Merge tag 'x86_cache_for_v6.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:

 - Add support for AMD's Smart Data Cache Injection feature which allows
   for direct insertion of data from I/O devices into the L3 cache, thus
   bypassing DRAM and saving its bandwidth; the resctrl side of the
   feature allows the size of the L3 used for data injection to be
   controlled

 - Add Intel Clearwater Forest to the list of CPUs which support
   Sub-NUMA clustering

 - Other fixes and cleanups

* tag 'x86_cache_for_v6.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  fs/resctrl: Update bit_usage to reflect io_alloc
  fs/resctrl: Introduce interface to modify io_alloc capacity bitmasks
  fs/resctrl: Modify struct rdt_parse_data to pass mode and CLOSID
  fs/resctrl: Introduce interface to display io_alloc CBMs
  fs/resctrl: Add user interface to enable/disable io_alloc feature
  fs/resctrl: Introduce interface to display "io_alloc" support
  x86,fs/resctrl: Implement "io_alloc" enable/disable handlers
  x86,fs/resctrl: Detect io_alloc feature
  x86/resctrl: Add SDCIAE feature in the command line options
  x86/cpufeatures: Add support for L3 Smart Data Cache Injection Allocation Enforcement
  fs/resctrl: Consider sparse masks when initializing new group's allocation
  x86/resctrl: Support Sub-NUMA Cluster (SNC) mode on Clearwater Forest

13 files changed, 580 insertions, 47 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e63827475792..8c5636a120ee 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6207,7 +6207,7 @@
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba, smba, bmec, abmc.
+			mba, smba, bmec, abmc, sdciae.
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
 
diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index b7f35b07876a..8c8ce678148a 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -17,17 +17,18 @@ AMD refers to this feature as AMD Platform Quality of Service(AMD QoS).
 This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo
 flag bits:
 
-===============================================	================================
-RDT (Resource Director Technology) Allocation	"rdt_a"
-CAT (Cache Allocation Technology)		"cat_l3", "cat_l2"
-CDP (Code and Data Prioritization)		"cdp_l3", "cdp_l2"
-CQM (Cache QoS Monitoring)			"cqm_llc", "cqm_occup_llc"
-MBM (Memory Bandwidth Monitoring)		"cqm_mbm_total", "cqm_mbm_local"
-MBA (Memory Bandwidth Allocation)		"mba"
-SMBA (Slow Memory Bandwidth Allocation)         ""
-BMEC (Bandwidth Monitoring Event Configuration) ""
-ABMC (Assignable Bandwidth Monitoring Counters) ""
-===============================================	================================
+=============================================================== ================================
+RDT (Resource Director Technology) Allocation			"rdt_a"
+CAT (Cache Allocation Technology)				"cat_l3", "cat_l2"
+CDP (Code and Data Prioritization)				"cdp_l3", "cdp_l2"
+CQM (Cache QoS Monitoring)					"cqm_llc", "cqm_occup_llc"
+MBM (Memory Bandwidth Monitoring)				"cqm_mbm_total", "cqm_mbm_local"
+MBA (Memory Bandwidth Allocation)				"mba"
+SMBA (Slow Memory Bandwidth Allocation)				""
+BMEC (Bandwidth Monitoring Event Configuration)			""
+ABMC (Assignable Bandwidth Monitoring Counters)			""
+SDCIAE (Smart Data Cache Injection Allocation Enforcement)	""
+=============================================================== ================================
 
 Historically, new features were made visible by default in /proc/cpuinfo. This
 resulted in the feature flags becoming hard to parse by humans. Adding a new
@@ -72,6 +73,11 @@ The 'info' directory contains information about the enabled
 resources. Each resource has its own subdirectory. The subdirectory
 names reflect the resource names.
 
+Most of the files in the resource's subdirectory are read-only, and
+describe properties of the resource. Resources that support global
+configuration options also include writable files that can be used
+to modify those settings.
+
 Each subdirectory contains the following files with respect to
 allocation:
 
@@ -90,12 +96,19 @@ related to allocation:
 		must be set when writing a mask.
 
 "shareable_bits":
-		Bitmask of shareable resource with other executing
-		entities (e.g. I/O). User can use this when
-		setting up exclusive cache partitions. Note that
-		some platforms support devices that have their
-		own settings for cache use which can over-ride
-		these bits.
+		Bitmask of shareable resource with other executing entities
+		(e.g. I/O). Applies to all instances of this resource. User
+		can use this when setting up exclusive cache partitions.
+		Note that some platforms support devices that have their
+		own settings for cache use which can over-ride these bits.
+
+		When "io_alloc" is enabled, a portion of each cache instance can
+		be configured for shared use between hardware and software.
+		"bit_usage" should be used to see which portions of each cache
+		instance is configured for hardware use via "io_alloc" feature
+		because every cache instance can have its "io_alloc" bitmask
+		configured independently via "io_alloc_cbm".
+
 "bit_usage":
 		Annotated capacity bitmasks showing how all
 		instances of the resource are used. The legend is:
@@ -109,16 +122,16 @@ related to allocation:
 			"H":
 			      Corresponding region is used by hardware only
 			      but available for software use. If a resource
-			      has bits set in "shareable_bits" but not all
-			      of these bits appear in the resource groups'
-			      schematas then the bits appearing in
-			      "shareable_bits" but no resource group will
-			      be marked as "H".
+			      has bits set in "shareable_bits" or "io_alloc_cbm"
+			      but not all of these bits appear in the resource
+			      groups' schemata then the bits appearing in
+			      "shareable_bits" or "io_alloc_cbm" but no
+			      resource group will be marked as "H".
 			"X":
 			      Corresponding region is available for sharing and
-			      used by hardware and software. These are the
-			      bits that appear in "shareable_bits" as
-			      well as a resource group's allocation.
+			      used by hardware and software. These are the bits
+			      that appear in "shareable_bits" or "io_alloc_cbm"
+			      as well as a resource group's allocation.
 			"S":
 			      Corresponding region is used by software
 			      and available for sharing.
@@ -136,6 +149,77 @@ 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":
+			      Resource supports "io_alloc" but the feature is 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 feature can be modified by writing to the interface, for example:
+
+		To enable::
+
+			# echo 1 > /sys/fs/resctrl/info/L3/io_alloc
+
+		To disable::
+
+			# echo 0 > /sys/fs/resctrl/info/L3/io_alloc
+
+		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, 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 (CDP_CODE), making this CLOSID no longer
+		available for general (CPU) cache allocation for both the CDP_CODE
+		and CDP_DATA resources.
+
+"io_alloc_cbm":
+		Capacity bitmasks that describe the portions of cache instances to
+		which I/O traffic from supported I/O devices are routed when "io_alloc"
+		is enabled.
+
+		CBMs are displayed in the following format:
+
+			<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+		Example::
+
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=ffff;1=ffff
+
+		CBMs can be configured by writing to the interface.
+
+		Example::
+
+			# echo 1=ff > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=ffff;1=00ff
+
+			# echo "0=ff;1=f" > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=00ff;1=000f
+
+		When CDP is enabled "io_alloc_cbm" associated with the CDP_DATA and CDP_CODE
+		resources may reflect the same values. For example, values read from and
+		written to /sys/fs/resctrl/info/L3DATA/io_alloc_cbm may be reflected by
+		/sys/fs/resctrl/info/L3CODE/io_alloc_cbm and vice versa.
+
 Memory bandwidth(MB) subdirectory contains the following files
 with respect to allocation:
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4091a776e37a..2abee3e9dc75 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -500,6 +500,8 @@
 #define X86_FEATURE_ABMC		(21*32+15) /* Assignable Bandwidth Monitoring Counters */
 #define X86_FEATURE_MSR_IMM		(21*32+16) /* MSR immediate form instructions */
 
+#define X86_FEATURE_SDCIAE		(21*32+18) /* L3 Smart Data Cache Injection Allocation Enforcement */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 46efcbd6afa4..87e78586395b 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -72,6 +72,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_MBM_LOCAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_BMEC,			X86_FEATURE_CQM_MBM_TOTAL   },
 	{ X86_FEATURE_BMEC,			X86_FEATURE_CQM_MBM_LOCAL   },
+	{ X86_FEATURE_SDCIAE,			X86_FEATURE_CAT_L3    },
 	{ X86_FEATURE_AVX512_BF16,		X86_FEATURE_AVX512VL  },
 	{ X86_FEATURE_AVX512_FP16,		X86_FEATURE_AVX512BW  },
 	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 06ca5a30140c..3792ab4819dc 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -274,6 +274,11 @@ static void rdt_get_cdp_config(int level)
 	rdt_resources_all[level].r_resctrl.cdp_capable = true;
 }
 
+static void rdt_set_io_alloc_capable(struct rdt_resource *r)
+{
+	r->cache.io_alloc_capable = true;
+}
+
 static void rdt_get_cdp_l3_config(void)
 {
 	rdt_get_cdp_config(RDT_RESOURCE_L3);
@@ -719,6 +724,7 @@ enum {
 	RDT_FLAG_SMBA,
 	RDT_FLAG_BMEC,
 	RDT_FLAG_ABMC,
+	RDT_FLAG_SDCIAE,
 };
 
 #define RDT_OPT(idx, n, f)	\
@@ -745,6 +751,7 @@ static struct rdt_options rdt_options[]  __ro_after_init = {
 	RDT_OPT(RDT_FLAG_SMBA,	    "smba",	X86_FEATURE_SMBA),
 	RDT_OPT(RDT_FLAG_BMEC,	    "bmec",	X86_FEATURE_BMEC),
 	RDT_OPT(RDT_FLAG_ABMC,	    "abmc",	X86_FEATURE_ABMC),
+	RDT_OPT(RDT_FLAG_SDCIAE,    "sdciae",	X86_FEATURE_SDCIAE),
 };
 #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
 
@@ -853,6 +860,8 @@ static __init bool get_rdt_alloc_resources(void)
 		rdt_get_cache_alloc_cfg(1, r);
 		if (rdt_cpu_has(X86_FEATURE_CDP_L3))
 			rdt_get_cdp_l3_config();
+		if (rdt_cpu_has(X86_FEATURE_SDCIAE))
+			rdt_set_io_alloc_capable(r);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 1189c0df4ad7..b20e705606b8 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -91,3 +91,43 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 
 	return hw_dom->ctrl_val[idx];
 }
+
+bool resctrl_arch_get_io_alloc_enabled(struct rdt_resource *r)
+{
+	return resctrl_to_arch_res(r)->sdciae_enabled;
+}
+
+static void resctrl_sdciae_set_one_amd(void *arg)
+{
+	bool *enable = arg;
+
+	if (*enable)
+		msr_set_bit(MSR_IA32_L3_QOS_EXT_CFG, SDCIAE_ENABLE_BIT);
+	else
+		msr_clear_bit(MSR_IA32_L3_QOS_EXT_CFG, SDCIAE_ENABLE_BIT);
+}
+
+static void _resctrl_sdciae_enable(struct rdt_resource *r, bool enable)
+{
+	struct rdt_ctrl_domain *d;
+
+	/* Walking r->ctrl_domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	/* Update MSR_IA32_L3_QOS_EXT_CFG MSR on all the CPUs in all domains */
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list)
+		on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_sdciae_set_one_amd, &enable, 1);
+}
+
+int resctrl_arch_io_alloc_enable(struct rdt_resource *r, bool enable)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+	if (hw_res->r_resctrl.cache.io_alloc_capable &&
+	    hw_res->sdciae_enabled != enable) {
+		_resctrl_sdciae_enable(r, enable);
+		hw_res->sdciae_enabled = enable;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 9f4c2f0aaf5c..4a916c84a322 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -46,6 +46,9 @@ struct arch_mbm_state {
 #define ABMC_EXTENDED_EVT_ID		BIT(31)
 #define ABMC_EVT_ID			BIT(0)
 
+/* Setting bit 1 in MSR_IA32_L3_QOS_EXT_CFG enables the SDCIAE feature. */
+#define SDCIAE_ENABLE_BIT		1
+
 /**
  * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
  *			       a resource for a control function
@@ -112,6 +115,7 @@ struct msr_param {
  * @mbm_width:		Monitor width, to detect and correct for overflow.
  * @cdp_enabled:	CDP state of this resource
  * @mbm_cntr_assign_enabled:	ABMC feature is enabled
+ * @sdciae_enabled:	SDCIAE feature (backing "io_alloc") is enabled.
  *
  * Members of this structure are either private to the architecture
  * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g.
@@ -126,6 +130,7 @@ struct rdt_hw_resource {
 	unsigned int		mbm_width;
 	bool			cdp_enabled;
 	bool			mbm_cntr_assign_enabled;
+	bool			sdciae_enabled;
 };
 
 static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index fe1a2aa53c16..dffcc8307500 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -361,6 +361,7 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0),
 	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, 0),
 	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, 0),
+	X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, 0),
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index caa4dc885c21..d113863a8eab 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -53,6 +53,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_SMBA,			CPUID_EBX,  2, 0x80000020, 0 },
 	{ X86_FEATURE_BMEC,			CPUID_EBX,  3, 0x80000020, 0 },
 	{ X86_FEATURE_ABMC,			CPUID_EBX,  5, 0x80000020, 0 },
+	{ X86_FEATURE_SDCIAE,			CPUID_EBX,  6, 0x80000020, 0 },
 	{ X86_FEATURE_TSA_SQ_NO,		CPUID_ECX,  1, 0x80000021, 0 },
 	{ X86_FEATURE_TSA_L1_NO,		CPUID_ECX,  2, 0x80000021, 0 },
 	{ X86_FEATURE_AMD_WORKLOAD_CLASS,	CPUID_EAX, 22, 0x80000021, 0 },
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 0d0ef54fc4de..b2d178d3556e 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -24,7 +24,8 @@
 #include "internal.h"
 
 struct rdt_parse_data {
-	struct rdtgroup		*rdtgrp;
+	u32			closid;
+	enum rdtgrp_mode	mode;
 	char			*buf;
 };
 
@@ -77,8 +78,8 @@ static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
 		    struct rdt_ctrl_domain *d)
 {
 	struct resctrl_staged_config *cfg;
-	u32 closid = data->rdtgrp->closid;
 	struct rdt_resource *r = s->res;
+	u32 closid = data->closid;
 	u32 bw_val;
 
 	cfg = &d->staged_config[s->conf_type];
@@ -156,9 +157,10 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
 		     struct rdt_ctrl_domain *d)
 {
-	struct rdtgroup *rdtgrp = data->rdtgrp;
+	enum rdtgrp_mode mode = data->mode;
 	struct resctrl_staged_config *cfg;
 	struct rdt_resource *r = s->res;
+	u32 closid = data->closid;
 	u32 cbm_val;
 
 	cfg = &d->staged_config[s->conf_type];
@@ -171,7 +173,7 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
 	 * Cannot set up more than one pseudo-locked region in a cache
 	 * hierarchy.
 	 */
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	if (mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
 		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
 		return -EINVAL;
@@ -180,8 +182,7 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
 	if (!cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
-	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+	if ((mode == RDT_MODE_EXCLUSIVE || mode == RDT_MODE_SHAREABLE) &&
 	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
 		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
 		return -EINVAL;
@@ -191,14 +192,14 @@ static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
 	 * The CBM may not overlap with the CBM of another closid if
 	 * either is exclusive.
 	 */
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
+	if (rdtgroup_cbm_overlaps(s, d, cbm_val, closid, true)) {
 		rdt_last_cmd_puts("Overlaps with exclusive group\n");
 		return -EINVAL;
 	}
 
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
-		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+	if (rdtgroup_cbm_overlaps(s, d, cbm_val, closid, false)) {
+		if (mode == RDT_MODE_EXCLUSIVE ||
+		    mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 			rdt_last_cmd_puts("Overlaps with other group\n");
 			return -EINVAL;
 		}
@@ -262,7 +263,8 @@ next:
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		if (d->hdr.id == dom_id) {
 			data.buf = dom;
-			data.rdtgrp = rdtgrp;
+			data.closid = rdtgrp->closid;
+			data.mode = rdtgrp->mode;
 			if (parse_ctrlval(&data, s, d))
 				return -EINVAL;
 			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -381,7 +383,8 @@ out:
 	return ret ?: nbytes;
 }
 
-static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
+static void show_doms(struct seq_file *s, struct resctrl_schema *schema,
+		      char *resource_name, int closid)
 {
 	struct rdt_resource *r = schema->res;
 	struct rdt_ctrl_domain *dom;
@@ -391,7 +394,8 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	seq_printf(s, "%*s:", max_name_width, schema->name);
+	if (resource_name)
+		seq_printf(s, "%*s:", max_name_width, resource_name);
 	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
@@ -437,7 +441,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			closid = rdtgrp->closid;
 			list_for_each_entry(schema, &resctrl_schema_all, list) {
 				if (closid < schema->num_closid)
-					show_doms(s, schema, closid);
+					show_doms(s, schema, schema->name, closid);
 			}
 		}
 	} else {
@@ -676,3 +680,280 @@ out:
 	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;
+}
+
+/*
+ * resctrl_io_alloc_closid_supported() - io_alloc feature utilizes the
+ * highest CLOSID value to direct I/O traffic. Ensure that io_alloc_closid
+ * is in the supported range.
+ */
+static bool resctrl_io_alloc_closid_supported(u32 io_alloc_closid)
+{
+	return io_alloc_closid < closids_supported();
+}
+
+/*
+ * Initialize io_alloc CLOSID cache resource CBM with all usable (shared
+ * and unused) cache portions.
+ */
+static int resctrl_io_alloc_init_cbm(struct resctrl_schema *s, u32 closid)
+{
+	enum resctrl_conf_type peer_type;
+	struct rdt_resource *r = s->res;
+	struct rdt_ctrl_domain *d;
+	int ret;
+
+	rdt_staged_configs_clear();
+
+	ret = rdtgroup_init_cat(s, closid);
+	if (ret < 0)
+		goto out;
+
+	/* Keep CDP_CODE and CDP_DATA of io_alloc CLOSID's CBM in sync. */
+	if (resctrl_arch_get_cdp_enabled(r->rid)) {
+		peer_type = resctrl_peer_type(s->conf_type);
+		list_for_each_entry(d, &s->res->ctrl_domains, hdr.list)
+			memcpy(&d->staged_config[peer_type],
+			       &d->staged_config[s->conf_type],
+			       sizeof(d->staged_config[0]));
+	}
+
+	ret = resctrl_arch_update_domains(r, closid);
+out:
+	rdt_staged_configs_clear();
+	return ret;
+}
+
+/*
+ * resctrl_io_alloc_closid() - io_alloc feature routes I/O traffic using
+ * the highest available CLOSID. Retrieve the maximum CLOSID supported by the
+ * resource. Note that if Code Data Prioritization (CDP) is enabled, the number
+ * of available CLOSIDs is reduced by half.
+ */
+u32 resctrl_io_alloc_closid(struct rdt_resource *r)
+{
+	if (resctrl_arch_get_cdp_enabled(r->rid))
+		return resctrl_arch_get_num_closid(r) / 2  - 1;
+	else
+		return resctrl_arch_get_num_closid(r) - 1;
+}
+
+ssize_t resctrl_io_alloc_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;
+	char const *grp_name;
+	u32 io_alloc_closid;
+	bool enable;
+	int ret;
+
+	ret = kstrtobool(buf, &enable);
+	if (ret)
+		return ret;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	if (!r->cache.io_alloc_capable) {
+		rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name);
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	/* If the feature is already up to date, no action is needed. */
+	if (resctrl_arch_get_io_alloc_enabled(r) == enable)
+		goto out_unlock;
+
+	io_alloc_closid = resctrl_io_alloc_closid(r);
+	if (!resctrl_io_alloc_closid_supported(io_alloc_closid)) {
+		rdt_last_cmd_printf("io_alloc CLOSID (ctrl_hw_id) %u is not available\n",
+				    io_alloc_closid);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (enable) {
+		if (!closid_alloc_fixed(io_alloc_closid)) {
+			grp_name = rdtgroup_name_by_closid(io_alloc_closid);
+			WARN_ON_ONCE(!grp_name);
+			rdt_last_cmd_printf("CLOSID (ctrl_hw_id) %u for io_alloc is used by %s group\n",
+					    io_alloc_closid, grp_name ? grp_name : "another");
+			ret = -ENOSPC;
+			goto out_unlock;
+		}
+
+		ret = resctrl_io_alloc_init_cbm(s, io_alloc_closid);
+		if (ret) {
+			rdt_last_cmd_puts("Failed to initialize io_alloc allocations\n");
+			closid_free(io_alloc_closid);
+			goto out_unlock;
+		}
+	} else {
+		closid_free(io_alloc_closid);
+	}
+
+	ret = resctrl_arch_io_alloc_enable(r, enable);
+	if (enable && ret) {
+		rdt_last_cmd_puts("Failed to enable io_alloc feature\n");
+		closid_free(io_alloc_closid);
+	}
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
+
+int resctrl_io_alloc_cbm_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;
+	int ret = 0;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	if (!r->cache.io_alloc_capable) {
+		rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name);
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	if (!resctrl_arch_get_io_alloc_enabled(r)) {
+		rdt_last_cmd_printf("io_alloc is not enabled on %s\n", s->name);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	/*
+	 * When CDP is enabled, the CBMs of the highest CLOSID of CDP_CODE and
+	 * CDP_DATA are kept in sync. As a result, the io_alloc CBMs shown for
+	 * either CDP resource are identical and accurately represent the CBMs
+	 * used for I/O.
+	 */
+	show_doms(seq, s, NULL, resctrl_io_alloc_closid(r));
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+static int resctrl_io_alloc_parse_line(char *line,  struct rdt_resource *r,
+				       struct resctrl_schema *s, u32 closid)
+{
+	enum resctrl_conf_type peer_type;
+	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;
+			/*
+			 * Keep io_alloc CLOSID's CBM of CDP_CODE and CDP_DATA
+			 * in sync.
+			 */
+			if (resctrl_arch_get_cdp_enabled(r->rid)) {
+				peer_type = resctrl_peer_type(s->conf_type);
+				memcpy(&d->staged_config[peer_type],
+				       &d->staged_config[s->conf_type],
+				       sizeof(d->staged_config[0]));
+			}
+			goto next;
+		}
+	}
+
+	return -EINVAL;
+}
+
+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';
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+	rdt_last_cmd_clear();
+
+	if (!r->cache.io_alloc_capable) {
+		rdt_last_cmd_printf("io_alloc is not supported on %s\n", s->name);
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	if (!resctrl_arch_get_io_alloc_enabled(r)) {
+		rdt_last_cmd_printf("io_alloc is not enabled on %s\n", s->name);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	io_alloc_closid = resctrl_io_alloc_closid(r);
+
+	rdt_staged_configs_clear();
+	ret = resctrl_io_alloc_parse_line(buf, r, s, io_alloc_closid);
+	if (ret)
+		goto out_clear_configs;
+
+	ret = resctrl_arch_update_domains(r, io_alloc_closid);
+
+out_clear_configs:
+	rdt_staged_configs_clear();
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index cf1fd82dc5a9..bff4a54ae333 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -390,6 +390,8 @@ void rdt_staged_configs_clear(void);
 
 bool closid_allocated(unsigned int closid);
 
+bool closid_alloc_fixed(u32 closid);
+
 int resctrl_find_cleanest_closid(void);
 
 void *rdt_kn_parent_priv(struct kernfs_node *kn);
@@ -426,6 +428,21 @@ int mbm_L3_assignments_show(struct kernfs_open_file *of, struct seq_file *s, voi
 
 ssize_t mbm_L3_assignments_write(struct kernfs_open_file *of, char *buf, size_t nbytes,
 				 loff_t off);
+int resctrl_io_alloc_show(struct kernfs_open_file *of, struct seq_file *seq, void *v);
+
+int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid);
+
+enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type);
+
+ssize_t resctrl_io_alloc_write(struct kernfs_open_file *of, char *buf,
+			       size_t nbytes, loff_t off);
+
+const char *rdtgroup_name_by_closid(u32 closid);
+int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of, struct seq_file *seq,
+			      void *v);
+ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of, char *buf,
+				   size_t nbytes, loff_t off);
+u32 resctrl_io_alloc_closid(struct rdt_resource *r);
 
 #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 0320360cd7a6..8e39dfda56bc 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -226,6 +226,11 @@ bool closid_allocated(unsigned int closid)
 	return !test_bit(closid, closid_free_map);
 }
 
+bool closid_alloc_fixed(u32 closid)
+{
+	return __test_and_clear_bit(closid, closid_free_map);
+}
+
 /**
  * rdtgroup_mode_by_closid - Return mode of resource group with closid
  * @closid: closid if the resource group
@@ -1057,15 +1062,17 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
-	hw_shareable = r->cache.shareable_bits;
 	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_putc(seq, ';');
+		hw_shareable = r->cache.shareable_bits;
 		sw_shareable = 0;
 		exclusive = 0;
 		seq_printf(seq, "%d=", dom->hdr.id);
 		for (i = 0; i < closids_supported(); i++) {
-			if (!closid_allocated(i))
+			if (!closid_allocated(i) ||
+			    (resctrl_arch_get_io_alloc_enabled(r) &&
+			     i == resctrl_io_alloc_closid(r)))
 				continue;
 			ctrl_val = resctrl_arch_get_config(r, dom, i,
 							   s->conf_type);
@@ -1093,6 +1100,21 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 				break;
 			}
 		}
+
+		/*
+		 * When the "io_alloc" feature is enabled, a portion of the cache
+		 * is configured for shared use between hardware and software.
+		 * Also, when CDP is enabled the CBMs of CDP_CODE and CDP_DATA
+		 * resources are kept in sync. So, the CBMs for "io_alloc" can
+		 * be accessed through either resource.
+		 */
+		if (resctrl_arch_get_io_alloc_enabled(r)) {
+			ctrl_val = resctrl_arch_get_config(r, dom,
+							   resctrl_io_alloc_closid(r),
+							   s->conf_type);
+			hw_shareable |= ctrl_val;
+		}
+
 		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
 			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
 			hwb = test_bit(i, &hw_shareable);
@@ -1247,7 +1269,7 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
 	return 0;
 }
 
-static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
+enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
 {
 	switch (my_type) {
 	case CDP_CODE:
@@ -1838,6 +1860,18 @@ void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_
 		kernfs_put(mon_kn);
 }
 
+const char *rdtgroup_name_by_closid(u32 closid)
+{
+	struct rdtgroup *rdtgrp;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->closid == closid)
+			return rdt_kn_name(rdtgrp->kn);
+	}
+
+	return NULL;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -1948,6 +1982,20 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdt_thread_throttle_mode_show,
 	},
 	{
+		.name		= "io_alloc",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_io_alloc_show,
+		.write          = resctrl_io_alloc_write,
+	},
+	{
+		.name		= "io_alloc_cbm",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_io_alloc_cbm_show,
+		.write		= resctrl_io_alloc_cbm_write,
+	},
+	{
 		.name		= "max_threshold_occupancy",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -2138,6 +2186,23 @@ 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);
+		resctrl_file_fflags_init("io_alloc_cbm",
+					 RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE);
+	}
+}
+
 void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 {
 	struct rftype *rft;
@@ -3383,11 +3448,12 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
 {
 	unsigned int cbm_len = r->cache.cbm_len;
 	unsigned long first_bit, zero_bit;
-	unsigned long val = _val;
+	unsigned long val;
 
-	if (!val)
-		return 0;
+	if (!_val || r->cache.arch_has_sparse_bitmasks)
+		return _val;
 
+	val = _val;
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
@@ -3480,7 +3546,7 @@ static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schem
  * If there are no more shareable bits available on any domain then
  * the entire allocation will fail.
  */
-static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
+int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
 {
 	struct rdt_ctrl_domain *d;
 	int ret;
@@ -4408,6 +4474,8 @@ int resctrl_init(void)
 
 	thread_throttle_mode_init();
 
+	io_alloc_init();
+
 	ret = resctrl_mon_resource_init();
 	if (ret)
 		return ret;
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index a7d92718b653..54701668b3df 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -206,6 +206,8 @@ struct rdt_mon_domain {
  * @arch_has_sparse_bitmasks:	True if a bitmask like f00f is valid.
  * @arch_has_per_cpu_cfg:	True if QOS_CFG register for this cache
  *				level has CPU scope.
+ * @io_alloc_capable:	True if portion of the cache can be configured
+ *			for I/O traffic.
  */
 struct resctrl_cache {
 	unsigned int	cbm_len;
@@ -213,6 +215,7 @@ struct resctrl_cache {
 	unsigned int	shareable_bits;
 	bool		arch_has_sparse_bitmasks;
 	bool		arch_has_per_cpu_cfg;
+	bool		io_alloc_capable;
 };
 
 /**
@@ -654,6 +657,27 @@ void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 closid, u32 rmid, int cntr_id,
 			     enum resctrl_event_id eventid);
 
+/**
+ * resctrl_arch_io_alloc_enable() - Enable/disable io_alloc feature.
+ * @r:		The resctrl resource.
+ * @enable:	Enable (true) or disable (false) io_alloc on resource @r.
+ *
+ * This can be called from any CPU.
+ *
+ * Return:
+ * 0 on success, <0 on error.
+ */
+int resctrl_arch_io_alloc_enable(struct rdt_resource *r, bool enable);
+
+/**
+ * resctrl_arch_get_io_alloc_enabled() - Get io_alloc feature state.
+ * @r:		The resctrl resource.
+ *
+ * Return:
+ * true if io_alloc is enabled or false if disabled.
+ */
+bool resctrl_arch_get_io_alloc_enabled(struct rdt_resource *r);
+
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;