Merge tag 'x86_cache_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cache resource control updates from Borislav Petkov:

 - Misc cleanups to the resctrl code in preparation for the ARM side
   (James Morse)

 - Add support for controlling per-thread memory bandwidth throttling
   delay values on hw which supports it (Fenghua Yu)

* tag 'x86_cache_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Enable user to view thread or core throttling mode
  x86/resctrl: Enumerate per-thread MBA controls
  cacheinfo: Move resctrl's get_cache_id() to the cacheinfo header file
  x86/resctrl: Add struct rdt_cache::arch_has_{sparse, empty}_bitmaps
  x86/resctrl: Merge AMD/Intel parse_bw() calls
  x86/resctrl: Add struct rdt_membw::arch_needs_linear to explain AMD/Intel MBA difference
  x86/resctrl: Use is_closid_match() in more places
  x86/resctrl: Include pid.h
  x86/resctrl: Use container_of() in delayed_work handlers
  x86/resctrl: Fix stale comment
  x86/resctrl: Remove struct rdt_membw::max_delay
  x86/resctrl: Remove unused struct mbm_state::chunks_bw

11 files changed, 185 insertions, 157 deletions

diff --git a/Documentation/x86/resctrl_ui.rst b/Documentation/x86/resctrl_ui.rst
index 5368cedfb5309d..e59b7b93a9b49b 100644
--- a/Documentation/x86/resctrl_ui.rst
+++ b/Documentation/x86/resctrl_ui.rst
@@ -138,6 +138,18 @@ with respect to allocation:
 		non-linear. This field is purely informational
 		only.
 
+"thread_throttle_mode":
+		Indicator on Intel systems of how tasks running on threads
+		of a physical core are throttled in cases where they
+		request different memory bandwidth percentages:
+
+		"max":
+			the smallest percentage is applied
+			to all threads
+		"per-thread":
+			bandwidth percentages are directly applied to
+			the threads running on the core
+
 If RDT monitoring is available there will be an "L3_MON" directory
 with the following files:
 
@@ -364,8 +376,10 @@ to the next control step available on the hardware.
 
 The bandwidth throttling is a core specific mechanism on some of Intel
 SKUs. Using a high bandwidth and a low bandwidth setting on two threads
-sharing a core will result in both threads being throttled to use the
-low bandwidth. The fact that Memory bandwidth allocation(MBA) is a core
+sharing a core may result in both threads being throttled to use the
+low bandwidth (see "thread_throttle_mode").
+
+The fact that Memory bandwidth allocation(MBA) may be a core
 specific mechanism where as memory bandwidth monitoring(MBM) is done at
 the package level may lead to confusion when users try to apply control
 via the MBA and then monitor the bandwidth to see if the controls are
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a48458b04e1eab..7b0afd5e6c57ad 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -288,6 +288,7 @@
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
 #define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 3a02707c1f4d0b..d502241995a39d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -70,6 +70,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_MBM_LOCAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_AVX512_BF16,		X86_FEATURE_AVX512VL  },
 	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },
+	{ X86_FEATURE_PER_THREAD_MBA,		X86_FEATURE_MBA       },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 9cceee61256976..e5f4ee8f4c3bbd 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -168,6 +168,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
 		.cache_level		= 3,
+		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
@@ -254,22 +255,30 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 {
 	union cpuid_0x10_3_eax eax;
 	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx;
+	u32 ebx, ecx, max_delay;
 
 	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
 	r->num_closid = edx.split.cos_max + 1;
-	r->membw.max_delay = eax.split.max_delay + 1;
+	max_delay = eax.split.max_delay + 1;
 	r->default_ctrl = MAX_MBA_BW;
+	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
-		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
-		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+		r->membw.min_bw = MAX_MBA_BW - max_delay;
+		r->membw.bw_gran = MAX_MBA_BW - max_delay;
 	} else {
 		if (!rdt_get_mb_table(r))
 			return false;
+		r->membw.arch_needs_linear = false;
 	}
 	r->data_width = 3;
 
+	if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA))
+		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
+	else
+		r->membw.throttle_mode = THREAD_THROTTLE_MAX;
+	thread_throttle_mode_init();
+
 	r->alloc_capable = true;
 	r->alloc_enabled = true;
 
@@ -288,7 +297,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
+	r->membw.arch_needs_linear = false;
 
+	/*
+	 * AMD does not use memory delay throttle model to control
+	 * the allocation like Intel does.
+	 */
+	r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED;
 	r->membw.min_bw = 0;
 	r->membw.bw_gran = 1;
 	/* Max value is 2048, Data width should be 4 in decimal */
@@ -346,19 +361,6 @@ static void rdt_get_cdp_l2_config(void)
 	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
 }
 
-static int get_cache_id(int cpu, int level)
-{
-	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
-	int i;
-
-	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == level)
-			return ci->info_list[i].id;
-	}
-
-	return -1;
-}
-
 static void
 mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
 {
@@ -556,7 +558,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -602,7 +604,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct rdt_domain *d;
 
 	d = rdt_find_domain(r, id, NULL);
@@ -918,12 +920,12 @@ static __init void rdt_init_res_defs_intel(void)
 		    r->rid == RDT_RESOURCE_L3CODE ||
 		    r->rid == RDT_RESOURCE_L2 ||
 		    r->rid == RDT_RESOURCE_L2DATA ||
-		    r->rid == RDT_RESOURCE_L2CODE)
-			r->cbm_validate = cbm_validate_intel;
-		else if (r->rid == RDT_RESOURCE_MBA) {
+		    r->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = false;
+			r->cache.arch_has_empty_bitmaps = false;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
-			r->parse_ctrlval = parse_bw_intel;
 		}
 	}
 }
@@ -938,12 +940,12 @@ static __init void rdt_init_res_defs_amd(void)
 		    r->rid == RDT_RESOURCE_L3CODE ||
 		    r->rid == RDT_RESOURCE_L2 ||
 		    r->rid == RDT_RESOURCE_L2DATA ||
-		    r->rid == RDT_RESOURCE_L2CODE)
-			r->cbm_validate = cbm_validate_amd;
-		else if (r->rid == RDT_RESOURCE_MBA) {
+		    r->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = true;
+			r->cache.arch_has_empty_bitmaps = true;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
-			r->parse_ctrlval = parse_bw_amd;
 		}
 	}
 }
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 934c8fb8a64a7d..c877642e8a1475 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -23,53 +23,6 @@
 
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and maximum bandwidth values specified by
- * the hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate_amd(char *buf, unsigned long *data,
-			    struct rdt_resource *r)
-{
-	unsigned long bw;
-	int ret;
-
-	ret = kstrtoul(buf, 10, &bw);
-	if (ret) {
-		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
-		return false;
-	}
-
-	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
-		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
-				    r->membw.min_bw, r->default_ctrl);
-		return false;
-	}
-
-	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
-	return true;
-}
-
-int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
-		 struct rdt_domain *d)
-{
-	unsigned long bw_val;
-
-	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
-		return -EINVAL;
-	}
-
-	if (!bw_validate_amd(data->buf, &bw_val, r))
-		return -EINVAL;
-
-	d->new_ctrl = bw_val;
-	d->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
  * checked against the minimum and max bandwidth values specified by the
  * hardware. The allocated bandwidth percentage is rounded to the next
  * control step available on the hardware.
@@ -82,7 +35,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
 	 */
-	if (!r->membw.delay_linear) {
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
 		rdt_last_cmd_puts("No support for non-linear MB domains\n");
 		return false;
 	}
@@ -104,8 +57,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
-		   struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d)
 {
 	unsigned long bw_val;
 
@@ -123,12 +76,14 @@ int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
 }
 
 /*
- * Check whether a cache bit mask is valid. The SDM says:
+ * Check whether a cache bit mask is valid.
+ * For Intel the SDM says:
  *	Please note that all (and only) contiguous '1' combinations
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
+ * AMD allows non-contiguous bitmasks.
  */
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -140,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 		return false;
 	}
 
-	if (val == 0 || val > r->default_ctrl) {
+	if ((!r->cache.arch_has_empty_bitmaps && val == 0) ||
+	    val > r->default_ctrl) {
 		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
 	}
@@ -148,7 +104,9 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+	/* Are non-contiguous bitmaps allowed? */
+	if (!r->cache.arch_has_sparse_bitmaps &&
+	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
 		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
 		return false;
 	}
@@ -164,30 +122,6 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 }
 
 /*
- * Check whether a cache bit mask is valid. AMD allows non-contiguous
- * bitmasks
- */
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret) {
-		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
-		return false;
-	}
-
-	if (val > r->default_ctrl) {
-		rdt_last_cmd_puts("Mask out of range\n");
-		return false;
-	}
-
-	*data = val;
-	return true;
-}
-
-/*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
@@ -212,7 +146,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 		return -EINVAL;
 	}
 
-	if (!r->cbm_validate(data->buf, &cbm_val, r))
+	if (!cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
 	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 5ffa32256b3b26..80fa997fae60e3 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -283,7 +283,6 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
  * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
- * @chunks_bw	Total local data moved. Used for bandwidth calculation
  * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
  * @prev_bw	The most recent bandwidth in MBps
  * @delta_bw	Difference between the current and previous bandwidth
@@ -292,7 +291,6 @@ struct rftype {
 struct mbm_state {
 	u64	chunks;
 	u64	prev_msr;
-	u64	chunks_bw;
 	u64	prev_bw_msr;
 	u32	prev_bw;
 	u32	delta_bw;
@@ -360,6 +358,8 @@ struct msr_param {
  *			in a cache bit mask
  * @shareable_bits:	Bitmask of shareable resource with other
  *			executing entities
+ * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
+ * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
  */
 struct rdt_cache {
 	unsigned int	cbm_len;
@@ -367,25 +367,43 @@ struct rdt_cache {
 	unsigned int	cbm_idx_mult;
 	unsigned int	cbm_idx_offset;
 	unsigned int	shareable_bits;
+	bool		arch_has_sparse_bitmaps;
+	bool		arch_has_empty_bitmaps;
+};
+
+/**
+ * enum membw_throttle_mode - System's memory bandwidth throttling mode
+ * @THREAD_THROTTLE_UNDEFINED:	Not relevant to the system
+ * @THREAD_THROTTLE_MAX:	Memory bandwidth is throttled at the core
+ *				always using smallest bandwidth percentage
+ *				assigned to threads, aka "max throttling"
+ * @THREAD_THROTTLE_PER_THREAD:	Memory bandwidth is throttled at the thread
+ */
+enum membw_throttle_mode {
+	THREAD_THROTTLE_UNDEFINED = 0,
+	THREAD_THROTTLE_MAX,
+	THREAD_THROTTLE_PER_THREAD,
 };
 
 /**
  * struct rdt_membw - Memory bandwidth allocation related data
- * @max_delay:		Max throttle delay. Delay is the hardware
- *			representation for memory bandwidth.
  * @min_bw:		Minimum memory bandwidth percentage user can request
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
  * @delay_linear:	True if memory B/W delay is in linear scale
+ * @arch_needs_linear:	True if we can't configure non-linear resources
+ * @throttle_mode:	Bandwidth throttling mode when threads request
+ *			different memory bandwidths
  * @mba_sc:		True if MBA software controller(mba_sc) is enabled
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
  */
 struct rdt_membw {
-	u32		max_delay;
-	u32		min_bw;
-	u32		bw_gran;
-	u32		delay_linear;
-	bool		mba_sc;
-	u32		*mb_map;
+	u32				min_bw;
+	u32				bw_gran;
+	u32				delay_linear;
+	bool				arch_needs_linear;
+	enum membw_throttle_mode	throttle_mode;
+	bool				mba_sc;
+	u32				*mb_map;
 };
 
 static inline bool is_llc_occupancy_enabled(void)
@@ -437,7 +455,6 @@ struct rdt_parse_data {
  * @cache:		Cache allocation related data
  * @format_str:		Per resource format string to show domain value
  * @parse_ctrlval:	Per resource function pointer to parse control values
- * @cbm_validate	Cache bitmask validate function
  * @evt_list:		List of monitoring events
  * @num_rmid:		Number of RMIDs available
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
@@ -464,7 +481,6 @@ struct rdt_resource {
 	int (*parse_ctrlval)(struct rdt_parse_data *data,
 			     struct rdt_resource *r,
 			     struct rdt_domain *d);
-	bool (*cbm_validate)(char *buf, u32 *data, struct rdt_resource *r);
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
@@ -474,10 +490,8 @@ struct rdt_resource {
 
 int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	      struct rdt_domain *d);
-int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
-		   struct rdt_domain *d);
-int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
-		 struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -609,8 +623,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
 void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
+void __init thread_throttle_mode_init(void);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 837d7d012b7b14..54dffe574e67ac 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -279,8 +279,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 		return;
 
 	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
-	m->chunks_bw += chunks;
-	m->chunks = m->chunks_bw;
+	m->chunks += chunks;
 	cur_bw = (chunks * r->mon_scale) >> 20;
 
 	if (m->delta_comp)
@@ -478,19 +477,13 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3];
-	d = get_domain_from_cpu(cpu, r);
-
-	if (!d) {
-		pr_warn_once("Failure to get domain for limbo worker\n");
-		goto out_unlock;
-	}
+	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
 	if (has_busy_rmid(r, d))
 		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
 
-out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -520,10 +513,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3];
-
-	d = get_domain_from_cpu(cpu, r);
-	if (!d)
-		goto out_unlock;
+	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 3f844f14fc0a63..b494187632b2b1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -592,6 +592,18 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	return ret;
 }
 
+static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (rdt_alloc_capable &&
+	       (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
+}
+
+static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (rdt_mon_capable &&
+	       (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
+}
+
 /**
  * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
  * @r: Resource group
@@ -607,8 +619,7 @@ int rdtgroup_tasks_assigned(struct rdtgroup *r)
 
 	rcu_read_lock();
 	for_each_process_thread(p, t) {
-		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
-		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
 			ret = 1;
 			break;
 		}
@@ -706,8 +717,7 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
 
 	rcu_read_lock();
 	for_each_process_thread(p, t) {
-		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
-		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
+		if (is_closid_match(t, r) || is_rmid_match(t, r))
 			seq_printf(s, "%d\n", t->pid);
 	}
 	rcu_read_unlock();
@@ -1017,6 +1027,19 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
+					 struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
+		seq_puts(seq, "per-thread\n");
+	else
+		seq_puts(seq, "max\n");
+
+	return 0;
+}
+
 static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 				       char *buf, size_t nbytes, loff_t off)
 {
@@ -1513,6 +1536,17 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdt_delay_linear_show,
 		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
 	},
+	/*
+	 * Platform specific which (if any) capabilities are provided by
+	 * thread_throttle_mode. Defer "fflags" initialization to platform
+	 * discovery.
+	 */
+	{
+		.name		= "thread_throttle_mode",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_thread_throttle_mode_show,
+	},
 	{
 		.name		= "max_threshold_occupancy",
 		.mode		= 0644,
@@ -1583,7 +1617,7 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	for (rft = rfts; rft < rfts + len; rft++) {
-		if ((fflags & rft->fflags) == rft->fflags) {
+		if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
 			ret = rdtgroup_add_file(kn, rft);
 			if (ret)
 				goto error;
@@ -1600,6 +1634,33 @@ error:
 	return ret;
 }
 
+static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
+{
+	struct rftype *rfts, *rft;
+	int len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			return rft;
+	}
+
+	return NULL;
+}
+
+void __init thread_throttle_mode_init(void)
+{
+	struct rftype *rft;
+
+	rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
+	if (!rft)
+		return;
+
+	rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
+}
+
 /**
  * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
  * @r: The resource group with which the file is associated.
@@ -2245,18 +2306,6 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	return 0;
 }
 
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (rdt_alloc_capable &&
-		(r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (rdt_mon_capable &&
-		(r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
-}
-
 /*
  * Move tasks from one to the other group. If @from is NULL, then all tasks
  * in the systems are moved unconditionally (used for teardown).
@@ -3196,7 +3245,7 @@ int __init rdtgroup_init(void)
 	 * It may also be ok since that would enable debugging of RDT before
 	 * resctrl is mounted.
 	 * The reason why the debugfs directory is created here and not in
-	 * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
 	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
 	 * (the lockdep class of inode->i_rwsem). Other filesystem
 	 * interactions (eg. SyS_getdents) have the lock ordering:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3221b71a0df836..2eb0a8c44b3522 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -35,6 +35,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
 	{ X86_FEATURE_CDP_L2,		CPUID_ECX,  2, 0x00000010, 2 },
 	{ X86_FEATURE_MBA,		CPUID_EBX,  3, 0x00000010, 0 },
+	{ X86_FEATURE_PER_THREAD_MBA,	CPUID_ECX,  0, 0x00000010, 3 },
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 46b92cd61d0c82..4f72b47973c304 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,6 +3,7 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
@@ -119,4 +120,24 @@ int acpi_find_last_cache_level(unsigned int cpu);
 
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
 
+/*
+ * Get the id of the cache associated with @cpu at level @level.
+ * cpuhp lock must be held.
+ */
+static inline int get_cpu_cacheinfo_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level) {
+			if (ci->info_list[i].attributes & CACHE_ID)
+				return ci->info_list[i].id;
+			return -1;
+		}
+	}
+
+	return -1;
+}
+
 #endif /* _LINUX_CACHEINFO_H */
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index daf5cf64c6a683..9b05af9b3e28d5 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -2,6 +2,8 @@
 #ifndef _RESCTRL_H
 #define _RESCTRL_H
 
+#include <linux/pid.h>
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 int proc_resctrl_show(struct seq_file *m,