Changes in monitor.c

79727019ce3da234d877ec0cb6a3985f001e2b2d - fs/resctrl: Add missing return value descriptions

Tue, 07 Apr 2026 18:01:59 +0200

fs/resctrl: Add missing return value descriptionsUsing the stricter "./tools/docs/kernel-doc -Wall -v" to verify properformatting of documentation comments includes warnings related to returnmarkup on functions that are omitted during the default verificationchecks. This stricter verification reports a couple of missing returndescriptions in resctrl: Warning: .../fs/resctrl/rdtgroup.c:1536 No description found for return value of 'rdtgroup_cbm_to_size' Warning: .../fs/resctrl/rdtgroup.c:3131 No description found for return value of 'mon_get_kn_priv' Warning: .../fs/resctrl/rdtgroup.c:3523 No description found for return value of 'cbm_ensure_valid' Warning: .../fs/resctrl/monitor.c:238 No description found for return value of 'resctrl_find_cleanest_closid'Add the missing return descriptions.Signed-off-by: Reinette Chatre Signed-off-by: Borislav Petkov (AMD) Link: https://patch.msgid.link/1c50b9f7c73251c007133590986f127e1af57780.1775576382.git.reinette.chatre@intel.com List of files: /linux/fs/resctrl/monitor.c

bf4afc53b77aeaa48b5409da5c8da6bb4eff7f43 - Convert 'alloc_obj' family to use the new default GFP_KERNEL argument

Sun, 22 Feb 2026 01:37:42 +0100

Convert 'alloc_obj' family to use the new default GFP_KERNEL argumentThis was done entirely with mindless brute force, using git grep -l '\ List of files: /linux/fs/resctrl/monitor.c

69050f8d6d075dc01af7a5f2f550a8067510366f - treewide: Replace kmalloc with kmalloc_obj for non-scalar types

Sat, 21 Feb 2026 08:49:23 +0100

treewide: Replace kmalloc with kmalloc_obj for non-scalar typesThis is the result of running the Coccinelle script fromscripts/coccinelle/api/kmalloc_objs.cocci. The script is designed toavoid scalar types (which need careful case-by-case checking), andinstead replace kmalloc-family calls that allocate struct or unionobject instances:Single allocations: kmalloc(sizeof(TYPE), ...)are replaced with: kmalloc_obj(TYPE, ...)Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)are replaced with: kmalloc_objs(TYPE, COUNT, ...)Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)(where TYPE may also be *VAR)The resulting allocations no longer return "void *", instead returning"TYPE *".Signed-off-by: Kees Cook List of files: /linux/fs/resctrl/monitor.c

d0891647fbc6e931f27517364cbc4ee1811d76db - fs/resctrl: Move RMID initialization to first mount

Wed, 17 Dec 2025 18:21:15 +0100

fs/resctrl: Move RMID initialization to first mountL3 monitor features are enumerated during resctrl initialization andrmid_ptrs[] that tracks all RMIDs and depends on the number of supportedRMIDs is allocated during this time.Telemetry monitor features are enumerated during first resctrl mount andmay support a different number of RMIDs compared to L3 monitor features.Delay allocation and initialization of rmid_ptrs[] until first mount.Since the number of RMIDs cannot change on later mounts, keep the same set ofrmid_ptrs[] until resctrl_exit(). This is required because the limbo handlerkeeps running after resctrl is unmounted and needs to access rmid_ptrs[]as it keeps tracking busy RMIDs after unmount.Rename routines to match what they now do:dom_data_init() -> setup_rmid_lru_list()dom_data_exit() -> free_rmid_lru_list()Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

ee7f6af79f0916b6c49e15edd4cba020b3e4c4ac - fs/resctrl: Move allocation/free of closid_num_dirty_rmid[]

Wed, 17 Dec 2025 18:21:13 +0100

fs/resctrl: Move allocation/free of closid_num_dirty_rmid[]closid_num_dirty_rmid[] and rmid_ptrs[] are allocated together during resctrlinitialization and freed together during resctrl exit.Telemetry events are enumerated on resctrl mount so only at resctrl mount willthe number of RMID supported by all monitoring resources and needed as sizefor rmid_ptrs[] be known.Separate closid_num_dirty_rmid[] and rmid_ptrs[] allocation and free inpreparation for rmid_ptrs[] to be allocated on resctrl mount.Keep the rdtgroup_mutex protection around the allocation and free ofclosid_num_dirty_rmid[] as ARM needs this to guarantee memory ordering.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

51541f6ca7718d8278e12fe80af80033268743b2 - x86/resctrl: Read telemetry events

Wed, 17 Dec 2025 18:21:07 +0100

x86/resctrl: Read telemetry eventsIntroduce intel_aet_read_event() to read telemetry events for resourceRDT_RESOURCE_PERF_PKG. There may be multiple aggregators tracking eachpackage, so scan all of them and add up all counters. Aggregators may returnan invalid data indication if they have received no records for a given RMID.The user will see "Unavailable" if none of the aggregators on a packageprovide valid counts.Resctrl now uses readq() so depends on X86_64. Update Kconfig.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

7e6df9614546ae7eb1f1b2074d7b6039bb01540d - x86/resctrl: Find and enable usable telemetry events

Wed, 17 Dec 2025 18:21:06 +0100

x86/resctrl: Find and enable usable telemetry eventsEvery event group has a private copy of the data of all telemetry eventaggregators (aka "telemetry regions") tracking its feature type. Includedmay be regions that have the same feature type but tracking different GUIDfrom the event group's.Traverse the event group's telemetry region data and mark all regions thatare not usable by the event group as unusable by clearing those regions'MMIO addresses. A region is considered unusable if:1) GUID does not match the GUID of the event group.2) Package ID is invalid.3) The enumerated size of the MMIO region does not match the expected value from the XML description file.Hereafter any telemetry region with an MMIO address is considered valid forthe event group it is associated with.Enable all the event group's events as long as there is at least one usableregion from where data for its events can be read. Enabling of an event canfail if the same event has already been enabled as part of another eventgroup. It should never happen that the same event is described by differentGUID supported by the same system so just WARN (via resctrl_enable_mon_event())and skip the event.Note that it is architecturally possible that some telemetry events are onlysupported by a subset of the packages in the system. It is not expected thatsystems will ever do this. If they do the user will see event files in resctrlthat always return "Unavailable".Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

8ccb1f8fa6a3dfde32cf33e7ded3558014e6cca2 - x86,fs/resctrl: Add architectural event pointer

Wed, 17 Dec 2025 18:21:05 +0100

x86,fs/resctrl: Add architectural event pointerThe resctrl file system layer passes the domain, RMID, and event id to thearchitecture to fetch an event counter.Fetching a telemetry event counter requires additional information that isprivate to the architecture, for example, the offset into MMIO space fromwhere the counter should be read.Add mon_evt::arch_priv that architecture can use for any private data relatedto the event. The resctrl filesystem initializes mon_evt::arch_priv when thearchitecture enables the event and passes it back to architecture when needingto fetch an event counter.Suggested-by: Reinette Chatre Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

8f6b6ad69b50bf16bb762ffafbfa44a4884f9a17 - x86,fs/resctrl: Fill in details of events for performance and energy GUIDs

Wed, 17 Dec 2025 18:21:04 +0100

x86,fs/resctrl: Fill in details of events for performance and energy GUIDsThe telemetry event aggregators of the Intel Clearwater Forest CPU support twoRMID-based feature types: "energy" with GUID 0x26696143¹, and "perf" withGUID 0x26557651².The event counter offsets in an aggregator's MMIO space are arranged in groupsfor each RMID.E.g., the "energy" counters for GUID 0x26696143 are arranged like this: MMIO offset:0x0000 Counter for RMID 0 PMT_EVENT_ENERGY MMIO offset:0x0008 Counter for RMID 0 PMT_EVENT_ACTIVITY MMIO offset:0x0010 Counter for RMID 1 PMT_EVENT_ENERGY MMIO offset:0x0018 Counter for RMID 1 PMT_EVENT_ACTIVITY ... MMIO offset:0x23F0 Counter for RMID 575 PMT_EVENT_ENERGY MMIO offset:0x23F8 Counter for RMID 575 PMT_EVENT_ACTIVITYAfter all counters there are three status registers that provide indicationsof how many times an aggregator was unable to process event counts, the timestamp for the most recent loss of data, and the time stamp of the most recentsuccessful update. MMIO offset:0x2400 AGG_DATA_LOSS_COUNT MMIO offset:0x2408 AGG_DATA_LOSS_TIMESTAMP MMIO offset:0x2410 LAST_UPDATE_TIMESTAMPDefine event_group structures for both of these aggregator types and definethe events tracked by the aggregators in the file system code.PMT_EVENT_ENERGY and PMT_EVENT_ACTIVITY are produced in fixed point format.File system code must output as floating point values. ¹https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml ²https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml [ bp: Massage commit message. ]Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

e37c9a3dc9f9645532780d5ef34ea3b8fcf9ddef - x86,fs/resctrl: Support binary fixed point event counters

Wed, 17 Dec 2025 18:20:59 +0100

x86,fs/resctrl: Support binary fixed point event countersresctrl assumes that all monitor events can be displayed as unsigned decimalintegers.Hardware architecture counters may provide some telemetry events with greaterprecision where the event is not a simple count, but is a measurement of somesort (e.g. Joules for energy consumed).Add a new argument to resctrl_enable_mon_event() for architecture code toinform the file system that the value for a counter is a fixed-point valuewith a specific number of binary places.Only allow architecture to use floating point format on events that the filesystem has marked with mon_evt::is_floating_point which reflects the contractwith user space on how the event values are displayed.Display fixed point values with values rounded to ceil(binary_bits * log10(2))decimal places. Special case for zero binary bits to print "{value}.0".Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

ab0308aee3819a3eccde42f9eb5bb01d6733be38 - x86,fs/resctrl: Handle events that can be read from any CPU

Wed, 17 Dec 2025 18:20:58 +0100

x86,fs/resctrl: Handle events that can be read from any CPUresctrl assumes that monitor events can only be read from a CPU in thecpumask_t set of each domain. This is true for x86 events accessed with anMSR interface, but may not be true for other access methods such as MMIO.Introduce and use flag mon_evt::any_cpu, settable by architecture, thatindicates there are no restrictions on which CPU can read that event. Thisflag is not supported by the L3 event reading that requires to be run on a CPUthat belongs to the L3 domain of the event being read.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

dd110880e80d35ad07e460e7a8da007c8058e7bf - fs/resctrl: Make event details accessible to functions when reading events

Wed, 17 Dec 2025 18:20:57 +0100

fs/resctrl: Make event details accessible to functions when reading eventsReading monitoring event data from MMIO requires more context than the event idto be able to read the correct memory location. struct mon_evt is the appropriateplace for this event specific context.Prepare for addition of extra fields to struct mon_evt by changing the callingconventions to pass a pointer to the mon_evt structure instead of just theevent id.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

9c214d10c50990c7a61b95887493df9ae713eec5 - x86,fs/resctrl: Rename some L3 specific functions

Wed, 17 Dec 2025 18:20:56 +0100

x86,fs/resctrl: Rename some L3 specific functionsWith the arrival of monitor events tied to new domains associated with adifferent resource it would be clearer if the L3 resource specific functionsare more accurately named.Rename three groups of functions:Functions that allocate/free architecture per-RMID MBM state information:arch_domain_mbm_alloc() -> l3_mon_domain_mbm_alloc()mon_domain_free() -> l3_mon_domain_free()Functions that allocate/free filesystem per-RMID MBM state information:domain_setup_mon_state() -> domain_setup_l3_mon_state()domain_destroy_mon_state() -> domain_destroy_l3_mon_state()Initialization/exit:rdt_get_mon_l3_config() -> rdt_get_l3_mon_config()resctrl_mon_resource_init() -> resctrl_l3_mon_resource_init()resctrl_mon_resource_exit() -> resctrl_l3_mon_resource_exit()Ensure kernel-doc descriptions of these functions' return values are presentand correctly formatted.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

4bc3ef46ff41d5e7ba557e56e9cd2031527cd7f8 - x86,fs/resctrl: Rename struct rdt_mon_domain and rdt_hw_mon_domain

Wed, 17 Dec 2025 18:20:55 +0100

x86,fs/resctrl: Rename struct rdt_mon_domain and rdt_hw_mon_domainThe upcoming telemetry event monitoring is not tied to the L3 resource andwill have a new domain structure.Rename the L3 resource specific domain data structures to include "l3_"in their names to avoid confusion between the different resource specificdomain structures:rdt_mon_domain -> rdt_l3_mon_domainrdt_hw_mon_domain -> rdt_hw_l3_mon_domainNo functional change.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

6b10cf7b6ea857cdf9570e21c077a05803f60575 - x86,fs/resctrl: Use struct rdt_domain_hdr when reading counters

Wed, 17 Dec 2025 18:20:54 +0100

x86,fs/resctrl: Use struct rdt_domain_hdr when reading countersConvert the whole call sequence from mon_event_read() to resctrl_arch_rmid_read() topass resource independent struct rdt_domain_hdr instead of an L3 specific domainstructure to prepare for monitoring events in other resources.This additional layer of indirection obscures which aspects of event counting dependon a valid domain. Event initialization, support for assignable counters, and normalevent counting implicitly depend on a valid domain while summing of domains does not.Split summing domains from the core event counting handling to make their respectivedependencies obvious.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

ad5c2ff75e0c53d2588dfc10eb87458e759b6bbe - fs/resctrl: Split L3 dependent parts out of __mon_event_count()

Wed, 17 Dec 2025 18:20:53 +0100

fs/resctrl: Split L3 dependent parts out of __mon_event_count()Carve out the L3 resource specific event reading code into a separate helperto support reading event data from a new monitoring resource.Suggested-by: Reinette Chatre Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com List of files: /linux/fs/resctrl/monitor.c

19de7113bfac33ba92c004a9b510612bb745cfa0 - x86,fs/resctrl: Fix NULL pointer dereference with events force-disabled in mbm_event mode

Thu, 16 Oct 2025 15:34:19 +0200

x86,fs/resctrl: Fix NULL pointer dereference with events force-disabled in mbm_event modeThe following NULL pointer dereference is encountered on mount of resctrl fsafter booting a system that supports assignable counters with the"rdt=!mbmtotal,!mbmlocal" kernel parameters: BUG: kernel NULL pointer dereference, address: 0000000000000008 RIP: 0010:mbm_cntr_get Call Trace: rdtgroup_assign_cntr_event rdtgroup_assign_cntrs rdt_get_treeSpecifying the kernel parameter "rdt=!mbmtotal,!mbmlocal" effectively disablesthe legacy X86_FEATURE_CQM_MBM_TOTAL and X86_FEATURE_CQM_MBM_LOCAL featuresand the MBM events they represent. This results in the per-domain MBM eventrelated data structures to not be allocated during early initialization.resctrl fs initialization follows by implicitly enabling both MBM total andlocal events on a system that supports assignable counters (mbm_event mode),but this enabling occurs after the per-domain data structures have beencreated.After booting, resctrl fs assumes that an enabled event can access all itsstate. This results in NULL pointer dereference when resctrl attempts toaccess the un-allocated structures of an enabled event.Remove the late MBM event enabling from resctrl fs.This leaves a problem where the X86_FEATURE_CQM_MBM_TOTAL andX86_FEATURE_CQM_MBM_LOCAL features may be disabled while assignable counter(mbm_event) mode is enabled without any events to support. Switching betweenthe "default" and "mbm_event" mode without any events is not practical.Create a dependency between the X86_FEATURE_{CQM_MBM_TOTAL,CQM_MBM_LOCAL} andX86_FEATURE_ABMC (assignable counter) hardware features. An x86 system thatsupports assignable counters now requires support of X86_FEATURE_CQM_MBM_TOTALor X86_FEATURE_CQM_MBM_LOCAL.This ensures all needed MBM related data structures are created before use andthat it is only possible to switch between "default" and "mbm_event" mode whenthe same events are available in both modes. This dependency does not exist inthe hardware but this usage of these feature settings work for known systems. [ bp: Massage commit message. ]Fixes: 13390861b426e ("x86,fs/resctrl: Detect Assignable Bandwidth Monitoring feature details")Co-developed-by: Reinette Chatre Signed-off-by: Reinette Chatre Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://patch.msgid.link/a62e6ac063d0693475615edd213d5be5e55443e6.1760560934.git.babu.moger@amd.com List of files: /linux/fs/resctrl/monitor.c

dd86b69d20fb9fa7e941ed01ff05f1e662fcc3ff - fs/resctrl: Fix counter auto-assignment on mkdir with mbm_event enabled

Tue, 16 Sep 2025 19:25:49 +0200

fs/resctrl: Fix counter auto-assignment on mkdir with mbm_event enabledrdt_resource::resctrl_mon::mbm_assign_on_mkdir determines if a counter willautomatically be assigned to an RMID, MBM event pair when its associatedmonitor group is created via mkdir.Testing shows that counters are always automatically assigned to new monitorgroups, whether mbm_assign_on_mkdir is set or not.To support automatic counter assignment the check for mbm_assign_on_mkdirshould be in rdtgroup_assign_cntrs() that assigns counters during monitorgroup creation. Instead, the check for mbm_assign_on_mkdir is inrdtgroup_unassign_cntrs() that is called on monitor group deletion from wherecounters should always be unassigned, whether mbm_assign_on_mkdir is set ornot.Fix automatic counter assignment by moving the mbm_assign_on_mkdir check fromrdtgroup_unassign_cntrs() to rdtgroup_assign_cntrs(). [ bp: Replace commit message with Reinette's version. ]Fixes: ef712fe97ec57 ("fs/resctrl: Auto assign counters on mkdir and clean up on group removal")Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Acked-by: Reinette Chatre List of files: /linux/fs/resctrl/monitor.c

8004ea01cf6338298e0c6ab055bc3ec659ce381b - fs/resctrl: Introduce the interface to switch between monitor modes

Fri, 05 Sep 2025 23:34:30 +0200

fs/resctrl: Introduce the interface to switch between monitor modesResctrl subsystem can support two monitoring modes, "mbm_event" or "default".In mbm_event mode, monitoring event can only accumulate data while it isbacked by a hardware counter. In "default" mode, resctrl assumes there isa hardware counter for each event within every CTRL_MON and MON group.Introduce mbm_assign_mode resctrl file to switch between mbm_event and defaultmodes.Example:To list the MBM monitor modes supported: $ cat /sys/fs/resctrl/info/L3_MON/mbm_assign_mode [mbm_event] defaultTo enable the "mbm_event" counter assignment mode: $ echo "mbm_event" > /sys/fs/resctrl/info/L3_MON/mbm_assign_modeTo enable the "default" monitoring mode: $ echo "default" > /sys/fs/resctrl/info/L3_MON/mbm_assign_modeReset MBM event counters automatically as part of changing the mode. Clearboth architectural and non-architectural event states to prevent overflowconditions during the next event read. Clear assignable counter configurationon all the domains. Also, enable auto assignment when switching to "mbm_event"mode.Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com List of files: /linux/fs/resctrl/monitor.c

88bee79640aea6192f98c8faae30e0013453479d - fs/resctrl: Introduce the interface to modify assignments in a group

Fri, 05 Sep 2025 23:34:28 +0200

fs/resctrl: Introduce the interface to modify assignments in a groupEnable the mbm_l3_assignments resctrl file to be used to modify counterassignments of CTRL_MON and MON groups when the "mbm_event" counterassignment mode is enabled.Process the assignment modifications in the following format::=;=Event: A valid MBM event in the /sys/fs/resctrl/info/L3_MON/event_configs directory.Domain ID: A valid domain ID. When writing, '*' applies the changes to all domains.Assignment states: _ : Unassign a counter. e : Assign a counter exclusively.Examples: $ cd /sys/fs/resctrl $ cat /sys/fs/resctrl/mbm_L3_assignments mbm_total_bytes:0=e;1=e mbm_local_bytes:0=e;1=eTo unassign the counter associated with the mbm_total_bytes event ondomain 0: $ echo "mbm_total_bytes:0=_" > mbm_L3_assignments $ cat /sys/fs/resctrl/mbm_L3_assignments mbm_total_bytes:0=_;1=e mbm_local_bytes:0=e;1=eTo unassign the counter associated with the mbm_total_bytes event onall the domains: $ echo "mbm_total_bytes:*=_" > mbm_L3_assignments $ cat /sys/fs/resctrl/mbm_L3_assignments mbm_total_bytes:0=_;1=_ mbm_local_bytes:0=e;1=eSigned-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com List of files: /linux/fs/resctrl/monitor.c