mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Babu Moger <babu.moger@amd.com>
To: <corbet@lwn.net>, <tony.luck@intel.com>,
	<reinette.chatre@intel.com>, <Dave.Martin@arm.com>,
	<james.morse@arm.com>, <tglx@linutronix.de>, <mingo@redhat.com>,
	<bp@alien8.de>, <dave.hansen@linux.intel.com>
Cc: <x86@kernel.org>, <hpa@zytor.com>, <akpm@linux-foundation.org>,
	<paulmck@kernel.org>, <rostedt@goodmis.org>,
	<Neeraj.Upadhyay@amd.com>, <david@redhat.com>, <arnd@arndb.de>,
	<fvdl@google.com>, <seanjc@google.com>, <thomas.lendacky@amd.com>,
	<pawan.kumar.gupta@linux.intel.com>, <babu.moger@amd.com>,
	<yosry.ahmed@linux.dev>, <sohil.mehta@intel.com>, <xin@zytor.com>,
	<kai.huang@intel.com>, <xiaoyao.li@intel.com>,
	<peterz@infradead.org>, <me@mixaill.net>,
	<mario.limonciello@amd.com>, <xin3.li@intel.com>,
	<ebiggers@google.com>, <ak@linux.intel.com>,
	<chang.seok.bae@intel.com>, <andrew.cooper3@citrix.com>,
	<perry.yuan@amd.com>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <manali.shukla@amd.com>,
	<gautham.shenoy@amd.com>
Subject: [PATCH v8 05/10] fs/resctrl: Introduce interface to display "io_alloc" support
Date: Tue, 5 Aug 2025 18:30:25 -0500	[thread overview]
Message-ID: <1004ca25abe2f7460960f08bf9bacacbb5b07b3b.1754436586.git.babu.moger@amd.com> (raw)
In-Reply-To: <cover.1754436586.git.babu.moger@amd.com>

"io_alloc" feature in resctrl allows direct insertion of data from I/O
devices into the cache.

Introduce the 'io_alloc' resctrl file to indicate the support for the
feature.

Signed-off-by: Babu Moger <babu.moger@amd.com>
---
v8: Updated Documentation/filesystems/resctrl.rst.
    Moved resctrl_io_alloc_show() to fs/resctrl/ctrlmondata.c.
    Added prototype for rdt_kn_parent_priv() in fs/resctrl/internal.h
    so, it can be uses in other fs/resctrl/ files.
    Added comment for io_alloc_init().

v7: Updated the changelog.
    Updated user doc for io_alloc in resctrl.rst.
    Added mutex rdtgroup_mutex in resctrl_io_alloc_show();

v6: Added "io_alloc_cbm" details in user doc resctrl.rst.
    Resource name is not printed in CBM now. Corrected the texts about it
    in resctrl.rst.

v5: Resolved conflicts due to recent resctrl FS/ARCH code restructure.
    Updated show_doms() to print the resource if only it is valid. Pass NULL while
    printing io_alloc CBM.
    Changed the code to access the CBMs via either L3CODE or L3DATA resources.

v4: Updated the change log.
    Added rdtgroup_mutex before rdt_last_cmd_puts().
    Returned -ENODEV when resource type is CDP_DATA.
    Kept the resource name while printing the CBM (L3:0=fff) that way
    I dont have to change show_doms() just for this feature and it is
    consistant across all the schemata display.

v3: Minor changes due to changes in resctrl_arch_get_io_alloc_enabled()
    and resctrl_io_alloc_closid_get().
    Added the check to verify CDP resource type.
    Updated the commit log.

v2: Fixed to display only on L3 resources.
    Added the locks while processing.
    Rename the displat to io_alloc_cbm (from sdciae_cmd).
---
 Documentation/filesystems/resctrl.rst | 29 +++++++++++++++++++++++++++
 fs/resctrl/ctrlmondata.c              | 21 +++++++++++++++++++
 fs/resctrl/internal.h                 |  5 +++++
 fs/resctrl/rdtgroup.c                 | 24 +++++++++++++++++++++-
 4 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index f08699030312..fff7e04d1e2a 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -136,6 +136,35 @@ related to allocation:
 			"1":
 			      Non-contiguous 1s value in CBM is supported.
 
+"io_alloc":
+		"io_alloc" enables system software to configure the portion of
+		the cache allocated for I/O traffic. File may only exist if the
+		system supports this feature on some of its cache resources.
+
+			"disabled":
+			      Portions of cache used for allocation of I/O traffic
+			      cannot be configured.
+			"enabled":
+			      Portions of cache used for allocation of I/O traffic
+			      can be configured using "io_alloc_cbm".
+			"not supported":
+			      Support not available for this resource.
+
+		The underlying implementation may reduce resources available to
+		general (CPU) cache allocation. See architecture specific notes
+		below. Depending on usage requirements the feature can be enabled
+		or disabled.
+
+		On AMD systems, the io_alloc feature is supported by the L3 Smart
+		Data Cache Injection Allocation Enforcement (SDCIAE). The CLOSID for
+		io_alloc is the highest CLOSID supported by the resource. When
+		io_alloc is enabled, the highest CLOSID is dedicated to io_alloc and
+		no longer available for general (CPU) cache allocation. When CDP is
+		enabled, io_alloc routes I/O traffic using the highest CLOSID allocated
+		for the instruction cache (L3CODE), making this CLOSID no longer
+		available for general (CPU) cache allocation for both the L3CODE and
+		L3DATA resources.
+
 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 d98e0d2de09f..d495a5d5c9d5 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -664,3 +664,24 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	rdtgroup_kn_unlock(of->kn);
 	return ret;
 }
+
+int resctrl_io_alloc_show(struct kernfs_open_file *of, struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (r->cache.io_alloc_capable) {
+		if (resctrl_arch_get_io_alloc_enabled(r))
+			seq_puts(seq, "enabled\n");
+		else
+			seq_puts(seq, "disabled\n");
+	} else {
+		seq_puts(seq, "not supported\n");
+	}
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 0a1eedba2b03..1a4543c2b988 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -375,6 +375,11 @@ bool closid_allocated(unsigned int closid);
 
 int resctrl_find_cleanest_closid(void);
 
+int resctrl_io_alloc_show(struct kernfs_open_file *of, struct seq_file *seq,
+			  void *v);
+
+void *rdt_kn_parent_priv(struct kernfs_node *kn);
+
 #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 77d08229d855..acc9edc1a268 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -981,7 +981,7 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
 	return 0;
 }
 
-static void *rdt_kn_parent_priv(struct kernfs_node *kn)
+void *rdt_kn_parent_priv(struct kernfs_node *kn)
 {
 	/*
 	 * The parent pointer is only valid within RCU section since it can be
@@ -1893,6 +1893,12 @@ static struct rftype res_common_files[] = {
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_thread_throttle_mode_show,
 	},
+	{
+		.name		= "io_alloc",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_io_alloc_show,
+	},
 	{
 		.name		= "max_threshold_occupancy",
 		.mode		= 0644,
@@ -2062,6 +2068,20 @@ static void thread_throttle_mode_init(void)
 				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
 }
 
+/*
+ * The resctrl file "io_alloc" is added using L3 resource. However, it results
+ * in this file being visible for *all* cache resources (eg. L2 cache),
+ * whether it supports "io_alloc" or not.
+ */
+static void io_alloc_init(void)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	if (r->cache.io_alloc_capable)
+		resctrl_file_fflags_init("io_alloc", RFTYPE_CTRL_INFO |
+					 RFTYPE_RES_CACHE);
+}
+
 void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 {
 	struct rftype *rft;
@@ -4249,6 +4269,8 @@ int resctrl_init(void)
 
 	thread_throttle_mode_init();
 
+	io_alloc_init();
+
 	ret = resctrl_mon_resource_init();
 	if (ret)
 		return ret;
-- 
2.34.1


  parent reply	other threads:[~2025-08-05 23:31 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-05 23:30 [PATCH v8 00/10] x86,fs/resctrl: Support L3 Smart Data Cache Injection Allocation Enforcement (SDCIAE) Babu Moger
2025-08-05 23:30 ` [PATCH v8 01/10] x86/cpufeatures: Add support for L3 Smart Data Cache Injection Allocation Enforcement Babu Moger
2025-08-05 23:30 ` [PATCH v8 02/10] x86/resctrl: Add SDCIAE feature in the command line options Babu Moger
2025-08-08  1:44   ` Reinette Chatre
2025-08-22 22:07     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 03/10] x86,fs/resctrl: Detect io_alloc feature Babu Moger
2025-08-05 23:30 ` [PATCH v8 04/10] x86,fs/resctrl: Implement "io_alloc" enable/disable handlers Babu Moger
2025-08-08  1:47   ` Reinette Chatre
2025-08-22 22:10     ` Moger, Babu
2025-08-05 23:30 ` Babu Moger [this message]
2025-08-08  1:48   ` [PATCH v8 05/10] fs/resctrl: Introduce interface to display "io_alloc" support Reinette Chatre
2025-08-22 22:12     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 06/10] fs/resctrl: Add user interface to enable/disable io_alloc feature Babu Moger
2025-08-08  1:49   ` Reinette Chatre
2025-08-22 22:53     ` Moger, Babu
2025-08-27 20:39       ` Moger, Babu
2025-08-29  2:47         ` Reinette Chatre
2025-09-02 16:20           ` Moger, Babu
2025-08-21  5:02   ` Gautham R. Shenoy
2025-08-22 23:10     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 07/10] fs/resctrl: Introduce interface to display io_alloc CBMs Babu Moger
2025-08-08  1:51   ` Reinette Chatre
2025-08-26 18:33     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 08/10] fs/resctrl: Modify rdt_parse_data to pass mode and CLOSID Babu Moger
2025-08-08  1:52   ` Reinette Chatre
2025-08-26 18:40     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 09/10] fs/resctrl: Introduce interface to modify io_alloc Capacity Bit Masks Babu Moger
2025-08-08  1:53   ` Reinette Chatre
2025-08-26 18:53     ` Moger, Babu
2025-08-05 23:30 ` [PATCH v8 10/10] fs/resctrl: Update bit_usage to reflect io_alloc Babu Moger
2025-08-08  1:54   ` Reinette Chatre
2025-08-26 22:51     ` Moger, Babu
2025-08-29  3:11       ` Reinette Chatre
2025-09-02 16:32         ` Moger, Babu

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=1004ca25abe2f7460960f08bf9bacacbb5b07b3b.1754436586.git.babu.moger@amd.com \
    --to=babu.moger@amd.com \
    --cc=Dave.Martin@arm.com \
    --cc=Neeraj.Upadhyay@amd.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=andrew.cooper3@citrix.com \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=chang.seok.bae@intel.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=ebiggers@google.com \
    --cc=fvdl@google.com \
    --cc=gautham.shenoy@amd.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=kai.huang@intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=manali.shukla@amd.com \
    --cc=mario.limonciello@amd.com \
    --cc=me@mixaill.net \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=pawan.kumar.gupta@linux.intel.com \
    --cc=perry.yuan@amd.com \
    --cc=peterz@infradead.org \
    --cc=reinette.chatre@intel.com \
    --cc=rostedt@goodmis.org \
    --cc=seanjc@google.com \
    --cc=sohil.mehta@intel.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tony.luck@intel.com \
    --cc=x86@kernel.org \
    --cc=xiaoyao.li@intel.com \
    --cc=xin3.li@intel.com \
    --cc=xin@zytor.com \
    --cc=yosry.ahmed@linux.dev \
    /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

all inboxes | Powered by JetHome®