From: Anisa Su <anisa.su887@gmail.com>
To: linux-cxl@vger.kernel.org
Cc: nvdimm@lists.linux.dev, linux-kernel@vger.kernel.org,
Dan Williams <djbw@kernel.org>, Dave Jiang <dave.jiang@intel.com>,
Alison Schofield <alison.schofield@intel.com>,
Jonathan Cameron <jic23@kernel.org>,
Davidlohr Bueso <dave@stgolabs.net>,
Ira Weiny <iweiny@kernel.org>,
Vishal Verma <vishal.l.verma@intel.com>,
Fan Ni <nifan.cxl@gmail.com>, Li Ming <ming.li@zohomail.com>,
Benjamin Cheatham <benjamin.cheatham@amd.com>,
Gregory Price <gourry@gourry.net>,
Richard Cheng <icheng@nvidia.com>,
Anisa Su <anisa.su@samsung.com>
Subject: [PATCH v15 3/8] cxl/cdat: Gather DSMAS data for DCD partitions
Date: Wed, 7 Oct 2026 13:16:36 -0700 [thread overview]
Message-ID: <20261007201828.952-4-anisa.su@samsung.com> (raw)
In-Reply-To: <20261007201828.952-1-anisa.su@samsung.com>
From: Ira Weiny <iweiny@kernel.org>
Additional DCD partition (AKA region) information is contained in the
DSMAS CDAT tables, including performance, shareable and read-only
attributes.
Match DCD partitions with DSMAS tables and store the meta data. A DCD
shall describe its DC partition in a DSMAS entry (CXL r4.0 9.13.3), so
if the CDAT is absent, fails to parse, or has no entry matching the DC
partition, disable DCD rather than run with unknown attributes.
DSLBIS is optional, but cxl_cdat_endpoint_process() treated zero DSLBIS
entries as a parse failure, which would now disable DCD on a device with
a valid DSMAS. Accept an empty DSLBIS, and skip DSMAS entries with no
DSLBIS coordinates.
Signed-off-by: Ira Weiny <iweiny@kernel.org>
Co-developed-by: Anisa Su <anisa.su@samsung.com>
Signed-off-by: Anisa Su <anisa.su@samsung.com>
---
Changes:
1. cdat.c: disable DCD when the DC partition has no valid DSMAS entry:
no CDAT, CDAT parse failure, or no entry matching the partition.
[Richard, Dave]
2. cdat.c: DSLBIS is optional. An empty DSLBIS no longer fails the
CDAT parse, and cxl_port_perf_data_calculate() skips entries that
have no DSLBIS coordinates.
[Richard, Dave]
3. cdat.c: cxl_memdev_apply_dsmas() takes an enum cxl_dsmas_apply
instead of a bool so the call sites say what is applied.
[Dave]
4. Also record the DSMAS read-only flag (CDAT 1.04, Flags bit 6) on
the partition, alongside shareable.
[Jonathan]
---
drivers/cxl/core/cdat.c | 97 ++++++++++++++++++++++++++++++++++-----
drivers/cxl/core/hdm.c | 1 +
drivers/cxl/core/mbox.c | 9 ++++
drivers/cxl/core/memdev.c | 17 ++++---
drivers/cxl/cxlmem.h | 2 +
include/cxl/cxl.h | 6 +++
6 files changed, 113 insertions(+), 19 deletions(-)
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 5c9f07262513..07aedff657d9 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -17,6 +17,8 @@ struct dsmas_entry {
struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX];
int entries;
int qos_class;
+ bool shareable;
+ bool read_only;
};
static u32 cdat_normalize(u16 entry, u64 base, u8 type)
@@ -74,6 +76,10 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
return -ENOMEM;
dent->handle = dsmas->dsmad_handle;
+ /* Shareable is CDAT 1.03 and later, DSMAS Flags bit 3 */
+ dent->shareable = dsmas->flags & ACPI_CDAT_DSMAS_SHAREABLE;
+ /* Read Only is CDAT 1.04 and later, DSMAS Flags bit 6 */
+ dent->read_only = dsmas->flags & ACPI_CDAT_DSMAS_READ_ONLY;
dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address);
dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) +
le64_to_cpu((__force __le64)dsmas->dpa_length) - 1;
@@ -188,9 +194,10 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
if (rc)
return rc;
+ /* DSLBIS is optional; zero entries is not an error */
rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
dsmas_xa, port->cdat.table, port->cdat.length);
- return cdat_table_parse_output(rc);
+ return rc < 0 ? rc : 0;
}
static int cxl_port_perf_data_calculate(struct cxl_port *port,
@@ -219,6 +226,13 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
xa_for_each(dsmas_xa, index, dent) {
int qos_class;
+ /* No DSLBIS for this DSMAS; nothing to hand the QTG _DSM */
+ if (!dent->cdat_coord[ACCESS_COORDINATE_CPU].read_bandwidth &&
+ !dent->cdat_coord[ACCESS_COORDINATE_CPU].write_bandwidth &&
+ !dent->cdat_coord[ACCESS_COORDINATE_CPU].read_latency &&
+ !dent->cdat_coord[ACCESS_COORDINATE_CPU].write_latency)
+ continue;
+
cxl_coordinates_combine(dent->coord, dent->cdat_coord, ep_c);
dent->entries = 1;
rc = cxl_root->ops.qos_class(cxl_root,
@@ -255,35 +269,90 @@ static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
dent->coord[ACCESS_COORDINATE_CPU].write_latency);
}
-static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
- struct xarray *dsmas_xa)
+/*
+ * A DCD shall describe its DC partition in a DSMAS entry (CXL r4.0 9.13.3).
+ * Without one the partition's attributes are unknown, so disable DCD.
+ */
+static void cxl_dcd_dsmas_missing(struct cxl_dev_state *cxlds, const char *why)
+{
+ struct cxl_memdev_state *mds;
+
+ if (cxlds->type != CXL_DEVTYPE_CLASSMEM)
+ return;
+
+ mds = to_cxl_memdev_state(cxlds);
+ if (!cxl_dcd_supported(mds) ||
+ !cxl_part_size(cxlds, CXL_PARTMODE_DYNAMIC_RAM))
+ return;
+
+ dev_warn(cxlds->dev, "DC partition has no valid DSMAS entry (%s), disabling DCD\n",
+ why);
+ cxl_disable_dcd(mds);
+}
+
+enum cxl_dsmas_apply {
+ CXL_DSMAS_APPLY_FLAGS, /* shareable etc.; no QTG data */
+ CXL_DSMAS_APPLY_FLAGS_PERF, /* perf coordinates and qos_class */
+};
+
+/*
+ * DSMAS flags such as shareable are properties of the CDAT entry and are
+ * applied regardless; perf data is applied only if the QTG lookup produced
+ * recommendations.
+ */
+static void cxl_memdev_apply_dsmas(struct cxl_dev_state *cxlds,
+ struct xarray *dsmas_xa,
+ enum cxl_dsmas_apply attrs)
{
struct device *dev = cxlds->dev;
struct dsmas_entry *dent;
+ bool dc_matched = false;
unsigned long index;
xa_for_each(dsmas_xa, index, dent) {
bool found = false;
for (int i = 0; i < cxlds->nr_partitions; i++) {
- struct resource *res = &cxlds->part[i].res;
+ struct cxl_dpa_partition *part = &cxlds->part[i];
struct range range = {
- .start = res->start,
- .end = res->end,
+ .start = part->res.start,
+ .end = part->res.end,
};
- if (range_contains(&range, &dent->dpa_range)) {
- update_perf_entry(dev, dent,
- &cxlds->part[i].perf);
- found = true;
+ if (!range_contains(&range, &dent->dpa_range))
+ continue;
+
+ found = true;
+ /*
+ * part->handle is from Get DC Config, dent->handle
+ * from the CDAT DSMAS entry.
+ */
+ if (part->mode == CXL_PARTMODE_DYNAMIC_RAM &&
+ dent->handle != part->handle) {
+ dev_warn(dev,
+ "DSMAD handle mismatch: %pra has %u, DSMAS %pra has %u\n",
+ &range, part->handle,
+ &dent->dpa_range, dent->handle);
break;
}
+
+ if (attrs == CXL_DSMAS_APPLY_FLAGS_PERF)
+ update_perf_entry(dev, dent, &part->perf);
+ if (part->mode == CXL_PARTMODE_DYNAMIC_RAM) {
+ part->shareable = dent->shareable;
+ part->read_only = dent->read_only;
+ dc_matched = true;
+ }
+ break;
}
if (!found)
dev_dbg(dev, "no partition for dsmas dpa: %pra\n",
&dent->dpa_range);
}
+
+ if (!dc_matched)
+ cxl_dcd_dsmas_missing(cxlds, "no matching entry");
}
static int match_cxlrd_qos_class(struct device *dev, void *data)
@@ -409,22 +478,26 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
int rc;
xa_init(&__dsmas_xa);
- if (!port->cdat.table)
+ if (!port->cdat.table) {
+ cxl_dcd_dsmas_missing(cxlds, "no CDAT");
return;
+ }
rc = cxl_cdat_endpoint_process(port, dsmas_xa);
if (rc < 0) {
dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc);
+ cxl_dcd_dsmas_missing(cxlds, "CDAT parse failed");
return;
}
rc = cxl_port_perf_data_calculate(port, dsmas_xa);
if (rc) {
dev_dbg(&port->dev, "Failed to do perf coord calculations.\n");
+ cxl_memdev_apply_dsmas(cxlds, dsmas_xa, CXL_DSMAS_APPLY_FLAGS);
return;
}
- cxl_memdev_set_qos_class(cxlds, dsmas_xa);
+ cxl_memdev_apply_dsmas(cxlds, dsmas_xa, CXL_DSMAS_APPLY_FLAGS_PERF);
cxl_qos_class_verify(cxlmd);
cxl_memdev_update_perf(cxlmd);
}
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 5fa2177cefcc..379540246333 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -486,6 +486,7 @@ int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info)
cxlds->part[i].perf.qos_class = CXL_QOS_CLASS_INVALID;
cxlds->part[i].mode = part->mode;
+ cxlds->part[i].handle = part->handle;
/* Require ordered + contiguous partitions */
if (i) {
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 72af23ba288e..12598d329e95 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1366,6 +1366,7 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
u64 decode_len = le64_to_cpu(dev_part->decode_length);
u64 blk_size = le64_to_cpu(dev_part->block_size);
u64 len = le64_to_cpu(dev_part->length);
+ u32 handle = le32_to_cpu(dev_part->dsmad_handle);
u64 size;
/*
@@ -1378,6 +1379,13 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
return 0;
}
+ /* The CDAT DSMAD handle this refers to is 8 bits */
+ if (handle & ~0xFF) {
+ dev_warn(dev, "DSMAD handle 0x%x exceeds the 8 bit CDAT DSMAD handle\n",
+ handle);
+ return -EINVAL;
+ }
+
/*
* Decode length is a count of 256M units, so a device reporting 2^36
* or more wraps.
@@ -1391,6 +1399,7 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
*part = (struct cxl_dc_partition_info) {
.start = le64_to_cpu(dev_part->base),
.size = size,
+ .handle = handle,
};
/*
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index def26c490dfe..7aa79a1a53e4 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -594,7 +594,8 @@ bool is_cxl_memdev(const struct device *dev)
}
EXPORT_SYMBOL_NS_GPL(is_cxl_memdev, "CXL");
-static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_partition_mode mode)
+static void add_part(struct cxl_dpa_info *info, u64 start, u64 size,
+ enum cxl_partition_mode mode, u8 handle)
{
int i = info->nr_partitions;
@@ -606,6 +607,7 @@ static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_pa
.end = start + size - 1,
};
info->part[i].mode = mode;
+ info->part[i].handle = handle;
info->nr_partitions++;
}
@@ -623,9 +625,9 @@ int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
info->size = mds->total_bytes;
if (mds->partition_align_bytes == 0) {
- add_part(info, 0, mds->volatile_only_bytes, CXL_PARTMODE_RAM);
+ add_part(info, 0, mds->volatile_only_bytes, CXL_PARTMODE_RAM, 0);
add_part(info, mds->volatile_only_bytes,
- mds->persistent_only_bytes, CXL_PARTMODE_PMEM);
+ mds->persistent_only_bytes, CXL_PARTMODE_PMEM, 0);
return 0;
}
@@ -635,9 +637,9 @@ int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
return rc;
}
- add_part(info, 0, mds->active_volatile_bytes, CXL_PARTMODE_RAM);
+ add_part(info, 0, mds->active_volatile_bytes, CXL_PARTMODE_RAM, 0);
add_part(info, mds->active_volatile_bytes, mds->active_persistent_bytes,
- CXL_PARTMODE_PMEM);
+ CXL_PARTMODE_PMEM, 0);
return 0;
}
@@ -685,7 +687,8 @@ int cxl_configure_dcd(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
info->size = total;
dev_dbg(dev, "Adding dynamic ram partition; %#llx size %#llx\n",
dc_info.start, dc_info.size);
- add_part(info, dc_info.start, dc_info.size, CXL_PARTMODE_DYNAMIC_RAM);
+ add_part(info, dc_info.start, dc_info.size, CXL_PARTMODE_DYNAMIC_RAM,
+ dc_info.handle);
return 0;
}
@@ -703,7 +706,7 @@ int cxl_set_capacity(struct cxl_dev_state *cxlds, u64 capacity)
.size = capacity,
};
- add_part(&range_info, 0, capacity, CXL_PARTMODE_RAM);
+ add_part(&range_info, 0, capacity, CXL_PARTMODE_RAM, 0);
return cxl_dpa_setup(cxlds, &range_info);
}
EXPORT_SYMBOL_NS_GPL(cxl_set_capacity, "CXL");
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 4fac65dbb808..9fd5af2e41d4 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -140,6 +140,7 @@ struct cxl_dpa_info {
struct cxl_dpa_part_info {
struct range range;
enum cxl_partition_mode mode;
+ u8 handle;
} part[CXL_NR_PARTITIONS_MAX];
int nr_partitions;
};
@@ -851,6 +852,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds);
struct cxl_dc_partition_info {
u64 start;
u64 size;
+ u8 handle;
};
int cxl_dev_dc_identify(struct cxl_mailbox *mbox,
diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
index e07360849344..728decda57fd 100644
--- a/include/cxl/cxl.h
+++ b/include/cxl/cxl.h
@@ -141,11 +141,17 @@ enum cxl_partition_mode {
* @res: shortcut to the partition in the DPA resource tree (cxlds->dpa_res)
* @perf: performance attributes of the partition from CDAT
* @mode: operation mode for the DPA capacity, e.g. ram, pmem, dynamic...
+ * @handle: DSMAS handle that represents this partition
+ * @shareable: Is the partition shareable (from its CDAT DSMAS entry)
+ * @read_only: Is the partition read-only (from its CDAT DSMAS entry)
*/
struct cxl_dpa_partition {
struct resource res;
struct cxl_dpa_perf perf;
enum cxl_partition_mode mode;
+ u8 handle;
+ bool shareable;
+ bool read_only;
};
#define CXL_NR_PARTITIONS_MAX 3
--
2.43.0
next prev parent reply other threads:[~2026-10-07 20:18 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-07 20:16 [PATCH v15 0/8] DCD Prep Series Anisa Su
2026-10-07 20:16 ` [PATCH v15 1/8] cxl/mbox: Flag support for Dynamic Capacity Devices (DCD) Anisa Su
2026-10-07 20:16 ` [PATCH v15 2/8] cxl/mem: Read dynamic capacity configuration from the device Anisa Su
2026-10-07 20:29 ` sashiko-bot
2026-10-07 21:25 ` Anisa Su
2026-10-07 23:43 ` Alison Schofield
2026-10-08 8:15 ` Anisa Su
2026-10-08 8:33 ` Richard Cheng
2026-10-07 20:16 ` Anisa Su [this message]
2026-10-07 20:33 ` [PATCH v15 3/8] cxl/cdat: Gather DSMAS data for DCD partitions sashiko-bot
2026-10-07 23:45 ` Alison Schofield
2026-10-08 21:29 ` Dave Jiang
2026-10-07 20:16 ` [PATCH v15 4/8] cxl/events: Split event msgnum configuration from irq setup Anisa Su
2026-10-07 20:16 ` [PATCH v15 5/8] cxl/pci: Factor out interrupt policy check Anisa Su
2026-10-07 20:16 ` [PATCH v15 6/8] cxl/mem: Configure dynamic capacity interrupts Anisa Su
2026-10-07 20:30 ` sashiko-bot
2026-10-07 23:46 ` Alison Schofield
2026-10-08 8:58 ` Richard Cheng
2026-10-07 20:16 ` [PATCH v15 7/8] cxl/core: Enforce partition order/simplify partition calls Anisa Su
2026-10-07 20:16 ` [PATCH v15 8/8] Documentation/cxl: Document DPA partition layout and ordering rules Anisa Su
2026-10-08 8:26 ` [PATCH v15 0/8] DCD Prep Series Anisa Su
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=20261007201828.952-4-anisa.su@samsung.com \
--to=anisa.su887@gmail.com \
--cc=alison.schofield@intel.com \
--cc=anisa.su@samsung.com \
--cc=benjamin.cheatham@amd.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=djbw@kernel.org \
--cc=gourry@gourry.net \
--cc=icheng@nvidia.com \
--cc=iweiny@kernel.org \
--cc=jic23@kernel.org \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.li@zohomail.com \
--cc=nifan.cxl@gmail.com \
--cc=nvdimm@lists.linux.dev \
--cc=vishal.l.verma@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.