xe->ras;
> >> @@ -245,5 +319,12 @@ int xe_drm_ras_init(struct xe_device *xe)
> >>  		return err;
> >>  	}
> >>  
> >> +	err = register_retired_node(xe);
> >> +	if (err) {
> >> +		drm_err(&xe->drm, "Failed to register DRM RAS retired node (%pe)\n",
> >> +			ERR_PTR(err));
> >> +		return err;
> >> +	}
> >> +
> >>  	return 0;
> >>  }
> >> diff --git a/drivers/gpu/drm/xe/xe_drm_ras_types.h b/drivers/gpu/drm/xe/xe_drm_ras_types.h
> >> index 83899cf04793..e1bdb7edd0e1 100644
> >> --- a/drivers/gpu/drm/xe/xe_drm_ras_types.h
> >> +++ b/drivers/gpu/drm/xe/xe_drm_ras_types.h
> >> @@ -41,6 +41,9 @@ struct xe_drm_ras {
> >>  	/** @node: DRM RAS node */
> >>  	struct drm_ras_node *node;
> >>  
> >> +	/** @retired_node: DRM RAS retired-resources node for VRAM bad pages */
> >> +	struct drm_ras_node *retired_node;
> >> +
> >>  	/** @info: info array for all types of errors */
> >>  	struct xe_drm_ras_counter *info[DRM_XE_RAS_ERR_SEV_MAX];
> >>  
> >> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> >> index c54ad017725f..bc2fa43009f4 100644
> >> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> >> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> >> @@ -15,6 +15,8 @@
> >>  #include <drm/ttm/ttm_placement.h>
> >>  #include <drm/ttm/ttm_range_manager.h>
> >>  
> >> +#include <uapi/drm/drm_ras.h>
> >> +
> >>  #include "regs/xe_regs.h"
> >>  #include "xe_bo.h"
> >>  #include "xe_configfs.h"
> >> @@ -581,6 +583,138 @@ u64 xe_ttm_vram_get_avail(struct ttm_resource_manager *man)
> >>  	return avail;
> >>  }
> >>  
> >> +/**
> >> + * xe_ttm_vram_get_retired_page - Fetch the next retired VRAM page by address
> >> + * @xe: xe device instance
> >> + * @min_addr: inclusive lower bound; return the page with the smallest DPA >=
> >> + *            this value
> >> + * @addr: output, device physical address (DPA) of the page
> >> + * @size: output, size of the page in bytes
> >> + * @status: output, retirement status (enum drm_ras_retired_resource_status)
> >> + *
> >> + * Scans the offlined and queued page lists across all tiles and returns the
> >> + * entry with the smallest DPA that is >= @min_addr. Because retired pages have
> >> + * unique addresses, iterating with @min_addr = previous_addr + 1 walks every
> >> + * entry in a stable address order, which is robust against concurrent
> >> + * insertion or removal between calls. Intended to back the drm-ras
> >> + * retired-resources node enumeration.
> >> + *
> >> + * Return: 0 on success, -ENOENT when no page has a DPA >= @min_addr.
> >> + */
> >> +int xe_ttm_vram_get_retired_page(struct xe_device *xe, u64 min_addr,
> >> +				 u64 *addr, u64 *size, u32 *status)
> >> +{
> >> +	struct xe_ttm_vram_offline_resource *pos;
> >> +	struct ttm_resource_manager *man;
> >> +	struct gpu_buddy_block *block;
> >> +	struct xe_ttm_vram_mgr *mgr;
> >> +	u64 best_addr = 0, best_size = 0;
> >> +	struct xe_tile *tile;
> >> +	u32 best_status = 0;
> >> +	bool found = false;
> >> +	u8 id;
> >> +
> >> +	for_each_tile(tile, xe, id) {
> >> +		struct xe_vram_region *vr = tile->mem.vram;
> >> +		u64 a, s;
> >> +
> >> +		man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0 + id);
> >> +		if (!man || !vr)
> >> +			continue;
> >> +		mgr = to_xe_ttm_vram_mgr(man);
> >> +
> >> +		rcu_read_lock();
> >> +
> >> +		list_for_each_entry_rcu(pos, &mgr->offlined_pages, offlined_link) {
> >> +			block = list_first_entry_or_null(&pos->blocks,
> >> +							 struct gpu_buddy_block, link);
> >> +			if (block) {
> >> +				a = gpu_buddy_block_offset(block) + vr->dpa_base;
> >> +				s = gpu_buddy_block_size(&mgr->mm, block);
> >> +			} else {
> >> +				a = pos->addr + vr->dpa_base;
> >> +				s = SZ_4K;
> >> +			}
> >> +
> >> +			if (a >= min_addr && (!found || a < best_addr)) {
> >> +				best_addr = a;
> >> +				best_size = s;
> >> +				best_status = DRM_RAS_RETIRED_RESOURCE_STATUS_RETIRED;
> >> +				found = true;
> >> +			}
> >> +		}
> >> +
> >> +		list_for_each_entry_rcu(pos, &mgr->queued_pages, queued_link) {
> >> +			block = list_first_entry_or_null(&pos->blocks,
> >> +							 struct gpu_buddy_block, link);
> >> +			if (block) {
> >> +				a = gpu_buddy_block_offset(block) + vr->dpa_base;
> >> +				s = gpu_buddy_block_size(&mgr->mm, block);
> >> +			} else {
> >> +				a = pos->addr + vr->dpa_base;
> >> +				s = SZ_4K;
> >> +			}
> >> +
> >> +			if (a >= min_addr && (!found || a < best_addr)) {
> >> +				best_addr = a;
> >> +				best_size = s;
> >> +				best_status = pos->status == XE_PAGE_RESERVE_FAIL ?
> >> +					      DRM_RAS_RETIRED_RESOURCE_STATUS_FAILED :
> >> +					      DRM_RAS_RETIRED_RESOURCE_STATUS_PENDING;
> >> +				found = true;
> >> +			}
> >> +		}
> >> +
> >> +		rcu_read_unlock();
> >> +	}
> >> +
> >> +	if (!found)
> >> +		return -ENOENT;
> >> +
> >> +	*addr = best_addr;
> >> +	*size = best_size;
> >> +	*status = best_status;
> >> +
> >> +	return 0;
> >> +}
> >> +
> >> +/**
> >> + * xe_ttm_vram_get_retired_info - Fetch device-wide retired page limits/counts
> >> + * @xe: xe device instance
> >> + * @max: output, maximum pages that can be offlined (summed across tiles)
> >> + * @offlined: output, pages currently retired (summed across tiles)
> >> + * @queued: output, pages queued for retirement (summed across tiles)
> >> + *
> >> + * Aggregates the per-tile VRAM offline limits and occupancy. Intended to back
> >> + * the drm-ras retired-resources info query.
> >> + */
> >> +void xe_ttm_vram_get_retired_info(struct xe_device *xe, u32 *max,
> >> +				  u32 *offlined, u32 *queued)
> >> +{
> >> +	struct ttm_resource_manager *man;
> >> +	struct xe_ttm_vram_mgr *mgr;
> >> +	struct xe_tile *tile;
> >> +	u32 m = 0, o = 0, q = 0;
> >> +	u8 id;
> >> +
> >> +	for_each_tile(tile, xe, id) {
> >> +		man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0 + id);
> >> +		if (!man || !tile->mem.vram)
> >> +			continue;
> >> +		mgr = to_xe_ttm_vram_mgr(man);
> >> +
> >> +		scoped_guard(mutex, &mgr->lock) {
> >> +			m += mgr->max_pages;
> > This is awkward. You document the max_count as the maximum that can be retired,
> > but you are actually counting how many are retired at a given point.
> yes the max count should be coming from FW query and its static, i will
> fix it thanks for catching
> >
> >> +			o += mgr->n_offlined_pages;
> >> +			q += mgr->n_queued_pages;
> >
> > You should probably have a single function that gets all the entries and
> > the count. Otherwise you might have inconsistencies in the information.
> >
> > info command followed by dump can show different discrepant information...
> >
> > perhaps we could even delete the info command entirely and only use the dump?
> 
> makes sense I believe we can even drop the offlined and queued counts as
> anyways that info can be retrieved from the earlier ops and can be
> derived by userspace consumer.
> 
> So will just have the max_page count as the leading information to per
> page entries.
> 
> >
> >> +		}
> >> +	}
> >> +
> >> +	*max = m;
> >> +	*offlined = o;
> >> +	*queued = q;
> >> +}
> >> +
> >>  static int xe_ttm_vram_purge_page(struct xe_device *xe, struct xe_bo *bo)
> >>  {
> >>  	u32	q_flag = DRM_XE_EXEC_QUEUE_BAN_REASON_PAGE_OFFLINE;
> >> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> >> index 8878e36292b2..9f849ee40e5b 100644
> >> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> >> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> >> @@ -35,6 +35,11 @@ void xe_ttm_vram_get_used(struct ttm_resource_manager *man,
> >>  int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr);
> >>  int xe_ttm_vram_inject_fault(struct xe_device *xe);
> >>  void xe_ttm_vram_debugfs_init(struct xe_device *xe, struct dentry *root);
> >> +int xe_ttm_vram_get_retired_page(struct xe_device *xe, u64 min_addr,
> >> +				 u64 *addr, u64 *size, u32 *status);
> >> +void xe_ttm_vram_get_retired_info(struct xe_device *xe, u32 *max,
> >> +				  u32 *offlined, u32 *queued);
> >> +
> >>  static inline struct xe_ttm_vram_mgr_resource *
> >>  to_xe_ttm_vram_mgr_resource(struct ttm_resource *res)
> >>  {
> >> diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
> >> index ee2caa0edc6f..024f6a08c079 100644
> >> --- a/include/drm/drm_ras.h
> >> +++ b/include/drm/drm_ras.h
> >> @@ -10,6 +10,54 @@
> >>  
> >>  #include <uapi/drm/drm_ras.h>
> >>  
> >> +/**
> >> + * struct drm_ras_retired_resource - A single retired resource entry
> >> + *
> >> + * Describes one hardware resource that has been taken out of service and is
> >> + * reported by a %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES node. @type selects which
> >> + * member of the anonymous union is valid, allowing new hardware resource types
> >> + * to be added without changing the common fields.
> >> + */
> >> +struct drm_ras_retired_resource {
> >> +	/** @type: Resource type (enum drm_ras_retired_resource_type). */
> >> +	__u32 type;
> >> +	/** @status: Retirement status (enum drm_ras_retired_resource_status). */
> >> +	__u32 status;
> >> +	/**
> >> +	 * @key: Opaque, driver-assigned ordering key for this entry. drm-ras
> >> +	 * uses it only to advance the dump cursor; entries must be enumerable
> >> +	 * in strictly increasing @key order and keys must be unique.
> >> +	 */
> >> +	__u64 key;
> >> +	union {
> >> +		/** @vram_page: Valid when @type is VRAM_PAGE. */
> >> +		struct {
> >> +			/** @vram_page.address: Device address (e.g. DPA). */
> >> +			__u64 address;
> >> +			/** @vram_page.size: Size in bytes. */
> >> +			__u64 size;
> >> +		} vram_page;
> >> +	};
> >> +};
> >> +
> >> +/**
> >> + * struct drm_ras_retired_info - Per-type retired resource limits and counts
> >> + *
> >> + * Reported by a %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES node to describe the
> >> + * capacity and current occupancy of one resource type. A node that tracks
> >> + * several resource types reports one entry per type.
> >> + */
> >> +struct drm_ras_retired_info {
> >> +	/** @type: Resource type (enum drm_ras_retired_resource_type). */
> >> +	__u32 type;
> >> +	/** @max_count: Maximum resources of @type that can be retired. */
> >> +	__u32 max_count;
> >> +	/** @offlined_count: Resources of @type currently retired. */
> >> +	__u32 offlined_count;
> >> +	/** @queued_count: Resources of @type queued (pending or failed). */
> >> +	__u32 queued_count;
> >> +};
> >> +
> >>  /**
> >>   * struct drm_ras_node - A DRM RAS Node
> >>   */
> >> @@ -71,6 +119,45 @@ struct drm_ras_node {
> >>  	 */
> >>  	int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id);
> >>  
> >> +	/**
> >> +	 * @query_retired_resource:
> >> +	 *
> >> +	 * This callback is used by drm-ras to enumerate retired resources of a
> >> +	 * %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES node. It is called with @cursor
> >> +	 * and must return the next entry whose ordering key is greater than or
> >> +	 * equal to @cursor, setting @res->key to that entry's key. drm-ras
> >> +	 * resumes multi-part dumps from the returned key, so enumeration stays
> >> +	 * correct across concurrent insertion or removal.
> >> +	 *
> >> +	 * The @query_retired_resource is a mandatory callback for
> >> +	 * retired-resources nodes.
> >> +	 *
> >> +	 * Returns: 0 on success,
> >> +	 *          -ENOENT when no entry has a key >= @cursor, used as an
> >> +	 *                  indication that enumeration is complete.
> >> +	 *          Other negative values on errors that should terminate the
> >> +	 *          netlink query.
> >> +	 */
> >> +	int (*query_retired_resource)(struct drm_ras_node *node, u64 cursor,
> >> +				      struct drm_ras_retired_resource *res);
> >> +
> >> +	/**
> >> +	 * @query_retired_info:
> >> +	 *
> >> +	 * This optional callback is used by drm-ras to report per-type limits
> >> +	 * and current occupancy for a %DRM_RAS_NODE_TYPE_RETIRED_RESOURCES node.
> >> +	 * It is called with @index starting at 0 and incrementing until the
> >> +	 * driver returns -ENOENT, allowing one entry per resource type.
> >> +	 *
> >> +	 * Returns: 0 on success,
> >> +	 *          -ENOENT when @index is past the last type, used as an
> >> +	 *                  indication that enumeration is complete.
> >> +	 *          Other negative values on errors that should terminate the
> >> +	 *          netlink query.
> >> +	 */
> >> +	int (*query_retired_info)(struct drm_ras_node *node, u32 index,
> >> +				  struct drm_ras_retired_info *info);
> >> +
> >>  	/** @priv: Driver private data */
> >>  	void *priv;
> >>  };
> >> diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
> >> index eab8231aa87c..de6f6dd3ffa9 100644
> >> --- a/include/uapi/drm/drm_ras.h
> >> +++ b/include/uapi/drm/drm_ras.h
> > you are auto-generating these with the ynl commands right? please make sure
> > to mention that in the commit message just to be sure.
> 
> sure will do it.
> 
> Thanks,
> Aravind.
> >
> > Thanks,
> > Rodrigo.
> >
> >> @@ -11,11 +11,38 @@
> >>  #define DRM_RAS_FAMILY_VERSION	1
> >>  
> >>  /*
> >> - * Type of the node. Currently, only error-counter nodes are supported, which
> >> - * expose reliability counters for a hardware/software component.
> >> + * Type of the node.
> >> + *  - error-counter nodes expose reliability counters for a
> >> + *    hardware/software component.
> >> + *  - retired-resources nodes enumerate hardware resources (e.g. VRAM pages)
> >> + *    that have been permanently taken out of service.
> >>   */
> >>  enum drm_ras_node_type {
> >>  	DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1,
> >> +	DRM_RAS_NODE_TYPE_RETIRED_RESOURCES,
> >> +};
> >> +
> >> +/*
> >> + * Status of a retired resource entry reported by a retired-resources node.
> >> + *  - retired: resource is permanently reserved and out of service.
> >> + *  - pending: retirement is queued but reservation is not yet complete.
> >> + *  - failed:  reservation of the resource failed and it may still be in use.
> >> + */
> >> +enum drm_ras_retired_resource_status {
> >> +	DRM_RAS_RETIRED_RESOURCE_STATUS_RETIRED = 0,
> >> +	DRM_RAS_RETIRED_RESOURCE_STATUS_PENDING,
> >> +	DRM_RAS_RETIRED_RESOURCE_STATUS_FAILED,
> >> +};
> >> +
> >> +/*
> >> + * Type of a retired resource entry. The type selects which type-specific
> >> + * nested attribute is present in a retired-resource entry. New hardware
> >> + * resource types can be added here, each carrying its own nested attribute
> >> + * set, without affecting existing types.
> >> + *  - vram-page: a VRAM page identified by device address and size.
> >> + */
> >> +enum drm_ras_retired_resource_type {
> >> +	DRM_RAS_RETIRED_RESOURCE_TYPE_VRAM_PAGE = 1,
> >>  };
> >>  
> >>  enum {
> >> @@ -50,11 +77,43 @@ enum {
> >>  	DRM_RAS_A_ERROR_EVENT_ATTRS_MAX = (__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX - 1)
> >>  };
> >>  
> >> +enum {
> >> +	DRM_RAS_A_RETIRED_RESOURCE_ATTRS_NODE_ID = 1,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_ATTRS_TYPE,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_ATTRS_STATUS,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_ATTRS_VRAM_PAGE,
> >> +
> >> +	__DRM_RAS_A_RETIRED_RESOURCE_ATTRS_MAX,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_ATTRS_MAX = (__DRM_RAS_A_RETIRED_RESOURCE_ATTRS_MAX - 1)
> >> +};
> >> +
> >> +enum {
> >> +	DRM_RAS_A_VRAM_PAGE_ATTRS_ADDRESS = 1,
> >> +	DRM_RAS_A_VRAM_PAGE_ATTRS_SIZE,
> >> +	DRM_RAS_A_VRAM_PAGE_ATTRS_PAD,
> >> +
> >> +	__DRM_RAS_A_VRAM_PAGE_ATTRS_MAX,
> >> +	DRM_RAS_A_VRAM_PAGE_ATTRS_MAX = (__DRM_RAS_A_VRAM_PAGE_ATTRS_MAX - 1)
> >> +};
> >> +
> >> +enum {
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_NODE_ID = 1,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_TYPE,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_MAX_COUNT,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_OFFLINED_COUNT,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_QUEUED_COUNT,
> >> +
> >> +	__DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_MAX,
> >> +	DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_MAX = (__DRM_RAS_A_RETIRED_RESOURCE_INFO_ATTRS_MAX - 1)
> >> +};
> >> +
> >>  enum {
> >>  	DRM_RAS_CMD_LIST_NODES = 1,
> >>  	DRM_RAS_CMD_GET_ERROR_COUNTER,
> >>  	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
> >>  	DRM_RAS_CMD_ERROR_EVENT,
> >> +	DRM_RAS_CMD_GET_RETIRED_RESOURCES,
> >> +	DRM_RAS_CMD_GET_RETIRED_RESOURCES_INFO,
> >>  
> >>  	__DRM_RAS_CMD_MAX,
> >>  	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
> >> -- 
> >> 2.25.1
> >>