mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-08-09 06:14:34 +02:00
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
...
680 lines
12 KiB
C
680 lines
12 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#define _GNU_SOURCE
|
|
|
|
#include <errno.h>
|
|
#include <fcntl.h>
|
|
#include <linux/limits.h>
|
|
#include <poll.h>
|
|
#include <signal.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <sys/inotify.h>
|
|
#include <sys/stat.h>
|
|
#include <sys/types.h>
|
|
#include <sys/wait.h>
|
|
#include <unistd.h>
|
|
|
|
#include "cgroup_util.h"
|
|
#include "../../clone3/clone3_selftests.h"
|
|
|
|
bool cg_test_v1_named;
|
|
|
|
/* Returns read len on success, or -errno on failure. */
|
|
ssize_t read_text(const char *path, char *buf, size_t max_len)
|
|
{
|
|
ssize_t len;
|
|
int fd;
|
|
|
|
fd = open(path, O_RDONLY);
|
|
if (fd < 0)
|
|
return -errno;
|
|
|
|
len = read(fd, buf, max_len - 1);
|
|
|
|
if (len >= 0)
|
|
buf[len] = 0;
|
|
|
|
close(fd);
|
|
return len < 0 ? -errno : len;
|
|
}
|
|
|
|
/* Returns written len on success, or -errno on failure. */
|
|
ssize_t write_text(const char *path, char *buf, ssize_t len)
|
|
{
|
|
int fd;
|
|
|
|
fd = open(path, O_WRONLY | O_APPEND);
|
|
if (fd < 0)
|
|
return -errno;
|
|
|
|
len = write(fd, buf, len);
|
|
close(fd);
|
|
return len < 0 ? -errno : len;
|
|
}
|
|
|
|
char *cg_name(const char *root, const char *name)
|
|
{
|
|
size_t len = strlen(root) + strlen(name) + 2;
|
|
char *ret = malloc(len);
|
|
|
|
if (ret)
|
|
snprintf(ret, len, "%s/%s", root, name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
char *cg_name_indexed(const char *root, const char *name, int index)
|
|
{
|
|
size_t len = strlen(root) + strlen(name) + 10;
|
|
char *ret = malloc(len);
|
|
|
|
if (ret)
|
|
snprintf(ret, len, "%s/%s_%d", root, name, index);
|
|
|
|
return ret;
|
|
}
|
|
|
|
char *cg_control(const char *cgroup, const char *control)
|
|
{
|
|
size_t len = strlen(cgroup) + strlen(control) + 2;
|
|
char *ret = malloc(len);
|
|
|
|
if (ret)
|
|
snprintf(ret, len, "%s/%s", cgroup, control);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/* Returns 0 on success, or -errno on failure. */
|
|
int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
|
|
{
|
|
char path[PATH_MAX];
|
|
ssize_t ret;
|
|
|
|
snprintf(path, sizeof(path), "%s/%s", cgroup, control);
|
|
|
|
ret = read_text(path, buf, len);
|
|
return ret >= 0 ? 0 : ret;
|
|
}
|
|
|
|
int cg_read_strcmp(const char *cgroup, const char *control,
|
|
const char *expected)
|
|
{
|
|
size_t size;
|
|
char *buf;
|
|
int ret;
|
|
|
|
/* Handle the case of comparing against empty string */
|
|
if (!expected)
|
|
return -1;
|
|
|
|
/* needs size > 1, otherwise cg_read() reads 0 bytes */
|
|
size = (expected[0] == '\0') ? 2 : strlen(expected) + 1;
|
|
|
|
buf = malloc(size);
|
|
if (!buf)
|
|
return -1;
|
|
|
|
if (cg_read(cgroup, control, buf, size)) {
|
|
free(buf);
|
|
return -1;
|
|
}
|
|
|
|
ret = strcmp(expected, buf);
|
|
free(buf);
|
|
return ret;
|
|
}
|
|
|
|
int cg_read_strcmp_wait(const char *cgroup, const char *control,
|
|
const char *expected)
|
|
{
|
|
int i, ret;
|
|
|
|
for (i = 0; i < 100; i++) {
|
|
ret = cg_read_strcmp(cgroup, control, expected);
|
|
if (!ret)
|
|
return ret;
|
|
usleep(10000);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
|
|
if (cg_read(cgroup, control, buf, sizeof(buf)))
|
|
return -1;
|
|
|
|
return strstr(buf, needle) ? 0 : -1;
|
|
}
|
|
|
|
long cg_read_long(const char *cgroup, const char *control)
|
|
{
|
|
char buf[128];
|
|
|
|
if (cg_read(cgroup, control, buf, sizeof(buf)))
|
|
return -1;
|
|
|
|
return atol(buf);
|
|
}
|
|
|
|
long cg_read_long_fd(int fd)
|
|
{
|
|
char buf[128];
|
|
|
|
if (pread(fd, buf, sizeof(buf), 0) <= 0)
|
|
return -1;
|
|
|
|
return atol(buf);
|
|
}
|
|
|
|
long cg_read_key_long(const char *cgroup, const char *control, const char *key)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
char *ptr;
|
|
|
|
if (cg_read(cgroup, control, buf, sizeof(buf)))
|
|
return -1;
|
|
|
|
ptr = strstr(buf, key);
|
|
if (!ptr)
|
|
return -1;
|
|
|
|
return atol(ptr + strlen(key));
|
|
}
|
|
|
|
long cg_read_key_long_poll(const char *cgroup, const char *control,
|
|
const char *key, long expected, int retries,
|
|
useconds_t wait_interval_us)
|
|
{
|
|
long val = -1;
|
|
int i;
|
|
|
|
for (i = 0; i < retries; i++) {
|
|
val = cg_read_key_long(cgroup, control, key);
|
|
if (val < 0)
|
|
return val;
|
|
|
|
if (val == expected)
|
|
break;
|
|
|
|
usleep(wait_interval_us);
|
|
}
|
|
|
|
return val;
|
|
}
|
|
|
|
long cg_read_lc(const char *cgroup, const char *control)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
const char delim[] = "\n";
|
|
char *line;
|
|
long cnt = 0;
|
|
|
|
if (cg_read(cgroup, control, buf, sizeof(buf)))
|
|
return -1;
|
|
|
|
for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
|
|
cnt++;
|
|
|
|
return cnt;
|
|
}
|
|
|
|
/* Returns 0 on success, or -errno on failure. */
|
|
int cg_write(const char *cgroup, const char *control, char *buf)
|
|
{
|
|
char path[PATH_MAX];
|
|
ssize_t len = strlen(buf), ret;
|
|
|
|
snprintf(path, sizeof(path), "%s/%s", cgroup, control);
|
|
ret = write_text(path, buf, len);
|
|
return ret == len ? 0 : ret;
|
|
}
|
|
|
|
/*
|
|
* Returns fd on success, or -1 on failure.
|
|
* (fd should be closed with close() as usual)
|
|
*/
|
|
int cg_open(const char *cgroup, const char *control, int flags)
|
|
{
|
|
char path[PATH_MAX];
|
|
|
|
snprintf(path, sizeof(path), "%s/%s", cgroup, control);
|
|
return open(path, flags);
|
|
}
|
|
|
|
int cg_write_numeric(const char *cgroup, const char *control, long value)
|
|
{
|
|
char buf[64];
|
|
int ret;
|
|
|
|
ret = sprintf(buf, "%lu", value);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
return cg_write(cgroup, control, buf);
|
|
}
|
|
|
|
static int cg_find_root(char *root, size_t len, const char *controller,
|
|
bool *nsdelegate)
|
|
{
|
|
char buf[10 * BUF_SIZE];
|
|
char *fs, *mount, *type, *options;
|
|
const char delim[] = "\n\t ";
|
|
|
|
if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
|
|
return -1;
|
|
|
|
/*
|
|
* Example:
|
|
* cgroup /sys/fs/cgroup cgroup2 rw,seclabel,noexec,relatime 0 0
|
|
*/
|
|
for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
|
|
mount = strtok(NULL, delim);
|
|
type = strtok(NULL, delim);
|
|
options = strtok(NULL, delim);
|
|
strtok(NULL, delim);
|
|
strtok(NULL, delim);
|
|
if (strcmp(type, "cgroup") == 0) {
|
|
if (!controller || !strstr(options, controller))
|
|
continue;
|
|
} else if (strcmp(type, "cgroup2") == 0) {
|
|
if (controller &&
|
|
cg_read_strstr(mount, "cgroup.controllers", controller))
|
|
continue;
|
|
} else {
|
|
continue;
|
|
}
|
|
strncpy(root, mount, len);
|
|
|
|
if (nsdelegate)
|
|
*nsdelegate = !!strstr(options, "nsdelegate");
|
|
return 0;
|
|
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
int cg_find_controller_root(char *root, size_t len, const char *controller)
|
|
{
|
|
return cg_find_root(root, len, controller, NULL);
|
|
}
|
|
|
|
int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
|
|
{
|
|
return cg_find_root(root, len, NULL, nsdelegate);
|
|
}
|
|
|
|
int cg_create(const char *cgroup)
|
|
{
|
|
return mkdir(cgroup, 0755);
|
|
}
|
|
|
|
int cg_wait_for_proc_count(const char *cgroup, int count)
|
|
{
|
|
char buf[10 * BUF_SIZE] = {0};
|
|
int attempts;
|
|
char *ptr;
|
|
|
|
for (attempts = 10; attempts >= 0; attempts--) {
|
|
int nr = 0;
|
|
|
|
if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
|
|
break;
|
|
|
|
for (ptr = buf; *ptr; ptr++)
|
|
if (*ptr == '\n')
|
|
nr++;
|
|
|
|
if (nr >= count)
|
|
return 0;
|
|
|
|
usleep(100000);
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
int cg_killall(const char *cgroup)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
char *ptr = buf;
|
|
|
|
/* If cgroup.kill exists use it. */
|
|
if (!cg_write(cgroup, "cgroup.kill", "1"))
|
|
return 0;
|
|
|
|
if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
|
|
return -1;
|
|
|
|
while (ptr < buf + sizeof(buf)) {
|
|
int pid = strtol(ptr, &ptr, 10);
|
|
|
|
if (pid == 0)
|
|
break;
|
|
if (*ptr)
|
|
ptr++;
|
|
else
|
|
break;
|
|
if (kill(pid, SIGKILL))
|
|
return -1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int cg_destroy(const char *cgroup)
|
|
{
|
|
int ret;
|
|
|
|
if (!cgroup)
|
|
return 0;
|
|
retry:
|
|
ret = rmdir(cgroup);
|
|
if (ret && errno == EBUSY) {
|
|
cg_killall(cgroup);
|
|
usleep(100);
|
|
goto retry;
|
|
}
|
|
|
|
if (ret && errno == ENOENT)
|
|
ret = 0;
|
|
|
|
return ret;
|
|
}
|
|
|
|
int cg_enter(const char *cgroup, int pid)
|
|
{
|
|
char pidbuf[64];
|
|
|
|
snprintf(pidbuf, sizeof(pidbuf), "%d", pid);
|
|
return cg_write(cgroup, "cgroup.procs", pidbuf);
|
|
}
|
|
|
|
int cg_enter_current(const char *cgroup)
|
|
{
|
|
return cg_write(cgroup, "cgroup.procs", "0");
|
|
}
|
|
|
|
int cg_enter_current_thread(const char *cgroup)
|
|
{
|
|
return cg_write(cgroup, CG_THREADS_FILE, "0");
|
|
}
|
|
|
|
int cg_run(const char *cgroup,
|
|
int (*fn)(const char *cgroup, void *arg),
|
|
void *arg)
|
|
{
|
|
int pid, retcode;
|
|
|
|
pid = fork();
|
|
if (pid < 0) {
|
|
return pid;
|
|
} else if (pid == 0) {
|
|
char buf[64];
|
|
|
|
snprintf(buf, sizeof(buf), "%d", getpid());
|
|
if (cg_write(cgroup, "cgroup.procs", buf))
|
|
exit(EXIT_FAILURE);
|
|
exit(fn(cgroup, arg));
|
|
} else {
|
|
waitpid(pid, &retcode, 0);
|
|
if (WIFEXITED(retcode))
|
|
return WEXITSTATUS(retcode);
|
|
else
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
pid_t clone_into_cgroup(int cgroup_fd)
|
|
{
|
|
#ifdef CLONE_ARGS_SIZE_VER2
|
|
pid_t pid;
|
|
|
|
struct __clone_args args = {
|
|
.flags = CLONE_INTO_CGROUP,
|
|
.exit_signal = SIGCHLD,
|
|
.cgroup = cgroup_fd,
|
|
};
|
|
|
|
pid = sys_clone3(&args, sizeof(struct __clone_args));
|
|
/*
|
|
* Verify that this is a genuine test failure:
|
|
* ENOSYS -> clone3() not available
|
|
* E2BIG -> CLONE_INTO_CGROUP not available
|
|
*/
|
|
if (pid < 0 && (errno == ENOSYS || errno == E2BIG))
|
|
goto pretend_enosys;
|
|
|
|
return pid;
|
|
|
|
pretend_enosys:
|
|
#endif
|
|
errno = ENOSYS;
|
|
return -ENOSYS;
|
|
}
|
|
|
|
int clone_reap(pid_t pid, int options)
|
|
{
|
|
int ret;
|
|
siginfo_t info = {
|
|
.si_signo = 0,
|
|
};
|
|
|
|
again:
|
|
ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD);
|
|
if (ret < 0) {
|
|
if (errno == EINTR)
|
|
goto again;
|
|
return -1;
|
|
}
|
|
|
|
if (options & WEXITED) {
|
|
if (WIFEXITED(info.si_status))
|
|
return WEXITSTATUS(info.si_status);
|
|
}
|
|
|
|
if (options & WSTOPPED) {
|
|
if (WIFSTOPPED(info.si_status))
|
|
return WSTOPSIG(info.si_status);
|
|
}
|
|
|
|
if (options & WCONTINUED) {
|
|
if (WIFCONTINUED(info.si_status))
|
|
return 0;
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
int dirfd_open_opath(const char *dir)
|
|
{
|
|
return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH);
|
|
}
|
|
|
|
#define close_prot_errno(fd) \
|
|
if (fd >= 0) { \
|
|
int _e_ = errno; \
|
|
close(fd); \
|
|
errno = _e_; \
|
|
}
|
|
|
|
static int clone_into_cgroup_run_nowait(const char *cgroup,
|
|
int (*fn)(const char *cgroup, void *arg),
|
|
void *arg)
|
|
{
|
|
int cgroup_fd;
|
|
pid_t pid;
|
|
|
|
cgroup_fd = dirfd_open_opath(cgroup);
|
|
if (cgroup_fd < 0)
|
|
return -1;
|
|
|
|
pid = clone_into_cgroup(cgroup_fd);
|
|
close_prot_errno(cgroup_fd);
|
|
if (pid == 0)
|
|
exit(fn(cgroup, arg));
|
|
|
|
return pid;
|
|
}
|
|
|
|
int cg_run_nowait(const char *cgroup,
|
|
int (*fn)(const char *cgroup, void *arg),
|
|
void *arg)
|
|
{
|
|
int pid;
|
|
|
|
pid = clone_into_cgroup_run_nowait(cgroup, fn, arg);
|
|
if (pid > 0)
|
|
return pid;
|
|
|
|
/* Genuine test failure. */
|
|
if (pid < 0 && errno != ENOSYS)
|
|
return -1;
|
|
|
|
pid = fork();
|
|
if (pid == 0) {
|
|
char buf[64];
|
|
|
|
snprintf(buf, sizeof(buf), "%d", getpid());
|
|
if (cg_write(cgroup, "cgroup.procs", buf))
|
|
exit(EXIT_FAILURE);
|
|
exit(fn(cgroup, arg));
|
|
}
|
|
|
|
return pid;
|
|
}
|
|
|
|
int proc_mount_contains(const char *option)
|
|
{
|
|
char buf[4 * BUF_SIZE];
|
|
ssize_t read;
|
|
|
|
read = read_text("/proc/mounts", buf, sizeof(buf));
|
|
if (read < 0)
|
|
return read;
|
|
|
|
return strstr(buf, option) != NULL;
|
|
}
|
|
|
|
int cgroup_feature(const char *feature)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
ssize_t read;
|
|
|
|
read = read_text("/sys/kernel/cgroup/features", buf, sizeof(buf));
|
|
if (read < 0)
|
|
return read;
|
|
|
|
return strstr(buf, feature) != NULL;
|
|
}
|
|
|
|
ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
|
|
{
|
|
char path[PATH_MAX];
|
|
ssize_t ret;
|
|
|
|
if (!pid)
|
|
snprintf(path, sizeof(path), "/proc/%s/%s",
|
|
thread ? "thread-self" : "self", item);
|
|
else
|
|
snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
|
|
|
|
ret = read_text(path, buf, size);
|
|
return ret < 0 ? -1 : ret;
|
|
}
|
|
|
|
int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
|
|
{
|
|
char buf[BUF_SIZE];
|
|
|
|
if (proc_read_text(pid, thread, item, buf, sizeof(buf)) < 0)
|
|
return -1;
|
|
|
|
return strstr(buf, needle) ? 0 : -1;
|
|
}
|
|
|
|
int clone_into_cgroup_run_wait(const char *cgroup)
|
|
{
|
|
int cgroup_fd;
|
|
pid_t pid;
|
|
|
|
cgroup_fd = dirfd_open_opath(cgroup);
|
|
if (cgroup_fd < 0)
|
|
return -1;
|
|
|
|
pid = clone_into_cgroup(cgroup_fd);
|
|
close_prot_errno(cgroup_fd);
|
|
if (pid < 0)
|
|
return -1;
|
|
|
|
if (pid == 0)
|
|
exit(EXIT_SUCCESS);
|
|
|
|
/*
|
|
* We don't care whether this fails. We only care whether the initial
|
|
* clone succeeded.
|
|
*/
|
|
(void)clone_reap(pid, WEXITED);
|
|
return 0;
|
|
}
|
|
|
|
static int __prepare_for_wait(const char *cgroup, const char *filename)
|
|
{
|
|
int fd, ret = -1;
|
|
|
|
fd = inotify_init1(0);
|
|
if (fd == -1)
|
|
return fd;
|
|
|
|
ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY);
|
|
if (ret == -1) {
|
|
close(fd);
|
|
fd = -1;
|
|
}
|
|
|
|
return fd;
|
|
}
|
|
|
|
int cg_prepare_for_wait(const char *cgroup)
|
|
{
|
|
return __prepare_for_wait(cgroup, "cgroup.events");
|
|
}
|
|
|
|
int memcg_prepare_for_wait(const char *cgroup)
|
|
{
|
|
return __prepare_for_wait(cgroup, "memory.events");
|
|
}
|
|
|
|
int cg_wait_for(int fd)
|
|
{
|
|
int ret = -1;
|
|
struct pollfd fds = {
|
|
.fd = fd,
|
|
.events = POLLIN,
|
|
};
|
|
|
|
while (true) {
|
|
ret = poll(&fds, 1, 10000);
|
|
|
|
if (ret == -1) {
|
|
if (errno == EINTR)
|
|
continue;
|
|
|
|
break;
|
|
}
|
|
|
|
if (ret > 0 && fds.revents & POLLIN) {
|
|
ret = 0;
|
|
break;
|
|
}
|
|
}
|
|
|
|
return ret;
|
|
}
|