Although it is not typical for real users to create a complicated nested partition hierarchy, it is currently allowed to create nested root and isolated partitions. In addition, disabling or invalidating a partition should always be allowed especially when the cpuset is being deleted.
With a nested root and isolated partition hierarchy, it is possible that all active housekeeping CPUs can be exhausted when disabling or invalidating a root partition and returning its CPUs to the isolated parent. One way to avoid this problem is to disallow the creation of a root partition under an isolated parent. It is indeed a new limitation imposed on the existing cpuset partition functionality. However an isolated partition is usually a left node where scheduling and some other kernel noises are disabled. It doesn't make much sense to create a child root partition under an isolated parent and remove some CPUs from the set of isolated CPUs again. Creation of a child isolated partition under a root or isolated parent is still allowed. If a partition with child root partitions is converted to isolated, the child root partitions will be invalidated. The cgroup-v2 documentation is also updated to reflect this new limitation. New test cases are added to test_cpuset_prs.sh to verify this new behavior. Some existing test cases are also updated accordingly. Signed-off-by: Waiman Long <[email protected]> --- Documentation/admin-guide/cgroup-v2.rst | 4 ++- kernel/cgroup/cpuset-internal.h | 1 + kernel/cgroup/cpuset.c | 32 ++++++++++++++++--- .../selftests/cgroup/test_cpuset_prs.sh | 23 +++++++------ 4 files changed, 46 insertions(+), 14 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index bd8c80f3bbc9..2c445829e24d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2767,7 +2767,9 @@ Cpuset Interface Files be retained, but behaves more like a "member". All possible state transitions among "member", "root" and - "isolated" are allowed. + "isolated" are allowed with the exception that a local child + "root" partition is not allowed to be created under an "isolated" + parent partition. On read, the "cpuset.cpus.partition" file can show the following values. diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index 5da9c91295b0..2e44dc8634dc 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -35,6 +35,7 @@ enum prs_errcode { PERR_HKEEPING, PERR_ACCESS, PERR_REMOTE, + PERR_ISOPARENT, }; /* bits in struct cpuset flags field */ diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5a0a4269e7c0..0f047d6bbd9a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -60,6 +60,7 @@ static const char * const perr_strings[] = { [PERR_HKEEPING] = "partition config conflicts with housekeeping setup", [PERR_ACCESS] = "Enable partition not permitted", [PERR_REMOTE] = "Have remote partition underneath", + [PERR_ISOPARENT] = "Root partition is not allowed with isolated parent", }; /* @@ -1899,6 +1900,10 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, part_error = PERR_CPUSEMPTY; goto write_error; } + if ((parent_prs == PRS_ISOLATED) && (old_prs == -PRS_ROOT)) { + part_error = PERR_ISOPARENT; + goto write_error; + } /* Check newmask again, whether cpus are available for parent/cs */ nocpu |= tasks_nocpu_error(parent, cs, newmask); @@ -1974,6 +1979,13 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, adding = cpumask_and(tmp->addmask, cs->effective_xcpus, parent->effective_xcpus); + } else if ((parent_prs == PRS_ISOLATED) && + ((old_prs == PRS_ROOT) || (old_prs == -PRS_ROOT))) { + part_error = PERR_ISOPARENT; + if (old_prs == PRS_ROOT) { + cpumask_copy(tmp->addmask, cs->effective_xcpus); + adding = true; + } } else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) && cpumask_subset(xcpus, parent->effective_xcpus)) { struct cgroup_subsys_state *css; @@ -2927,6 +2939,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) int err = PERR_NONE, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; + int parent_prs = parent->partition_root_state; bool isolcpus_updated = false; bool disable_partition = false; @@ -2972,6 +2985,14 @@ static int update_prstate(struct cpuset *cs, int new_prs) enum partition_cmd cmd = (new_prs == PRS_ROOT) ? partcmd_enable : partcmd_enablei; + /* + * It is not allowed to create a root partition under + * an isolated parent partition. + */ + if ((new_prs == PRS_ROOT) && (parent_prs == PRS_ISOLATED)) { + err = PERR_ISOPARENT; + goto out; + } err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask); } else { err = remote_partition_enable(cs, new_prs, &tmpmask); @@ -2985,12 +3006,15 @@ static int update_prstate(struct cpuset *cs, int new_prs) * Need to update isolated_cpus. */ if (prstate_housekeeping_conflict(new_prs, parent_prs, - cs->effective_xcpus, NULL)) { - disable_partition = true; + cs->effective_xcpus, NULL)) err = PERR_HKEEPING; - } else { + else if (parent_prs == PRS_ISOLATED) + err = PERR_ISOPARENT; + + if (!err) isolcpus_updated = true; - } + else + disable_partition = true; } else { /* * Switching back to member is always allowed even if it diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index f1dda27b1394..872a9988e4c4 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -288,16 +288,14 @@ TEST_MATRIX=( A1:P0|A2:P1|A3:P0|B1:P1" " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3" - " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ - A1:P0|A2:P2|A3:P1 2-4|2-3" - " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ - A1:P0|A2:P2|A3:P1 2" + " C1-6:P1 C3-6:P1 C5-6:P1 . . P2 . . 0 A1:1-2|A2:3-6|A3:5-6 \ + A1:P1|A2:P2|A3:P-1 3-6" " C1-4:X2-4 C2-4:X3-4:P1 C3-4:X4:P2 \ . . X5 . . 0 A1:1-4|A2:2-4|A3:3-4 \ A1:P0|A2:P-1|A3:P-2 ." - " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ - . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \ - A1:P0|A2:P2|A3:P-1 2-4" + " C1-4:X2-4 C1-4:X3-4:P1 C3-4:X4:P2 \ + . . . X1 . 0 A1:1-2|A2:3-4|A3:3-4 \ + A1:P0|A2:P1|A3:P-2 ." " CX1-3:P1 CX1-3 CX1-3 . . . P1 . 0 A1:1-3|A2:1-3|A3:1-3 \ A1:P1|A2:P0|A3:P-1" @@ -331,8 +329,8 @@ TEST_MATRIX=( " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" # Local partition CPU change tests - " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" - " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" + " C0-5:P1 C4-5:P2 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P1|A2:P2 3-5" + " C0-5:P1 C4-5:P2 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P1|A2:P2 4-5" # cpus_allowed/exclusive_cpus update tests " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ @@ -430,6 +428,13 @@ TEST_MATRIX=( # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3" + # Creation of root partition under an isolated partition is not allowed + " C1-3:P2 C2 . . . P1 . . 0 A1:1-3|A2:2 A1:P2|A2:P-1 1-3" + " C1-3:P2 C2 . . . P2 . . 0 A1:1,3|A2:2 A1:P2|A2:P2 1-3" + " C1-3:P2 C2:P2 . . . P1 . . 0 A1:1-3|A2:2 A1:P2|A2:P-1 1-3" + " C1-3:P2 C2:P1 . . . C2-3 . . 0 A1:1-3|A2:2-3 A1:P2|A2:P-1 1-3" + + # # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: -- 2.55.0
