Experimental support for cgroups v2

Currently one test in the integration specs is failing. Unclear if this
is the fault of my docker setup or if this represents an actual issue
with how `runc` is being setup.

Failure:
```
------------------------------
• [FAILED] [0.167 seconds]
resource limits memory [It] gets OOMed when it exceeds its memory limit
/bpm/src/bpm/integration/resource_limits_test.go:116

  Timeline >>
  If this test fails, then make sure you have enabled swap accounting! Details are in the README.
  Error: failed to start job-process: exit status 1
  [FAILED] in [It] - /bpm/src/bpm/integration/resource_limits_test.go:122 @ 06/28/24 22:07:30.852
  BEGIN '/bpmtmp/resource-limits-test1115196611/sys/log/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2.stderr.log'
  time="2024-06-28T22:07:30Z" level=warning msg="unable to get oom kill count" error="openat2 /sys/fs/cgroup/bpm-0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2/memory.events: no such file or directory"
  time="2024-06-28T22:07:30Z" level=error msg="runc run failed: unable to start container process: unable to apply cgroup configuration: cannot enter cgroupv2 \"/sys/fs/cgroup/bpm-0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2\" with domain controllers -- it is in an invalid state"
  END   '/bpmtmp/resource-limits-test1115196611/sys/log/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2.stderr.log'
  BEGIN '/bpmtmp/resource-limits-test1115196611/sys/log/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2.stdout.log'
  END   '/bpmtmp/resource-limits-test1115196611/sys/log/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2/0cf7c73a-0b65-4f46-90a7-eb0bb809e6c2.stdout.log'
  << Timeline

  [FAILED] Expected
      <int>: 1
  to match exit code:
      <int>: 0
  In [It] at: /bpm/src/bpm/integration/resource_limits_test.go:122 @ 06/28/24 22:07:30.852
------------------------------
••••••••••••••••••••••••••
------------------------------
• [FAILED] [0.364 seconds]
start when a broken runc configuration is left on the system [It] `bpm start` cleans up the broken-ness and starts it
/bpm/src/bpm/integration/start_test.go:329

  Timeline >>
  Error: failed to start job-process: exit status 1
  [FAILED] in [It] - /bpm/src/bpm/integration/start_test.go:337 @ 06/28/24 22:07:31.915
  BEGIN '/bpmtmp/start-test2475062763/sys/log/e599a26c-5d89-421d-a740-04dd490c314b/e599a26c-5d89-421d-a740-04dd490c314b.stdout.log'
  en_US.UTF-8
  Logging to STDOUT
  Received a TERM signal
  END   '/bpmtmp/start-test2475062763/sys/log/e599a26c-5d89-421d-a740-04dd490c314b/e599a26c-5d89-421d-a740-04dd490c314b.stdout.log'
  BEGIN '/bpmtmp/start-test2475062763/sys/log/e599a26c-5d89-421d-a740-04dd490c314b/e599a26c-5d89-421d-a740-04dd490c314b.stderr.log'
  Logging to STDERR
  [WARN  tini (1)] Reaped zombie process with pid=8
  time="2024-06-28T22:07:31Z" level=error msg="runc run failed: unable to get cgroup PIDs: read /sys/fs/cgroup/bpm-e599a26c-5d89-421d-a740-04dd490c314b/cgroup.procs: operation not supported"
  END   '/bpmtmp/start-test2475062763/sys/log/e599a26c-5d89-421d-a740-04dd490c314b/e599a26c-5d89-421d-a740-04dd490c314b.stderr.log'
  << Timeline

  [FAILED] Expected
      <int>: 1
  to match exit code:
      <int>: 0
  In [It] at: /bpm/src/bpm/integration/start_test.go:337 @ 06/28/24 22:07:31.915
------------------------------
•••••••••••••••••••••••••••••

Summarizing 2 Failures:
  [FAIL] resource limits memory [It] gets OOMed when it exceeds its memory limit
  /bpm/src/bpm/integration/resource_limits_test.go:122
  [FAIL] start when a broken runc configuration is left on the system [It] `bpm start` cleans up the broken-ness and starts it
  /bpm/src/bpm/integration/start_test.go:337

Ran 69 of 69 Specs in 27.622 seconds
FAIL! -- 67 Passed | 2 Failed | 0 Pending | 0 Skipped
```

Author: aramprice

src/bpm/cgroups/cgroup.go

@@ -32,6 +32,10 @@ import (
 const cgroupRoot = "/sys/fs/cgroup"
 
 func Setup() error {
+	if cgroups.IsCgroup2UnifiedMode() {
+		return nil
+	}
+
 	mounts, err := mountinfo.GetMounts(mountinfo.ParentsFilter(cgroupRoot))
 	if err != nil {
 		return fmt.Errorf("unable to retrieve mounts: %s", err)

src/bpm/sysfeat/sysfeat.go

@@ -25,7 +25,11 @@ import (
 )
 
 const (
-	swapPath = "memory.memsw.limit_in_bytes"
+	swapPathCgroup1 = "memory.memsw.limit_in_bytes"
+	swapPathCgroup2 = "memory.swap.max"
+
+	unifiedMountpoint = "/sys/fs/cgroup"
+	hybridMountpoint  = "/sys/fs/cgroup/unified"
 )
 
 // Features contains information about what features the host system supports.
@@ -35,17 +39,43 @@ type Features struct {
 }
 
 func Fetch() (*Features, error) {
-	mountpoint, err := cgroups.FindCgroupMountpoint("", "memory")
+	supported, err := swapLimitSupported()
 	if err != nil {
 		return nil, err
 	}
 
 	return &Features{
-		SwapLimitSupported: swapLimitSupported(mountpoint),
+		SwapLimitSupported: supported,
 	}, nil
 }
 
-func swapLimitSupported(mount string) bool {
-	_, err := os.Stat(filepath.Join(mount, swapPath))
-	return err == nil
+func swapLimitSupported() (bool, error) {
+	if cgroups.IsCgroup2UnifiedMode() {
+		return swapLimitSupportedCgroup2()
+	}
+
+	return swapLimitSupportedCgroup1()
+}
+
+func swapLimitSupportedCgroup2() (bool, error) {
+	mountpoint := unifiedMountpoint
+	if cgroups.IsCgroup2HybridMode() {
+		mountpoint = hybridMountpoint
+	}
+
+	if cgroups.PathExists(filepath.Join(mountpoint, swapPathCgroup2)) {
+		return true, nil
+	}
+
+	return false, nil
+}
+
+func swapLimitSupportedCgroup1() (bool, error) {
+	mountPoint, err := cgroups.FindCgroupMountpoint("", "memory")
+	if err != nil {
+		return false, err
+	}
+
+	_, err = os.Stat(filepath.Join(mountPoint, swapPathCgroup1))
+	return err == nil, nil
 }