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

Pull x86 cpu updates from Ingo Molnar:
 "The biggest changes are an extension of the Intel RDT code to extend
  it with Intel Memory Bandwidth Allocation CPU support: MBA allows
  bandwidth allocation between cores, while CBM (already upstream)
  allows CPU cache partitioning.

  There's also misc smaller fixes and updates"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/intel_rdt: Return error for incorrect resource names in schemata
  x86/intel_rdt: Trim whitespace while parsing schemata input
  x86/intel_rdt: Fix padding when resource is enabled via mount
  x86/intel_rdt: Get rid of anon union
  x86/cpu: Keep model defines sorted by model number
  x86/intel_rdt/mba: Add schemata file support for MBA
  x86/intel_rdt: Make schemata file parsers resource specific
  x86/intel_rdt/mba: Add info directory files for Memory Bandwidth Allocation
  x86/intel_rdt: Make information files resource specific
  x86/intel_rdt/mba: Add primary support for Memory Bandwidth Allocation (MBA)
  x86/intel_rdt/mba: Memory bandwith allocation feature detect
  x86/intel_rdt: Add resource specific msr update function
  x86/intel_rdt: Move CBM specific data into a struct
  x86/intel_rdt: Cleanup namespace to support multiple resource types
  Documentation, x86: Intel Memory bandwidth allocation
  x86/intel_rdt: Organize code properly
  x86/intel_rdt: Init padding only if a device exists
  x86/intel_rdt: Add cpus_list rdtgroup file
  x86/intel_rdt: Cleanup kernel-doc
  x86/intel_rdt: Update schemata read to show data in tabular format
  ...

4 files changed, 117 insertions, 59 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0fe00446f9ca..2701e5f8145b 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -202,6 +202,8 @@
 #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
+#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 9814db42b790..75b748a1deb8 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -12,6 +12,7 @@
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
+
 #define INTEL_FAM6_CORE2_MEROM		0x0F
 #define INTEL_FAM6_CORE2_MEROM_L	0x16
 #define INTEL_FAM6_CORE2_PENRYN		0x17
@@ -21,6 +22,7 @@
 #define INTEL_FAM6_NEHALEM_G		0x1F /* Auburndale / Havendale */
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
+
 #define INTEL_FAM6_WESTMERE		0x25
 #define INTEL_FAM6_WESTMERE_EP		0x2C
 #define INTEL_FAM6_WESTMERE_EX		0x2F
@@ -36,9 +38,9 @@
 #define INTEL_FAM6_HASWELL_GT3E		0x46
 
 #define INTEL_FAM6_BROADWELL_CORE	0x3D
-#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 #define INTEL_FAM6_BROADWELL_GT3E	0x47
 #define INTEL_FAM6_BROADWELL_X		0x4F
+#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 
 #define INTEL_FAM6_SKYLAKE_MOBILE	0x4E
 #define INTEL_FAM6_SKYLAKE_DESKTOP	0x5E
@@ -59,8 +61,8 @@
 #define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
 #define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
-#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
+#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 0d64397cee58..597dc4995678 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -12,6 +12,7 @@
 #define IA32_L3_QOS_CFG		0xc81
 #define IA32_L3_CBM_BASE	0xc90
 #define IA32_L2_CBM_BASE	0xd10
+#define IA32_MBA_THRTL_BASE	0xd50
 
 #define L3_QOS_CDP_ENABLE	0x01ULL
 
@@ -37,23 +38,30 @@ struct rdtgroup {
 /* rdtgroup.flags */
 #define	RDT_DELETED		1
 
+/* rftype.flags */
+#define RFTYPE_FLAGS_CPUS_LIST	1
+
 /* List of all resource groups */
 extern struct list_head rdt_all_groups;
 
+extern int max_name_width, max_data_width;
+
 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
+ * @name:	File name
+ * @mode:	Access mode
+ * @kf_ops:	File operations
+ * @flags:	File specific RFTYPE_FLAGS_* flags
+ * @seq_show:	Show content of the file
+ * @write:	Write to the file
  */
 struct rftype {
 	char			*name;
 	umode_t			mode;
 	struct kernfs_ops	*kf_ops;
+	unsigned long		flags;
 
 	int (*seq_show)(struct kernfs_open_file *of,
 			struct seq_file *sf, void *v);
@@ -67,54 +75,21 @@ struct rftype {
 };
 
 /**
- * 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)
+ * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ * @new_ctrl:	new ctrl value to be loaded
+ * @have_new_ctrl: did user provide new_ctrl for this domain
  */
 struct rdt_domain {
 	struct list_head	list;
 	int			id;
 	struct cpumask		cpu_mask;
-	u32			*cbm;
+	u32			*ctrl_val;
+	u32			new_ctrl;
+	bool			have_new_ctrl;
 };
 
 /**
@@ -129,6 +104,83 @@ struct msr_param {
 	int			high;
 };
 
+/**
+ * struct rdt_cache - Cache allocation related data
+ * @cbm_len:		Length of the cache bit mask
+ * @min_cbm_bits:	Minimum number of consecutive bits to be set
+ * @cbm_idx_mult:	Multiplier of CBM index
+ * @cbm_idx_offset:	Offset of CBM index. CBM index is computed by:
+ *			closid * cbm_idx_multi + cbm_idx_offset
+ *			in a cache bit mask
+ */
+struct rdt_cache {
+	unsigned int	cbm_len;
+	unsigned int	min_cbm_bits;
+	unsigned int	cbm_idx_mult;
+	unsigned int	cbm_idx_offset;
+};
+
+/**
+ * struct rdt_membw - Memory bandwidth allocation related data
+ * @max_delay:		Max throttle delay. Delay is the hardware
+ *			representation for memory bandwidth.
+ * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @delay_linear:	True if memory B/W delay is in linear scale
+ * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
+ */
+struct rdt_membw {
+	u32		max_delay;
+	u32		min_bw;
+	u32		bw_gran;
+	u32		delay_linear;
+	u32		*mb_map;
+};
+
+/**
+ * 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
+ * @cache_level:	Which cache level defines scope of this resource
+ * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
+ * @msr_base:		Base MSR address for CBMs
+ * @msr_update:		Function pointer to update QOS MSRs
+ * @data_width:		Character width of data when displaying
+ * @domains:		All domains for this resource
+ * @cache:		Cache allocation related data
+ * @info_files:		resctrl info files for the resource
+ * @nr_info_files:	Number of info files
+ * @format_str:		Per resource format string to show domain value
+ * @parse_ctrlval:	Per resource function pointer to parse control values
+ */
+struct rdt_resource {
+	bool			enabled;
+	bool			capable;
+	char			*name;
+	int			num_closid;
+	int			cache_level;
+	u32			default_ctrl;
+	unsigned int		msr_base;
+	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
+				 struct rdt_resource *r);
+	int			data_width;
+	struct list_head	domains;
+	struct rdt_cache	cache;
+	struct rdt_membw	membw;
+	struct rftype		*info_files;
+	int			nr_info_files;
+	const char		*format_str;
+	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+				 struct rdt_domain *d);
+};
+
+void rdt_get_cache_infofile(struct rdt_resource *r);
+void rdt_get_mba_infofile(struct rdt_resource *r);
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_resource rdt_resources_all[];
@@ -142,6 +194,7 @@ enum {
 	RDT_RESOURCE_L3DATA,
 	RDT_RESOURCE_L3CODE,
 	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
 
 	/* Must be the last */
 	RDT_NUM_RESOURCES,
@@ -149,7 +202,7 @@ enum {
 
 #define for_each_capable_rdt_resource(r)				      \
 	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
-	     r++) 							      \
+	     r++)							      \
 		if (r->capable)
 
 #define for_each_enabled_rdt_resource(r)				      \
@@ -165,8 +218,16 @@ union cpuid_0x10_1_eax {
 	unsigned int full;
 };
 
-/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
-union cpuid_0x10_1_edx {
+/* CPUID.(EAX=10H, ECX=ResID=3).EAX */
+union cpuid_0x10_3_eax {
+	struct {
+		unsigned int max_delay:12;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID).EDX */
+union cpuid_0x10_x_edx {
 	struct {
 		unsigned int cos_max:16;
 	} split;
@@ -175,7 +236,7 @@ union cpuid_0x10_1_edx {
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
 
-void rdt_cbm_update(void *arg);
+void rdt_ctrl_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,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a80c1b3997ed..78defd0aa220 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -80,7 +80,7 @@ extern u16 __read_mostly tlb_lld_1g[NR_INFO];
 
 /*
  *  CPU type and hardware bug flags. Kept separately for each CPU.
- *  Members of this structure are referenced in head.S, so think twice
+ *  Members of this structure are referenced in head_32.S, so think twice
  *  before touching them. [mj]
  */
 
@@ -89,14 +89,7 @@ struct cpuinfo_x86 {
 	__u8			x86_vendor;	/* CPU vendor */
 	__u8			x86_model;
 	__u8			x86_mask;
-#ifdef CONFIG_X86_32
-	char			wp_works_ok;	/* It doesn't on 386's */
-
-	/* Problems on some 486Dx4's and old 386's: */
-	char			rfu;
-	char			pad0;
-	char			pad1;
-#else
+#ifdef CONFIG_X86_64
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
 #endif