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
  ...

3 files changed, 255 insertions, 0 deletions

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 */