From c39a0e2c8850f08249383f2425dbd8dbe4baad69 Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:20 -0700 Subject: x86/perf/cqm: Wipe out perf based cqm 'perf cqm' never worked due to the incompatibility between perf infrastructure and cqm hardware support. The hardware uses RMIDs to track the llc occupancy of tasks and these RMIDs are per package. This makes monitoring a hierarchy like cgroup along with monitoring of tasks separately difficult and several patches sent to lkml to fix them were NACKed. Further more, the following issues in the current perf cqm make it almost unusable: 1. No support to monitor the same group of tasks for which we do allocation using resctrl. 2. It gives random and inaccurate data (mostly 0s) once we run out of RMIDs due to issues in Recycling. 3. Recycling results in inaccuracy of data because we cannot guarantee that the RMID was stolen from a task when it was not pulling data into cache or even when it pulled the least data. Also for monitoring llc_occupancy, if we stop using an RMID_x and then start using an RMID_y after we reclaim an RMID from an other event, we miss accounting all the occupancy that was tagged to RMID_x at a later perf_count. 2. Recycling code makes the monitoring code complex including scheduling because the event can lose RMID any time. Since MBM counters count bandwidth for a period of time by taking snap shot of total bytes at two different times, recycling complicates the way we count MBM in a hierarchy. Also we need a spin lock while we do the processing to account for MBM counter overflow. We also currently use a spin lock in scheduling to prevent the RMID from being taken away. 4. Lack of support when we run different kind of event like task, system-wide and cgroup events together. Data mostly prints 0s. This is also because we can have only one RMID tied to a cpu as defined by the cqm hardware but a perf can at the same time tie multiple events during one sched_in. 5. No support of monitoring a group of tasks. There is partial support for cgroup but it does not work once there is a hierarchy of cgroups or if we want to monitor a task in a cgroup and the cgroup itself. 6. No support for monitoring tasks for the lifetime without perf overhead. 7. It reported the aggregate cache occupancy or memory bandwidth over all sockets. But most cloud and VMM based use cases want to know the individual per-socket usage. Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-2-git-send-email-vikas.shivappa@linux.intel.com --- arch/x86/include/asm/intel_rdt_common.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/include/asm/intel_rdt_common.h') diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h index b31081b89407..c95321870842 100644 --- a/arch/x86/include/asm/intel_rdt_common.h +++ b/arch/x86/include/asm/intel_rdt_common.h @@ -7,7 +7,6 @@ * 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 @@ -19,7 +18,6 @@ struct intel_pqr_state { u32 rmid; u32 closid; - int rmid_usecnt; }; DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); -- cgit v1.2.3 From 0583020456cea9fcf43b84bb13a41eab059ae0a8 Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:23 -0700 Subject: x86/intel_rdt: Change file names to accommodate RDT monitor code Because the "perf cqm" and resctrl code were separately added and indivdually configurable, there seem to be separate context switch code and also things on global .h which are not really needed. Move only the scheduling specific code and definitions to and the put all the other declarations to a local intel_rdt.h. h/t to Reinette Chatre for pointing out that we should separate the public interfaces used by other parts of the kernel from private objects shared between the various files comprising RDT. No functional change. Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-5-git-send-email-vikas.shivappa@linux.intel.com --- MAINTAINERS | 2 +- arch/x86/include/asm/intel_rdt.h | 286 ------------------------------- arch/x86/include/asm/intel_rdt_common.h | 25 --- arch/x86/include/asm/intel_rdt_sched.h | 72 ++++++++ arch/x86/kernel/cpu/intel_rdt.c | 5 +- arch/x86/kernel/cpu/intel_rdt.h | 243 ++++++++++++++++++++++++++ arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 4 +- arch/x86/kernel/cpu/intel_rdt_schemata.c | 2 +- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 10 files changed, 324 insertions(+), 319 deletions(-) delete mode 100644 arch/x86/include/asm/intel_rdt.h delete mode 100644 arch/x86/include/asm/intel_rdt_common.h create mode 100644 arch/x86/include/asm/intel_rdt_sched.h create mode 100644 arch/x86/kernel/cpu/intel_rdt.h (limited to 'arch/x86/include/asm/intel_rdt_common.h') diff --git a/MAINTAINERS b/MAINTAINERS index f66488dfdbc9..cbbc79a81dea 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11103,7 +11103,7 @@ M: Fenghua Yu L: linux-kernel@vger.kernel.org S: Supported F: arch/x86/kernel/cpu/intel_rdt* -F: arch/x86/include/asm/intel_rdt* +F: arch/x86/include/asm/intel_rdt_sched.h F: Documentation/x86/intel_rdt* READ-COPY UPDATE (RCU) diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h deleted file mode 100644 index ae1efc3609d3..000000000000 --- a/arch/x86/include/asm/intel_rdt.h +++ /dev/null @@ -1,286 +0,0 @@ -#ifndef _ASM_X86_INTEL_RDT_H -#define _ASM_X86_INTEL_RDT_H - -#ifdef CONFIG_INTEL_RDT - -#include -#include -#include - -#include - -#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 - -/** - * 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 - -/* 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: 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); - /* - * 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_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 - * @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 *ctrl_val; - u32 new_ctrl; - bool have_new_ctrl; -}; - -/** - * 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; -}; - -/** - * 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[]; -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, - RDT_RESOURCE_MBA, - - /* 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=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; - unsigned int full; -}; - -DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); - -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, - 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 */ -#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 deleted file mode 100644 index c95321870842..000000000000 --- a/arch/x86/include/asm/intel_rdt_common.h +++ /dev/null @@ -1,25 +0,0 @@ -#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 - * - * 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; -}; - -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); - -#endif /* _ASM_X86_INTEL_RDT_COMMON_H */ diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/intel_rdt_sched.h new file mode 100644 index 000000000000..62a70bc85bce --- /dev/null +++ b/arch/x86/include/asm/intel_rdt_sched.h @@ -0,0 +1,72 @@ +#ifndef _ASM_X86_INTEL_RDT_SCHED_H +#define _ASM_X86_INTEL_RDT_SCHED_H + +#ifdef CONFIG_INTEL_RDT + +#include +#include + +#define 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 + * + * The upper 32 bits of IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to 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; +}; + +DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); +DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +/* + * 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(IA32_PQR_ASSOC, state->rmid, closid); + } + } +} + +#else + +static inline void intel_rdt_sched_in(void) {} + +#endif /* CONFIG_INTEL_RDT */ + +#endif /* _ASM_X86_INTEL_RDT_SCHED_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 989a997fce47..08872e9e09c3 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -30,7 +30,8 @@ #include #include -#include +#include +#include "intel_rdt.h" #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 @@ -455,7 +456,7 @@ static void clear_closid(int cpu) per_cpu(cpu_closid, cpu) = 0; state->closid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0); + wrmsr(IA32_PQR_ASSOC, state->rmid, 0); } static int intel_rdt_online_cpu(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h new file mode 100644 index 000000000000..0e4852d68faf --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -0,0 +1,243 @@ +#ifndef _ASM_X86_INTEL_RDT_H +#define _ASM_X86_INTEL_RDT_H + +#include +#include +#include + +#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 + +/** + * 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 + +/* 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: 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); + /* + * 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_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 + * @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 *ctrl_val; + u32 new_ctrl; + bool have_new_ctrl; +}; + +/** + * 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; +}; + +/** + * 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[]; +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, + RDT_RESOURCE_MBA, + + /* 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=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; + unsigned int full; +}; + +DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); + +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, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); + +#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9257bd9dc664..fab88117ae5f 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -32,8 +32,8 @@ #include -#include -#include +#include +#include "intel_rdt.h" DEFINE_STATIC_KEY_FALSE(rdt_enable_key); struct kernfs_root *rdt_root; diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c index 406d7a6532f9..8cef1c8e223a 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include "intel_rdt.h" /* * Check whether MBA bandwidth percentage value is correct. The value is diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c6d6dc5f8bb2..22802162eeb9 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -56,7 +56,7 @@ #include #include #include -#include +#include #include void __show_regs(struct pt_regs *regs, int all) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c3169be4c596..77a35c817b2b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ #include #include #include -#include +#include #include #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ -- cgit v1.2.3