Merge branch 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cache allocation interface from Thomas Gleixner:
 "This provides support for Intel's Cache Allocation Technology, a cache
  partitioning mechanism.

  The interface is odd, but the hardware interface of that CAT stuff is
  odd as well.

  We tried hard to come up with an abstraction, but that only allows
  rather simple partitioning, but no way of sharing and dealing with the
  per package nature of this mechanism.

  In the end we decided to expose the allocation bitmaps directly so all
  combinations of the hardware can be utilized.

  There are two ways of associating a cache partition:

   - Task

     A task can be added to a resource group. It uses the cache
     partition associated to the group.

   - CPU

     All tasks which are not member of a resource group use the group to
     which the CPU they are running on is associated with.

     That allows for simple CPU based partitioning schemes.

  The main expected user sare:

   - Virtualization so a VM can only trash only the associated part of
     the cash w/o disturbing others

   - Real-Time systems to seperate RT and general workloads.

   - Latency sensitive enterprise workloads

   - In theory this also can be used to protect against cache side
     channel attacks"

[ Intel RDT is "Resource Director Technology". The interface really is
  rather odd and very specific, which delayed this pull request while I
  was thinking about it. The pull request itself came in early during
  the merge window, I just delayed it until things had calmed down and I
  had more time.

  But people tell me they'll use this, and the good news is that it is
  _so_ specific that it's rather independent of anything else, and no
  user is going to depend on the interface since it's pretty rare. So if
  push comes to shove, we can just remove the interface and nothing will
  break ]

* 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (31 commits)
  x86/intel_rdt: Implement show_options() for resctrlfs
  x86/intel_rdt: Call intel_rdt_sched_in() with preemption disabled
  x86/intel_rdt: Update task closid immediately on CPU in rmdir and unmount
  x86/intel_rdt: Fix setting of closid when adding CPUs to a group
  x86/intel_rdt: Update percpu closid immeditately on CPUs affected by changee
  x86/intel_rdt: Reset per cpu closids on unmount
  x86/intel_rdt: Select KERNFS when enabling INTEL_RDT_A
  x86/intel_rdt: Prevent deadlock against hotplug lock
  x86/intel_rdt: Protect info directory from removal
  x86/intel_rdt: Add info files to Documentation
  x86/intel_rdt: Export the minimum number of set mask bits in sysfs
  x86/intel_rdt: Propagate error in rdt_mount() properly
  x86/intel_rdt: Add a missing #include
  MAINTAINERS: Add maintainer for Intel RDT resource allocation
  x86/intel_rdt: Add scheduler hook
  x86/intel_rdt: Add schemata file
  x86/intel_rdt: Add tasks files
  x86/intel_rdt: Add cpus file
  x86/intel_rdt: Add mkdir to resctrl file system
  x86/intel_rdt: Add "info" files to resctrl file system
  ...

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

Documentation/x86/intel_rdt_ui.txt

+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

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>

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"

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

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 */

arch/x86/include/asm/intel_rdt.h

+#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 */

arch/x86/include/asm/intel_rdt_common.h

+#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 */

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/

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);
 	}

arch/x86/kernel/cpu/intel_rdt.c

+/*
+ * 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]);
+	}
+}
+
+/*
+ * rdt_find_domain - Find a domain in a resource that matches input resource id
+ *
+ * Search resource r's domain list to find the resource id. If the resource
+ * id is found in a domain, return the domain. Otherwise, if requested by
+ * caller, return the first domain whose id is bigger than the input id.
+ * The domain list is sorted by id in ascending order.
+ */
+static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+					  struct list_head **pos)
+{
+	struct rdt_domain *d;
+	struct list_head *l;
+
+	if (id < 0)
+		return ERR_PTR(id);
+
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+
+	if (pos)
+		*pos = l;
+
+	return NULL;
+}
+
+/*
+ * domain_add_cpu - Add a cpu to a resource's domain list.
+ *
+ * If an existing domain in the resource r's domain list matches the cpu's
+ * resource id, add the cpu in the domain.
+ *
+ * Otherwise, a new domain is allocated and inserted into the right position
+ * in the domain list sorted by id in ascending order.
+ *
+ * The order in the domain list is visible to users when we print entries
+ * in the schemata file and schemata input is validated to have the same order
+ * as this list.
+ */
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
+{
+	int i, id = get_cache_id(cpu, r->cache_level);
+	struct list_head *add_pos = NULL;
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, &add_pos);
+	if (IS_ERR(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	if (d) {
+		cpumask_set_cpu(cpu, &d->cpu_mask);
+		return;
+	}
+
+	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
+	if (!d)
+		return;
+
+	d->id = id;
+
+	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
+	if (!d->cbm) {
+		kfree(d);
+		return;
+	}
+
+	for (i = 0; i < r->num_closid; i++) {
+		int idx = cbm_idx(r, i);
+
+		d->cbm[i] = r->max_cbm;
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+
+	cpumask_set_cpu(cpu, &d->cpu_mask);
+	list_add_tail(&d->list, add_pos);
+	r->num_domains++;
+}
+
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+	int id = get_cache_id(cpu, r->cache_level);
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, NULL);
+	if (IS_ERR_OR_NULL(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	cpumask_clear_cpu(cpu, &d->cpu_mask);
+	if (cpumask_empty(&d->cpu_mask)) {
+		r->num_domains--;
+		kfree(d->cbm);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+static void clear_closid(int cpu)
+{
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+
+	per_cpu(cpu_closid, cpu) = 0;
+	state->closid = 0;
+	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+}
+
+static int intel_rdt_online_cpu(unsigned int cpu)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_add_cpu(cpu, r);
+	/* The cpu is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int intel_rdt_offline_cpu(unsigned int cpu)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_remove_cpu(cpu, r);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask))
+			break;
+	}
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int __init intel_rdt_late_init(void)
+{
+	struct rdt_resource *r;
+	int state, ret;
+
+	if (!get_rdt_resources())
+		return -ENODEV;
+
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				  "x86/rdt/cat:online:",
+				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+	if (state < 0)
+		return state;
+
+	ret = rdtgroup_init();
+	if (ret) {
+		cpuhp_remove_state(state);
+		return ret;
+	}
+
+	for_each_capable_rdt_resource(r)
+		pr_info("Intel RDT %s allocation detected\n", r->name);
+
+	return 0;
+}
+
+late_initcall(intel_rdt_late_init);

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

+/*
+ * User interface for Resource Alloction in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@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.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/task_work.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/intel_rdt.h>
+#include <asm/intel_rdt_common.h>
+
+DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
+struct kernfs_root *rdt_root;
+struct rdtgroup rdtgroup_default;
+LIST_HEAD(rdt_all_groups);
+
+/* Kernel fs node for "info" directory under root */
+static struct kernfs_node *kn_info;
+
+/*
+ * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
+ * we can keep a bitmap of free CLOSIDs in a single integer.
+ *
+ * Using a global CLOSID across all resources has some advantages and
+ * some drawbacks:
+ * + We can simply set "current->closid" to assign a task to a resource
+ *   group.
+ * + Context switch code can avoid extra memory references deciding which
+ *   CLOSID to load into the PQR_ASSOC MSR
+ * - We give up some options in configuring resource groups across multi-socket
+ *   systems.
+ * - Our choices on how to configure each resource become progressively more
+ *   limited as the number of resources grows.
+ */
+static int closid_free_map;
+
+static void closid_init(void)
+{
+	struct rdt_resource *r;
+	int rdt_min_closid = 32;
+
+	/* Compute rdt_min_closid across all resources */
+	for_each_enabled_rdt_resource(r)
+		rdt_min_closid = min(rdt_min_closid, r->num_closid);
+
+	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
+
+	/* CLOSID 0 is always reserved for the default group */
+	closid_free_map &= ~1;
+}
+
+int closid_alloc(void)
+{
+	int closid = ffs(closid_free_map);
+
+	if (closid == 0)
+		return -ENOSPC;
+	closid--;
+	closid_free_map &= ~(1 << closid);
+
+	return closid;
+}
+
+static void closid_free(int closid)
+{
+	closid_free_map |= 1 << closid;
+}
+
+/* set uid and gid of rdtgroup dirs and files to that of the creator */
+static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
+{
+	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
+				.ia_uid = current_fsuid(),
+				.ia_gid = current_fsgid(), };
+
+	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
+	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
+		return 0;
+
+	return kernfs_setattr(kn, &iattr);
+}
+
+static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
+				  0, rft->kf_ops, rft, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts,
+			      int len)
+{
+	struct rftype *rft;
+	int ret;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		ret = rdtgroup_add_file(kn, rft);
+		if (ret)
+			goto error;
+	}
+
+	return 0;
+error:
+	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
+	while (--rft >= rfts)
+		kernfs_remove_by_name(kn, rft->name);
+	return ret;
+}
+
+static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->seq_show)
+		return rft->seq_show(of, m, arg);
+	return 0;
+}
+
+static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
+				   size_t nbytes, loff_t off)
+{
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->write)
+		return rft->write(of, buf, nbytes, off);
+
+	return -EINVAL;
+}
+
+static struct kernfs_ops rdtgroup_kf_single_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= rdtgroup_file_write,
+	.seq_show		= rdtgroup_seqfile_show,
+};
+
+static int rdtgroup_cpus_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/*
+ * This is safe against intel_rdt_sched_in() called from __switch_to()
+ * because __switch_to() is executed with interrupts disabled. A local call
+ * from rdt_update_closid() is proteced against __switch_to() because
+ * preemption is disabled.
+ */
+static void rdt_update_cpu_closid(void *closid)
+{
+	if (closid)
+		this_cpu_write(cpu_closid, *(int *)closid);
+	/*
+	 * We cannot unconditionally write the MSR because the current
+	 * executing task might have its own closid selected. Just reuse
+	 * the context switch code.
+	 */
+	intel_rdt_sched_in();
+}
+
+/*
+ * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
+ *
+ * Per task closids must have been set up before calling this function.
+ *
+ * The per cpu closids are updated with the smp function call, when @closid
+ * is not NULL. If @closid is NULL then all affected percpu closids must
+ * have been set up before calling this function.
+ */
+static void
+rdt_update_closid(const struct cpumask *cpu_mask, int *closid)
+{
+	int cpu = get_cpu();
+
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_update_cpu_closid(closid);
+	smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1);
+	put_cpu();
+}
+
+static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	cpumask_var_t tmpmask, newmask;
+	struct rdtgroup *rdtgrp, *r;
+	int ret;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		return -ENOMEM;
+	}
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = cpumask_parse(buf, newmask);
+	if (ret)
+		goto unlock;
+
+	/* check that user didn't specify any offline cpus */
+	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
+	if (cpumask_weight(tmpmask)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (cpumask_weight(tmpmask)) {
+		/* Can't drop from default group */
+		if (rdtgrp == &rdtgroup_default) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+		/* Give any dropped cpus to rdtgroup_default */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, tmpmask);
+		rdt_update_closid(tmpmask, &rdtgroup_default.closid);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group that owned them
+	 * and update per-cpu closid
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (cpumask_weight(tmpmask)) {
+		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
+			if (r == rdtgrp)
+				continue;
+			cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask);
+		}
+		rdt_update_closid(tmpmask, &rdtgrp->closid);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+	free_cpumask_var(tmpmask);
+	free_cpumask_var(newmask);
+
+	return ret ?: nbytes;
+}
+
+struct task_move_callback {
+	struct callback_head	work;
+	struct rdtgroup		*rdtgrp;
+};
+
+static void move_myself(struct callback_head *head)
+{
+	struct task_move_callback *callback;
+	struct rdtgroup *rdtgrp;
+
+	callback = container_of(head, struct task_move_callback, work);
+	rdtgrp = callback->rdtgrp;
+
+	/*
+	 * If resource group was deleted before this task work callback
+	 * was invoked, then assign the task to root group and free the
+	 * resource group.
+	 */
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		current->closid = 0;
+		kfree(rdtgrp);
+	}
+
+	preempt_disable();
+	/* update PQR_ASSOC MSR to make resource group go into effect */
+	intel_rdt_sched_in();
+	preempt_enable();
+
+	kfree(callback);
+}
+
+static int __rdtgroup_move_task(struct task_struct *tsk,
+				struct rdtgroup *rdtgrp)
+{
+	struct task_move_callback *callback;
+	int ret;
+
+	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
+	if (!callback)
+		return -ENOMEM;
+	callback->work.func = move_myself;
+	callback->rdtgrp = rdtgrp;
+
+	/*
+	 * Take a refcount, so rdtgrp cannot be freed before the
+	 * callback has been invoked.
+	 */
+	atomic_inc(&rdtgrp->waitcount);
+	ret = task_work_add(tsk, &callback->work, true);
+	if (ret) {
+		/*
+		 * Task is exiting. Drop the refcount and free the callback.
+		 * No need to check the refcount as the group cannot be
+		 * deleted before the write function unlocks rdtgroup_mutex.
+		 */
+		atomic_dec(&rdtgrp->waitcount);
+		kfree(callback);
+	} else {
+		tsk->closid = rdtgrp->closid;
+	}
+	return ret;
+}
+
+static int rdtgroup_task_write_permission(struct task_struct *task,
+					  struct kernfs_open_file *of)
+{
+	const struct cred *tcred = get_task_cred(task);
+	const struct cred *cred = current_cred();
+	int ret = 0;
+
+	/*
+	 * Even if we're attaching all tasks in the thread group, we only
+	 * need to check permissions on one of them.
+	 */
+	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+	    !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->euid, tcred->suid))
+		ret = -EPERM;
+
+	put_cred(tcred);
+	return ret;
+}
+
+static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
+			      struct kernfs_open_file *of)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	rcu_read_lock();
+	if (pid) {
+		tsk = find_task_by_vpid(pid);
+		if (!tsk) {
+			rcu_read_unlock();
+			return -ESRCH;
+		}
+	} else {
+		tsk = current;
+	}
+
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = rdtgroup_task_write_permission(tsk, of);
+	if (!ret)
+		ret = __rdtgroup_move_task(tsk, rdtgrp);
+
+	put_task_struct(tsk);
+	return ret;
+}
+
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+	pid_t pid;
+
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		ret = rdtgroup_move_task(pid, rdtgrp, of);
+	else
+		ret = -ENOENT;
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
+{
+	struct task_struct *p, *t;
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if (t->closid == r->closid)
+			seq_printf(s, "%d\n", t->pid);
+	}
+	rcu_read_unlock();
+}
+
+static int rdtgroup_tasks_show(struct kernfs_open_file *of,
+			       struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		show_rdt_tasks(rdtgrp, s);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/* Files in each rdtgroup */
+static struct rftype rdtgroup_base_files[] = {
+	{
+		.name		= "cpus",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+	},
+	{
+		.name		= "tasks",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_tasks_write,
+		.seq_show	= rdtgroup_tasks_show,
+	},
+	{
+		.name		= "schemata",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_schemata_write,
+		.seq_show	= rdtgroup_schemata_show,
+	},
+};
+
+static int rdt_num_closids_show(struct kernfs_open_file *of,
+				struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->num_closid);
+
+	return 0;
+}
+
+static int rdt_cbm_mask_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%x\n", r->max_cbm);
+
+	return 0;
+}
+
+static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->min_cbm_bits);
+
+	return 0;
+}
+
+/* rdtgroup information files for one cache resource. */
+static struct rftype res_info_files[] = {
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+	},
+	{
+		.name		= "cbm_mask",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_cbm_mask_show,
+	},
+	{
+		.name		= "min_cbm_bits",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_cbm_bits_show,
+	},
+};
+
+static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
+{
+	struct kernfs_node *kn_subdir;
+	struct rdt_resource *r;
+	int ret;
+
+	/* create the directory */
+	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
+	if (IS_ERR(kn_info))
+		return PTR_ERR(kn_info);
+	kernfs_get(kn_info);
+
+	for_each_enabled_rdt_resource(r) {
+		kn_subdir = kernfs_create_dir(kn_info, r->name,
+					      kn_info->mode, r);
+		if (IS_ERR(kn_subdir)) {
+			ret = PTR_ERR(kn_subdir);
+			goto out_destroy;
+		}
+		kernfs_get(kn_subdir);
+		ret = rdtgroup_kn_set_ugid(kn_subdir);
+		if (ret)
+			goto out_destroy;
+		ret = rdtgroup_add_files(kn_subdir, res_info_files,
+					 ARRAY_SIZE(res_info_files));
+		if (ret)
+			goto out_destroy;
+		kernfs_activate(kn_subdir);
+	}
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that @rdtgrp->kn is always accessible.
+	 */
+	kernfs_get(kn_info);
+
+	ret = rdtgroup_kn_set_ugid(kn_info);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn_info);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn_info);
+	return ret;
+}
+
+static void l3_qos_cfg_update(void *arg)
+{
+	bool *enable = arg;
+
+	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+}
+
+static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+{
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Pick one CPU from each domain instance to update MSR */
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+	}
+	cpu = get_cpu();
+	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		l3_qos_cfg_update(&enable);
+	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+static int cdp_enable(void)
+{
+	struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
+	struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	int ret;
+
+	if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable)
+		return -EINVAL;
+
+	ret = set_l3_qos_cfg(r_l3, true);
+	if (!ret) {
+		r_l3->enabled = false;
+		r_l3data->enabled = true;
+		r_l3code->enabled = true;
+	}
+	return ret;
+}
+
+static void cdp_disable(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	r->enabled = r->capable;
+
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) {
+		rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false;
+		rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false;
+		set_l3_qos_cfg(r, false);
+	}
+}
+
+static int parse_rdtgroupfs_options(char *data)
+{
+	char *token, *o = data;
+	int ret = 0;
+
+	while ((token = strsep(&o, ",")) != NULL) {
+		if (!*token)
+			return -EINVAL;
+
+		if (!strcmp(token, "cdp"))
+			ret = cdp_enable();
+	}
+
+	return ret;
+}
+
+/*
+ * We don't allow rdtgroup directories to be created anywhere
+ * except the root directory. Thus when looking for the rdtgroup
+ * structure for a kernfs node we are either looking at a directory,
+ * in which case the rdtgroup structure is pointed at by the "priv"
+ * field, otherwise we have a file, and need only look to the parent
+ * to find the rdtgroup.
+ */
+static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
+{
+	if (kernfs_type(kn) == KERNFS_DIR) {
+		/*
+		 * All the resource directories use "kn->priv"
+		 * to point to the "struct rdtgroup" for the
+		 * resource. "info" and its subdirectories don't
+		 * have rdtgroup structures, so return NULL here.
+		 */
+		if (kn == kn_info || kn->parent == kn_info)
+			return NULL;
+		else
+			return kn->priv;
+	} else {
+		return kn->parent->priv;
+	}
+}
+
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return NULL;
+
+	atomic_inc(&rdtgrp->waitcount);
+	kernfs_break_active_protection(kn);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/* Was this group deleted while we waited? */
+	if (rdtgrp->flags & RDT_DELETED)
+		return NULL;
+
+	return rdtgrp;
+}
+
+void rdtgroup_kn_unlock(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return;
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		kernfs_unbreak_active_protection(kn);
+		kernfs_put(kn);
+		kfree(rdtgrp);
+	} else {
+		kernfs_unbreak_active_protection(kn);
+	}
+}
+
+static struct dentry *rdt_mount(struct file_system_type *fs_type,
+				int flags, const char *unused_dev_name,
+				void *data)
+{
+	struct dentry *dentry;
+	int ret;
+
+	mutex_lock(&rdtgroup_mutex);
+	/*
+	 * resctrl file system can only be mounted once.
+	 */
+	if (static_branch_unlikely(&rdt_enable_key)) {
+		dentry = ERR_PTR(-EBUSY);
+		goto out;
+	}
+
+	ret = parse_rdtgroupfs_options(data);
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_cdp;
+	}
+
+	closid_init();
+
+	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_cdp;
+	}
+
+	dentry = kernfs_mount(fs_type, flags, rdt_root,
+			      RDTGROUP_SUPER_MAGIC, NULL);
+	if (IS_ERR(dentry))
+		goto out_cdp;
+
+	static_branch_enable(&rdt_enable_key);
+	goto out;
+
+out_cdp:
+	cdp_disable();
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return dentry;
+}
+
+static int reset_all_cbms(struct rdt_resource *r)
+{
+	struct msr_param msr_param;
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int i, cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	msr_param.res = r;
+	msr_param.low = 0;
+	msr_param.high = r->num_closid;
+
+	/*
+	 * Disable resource control for this resource by setting all
+	 * CBMs in all domains to the maximum mask value. Pick one CPU
+	 * from each domain to update the MSRs below.
+	 */
+	list_for_each_entry(d, &r->domains, list) {
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+
+		for (i = 0; i < r->num_closid; i++)
+			d->cbm[i] = r->max_cbm;
+	}
+	cpu = get_cpu();
+	/* Update CBM on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_cbm_update(&msr_param);
+	/* Update CBM on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+/*
+ * Move tasks from one to the other group. If @from is NULL, then all tasks
+ * in the systems are moved unconditionally (used for teardown).
+ *
+ * If @mask is not NULL the cpus on which moved tasks are running are set
+ * in that mask so the update smp function call is restricted to affected
+ * cpus.
+ */
+static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
+				 struct cpumask *mask)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(p, t) {
+		if (!from || t->closid == from->closid) {
+			t->closid = to->closid;
+#ifdef CONFIG_SMP
+			/*
+			 * This is safe on x86 w/o barriers as the ordering
+			 * of writing to task_cpu() and t->on_cpu is
+			 * reverse to the reading here. The detection is
+			 * inaccurate as tasks might move or schedule
+			 * before the smp function call takes place. In
+			 * such a case the function call is pointless, but
+			 * there is no other side effect.
+			 */
+			if (mask && t->on_cpu)
+				cpumask_set_cpu(task_cpu(t), mask);
+#endif
+		}
+	}
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Forcibly remove all of subdirectories under root.
+ */
+static void rmdir_all_sub(void)
+{
+	struct rdtgroup *rdtgrp, *tmp;
+
+	/* Move all tasks to the default resource group */
+	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
+
+	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
+		/* Remove each rdtgroup other than root */
+		if (rdtgrp == &rdtgroup_default)
+			continue;
+
+		/*
+		 * Give any CPUs back to the default group. We cannot copy
+		 * cpu_online_mask because a CPU might have executed the
+		 * offline callback already, but is still marked online.
+		 */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+		kernfs_remove(rdtgrp->kn);
+		list_del(&rdtgrp->rdtgroup_list);
+		kfree(rdtgrp);
+	}
+	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
+	get_online_cpus();
+	rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid);
+	put_online_cpus();
+
+	kernfs_remove(kn_info);
+}
+
+static void rdt_kill_sb(struct super_block *sb)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/*Put everything back to default values. */
+	for_each_enabled_rdt_resource(r)
+		reset_all_cbms(r);
+	cdp_disable();
+	rmdir_all_sub();
+	static_branch_disable(&rdt_enable_key);
+	kernfs_kill_sb(sb);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static struct file_system_type rdt_fs_type = {
+	.name    = "resctrl",
+	.mount   = rdt_mount,
+	.kill_sb = rdt_kill_sb,
+};
+
+static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			  umode_t mode)
+{
+	struct rdtgroup *parent, *rdtgrp;
+	struct kernfs_node *kn;
+	int ret, closid;
+
+	/* Only allow mkdir in the root directory */
+	if (parent_kn != rdtgroup_default.kn)
+		return -EPERM;
+
+	/* Do not accept '\n' to avoid unparsable situation. */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
+	parent = rdtgroup_kn_lock_live(parent_kn);
+	if (!parent) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	ret = closid_alloc();
+	if (ret < 0)
+		goto out_unlock;
+	closid = ret;
+
+	/* allocate the rdtgroup. */
+	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
+	if (!rdtgrp) {
+		ret = -ENOSPC;
+		goto out_closid_free;
+	}
+	rdtgrp->closid = closid;
+	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
+
+	/* kernfs creates the directory for rdtgrp */
+	kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp);
+	if (IS_ERR(kn)) {
+		ret = PTR_ERR(kn);
+		goto out_cancel_ref;
+	}
+	rdtgrp->kn = kn;
+
+	/*
+	 * kernfs_remove() will drop the reference count on "kn" which
+	 * will free it. But we still need it to stick around for the
+	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
+	 * here, which will be dropped inside rdtgroup_kn_unlock().
+	 */
+	kernfs_get(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	ret = rdtgroup_add_files(kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn);
+
+	ret = 0;
+	goto out_unlock;
+
+out_destroy:
+	kernfs_remove(rdtgrp->kn);
+out_cancel_ref:
+	list_del(&rdtgrp->rdtgroup_list);
+	kfree(rdtgrp);
+out_closid_free:
+	closid_free(closid);
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+}
+
+static int rdtgroup_rmdir(struct kernfs_node *kn)
+{
+	int ret, cpu, closid = rdtgroup_default.closid;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	rdtgrp = rdtgroup_kn_lock_live(kn);
+	if (!rdtgrp) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	/* Give any tasks back to the default group */
+	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
+
+	/* Give any CPUs back to the default group */
+	cpumask_or(&rdtgroup_default.cpu_mask,
+		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+	/* Update per cpu closid of the moved CPUs first */
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		per_cpu(cpu_closid, cpu) = closid;
+	/*
+	 * Update the MSR on moved CPUs and CPUs which have moved
+	 * task running on them.
+	 */
+	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
+	rdt_update_closid(tmpmask, NULL);
+
+	rdtgrp->flags = RDT_DELETED;
+	closid_free(rdtgrp->closid);
+	list_del(&rdtgrp->rdtgroup_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+	ret = 0;
+out:
+	rdtgroup_kn_unlock(kn);
+	free_cpumask_var(tmpmask);
+	return ret;
+}
+
+static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
+{
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled)
+		seq_puts(seq, ",cdp");
+	return 0;
+}
+
+static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
+	.mkdir		= rdtgroup_mkdir,
+	.rmdir		= rdtgroup_rmdir,
+	.show_options	= rdtgroup_show_options,
+};
+
+static int __init rdtgroup_setup_root(void)
+{
+	int ret;
+
+	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
+				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      &rdtgroup_default);
+	if (IS_ERR(rdt_root))
+		return PTR_ERR(rdt_root);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgroup_default.closid = 0;
+	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
+
+	ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret) {
+		kernfs_destroy_root(rdt_root);
+		goto out;
+	}
+
+	rdtgroup_default.kn = rdt_root->kn;
+	kernfs_activate(rdtgroup_default.kn);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return ret;
+}
+
+/*
+ * rdtgroup_init - rdtgroup initialization
+ *
+ * Setup resctrl file system including set up root, create mount point,
+ * register rdtgroup filesystem, and initialize files under root directory.
+ *
+ * Return: 0 on success or -errno
+ */
+int __init rdtgroup_init(void)
+{
+	int ret = 0;
+
+	ret = rdtgroup_setup_root();
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	if (ret)
+		goto cleanup_root;
+
+	ret = register_filesystem(&rdt_fs_type);
+	if (ret)
+		goto cleanup_mountpoint;
+
+	return 0;
+
+cleanup_mountpoint:
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+cleanup_root:
+	kernfs_destroy_root(rdt_root);
+
+	return ret;
+}

arch/x86/kernel/cpu/intel_rdt_schemata.c

+/*
+ * 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>
+ *
+ * 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/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <asm/intel_rdt.h>
+
+/*
+ * Check whether a cache bit mask is valid. 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.
+ */
+static bool cbm_validate(unsigned long var, struct rdt_resource *r)
+{
+	unsigned long first_bit, zero_bit;
+
+	if (var == 0 || var > r->max_cbm)
+		return false;
+
+	first_bit = find_first_bit(&var, r->cbm_len);
+	zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit);
+
+	if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len)
+		return false;
+
+	if ((zero_bit - first_bit) < r->min_cbm_bits)
+		return false;
+	return true;
+}
+
+/*
+ * Read one cache bit mask (hex). Check that it is valid for the current
+ * resource type.
+ */
+static int parse_cbm(char *buf, struct rdt_resource *r)
+{
+	unsigned long data;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &data);
+	if (ret)
+		return ret;
+	if (!cbm_validate(data, r))
+		return -EINVAL;
+	r->tmp_cbms[r->num_tmp_cbms++] = data;
+
+	return 0;
+}
+
+/*
+ * For each domain in this resource we expect to find a series of:
+ *	id=mask
+ * separated by ";". The "id" is in decimal, and must appear in the
+ * right order.
+ */
+static int parse_line(char *line, struct rdt_resource *r)
+{
+	char *dom = NULL, *id;
+	struct rdt_domain *d;
+	unsigned long dom_id;
+
+	list_for_each_entry(d, &r->domains, list) {
+		dom = strsep(&line, ";");
+		if (!dom)
+			return -EINVAL;
+		id = strsep(&dom, "=");
+		if (kstrtoul(id, 10, &dom_id) || dom_id != d->id)
+			return -EINVAL;
+		if (parse_cbm(dom, r))
+			return -EINVAL;
+	}
+
+	/* Any garbage at the end of the line? */
+	if (line && line[0])
+		return -EINVAL;
+	return 0;
+}
+
+static int update_domains(struct rdt_resource *r, int closid)
+{
+	struct msr_param msr_param;
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int cpu, idx = 0;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	msr_param.low = closid;
+	msr_param.high = msr_param.low + 1;
+	msr_param.res = r;
+
+	list_for_each_entry(d, &r->domains, list) {
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		d->cbm[msr_param.low] = r->tmp_cbms[idx++];
+	}
+	cpu = get_cpu();
+	/* Update CBM on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_cbm_update(&msr_param);
+	/* Update CBM on other cpus. */
+	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	char *tok, *resname;
+	int closid, ret = 0;
+	u32 *l3_cbms = NULL;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	closid = rdtgrp->closid;
+
+	/* get scratch space to save all the masks while we validate input */
+	for_each_enabled_rdt_resource(r) {
+		r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms),
+				      GFP_KERNEL);
+		if (!r->tmp_cbms) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		r->num_tmp_cbms = 0;
+	}
+
+	while ((tok = strsep(&buf, "\n")) != NULL) {
+		resname = strsep(&tok, ":");
+		if (!tok) {
+			ret = -EINVAL;
+			goto out;
+		}
+		for_each_enabled_rdt_resource(r) {
+			if (!strcmp(resname, r->name) &&
+			    closid < r->num_closid) {
+				ret = parse_line(tok, r);
+				if (ret)
+					goto out;
+				break;
+			}
+		}
+		if (!r->name) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/* Did the parser find all the masks we need? */
+	for_each_enabled_rdt_resource(r) {
+		if (r->num_tmp_cbms != r->num_domains) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	for_each_enabled_rdt_resource(r) {
+		ret = update_domains(r, closid);
+		if (ret)
+			goto out;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	for_each_enabled_rdt_resource(r) {
+		kfree(r->tmp_cbms);
+		r->tmp_cbms = NULL;
+	}
+	return ret ?: nbytes;
+}
+
+static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
+{
+	struct rdt_domain *dom;
+	bool sep = false;
+
+	seq_printf(s, "%s:", r->name);
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_puts(s, ";");
+		seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]);
+		sep = true;
+	}
+	seq_puts(s, "\n");
+}
+
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	int closid, ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp) {
+		closid = rdtgrp->closid;
+		for_each_enabled_rdt_resource(r) {
+			if (closid < r->num_closid)
+				show_doms(s, r, closid);
+		}
+	} else {
+		ret = -ENOENT;
+	}
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}

arch/x86/kernel/cpu/scattered.c

@@ -24,6 +24,9 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
+	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
+	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
+	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
 	{ 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 },

arch/x86/kernel/process_32.c

@@ -53,6 +53,7 @@
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
+#include <asm/intel_rdt.h>
 
 void __show_regs(struct pt_regs *regs, int all)
 {
@@ -296,5 +297,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	this_cpu_write(current_task, next_p);
 
+	/* Load the Intel cache allocation PQR MSR. */
+	intel_rdt_sched_in();
+
 	return prev_p;
 }

arch/x86/kernel/process_64.c

@@ -49,6 +49,7 @@
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
+#include <asm/intel_rdt.h>
 
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
@@ -476,6 +477,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 			loadsegment(ss, __KERNEL_DS);
 	}
 
+	/* Load the Intel cache allocation PQR MSR. */
+	intel_rdt_sched_in();
+
 	return prev_p;
 }
 

drivers/base/cacheinfo.c

@@ -363,6 +363,7 @@ static ssize_t file_name##_show(struct device *dev,		\
 	return sprintf(buf, "%u\n", this_leaf->object);		\
 }
 
+show_one(id, id);
 show_one(level, level);
 show_one(coherency_line_size, coherency_line_size);
 show_one(number_of_sets, number_of_sets);
@@ -444,6 +445,7 @@ static ssize_t write_policy_show(struct device *dev,
 	return n;
 }
 
+static DEVICE_ATTR_RO(id);
 static DEVICE_ATTR_RO(level);
 static DEVICE_ATTR_RO(type);
 static DEVICE_ATTR_RO(coherency_line_size);
@@ -457,6 +459,7 @@ static DEVICE_ATTR_RO(shared_cpu_list);
 static DEVICE_ATTR_RO(physical_line_partition);
 
 static struct attribute *cache_default_attrs[] = {
+	&dev_attr_id.attr,
 	&dev_attr_type.attr,
 	&dev_attr_level.attr,
 	&dev_attr_shared_cpu_map.attr,
@@ -480,6 +483,8 @@ cache_default_attrs_is_visible(struct kobject *kobj,
 	const struct cpumask *mask = &this_leaf->shared_cpu_map;
 	umode_t mode = attr->mode;
 
+	if ((attr == &dev_attr_id.attr) && (this_leaf->attributes & CACHE_ID))
+		return mode;
 	if ((attr == &dev_attr_type.attr) && this_leaf->type)
 		return mode;
 	if ((attr == &dev_attr_level.attr) && this_leaf->level)

include/linux/cacheinfo.h

@@ -18,6 +18,7 @@ enum cache_type {
 
 /**
  * struct cacheinfo - represent a cache leaf node
+ * @id: This cache's id. It is unique among caches with the same (type, level).
  * @type: type of the cache - data, inst or unified
  * @level: represents the hierarchy in the multi-level cache
  * @coherency_line_size: size of each cache line usually representing
@@ -44,6 +45,7 @@ enum cache_type {
  * keeping, the remaining members form the core properties of the cache
  */
 struct cacheinfo {
+	unsigned int id;
 	enum cache_type type;
 	unsigned int level;
 	unsigned int coherency_line_size;
@@ -61,6 +63,7 @@ struct cacheinfo {
 #define CACHE_WRITE_ALLOCATE	BIT(3)
 #define CACHE_ALLOCATE_POLICY_MASK	\
 	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
+#define CACHE_ID		BIT(4)
 
 	struct device_node *of_node;
 	bool disable_sysfs;

include/linux/sched.h

@@ -1821,6 +1821,9 @@ struct task_struct {
 	/* cg_list protected by css_set_lock and tsk->alloc_lock */
 	struct list_head cg_list;
 #endif
+#ifdef CONFIG_INTEL_RDT_A
+	int closid;
+#endif
 #ifdef CONFIG_FUTEX
 	struct robust_list_head __user *robust_list;
 #ifdef CONFIG_COMPAT

include/uapi/linux/magic.h

@@ -57,6 +57,7 @@
 #define CGROUP_SUPER_MAGIC	0x27e0eb
 #define CGROUP2_SUPER_MAGIC	0x63677270
 
+#define RDTGROUP_SUPER_MAGIC	0x7655821
 
 #define STACK_END_MAGIC		0x57AC6E9D