20 files changed, 2320 insertions, 25 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 498741737055..2a4a423d08e0 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -272,6 +272,22 @@ Description:	Parameters for the CPU cache attributes
 				     the modified cache line is written to main
 				     memory only when it is replaced
 
+
+What:		/sys/devices/system/cpu/cpu*/cache/index*/id
+Date:		September 2016
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Cache id
+
+		The id provides a unique number for a specific instance of
+		a cache of a particular type. E.g. there may be a level
+		3 unified cache on each socket in a server and we may
+		assign them ids 0, 1, 2, ...
+
+		Note that id value can be non-contiguous. E.g. level 1
+		caches typically exist per core, but there may not be a
+		power of two cores on a socket, so these caches may be
+		numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ...
+
 What:		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats
 		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat
 		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
new file mode 100644
index 000000000000..d918d268cd72
--- /dev/null
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -0,0 +1,214 @@
+User Interface for Resource Allocation in Intel Resource Director Technology
+
+Copyright (C) 2016 Intel Corporation
+
+Fenghua Yu <fenghua.yu@intel.com>
+Tony Luck <tony.luck@intel.com>
+
+This feature is enabled by the CONFIG_INTEL_RDT_A Kconfig and the
+X86 /proc/cpuinfo flag bits "rdt", "cat_l3" and "cdp_l3".
+
+To use the feature mount the file system:
+
+ # mount -t resctrl resctrl [-o cdp] /sys/fs/resctrl
+
+mount options are:
+
+"cdp": Enable code/data prioritization in L3 cache allocations.
+
+
+Info directory
+--------------
+
+The 'info' directory contains information about the enabled
+resources. Each resource has its own subdirectory. The subdirectory
+names reflect the resource names. Each subdirectory contains the
+following files:
+
+"num_closids":  The number of CLOSIDs which are valid for this
+	        resource. The kernel uses the smallest number of
+		CLOSIDs of all enabled resources as limit.
+
+"cbm_mask":     The bitmask which is valid for this resource. This
+		mask is equivalent to 100%.
+
+"min_cbm_bits": The minimum number of consecutive bits which must be
+		set when writing a mask.
+
+
+Resource groups
+---------------
+Resource groups are represented as directories in the resctrl file
+system. The default group is the root directory. Other groups may be
+created as desired by the system administrator using the "mkdir(1)"
+command, and removed using "rmdir(1)".
+
+There are three files associated with each group:
+
+"tasks": A list of tasks that belongs to this group. Tasks can be
+	added to a group by writing the task ID to the "tasks" file
+	(which will automatically remove them from the previous
+	group to which they belonged). New tasks created by fork(2)
+	and clone(2) are added to the same group as their parent.
+	If a pid is not in any sub partition, it is in root partition
+	(i.e. default partition).
+
+"cpus": A bitmask of logical CPUs assigned to this group. Writing
+	a new mask can add/remove CPUs from this group. Added CPUs
+	are removed from their previous group. Removed ones are
+	given to the default (root) group. You cannot remove CPUs
+	from the default group.
+
+"schemata": A list of all the resources available to this group.
+	Each resource has its own line and format - see below for
+	details.
+
+When a task is running the following rules define which resources
+are available to it:
+
+1) If the task is a member of a non-default group, then the schemata
+for that group is used.
+
+2) Else if the task belongs to the default group, but is running on a
+CPU that is assigned to some specific group, then the schemata for
+the CPU's group is used.
+
+3) Otherwise the schemata for the default group is used.
+
+
+Schemata files - general concepts
+---------------------------------
+Each line in the file describes one resource. The line starts with
+the name of the resource, followed by specific values to be applied
+in each of the instances of that resource on the system.
+
+Cache IDs
+---------
+On current generation systems there is one L3 cache per socket and L2
+caches are generally just shared by the hyperthreads on a core, but this
+isn't an architectural requirement. We could have multiple separate L3
+caches on a socket, multiple cores could share an L2 cache. So instead
+of using "socket" or "core" to define the set of logical cpus sharing
+a resource we use a "Cache ID". At a given cache level this will be a
+unique number across the whole system (but it isn't guaranteed to be a
+contiguous sequence, there may be gaps).  To find the ID for each logical
+CPU look in /sys/devices/system/cpu/cpu*/cache/index*/id
+
+Cache Bit Masks (CBM)
+---------------------
+For cache resources we describe the portion of the cache that is available
+for allocation using a bitmask. The maximum value of the mask is defined
+by each cpu model (and may be different for different cache levels). It
+is found using CPUID, but is also provided in the "info" directory of
+the resctrl file system in "info/{resource}/cbm_mask". X86 hardware
+requires that these masks have all the '1' bits in a contiguous block. So
+0x3, 0x6 and 0xC are legal 4-bit masks with two bits set, but 0x5, 0x9
+and 0xA are not.  On a system with a 20-bit mask each bit represents 5%
+of the capacity of the cache. You could partition the cache into four
+equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
+
+
+L3 details (code and data prioritization disabled)
+--------------------------------------------------
+With CDP disabled the L3 schemata format is:
+
+	L3:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+L3 details (CDP enabled via mount option to resctrl)
+----------------------------------------------------
+When CDP is enabled L3 control is split into two separate resources
+so you can specify independent masks for code and data like this:
+
+	L3data:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+	L3code:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+L2 details
+----------
+L2 cache does not support code and data prioritization, so the
+schemata format is always:
+
+	L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+Example 1
+---------
+On a two socket machine (one L3 cache per socket) with just four bits
+for cache bit masks
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+# mkdir p0 p1
+# echo "L3:0=3;1=c" > /sys/fs/resctrl/p0/schemata
+# echo "L3:0=3;1=3" > /sys/fs/resctrl/p1/schemata
+
+The default resource group is unmodified, so we have access to all parts
+of all caches (its schemata file reads "L3:0=f;1=f").
+
+Tasks that are under the control of group "p0" may only allocate from the
+"lower" 50% on cache ID 0, and the "upper" 50% of cache ID 1.
+Tasks in group "p1" use the "lower" 50% of cache on both sockets.
+
+Example 2
+---------
+Again two sockets, but this time with a more realistic 20-bit mask.
+
+Two real time tasks pid=1234 running on processor 0 and pid=5678 running on
+processor 1 on socket 0 on a 2-socket and dual core machine. To avoid noisy
+neighbors, each of the two real-time tasks exclusively occupies one quarter
+of L3 cache on socket 0.
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+
+First we reset the schemata for the default group so that the "upper"
+50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+
+# echo "L3:0=3ff;1=fffff" > schemata
+
+Next we make a resource group for our first real time task and give
+it access to the "top" 25% of the cache on socket 0.
+
+# mkdir p0
+# echo "L3:0=f8000;1=fffff" > p0/schemata
+
+Finally we move our first real time task into this resource group. We
+also use taskset(1) to ensure the task always runs on a dedicated CPU
+on socket 0. Most uses of resource groups will also constrain which
+processors tasks run on.
+
+# echo 1234 > p0/tasks
+# taskset -cp 1 1234
+
+Ditto for the second real time task (with the remaining 25% of cache):
+
+# mkdir p1
+# echo "L3:0=7c00;1=fffff" > p1/schemata
+# echo 5678 > p1/tasks
+# taskset -cp 2 5678
+
+Example 3
+---------
+
+A single socket system which has real-time tasks running on core 4-7 and
+non real-time workload assigned to core 0-3. The real-time tasks share text
+and data, so a per task association is not required and due to interaction
+with the kernel it's desired that the kernel on these cores shares L3 with
+the tasks.
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+
+First we reset the schemata for the default group so that the "upper"
+50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+
+# echo "L3:0=3ff" > schemata
+
+Next we make a resource group for our real time cores and give
+it access to the "top" 50% of the cache on socket 0.
+
+# mkdir p0
+# echo "L3:0=ffc00;" > p0/schemata
+
+Finally we move core 4-7 over to the new group and make sure that the
+kernel and the tasks running there get 50% of the cache.
+
+# echo C0 > p0/cpus
diff --git a/MAINTAINERS b/MAINTAINERS
index f6eb97b35e0f..7c21c7638bb5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10327,6 +10327,14 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
+RDT - RESOURCE ALLOCATION
+M:	Fenghua Yu <fenghua.yu@intel.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	arch/x86/kernel/cpu/intel_rdt*
+F:	arch/x86/include/asm/intel_rdt*
+F:	Documentation/x86/intel_rdt*
+
 READ-COPY UPDATE (RCU)
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 64024c999531..e487493bbd47 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -412,6 +412,19 @@ config GOLDFISH
        def_bool y
        depends on X86_GOLDFISH
 
+config INTEL_RDT_A
+	bool "Intel Resource Director Technology Allocation support"
+	default n
+	depends on X86 && CPU_SUP_INTEL
+	select KERNFS
+	help
+	  Select to enable resource allocation which is a sub-feature of
+	  Intel Resource Director Technology(RDT). More information about
+	  RDT can be found in the Intel x86 Architecture Software
+	  Developer Manual.
+
+	  Say N if unsure.
+
 if X86_32
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8f82b02934fa..0c45cc8e64ba 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,9 +7,9 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel_rdt_common.h>
 #include "../perf_event.h"
 
-#define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
@@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 static bool cqm_enabled, mbm_enabled;
 unsigned int mbm_socket_max;
 
-/**
- * struct intel_pqr_state - State cache for the PQR MSR
- * @rmid:		The cached Resource Monitoring ID
- * @closid:		The cached Class Of Service ID
- * @rmid_usecnt:	The usage counter for rmid
- *
- * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
- * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
- * contains both parts, so we need to cache them.
- *
- * The cache also helps to avoid pointless updates if the value does
- * not change.
- */
-struct intel_pqr_state {
-	u32			rmid;
-	u32			closid;
-	int			rmid_usecnt;
-};
-
 /*
  * The cached intel_pqr_state is strictly per CPU and can never be
  * updated from a remote CPU. Both functions which modify the state
  * (intel_cqm_event_start and intel_cqm_event_stop) are called with
  * interrupts disabled, which is sufficient for the protection.
  */
-static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 static struct hrtimer *mbm_timers;
 /**
  * struct sample - mbm event's (local or total) data
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6ccbf1aaa7ce..eafee3161d1c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -189,6 +189,9 @@
 
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
 
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
@@ -222,6 +225,7 @@
 #define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
 #define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
 #define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
new file mode 100644
index 000000000000..95ce5c85b009
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -0,0 +1,224 @@
+#ifndef _ASM_X86_INTEL_RDT_H
+#define _ASM_X86_INTEL_RDT_H
+
+#ifdef CONFIG_INTEL_RDT_A
+
+#include <linux/kernfs.h>
+#include <linux/jump_label.h>
+
+#include <asm/intel_rdt_common.h>
+
+#define IA32_L3_QOS_CFG		0xc81
+#define IA32_L3_CBM_BASE	0xc90
+#define IA32_L2_CBM_BASE	0xd10
+
+#define L3_QOS_CDP_ENABLE	0x01ULL
+
+/**
+ * struct rdtgroup - store rdtgroup's data in resctrl file system.
+ * @kn:				kernfs node
+ * @rdtgroup_list:		linked list for all rdtgroups
+ * @closid:			closid for this rdtgroup
+ * @cpu_mask:			CPUs assigned to this rdtgroup
+ * @flags:			status bits
+ * @waitcount:			how many cpus expect to find this
+ *				group when they acquire rdtgroup_mutex
+ */
+struct rdtgroup {
+	struct kernfs_node	*kn;
+	struct list_head	rdtgroup_list;
+	int			closid;
+	struct cpumask		cpu_mask;
+	int			flags;
+	atomic_t		waitcount;
+};
+
+/* rdtgroup.flags */
+#define	RDT_DELETED		1
+
+/* List of all resource groups */
+extern struct list_head rdt_all_groups;
+
+int __init rdtgroup_init(void);
+
+/**
+ * struct rftype - describe each file in the resctrl file system
+ * @name: file name
+ * @mode: access mode
+ * @kf_ops: operations
+ * @seq_show: show content of the file
+ * @write: write to the file
+ */
+struct rftype {
+	char			*name;
+	umode_t			mode;
+	struct kernfs_ops	*kf_ops;
+
+	int (*seq_show)(struct kernfs_open_file *of,
+			struct seq_file *sf, void *v);
+	/*
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
+};
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @enabled:			Is this feature enabled on this machine
+ * @capable:			Is this feature available on this machine
+ * @name:			Name to use in "schemata" file
+ * @num_closid:			Number of CLOSIDs available
+ * @max_cbm:			Largest Cache Bit Mask allowed
+ * @min_cbm_bits:		Minimum number of consecutive bits to be set
+ *				in a cache bit mask
+ * @domains:			All domains for this resource
+ * @num_domains:		Number of domains active
+ * @msr_base:			Base MSR address for CBMs
+ * @tmp_cbms:			Scratch space when updating schemata
+ * @num_tmp_cbms:		Number of CBMs in tmp_cbms
+ * @cache_level:		Which cache level defines scope of this domain
+ * @cbm_idx_multi:		Multiplier of CBM index
+ * @cbm_idx_offset:		Offset of CBM index. CBM index is computed by:
+ *				closid * cbm_idx_multi + cbm_idx_offset
+ */
+struct rdt_resource {
+	bool			enabled;
+	bool			capable;
+	char			*name;
+	int			num_closid;
+	int			cbm_len;
+	int			min_cbm_bits;
+	u32			max_cbm;
+	struct list_head	domains;
+	int			num_domains;
+	int			msr_base;
+	u32			*tmp_cbms;
+	int			num_tmp_cbms;
+	int			cache_level;
+	int			cbm_idx_multi;
+	int			cbm_idx_offset;
+};
+
+/**
+ * struct rdt_domain - group of cpus sharing an RDT resource
+ * @list:	all instances of this resource
+ * @id:		unique id for this instance
+ * @cpu_mask:	which cpus share this resource
+ * @cbm:	array of cache bit masks (indexed by CLOSID)
+ */
+struct rdt_domain {
+	struct list_head	list;
+	int			id;
+	struct cpumask		cpu_mask;
+	u32			*cbm;
+};
+
+/**
+ * struct msr_param - set a range of MSRs from a domain
+ * @res:       The resource to use
+ * @low:       Beginning index from base MSR
+ * @high:      End index
+ */
+struct msr_param {
+	struct rdt_resource	*res;
+	int			low;
+	int			high;
+};
+
+extern struct mutex rdtgroup_mutex;
+
+extern struct rdt_resource rdt_resources_all[];
+extern struct rdtgroup rdtgroup_default;
+DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+
+int __init rdtgroup_init(void);
+
+enum {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L3DATA,
+	RDT_RESOURCE_L3CODE,
+	RDT_RESOURCE_L2,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
+#define for_each_capable_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++) 							      \
+		if (r->capable)
+
+#define for_each_enabled_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->enabled)
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
+union cpuid_0x10_1_eax {
+	struct {
+		unsigned int cbm_len:5;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
+union cpuid_0x10_1_edx {
+	struct {
+		unsigned int cos_max:16;
+	} split;
+	unsigned int full;
+};
+
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
+void rdt_cbm_update(void *arg);
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
+void rdtgroup_kn_unlock(struct kernfs_node *kn);
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off);
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v);
+
+/*
+ * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR
+ *
+ * Following considerations are made so that this has minimal impact
+ * on scheduler hot path:
+ * - This will stay as no-op unless we are running on an Intel SKU
+ *   which supports resource control and we enable by mounting the
+ *   resctrl file system.
+ * - Caches the per cpu CLOSid values and does the MSR write only
+ *   when a task with a different CLOSid is scheduled in.
+ *
+ * Must be called with preemption disabled.
+ */
+static inline void intel_rdt_sched_in(void)
+{
+	if (static_branch_likely(&rdt_enable_key)) {
+		struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+		int closid;
+
+		/*
+		 * If this task has a closid assigned, use it.
+		 * Else use the closid assigned to this cpu.
+		 */
+		closid = current->closid;
+		if (closid == 0)
+			closid = this_cpu_read(cpu_closid);
+
+		if (closid != state->closid) {
+			state->closid = closid;
+			wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, closid);
+		}
+	}
+}
+
+#else
+
+static inline void intel_rdt_sched_in(void) {}
+
+#endif /* CONFIG_INTEL_RDT_A */
+#endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h
new file mode 100644
index 000000000000..b31081b89407
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt_common.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_X86_INTEL_RDT_COMMON_H
+#define _ASM_X86_INTEL_RDT_COMMON_H
+
+#define MSR_IA32_PQR_ASSOC	0x0c8f
+
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
+};
+
+DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);
+
+#endif /* _ASM_X86_INTEL_RDT_COMMON_H */
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 33b63670bf09..52000010c62e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,6 +32,8 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
+obj-$(CONFIG_INTEL_RDT_A)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o
+
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index be6337156502..0282b0df004a 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -153,6 +153,7 @@ struct _cpuid4_info_regs {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
+	unsigned int id;
 	unsigned long size;
 	struct amd_northbridge *nb;
 };
@@ -894,6 +895,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 static void ci_leaf_init(struct cacheinfo *this_leaf,
 			 struct _cpuid4_info_regs *base)
 {
+	this_leaf->id = base->id;
+	this_leaf->attributes = CACHE_ID;
 	this_leaf->level = base->eax.split.level;
 	this_leaf->type = cache_type_map[base->eax.split.type];
 	this_leaf->coherency_line_size =
@@ -920,6 +923,22 @@ static int __init_cache_level(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * ECX as cache index. Then right shift apicid by the number's order to get
+ * cache id for this cache node.
+ */
+static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	unsigned long num_threads_sharing;
+	int index_msb;
+
+	num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+	index_msb = get_count_order(num_threads_sharing);
+	id4_regs->id = c->apicid >> index_msb;
+}
+
 static int __populate_cache_leaves(unsigned int cpu)
 {
 	unsigned int idx, ret;
@@ -931,6 +950,7 @@ static int __populate_cache_leaves(unsigned int cpu)
 		ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
 		if (ret)
 			return ret;
+		get_cache_id(cpu, &id4_regs);
 		ci_leaf_init(this_leaf++, &id4_regs);
 		__cache_cpumap_setup(cpu, idx, &id4_regs);
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
new file mode 100644
index 000000000000..5a533fefefa0
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -0,0 +1,403 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Cache Allocation code.
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Authors:
+ *    Fenghua Yu <fenghua.yu@intel.com>
+ *    Tony Luck <tony.luck@intel.com>
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpuhotplug.h>
+
+#include <asm/intel-family.h>
+#include <asm/intel_rdt.h>
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
+#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
+
+struct rdt_resource rdt_resources_all[] = {
+	{
+		.name		= "L3",
+		.domains	= domain_init(RDT_RESOURCE_L3),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3DATA",
+		.domains	= domain_init(RDT_RESOURCE_L3DATA),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3CODE",
+		.domains	= domain_init(RDT_RESOURCE_L3CODE),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 1
+	},
+	{
+		.name		= "L2",
+		.domains	= domain_init(RDT_RESOURCE_L2),
+		.msr_base	= IA32_L2_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 2,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+};
+
+static int cbm_idx(struct rdt_resource *r, int closid)
+{
+	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+}
+
+/*
+ * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
+ * as they do not have CPUID enumeration support for Cache allocation.
+ * The check for Vendor/Family/Model is not enough to guarantee that
+ * the MSRs won't #GP fault because only the following SKUs support
+ * CAT:
+ *	Intel(R) Xeon(R)  CPU E5-2658  v3  @  2.20GHz
+ *	Intel(R) Xeon(R)  CPU E5-2648L v3  @  1.80GHz
+ *	Intel(R) Xeon(R)  CPU E5-2628L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2618L v3  @  2.30GHz
+ *	Intel(R) Xeon(R)  CPU E5-2608L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2658A v3  @  2.20GHz
+ *
+ * Probe by trying to write the first of the L3 cach mask registers
+ * and checking that the bits stick. Max CLOSids is always 4 and max cbm length
+ * is always 20 on hsw server parts. The minimum cache bitmask length
+ * allowed for HSW server is always 2 bits. Hardcode all of them.
+ */
+static inline bool cache_alloc_hsw_probe(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6 &&
+	    boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) {
+		struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
+		u32 l, h, max_cbm = BIT_MASK(20) - 1;
+
+		if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
+			return false;
+		rdmsr(IA32_L3_CBM_BASE, l, h);
+
+		/* If all the bits were set in MSR, return success */
+		if (l != max_cbm)
+			return false;
+
+		r->num_closid = 4;
+		r->cbm_len = 20;
+		r->max_cbm = max_cbm;
+		r->min_cbm_bits = 2;
+		r->capable = true;
+		r->enabled = true;
+
+		return true;
+	}
+
+	return false;
+}
+
+static void rdt_get_config(int idx, struct rdt_resource *r)
+{
+	union cpuid_0x10_1_eax eax;
+	union cpuid_0x10_1_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->cbm_len = eax.split.cbm_len + 1;
+	r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->capable = true;
+	r->enabled = true;
+}
+
+static void rdt_get_cdp_l3_config(int type)
+{
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r = &rdt_resources_all[type];
+
+	r->num_closid = r_l3->num_closid / 2;
+	r->cbm_len = r_l3->cbm_len;
+	r->max_cbm = r_l3->max_cbm;
+	r->capable = true;
+	/*
+	 * By default, CDP is disabled. CDP can be enabled by mount parameter
+	 * "cdp" during resctrl file system mount time.
+	 */
+	r->enabled = false;
+}
+
+static inline bool get_rdt_resources(void)
+{
+	bool ret = false;
+
+	if (cache_alloc_hsw_probe())
+		return true;
+
+	if (!boot_cpu_has(X86_FEATURE_RDT_A))
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
+		}
+		ret = true;
+	}
+	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+		/* CPUID 0x10.2 fields are same format at 0x10.1 */
+		rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		ret = true;
+	}
+
+	return ret;
+}
+
+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;
+}
+
+void rdt_cbm_update(void *arg)
+{
+	struct msr_param *m = (struct msr_param *)arg;
+	struct rdt_resource *r = m->res;
+	int i, cpu = smp_processor_id();
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+			goto found;
+	}
+	pr_info_once("cpu %d not found in any domain for resource %s\n",
+		     cpu, r->name);
+
+	return;
+
+found:
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+}