Merge tag 'x86_cache_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:

 - Add support for a new AMD feature called slow memory bandwidth
   allocation. Its goal is to control resource allocation in external
   slow memory which is connected to the machine like for example
   through CXL devices, accelerators etc

* tag 'x86_cache_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Fix a silly -Wunused-but-set-variable warning
  Documentation/x86: Update resctrl.rst for new features
  x86/resctrl: Add interface to write mbm_local_bytes_config
  x86/resctrl: Add interface to write mbm_total_bytes_config
  x86/resctrl: Add interface to read mbm_local_bytes_config
  x86/resctrl: Add interface to read mbm_total_bytes_config
  x86/resctrl: Support monitor configuration
  x86/resctrl: Add __init attribute to rdt_get_mon_l3_config()
  x86/resctrl: Detect and configure Slow Memory Bandwidth Allocation
  x86/resctrl: Include new features in command line options
  x86/cpufeatures: Add Bandwidth Monitoring Event Configuration feature flag
  x86/resctrl: Add a new resource type RDT_RESOURCE_SMBA
  x86/cpufeatures: Add Slow Memory Bandwidth Allocation feature flag
  x86/resctrl: Replace smp_call_function_many() with on_each_cpu_mask()

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -5221,7 +5221,7 @@
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba.
+			mba, smba, bmec.
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
 

Documentation/x86/resctrl.rst

@@ -17,14 +17,21 @@ 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) ""
+===============================================	================================
+
+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
+flag to /proc/cpuinfo should be avoided if user space can obtain information
+about the feature from resctrl's info directory.
 
 To use the feature mount the file system::
 
@@ -161,6 +168,83 @@ with the following files:
 "mon_features":
 		Lists the monitoring events if
 		monitoring is enabled for the resource.
+		Example::
+
+			# cat /sys/fs/resctrl/info/L3_MON/mon_features
+			llc_occupancy
+			mbm_total_bytes
+			mbm_local_bytes
+
+		If the system supports Bandwidth Monitoring Event
+		Configuration (BMEC), then the bandwidth events will
+		be configurable. The output will be::
+
+			# cat /sys/fs/resctrl/info/L3_MON/mon_features
+			llc_occupancy
+			mbm_total_bytes
+			mbm_total_bytes_config
+			mbm_local_bytes
+			mbm_local_bytes_config
+
+"mbm_total_bytes_config", "mbm_local_bytes_config":
+	Read/write files containing the configuration for the mbm_total_bytes
+	and mbm_local_bytes events, respectively, when the Bandwidth
+	Monitoring Event Configuration (BMEC) feature is supported.
+	The event configuration settings are domain specific and affect
+	all the CPUs in the domain. When either event configuration is
+	changed, the bandwidth counters for all RMIDs of both events
+	(mbm_total_bytes as well as mbm_local_bytes) are cleared for that
+	domain. The next read for every RMID will report "Unavailable"
+	and subsequent reads will report the valid value.
+
+	Following are the types of events supported:
+
+	====    ========================================================
+	Bits    Description
+	====    ========================================================
+	6       Dirty Victims from the QOS domain to all types of memory
+	5       Reads to slow memory in the non-local NUMA domain
+	4       Reads to slow memory in the local NUMA domain
+	3       Non-temporal writes to non-local NUMA domain
+	2       Non-temporal writes to local NUMA domain
+	1       Reads to memory in the non-local NUMA domain
+	0       Reads to memory in the local NUMA domain
+	====    ========================================================
+
+	By default, the mbm_total_bytes configuration is set to 0x7f to count
+	all the event types and the mbm_local_bytes configuration is set to
+	0x15 to count all the local memory events.
+
+	Examples:
+
+	* To view the current configuration::
+	  ::
+
+	    # cat /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config
+	    0=0x7f;1=0x7f;2=0x7f;3=0x7f
+
+	    # cat /sys/fs/resctrl/info/L3_MON/mbm_local_bytes_config
+	    0=0x15;1=0x15;3=0x15;4=0x15
+
+	* To change the mbm_total_bytes to count only reads on domain 0,
+	  the bits 0, 1, 4 and 5 needs to be set, which is 110011b in binary
+	  (in hexadecimal 0x33):
+	  ::
+
+	    # echo  "0=0x33" > /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config
+
+	    # cat /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config
+	    0=0x33;1=0x7f;2=0x7f;3=0x7f
+
+	* To change the mbm_local_bytes to count all the slow memory reads on
+	  domain 0 and 1, the bits 4 and 5 needs to be set, which is 110000b
+	  in binary (in hexadecimal 0x30):
+	  ::
+
+	    # echo  "0=0x30;1=0x30" > /sys/fs/resctrl/info/L3_MON/mbm_local_bytes_config
+
+	    # cat /sys/fs/resctrl/info/L3_MON/mbm_local_bytes_config
+	    0=0x30;1=0x30;3=0x15;4=0x15
 
 "max_threshold_occupancy":
 		Read/write file provides the largest value (in
@@ -464,6 +548,25 @@ Memory bandwidth domain is L3 cache.
 
 	MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
 
+Slow Memory Bandwidth Allocation (SMBA)
+---------------------------------------
+AMD hardware supports Slow Memory Bandwidth Allocation (SMBA).
+CXL.memory is the only supported "slow" memory device. With the
+support of SMBA, the hardware enables bandwidth allocation on
+the slow memory devices. If there are multiple such devices in
+the system, the throttling logic groups all the slow sources
+together and applies the limit on them as a whole.
+
+The presence of SMBA (with CXL.memory) is independent of slow memory
+devices presence. If there are no such devices on the system, then
+configuring SMBA will have no impact on the performance of the system.
+
+The bandwidth domain for slow memory is L3 cache. Its schemata file
+is formatted as:
+::
+
+	SMBA:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
+
 Reading/writing the schemata file
 ---------------------------------
 Reading the schemata file will show the state of all resources
@@ -479,6 +582,46 @@ which you wish to change.  E.g.
   L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
   L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 
+Reading/writing the schemata file (on AMD systems)
+--------------------------------------------------
+Reading the schemata file will show the current bandwidth limit on all
+domains. The allocated resources are in multiples of one eighth GB/s.
+When writing to the file, you need to specify what cache id you wish to
+configure the bandwidth limit.
+
+For example, to allocate 2GB/s limit on the first cache id:
+
+::
+
+  # cat schemata
+    MB:0=2048;1=2048;2=2048;3=2048
+    L3:0=ffff;1=ffff;2=ffff;3=ffff
+
+  # echo "MB:1=16" > schemata
+  # cat schemata
+    MB:0=2048;1=  16;2=2048;3=2048
+    L3:0=ffff;1=ffff;2=ffff;3=ffff
+
+Reading/writing the schemata file (on AMD systems) with SMBA feature
+--------------------------------------------------------------------
+Reading and writing the schemata file is the same as without SMBA in
+above section.
+
+For example, to allocate 8GB/s limit on the first cache id:
+
+::
+
+  # cat schemata
+    SMBA:0=2048;1=2048;2=2048;3=2048
+      MB:0=2048;1=2048;2=2048;3=2048
+      L3:0=ffff;1=ffff;2=ffff;3=ffff
+
+  # echo "SMBA:1=64" > schemata
+  # cat schemata
+    SMBA:0=2048;1=  64;2=2048;3=2048
+      MB:0=2048;1=2048;2=2048;3=2048
+      L3:0=ffff;1=ffff;2=ffff;3=ffff
+
 Cache Pseudo-Locking
 ====================
 CAT enables a user to specify the amount of cache space that an

arch/x86/include/asm/cpufeatures.h

@@ -307,6 +307,8 @@
 #define X86_FEATURE_SGX_EDECCSSA	(11*32+18) /* "" SGX EDECCSSA user leaf function */
 #define X86_FEATURE_CALL_DEPTH		(11*32+19) /* "" Call depth tracking for RSB stuffing */
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
+#define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */

arch/x86/include/asm/msr-index.h

@@ -1084,6 +1084,8 @@
 
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
+#define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
 /* MSR_IA32_VMX_MISC bits */
 #define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)

arch/x86/kernel/cpu/cpuid-deps.c

@@ -68,6 +68,8 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_OCCUP_LLC,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_CQM_MBM_TOTAL,		X86_FEATURE_CQM_LLC   },
 	{ 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_AVX512_BF16,		X86_FEATURE_AVX512VL  },
 	{ X86_FEATURE_AVX512_FP16,		X86_FEATURE_AVX512BW  },
 	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },

arch/x86/kernel/cpu/resctrl/core.c

@@ -100,6 +100,18 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.fflags			= RFTYPE_RES_MB,
 		},
 	},
+	[RDT_RESOURCE_SMBA] =
+	{
+		.r_resctrl = {
+			.rid			= RDT_RESOURCE_SMBA,
+			.name			= "SMBA",
+			.cache_level		= 3,
+			.domains		= domain_init(RDT_RESOURCE_SMBA),
+			.parse_ctrlval		= parse_bw,
+			.format_str		= "%d=%*u",
+			.fflags			= RFTYPE_RES_MB,
+		},
+	},
 };
 
 /*
@@ -150,6 +162,13 @@ bool is_mba_sc(struct rdt_resource *r)
 	if (!r)
 		return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc;
 
+	/*
+	 * The software controller support is only applicable to MBA resource.
+	 * Make sure to check for resource type.
+	 */
+	if (r->rid != RDT_RESOURCE_MBA)
+		return false;
+
 	return r->membw.mba_sc;
 }
 
@@ -213,9 +232,15 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	union cpuid_0x10_3_eax eax;
 	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx;
+	u32 ebx, ecx, subleaf;
+
+	/*
+	 * Query CPUID_Fn80000020_EDX_x01 for MBA and
+	 * CPUID_Fn80000020_EDX_x02 for SMBA
+	 */
+	subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 :  1;
 
-	cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
+	cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full);
 	hw_res->num_closid = edx.split.cos_max + 1;
 	r->default_ctrl = MAX_MBA_BW_AMD;
 
@@ -647,6 +672,8 @@ enum {
 	RDT_FLAG_L2_CAT,
 	RDT_FLAG_L2_CDP,
 	RDT_FLAG_MBA,
+	RDT_FLAG_SMBA,
+	RDT_FLAG_BMEC,
 };
 
 #define RDT_OPT(idx, n, f)	\
@@ -670,6 +697,8 @@ static struct rdt_options rdt_options[]  __initdata = {
 	RDT_OPT(RDT_FLAG_L2_CAT,    "l2cat",	X86_FEATURE_CAT_L2),
 	RDT_OPT(RDT_FLAG_L2_CDP,    "l2cdp",	X86_FEATURE_CDP_L2),
 	RDT_OPT(RDT_FLAG_MBA,	    "mba",	X86_FEATURE_MBA),
+	RDT_OPT(RDT_FLAG_SMBA,	    "smba",	X86_FEATURE_SMBA),
+	RDT_OPT(RDT_FLAG_BMEC,	    "bmec",	X86_FEATURE_BMEC),
 };
 #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
 
@@ -699,7 +728,7 @@ static int __init set_rdt_options(char *str)
 }
 __setup("rdt", set_rdt_options);
 
-static bool __init rdt_cpu_has(int flag)
+bool __init rdt_cpu_has(int flag)
 {
 	bool ret = boot_cpu_has(flag);
 	struct rdt_options *o;
@@ -734,6 +763,19 @@ static __init bool get_mem_config(void)
 	return false;
 }
 
+static __init bool get_slow_mem_config(void)
+{
+	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_SMBA];
+
+	if (!rdt_cpu_has(X86_FEATURE_SMBA))
+		return false;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return __rdt_get_mem_config_amd(&hw_res->r_resctrl);
+
+	return false;
+}
+
 static __init bool get_rdt_alloc_resources(void)
 {
 	struct rdt_resource *r;
@@ -764,6 +806,9 @@ static __init bool get_rdt_alloc_resources(void)
 	if (get_mem_config())
 		ret = true;
 
+	if (get_slow_mem_config())
+		ret = true;
+
 	return ret;
 }
 
@@ -853,6 +898,9 @@ static __init void rdt_init_res_defs_amd(void)
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
 			hw_res->msr_update = mba_wrmsr_amd;
+		} else if (r->rid == RDT_RESOURCE_SMBA) {
+			hw_res->msr_base = MSR_IA32_SMBA_BW_BASE;
+			hw_res->msr_update = mba_wrmsr_amd;
 		}
 	}
 }

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -209,7 +209,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	unsigned long dom_id;
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
-	    r->rid == RDT_RESOURCE_MBA) {
+	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
 		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
 		return -EINVAL;
 	}
@@ -310,7 +310,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	enum resctrl_conf_type t;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
-	int cpu;
 	u32 idx;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -341,13 +340,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
 	if (cpumask_empty(cpu_mask))
 		goto done;
-	cpu = get_cpu();
-	/* Update resource control msr on this CPU if it's in cpu_mask. */
-	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_ctrl_update(&msr_param);
-	/* Update resource control msr on other CPUs. */
-	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-	put_cpu();
+
+	/* Update resource control msr on all the CPUs. */
+	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 
 done:
 	free_cpumask_var(cpu_mask);