diff --git a/Documentation/cgroup-v1/cgroups.txt b/Documentation/cgroup-v1/cgroups.txt index 308e5ff7207a351e0cf66946bd3e0c4190cd106a..059f7063eea6a081fd9891bca249594993654ce6 100644 --- a/Documentation/cgroup-v1/cgroups.txt +++ b/Documentation/cgroup-v1/cgroups.txt @@ -523,12 +523,7 @@ Accessing a task's cgroup pointer may be done in the following ways: Each subsystem should: - add an entry in linux/cgroup_subsys.h -- define a cgroup_subsys object called _subsys - -If a subsystem can be compiled as a module, it should also have in its -module initcall a call to cgroup_load_subsys(), and in its exitcall a -call to cgroup_unload_subsys(). It should also set its_subsys.module = -THIS_MODULE in its .c file. +- define a cgroup_subsys object called _cgrp_subsys Each subsystem may export the following methods. The only mandatory methods are css_alloc/free. Any others that are null are presumed to diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt index cefb6363907003581efe476f569b4bd5660ca194..a4af2e124e246fefd1aafd21c22cd20c43f1248f 100644 --- a/Documentation/cgroup-v1/memory.txt +++ b/Documentation/cgroup-v1/memory.txt @@ -524,9 +524,9 @@ Note: Only anonymous and swap cache memory is listed as part of 'rss' stat. This should not be confused with the true 'resident set size' or the amount of physical memory used by the cgroup. - 'rss + file_mapped" will give you resident set size of cgroup. + 'rss + mapped_file" will give you resident set size of cgroup. (Note: file and shmem may be shared among other cgroups. In that case, - file_mapped is accounted only when the memory cgroup is owner of page + mapped_file is accounted only when the memory cgroup is owner of page cache.) 5.3 swappiness diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 2cddab7efb20df0dcf07c4d7d64a5611138a8d7c..74cdeaed9f7afb4f0b514f1213b38b2eda106f56 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -53,10 +53,14 @@ v1 is available under Documentation/cgroup-v1/. 5-3-2. Writeback 5-4. PID 5-4-1. PID Interface Files - 5-5. RDMA - 5-5-1. RDMA Interface Files - 5-6. Misc - 5-6-1. perf_event + 5-5. Device + 5-6. RDMA + 5-6-1. RDMA Interface Files + 5-7. Misc + 5-7-1. perf_event + 5-N. Non-normative information + 5-N-1. CPU controller root cgroup process behaviour + 5-N-2. IO controller root cgroup process behaviour 6. Namespace 6-1. Basics 6-2. The Root and Views @@ -279,7 +283,7 @@ thread mode, the following conditions must be met. exempt from this requirement. Topology-wise, a cgroup can be in an invalid state. Please consider -the following toplogy:: +the following topology:: A (threaded domain) - B (threaded) - C (domain, just created) @@ -420,7 +424,9 @@ The root cgroup is exempt from this restriction. Root contains processes and anonymous resource consumption which can't be associated with any other cgroups and requires special treatment from most controllers. How resource consumption in the root cgroup is governed -is up to each controller. +is up to each controller (for more information on this topic please +refer to the Non-normative information section in the Controllers +chapter). Note that the restriction doesn't get in the way if there is no enabled controller in the cgroup's "cgroup.subtree_control". This is @@ -1063,10 +1069,10 @@ PAGE_SIZE multiple when read back. reached the limit and allocation was about to fail. Depending on context result could be invocation of OOM - killer and retrying allocation or failing alloction. + killer and retrying allocation or failing allocation. Failed allocation in its turn could be returned into - userspace as -ENOMEM or siletly ignored in cases like + userspace as -ENOMEM or silently ignored in cases like disk readahead. For now OOM in memory cgroup kills tasks iff shortage has happened inside page fault. @@ -1191,7 +1197,7 @@ PAGE_SIZE multiple when read back. cgroups. The default is "max". Swap usage hard limit. If a cgroup's swap usage reaches this - limit, anonymous meomry of the cgroup will not be swapped out. + limit, anonymous memory of the cgroup will not be swapped out. Usage Guidelines @@ -1429,6 +1435,30 @@ through fork() or clone(). These will return -EAGAIN if the creation of a new process would cause a cgroup policy to be violated. +Device controller +----------------- + +Device controller manages access to device files. It includes both +creation of new device files (using mknod), and access to the +existing device files. + +Cgroup v2 device controller has no interface files and is implemented +on top of cgroup BPF. To control access to device files, a user may +create bpf programs of the BPF_CGROUP_DEVICE type and attach them +to cgroups. On an attempt to access a device file, corresponding +BPF programs will be executed, and depending on the return value +the attempt will succeed or fail with -EPERM. + +A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx +structure, which describes the device access attempt: access type +(mknod/read/write) and device (type, major and minor numbers). +If the program returns 0, the attempt fails with -EPERM, otherwise +it succeeds. + +An example of BPF_CGROUP_DEVICE program may be found in the kernel +source tree in the tools/testing/selftests/bpf/dev_cgroup.c file. + + RDMA ---- @@ -1481,6 +1511,35 @@ always be filtered by cgroup v2 path. The controller can still be moved to a legacy hierarchy after v2 hierarchy is populated. +Non-normative information +------------------------- + +This section contains information that isn't considered to be a part of +the stable kernel API and so is subject to change. + + +CPU controller root cgroup process behaviour +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +When distributing CPU cycles in the root cgroup each thread in this +cgroup is treated as if it was hosted in a separate child cgroup of the +root cgroup. This child cgroup weight is dependent on its thread nice +level. + +For details of this mapping see sched_prio_to_weight array in +kernel/sched/core.c file (values from this array should be scaled +appropriately so the neutral - nice 0 - value is 100 instead of 1024). + + +IO controller root cgroup process behaviour +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Root cgroup processes are hosted in an implicit leaf child node. +When distributing IO resources this implicit child node is taken into +account as if it was a normal child cgroup of the root cgroup with a +weight value of 200. + + Namespace ========= diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8b7fd8eeccee26c5694530a45f8f9332aaf681c7..9f242b876fde2c29b1d3c023a3934ef01d04cfa9 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -561,7 +561,7 @@ struct cftype { /* * Control Group subsystem type. - * See Documentation/cgroups/cgroups.txt for details + * See Documentation/cgroup-v1/cgroups.txt for details */ struct cgroup_subsys { struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); diff --git a/include/linux/string.h b/include/linux/string.h index cfd83eb2f926c74622f46ed931bb1c58277df49f..96115bf561b452112f411ecbcd61f5e016b00911 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -28,7 +28,7 @@ extern char * strncpy(char *,const char *, __kernel_size_t); size_t strlcpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRSCPY -ssize_t __must_check strscpy(char *, const char *, size_t); +ssize_t strscpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7e4c4453811967e80250464bd91633e957549375..8cda3bc3ae22841f9c3a9478ae65cadba6b65f66 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1397,7 +1397,7 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); else - strlcpy(buf, cft->name, CGROUP_FILE_NAME_MAX); + strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); return buf; } @@ -1864,9 +1864,9 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts) root->flags = opts->flags; if (opts->release_agent) - strlcpy(root->release_agent_path, opts->release_agent, PATH_MAX); + strscpy(root->release_agent_path, opts->release_agent, PATH_MAX); if (opts->name) - strlcpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN); + strscpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN); if (opts->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); }