From: ira.weiny@intel.com
To: Dave Jiang <dave.jiang@intel.com>, Fan Ni <fan.ni@samsung.com>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Navneet Singh <navneet.singh@intel.com>,
Jonathan Corbet <corbet@lwn.net>,
Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Alison Schofield <alison.schofield@intel.com>,
Vishal Verma <vishal.l.verma@intel.com>,
Ira Weiny <ira.weiny@intel.com>,
linux-cxl@vger.kernel.org, linux-doc@vger.kernel.org,
nvdimm@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH v5 13/27] cxl/mem: Expose DCD partition capabilities in sysfs
Date: Tue, 29 Oct 2024 15:34:48 -0500 [thread overview]
Message-ID: <20241029-dcd-type2-upstream-v5-13-8739cb67c374@intel.com> (raw)
In-Reply-To: <20241029-dcd-type2-upstream-v5-0-8739cb67c374@intel.com>
From: Navneet Singh <navneet.singh@intel.com>
To properly configure CXL regions on Dynamic Capacity Devices (DCD),
user space will need to know the details of the DC partitions available.
Expose dynamic capacity capabilities through sysfs.
Signed-off-by: Navneet Singh <navneet.singh@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Co-developed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes:
[Fan: Use proper str_false_true() call]
[Jonathan: minor cleanups]
[Bagas: Clean up documentation language]
---
Documentation/ABI/testing/sysfs-bus-cxl | 45 ++++++++++++
drivers/cxl/core/memdev.c | 124 ++++++++++++++++++++++++++++++++
2 files changed, 169 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index 3f5627a1210a16aca7c18d17131a56491048a0c2..ff3ae83477f0876c0ee2d3955d27a11fa9d16d83 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -54,6 +54,51 @@ Description:
identically named field in the Identify Memory Device Output
Payload in the CXL-2.0 specification.
+What: /sys/bus/cxl/devices/memX/dcY/size
+Date: December, 2024
+KernelVersion: v6.13
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) Dynamic Capacity (DC) region information. Devices only
+ export dcY if DCD partition Y is supported.
+ dcY/size is the size of each of those partitions.
+
+What: /sys/bus/cxl/devices/memX/dcY/read_only
+Date: December, 2024
+KernelVersion: v6.13
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) Dynamic Capacity (DC) region information. Devices only
+ export dcY if DCD partition Y is supported.
+ dcY/read_only indicates true if the region is exported
+ read_only from the device.
+
+What: /sys/bus/cxl/devices/memX/dcY/shareable
+Date: December, 2024
+KernelVersion: v6.13
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) Dynamic Capacity (DC) region information. Devices only
+ export dcY if DCD partition Y is supported.
+ dcY/shareable indicates true if the region is exported
+ shareable from the device.
+
+What: /sys/bus/cxl/devices/memX/dcY/qos_class
+Date: December, 2024
+KernelVersion: v6.13
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) Dynamic Capacity (DC) region information. Devices only
+ export dcY if DCD partition Y is supported. For CXL host
+ platforms that support "QoS Telemmetry" this attribute conveys
+ a comma delimited list of platform specific cookies that
+ identifies a QoS performance class for the persistent partition
+ of the CXL mem device. These class-ids can be compared against
+ a similar "qos_class" published for a root decoder. While it is
+ not required that the endpoints map their local memory-class to
+ a matching platform class, mismatches are not recommended as
+ there are platform specific performance related side-effects
+ that may result. First class-id is displayed.
What: /sys/bus/cxl/devices/memX/pmem/qos_class
Date: May, 2023
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 84fefb76dafabc22e6e1a12397381b3f18eea7c5..857a9dd88b20291116d20b9c0bbe9e7961f4491f 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -2,6 +2,7 @@
/* Copyright(c) 2020 Intel Corporation. */
#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/string_choices.h>
#include <linux/firmware.h>
#include <linux/device.h>
#include <linux/slab.h>
@@ -449,6 +450,121 @@ static struct attribute *cxl_memdev_security_attributes[] = {
NULL,
};
+static ssize_t show_size_dcN(struct cxl_memdev *cxlmd, char *buf, int pos)
+{
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+ return sysfs_emit(buf, "%#llx\n", mds->dc_region[pos].decode_len);
+}
+
+static ssize_t show_read_only_dcN(struct cxl_memdev *cxlmd, char *buf, int pos)
+{
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+ return sysfs_emit(buf, "%s\n",
+ str_true_false(mds->dc_region[pos].read_only));
+}
+
+static ssize_t show_shareable_dcN(struct cxl_memdev *cxlmd, char *buf, int pos)
+{
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+ return sysfs_emit(buf, "%s\n",
+ str_true_false(mds->dc_region[pos].shareable));
+}
+
+static ssize_t show_qos_class_dcN(struct cxl_memdev *cxlmd, char *buf, int pos)
+{
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+ return sysfs_emit(buf, "%d\n", mds->dc_perf[pos].qos_class);
+}
+
+#define CXL_MEMDEV_DC_ATTR_GROUP(n) \
+static ssize_t dc##n##_size_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_size_dcN(to_cxl_memdev(dev), buf, (n)); \
+} \
+struct device_attribute dc##n##_size = { \
+ .attr = { .name = "size", .mode = 0444 }, \
+ .show = dc##n##_size_show, \
+}; \
+static ssize_t dc##n##_read_only_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_read_only_dcN(to_cxl_memdev(dev), buf, (n)); \
+} \
+struct device_attribute dc##n##_read_only = { \
+ .attr = { .name = "read_only", .mode = 0444 }, \
+ .show = dc##n##_read_only_show, \
+}; \
+static ssize_t dc##n##_shareable_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_shareable_dcN(to_cxl_memdev(dev), buf, (n)); \
+} \
+struct device_attribute dc##n##_shareable = { \
+ .attr = { .name = "shareable", .mode = 0444 }, \
+ .show = dc##n##_shareable_show, \
+}; \
+static ssize_t dc##n##_qos_class_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return show_qos_class_dcN(to_cxl_memdev(dev), buf, (n)); \
+} \
+struct device_attribute dc##n##_qos_class = { \
+ .attr = { .name = "qos_class", .mode = 0444 }, \
+ .show = dc##n##_qos_class_show, \
+}; \
+static struct attribute *cxl_memdev_dc##n##_attributes[] = { \
+ &dc##n##_size.attr, \
+ &dc##n##_read_only.attr, \
+ &dc##n##_shareable.attr, \
+ &dc##n##_qos_class.attr, \
+ NULL \
+}; \
+static umode_t cxl_memdev_dc##n##_attr_visible(struct kobject *kobj, \
+ struct attribute *a, \
+ int pos) \
+{ \
+ struct device *dev = kobj_to_dev(kobj); \
+ struct cxl_memdev *cxlmd = to_cxl_memdev(dev); \
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); \
+ \
+ /* Not a memory device */ \
+ if (!mds) \
+ return 0; \
+ return a->mode; \
+} \
+static umode_t cxl_memdev_dc##n##_group_visible(struct kobject *kobj) \
+{ \
+ struct device *dev = kobj_to_dev(kobj); \
+ struct cxl_memdev *cxlmd = to_cxl_memdev(dev); \
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); \
+ \
+ /* Not a memory device or partition not supported */ \
+ return mds && n < mds->nr_dc_region; \
+} \
+DEFINE_SYSFS_GROUP_VISIBLE(cxl_memdev_dc##n); \
+static struct attribute_group cxl_memdev_dc##n##_group = { \
+ .name = "dc"#n, \
+ .attrs = cxl_memdev_dc##n##_attributes, \
+ .is_visible = SYSFS_GROUP_VISIBLE(cxl_memdev_dc##n), \
+}
+CXL_MEMDEV_DC_ATTR_GROUP(0);
+CXL_MEMDEV_DC_ATTR_GROUP(1);
+CXL_MEMDEV_DC_ATTR_GROUP(2);
+CXL_MEMDEV_DC_ATTR_GROUP(3);
+CXL_MEMDEV_DC_ATTR_GROUP(4);
+CXL_MEMDEV_DC_ATTR_GROUP(5);
+CXL_MEMDEV_DC_ATTR_GROUP(6);
+CXL_MEMDEV_DC_ATTR_GROUP(7);
+
static umode_t cxl_memdev_visible(struct kobject *kobj, struct attribute *a,
int n)
{
@@ -525,6 +641,14 @@ static struct attribute_group cxl_memdev_security_attribute_group = {
};
static const struct attribute_group *cxl_memdev_attribute_groups[] = {
+ &cxl_memdev_dc0_group,
+ &cxl_memdev_dc1_group,
+ &cxl_memdev_dc2_group,
+ &cxl_memdev_dc3_group,
+ &cxl_memdev_dc4_group,
+ &cxl_memdev_dc5_group,
+ &cxl_memdev_dc6_group,
+ &cxl_memdev_dc7_group,
&cxl_memdev_attribute_group,
&cxl_memdev_ram_attribute_group,
&cxl_memdev_pmem_attribute_group,
--
2.47.0
next prev parent reply other threads:[~2024-10-29 20:35 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-29 20:34 [PATCH v5 00/27] DCD: Add support for Dynamic Capacity Devices (DCD) Ira Weiny
2024-10-29 20:34 ` [PATCH v5 01/27] range: Add range_overlaps() Ira Weiny
2024-10-29 20:34 ` [PATCH v5 02/27] ACPI/CDAT: Add CDAT/DSMAS shared and read only flag values Ira Weiny
2024-10-29 20:34 ` [PATCH v5 03/27] dax: Document struct dev_dax_range Ira Weiny
2024-10-30 13:28 ` Jonathan Cameron
2024-10-29 20:34 ` [PATCH v5 04/27] cxl/pci: Delay event buffer allocation Ira Weiny
2024-10-29 20:34 ` [PATCH v5 05/27] cxl/hdm: Use guard() in cxl_dpa_set_mode() Ira Weiny
2024-10-30 13:29 ` Jonathan Cameron
2024-10-31 0:16 ` Davidlohr Bueso
2024-10-29 20:34 ` [PATCH v5 06/27] cxl/region: Refactor common create region code Ira Weiny
2024-10-29 20:34 ` [PATCH v5 07/27] cxl/mbox: Flag support for Dynamic Capacity Devices (DCD) ira.weiny
2024-10-29 20:34 ` [PATCH v5 08/27] cxl/mem: Read dynamic capacity configuration from the device ira.weiny
2024-10-30 14:05 ` Jonathan Cameron
2024-10-30 16:28 ` Ira Weiny
2024-10-31 0:24 ` Davidlohr Bueso
2024-10-31 14:48 ` Ira Weiny
2024-10-31 1:34 ` Davidlohr Bueso
2024-10-31 16:00 ` Fan Ni
2024-10-31 22:16 ` Ira Weiny
2024-11-04 17:09 ` Davidlohr Bueso
2024-11-05 1:53 ` Ira Weiny
2024-10-29 20:34 ` [PATCH v5 09/27] cxl/core: Separate region mode from decoder mode ira.weiny
2024-10-29 20:34 ` [PATCH v5 10/27] cxl/region: Add dynamic capacity decoder and region modes ira.weiny
2024-10-29 20:34 ` [PATCH v5 11/27] cxl/hdm: Add dynamic capacity size support to endpoint decoders ira.weiny
2024-10-29 20:34 ` [PATCH v5 12/27] cxl/cdat: Gather DSMAS data for DCD regions Ira Weiny
2024-10-30 18:32 ` Dave Jiang
2024-10-29 20:34 ` ira.weiny [this message]
2024-10-30 17:50 ` [PATCH v5 13/27] cxl/mem: Expose DCD partition capabilities in sysfs Fan Ni
2024-10-29 20:34 ` [PATCH v5 14/27] cxl/port: Add endpoint decoder DC mode support to sysfs ira.weiny
2024-10-29 20:34 ` [PATCH v5 15/27] cxl/region: Add sparse DAX region support ira.weiny
2024-10-29 20:34 ` [PATCH v5 16/27] cxl/events: Split event msgnum configuration from irq setup Ira Weiny
2024-10-29 20:34 ` [PATCH v5 17/27] cxl/pci: Factor out interrupt policy check Ira Weiny
2024-10-29 20:34 ` [PATCH v5 18/27] cxl/mem: Configure dynamic capacity interrupts ira.weiny
2024-10-30 17:58 ` Fan Ni
2024-10-29 20:34 ` [PATCH v5 19/27] cxl/core: Return endpoint decoder information from region search Ira Weiny
2024-10-29 20:34 ` [PATCH v5 20/27] cxl/extent: Process DCD events and realize region extents ira.weiny
2024-10-30 14:32 ` Jonathan Cameron
2024-10-30 16:36 ` Ira Weiny
2024-11-01 12:07 ` Jonathan Cameron
2024-10-29 20:34 ` [PATCH v5 21/27] cxl/region/extent: Expose region extent information in sysfs ira.weiny
2024-10-29 20:34 ` [PATCH v5 22/27] dax/bus: Factor out dev dax resize logic Ira Weiny
2024-10-29 20:34 ` [PATCH v5 23/27] dax/region: Create resources on sparse DAX regions ira.weiny
2024-10-30 14:44 ` Jonathan Cameron
2024-10-29 20:34 ` [PATCH v5 24/27] cxl/region: Read existing extents on region creation ira.weiny
2024-10-29 20:35 ` [PATCH v5 25/27] cxl/mem: Trace Dynamic capacity Event Record ira.weiny
2024-10-29 20:35 ` [PATCH v5 26/27] tools/testing/cxl: Make event logs dynamic Ira Weiny
2024-10-29 20:35 ` [PATCH v5 27/27] tools/testing/cxl: Add DC Regions to mock mem data Ira Weiny
2024-10-30 14:48 ` [PATCH v5 00/27] DCD: Add support for Dynamic Capacity Devices (DCD) Jonathan Cameron
2024-10-31 15:55 ` Dave Jiang
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=20241029-dcd-type2-upstream-v5-13-8739cb67c374@intel.com \
--to=ira.weiny@intel.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=alison.schofield@intel.com \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=fan.ni@samsung.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=navneet.singh@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox