lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ad6ee3076967940e9a173c595ec5db6725d93846.1747943499.git.babu.moger@amd.com>
Date: Thu, 22 May 2025 14:51:39 -0500
From: Babu Moger <babu.moger@....com>
To: <corbet@....net>, <tony.luck@...el.com>, <reinette.chatre@...el.com>,
	<Dave.Martin@....com>, <james.morse@....com>, <tglx@...utronix.de>,
	<mingo@...hat.com>, <bp@...en8.de>, <dave.hansen@...ux.intel.com>
CC: <x86@...nel.org>, <hpa@...or.com>, <akpm@...ux-foundation.org>,
	<rostedt@...dmis.org>, <paulmck@...nel.org>, <thuth@...hat.com>,
	<ardb@...nel.org>, <gregkh@...uxfoundation.org>, <thomas.lendacky@....com>,
	<seanjc@...gle.com>, <mario.limonciello@....com>, <perry.yuan@....com>,
	<kai.huang@...el.com>, <xiaoyao.li@...el.com>, <nikunj@....com>,
	<kan.liang@...ux.intel.com>, <xin3.li@...el.com>, <babu.moger@....com>,
	<andrew.cooper3@...rix.com>, <ebiggers@...gle.com>, <xin@...or.com>,
	<sohil.mehta@...el.com>, <Xiaojian.Du@....com>, <gautham.shenoy@....com>,
	<linux-doc@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: [PATCH v5 8/8] x86/resctrl: Introduce interface to modify io_alloc Capacity Bit Masks

"io_alloc" feature is a mechanism that enables direct insertion of data
from I/O devices into the L3 cache. By directly caching data from I/O
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
devices. Provide the interface to modify io_alloc CBMs (Capacity Bit Mask)
when feature is enabled.

Signed-off-by: Babu Moger <babu.moger@....com>
---
v5: Changes due to FS/ARCH code restructure. The files monitor.c/rdtgroup.c
    have been split between FS and ARCH directories.
    Changed the code to access the CBMs via either L3CODE or L3DATA resources.

v4: Removed resctrl_io_alloc_parse_cbm and called parse_cbm() directly.

v3: Minor changes due to changes in resctrl_arch_get_io_alloc_enabled()
    and resctrl_io_alloc_closid_get().
    Taken care of handling the CBM update when CDP is enabled.
    Updated the commit log to make it generic.

v2: Added more generic text in documentation.
---
 Documentation/filesystems/resctrl.rst | 23 +++++++
 fs/resctrl/ctrlmondata.c              |  4 +-
 fs/resctrl/internal.h                 |  2 +
 fs/resctrl/rdtgroup.c                 | 89 ++++++++++++++++++++++++++-
 4 files changed, 115 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index 5594422f133f..59697c99a22e 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -169,6 +169,29 @@ related to allocation:
 		When CDP is enabled, io_alloc routes I/O traffic using the highest
 		CLOSID allocated for the instruction cache (L3CODE).
 
+"io_alloc_cbm":
+		Capacity Bit Masks (CBMs) available to supported IO devices which
+		can directly insert cache lines in L3 which can help to reduce the
+		latency. CBM can be configured by writing to the interface in the
+		following format::
+
+			<resource_name>:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+		Example::
+
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			L3:0=ffff;1=ffff
+
+			# echo L3:1=FF > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			L3:0=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.
+
+
 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 9277b9c146bd..b84fee51c57d 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2035,6 +2035,92 @@ 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");
+		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;
+	}
+
+	io_alloc_closid = resctrl_io_alloc_closid_get(r);
+	if (io_alloc_closid < 0) {
+		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);
+	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[] = {
 	{
@@ -2196,9 +2282,10 @@ 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",
-- 
2.34.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ