xref: /linux/fs/resctrl/Kconfig (revision 664a231d90aa450f9f6f029bee3a94dd08e1aac6)
1config RESCTRL_FS
2	bool "CPU Resource Control Filesystem (resctrl)"
3	depends on ARCH_HAS_CPU_RESCTRL
4	select KERNFS
5	select PROC_CPU_RESCTRL if PROC_FS
6	help
7	  Some architectures provide hardware facilities to group tasks and
8	  monitor and control their usage of memory system resources such as
9	  caches and memory bandwidth.  Examples of such facilities include
10	  Intel's Resource Director Technology (Intel(R) RDT) and AMD's
11	  Platform Quality of Service (AMD QoS).
12
13	  If your system has the necessary support and you want to be able to
14	  assign tasks to groups and manipulate the associated resource
15	  monitors and controls from userspace, say Y here to get a mountable
16	  'resctrl' filesystem that lets you do just that.
17
18	  If nothing mounts or prods the 'resctrl' filesystem, resource
19	  controls and monitors are left in a quiescent, permissive state.
20
21	  On architectures where this can be disabled independently, it is
22	  safe to say N.
23
24	  See <file:Documentation/filesystems/resctrl.rst> for more information.
25
26config RESCTRL_FS_PSEUDO_LOCK
27	bool
28	depends on RESCTRL_FS
29	help
30	  Software mechanism to pin data in a cache portion using
31	  micro-architecture specific knowledge.
32
33config RESCTRL_RMID_DEPENDS_ON_CLOSID
34	bool
35	depends on RESCTRL_FS
36	help
37	  Enabled by the architecture when the RMID values depend on the CLOSID.
38	  This causes the CLOSID allocator to search for CLOSID with clean
39	  RMID.
40