diff options
| -rw-r--r-- | Documentation/admin-guide/kernel-parameters.rst | 1 | ||||
| -rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 6 | ||||
| -rw-r--r-- | Documentation/x86/intel_rdt_ui.txt | 323 | ||||
| -rw-r--r-- | MAINTAINERS | 2 | ||||
| -rw-r--r-- | arch/x86/Kconfig | 12 | ||||
| -rw-r--r-- | arch/x86/events/intel/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/events/intel/cqm.c | 1766 | ||||
| -rw-r--r-- | arch/x86/include/asm/intel_rdt.h | 286 | ||||
| -rw-r--r-- | arch/x86/include/asm/intel_rdt_common.h | 27 | ||||
| -rw-r--r-- | arch/x86/include/asm/intel_rdt_sched.h | 92 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt.c | 375 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt.h | 440 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c (renamed from arch/x86/kernel/cpu/intel_rdt_schemata.c) | 67 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_monitor.c | 499 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 1117 | ||||
| -rw-r--r-- | arch/x86/kernel/process_32.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/process_64.c | 2 | ||||
| -rw-r--r-- | include/linux/perf_event.h | 18 | ||||
| -rw-r--r-- | include/linux/sched.h | 5 | ||||
| -rw-r--r-- | kernel/events/core.c | 14 |
21 files changed, 2631 insertions, 2427 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst index d76ab3907e2b..b2598cc9834c 100644 --- a/Documentation/admin-guide/kernel-parameters.rst +++ b/Documentation/admin-guide/kernel-parameters.rst @@ -138,6 +138,7 @@ parameter is applicable:: PPT Parallel port support is enabled. PS2 Appropriate PS/2 support is enabled. RAM RAM disk support is enabled. + RDT Intel Resource Director Technology. S390 S390 architecture is enabled. SCSI Appropriate SCSI support is enabled. A lot of drivers have their options described inside diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index dad6fa01af95..591d48f3a7de 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3612,6 +3612,12 @@ Run specified binary instead of /init from the ramdisk, used for early userspace startup. See initrd. + rdt= [HW,X86,RDT] + Turn on/off individual RDT features. List is: + cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, mba. + E.g. to turn on cmt and turn off mba use: + rdt=cmt,!mba + reboot= [KNL] Format (x86 or x86_64): [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \ diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt index c491a1b82de2..4d8848e4e224 100644 --- a/Documentation/x86/intel_rdt_ui.txt +++ b/Documentation/x86/intel_rdt_ui.txt @@ -6,8 +6,8 @@ Fenghua Yu <fenghua.yu@intel.com> Tony Luck <tony.luck@intel.com> Vikas Shivappa <vikas.shivappa@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". +This feature is enabled by the CONFIG_INTEL_RDT Kconfig and the +X86 /proc/cpuinfo flag bits "rdt", "cqm", "cat_l3" and "cdp_l3". To use the feature mount the file system: @@ -17,6 +17,13 @@ mount options are: "cdp": Enable code/data prioritization in L3 cache allocations. +RDT features are orthogonal. A particular system may support only +monitoring, only control, or both monitoring and control. + +The mount succeeds if either of allocation or monitoring is present, but +only those files and directories supported by the system will be created. +For more details on the behavior of the interface during monitoring +and allocation, see the "Resource alloc and monitor groups" section. Info directory -------------- @@ -24,7 +31,12 @@ Info directory The 'info' directory contains information about the enabled resources. Each resource has its own subdirectory. The subdirectory names reflect the resource names. -Cache resource(L3/L2) subdirectory contains the following files: + +Each subdirectory contains the following files with respect to +allocation: + +Cache resource(L3/L2) subdirectory contains the following files +related to allocation: "num_closids": The number of CLOSIDs which are valid for this resource. The kernel uses the smallest number of @@ -36,7 +48,15 @@ Cache resource(L3/L2) subdirectory contains the following files: "min_cbm_bits": The minimum number of consecutive bits which must be set when writing a mask. -Memory bandwitdh(MB) subdirectory contains the following files: +"shareable_bits": Bitmask of shareable resource with other executing + entities (e.g. I/O). User can use this when + setting up exclusive cache partitions. Note that + some platforms support devices that have their + own settings for cache use which can over-ride + these bits. + +Memory bandwitdh(MB) subdirectory contains the following files +with respect to allocation: "min_bandwidth": The minimum memory bandwidth percentage which user can request. @@ -52,48 +72,152 @@ Memory bandwitdh(MB) subdirectory contains the following files: non-linear. This field is purely informational only. -Resource groups ---------------- +If RDT monitoring is available there will be an "L3_MON" directory +with the following files: + +"num_rmids": The number of RMIDs available. This is the + upper bound for how many "CTRL_MON" + "MON" + groups can be created. + +"mon_features": Lists the monitoring events if + monitoring is enabled for the resource. + +"max_threshold_occupancy": + Read/write file provides the largest value (in + bytes) at which a previously used LLC_occupancy + counter can be considered for re-use. + + +Resource alloc and monitor 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)". +system. The default group is the root directory which, immediately +after mounting, owns all the tasks and cpus in the system and can make +full use of all resources. + +On a system with RDT control features additional directories can be +created in the root directory that specify different amounts of each +resource (see "schemata" below). The root and these additional top level +directories are referred to as "CTRL_MON" groups below. + +On a system with RDT monitoring the root directory and other top level +directories contain a directory named "mon_groups" in which additional +directories can be created to monitor subsets of tasks in the CTRL_MON +group that is their ancestor. These are called "MON" groups in the rest +of this document. + +Removing a directory will move all tasks and cpus owned by the group it +represents to the parent. Removing one of the created CTRL_MON groups +will automatically remove all MON groups below it. + +All groups contain the following files: + +"tasks": + Reading this file shows the list of all tasks that belong to + this group. Writing a task id to the file will add a task to the + group. If the group is a CTRL_MON group the task is removed from + whichever previous CTRL_MON group owned the task and also from + any MON group that owned the task. If the group is a MON group, + then the task must already belong to the CTRL_MON parent of this + group. The task is removed from any previous MON group. + + +"cpus": + Reading this file shows a bitmask of the logical CPUs owned by + this group. Writing a mask to this file will add and remove + CPUs to/from this group. As with the tasks file a hierarchy is + maintained where MON groups may only include CPUs owned by the + parent CTRL_MON group. + -There are three files associated with each group: +"cpus_list": + Just like "cpus", only using ranges of CPUs instead of bitmasks. -"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. +When control is enabled all CTRL_MON groups will also contain: -"cpus_list": One or more CPU ranges of logical CPUs assigned to this - group. Same rules apply like for the "cpus" file. +"schemata": + A list of all the resources available to this group. + Each resource has its own line and format - see below for details. -"schemata": A list of all the resources available to this group. - Each resource has its own line and format - see below for - details. +When monitoring is enabled all MON groups will also contain: -When a task is running the following rules define which resources -are available to it: +"mon_data": + This contains a set of files organized by L3 domain and by + RDT event. E.g. on a system with two L3 domains there will + be subdirectories "mon_L3_00" and "mon_L3_01". Each of these + directories have one file per event (e.g. "llc_occupancy", + "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these + files provide a read out of the current value of the event for + all tasks in the group. In CTRL_MON groups these files provide + the sum for all tasks in the CTRL_MON group and all tasks in + MON groups. Please see example section for more details on usage. + +Resource allocation rules +------------------------- +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. + 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. + 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. +Resource monitoring rules +------------------------- +1) If a task is a member of a MON group, or non-default CTRL_MON group + then RDT events for the task will be reported in that group. + +2) If a task is a member of the default CTRL_MON group, but is running + on a CPU that is assigned to some specific group, then the RDT events + for the task will be reported in that group. + +3) Otherwise RDT events for the task will be reported in the root level + "mon_data" group. + + +Notes on cache occupancy monitoring and control +----------------------------------------------- +When moving a task from one group to another you should remember that +this only affects *new* cache allocations by the task. E.g. you may have +a task in a monitor group showing 3 MB of cache occupancy. If you move +to a new group and immediately check the occupancy of the old and new +groups you will likely see that the old group is still showing 3 MB and +the new group zero. When the task accesses locations still in cache from +before the move, the h/w does not update any counters. On a busy system +you will likely see the occupancy in the old group go down as cache lines +are evicted and re-used while the occupancy in the new group rises as +the task accesses memory and loads into the cache are counted based on +membership in the new group. + +The same applies to cache allocation control. Moving a task to a group +with a smaller cache partition will not evict any cache lines. The +process may continue to use them from the old partition. + +Hardware uses CLOSid(Class of service ID) and an RMID(Resource monitoring ID) +to identify a control group and a monitoring group respectively. Each of +the resource groups are mapped to these IDs based on the kind of group. The +number of CLOSid and RMID are limited by the hardware and hence the creation of +a "CTRL_MON" directory may fail if we run out of either CLOSID or RMID +and creation of "MON" group may fail if we run out of RMIDs. + +max_threshold_occupancy - generic concepts +------------------------------------------ + +Note that an RMID once freed may not be immediately available for use as +the RMID is still tagged the cache lines of the previous user of RMID. +Hence such RMIDs are placed on limbo list and checked back if the cache +occupancy has gone down. If there is a time when system has a lot of +limbo RMIDs but which are not ready to be used, user may see an -EBUSY +during mkdir. + +max_threshold_occupancy is a user configurable value to determine the +occupancy at which an RMID can be freed. Schemata files - general concepts --------------------------------- @@ -143,22 +267,22 @@ SKUs. Using a high bandwidth and a low bandwidth setting on two threads sharing a core will result in both threads being throttled to use the low bandwidth. -L3 details (code and data prioritization disabled) --------------------------------------------------- +L3 schemata file 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) ----------------------------------------------------- +L3 schemata file 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 schemata file details +------------------------ L2 cache does not support code and data prioritization, so the schemata format is always: @@ -185,6 +309,8 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff L3DATA:0=fffff;1=fffff;2=3c0;3=fffff L3CODE:0=fffff;1=fffff;2=fffff;3=fffff +Examples for RDT allocation usage: + Example 1 --------- On a two socket machine (one L3 cache per socket) with just four bits @@ -410,3 +536,124 @@ void main(void) /* code to read and write directory contents */ resctrl_release_lock(fd); } + +Examples for RDT Monitoring along with allocation usage: + +Reading monitored data +---------------------- +Reading an event file (for ex: mon_data/mon_L3_00/llc_occupancy) would +show the current snapshot of LLC occupancy of the corresponding MON +group or CTRL_MON group. + + +Example 1 (Monitor CTRL_MON group and subset of tasks in CTRL_MON group) +--------- +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 +# echo 5678 > p1/tasks +# echo 5679 > p1/tasks + +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. + +Create monitor groups and assign a subset of tasks to each monitor group. + +# cd /sys/fs/resctrl/p1/mon_groups +# mkdir m11 m12 +# echo 5678 > m11/tasks +# echo 5679 > m12/tasks + +fetch data (data shown in bytes) + +# cat m11/mon_data/mon_L3_00/llc_occupancy +16234000 +# cat m11/mon_data/mon_L3_01/llc_occupancy +14789000 +# cat m12/mon_data/mon_L3_00/llc_occupancy +16789000 + +The parent ctrl_mon group shows the aggregated data. + +# cat /sys/fs/resctrl/p1/mon_data/mon_l3_00/llc_occupancy +31234000 + +Example 2 (Monitor a task from its creation) +--------- +On a two socket machine (one L3 cache per socket) + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl +# mkdir p0 p1 + +An RMID is allocated to the group once its created and hence the <cmd> +below is monitored from its creation. + +# echo $$ > /sys/fs/resctrl/p1/tasks +# <cmd> + +Fetch the data + +# cat /sys/fs/resctrl/p1/mon_data/mon_l3_00/llc_occupancy +31789000 + +Example 3 (Monitor without CAT support or before creating CAT groups) +--------- + +Assume a system like HSW has only CQM and no CAT support. In this case +the resctrl will still mount but cannot create CTRL_MON directories. +But user can create different MON groups within the root group thereby +able to monitor all tasks including kernel threads. + +This can also be used to profile jobs cache size footprint before being +able to allocate them to different allocation groups. + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl +# mkdir mon_groups/m01 +# mkdir mon_groups/m02 + +# echo 3478 > /sys/fs/resctrl/mon_groups/m01/tasks +# echo 2467 > /sys/fs/resctrl/mon_groups/m02/tasks + +Monitor the groups separately and also get per domain data. From the +below its apparent that the tasks are mostly doing work on +domain(socket) 0. + +# cat /sys/fs/resctrl/mon_groups/m01/mon_L3_00/llc_occupancy +31234000 +# cat /sys/fs/resctrl/mon_groups/m01/mon_L3_01/llc_occupancy +34555 +# cat /sys/fs/resctrl/mon_groups/m02/mon_L3_00/llc_occupancy +31234000 +# cat /sys/fs/resctrl/mon_groups/m02/mon_L3_01/llc_occupancy +32789 + + +Example 4 (Monitor real time tasks) +----------------------------------- + +A single socket system which has real time tasks running on cores 4-7 +and non real time tasks on other cpus. We want to monitor the cache +occupancy of the real time threads on these cores. + +# mount -t resctrl resctrl /sys/fs/resctrl +# cd /sys/fs/resctrl +# mkdir p1 + +Move the cpus 4-7 over to p1 +# echo f0 > p0/cpus + +View the llc occupancy snapshot + +# cat /sys/fs/resctrl/p1/mon_data/mon_L3_00/llc_occupancy +11234000 diff --git a/MAINTAINERS b/MAINTAINERS index b81e93b71c4b..8ef4694af6e8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11121,7 +11121,7 @@ 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: arch/x86/include/asm/intel_rdt_sched.h F: Documentation/x86/intel_rdt* READ-COPY UPDATE (RCU) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b4b27ab016f6..acb366bf6bc1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -429,16 +429,16 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH -config INTEL_RDT_A - bool "Intel Resource Director Technology Allocation support" +config INTEL_RDT + bool "Intel Resource Director Technology 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. + Select to enable resource allocation and monitoring which are + sub-features 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. diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 06c2baa51814..e9d8520a801a 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,4 +1,4 @@ -obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c deleted file mode 100644 index 2521f771f2f5..000000000000 --- a/arch/x86/events/intel/cqm.c +++ /dev/null @@ -1,1766 +0,0 @@ -/* - * Intel Cache Quality-of-Service Monitoring (CQM) support. - * - * Based very, very heavily on work by Peter Zijlstra. - */ - -#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_QM_CTR 0x0c8e -#define MSR_IA32_QM_EVTSEL 0x0c8d - -#define MBM_CNTR_WIDTH 24 -/* - * Guaranteed time in ms as per SDM where MBM counters will not overflow. - */ -#define MBM_CTR_OVERFLOW_TIME 1000 - -static u32 cqm_max_rmid = -1; -static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -static bool cqm_enabled, mbm_enabled; -unsigned int mbm_socket_max; - -/* - * 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. - */ -DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); -static struct hrtimer *mbm_timers; -/** - * struct sample - mbm event's (local or total) data - * @total_bytes #bytes since we began monitoring - * @prev_msr previous value of MSR - */ -struct sample { - u64 total_bytes; - u64 prev_msr; -}; - -/* - * samples profiled for total memory bandwidth type events - */ -static struct sample *mbm_total; -/* - * samples profiled for local memory bandwidth type events - */ -static struct sample *mbm_local; - -#define pkg_id topology_physical_package_id(smp_processor_id()) -/* - * rmid_2_index returns the index for the rmid in mbm_local/mbm_total array. - * mbm_total[] and mbm_local[] are linearly indexed by socket# * max number of - * rmids per socket, an example is given below - * RMID1 of Socket0: vrmid = 1 - * RMID1 of Socket1: vrmid = 1 * (cqm_max_rmid + 1) + 1 - * RMID1 of Socket2: vrmid = 2 * (cqm_max_rmid + 1) + 1 - */ -#define rmid_2_index(rmid) ((pkg_id * (cqm_max_rmid + 1)) + rmid) -/* - * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. - * Also protects event->hw.cqm_rmid - * - * Hold either for stability, both for modification of ->hw.cqm_rmid. - */ -static DEFINE_MUTEX(cache_mutex); -static DEFINE_RAW_SPINLOCK(cache_lock); - -/* - * Groups of events that have the same target(s), one RMID per group. - */ -static LIST_HEAD(cache_groups); - -/* - * Mask of CPUs for reading CQM values. We only need one per-socket. - */ -static cpumask_t cqm_cpumask; - -#define RMID_VAL_ERROR (1ULL << 63) -#define RMID_VAL_UNAVAIL (1ULL << 62) - -/* - * Event IDs are used to program IA32_QM_EVTSEL before reading event - * counter from IA32_QM_CTR - */ -#define QOS_L3_OCCUP_EVENT_ID 0x01 -#define QOS_MBM_TOTAL_EVENT_ID 0x02 -#define QOS_MBM_LOCAL_EVENT_ID 0x03 - -/* - * This is central to the rotation algorithm in __intel_cqm_rmid_rotate(). - * - * This rmid is always free and is guaranteed to have an associated - * near-zero occupancy value, i.e. no cachelines are tagged with this - * RMID, once __intel_cqm_rmid_rotate() returns. - */ -static u32 intel_cqm_rotation_rmid; - -#define INVALID_RMID (-1) - -/* - * Is @rmid valid for programming the hardware? - * - * rmid 0 is reserved by the hardware for all non-monitored tasks, which - * means that we should never come across an rmid with that value. - * Likewise, an rmid value of -1 is used to indicate "no rmid currently - * assigned" and is used as part of the rotation code. - */ -static inline bool __rmid_valid(u32 rmid) -{ - if (!rmid || rmid == INVALID_RMID) - return false; - - return true; -} - -static u64 __rmid_read(u32 rmid) -{ - u64 val; - - /* - * Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt, - * it just says that to increase confusion. - */ - wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid); - rdmsrl(MSR_IA32_QM_CTR, val); - - /* - * Aside from the ERROR and UNAVAIL bits, assume this thing returns - * the number of cachelines tagged with @rmid. - */ - return val; -} - -enum rmid_recycle_state { - RMID_YOUNG = 0, - RMID_AVAILABLE, - RMID_DIRTY, -}; - -struct cqm_rmid_entry { - u32 rmid; - enum rmid_recycle_state state; - struct list_head list; - unsigned long queue_time; -}; - -/* - * cqm_rmid_free_lru - A least recently used list of RMIDs. - * - * Oldest entry at the head, newest (most recently used) entry at the - * tail. This list is never traversed, it's only used to keep track of - * the lru order. That is, we only pick entries of the head or insert - * them on the tail. - * - * All entries on the list are 'free', and their RMIDs are not currently - * in use. To mark an RMID as in use, remove its entry from the lru - * list. - * - * - * cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs. - * - * This list is contains RMIDs that no one is currently using but that - * may have a non-zero occupancy value associated with them. The - * rotation worker moves RMIDs from the limbo list to the free list once - * the occupancy value drops below __intel_cqm_threshold. - * - * Both lists are protected by cache_mutex. - */ -static LIST_HEAD(cqm_rmid_free_lru); -static LIST_HEAD(cqm_rmid_limbo_lru); - -/* - * We use a simple array of pointers so that we can lookup a struct - * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid() - * and __put_rmid() from having to worry about dealing with struct - * cqm_rmid_entry - they just deal with rmids, i.e. integers. - * - * Once this array is initialized it is read-only. No locks are required - * to access it. - * - * All entries for all RMIDs can be looked up in the this array at all - * times. - */ -static struct cqm_rmid_entry **cqm_rmid_ptrs; - -static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) -{ - struct cqm_rmid_entry *entry; - - entry = cqm_rmid_ptrs[rmid]; - WARN_ON(entry->rmid != rmid); - - return entry; -} - -/* - * Returns < 0 on fail. - * - * We expect to be called with cache_mutex held. - */ -static u32 __get_rmid(void) -{ - struct cqm_rmid_entry *entry; - - lockdep_assert_held(&cache_mutex); - - if (list_empty(&cqm_rmid_free_lru)) - return INVALID_RMID; - - entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list); - list_del(&entry->list); - - return entry->rmid; -} - -static void __put_rmid(u32 rmid) -{ - struct cqm_rmid_entry *entry; - - lockdep_assert_held(&cache_mutex); - - WARN_ON(!__rmid_valid(rmid)); - entry = __rmid_entry(rmid); - - entry->queue_time = jiffies; - entry->state = RMID_YOUNG; - - list_add_tail(&entry->list, &cqm_rmid_limbo_lru); -} - -static void cqm_cleanup(void) -{ - int i; - - if (!cqm_rmid_ptrs) - return; - - for (i = 0; i < cqm_max_rmid; i++) - kfree(cqm_rmid_ptrs[i]); - - kfree(cqm_rmid_ptrs); - cqm_rmid_ptrs = NULL; - cqm_enabled = false; -} - -static int intel_cqm_setup_rmid_cache(void) -{ - struct cqm_rmid_entry *entry; - unsigned int nr_rmids; - int r = 0; - - nr_rmids = cqm_max_rmid + 1; - cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) * - nr_rmids, GFP_KERNEL); - if (!cqm_rmid_ptrs) - return -ENOMEM; - - for (; r <= cqm_max_rmid; r++) { - struct cqm_rmid_entry *entry; - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto fail; - - INIT_LIST_HEAD(&entry->list); - entry->rmid = r; - cqm_rmid_ptrs[r] = entry; - - list_add_tail(&entry->list, &cqm_rmid_free_lru); - } - - /* - * RMID 0 is special and is always allocated. It's used for all - * tasks that are not monitored. - */ - entry = __rmid_entry(0); - list_del(&entry->list); - - mutex_lock(&cache_mutex); - intel_cqm_rotation_rmid = __get_rmid(); - mutex_unlock(&cache_mutex); - - return 0; - -fail: - cqm_cleanup(); - return -ENOMEM; -} - -/* - * Determine if @a and @b measure the same set of tasks. - * - * If @a and @b measure the same set of tasks then we want to share a - * single RMID. - */ -static bool __match_event(struct perf_event *a, struct perf_event *b) -{ - /* Per-cpu and task events don't mix */ - if ((a->attach_state & PERF_ATTACH_TASK) != - (b->attach_state & PERF_ATTACH_TASK)) - return false; - -#ifdef CONFIG_CGROUP_PERF - if (a->cgrp != b->cgrp) - return false; -#endif - - /* If not task event, we're machine wide */ - if (!(b->attach_state & PERF_ATTACH_TASK)) - return true; - - /* - * Events that target same task are placed into the same cache group. - * Mark it as a multi event group, so that we update ->count - * for every event rather than just the group leader later. - */ - if (a->hw.target == b->hw.target) { - b->hw.is_group_event = true; - return true; - } - - /* - * Are we an inherited event? - */ - if (b->parent == a) - return true; - - return false; -} - -#ifdef CONFIG_CGROUP_PERF -static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) -{ - if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target, event->ctx); - - return event->cgrp; -} -#endif - -/* - * Determine if @a's tasks intersect with @b's tasks - * - * There are combinations of events that we explicitly prohibit, - * - * PROHIBITS - * system-wide -> cgroup and task - * cgroup -> system-wide - * -> task in cgroup - * task -> system-wide - * -> task in cgroup - * - * Call this function before allocating an RMID. - */ -static bool __conflict_event(struct perf_event *a, struct perf_event *b) -{ -#ifdef CONFIG_CGROUP_PERF - /* - * We can have any number of cgroups but only one system-wide - * event at a time. - */ - if (a->cgrp && b->cgrp) { - struct perf_cgroup *ac = a->cgrp; - struct perf_cgroup *bc = b->cgrp; - - /* - * This condition should have been caught in - * __match_event() and we should be sharing an RMID. - */ - WARN_ON_ONCE(ac == bc); - - if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || - cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) - return true; - - return false; - } - - if (a->cgrp || b->cgrp) { - struct perf_cgroup *ac, *bc; - - /* - * cgroup and system-wide events are mutually exclusive - */ - if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) || - (b->cgrp && !(a->attach_state & PERF_ATTACH_TASK))) - return true; - - /* - * Ensure neither event is part of the other's cgroup - */ - ac = event_to_cgroup(a); - bc = event_to_cgroup(b); - if (ac == bc) - return true; - - /* - * Must have cgroup and non-intersecting task events. - */ - if (!ac || !bc) - return false; - - /* - * We have cgroup and task events, and the task belongs - * to a cgroup. Check for for overlap. - */ - if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || - cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) - return true; - - return false; - } -#endif - /* - * If one of them is not a task, same story as above with cgroups. - */ - if (!(a->attach_state & PERF_ATTACH_TASK) || - !(b->attach_state & PERF_ATTACH_TASK)) - return true; - - /* - * Must be non-overlapping. - */ - return false; -} - -struct rmid_read { - u32 rmid; - u32 evt_type; - atomic64_t value; -}; - -static void __intel_cqm_event_count(void *info); -static void init_mbm_sample(u32 rmid, u32 evt_type); -static void __intel_mbm_event_count(void *info); - -static bool is_cqm_event(int e) -{ - return (e == QOS_L3_OCCUP_EVENT_ID); -} - -static bool is_mbm_event(int e) -{ - return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID); -} - -static void cqm_mask_call(struct rmid_read *rr) -{ - if (is_mbm_event(rr->evt_type)) - on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_count, rr, 1); - else - on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, rr, 1); -} - -/* - * Exchange the RMID of a group of events. - */ -static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) -{ - struct perf_event *event; - struct list_head *head = &group->hw.cqm_group_entry; - u32 old_rmid = group->hw.cqm_rmid; - - lockdep_assert_held(&cache_mutex); - - /* - * If our RMID is being deallocated, perform a read now. - */ - if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) { - struct rmid_read rr = { - .rmid = old_rmid, - .evt_type = group->attr.config, - .value = ATOMIC64_INIT(0), - }; - - cqm_mask_call(&rr); - local64_set(&group->count, atomic64_read(&rr.value)); - } - - raw_spin_lock_irq(&cache_lock); - - group->hw.cqm_rmid = rmid; - list_for_each_entry(event, head, hw.cqm_group_entry) - event->hw.cqm_rmid = rmid; - - raw_spin_unlock_irq(&cache_lock); - - /* - * If the allocation is for mbm, init the mbm stats. - * Need to check if each event in the group is mbm event - * because there could be multiple type of events in the same group. - */ - if (__rmid_valid(rmid)) { - event = group; - if (is_mbm_event(event->attr.config)) - init_mbm_sample(rmid, event->attr.config); - - list_for_each_entry(event, head, hw.cqm_group_entry) { - if (is_mbm_event(event->attr.config)) - init_mbm_sample(rmid, event->attr.config); - } - } - - return old_rmid; -} - -/* - * If we fail to assign a new RMID for intel_cqm_rotation_rmid because - * cachelines are still tagged with RMIDs in limbo, we progressively - * increment the threshold until we find an RMID in limbo with <= - * __intel_cqm_threshold lines tagged. This is designed to mitigate the - * problem where cachelines tagged with an RMID are not steadily being - * evicted. - * - * On successful rotations we decrease the threshold back towards zero. - * - * __intel_cqm_max_threshold provides an upper bound on the threshold, - * and is measured in bytes because it's exposed to userland. - */ -static unsigned int __intel_cqm_threshold; -static unsigned int __intel_cqm_max_threshold; - -/* - * Test whether an RMID has a zero occupancy value on this cpu. - */ -static void intel_cqm_stable(void *arg) -{ - struct cqm_rmid_entry *entry; - - list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { - if (entry->state != RMID_AVAILABLE) - break; - - if (__rmid_read(entry->rmid) > __intel_cqm_threshold) - entry->state = RMID_DIRTY; - } -} - -/* - * If we have group events waiting for an RMID that don't conflict with - * events already running, assign @rmid. - */ -static bool intel_cqm_sched_in_event(u32 rmid) -{ - struct perf_event *leader, *event; - - lockdep_assert_held(&cache_mutex); - - leader = list_first_entry(&cache_groups, struct perf_event, - hw.cqm_groups_entry); - event = leader; - - list_for_each_entry_continue(event, &cache_groups, - hw.cqm_groups_entry) { - if (__rmid_valid(event->hw.cqm_rmid)) - continue; - - if (__conflict_event(event, leader)) - continue; - - intel_cqm_xchg_rmid(event, rmid); - return true; - } - - return false; -} - -/* - * Initially use this constant for both the limbo queue time and the - * rotation timer interval, pmu::hrtimer_interval_ms. - * - * They don't need to be the same, but the two are related since if you - * rotate faster than you recycle RMIDs, you may run out of available - * RMIDs. - */ -#define RMID_DEFAULT_QUEUE_TIME 250 /* ms */ - -static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME; - -/* - * intel_cqm_rmid_stabilize - move RMIDs from limbo to free list - * @nr_available: number of freeable RMIDs on the limbo list - * - * Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no - * cachelines are tagged with those RMIDs. After this we can reuse them - * and know that the current set of active RMIDs is stable. - * - * Return %true or %false depending on whether stabilization needs to be - * reattempted. - * - * If we return %true then @nr_available is updated to indicate the - * number of RMIDs on the limbo list that have been queued for the - * minimum queue time (RMID_AVAILABLE), but whose data occupancy values - * are above __intel_cqm_threshold. - */ -static bool intel_cqm_rmid_stabilize(unsigned int *available) -{ - struct cqm_rmid_entry *entry, *tmp; - - lockdep_assert_held(&cache_mutex); - - *available = 0; - list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { - unsigned long min_queue_time; - unsigned long now = jiffies; - - /* - * We hold RMIDs placed into limbo for a minimum queue - * time. Before the minimum queue time has elapsed we do - * not recycle RMIDs. - * - * The reasoning is that until a sufficient time has - * passed since we stopped using an RMID, any RMID - * placed onto the limbo list will likely still have - * data tagged in the cache, which means we'll probably - * fail to recycle it anyway. - * - * We can save ourselves an expensive IPI by skipping - * any RMIDs that have not been queued for the minimum - * time. - */ - min_queue_time = entry->queue_time + - msecs_to_jiffies(__rmid_queue_time_ms); - - if (time_after(min_queue_time, now)) - break; - - entry->state = RMID_AVAILABLE; - (*available)++; - } - - /* - * Fast return if none of the RMIDs on the limbo list have been - * sitting on the queue for the minimum queue time. - */ - if (!*available) - return false; - - /* - * Test whether an RMID is free for each package. - */ - on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true); - - list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) { - /* - * Exhausted all RMIDs that have waited min queue time. - */ - if (entry->state == RMID_YOUNG) - break; - - if (entry->state == RMID_DIRTY) - continue; - - list_del(&entry->list); /* remove from limbo */ - - /* - * The rotation RMID gets priority if it's - * currently invalid. In which case, skip adding - * the RMID to the the free lru. - */ - if (!__rmid_valid(intel_cqm_rotation_rmid)) { - intel_cqm_rotation_rmid = entry->rmid; - continue; - } - - /* - * If we have groups waiting for RMIDs, hand - * them one now provided they don't conflict. - */ - if (intel_cqm_sched_in_event(entry->rmid)) - continue; - - /* - * Otherwise place it onto the free list. - */ - list_add_tail(&entry->list, &cqm_rmid_free_lru); - } - - - return __rmid_valid(intel_cqm_rotation_rmid); -} - -/* - * Pick a victim group and move it to the tail of the group list. - * @next: The first group without an RMID - */ -static void __intel_cqm_pick_and_rotate(struct perf_event *next) -{ - struct perf_event *rotor; - u32 rmid; - - lockdep_assert_held(&cache_mutex); - - rotor = list_first_entry(&cache_groups, struct perf_event, - hw.cqm_groups_entry); - - /* - * The group at the front of the list should always have a valid - * RMID. If it doesn't then no groups have RMIDs assigned and we - * don't need to rotate the list. - */ - if (next == rotor) - return; - - rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID); - __put_rmid(rmid); - - list_rotate_left(&cache_groups); -} - -/* - * Deallocate the RMIDs from any events that conflict with @event, and - * place them on the back of the group list. - */ -static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) -{ - struct perf_event *group, *g; - u32 rmid; - - lockdep_assert_held(&cache_mutex); - - list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) { - if (group == event) - continue; - - rmid = group->hw.cqm_rmid; - - /* - * Skip events that don't have a valid RMID. - */ - if (!__rmid_valid(rmid)) - continue; - - /* - * No conflict? No problem! Leave the event alone. - */ - if (!__conflict_event(group, event)) - continue; - - intel_cqm_xchg_rmid(group, INVALID_RMID); - __put_rmid(rmid); - } -} - -/* - * Attempt to rotate the groups and assign new RMIDs. - * - * We rotate for two reasons, - * 1. To handle the scheduling of conflicting events - * 2. To recycle RMIDs - * - * Rotating RMIDs is complicated because the hardware doesn't give us - * any clues. - * - * There's problems with the hardware interface; when you change the - * task:RMID map cachelines retain their 'old' tags, giving a skewed - * picture. In order to work around this, we must always keep one free - * RMID - intel_cqm_rotation_rmid. - * - * Rotation works by taking away an RMID from a group (the old RMID), - * and assigning the free RMID to another group (the new RMID). We must - * then wait for the old RMID to not be used (no cachelines tagged). - * This ensure that all cachelines are tagged with 'active' RMIDs. At - * this point we can start reading values for the new RMID and treat the - * old RMID as the free RMID for the next rotation. - * - * Return %true or %false depending on whether we did any rotating. - */ -static bool __intel_cqm_rmid_rotate(void) -{ - struct perf_event *group, *start = NULL; - unsigned int threshold_limit; - unsigned int nr_needed = 0; - unsigned int nr_available; - bool rotated = false; - - mutex_lock(&cache_mutex); - -again: - /* - * Fast path through this function if there are no groups and no - * RMIDs that need cleaning. - */ - if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru)) - goto out; - - list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) { - if (!__rmid_valid(group->hw.cqm_rmid)) { - if (!start) - start = group; - nr_needed++; - } - } - - /* - * We have some event groups, but they all have RMIDs assigned - * and no RMIDs need cleaning. - */ - if (!nr_needed && list_empty(&cqm_rmid_limbo_lru)) - goto out; - - if (!nr_needed) - goto stabilize; - - /* - * We have more event groups without RMIDs than available RMIDs, - * or we have event groups that conflict with the ones currently - * scheduled. - * - * We force deallocate the rmid of the group at the head of - * cache_groups. The first event group without an RMID then gets - * assigned intel_cqm_rotation_rmid. This ensures we always make - * forward progress. - * - * Rotate the cache_groups list so the previous head is now the - * tail. - */ - __intel_cqm_pick_and_rotate(start); - - /* - * If the rotation is going to succeed, reduce the threshold so - * that we don't needlessly reuse dirty RMIDs. - */ - if (__rmid_valid(intel_cqm_rotation_rmid)) { - intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid); - intel_cqm_rotation_rmid = __get_rmid(); - - intel_cqm_sched_out_conflicting_events(start); - - if (__intel_cqm_threshold) - __intel_cqm_threshold--; - } - - rotated = true; - -stabilize: - /* - * We now need to stablize the RMID we freed above (if any) to - * ensure that the next time we rotate we have an RMID with zero - * occupancy value. - * - * Alternatively, if we didn't need to perform any rotation, - * we'll have a bunch of RMIDs in limbo that need stabilizing. - */ - threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale; - - while (intel_cqm_rmid_stabilize(&nr_available) && - __intel_cqm_threshold < threshold_limit) { - unsigned int steal_limit; - - /* - * Don't spin if nobody is actively waiting for an RMID, - * the rotation worker will be kicked as soon as an - * event needs an RMID anyway. - */ - if (!nr_needed) - break; - - /* Allow max 25% of RMIDs to be in limbo. */ - steal_limit = (cqm_max_rmid + 1) / 4; - - /* - * We failed to stabilize any RMIDs so our rotation - * logic is now stuck. In order to make forward progress - * we have a few options: - * - * 1. rotate ("steal") another RMID - * 2. increase the threshold - * 3. do nothing - * - * We do both of 1. and 2. until we hit the steal limit. - * - * The steal limit prevents all RMIDs ending up on the - * limbo list. This can happen if every RMID has a - * non-zero occupancy above threshold_limit, and the - * occupancy values aren't dropping fast enough. - * - * Note that there is prioritisation at work here - we'd - * rather increase the number of RMIDs on the limbo list - * than increase the threshold, because increasing the - * threshold skews the event data (because we reuse - * dirty RMIDs) - threshold bumps are a last resort. - */ - if (nr_available < steal_limit) - goto again; - - __intel_cqm_threshold++; - } - -out: - mutex_unlock(&cache_mutex); - return rotated; -} - -static void intel_cqm_rmid_rotate(struct work_struct *work); - -static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate); - -static struct pmu intel_cqm_pmu; - -static void intel_cqm_rmid_rotate(struct work_struct *work) -{ - unsigned long delay; - - __intel_cqm_rmid_rotate(); - - delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms); - schedule_delayed_work(&intel_cqm_rmid_work, delay); -} - -static u64 update_sample(unsigned int rmid, u32 evt_type, int first) -{ - struct sample *mbm_current; - u32 vrmid = rmid_2_index(rmid); - u64 val, bytes, shift; - u32 eventid; - - if (evt_type == QOS_MBM_LOCAL_EVENT_ID) { - mbm_current = &mbm_local[vrmid]; - eventid = QOS_MBM_LOCAL_EVENT_ID; - } else { - mbm_current = &mbm_total[vrmid]; - eventid = QOS_MBM_TOTAL_EVENT_ID; - } - - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, val); - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return mbm_current->total_bytes; - - if (first) { - mbm_current->prev_msr = val; - mbm_current->total_bytes = 0; - return mbm_current->total_bytes; - } - - /* - * The h/w guarantees that counters will not overflow - * so long as we poll them at least once per second. - */ - shift = 64 - MBM_CNTR_WIDTH; - bytes = (val << shift) - (mbm_current->prev_msr << shift); - bytes >>= shift; - - bytes *= cqm_l3_scale; - - mbm_current->total_bytes += bytes; - mbm_current->prev_msr = val; - - return mbm_current->total_bytes; -} - -static u64 rmid_read_mbm(unsigned int rmid, u32 evt_type) -{ - return update_sample(rmid, evt_type, 0); -} - -static void __intel_mbm_event_init(void *info) -{ - struct rmid_read *rr = info; - - update_sample(rr->rmid, rr->evt_type, 1); -} - -static void init_mbm_sample(u32 rmid, u32 evt_type) -{ - struct rmid_read rr = { - .rmid = rmid, - .evt_type = evt_type, - .value = ATOMIC64_INIT(0), - }; - - /* on each socket, init sample */ - on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_init, &rr, 1); -} - -/* - * Find a group and setup RMID. - * - * If we're part of a group, we use the group's RMID. - */ -static void intel_cqm_setup_event(struct perf_event *event, - struct perf_event **group) -{ - struct perf_event *iter; - bool conflict = false; - u32 rmid; - - event->hw.is_group_event = false; - list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { - rmid = iter->hw.cqm_rmid; - - if (__match_event(iter, event)) { - /* All tasks in a group share an RMID */ - event->hw.cqm_rmid = rmid; - *group = iter; - if (is_mbm_event(event->attr.config) && __rmid_valid(rmid)) - init_mbm_sample(rmid, event->attr.config); - return; - } - - /* - * We only care about conflicts for events that are - * actually scheduled in (and hence have a valid RMID). - */ - if (__conflict_event(iter, event) && __rmid_valid(rmid)) - conflict = true; - } - - if (conflict) - rmid = INVALID_RMID; - else - rmid = __get_rmid(); - - if (is_mbm_event(event->attr.config) && __rmid_valid(rmid)) - init_mbm_sample(rmid, event->attr.config); - - event->hw.cqm_rmid = rmid; -} - -static void intel_cqm_event_read(struct perf_event *event) -{ - unsigned long flags; - u32 rmid; - u64 val; - - /* - * Task events are handled by intel_cqm_event_count(). - */ - if (event->cpu == -1) - return; - - raw_spin_lock_irqsave(&cache_lock, flags); - rmid = event->hw.cqm_rmid; - - if (!__rmid_valid(rmid)) - goto out; - - if (is_mbm_event(event->attr.config)) - val = rmid_read_mbm(rmid, event->attr.config); - else - val = __rmid_read(rmid); - - /* - * Ignore this reading on error states and do not update the value. - */ - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - goto out; - - local64_set(&event->count, val); -out: - raw_spin_unlock_irqrestore(&cache_lock, flags); -} - -static void __intel_cqm_event_count(void *info) -{ - struct rmid_read *rr = info; - u64 val; - - val = __rmid_read(rr->rmid); - - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return; - - atomic64_add(val, &rr->value); -} - -static inline bool cqm_group_leader(struct perf_event *event) -{ - return !list_empty(&event->hw.cqm_groups_entry); -} - -static void __intel_mbm_event_count(void *info) -{ - struct rmid_read *rr = info; - u64 val; - - val = rmid_read_mbm(rr->rmid, rr->evt_type); - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return; - atomic64_add(val, &rr->value); -} - -static enum hrtimer_restart mbm_hrtimer_handle(struct hrtimer *hrtimer) -{ - struct perf_event *iter, *iter1; - int ret = HRTIMER_RESTART; - struct list_head *head; - unsigned long flags; - u32 grp_rmid; - - /* - * Need to cache_lock as the timer Event Select MSR reads - * can race with the mbm/cqm count() and mbm_init() reads. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - if (list_empty(&cache_groups)) { - ret = HRTIMER_NORESTART; - goto out; - } - - list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { - grp_rmid = iter->hw.cqm_rmid; - if (!__rmid_valid(grp_rmid)) - continue; - if (is_mbm_event(iter->attr.config)) - update_sample(grp_rmid, iter->attr.config, 0); - - head = &iter->hw.cqm_group_entry; - if (list_empty(head)) - continue; - list_for_each_entry(iter1, head, hw.cqm_group_entry) { - if (!iter1->hw.is_group_event) - break; - if (is_mbm_event(iter1->attr.config)) - update_sample(iter1->hw.cqm_rmid, - iter1->attr.config, 0); - } - } - - hrtimer_forward_now(hrtimer, ms_to_ktime(MBM_CTR_OVERFLOW_TIME)); -out: - raw_spin_unlock_irqrestore(&cache_lock, flags); - - return ret; -} - -static void __mbm_start_timer(void *info) -{ - hrtimer_start(&mbm_timers[pkg_id], ms_to_ktime(MBM_CTR_OVERFLOW_TIME), - HRTIMER_MODE_REL_PINNED); -} - -static void __mbm_stop_timer(void *info) -{ - hrtimer_cancel(&mbm_timers[pkg_id]); -} - -static void mbm_start_timers(void) -{ - on_each_cpu_mask(&cqm_cpumask, __mbm_start_timer, NULL, 1); -} - -static void mbm_stop_timers(void) -{ - on_each_cpu_mask(&cqm_cpumask, __mbm_stop_timer, NULL, 1); -} - -static void mbm_hrtimer_init(void) -{ - struct hrtimer *hr; - int i; - - for (i = 0; i < mbm_socket_max; i++) { - hr = &mbm_timers[i]; - hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hr->function = mbm_hrtimer_handle; - } -} - -static u64 intel_cqm_event_count(struct perf_event *event) -{ - unsigned long flags; - struct rmid_read rr = { - .evt_type = event->attr.config, - .value = ATOMIC64_INIT(0), - }; - - /* - * We only need to worry about task events. System-wide events - * are handled like usual, i.e. entirely with - * intel_cqm_event_read(). - */ - if (event->cpu != -1) - return __perf_event_count(event); - - /* - * Only the group leader gets to report values except in case of - * multiple events in the same group, we still need to read the - * other events.This stops us - * reporting duplicate values to userspace, and gives us a clear - * rule for which task gets to report the values. - * - * Note that it is impossible to attribute these values to - * specific packages - we forfeit that ability when we create - * task events. - */ - if (!cqm_group_leader(event) && !event->hw.is_group_event) - return 0; - - /* - * Getting up-to-date values requires an SMP IPI which is not - * possible if we're being called in interrupt context. Return - * the cached values instead. - */ - if (unlikely(in_interrupt())) - goto out; - - /* - * Notice that we don't perform the reading of an RMID - * atomically, because we can't hold a spin lock across the - * IPIs. - * - * Speculatively perform the read, since @event might be - * assigned a different (possibly invalid) RMID while we're - * busying performing the IPI calls. It's therefore necessary to - * check @event's RMID afterwards, and if it has changed, - * discard the result of the read. - */ - rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid); - - if (!__rmid_valid(rr.rmid)) - goto out; - - cqm_mask_call(&rr); - - raw_spin_lock_irqsave(&cache_lock, flags); - if (event->hw.cqm_rmid == rr.rmid) - local64_set(&event->count, atomic64_read(&rr.value)); - raw_spin_unlock_irqrestore(&cache_lock, flags); -out: - return __perf_event_count(event); -} - -static void intel_cqm_event_start(struct perf_event *event, int mode) -{ - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - u32 rmid = event->hw.cqm_rmid; - - if (!(event->hw.cqm_state & PERF_HES_STOPPED)) - return; - - event->hw.cqm_state &= ~PERF_HES_STOPPED; - - if (state->rmid_usecnt++) { - if (!WARN_ON_ONCE(state->rmid != rmid)) - return; - } else { - WARN_ON_ONCE(state->rmid); - } - - state->rmid = rmid; - wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); -} - -static void intel_cqm_event_stop(struct perf_event *event, int mode) -{ - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - - if (event->hw.cqm_state & PERF_HES_STOPPED) - return; - - event->hw.cqm_state |= PERF_HES_STOPPED; - - intel_cqm_event_read(event); - - if (!--state->rmid_usecnt) { - state->rmid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); - } else { - WARN_ON_ONCE(!state->rmid); - } -} - -static int intel_cqm_event_add(struct perf_event *event, int mode) -{ - unsigned long flags; - u32 rmid; - - raw_spin_lock_irqsave(&cache_lock, flags); - - event->hw.cqm_state = PERF_HES_STOPPED; - rmid = event->hw.cqm_rmid; - - if (__rmid_valid(rmid) && (mode & PERF_EF_START)) - intel_cqm_event_start(event, mode); - - raw_spin_unlock_irqrestore(&cache_lock, flags); - - return 0; -} - -static void intel_cqm_event_destroy(struct perf_event *event) -{ - struct perf_event *group_other = NULL; - unsigned long flags; - - mutex_lock(&cache_mutex); - /* - * Hold the cache_lock as mbm timer handlers could be - * scanning the list of events. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - /* - * If there's another event in this group... - */ - if (!list_empty(&event->hw.cqm_group_entry)) { - group_other = list_first_entry(&event->hw.cqm_group_entry, - struct perf_event, - hw.cqm_group_entry); - list_del(&event->hw.cqm_group_entry); - } - - /* - * And we're the group leader.. - */ - if (cqm_group_leader(event)) { - /* - * If there was a group_other, make that leader, otherwise - * destroy the group and return the RMID. - */ - if (group_other) { - list_replace(&event->hw.cqm_groups_entry, - &group_other->hw.cqm_groups_entry); - } else { - u32 rmid = event->hw.cqm_rmid; - - if (__rmid_valid(rmid)) - __put_rmid(rmid); - list_del(&event->hw.cqm_groups_entry); - } - } - - raw_spin_unlock_irqrestore(&cache_lock, flags); - - /* - * Stop the mbm overflow timers when the last event is destroyed. - */ - if (mbm_enabled && list_empty(&cache_groups)) - mbm_stop_timers(); - - mutex_unlock(&cache_mutex); -} - -static int intel_cqm_event_init(struct perf_event *event) -{ - struct perf_event *group = NULL; - bool rotate = false; - unsigned long flags; - - if (event->attr.type != intel_cqm_pmu.type) - return -ENOENT; - - if ((event->attr.config < QOS_L3_OCCUP_EVENT_ID) || - (event->attr.config > QOS_MBM_LOCAL_EVENT_ID)) - return -EINVAL; - - if ((is_cqm_event(event->attr.config) && !cqm_enabled) || - (is_mbm_event(event->attr.config) && !mbm_enabled)) - return -EINVAL; - - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest || - event->attr.sample_period) /* no sampling */ - return -EINVAL; - - INIT_LIST_HEAD(&event->hw.cqm_group_entry); - INIT_LIST_HEAD(&event->hw.cqm_groups_entry); - - event->destroy = intel_cqm_event_destroy; - - mutex_lock(&cache_mutex); - - /* - * Start the mbm overflow timers when the first event is created. - */ - if (mbm_enabled && list_empty(&cache_groups)) - mbm_start_timers(); - - /* Will also set rmid */ - intel_cqm_setup_event(event, &group); - - /* - * Hold the cache_lock as mbm timer handlers be - * scanning the list of events. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - if (group) { - list_add_tail(&event->hw.cqm_group_entry, - &group->hw.cqm_group_entry); - } else { - list_add_tail(&event->hw.cqm_groups_entry, - &cache_groups); - - /* - * All RMIDs are either in use or have recently been - * used. Kick the rotation worker to clean/free some. - * - * We only do this for the group leader, rather than for - * every event in a group to save on needless work. - */ - if (!__rmid_valid(event->hw.cqm_rmid)) - rotate = true; - } - - raw_spin_unlock_irqrestore(&cache_lock, flags); - mutex_unlock(&cache_mutex); - - if (rotate) - schedule_delayed_work(&intel_cqm_rmid_work, 0); - - return 0; -} - -EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01"); -EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1"); -EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes"); -EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL); -EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1"); - -EVENT_ATTR_STR(total_bytes, intel_cqm_total_bytes, "event=0x02"); -EVENT_ATTR_STR(total_bytes.per-pkg, intel_cqm_total_bytes_pkg, "1"); -EVENT_ATTR_STR(total_bytes.unit, intel_cqm_total_bytes_unit, "MB"); -EVENT_ATTR_STR(total_bytes.scale, intel_cqm_total_bytes_scale, "1e-6"); - -EVENT_ATTR_STR(local_bytes, intel_cqm_local_bytes, "event=0x03"); -EVENT_ATTR_STR(local_bytes.per-pkg, intel_cqm_local_bytes_pkg, "1"); -EVENT_ATTR_STR(local_bytes.unit, intel_cqm_local_bytes_unit, "MB"); -EVENT_ATTR_STR(local_bytes.scale, intel_cqm_local_bytes_scale, "1e-6"); - -static struct attribute *intel_cqm_events_attr[] = { - EVENT_PTR(intel_cqm_llc), - EVENT_PTR(intel_cqm_llc_pkg), - EVENT_PTR(intel_cqm_llc_unit), - EVENT_PTR(intel_cqm_llc_scale), - EVENT_PTR(intel_cqm_llc_snapshot), - NULL, -}; - -static struct attribute *intel_mbm_events_attr[] = { - EVENT_PTR(intel_cqm_total_bytes), - EVENT_PTR(intel_cqm_local_bytes), - EVENT_PTR(intel_cqm_total_bytes_pkg), - EVENT_PTR(intel_cqm_local_bytes_pkg), - EVENT_PTR(intel_cqm_total_bytes_unit), - EVENT_PTR(intel_cqm_local_bytes_unit), - EVENT_PTR(intel_cqm_total_bytes_scale), - EVENT_PTR(intel_cqm_local_bytes_scale), - NULL, -}; - -static struct attribute *intel_cmt_mbm_events_attr[] = { - EVENT_PTR(intel_cqm_llc), - EVENT_PTR(intel_cqm_total_bytes), - EVENT_PTR(intel_cqm_local_bytes), - EVENT_PTR(intel_cqm_llc_pkg), - EVENT_PTR(intel_cqm_total_bytes_pkg), - EVENT_PTR(intel_cqm_local_bytes_pkg), - EVENT_PTR(intel_cqm_llc_unit), - EVENT_PTR(intel_cqm_total_bytes_unit), - EVENT_PTR(intel_cqm_local_bytes_unit), - EVENT_PTR(intel_cqm_llc_scale), - EVENT_PTR(intel_cqm_total_bytes_scale), - EVENT_PTR(intel_cqm_local_bytes_scale), - EVENT_PTR(intel_cqm_llc_snapshot), - NULL, -}; - -static struct attribute_group intel_cqm_events_group = { - .name = "events", - .attrs = NULL, -}; - -PMU_FORMAT_ATTR(event, "config:0-7"); -static struct attribute *intel_cqm_formats_attr[] = { - &format_attr_event.attr, - NULL, -}; - -static struct attribute_group intel_cqm_format_group = { - .name = "format", - .attrs = intel_cqm_formats_attr, -}; - -static ssize_t -max_recycle_threshold_show(struct device *dev, struct device_attribute *attr, - char *page) -{ - ssize_t rv; - - mutex_lock(&cache_mutex); - rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold); - mutex_unlock(&cache_mutex); - - return rv; -} - -static ssize_t -max_recycle_threshold_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - unsigned int bytes, cachelines; - int ret; - - ret = kstrtouint(buf, 0, &bytes); - if (ret) - return ret; - - mutex_lock(&cache_mutex); - - __intel_cqm_max_threshold = bytes; - cachelines = bytes / cqm_l3_scale; - - /* - * The new maximum takes effect immediately. - */ - if (__intel_cqm_threshold > cachelines) - __intel_cqm_threshold = cachelines; - - mutex_unlock(&cache_mutex); - - return count; -} - -static DEVICE_ATTR_RW(max_recycle_threshold); - -static struct attribute *intel_cqm_attrs[] = { - &dev_attr_max_recycle_threshold.attr, - NULL, -}; - -static const struct attribute_group intel_cqm_group = { - .attrs = intel_cqm_attrs, -}; - -static const struct attribute_group *intel_cqm_attr_groups[] = { - &intel_cqm_events_group, - &intel_cqm_format_group, - &intel_cqm_group, - NULL, -}; - -static struct pmu intel_cqm_pmu = { - .hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME, - .attr_groups = intel_cqm_attr_groups, - .task_ctx_nr = perf_sw_context, - .event_init = intel_cqm_event_init, - .add = intel_cqm_event_add, - .del = intel_cqm_event_stop, - .start = intel_cqm_event_start, - .stop = intel_cqm_event_stop, - .read = intel_cqm_event_read, - .count = intel_cqm_event_count, -}; - -static inline void cqm_pick_event_reader(int cpu) -{ - int reader; - - /* First online cpu in package becomes the reader */ - reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu)); - if (reader >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cqm_cpumask); -} - -static int intel_cqm_cpu_starting(unsigned int cpu) -{ - struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); - struct cpuinfo_x86 *c = &cpu_data(cpu); - - state->rmid = 0; - state->closid = 0; - state->rmid_usecnt = 0; - - WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); - WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); - - cqm_pick_event_reader(cpu); - return 0; -} - -static int intel_cqm_cpu_exit(unsigned int cpu) -{ - int target; - - /* Is @cpu the current cqm reader for this package ? */ - if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) - return 0; - - /* Find another online reader in this package */ - target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - - if (target < nr_cpu_ids) - cpumask_set_cpu(target, &cqm_cpumask); - - return 0; -} - -static const struct x86_cpu_id intel_cqm_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC }, - {} -}; - -static void mbm_cleanup(void) -{ - if (!mbm_enabled) - return; - - kfree(mbm_local); - kfree(mbm_total); - mbm_enabled = false; -} - -static const struct x86_cpu_id intel_mbm_local_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_LOCAL }, - {} -}; - -static const struct x86_cpu_id intel_mbm_total_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_TOTAL }, - {} -}; - -static int intel_mbm_init(void) -{ - int ret = 0, array_size, maxid = cqm_max_rmid + 1; - - mbm_socket_max = topology_max_packages(); - array_size = sizeof(struct sample) * maxid * mbm_socket_max; - mbm_local = kmalloc(array_size, GFP_KERNEL); - if (!mbm_local) - return -ENOMEM; - - mbm_total = kmalloc(array_size, GFP_KERNEL); - if (!mbm_total) { - ret = -ENOMEM; - goto out; - } - - array_size = sizeof(struct hrtimer) * mbm_socket_max; - mbm_timers = kmalloc(array_size, GFP_KERNEL); - if (!mbm_timers) { - ret = -ENOMEM; - goto out; - } - mbm_hrtimer_init(); - -out: - if (ret) - mbm_cleanup(); - - return ret; -} - -static int __init intel_cqm_init(void) -{ - char *str = NULL, scale[20]; - int cpu, ret; - - if (x86_match_cpu(intel_cqm_match)) - cqm_enabled = true; - - if (x86_match_cpu(intel_mbm_local_match) && - x86_match_cpu(intel_mbm_total_match)) - mbm_enabled = true; - - if (!cqm_enabled && !mbm_enabled) - return -ENODEV; - - cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale; - - /* - * It's possible that not all resources support the same number - * of RMIDs. Instead of making scheduling much more complicated - * (where we have to match a task's RMID to a cpu that supports - * that many RMIDs) just find the minimum RMIDs supported across - * all cpus. - * - * Also, check that the scales match on all cpus. - */ - cpus_read_lock(); - for_each_online_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->x86_cache_max_rmid < cqm_max_rmid) - cqm_max_rmid = c->x86_cache_max_rmid; - - if (c->x86_cache_occ_scale != cqm_l3_scale) { - pr_err("Multiple LLC scale values, disabling\n"); - ret = -EINVAL; - goto out; - } - } - - /* - * A reasonable upper limit on the max threshold is the number - * of lines tagged per RMID if all RMIDs have the same number of - * lines tagged in the LLC. - * - * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. - */ - __intel_cqm_max_threshold = - boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1); - - snprintf(scale, sizeof(scale), "%u", cqm_l3_scale); - str = kstrdup(scale, GFP_KERNEL); - if (!str) { - ret = -ENOMEM; - goto out; - } - - event_attr_intel_cqm_llc_scale.event_str = str; - - ret = intel_cqm_setup_rmid_cache(); - if (ret) - goto out; - - if (mbm_enabled) - ret = intel_mbm_init(); - if (ret && !cqm_enabled) - goto out; - - if (cqm_enabled && mbm_enabled) - intel_cqm_events_group.attrs = intel_cmt_mbm_events_attr; - else if (!cqm_enabled && mbm_enabled) - intel_cqm_events_group.attrs = intel_mbm_events_attr; - else if (cqm_enabled && !mbm_enabled) - intel_cqm_events_group.attrs = intel_cqm_events_attr; - - ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1); - if (ret) { - pr_err("Intel CQM perf registration failed: %d\n", ret); - goto out; - } - - if (cqm_enabled) - pr_info("Intel CQM monitoring enabled\n"); - if (mbm_enabled) - pr_info("Intel MBM enabled\n"); - - /* - * Setup the hot cpu notifier once we are sure cqm - * is enabled to avoid notifier leak. - */ - cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING, - "perf/x86/cqm:starting", - intel_cqm_cpu_starting, NULL); - cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE, - "perf/x86/cqm:online", - NULL, intel_cqm_cpu_exit); -out: - cpus_read_unlock(); - - if (ret) { - kfree(str); - cqm_cleanup(); - mbm_cleanup(); - } - - return ret; -} -device_initcall(intel_cqm_init); diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h deleted file mode 100644 index 597dc4995678..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_A - -#include <linux/sched.h> -#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 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_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 deleted file mode 100644 index b31081b89407..000000000000 --- a/arch/x86/include/asm/intel_rdt_common.h +++ /dev/null @@ -1,27 +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 - * @rmid_usecnt: The usage counter for rmid - * - * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the - * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always - * contains both parts, so we need to cache them. - * - * The cache also helps to avoid pointless updates if the value does - * not change. - */ -struct intel_pqr_state { - u32 rmid; - u32 closid; - int rmid_usecnt; -}; - -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); - -#endif /* _ASM_X86_INTEL_RDT_COMMON_H */ diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/intel_rdt_sched.h new file mode 100644 index 000000000000..b4bbf8b21512 --- /dev/null +++ b/arch/x86/include/asm/intel_rdt_sched.h @@ -0,0 +1,92 @@ +#ifndef _ASM_X86_INTEL_RDT_SCHED_H +#define _ASM_X86_INTEL_RDT_SCHED_H + +#ifdef CONFIG_INTEL_RDT + +#include <linux/sched.h> +#include <linux/jump_label.h> + +#define IA32_PQR_ASSOC 0x0c8f + +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @cur_rmid: The cached Resource Monitoring ID + * @cur_closid: The cached Class Of Service ID + * @default_rmid: The user assigned Resource Monitoring ID + * @default_closid: The user assigned 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. This also + * stores the user configured per cpu CLOSID and RMID. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 cur_rmid; + u32 cur_closid; + u32 default_rmid; + u32 default_closid; +}; + +DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); + +/* + * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID 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 or monitoring and we enable by + * mounting the resctrl file system. + * - Caches the per cpu CLOSid/RMID values and does the MSR write only + * when a task with a different CLOSid/RMID is scheduled in. + * - We allocate RMIDs/CLOSids globally in order to keep this as + * simple as possible. + * Must be called with preemption disabled. + */ +static void __intel_rdt_sched_in(void) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 closid = state->default_closid; + u32 rmid = state->default_rmid; + + /* + * If this task has a closid/rmid assigned, use it. + * Else use the closid/rmid assigned to this cpu. + */ + if (static_branch_likely(&rdt_alloc_enable_key)) { + if (current->closid) + closid = current->closid; + } + + if (static_branch_likely(&rdt_mon_enable_key)) { + if (current->rmid) + rmid = current->rmid; + } + + if (closid != state->cur_closid || rmid != state->cur_rmid) { + state->cur_closid = closid; + state->cur_rmid = rmid; + wrmsr(IA32_PQR_ASSOC, rmid, closid); + } +} + +static inline void intel_rdt_sched_in(void) +{ + if (static_branch_likely(&rdt_enable_key)) + __intel_rdt_sched_in(); +} + +#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/Makefile b/arch/x86/kernel/cpu/Makefile index cdf82492b770..e17942c131c8 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -33,7 +33,7 @@ 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_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 5b366462f579..cd5fc61ba450 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -30,7 +30,8 @@ #include <linux/cpuhotplug.h> #include <asm/intel-family.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 @@ -38,7 +39,13 @@ /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); -DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Functions which modify the state + * are called with interrupts disabled and no preemption, which + * is sufficient for the protection. + */ +DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Used to store the max resource name width and max resource data width @@ -46,6 +53,12 @@ DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); */ int max_name_width, max_data_width; +/* + * Global boolean for rdt_alloc which is true if any + * resource allocation is enabled. + */ +bool rdt_alloc_capable; + static void mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); static void @@ -54,7 +67,9 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) struct rdt_resource rdt_resources_all[] = { + [RDT_RESOURCE_L3] = { + .rid = RDT_RESOURCE_L3, .name = "L3", .domains = domain_init(RDT_RESOURCE_L3), .msr_base = IA32_L3_CBM_BASE, @@ -67,8 +82,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3DATA] = { + .rid = RDT_RESOURCE_L3DATA, .name = "L3DATA", .domains = domain_init(RDT_RESOURCE_L3DATA), .msr_base = IA32_L3_CBM_BASE, @@ -81,8 +99,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3CODE] = { + .rid = RDT_RESOURCE_L3CODE, .name = "L3CODE", .domains = domain_init(RDT_RESOURCE_L3CODE), .msr_base = IA32_L3_CBM_BASE, @@ -95,8 +116,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L2] = { + .rid = RDT_RESOURCE_L2, .name = "L2", .domains = domain_init(RDT_RESOURCE_L2), .msr_base = IA32_L2_CBM_BASE, @@ -109,8 +133,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_MBA] = { + .rid = RDT_RESOURCE_MBA, .name = "MB", .domains = domain_init(RDT_RESOURCE_MBA), .msr_base = IA32_MBA_THRTL_BASE, @@ -118,6 +145,7 @@ struct rdt_resource rdt_resources_all[] = { .cache_level = 3, .parse_ctrlval = parse_bw, .format_str = "%d=%*d", + .fflags = RFTYPE_RES_MB, }, }; @@ -144,33 +172,28 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) * 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) +static inline void 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); + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; - /* If all the bits were set in MSR, return success */ - if (l != max_cbm) - return false; + if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) + return; + rdmsr(IA32_L3_CBM_BASE, l, h); - r->num_closid = 4; - r->default_ctrl = max_cbm; - r->cache.cbm_len = 20; - r->cache.min_cbm_bits = 2; - r->capable = true; - r->enabled = true; + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return; - return true; - } + r->num_closid = 4; + r->default_ctrl = max_cbm; + r->cache.cbm_len = 20; + r->cache.shareable_bits = 0xc0000; + r->cache.min_cbm_bits = 2; + r->alloc_capable = true; + r->alloc_enabled = true; - return false; + rdt_alloc_capable = true; } /* @@ -213,15 +236,14 @@ static bool rdt_get_mem_config(struct rdt_resource *r) return false; } r->data_width = 3; - rdt_get_mba_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; return true; } -static void rdt_get_cache_config(int idx, struct rdt_resource *r) +static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { union cpuid_0x10_1_eax eax; union cpuid_0x10_x_edx edx; @@ -231,10 +253,10 @@ static void rdt_get_cache_config(int idx, struct rdt_resource *r) r->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; - rdt_get_cache_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; } static void rdt_get_cdp_l3_config(int type) @@ -246,12 +268,12 @@ static void rdt_get_cdp_l3_config(int type) r->cache.cbm_len = r_l3->cache.cbm_len; r->default_ctrl = r_l3->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; - r->capable = true; + r->alloc_capable = true; /* * By default, CDP is disabled. CDP can be enabled by mount parameter * "cdp" during resctrl file system mount time. */ - r->enabled = false; + r->alloc_enabled = false; } static int get_cache_id(int cpu, int level) @@ -300,6 +322,19 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); } +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) +{ + 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)) + return d; + } + + return NULL; +} + void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; @@ -307,12 +342,10 @@ void rdt_ctrl_update(void *arg) int 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)) { - r->msr_update(d, m, r); - return; - } + d = get_domain_from_cpu(cpu, r); + if (d) { + r->msr_update(d, m, r); + return; } pr_warn_once("cpu %d not found in any domain for resource %s\n", cpu, r->name); @@ -326,8 +359,8 @@ void rdt_ctrl_update(void *arg) * 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 *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) { struct rdt_domain *d; struct list_head *l; @@ -377,6 +410,44 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) return 0; } +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +{ + size_t tsize; + + if (is_llc_occupancy_enabled()) { + d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), + sizeof(unsigned long), + GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + } + if (is_mbm_total_enabled()) { + tsize = sizeof(*d->mbm_total); + d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_total) { + kfree(d->rmid_busy_llc); + return -ENOMEM; + } + } + if (is_mbm_local_enabled()) { + tsize = sizeof(*d->mbm_local); + d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_local) { + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + return -ENOMEM; + } + } + + if (is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + } + + return 0; +} + /* * domain_add_cpu - Add a cpu to a resource's domain list. * @@ -412,14 +483,26 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; d->id = id; + cpumask_set_cpu(cpu, &d->cpu_mask); - if (domain_setup_ctrlval(r, d)) { + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { + kfree(d); + return; + } + + if (r->mon_capable && domain_setup_mon_state(r, d)) { kfree(d); return; } - cpumask_set_cpu(cpu, &d->cpu_mask); list_add_tail(&d->list, add_pos); + + /* + * If resctrl is mounted, add + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + mkdir_mondata_subdir_allrdtgrp(r, d); } static void domain_remove_cpu(int cpu, struct rdt_resource *r) @@ -435,19 +518,58 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + rmdir_mondata_subdir_allrdtgrp(r, d->id); kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); list_del(&d->list); + if (is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + /* + * When a package is going down, forcefully + * decrement rmid->ebusy. There is no way to know + * that the L3 was flushed and hence may lead to + * incorrect counts in rare scenarios, but leaving + * the RMID as busy creates RMID leaks if the + * package never comes back. + */ + __check_limbo(d, true); + cancel_delayed_work(&d->cqm_limbo); + } + kfree(d); + return; + } + + if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(r, d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0); + } } } -static void clear_closid(int cpu) +static void clear_closid_rmid(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); + state->default_closid = 0; + state->default_rmid = 0; + state->cur_closid = 0; + state->cur_rmid = 0; + wrmsr(IA32_PQR_ASSOC, 0, 0); } static int intel_rdt_online_cpu(unsigned int cpu) @@ -459,12 +581,23 @@ static int intel_rdt_online_cpu(unsigned int cpu) 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); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; } +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { + break; + } + } +} + static int intel_rdt_offline_cpu(unsigned int cpu) { struct rdtgroup *rdtgrp; @@ -474,10 +607,12 @@ static int intel_rdt_offline_cpu(unsigned int cpu) 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)) + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); break; + } } - clear_closid(cpu); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; @@ -492,7 +627,7 @@ static __init void rdt_init_padding(void) struct rdt_resource *r; int cl; - for_each_capable_rdt_resource(r) { + for_each_alloc_capable_rdt_resource(r) { cl = strlen(r->name); if (cl > max_name_width) max_name_width = cl; @@ -502,38 +637,153 @@ static __init void rdt_init_padding(void) } } -static __init bool get_rdt_resources(void) +enum { + RDT_FLAG_CMT, + RDT_FLAG_MBM_TOTAL, + RDT_FLAG_MBM_LOCAL, + RDT_FLAG_L3_CAT, + RDT_FLAG_L3_CDP, + RDT_FLAG_L2_CAT, + RDT_FLAG_MBA, +}; + +#define RDT_OPT(idx, n, f) \ +[idx] = { \ + .name = n, \ + .flag = f \ +} + +struct rdt_options { + char *name; + int flag; + bool force_off, force_on; +}; + +static struct rdt_options rdt_options[] __initdata = { + RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC), + RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL), + RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL), + RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3), + RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3), + RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), + RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), +}; +#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) + +static int __init set_rdt_options(char *str) +{ + struct rdt_options *o; + bool force_off; + char *tok; + + if (*str == '=') + str++; + while ((tok = strsep(&str, ",")) != NULL) { + force_off = *tok == '!'; + if (force_off) + tok++; + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (strcmp(tok, o->name) == 0) { + if (force_off) + o->force_off = true; + else + o->force_on = true; + break; + } + } + } + return 1; +} +__setup("rdt", set_rdt_options); + +static bool __init rdt_cpu_has(int flag) +{ + bool ret = boot_cpu_has(flag); + struct rdt_options *o; + + if (!ret) + return ret; + + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (flag == o->flag) { + if (o->force_off) + ret = false; + if (o->force_on) + ret = true; + break; + } + } + return ret; +} + +static __init bool get_rdt_alloc_resources(void) { bool ret = false; - if (cache_alloc_hsw_probe()) + if (rdt_alloc_capable) return true; if (!boot_cpu_has(X86_FEATURE_RDT_A)) return false; - if (boot_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); - if (boot_cpu_has(X86_FEATURE_CDP_L3)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (rdt_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)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); ret = true; } - if (boot_cpu_has(X86_FEATURE_MBA)) { + if (rdt_cpu_has(X86_FEATURE_MBA)) { if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA])) ret = true; } - return ret; } +static __init bool get_rdt_mon_resources(void) +{ + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) + rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + + if (!rdt_mon_features) + return false; + + return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); +} + +static __init void rdt_quirks(void) +{ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_HASWELL_X: + if (!rdt_options[RDT_FLAG_L3_CAT].force_off) + cache_alloc_hsw_probe(); + break; + case INTEL_FAM6_SKYLAKE_X: + if (boot_cpu_data.x86_mask <= 4) + set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); + } +} + +static __init bool get_rdt_resources(void) +{ + rdt_quirks(); + rdt_alloc_capable = get_rdt_alloc_resources(); + rdt_mon_capable = get_rdt_mon_resources(); + + return (rdt_mon_capable || rdt_alloc_capable); +} + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -556,9 +806,12 @@ static int __init intel_rdt_late_init(void) return ret; } - for_each_capable_rdt_resource(r) + for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); + for_each_mon_capable_rdt_resource(r) + pr_info("Intel RDT %s monitoring detected\n", r->name); + return 0; } diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h new file mode 100644 index 000000000000..ebaddaeef023 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -0,0 +1,440 @@ +#ifndef _ASM_X86_INTEL_RDT_H +#define _ASM_X86_INTEL_RDT_H + +#include <linux/sched.h> +#include <linux/kernfs.h> +#include <linux/jump_label.h> + +#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 + +/* + * Event IDs are used to program IA32_QM_EVTSEL before reading event + * counter from IA32_QM_CTR + */ +#define QOS_L3_OCCUP_EVENT_ID 0x01 +#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02 +#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03 + +#define CQM_LIMBOCHECK_INTERVAL 1000 + +#define MBM_CNTR_WIDTH 24 +#define MBM_OVERFLOW_INTERVAL 1000 + +#define RMID_VAL_ERROR BIT_ULL(63) +#define RMID_VAL_UNAVAIL BIT_ULL(62) + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +/** + * struct mon_evt - Entry in the event list of a resource + * @evtid: event id + * @name: name of the event + */ +struct mon_evt { + u32 evtid; + char *name; + struct list_head list; +}; + +/** + * struct mon_data_bits - Monitoring details for each event file + * @rid: Resource id associated with the event file. + * @evtid: Event id associated with the event file + * @domid: The domain to which the event file belongs + */ +union mon_data_bits { + void *priv; + struct { + unsigned int rid : 10; + unsigned int evtid : 8; + unsigned int domid : 14; + } u; +}; + +struct rmid_read { + struct rdtgroup *rgrp; + struct rdt_domain *d; + int evtid; + bool first; + u64 val; +}; + +extern unsigned int intel_cqm_threshold; +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; +extern unsigned int rdt_mon_features; + +enum rdt_group_type { + RDTCTRL_GROUP = 0, + RDTMON_GROUP, + RDT_NUM_GROUP, +}; + +/** + * struct mongroup - store mon group's data in resctrl fs. + * @mon_data_kn kernlfs node for the mon_data directory + * @parent: parent rdtgrp + * @crdtgrp_list: child rdtgroup node list + * @rmid: rmid for this rdtgroup + */ +struct mongroup { + struct kernfs_node *mon_data_kn; + struct rdtgroup *parent; + struct list_head crdtgrp_list; + u32 rmid; +}; + +/** + * 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 + * @type: indicates type of this rdtgroup - either + * monitor only or ctrl_mon group + * @mon: mongroup related data + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; +}; + +/* rdtgroup.flags */ +#define RDT_DELETED 1 + +/* rftype.flags */ +#define RFTYPE_FLAGS_CPUS_LIST 1 + +/* + * Define the file type flags for base and info directories. + */ +#define RFTYPE_INFO BIT(0) +#define RFTYPE_BASE BIT(1) +#define RF_CTRLSHIFT 4 +#define RF_MONSHIFT 5 +#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) +#define RFTYPE_MON BIT(RF_MONSHIFT) +#define RFTYPE_RES_CACHE BIT(8) +#define RFTYPE_RES_MB BIT(9) +#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) + +/* 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 + * @fflags: File specific RF_* or RFTYPE_* 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; + unsigned long fflags; + + 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 mbm_state - status for each MBM counter in each domain + * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) + * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it + */ +struct mbm_state { + u64 chunks; + u64 prev_msr; +}; + +/** + * 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 + * @rmid_busy_llc: + * bitmap of which limbo RMIDs are above threshold + * @mbm_total: saved state for MBM total bandwidth + * @mbm_local: saved state for MBM local bandwidth + * @mbm_over: worker to periodically read MBM h/w counters + * @cqm_limbo: worker to periodically read CQM h/w counters + * @mbm_work_cpu: + * worker cpu for MBM h/w counters + * @cqm_work_cpu: + * worker cpu for CQM h/w counters + * @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; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + 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 + * @shareable_bits: Bitmask of shareable resource with other + * executing entities + */ +struct rdt_cache { + unsigned int cbm_len; + unsigned int min_cbm_bits; + unsigned int cbm_idx_mult; + unsigned int cbm_idx_offset; + unsigned int shareable_bits; +}; + +/** + * 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; +}; + +static inline bool is_llc_occupancy_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); +} + +static inline bool is_mbm_total_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); +} + +static inline bool is_mbm_local_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); +} + +static inline bool is_mbm_enabled(void) +{ + return (is_mbm_total_enabled() || is_mbm_local_enabled()); +} + +static inline bool is_mbm_event(int e) +{ + return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && + e <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +/** + * struct rdt_resource - attributes of an RDT resource + * @rid: The index of the resource + * @alloc_enabled: Is allocation enabled on this machine + * @mon_enabled: Is monitoring enabled for this feature + * @alloc_capable: Is allocation available on this machine + * @mon_capable: Is monitor 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 + * @format_str: Per resource format string to show domain value + * @parse_ctrlval: Per resource function pointer to parse control values + * @evt_list: List of monitoring events + * @num_rmid: Number of RMIDs available + * @mon_scale: cqm counter * mon_scale = occupancy in bytes + * @fflags: flags to choose base and info files + */ +struct rdt_resource { + int rid; + bool alloc_enabled; + bool mon_enabled; + bool alloc_capable; + bool mon_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; + const char *format_str; + int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + struct rdt_domain *d); + struct list_head evt_list; + int num_rmid; + unsigned int mon_scale; + unsigned long fflags; +}; + +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_alloc_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->alloc_capable || r->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_capable) + +#define for_each_alloc_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_enabled) + +#define for_each_mon_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_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; +}; + +void rdt_ctrl_update(void *arg); +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); +void rdtgroup_kn_unlock(struct kernfs_node *kn); +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos); +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); +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int alloc_rmid(void); +void free_rmid(u32 rmid); +int rdt_get_mon_l3_config(struct rdt_resource *r); +void mon_event_count(void *info); +int rdtgroup_mondata_show(struct seq_file *m, void *arg); +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + unsigned int dom_id); +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d); +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first); +void mbm_setup_overflow_handler(struct rdt_domain *dom, + unsigned long delay_ms); +void mbm_handle_overflow(struct work_struct *work); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_handle_limbo(struct work_struct *work); +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +void __check_limbo(struct rdt_domain *d, bool force_free); + +#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 406d7a6532f9..f6ea94f8954a 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -26,7 +26,7 @@ #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> -#include <asm/intel_rdt.h> +#include "intel_rdt.h" /* * Check whether MBA bandwidth percentage value is correct. The value is @@ -192,7 +192,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid) { struct rdt_resource *r; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (!strcmp(resname, r->name) && closid < r->num_closid) return parse_line(tok, r); } @@ -221,7 +221,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) dom->have_new_ctrl = false; } @@ -237,7 +237,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { ret = update_domains(r, closid); if (ret) goto out; @@ -269,12 +269,13 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, { struct rdtgroup *rdtgrp; struct rdt_resource *r; - int closid, ret = 0; + int ret = 0; + u32 closid; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (closid < r->num_closid) show_doms(s, r, closid); } @@ -284,3 +285,57 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgroup_kn_unlock(of->kn); return ret; } + +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first) +{ + /* + * setup the parameters to send to the IPI to read the data. + */ + rr->rgrp = rdtgrp; + rr->evtid = evtid; + rr->d = d; + rr->val = 0; + rr->first = first; + + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); +} + +int rdtgroup_mondata_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + u32 resid, evtid, domid; + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + union mon_data_bits md; + struct rdt_domain *d; + struct rmid_read rr; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + md.priv = of->kn->priv; + resid = md.u.rid; + domid = md.u.domid; + evtid = md.u.evtid; + + r = &rdt_resources_all[resid]; + d = rdt_find_domain(r, domid, NULL); + if (!d) { + ret = -ENOENT; + goto out; + } + + mon_event_read(&rr, d, rdtgrp, evtid, false); + + if (rr.val & RMID_VAL_ERROR) + seq_puts(m, "Error\n"); + else if (rr.val & RMID_VAL_UNAVAIL) + seq_puts(m, "Unavailable\n"); + else + seq_printf(m, "%llu\n", rr.val * r->mon_scale); + +out: + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c new file mode 100644 index 000000000000..30827510094b --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -0,0 +1,499 @@ +/* + * Resource Director Technology(RDT) + * - Monitoring code + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * This replaces the cqm.c based on perf but we reuse a lot of + * code and datastructures originally from Peter Zijlstra and Matt Fleming. + * + * 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. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "intel_rdt.h" + +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +struct rmid_entry { + u32 rmid; + int busy; + struct list_head list; +}; + +/** + * @rmid_free_lru A least recently used list of free RMIDs + * These RMIDs are guaranteed to have an occupancy less than the + * threshold occupancy + */ +static LIST_HEAD(rmid_free_lru); + +/** + * @rmid_limbo_count count of currently unused but (potentially) + * dirty RMIDs. + * This counts RMIDs that no one is currently using but that + * may have a occupancy value > intel_cqm_threshold. User can change + * the threshold occupancy value. + */ +unsigned int rmid_limbo_count; + +/** + * @rmid_entry - The entry in the limbo and free lists. + */ +static struct rmid_entry *rmid_ptrs; + +/* + * Global boolean for rdt_monitor which is true if any + * resource monitoring is enabled. + */ +bool rdt_mon_capable; + +/* + * Global to indicate which monitoring events are enabled. + */ +unsigned int rdt_mon_features; + +/* + * This is the threshold cache occupancy at which we will consider an + * RMID available for re-allocation. + */ +unsigned int intel_cqm_threshold; + +static inline struct rmid_entry *__rmid_entry(u32 rmid) +{ + struct rmid_entry *entry; + + entry = &rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +static u64 __rmid_read(u32 rmid, u32 eventid) +{ + u64 val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + return val; +} + +static bool rmid_dirty(struct rmid_entry *entry) +{ + u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + + return val >= intel_cqm_threshold; +} + +/* + * Check the RMIDs that are marked as busy for this domain. If the + * reported LLC occupancy is below the threshold clear the busy bit and + * decrement the count. If the busy count gets to zero on an RMID, we + * free the RMID + */ +void __check_limbo(struct rdt_domain *d, bool force_free) +{ + struct rmid_entry *entry; + struct rdt_resource *r; + u32 crmid = 1, nrmid; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + /* + * Skip RMID 0 and start from RMID 1 and check all the RMIDs that + * are marked as busy for occupancy < threshold. If the occupancy + * is less than the threshold decrement the busy counter of the + * RMID and move it to the free list when the counter reaches 0. + */ + for (;;) { + nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); + if (nrmid >= r->num_rmid) + break; + + entry = __rmid_entry(nrmid); + if (force_free || !rmid_dirty(entry)) { + clear_bit(entry->rmid, d->rmid_busy_llc); + if (!--entry->busy) { + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + } + } + crmid = nrmid + 1; + } +} + +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +{ + return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; +} + +/* + * As of now the RMIDs allocation is global. + * However we keep track of which packages the RMIDs + * are used to optimize the limbo list management. + */ +int alloc_rmid(void) +{ + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? -EBUSY : -ENOSPC; + + entry = list_first_entry(&rmid_free_lru, + struct rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void add_rmid_to_limbo(struct rmid_entry *entry) +{ + struct rdt_resource *r; + struct rdt_domain *d; + int cpu; + u64 val; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + entry->busy = 0; + cpu = get_cpu(); + list_for_each_entry(d, &r->domains, list) { + if (cpumask_test_cpu(cpu, &d->cpu_mask)) { + val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + if (val <= intel_cqm_threshold) + continue; + } + + /* + * For the first limbo RMID in the domain, + * setup up the limbo worker. + */ + if (!has_busy_rmid(r, d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); + set_bit(entry->rmid, d->rmid_busy_llc); + entry->busy++; + } + put_cpu(); + + if (entry->busy) + rmid_limbo_count++; + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +void free_rmid(u32 rmid) +{ + struct rmid_entry *entry; + + if (!rmid) + return; + + lockdep_assert_held(&rdtgroup_mutex); + + entry = __rmid_entry(rmid); + + if (is_llc_occupancy_enabled()) + add_rmid_to_limbo(entry); + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +static int __mon_event_count(u32 rmid, struct rmid_read *rr) +{ + u64 chunks, shift, tval; + struct mbm_state *m; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { + rr->val = tval; + return -EINVAL; + } + switch (rr->evtid) { + case QOS_L3_OCCUP_EVENT_ID: + rr->val += tval; + return 0; + case QOS_L3_MBM_TOTAL_EVENT_ID: + m = &rr->d->mbm_total[rmid]; + break; + case QOS_L3_MBM_LOCAL_EVENT_ID: + m = &rr->d->mbm_local[rmid]; + break; + default: + /* + * Code would never reach here because + * an invalid event id would fail the __rmid_read. + */ + return -EINVAL; + } + + if (rr->first) { + m->prev_msr = tval; + m->chunks = 0; + return 0; + } + + shift = 64 - MBM_CNTR_WIDTH; + chunks = (tval << shift) - (m->prev_msr << shift); + chunks >>= shift; + m->chunks += chunks; + m->prev_msr = tval; + + rr->val += m->chunks; + return 0; +} + +/* + * This is called via IPI to read the CQM/MBM counters + * on a domain. + */ +void mon_event_count(void *info) +{ + struct rdtgroup *rdtgrp, *entry; + struct rmid_read *rr = info; + struct list_head *head; + + rdtgrp = rr->rgrp; + + if (__mon_event_count(rdtgrp->mon.rmid, rr)) + return; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rdtgrp->mon.crdtgrp_list; + + if (rdtgrp->type == RDTCTRL_GROUP) { + list_for_each_entry(entry, head, mon.crdtgrp_list) { + if (__mon_event_count(entry->mon.rmid, rr)) + return; + } + } +} + +static void mbm_update(struct rdt_domain *d, int rmid) +{ + struct rmid_read rr; + + rr.first = false; + rr.d = d; + + /* + * This is protected from concurrent reads from user + * as both the user and we hold the global mutex. + */ + if (is_mbm_total_enabled()) { + rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } + if (is_mbm_local_enabled()) { + rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } +} + +/* + * Handler to scan the limbo list and move the RMIDs + * to free list whose occupancy < threshold_occupancy. + */ +void cqm_handle_limbo(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); + int cpu = smp_processor_id(); + struct rdt_resource *r; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + d = get_domain_from_cpu(cpu, r); + + if (!d) { + pr_warn_once("Failure to get domain for limbo worker\n"); + goto out_unlock; + } + + __check_limbo(d, false); + + if (has_busy_rmid(r, d)) + schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + struct rdt_resource *r; + int cpu; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + cpu = cpumask_any(&dom->cpu_mask); + dom->cqm_work_cpu = cpu; + + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); +} + +void mbm_handle_overflow(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); + struct rdtgroup *prgrp, *crgrp; + int cpu = smp_processor_id(); + struct list_head *head; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + if (!static_branch_likely(&rdt_enable_key)) + goto out_unlock; + + d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); + if (!d) + goto out_unlock; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mbm_update(d, prgrp->mon.rmid); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) + mbm_update(d, crgrp->mon.rmid); + } + + schedule_delayed_work_on(cpu, &d->mbm_over, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + if (!static_branch_likely(&rdt_enable_key)) + return; + cpu = cpumask_any(&dom->cpu_mask); + dom->mbm_work_cpu = cpu; + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); +} + +static int dom_data_init(struct rdt_resource *r) +{ + struct rmid_entry *entry = NULL; + int i, nr_rmids; + + nr_rmids = r->num_rmid; + rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) + return -ENOMEM; + + for (i = 0; i < nr_rmids; i++) { + entry = &rmid_ptrs[i]; + INIT_LIST_HEAD(&entry->list); + + entry->rmid = i; + list_add_tail(&entry->list, &rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + return 0; +} + +static struct mon_evt llc_occupancy_event = { + .name = "llc_occupancy", + .evtid = QOS_L3_OCCUP_EVENT_ID, +}; + +static struct mon_evt mbm_total_event = { + .name = "mbm_total_bytes", + .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, +}; + +static struct mon_evt mbm_local_event = { + .name = "mbm_local_bytes", + .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, +}; + +/* + * Initialize the event list for the resource. + * + * Note that MBM events are also part of RDT_RESOURCE_L3 resource + * because as per the SDM the total and local memory bandwidth + * are enumerated as part of L3 monitoring. + */ +static void l3_mon_evt_init(struct rdt_resource *r) +{ + INIT_LIST_HEAD(&r->evt_list); + + if (is_llc_occupancy_enabled()) + list_add_tail(&llc_occupancy_event.list, &r->evt_list); + if (is_mbm_total_enabled()) + list_add_tail(&mbm_total_event.list, &r->evt_list); + if (is_mbm_local_enabled()) + list_add_tail(&mbm_local_event.list, &r->evt_list); +} + +int rdt_get_mon_l3_config(struct rdt_resource *r) +{ + int ret; + + r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + intel_cqm_threshold /= r->mon_scale; + + ret = dom_data_init(r); + if (ret) + return ret; + + l3_mon_evt_init(r); + + r->mon_capable = true; + r->mon_enabled = true; + + return 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9257bd9dc664..a869d4a073c5 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -32,17 +32,25 @@ #include <uapi/linux/magic.h> -#include <asm/intel_rdt.h> -#include <asm/intel_rdt_common.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" DEFINE_STATIC_KEY_FALSE(rdt_enable_key); -struct kernfs_root *rdt_root; +DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); +DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +static 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; +/* Kernel fs node for "mon_groups" directory under root */ +static struct kernfs_node *kn_mongrp; + +/* Kernel fs node for "mon_data" directory under root */ +static struct kernfs_node *kn_mondata; + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -66,7 +74,7 @@ static void closid_init(void) int rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) rdt_min_closid = min(rdt_min_closid, r->num_closid); closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -75,9 +83,9 @@ static void closid_init(void) closid_free_map &= ~1; } -int closid_alloc(void) +static int closid_alloc(void) { - int closid = ffs(closid_free_map); + u32 closid = ffs(closid_free_map); if (closid == 0) return -ENOSPC; @@ -125,28 +133,6 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) 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; @@ -174,6 +160,11 @@ static struct kernfs_ops rdtgroup_kf_single_ops = { .seq_show = rdtgroup_seqfile_show, }; +static struct kernfs_ops kf_mondata_ops = { + .atomic_write_len = PAGE_SIZE, + .seq_show = rdtgroup_mondata_show, +}; + static bool is_cpu_list(struct kernfs_open_file *of) { struct rftype *rft = of->kn->priv; @@ -203,13 +194,18 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, /* * 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 + * from update_closid_rmid() is proteced against __switch_to() because * preemption is disabled. */ -static void rdt_update_cpu_closid(void *closid) +static void update_cpu_closid_rmid(void *info) { - if (closid) - this_cpu_write(cpu_closid, *(int *)closid); + struct rdtgroup *r = info; + + if (r) { + this_cpu_write(pqr_state.default_closid, r->closid); + this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + } + /* * We cannot unconditionally write the MSR because the current * executing task might have its own closid selected. Just reuse @@ -221,28 +217,128 @@ static void rdt_update_cpu_closid(void *closid) /* * 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. + * Per task closids/rmids must have been set up before calling this function. */ static void -rdt_update_closid(const struct cpumask *cpu_mask, int *closid) +update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) { 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); + update_cpu_closid_rmid(r); + smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1); put_cpu(); } +static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp; + struct list_head *head; + + /* Check whether cpus belong to parent ctrl group */ + cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); + if (cpumask_weight(tmpmask)) + return -EINVAL; + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Give any dropped cpus to parent rdtgroup */ + cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); + update_closid_rmid(tmpmask, prgrp); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu rmid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + if (crgrp == rdtgrp) + continue; + cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask, + tmpmask); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + return 0; +} + +static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m) +{ + struct rdtgroup *crgrp; + + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m); + /* update the child mon group masks as well*/ + list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list) + cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask); +} + +static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask, cpumask_var_t tmpmask1) +{ + struct rdtgroup *r, *crgrp; + struct list_head *head; + + /* 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) + return -EINVAL; + + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + update_closid_rmid(tmpmask, &rdtgroup_default); + } + + /* + * If we added cpus, remove them from previous group and + * the prev group's child groups that owned them + * and update per-cpu closid/rmid. + */ + 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_and(tmpmask1, &r->cpu_mask, tmpmask); + if (cpumask_weight(tmpmask1)) + cpumask_rdtgrp_clear(r, tmpmask1); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + /* + * Clear child mon group masks since there is a new parent mask + * now and update the rmid for the cpus the child lost. + */ + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask); + update_closid_rmid(tmpmask, rdtgrp); + cpumask_clear(&crgrp->cpu_mask); + } + + return 0; +} + 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; + cpumask_var_t tmpmask, newmask, tmpmask1; + struct rdtgroup *rdtgrp; int ret; if (!buf) @@ -254,6 +350,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, free_cpumask_var(tmpmask); return -ENOMEM; } + if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + return -ENOMEM; + } rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -276,41 +377,18 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, 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); + if (rdtgrp->type == RDTCTRL_GROUP) + ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1); + else if (rdtgrp->type == RDTMON_GROUP) + ret = cpus_mon_write(rdtgrp, newmask, tmpmask); + else + ret = -EINVAL; unlock: rdtgroup_kn_unlock(of->kn); free_cpumask_var(tmpmask); free_cpumask_var(newmask); + free_cpumask_var(tmpmask1); return ret ?: nbytes; } @@ -336,6 +414,7 @@ static void move_myself(struct callback_head *head) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; + current->rmid = 0; kfree(rdtgrp); } @@ -374,7 +453,20 @@ static int __rdtgroup_move_task(struct task_struct *tsk, atomic_dec(&rdtgrp->waitcount); kfree(callback); } else { - tsk->closid = rdtgrp->closid; + /* + * For ctrl_mon groups move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. + */ + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) + tsk->rmid = rdtgrp->mon.rmid; + else + ret = -EINVAL; + } } return ret; } @@ -454,7 +546,8 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) rcu_read_lock(); for_each_process_thread(p, t) { - if (t->closid == r->closid) + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) seq_printf(s, "%d\n", t->pid); } rcu_read_unlock(); @@ -476,39 +569,6 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, 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 = "cpus_list", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_cpus_write, - .seq_show = rdtgroup_cpus_show, - .flags = RFTYPE_FLAGS_CPUS_LIST, - }, - { - .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) { @@ -536,6 +596,15 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, return 0; } +static int rdt_shareable_bits_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->cache.shareable_bits); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -545,6 +614,28 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, return 0; } +static int rdt_num_rmids_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_rmid); + + return 0; +} + +static int rdt_mon_features_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + struct mon_evt *mevt; + + list_for_each_entry(mevt, &r->evt_list, list) + seq_printf(seq, "%s\n", mevt->name); + + return 0; +} + static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -563,74 +654,200 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of, return 0; } +static int max_threshold_occ_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale); + + return 0; +} + +static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + unsigned int bytes; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + if (bytes > (boot_cpu_data.x86_cache_size * 1024)) + return -EINVAL; + + intel_cqm_threshold = bytes / r->mon_scale; + + return nbytes; +} + /* rdtgroup information files for one cache resource. */ -static struct rftype res_cache_info_files[] = { +static struct rftype res_common_files[] = { { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_closids_show, + .fflags = RF_CTRL_INFO, + }, + { + .name = "mon_features", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_mon_features_show, + .fflags = RF_MON_INFO, + }, + { + .name = "num_rmids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_rmids_show, + .fflags = RF_MON_INFO, }, { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_default_ctrl_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_cbm_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_cbm_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, -}; - -/* rdtgroup information files for memory bandwidth. */ -static struct rftype res_mba_info_files[] = { { - .name = "num_closids", + .name = "shareable_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_num_closids_show, + .seq_show = rdt_shareable_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_bw_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "bandwidth_gran", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bw_gran_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "delay_linear", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_delay_linear_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "max_threshold_occupancy", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = max_threshold_occ_write, + .seq_show = max_threshold_occ_show, + .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "cpus_list", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .flags = RFTYPE_FLAGS_CPUS_LIST, + .fflags = RFTYPE_BASE, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + .fflags = RF_CTRL_BASE, }, }; -void rdt_get_mba_infofile(struct rdt_resource *r) +static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) { - r->info_files = res_mba_info_files; - r->nr_info_files = ARRAY_SIZE(res_mba_info_files); + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + if ((fflags & rft->fflags) == rft->fflags) { + 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) { + if ((fflags & rft->fflags) == rft->fflags) + kernfs_remove_by_name(kn, rft->name); + } + return ret; } -void rdt_get_cache_infofile(struct rdt_resource *r) +static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, + unsigned long fflags) { - r->info_files = res_cache_info_files; - r->nr_info_files = ARRAY_SIZE(res_cache_info_files); + struct kernfs_node *kn_subdir; + int ret; + + kn_subdir = kernfs_create_dir(kn_info, name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) + return PTR_ERR(kn_subdir); + + kernfs_get(kn_subdir); + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + return ret; + + ret = rdtgroup_add_files(kn_subdir, fflags); + if (!ret) + kernfs_activate(kn_subdir); + + return ret; } static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) { - struct kernfs_node *kn_subdir; - struct rftype *res_info_files; struct rdt_resource *r; - int ret, len; + unsigned long fflags; + char name[32]; + int ret; /* create the directory */ kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); @@ -638,25 +855,19 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) 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); + for_each_alloc_enabled_rdt_resource(r) { + fflags = r->fflags | RF_CTRL_INFO; + ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); if (ret) goto out_destroy; + } - res_info_files = r->info_files; - len = r->nr_info_files; - - ret = rdtgroup_add_files(kn_subdir, res_info_files, len); + for_each_mon_enabled_rdt_resource(r) { + fflags = r->fflags | RF_MON_INFO; + sprintf(name, "%s_MON", r->name); + ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) goto out_destroy; - kernfs_activate(kn_subdir); } /* @@ -678,6 +889,39 @@ out_destroy: return ret; } +static int +mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, + char *name, struct kernfs_node **dest_kn) +{ + struct kernfs_node *kn; + int ret; + + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + if (dest_kn) + *dest_kn = kn; + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that @rdtgrp->kn is always accessible. + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} static void l3_qos_cfg_update(void *arg) { bool *enable = arg; @@ -718,14 +962,15 @@ static int cdp_enable(void) struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; int ret; - if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + if (!r_l3->alloc_capable || !r_l3data->alloc_capable || + !r_l3code->alloc_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; + r_l3->alloc_enabled = false; + r_l3data->alloc_enabled = true; + r_l3code->alloc_enabled = true; } return ret; } @@ -734,11 +979,11 @@ static void cdp_disable(void) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; - r->enabled = r->capable; + r->alloc_enabled = r->alloc_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; + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false; set_l3_qos_cfg(r, false); } } @@ -823,10 +1068,16 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) } } +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **mon_data_kn); + static struct dentry *rdt_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { + struct rdt_domain *dom; + struct rdt_resource *r; struct dentry *dentry; int ret; @@ -853,15 +1104,54 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out_cdp; } + if (rdt_mon_capable) { + ret = mongroup_create_dir(rdtgroup_default.kn, + NULL, "mon_groups", + &kn_mongrp); + if (ret) { + dentry = ERR_PTR(ret); + goto out_info; + } + kernfs_get(kn_mongrp); + + ret = mkdir_mondata_all(rdtgroup_default.kn, + &rdtgroup_default, &kn_mondata); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mongrp; + } + kernfs_get(kn_mondata); + rdtgroup_default.mon.mon_data_kn = kn_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_destroy; + goto out_mondata; + + if (rdt_alloc_capable) + static_branch_enable(&rdt_alloc_enable_key); + if (rdt_mon_capable) + static_branch_enable(&rdt_mon_enable_key); + + if (rdt_alloc_capable || rdt_mon_capable) + static_branch_enable(&rdt_enable_key); + + if (is_mbm_enabled()) { + r = &rdt_resources_all[RDT_RESOURCE_L3]; + list_for_each_entry(dom, &r->domains, list) + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + } - static_branch_enable(&rdt_enable_key); goto out; -out_destroy: +out_mondata: + if (rdt_mon_capable) + kernfs_remove(kn_mondata); +out_mongrp: + if (rdt_mon_capable) + kernfs_remove(kn_mongrp); +out_info: kernfs_remove(kn_info); out_cdp: cdp_disable(); @@ -909,6 +1199,18 @@ static int reset_all_ctrls(struct rdt_resource *r) return 0; } +static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_alloc_capable && + (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); +} + +static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_mon_capable && + (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); +} + /* * Move tasks from one to the other group. If @from is NULL, then all tasks * in the systems are moved unconditionally (used for teardown). @@ -924,8 +1226,11 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_lock(&tasklist_lock); for_each_process_thread(p, t) { - if (!from || t->closid == from->closid) { + if (!from || is_closid_match(t, from) || + is_rmid_match(t, from)) { t->closid = to->closid; + t->rmid = to->mon.rmid; + #ifdef CONFIG_SMP /* * This is safe on x86 w/o barriers as the ordering @@ -944,6 +1249,19 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_unlock(&tasklist_lock); } +static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) +{ + struct rdtgroup *sentry, *stmp; + struct list_head *head; + + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { + free_rmid(sentry->mon.rmid); + list_del(&sentry->mon.crdtgrp_list); + kfree(sentry); + } +} + /* * Forcibly remove all of subdirectories under root. */ @@ -955,6 +1273,9 @@ static void rmdir_all_sub(void) rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Free any child rmids */ + free_all_child_rdtgrp(rdtgrp); + /* Remove each rdtgroup other than root */ if (rdtgrp == &rdtgroup_default) continue; @@ -967,16 +1288,20 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + free_rmid(rdtgrp->mon.rmid); + 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); + update_closid_rmid(cpu_online_mask, &rdtgroup_default); put_online_cpus(); kernfs_remove(kn_info); + kernfs_remove(kn_mongrp); + kernfs_remove(kn_mondata); } static void rdt_kill_sb(struct super_block *sb) @@ -986,10 +1311,12 @@ static void rdt_kill_sb(struct super_block *sb) mutex_lock(&rdtgroup_mutex); /*Put everything back to default values. */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); + static_branch_disable(&rdt_alloc_enable_key); + static_branch_disable(&rdt_mon_enable_key); static_branch_disable(&rdt_enable_key); kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); @@ -1001,46 +1328,223 @@ static struct file_system_type rdt_fs_type = { .kill_sb = rdt_kill_sb, }; -static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, - umode_t mode) +static int mon_addfile(struct kernfs_node *parent_kn, const char *name, + void *priv) { - struct rdtgroup *parent, *rdtgrp; struct kernfs_node *kn; - int ret, closid; + int ret = 0; - /* Only allow mkdir in the root directory */ - if (parent_kn != rdtgroup_default.kn) - return -EPERM; + kn = __kernfs_create_file(parent_kn, name, 0444, 0, + &kf_mondata_ops, priv, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); - /* Do not accept '\n' to avoid unparsable situation. */ - if (strchr(name, '\n')) - return -EINVAL; + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } - parent = rdtgroup_kn_lock_live(parent_kn); - if (!parent) { - ret = -ENODEV; - goto out_unlock; + return ret; +} + +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups with given domain id. + */ +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + sprintf(name, "mon_%s_%02d", r->name, dom_id); + kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); } +} - ret = closid_alloc(); - if (ret < 0) +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + union mon_data_bits priv; + struct kernfs_node *kn; + struct mon_evt *mevt; + struct rmid_read rr; + char name[32]; + int ret; + + sprintf(name, "mon_%s_%02d", r->name, d->id); + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that kn is always accessible. + */ + kernfs_get(kn); + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + if (WARN_ON(list_empty(&r->evt_list))) { + ret = -EPERM; + goto out_destroy; + } + + priv.u.rid = r->rid; + priv.u.domid = d->id; + list_for_each_entry(mevt, &r->evt_list, list) { + priv.u.evtid = mevt->evtid; + ret = mon_addfile(kn, mevt->name, priv.priv); + if (ret) + goto out_destroy; + + if (is_mbm_event(mevt->evtid)) + mon_event_read(&rr, d, prgrp, mevt->evtid, true); + } + kernfs_activate(kn); + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +/* + * Add all subdirectories of mon_data for "ctrl_mon" groups + * and "monitor" groups with given domain id. + */ +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d) +{ + struct kernfs_node *parent_kn; + struct rdtgroup *prgrp, *crgrp; + struct list_head *head; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + parent_kn = prgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, prgrp); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + parent_kn = crgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, crgrp); + } + } +} + +static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, + struct rdt_resource *r, + struct rdtgroup *prgrp) +{ + struct rdt_domain *dom; + int ret; + + list_for_each_entry(dom, &r->domains, list) { + ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + if (ret) + return ret; + } + + return 0; +} + +/* + * This creates a directory mon_data which contains the monitored data. + * + * mon_data has one directory for each domain whic are named + * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data + * with L3 domain looks as below: + * ./mon_data: + * mon_L3_00 + * mon_L3_01 + * mon_L3_02 + * ... + * + * Each domain directory has one file per event: + * ./mon_L3_00/: + * llc_occupancy + * + */ +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **dest_kn) +{ + struct rdt_resource *r; + struct kernfs_node *kn; + int ret; + + /* + * Create the mon_data directory first. + */ + ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + if (ret) + return ret; + + if (dest_kn) + *dest_kn = kn; + + /* + * Create the subdirectories for each domain. Note that all events + * in a domain like L3 are grouped into a resource whose domain is L3 + */ + for_each_mon_enabled_rdt_resource(r) { + ret = mkdir_mondata_subdir_alldom(kn, r, prgrp); + if (ret) + goto out_destroy; + } + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode, + enum rdt_group_type rtype, struct rdtgroup **r) +{ + struct rdtgroup *prdtgrp, *rdtgrp; + struct kernfs_node *kn; + uint files = 0; + int ret; + + prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); + if (!prdtgrp) { + ret = -ENODEV; goto out_unlock; - closid = ret; + } /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { ret = -ENOSPC; - goto out_closid_free; + goto out_unlock; } - rdtgrp->closid = closid; - list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + *r = rdtgrp; + rdtgrp->mon.parent = prdtgrp; + rdtgrp->type = rtype; + INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list); /* kernfs creates the directory for rdtgrp */ - kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); + kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); - goto out_cancel_ref; + goto out_free_rgrp; } rdtgrp->kn = kn; @@ -1056,43 +1560,211 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; - ret = rdtgroup_add_files(kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); + files = RFTYPE_BASE | RFTYPE_CTRL; + files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + ret = rdtgroup_add_files(kn, files); if (ret) goto out_destroy; + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) + goto out_destroy; + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) + goto out_idfree; + } kernfs_activate(kn); - ret = 0; - goto out_unlock; + /* + * The caller unlocks the prgrp_kn upon success. + */ + return 0; +out_idfree: + free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_remove(rdtgrp->kn); -out_cancel_ref: - list_del(&rdtgrp->rdtgroup_list); +out_free_rgrp: kfree(rdtgrp); -out_closid_free: - closid_free(closid); out_unlock: - rdtgroup_kn_unlock(parent_kn); + rdtgroup_kn_unlock(prgrp_kn); return ret; } -static int rdtgroup_rmdir(struct kernfs_node *kn) +static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) +{ + kernfs_remove(rgrp->kn); + free_rmid(rgrp->mon.rmid); + kfree(rgrp); +} + +/* + * Create a monitor group under "mon_groups" directory of a control + * and monitor group(ctrl_mon). This is a resource group + * to monitor a subset of tasks and cpus in its parent ctrl_mon group. + */ +static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, + umode_t mode) +{ + struct rdtgroup *rdtgrp, *prgrp; + int ret; + + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP, + &rdtgrp); + if (ret) + return ret; + + prgrp = rdtgrp->mon.parent; + rdtgrp->closid = prgrp->closid; + + /* + * Add the rdtgrp to the list of rdtgrps the parent + * ctrl_mon group has to track. + */ + list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); + + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * These are rdtgroups created under the root directory. Can be used + * to allocate and monitor resources. + */ +static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode) { - int ret, cpu, closid = rdtgroup_default.closid; struct rdtgroup *rdtgrp; - cpumask_var_t tmpmask; + struct kernfs_node *kn; + u32 closid; + int ret; - if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) - return -ENOMEM; + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP, + &rdtgrp); + if (ret) + return ret; - rdtgrp = rdtgroup_kn_lock_live(kn); - if (!rdtgrp) { - ret = -EPERM; - goto out; + kn = rdtgrp->kn; + ret = closid_alloc(); + if (ret < 0) + goto out_common_fail; + closid = ret; + + rdtgrp->closid = closid; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + if (rdt_mon_capable) { + /* + * Create an empty mon_groups directory to hold the subset + * of tasks and cpus to monitor. + */ + ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + if (ret) + goto out_id_free; } + goto out_unlock; + +out_id_free: + closid_free(closid); + list_del(&rdtgrp->rdtgroup_list); +out_common_fail: + mkdir_rdt_prepare_clean(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * We allow creating mon groups only with in a directory called "mon_groups" + * which is present in every ctrl_mon group. Check if this is a valid + * "mon_groups" directory. + * + * 1. The directory should be named "mon_groups". + * 2. The mon group itself should "not" be named "mon_groups". + * This makes sure "mon_groups" directory always has a ctrl_mon group + * as parent. + */ +static bool is_mon_groups(struct kernfs_node *kn, const char *name) +{ + return (!strcmp(kn->name, "mon_groups") && + strcmp(name, "mon_groups")); +} + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + /* + * If the parent directory is the root directory and RDT + * allocation is supported, add a control and monitoring + * subdirectory + */ + if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode); + + /* + * If RDT monitoring is supported and the parent directory is a valid + * "mon_groups" directory, add a monitoring subdirectory. + */ + if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode); + + return -EPERM; +} + +static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + int cpu; + + /* Give any tasks back to the parent group */ + rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); + + /* Update per cpu rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + update_closid_rmid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + free_rmid(rdtgrp->mon.rmid); + + /* + * Remove the rdtgrp from the parent ctrl_mon group's list + */ + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_del(&rdtgrp->mon.crdtgrp_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + + return 0; +} + +static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + int cpu; + /* Give any tasks back to the default group */ rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); @@ -1100,18 +1772,28 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) 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 per cpu closid and rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) { + per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid; + per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid; + } + /* * 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); + update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); + free_rmid(rdtgrp->mon.rmid); + + /* + * Free all the child monitor group rmids. + */ + free_all_child_rdtgrp(rdtgrp); + list_del(&rdtgrp->rdtgroup_list); /* @@ -1120,7 +1802,41 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) */ kernfs_get(kn); kernfs_remove(rdtgrp->kn); - ret = 0; + + return 0; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + struct kernfs_node *parent_kn = kn->parent; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret = 0; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* + * If the rdtgroup is a ctrl_mon group and parent directory + * is the root directory, remove the ctrl_mon group. + * + * If the rdtgroup is a mon group and parent directory + * is a valid "mon_groups" directory, remove the mon group. + */ + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) + ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); + else + ret = -EPERM; + out: rdtgroup_kn_unlock(kn); free_cpumask_var(tmpmask); @@ -1129,7 +1845,7 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); return 0; } @@ -1153,10 +1869,13 @@ static int __init rdtgroup_setup_root(void) mutex_lock(&rdtgroup_mutex); rdtgroup_default.closid = 0; + rdtgroup_default.mon.rmid = 0; + rdtgroup_default.type = RDTCTRL_GROUP; + INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); + ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE); if (ret) { kernfs_destroy_root(rdt_root); goto out; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index efc5eeb58292..11966251cd42 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -56,7 +56,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/proto.h> 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 c85269a76511..302e7b2572d1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/unistd.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 718ba163c1b9..8e22f24ded6a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -139,14 +139,6 @@ struct hw_perf_event { /* for tp_event->class */ struct list_head tp_list; }; - struct { /* intel_cqm */ - int cqm_state; - u32 cqm_rmid; - int is_group_event; - struct list_head cqm_events_entry; - struct list_head cqm_groups_entry; - struct list_head cqm_group_entry; - }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; @@ -414,11 +406,6 @@ struct pmu { /* - * Return the count value for a counter. - */ - u64 (*count) (struct perf_event *event); /*optional*/ - - /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (int cpu, void **pages, @@ -1112,11 +1099,6 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, __perf_event_task_sched_out(prev, next); } -static inline u64 __perf_event_count(struct perf_event *event) -{ - return local64_read(&event->count) + atomic64_read(&event->child_count); -} - extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9ba42c663fba..68b38335d33c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -909,8 +909,9 @@ 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; +#ifdef CONFIG_INTEL_RDT + u32 closid; + u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; diff --git a/kernel/events/core.c b/kernel/events/core.c index ce64f3fed5c6..294f1927f944 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3673,10 +3673,7 @@ unlock: static inline u64 perf_event_count(struct perf_event *event) { - if (event->pmu->count) - return event->pmu->count(event); - - return __perf_event_count(event); + return local64_read(&event->count) + atomic64_read(&event->child_count); } /* @@ -3707,15 +3704,6 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; } - /* - * It must not have a pmu::count method, those are not - * NMI safe. - */ - if (event->pmu->count) { - ret = -EOPNOTSUPP; - goto out; - } - /* If this is a per-task event, it must be for current */ if ((event->attach_state & PERF_ATTACH_TASK) && event->hw.target != current) { |