Files
linux-stable-mirror/tools/testing/selftests/cgroup/test_freezer.c
T
Linus Torvalds a552c81ff4 Merge tag 'mm-stable-2026-06-18-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:

 - "selftests/mm: clean up build output and verbosity" (Li Wang)

   Remove some noise from the MM selftests build

 - "mm: Free contiguous order-0 pages efficiently" (Ryan Roberts)

   Speed up the freeing of a batch of 0-order pages by first scanning
   them for coalescing opportunities. This is applicable to vfree() and
   to the releasing of frozen pages

 - "mm/damon: introduce DAMOS failed region quota charge ratio"
   (SeongJae Park)

   Address a DAMOS usability issue: The DAMOS quota often exhausts
   prematurely because it charges for all memory attempted, causing slow
   and inconsistent performance when actions fail on unreclaimable
   memory.

   To fix this, a new feature lets users set a smaller, flexible quota
   charge ratio (via a numerator and denominator) for failed regions.
   Since failed actions cause less overhead, reducing their quota cost
   ensures more predictable and efficient DAMOS processing

 - "selftests/cgroup: improve zswap tests robustness and support large
   page sizes" (Li Wang)

   Fix various spurious failures and improves the overall robustness of
   the cgroup zswap selftests

 - "fix MAP_DROPPABLE not supported errno" (Anthony Yznaga)

   Fix an issue in the mlock selftests on arm32

 - "mm: huge_memory: clean up defrag sysfs with shared" (Breno Leitao)

   Some maintenance work in the huge_memory code

 - "treewide: fixup gfp_t printks" (Brendan Jackman)

   Use the special vprintf() gfp_t conversion in various places

 - "mm: Fix vmemmap optimization accounting and initialization" (Muchun
   Song)

   Fix several bugs in the vmemmap optimization, mainly around incorrect
   page accounting and memmap initialization in the DAX and memory
   hotplug paths. It also fixes pageblock migratetype initialization and
   struct page initialization for ZONE_DEVICE compound pages

 - "mm/damon: repost non-hotfix reviewed patches in damon/next tree"

   A sprinkle of unrelated minor bugfixes for DAMON

 - "mm: remove page_mapped()" (David Hildenbrand)

   Remove this function from the tree, replacing it with folio_mapped()

 - "mm/damon: let DAMON be paused and resumed" (SeongJae Park)

   Allow DAMON to be paused and resumed without losing its current state

 - "kasan: hw_tags: Disable tagging for stack and page-tables" (Muhammad
   Usama Anjum)

   Simplify and speed up kasan by removing its ineffective tagging of
   stacks and page tables

 - "mm/damon/reclaim,lru_sort: monitor all system rams by default"
   (SeongJae Park)

   Simplify deployment on diverse hardware like NUMA systems by updating
   DAMON_RECLAIM and DAMON_LRU_SORT to automatically monitor the
   physical address range covering all System RAM areas by default,
   replacing the overly restrictive behavior that only targeted the
   single largest memory block to save on negligible overhead

 - "mm/damon/sysfs: document filters/ directory as deprecated" (SeongJae
   Park)

   Update some DAMON docs

 - "mm: use spinlock guards for zone lock" (Dmitry Ilvokhin)

   Switch zone->lock handling over to using the guard() mechanisms

 - "mm/filemap: tighten mmap_miss hit accounting" (fujunjie)

   Fix a flaw where the mmap_miss counter over-credited page cache hits
   during fault-arounds and page-fault retries. This results in
   significant reduction of redundant synchronous mmap readahead I/O,
   drastically cutting down execution time and gigabytes read for sparse
   random or strided memory access workloads

 - "selftests/cgroup: Fix false positive failures in test_percpu_basic"
   (Li Wang)

   Fix a couple of false-positives in the cgroup kmem selftests

 - "mm/damon/reclaim: support monitoring intervals auto-tuning"
   (SeongJae Park)

   Add a new parameter to DAMON permitting DAMON_RECLAIM to
   automatically tune DAMON's sampling and aggregation intervals

 - "mm/damon/stat: add kdamond_pid parameter" (SeongJae Park)

   Change DAMON_STAT to provide the pid of its kdamond

 - "mm/kmemleak: dedupe verbose scan output" (Breno Leitao)

   Remove large amounts of duplicated backtraces from the verbose-mode
   kmemleak output

 - "mm: remove CONFIG_HAVE_BOOTMEM_INFO_NODE (Part 1)" (David
   Hildenbrand)

   Reduce our use of CONFIG_HAVE_BOOTMEM_INFO_NODE, with a view to
   removing it entirely in a later series

 - "mm/damon: validate min_region_size to be power of 2" (Liew Rui Yan)

   Prevent users from passing a non-power-of-2 value of `addr_unit', as
   this later results in undesirable behavior

 - "mm: document read_pages and simplify usage" (Frederick Mayle)

 - "tools/mm/page-types: Fix misc bugs" (Ye Liu)

   Fix three issues in tools/mm/page-types.c

 - "mm: misc cleanups from __GFP_UNMAPPED series" (Brendan Jackman)

   Implement several cleanups in the page allocator and related code

 - "mm, swap: swap table phase IV: unify allocation" (Kairui Song)

   Unify the allocation and charging of anon and shmem swap in folios,
   provides better synchronization, consolidates the metadata
   management, hence dropping the static array and map, and improves
   performance

 - "mm/damon: introduce data attributes monitoring" (SeongJae Park(

   Extend DAMON to monitor general data attributes other than accesses

 - "mm/vmalloc: free unused pages on vrealloc() shrink" (Shivam Kalra)

   Implement the TODO in vrealloc() to unmap and free unused pages when
   shrinking across a page boundary

 - "mm/damon: documentation and comment fixes" (niecheng)

 - "remove mmap_action success, error hooks" (Lorenzo Stoakes)

   Eliminate custom hooks from mmap_action by removing the problematic
   success_hook which allowed drivers to improperly access uninitialized
   VMAs. It replaces the error_hook with a simple error-code field and
   updates the memory char driver accordingly

 - "mm/damon: minor improvements for code readability and tests"
   (SeongJae Park)

 - "mm/damon: fix macro arguments and clarify quota goals doc" (Maksym
   Shcherba)

 - "userfaultfd: merge fs/userfaultfd.c into mm/userfaultfd.c" (Mike
   Rapoport)

 - "mm/mglru: improve reclaim loop and dirty folio" (Kairui Song and
   others)

   Clean up and slightly improves MGLRU's reclaim loop and dirty
   writeback handling. Large performance improvements are measured

 - "use vma locks for proc/pid/{smaps|numa_maps} reads" (Suren
   Baghdasaryan)

   Use per-vma locks when reading /proc/pid/smaps and numa_maps similar
   to reduce contention on central mmap_lock

 - "refactors thpsize_shmem_enabled_store() and thpsize_shmem_enabled_show()"
   (Ran Xiaokai)

   Some cleanup work in the THP code

 - "selftests/memfd: fix compilation warnings" (Konstantin Khorenko)

   Fix a few build glitches in the memfd selftest code.

 - "memcg: shrink obj_stock_pcp and cache multiple objcgs" (Shakeel
   Butt)

   Resolve a 68% performance regression caused by NUMA-node cache
   thrashing around struct obj_stock_pcp by shrinking its existing
   fields and expanding it into a multi-slot array that caches up to
   five obj_cgroup pointers per CPU, allowing per-node variants of the
   same memcg to coexist within a single 64-byte cache line.

 - "zram: writeback fixes" (Sergey Senozhatsky)

   address a couple of unrelated zram writeback issues

 - "mm: switch THP shrinker to list_lru" (Johannes Weiner)

   Resolve NUMA-awareness issues and streamlines callsite interaction by
   refactoring and extending the list_lru API to completely replace the
   complex, open-coded deferred split queue for Transparent Huge Pages

 - "mm: improve large folio readahead for exec memory" (Usama Arif)

   Improve large-folio readahead on systems like 64K-page arm64 by
   preventing the mmap_miss check from permanently disabling
   target-oriented VM_EXEC readahead, and by generalizing the
   force_thp_readahead gate to support mappings with any usefully large
   maximum folio order under the cache cap.

 - "userfaultfd/pagemap: pre-existing fixes" (Kiryl Shutsemau)

   Fix a bunch of minor issues in the userfaultfd/pagemap, all of which
   were flagged by Sashiko review of proposed new material

 - "mm/sparse-vmemmap: Provide generic vmemmap_set_pmd() and
   vmemmap_check_pmd()" (Muchun Song)

   Provide generic versions of these two functions so the four
   arch-specific implementations can be removed.

 - "mm/swap, PM: hibernate: fix swapoff race in uswsusp by pinning swap
   device" (Youngjun Park)

   Address a uswsusp-vs-swapoff race and reduces the swap device
   reference taking/releasing frequency.

 - "mm/hmm: A fix and a selftest" (Dev Jain)

* tag 'mm-stable-2026-06-18-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  selftests/mm/hmm-tests: test pagemap reads of PMD device-private entries
  fs/proc/task_mmu: do not warn on seeing non-migration pmd entry
  lib/test_hmm: check alloc_page_vma() return value and handle OOM
  mm/compaction: cap compact_gap() at COMPACT_CLUSTER_MAX
  mm/swap: remove redundant swap device reference in alloc/free
  mm/swap, PM: hibernate: fix swapoff race in uswsusp by pinning swap device
  mm/filemap: use folio_next_index() for start
  vmalloc: fix NULL pointer dereference in is_vm_area_hugepages()
  sparc/mm: drop vmemmap_check_pmd helper and use generic code
  loongarch/mm: drop vmemmap_check_pmd helper and use generic code
  riscv/mm: drop vmemmap_pmd helpers and use generic code
  arm64/mm: drop vmemmap_pmd helpers and use generic code
  mm/sparse-vmemmap: provide generic vmemmap_set_pmd() and vmemmap_check_pmd()
  rust: page: mark Page::nid as inline
  userfaultfd: build __VMA_UFFD_FLAGS from config-gated masks
  userfaultfd: gate must_wait writability check on pte_present()
  mm/huge_memory: preserve pmd_swp_uffd_wp on device-private PMD downgrade
  fs/proc/task_mmu: fix hugetlb self-deadlock in pagemap_scan_pte_hole()
  fs/proc/task_mmu: use huge_page_size() in pagemap_scan_hugetlb_entry()
  fs/proc/task_mmu: fix make_uffd_wp_huge_pte() prot-update race
  ...
2026-06-19 10:14:34 -07:00

1513 lines
29 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#include <stdbool.h>
#include <linux/limits.h>
#include <sys/ptrace.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <unistd.h>
#include <stdio.h>
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#include <sys/wait.h>
#include "kselftest.h"
#include "cgroup_util.h"
#define DEBUG
#ifdef DEBUG
#define debug(args...) fprintf(stderr, args)
#else
#define debug(args...)
#endif
/*
* Check if the cgroup is frozen by looking at the cgroup.events::frozen value.
*/
static int cg_check_frozen(const char *cgroup, bool frozen)
{
if (frozen) {
if (cg_read_strstr(cgroup, "cgroup.events", "frozen 1") != 0) {
debug("Cgroup %s isn't frozen\n", cgroup);
return -1;
}
} else {
/*
* Check the cgroup.events::frozen value.
*/
if (cg_read_strstr(cgroup, "cgroup.events", "frozen 0") != 0) {
debug("Cgroup %s is frozen\n", cgroup);
return -1;
}
}
return 0;
}
/*
* Freeze the given cgroup.
*/
static int cg_freeze_nowait(const char *cgroup, bool freeze)
{
return cg_write(cgroup, "cgroup.freeze", freeze ? "1" : "0");
}
/*
* Attach a task to the given cgroup and wait for a cgroup frozen event.
* All transient events (e.g. populated) are ignored.
*/
static int cg_enter_and_wait_for_frozen(const char *cgroup, int pid,
bool frozen)
{
int fd, ret = -1;
int attempts;
fd = cg_prepare_for_wait(cgroup);
if (fd < 0)
return fd;
ret = cg_enter(cgroup, pid);
if (ret)
goto out;
for (attempts = 0; attempts < 10; attempts++) {
ret = cg_wait_for(fd);
if (ret)
break;
ret = cg_check_frozen(cgroup, frozen);
if (ret)
continue;
}
out:
close(fd);
return ret;
}
/*
* Freeze the given cgroup and wait for the inotify signal.
* If there are no events in 10 seconds, treat this as an error.
* Then check that the cgroup is in the desired state.
*/
static int cg_freeze_wait(const char *cgroup, bool freeze)
{
int fd, ret = -1;
fd = cg_prepare_for_wait(cgroup);
if (fd < 0)
return fd;
ret = cg_freeze_nowait(cgroup, freeze);
if (ret) {
debug("Error: cg_freeze_nowait() failed\n");
goto out;
}
ret = cg_wait_for(fd);
if (ret)
goto out;
ret = cg_check_frozen(cgroup, freeze);
out:
close(fd);
return ret;
}
/*
* A simple process running in a sleep loop until being
* re-parented.
*/
static int child_fn(const char *cgroup, void *arg)
{
int ppid = getppid();
while (getppid() == ppid)
usleep(1000);
return getppid() == ppid;
}
/*
* A simple test for the cgroup freezer: populated the cgroup with 100
* running processes and freeze it. Then unfreeze it. Then it kills all
* processes and destroys the cgroup.
*/
static int test_cgfreezer_simple(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
int i;
cgroup = cg_name(root, "cg_test_simple");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
for (i = 0; i < 100; i++)
cg_run_nowait(cgroup, child_fn, NULL);
if (cg_wait_for_proc_count(cgroup, 100))
goto cleanup;
if (cg_check_frozen(cgroup, false))
goto cleanup;
if (cg_freeze_wait(cgroup, true))
goto cleanup;
if (cg_freeze_wait(cgroup, false))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* The test creates the following hierarchy:
* A
* / / \ \
* B E I K
* /\ |
* C D F
* |
* G
* |
* H
*
* with a process in C, H and 3 processes in K.
* Then it tries to freeze and unfreeze the whole tree.
*/
static int test_cgfreezer_tree(const char *root)
{
char *cgroup[10] = {0};
int ret = KSFT_FAIL;
int i;
cgroup[0] = cg_name(root, "cg_test_tree_A");
if (!cgroup[0])
goto cleanup;
cgroup[1] = cg_name(cgroup[0], "B");
if (!cgroup[1])
goto cleanup;
cgroup[2] = cg_name(cgroup[1], "C");
if (!cgroup[2])
goto cleanup;
cgroup[3] = cg_name(cgroup[1], "D");
if (!cgroup[3])
goto cleanup;
cgroup[4] = cg_name(cgroup[0], "E");
if (!cgroup[4])
goto cleanup;
cgroup[5] = cg_name(cgroup[4], "F");
if (!cgroup[5])
goto cleanup;
cgroup[6] = cg_name(cgroup[5], "G");
if (!cgroup[6])
goto cleanup;
cgroup[7] = cg_name(cgroup[6], "H");
if (!cgroup[7])
goto cleanup;
cgroup[8] = cg_name(cgroup[0], "I");
if (!cgroup[8])
goto cleanup;
cgroup[9] = cg_name(cgroup[0], "K");
if (!cgroup[9])
goto cleanup;
for (i = 0; i < 10; i++)
if (cg_create(cgroup[i]))
goto cleanup;
cg_run_nowait(cgroup[2], child_fn, NULL);
cg_run_nowait(cgroup[7], child_fn, NULL);
cg_run_nowait(cgroup[9], child_fn, NULL);
cg_run_nowait(cgroup[9], child_fn, NULL);
cg_run_nowait(cgroup[9], child_fn, NULL);
/*
* Wait until all child processes will enter
* corresponding cgroups.
*/
if (cg_wait_for_proc_count(cgroup[2], 1) ||
cg_wait_for_proc_count(cgroup[7], 1) ||
cg_wait_for_proc_count(cgroup[9], 3))
goto cleanup;
/*
* Freeze B.
*/
if (cg_freeze_wait(cgroup[1], true))
goto cleanup;
/*
* Freeze F.
*/
if (cg_freeze_wait(cgroup[5], true))
goto cleanup;
/*
* Freeze G.
*/
if (cg_freeze_wait(cgroup[6], true))
goto cleanup;
/*
* Check that A and E are not frozen.
*/
if (cg_check_frozen(cgroup[0], false))
goto cleanup;
if (cg_check_frozen(cgroup[4], false))
goto cleanup;
/*
* Freeze A. Check that A, B and E are frozen.
*/
if (cg_freeze_wait(cgroup[0], true))
goto cleanup;
if (cg_check_frozen(cgroup[1], true))
goto cleanup;
if (cg_check_frozen(cgroup[4], true))
goto cleanup;
/*
* Unfreeze B, F and G
*/
if (cg_freeze_nowait(cgroup[1], false))
goto cleanup;
if (cg_freeze_nowait(cgroup[5], false))
goto cleanup;
if (cg_freeze_nowait(cgroup[6], false))
goto cleanup;
/*
* Check that C and H are still frozen.
*/
if (cg_check_frozen(cgroup[2], true))
goto cleanup;
if (cg_check_frozen(cgroup[7], true))
goto cleanup;
/*
* Unfreeze A. Check that A, C and K are not frozen.
*/
if (cg_freeze_wait(cgroup[0], false))
goto cleanup;
if (cg_check_frozen(cgroup[2], false))
goto cleanup;
if (cg_check_frozen(cgroup[9], false))
goto cleanup;
ret = KSFT_PASS;
cleanup:
for (i = 9; i >= 0 && cgroup[i]; i--) {
cg_destroy(cgroup[i]);
free(cgroup[i]);
}
return ret;
}
/*
* A fork bomb emulator.
*/
static int forkbomb_fn(const char *cgroup, void *arg)
{
int ppid;
fork();
fork();
ppid = getppid();
while (getppid() == ppid)
usleep(1000);
return getppid() == ppid;
}
/*
* The test runs a fork bomb in a cgroup and tries to freeze it.
* Then it kills all processes and checks that cgroup isn't populated
* anymore.
*/
static int test_cgfreezer_forkbomb(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
cgroup = cg_name(root, "cg_forkbomb_test");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
cg_run_nowait(cgroup, forkbomb_fn, NULL);
usleep(100000);
if (cg_freeze_wait(cgroup, true))
goto cleanup;
if (cg_killall(cgroup))
goto cleanup;
if (cg_wait_for_proc_count(cgroup, 0))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* The test creates a cgroups and freezes it. Then it creates a child cgroup
* and populates it with a task. After that it checks that the child cgroup
* is frozen and the parent cgroup remains frozen too.
*/
static int test_cgfreezer_mkdir(const char *root)
{
int ret = KSFT_FAIL;
char *parent, *child = NULL;
int pid;
parent = cg_name(root, "cg_test_mkdir_A");
if (!parent)
goto cleanup;
child = cg_name(parent, "cg_test_mkdir_B");
if (!child)
goto cleanup;
if (cg_create(parent))
goto cleanup;
if (cg_freeze_wait(parent, true))
goto cleanup;
if (cg_create(child))
goto cleanup;
pid = cg_run_nowait(child, child_fn, NULL);
if (pid < 0)
goto cleanup;
if (cg_wait_for_proc_count(child, 1))
goto cleanup;
if (cg_check_frozen(child, true))
goto cleanup;
if (cg_check_frozen(parent, true))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (child)
cg_destroy(child);
free(child);
if (parent)
cg_destroy(parent);
free(parent);
return ret;
}
/*
* The test creates two nested cgroups, freezes the parent
* and removes the child. Then it checks that the parent cgroup
* remains frozen and it's possible to create a new child
* without unfreezing. The new child is frozen too.
*/
static int test_cgfreezer_rmdir(const char *root)
{
int ret = KSFT_FAIL;
char *parent, *child = NULL;
parent = cg_name(root, "cg_test_rmdir_A");
if (!parent)
goto cleanup;
child = cg_name(parent, "cg_test_rmdir_B");
if (!child)
goto cleanup;
if (cg_create(parent))
goto cleanup;
if (cg_create(child))
goto cleanup;
if (cg_freeze_wait(parent, true))
goto cleanup;
if (cg_destroy(child))
goto cleanup;
if (cg_check_frozen(parent, true))
goto cleanup;
if (cg_create(child))
goto cleanup;
if (cg_check_frozen(child, true))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (child)
cg_destroy(child);
free(child);
if (parent)
cg_destroy(parent);
free(parent);
return ret;
}
/*
* The test creates two cgroups: A and B, runs a process in A
* and performs several migrations:
* 1) A (running) -> B (frozen)
* 2) B (frozen) -> A (running)
* 3) A (frozen) -> B (frozen)
*
* On each step it checks the actual state of both cgroups.
*/
static int test_cgfreezer_migrate(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup[2] = {0};
int pid;
cgroup[0] = cg_name(root, "cg_test_migrate_A");
if (!cgroup[0])
goto cleanup;
cgroup[1] = cg_name(root, "cg_test_migrate_B");
if (!cgroup[1])
goto cleanup;
if (cg_create(cgroup[0]))
goto cleanup;
if (cg_create(cgroup[1]))
goto cleanup;
pid = cg_run_nowait(cgroup[0], child_fn, NULL);
if (pid < 0)
goto cleanup;
if (cg_wait_for_proc_count(cgroup[0], 1))
goto cleanup;
/*
* Migrate from A (running) to B (frozen)
*/
if (cg_freeze_wait(cgroup[1], true))
goto cleanup;
if (cg_enter_and_wait_for_frozen(cgroup[1], pid, true))
goto cleanup;
if (cg_check_frozen(cgroup[0], false))
goto cleanup;
/*
* Migrate from B (frozen) to A (running)
*/
if (cg_enter_and_wait_for_frozen(cgroup[0], pid, false))
goto cleanup;
if (cg_check_frozen(cgroup[1], true))
goto cleanup;
/*
* Migrate from A (frozen) to B (frozen)
*/
if (cg_freeze_wait(cgroup[0], true))
goto cleanup;
if (cg_enter_and_wait_for_frozen(cgroup[1], pid, true))
goto cleanup;
if (cg_check_frozen(cgroup[0], true))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup[0])
cg_destroy(cgroup[0]);
free(cgroup[0]);
if (cgroup[1])
cg_destroy(cgroup[1]);
free(cgroup[1]);
return ret;
}
/*
* The test checks that ptrace works with a tracing process in a frozen cgroup.
*/
static int test_cgfreezer_ptrace(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
siginfo_t siginfo;
int pid;
cgroup = cg_name(root, "cg_test_ptrace");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
pid = cg_run_nowait(cgroup, child_fn, NULL);
if (pid < 0)
goto cleanup;
if (cg_wait_for_proc_count(cgroup, 1))
goto cleanup;
if (cg_freeze_wait(cgroup, true))
goto cleanup;
if (ptrace(PTRACE_SEIZE, pid, NULL, NULL))
goto cleanup;
if (ptrace(PTRACE_INTERRUPT, pid, NULL, NULL))
goto cleanup;
waitpid(pid, NULL, 0);
/*
* Cgroup has to remain frozen, however the test task
* is in traced state.
*/
if (cg_check_frozen(cgroup, true))
goto cleanup;
if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo))
goto cleanup;
if (ptrace(PTRACE_DETACH, pid, NULL, NULL))
goto cleanup;
if (cg_check_frozen(cgroup, true))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Check if the process is stopped.
*/
static int proc_check_stopped(int pid)
{
char buf[BUF_SIZE];
int len;
len = proc_read_text(pid, 0, "stat", buf, sizeof(buf));
if (len == -1) {
debug("Can't get %d stat\n", pid);
return -1;
}
if (strstr(buf, "(test_freezer) T ") == NULL) {
debug("Process %d in the unexpected state: %s\n", pid, buf);
return -1;
}
return 0;
}
/*
* Test that it's possible to freeze a cgroup with a stopped process.
*/
static int test_cgfreezer_stopped(const char *root)
{
int pid, ret = KSFT_FAIL;
char *cgroup = NULL;
cgroup = cg_name(root, "cg_test_stopped");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
pid = cg_run_nowait(cgroup, child_fn, NULL);
if (cg_wait_for_proc_count(cgroup, 1))
goto cleanup;
if (kill(pid, SIGSTOP))
goto cleanup;
if (cg_check_frozen(cgroup, false))
goto cleanup;
if (cg_freeze_wait(cgroup, true))
goto cleanup;
if (cg_freeze_wait(cgroup, false))
goto cleanup;
if (proc_check_stopped(pid))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Test that it's possible to freeze a cgroup with a ptraced process.
*/
static int test_cgfreezer_ptraced(const char *root)
{
int pid, ret = KSFT_FAIL;
char *cgroup = NULL;
siginfo_t siginfo;
cgroup = cg_name(root, "cg_test_ptraced");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
pid = cg_run_nowait(cgroup, child_fn, NULL);
if (cg_wait_for_proc_count(cgroup, 1))
goto cleanup;
if (ptrace(PTRACE_SEIZE, pid, NULL, NULL))
goto cleanup;
if (ptrace(PTRACE_INTERRUPT, pid, NULL, NULL))
goto cleanup;
waitpid(pid, NULL, 0);
if (cg_check_frozen(cgroup, false))
goto cleanup;
if (cg_freeze_wait(cgroup, true))
goto cleanup;
/*
* cg_check_frozen(cgroup, true) will fail here,
* because the task is in the TRACEd state.
*/
if (cg_freeze_wait(cgroup, false))
goto cleanup;
if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo))
goto cleanup;
if (ptrace(PTRACE_DETACH, pid, NULL, NULL))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
static int vfork_fn(const char *cgroup, void *arg)
{
int pid = vfork();
if (pid == 0)
while (true)
sleep(1);
return pid;
}
/*
* Test that it's possible to freeze a cgroup with a process,
* which called vfork() and is waiting for a child.
*/
static int test_cgfreezer_vfork(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
cgroup = cg_name(root, "cg_test_vfork");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
cg_run_nowait(cgroup, vfork_fn, NULL);
if (cg_wait_for_proc_count(cgroup, 2))
goto cleanup;
if (cg_freeze_wait(cgroup, true))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Get the current frozen_usec for the cgroup.
*/
static long cg_check_freezetime(const char *cgroup)
{
return cg_read_key_long(cgroup, "cgroup.stat.local",
"frozen_usec ");
}
/*
* Test that the freeze time will behave as expected for an empty cgroup.
*/
static int test_cgfreezer_time_empty(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
long prev, curr;
cgroup = cg_name(root, "cg_time_test_empty");
if (!cgroup)
goto cleanup;
/*
* 1) Create an empty cgroup and check that its freeze time
* is 0.
*/
if (cg_create(cgroup))
goto cleanup;
curr = cg_check_freezetime(cgroup);
if (curr < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (curr > 0) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
if (cg_freeze_nowait(cgroup, true))
goto cleanup;
/*
* 2) Sleep for 1000 us. Check that the freeze time is at
* least 1000 us.
*/
usleep(1000);
curr = cg_check_freezetime(cgroup);
if (curr < 1000) {
debug("Expect time (%ld) to be at least 1000 us\n",
curr);
goto cleanup;
}
/*
* 3) Unfreeze the cgroup. Check that the freeze time is
* larger than at 2).
*/
if (cg_freeze_nowait(cgroup, false))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 4) Check the freeze time again to ensure that it has not
* changed.
*/
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr != prev) {
debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
curr, prev);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* A simple test for cgroup freezer time accounting. This test follows
* the same flow as test_cgfreezer_time_empty, but with a single process
* in the cgroup.
*/
static int test_cgfreezer_time_simple(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
long prev, curr;
cgroup = cg_name(root, "cg_time_test_simple");
if (!cgroup)
goto cleanup;
/*
* 1) Create a cgroup and check that its freeze time is 0.
*/
if (cg_create(cgroup))
goto cleanup;
curr = cg_check_freezetime(cgroup);
if (curr < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (curr > 0) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
/*
* 2) Populate the cgroup with one child and check that the
* freeze time is still 0.
*/
cg_run_nowait(cgroup, child_fn, NULL);
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr > prev) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
if (cg_freeze_nowait(cgroup, true))
goto cleanup;
/*
* 3) Sleep for 1000 us. Check that the freeze time is at
* least 1000 us.
*/
usleep(1000);
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr < 1000) {
debug("Expect time (%ld) to be at least 1000 us\n",
curr);
goto cleanup;
}
/*
* 4) Unfreeze the cgroup. Check that the freeze time is
* larger than at 3).
*/
if (cg_freeze_nowait(cgroup, false))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 5) Sleep for 1000 us. Check that the freeze time is the
* same as at 4).
*/
usleep(1000);
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr != prev) {
debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
curr, prev);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Test that freezer time accounting works as expected, even while we're
* populating a cgroup with processes.
*/
static int test_cgfreezer_time_populate(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
long prev, curr;
int i;
cgroup = cg_name(root, "cg_time_test_populate");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
curr = cg_check_freezetime(cgroup);
if (curr < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (curr > 0) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
/*
* 1) Populate the cgroup with 100 processes. Check that
* the freeze time is 0.
*/
for (i = 0; i < 100; i++)
cg_run_nowait(cgroup, child_fn, NULL);
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr != prev) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
/*
* 2) Wait for the group to become fully populated. Check
* that the freeze time is 0.
*/
if (cg_wait_for_proc_count(cgroup, 100))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr != prev) {
debug("Expect time (%ld) to be 0\n", curr);
goto cleanup;
}
/*
* 3) Freeze the cgroup and then populate it with 100 more
* processes. Check that the freeze time continues to grow.
*/
if (cg_freeze_nowait(cgroup, true))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
for (i = 0; i < 100; i++)
cg_run_nowait(cgroup, child_fn, NULL);
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 4) Wait for the group to become fully populated. Check
* that the freeze time is larger than at 3).
*/
if (cg_wait_for_proc_count(cgroup, 200))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 5) Unfreeze the cgroup. Check that the freeze time is
* larger than at 4).
*/
if (cg_freeze_nowait(cgroup, false))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 6) Kill the processes. Check that the freeze time is the
* same as it was at 5).
*/
if (cg_killall(cgroup))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr != prev) {
debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
curr, prev);
goto cleanup;
}
/*
* 7) Freeze and unfreeze the cgroup. Check that the freeze
* time is larger than it was at 6).
*/
if (cg_freeze_nowait(cgroup, true))
goto cleanup;
if (cg_freeze_nowait(cgroup, false))
goto cleanup;
prev = curr;
curr = cg_check_freezetime(cgroup);
if (curr <= prev) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr, prev);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Test that frozen time for a cgroup continues to work as expected,
* even as processes are migrated. Frozen cgroup A's freeze time should
* continue to increase and running cgroup B's should stay 0.
*/
static int test_cgfreezer_time_migrate(const char *root)
{
long prev_A, curr_A, curr_B;
char *cgroup[2] = {0};
int ret = KSFT_FAIL;
int pid;
cgroup[0] = cg_name(root, "cg_time_test_migrate_A");
if (!cgroup[0])
goto cleanup;
cgroup[1] = cg_name(root, "cg_time_test_migrate_B");
if (!cgroup[1])
goto cleanup;
if (cg_create(cgroup[0]))
goto cleanup;
if (cg_check_freezetime(cgroup[0]) < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (cg_create(cgroup[1]))
goto cleanup;
pid = cg_run_nowait(cgroup[0], child_fn, NULL);
if (pid < 0)
goto cleanup;
if (cg_wait_for_proc_count(cgroup[0], 1))
goto cleanup;
curr_A = cg_check_freezetime(cgroup[0]);
if (curr_A) {
debug("Expect time (%ld) to be 0\n", curr_A);
goto cleanup;
}
curr_B = cg_check_freezetime(cgroup[1]);
if (curr_B) {
debug("Expect time (%ld) to be 0\n", curr_B);
goto cleanup;
}
/*
* Freeze cgroup A.
*/
if (cg_freeze_wait(cgroup[0], true))
goto cleanup;
prev_A = curr_A;
curr_A = cg_check_freezetime(cgroup[0]);
if (curr_A <= prev_A) {
debug("Expect time (%ld) to be > 0\n", curr_A);
goto cleanup;
}
/*
* Migrate from A (frozen) to B (running).
*/
if (cg_enter(cgroup[1], pid))
goto cleanup;
usleep(1000);
curr_B = cg_check_freezetime(cgroup[1]);
if (curr_B) {
debug("Expect time (%ld) to be 0\n", curr_B);
goto cleanup;
}
prev_A = curr_A;
curr_A = cg_check_freezetime(cgroup[0]);
if (curr_A <= prev_A) {
debug("Expect time (%ld) to be more than previous check (%ld)\n",
curr_A, prev_A);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (cgroup[0])
cg_destroy(cgroup[0]);
free(cgroup[0]);
if (cgroup[1])
cg_destroy(cgroup[1]);
free(cgroup[1]);
return ret;
}
/*
* The test creates a cgroup and freezes it. Then it creates a child cgroup.
* After that it checks that the child cgroup has a non-zero freeze time
* that is less than the parent's. Next, it freezes the child, unfreezes
* the parent, and sleeps. Finally, it checks that the child's freeze
* time has grown larger than the parent's.
*/
static int test_cgfreezer_time_parent(const char *root)
{
char *parent, *child = NULL;
int ret = KSFT_FAIL;
long ptime, ctime;
parent = cg_name(root, "cg_test_parent_A");
if (!parent)
goto cleanup;
child = cg_name(parent, "cg_test_parent_B");
if (!child)
goto cleanup;
if (cg_create(parent))
goto cleanup;
if (cg_check_freezetime(parent) < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (cg_freeze_wait(parent, true))
goto cleanup;
usleep(1000);
if (cg_create(child))
goto cleanup;
if (cg_check_frozen(child, true))
goto cleanup;
/*
* Since the parent was frozen the entire time the child cgroup
* was being created, we expect the parent's freeze time to be
* larger than the child's.
*
* Ideally, we would be able to check both times simultaneously,
* but here we get the child's after we get the parent's.
*/
ptime = cg_check_freezetime(parent);
ctime = cg_check_freezetime(child);
if (ptime <= ctime) {
debug("Expect ptime (%ld) > ctime (%ld)\n", ptime, ctime);
goto cleanup;
}
if (cg_freeze_nowait(child, true))
goto cleanup;
if (cg_freeze_wait(parent, false))
goto cleanup;
if (cg_check_frozen(child, true))
goto cleanup;
usleep(100000);
ctime = cg_check_freezetime(child);
ptime = cg_check_freezetime(parent);
if (ctime <= ptime) {
debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (child)
cg_destroy(child);
free(child);
if (parent)
cg_destroy(parent);
free(parent);
return ret;
}
/*
* The test creates a parent cgroup and a child cgroup. Then, it freezes
* the child and checks that the child's freeze time is greater than the
* parent's, which should be zero.
*/
static int test_cgfreezer_time_child(const char *root)
{
char *parent, *child = NULL;
int ret = KSFT_FAIL;
long ptime, ctime;
parent = cg_name(root, "cg_test_child_A");
if (!parent)
goto cleanup;
child = cg_name(parent, "cg_test_child_B");
if (!child)
goto cleanup;
if (cg_create(parent))
goto cleanup;
if (cg_check_freezetime(parent) < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (cg_create(child))
goto cleanup;
if (cg_freeze_wait(child, true))
goto cleanup;
ctime = cg_check_freezetime(child);
ptime = cg_check_freezetime(parent);
if (ptime != 0) {
debug("Expect ptime (%ld) to be 0\n", ptime);
goto cleanup;
}
if (ctime <= ptime) {
debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
if (child)
cg_destroy(child);
free(child);
if (parent)
cg_destroy(parent);
free(parent);
return ret;
}
/*
* The test creates the following hierarchy:
* A
* |
* B
* |
* C
*
* Then it freezes the cgroups in the order C, B, A.
* Then it unfreezes the cgroups in the order A, B, C.
* Then it checks that C's freeze time is larger than B's and
* that B's is larger than A's.
*/
static int test_cgfreezer_time_nested(const char *root)
{
char *cgroup[3] = {0};
int ret = KSFT_FAIL;
long time[3] = {0};
int i;
cgroup[0] = cg_name(root, "cg_test_time_A");
if (!cgroup[0])
goto cleanup;
cgroup[1] = cg_name(cgroup[0], "B");
if (!cgroup[1])
goto cleanup;
cgroup[2] = cg_name(cgroup[1], "C");
if (!cgroup[2])
goto cleanup;
if (cg_create(cgroup[0]))
goto cleanup;
if (cg_check_freezetime(cgroup[0]) < 0) {
ret = KSFT_SKIP;
goto cleanup;
}
if (cg_create(cgroup[1]))
goto cleanup;
if (cg_create(cgroup[2]))
goto cleanup;
if (cg_freeze_nowait(cgroup[2], true))
goto cleanup;
if (cg_freeze_nowait(cgroup[1], true))
goto cleanup;
if (cg_freeze_nowait(cgroup[0], true))
goto cleanup;
usleep(1000);
if (cg_freeze_nowait(cgroup[0], false))
goto cleanup;
if (cg_freeze_nowait(cgroup[1], false))
goto cleanup;
if (cg_freeze_nowait(cgroup[2], false))
goto cleanup;
time[2] = cg_check_freezetime(cgroup[2]);
time[1] = cg_check_freezetime(cgroup[1]);
time[0] = cg_check_freezetime(cgroup[0]);
if (time[2] <= time[1]) {
debug("Expect C's time (%ld) > B's time (%ld)", time[2], time[1]);
goto cleanup;
}
if (time[1] <= time[0]) {
debug("Expect B's time (%ld) > A's time (%ld)", time[1], time[0]);
goto cleanup;
}
ret = KSFT_PASS;
cleanup:
for (i = 2; i >= 0 && cgroup[i]; i--) {
cg_destroy(cgroup[i]);
free(cgroup[i]);
}
return ret;
}
#define T(x) { x, #x }
struct cgfreezer_test {
int (*fn)(const char *root);
const char *name;
} tests[] = {
T(test_cgfreezer_simple),
T(test_cgfreezer_tree),
T(test_cgfreezer_forkbomb),
T(test_cgfreezer_mkdir),
T(test_cgfreezer_rmdir),
T(test_cgfreezer_migrate),
T(test_cgfreezer_ptrace),
T(test_cgfreezer_stopped),
T(test_cgfreezer_ptraced),
T(test_cgfreezer_vfork),
T(test_cgfreezer_time_empty),
T(test_cgfreezer_time_simple),
T(test_cgfreezer_time_populate),
T(test_cgfreezer_time_migrate),
T(test_cgfreezer_time_parent),
T(test_cgfreezer_time_child),
T(test_cgfreezer_time_nested),
};
#undef T
int main(int argc, char *argv[])
{
char root[PATH_MAX];
int i;
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
switch (tests[i].fn(root)) {
case KSFT_PASS:
ksft_test_result_pass("%s\n", tests[i].name);
break;
case KSFT_SKIP:
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
ksft_finished();
}