From efa058d142ab45be1ed03e1211b7e469aef89f9f Mon Sep 17 00:00:00 2001 From: Hui Zhu Date: Thu, 20 Aug 2026 14:12:26 +0800 Subject: [PATCH 1/2] mm/bpf: Add bpf_proactive_reclaim kfuncs Expose memcg proactive reclaim to sleepable BPF programs: unsigned long bpf_proactive_reclaim(memcg, size); unsigned long bpf_proactive_reclaim_swappiness(memcg, size, swappiness); They perform one reclaim pass on @memcg, like a write to memory.reclaim: swap is allowed, and the anon/file balance follows the cgroup's swappiness or an explicit override in [MIN_SWAPPINESS, MAX_SWAPPINESS] plus SWAPPINESS_ANON_ONLY. Both go through a shared helper, bpf_proactive_reclaim_pages(), which guards against reclaim recursion and calls try_to_free_mem_cgroup_pages() with GFP_KERNEL and MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE, the same parameters user_proactive_reclaim() uses, and unlike memory.reclaim they do not retry until @size is reached. Reclaim must not recurse: try_to_free_mem_cgroup_pages() overwrites current->reclaim_state on entry and NULLs it on exit, so a nested call from an in-flight reclaim would corrupt the outer reclaim state (e.g. MGLRU dereferences current->reclaim_state->mm_walk). Both kfuncs therefore refuse to reclaim when PF_MEMALLOC is set or current->reclaim_state is non-NULL. The latter check also closes the window in try_to_free_mem_cgroup_pages() where reclaim_state is already installed but PF_MEMALLOC is not: only a tracepoint call sits in between, and while a sleepable BPF program cannot attach to the tracepoint itself, it can attach to the generated trace iterator function (__traceiter_mm_vmscan_memcg_reclaim_begin) via fentry. The kfuncs take @size in bytes; the return value is normalized to bytes as well, matching the byte-based unit of bpf_mem_cgroup_usage() and bpf_mem_cgroup_page_state(), so callers can mix them without manual page/byte conversions. An out-of-range @swappiness is reported with (unsigned long)-1 instead of 0, following the convention of bpf_mem_cgroup_vm_events() and bpf_mem_cgroup_page_state(), as 0 cannot be told apart from a successful pass that reclaimed nothing. Signed-off-by: Hui Zhu --- mm/bpf_memcontrol.c | 118 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 118 insertions(+) diff --git a/mm/bpf_memcontrol.c b/mm/bpf_memcontrol.c index 716df49d76477..dc51868b3acfe 100644 --- a/mm/bpf_memcontrol.c +++ b/mm/bpf_memcontrol.c @@ -6,6 +6,7 @@ */ #include +#include #include __bpf_kfunc_start_defs(); @@ -159,6 +160,120 @@ __bpf_kfunc void bpf_mem_cgroup_flush_stats(struct mem_cgroup *memcg) mem_cgroup_flush_stats(memcg); } +/* + * Reclaim must not recurse. try_to_free_mem_cgroup_pages() unconditionally + * overwrites current->reclaim_state on entry and resets it to NULL on exit. + * So invoking it from an in-flight reclaim would clobber the outer reclaim + * state and corrupt its accounting. + * + * The guards are PF_MEMALLOC and current->reclaim_state. Every reclaim + * entry point marks the current task with PF_MEMALLOC for the whole + * reclaim window: try_to_free_mem_cgroup_pages() and __perform_reclaim() + * do so via memalloc_noreclaim_save(), and kswapd keeps it set for its + * entire lifetime. A hook inside the reclaim path (shrink_node, + * shrink_slab, ...) executes in the context of the reclaiming task, where + * current->flags already carries the flag. The page allocator, the memcg + * charging path and node_reclaim() rely on the same flag to avoid reclaim + * recursion. + * + * reclaim_state is checked in addition because it is set slightly before + * PF_MEMALLOC in try_to_free_mem_cgroup_pages(), with only a tracepoint + * call in between. A sleepable BPF program cannot attach to the tracepoint + * itself, but it can attach to the generated trace iterator function + * (__traceiter_mm_vmscan_memcg_reclaim_begin) via fentry, so PF_MEMALLOC + * alone would leave that window open. + * + * Also, PF_MEMALLOC is set in some non-reclaim contexts (e.g. direct compaction + * and vmalloc), where the kfunc conservatively refuses to reclaim as well. + */ +static bool bpf_in_reclaim_context(void) +{ + return (current->flags & PF_MEMALLOC) || current->reclaim_state; +} + +/* + * Shared implementation of the proactive reclaim kfuncs: performs one + * reclaim pass on @memcg with @nr_pages as the goal, allowing swap, and + * @swappiness as the anon/file balance override (NULL to follow the + * cgroup's own swappiness setting). Returns the reclaimed amount in + * bytes, keeping the byte-based unit of the kfuncs' @size argument. + */ +static unsigned long +bpf_proactive_reclaim_pages(struct mem_cgroup *memcg, unsigned long nr_pages, + int *swappiness) +{ + unsigned long nr_reclaimed; + + if (!nr_pages || unlikely(bpf_in_reclaim_context())) + return 0; + + nr_reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages, GFP_KERNEL, + MEMCG_RECLAIM_MAY_SWAP | + MEMCG_RECLAIM_PROACTIVE, + swappiness); + + return nr_reclaimed * PAGE_SIZE; +} + +/** + * bpf_proactive_reclaim - proactively reclaim memory from a memory + * cgroup + * @memcg: the target memory cgroup to reclaim from + * @size: the amount of memory to reclaim, in bytes + * + * Trigger one proactive reclaim pass on @memcg, similar to a write to + * the memory.reclaim cgroup file: pages are reclaimed according to the + * cgroup's own swappiness setting and swap is allowed. Note that, + * unlike memory.reclaim, this does not retry until @size is reached; + * callers can invoke it again if needed. + * + * The reclaim runs with GFP_KERNEL, so this function must not be called + * from a context that holds a filesystem lock (e.g. an LSM hook invoked + * with inode_lock held): the reclaim path may enter filesystem shrinkers + * and deadlock trying to reacquire the lock. Contexts that set + * PF_MEMALLOC_NOFS/NOIO are handled by the gfp context inheritance. + * + * Return: + * The amount of memory actually reclaimed, in bytes (rounded to full + * pages), or 0 if @size is smaller than a page or the calling task is + * already in a reclaim/freeing context (PF_MEMALLOC). + */ +__bpf_kfunc unsigned long bpf_proactive_reclaim(struct mem_cgroup *memcg, + unsigned long size) +{ + return bpf_proactive_reclaim_pages(memcg, size / PAGE_SIZE, NULL); +} + +/** + * bpf_proactive_reclaim_swappiness - proactively reclaim memory from a + * memory cgroup with an explicit + * swappiness + * @memcg: the target memory cgroup to reclaim from + * @size: the amount of memory to reclaim, in bytes + * @swappiness: swappiness override for this reclaim pass + * + * Same as bpf_proactive_reclaim(), except that the anon/file reclaim + * balance is controlled by @swappiness instead of the cgroup's + * swappiness setting. Valid values are [MIN_SWAPPINESS, MAX_SWAPPINESS] + * and SWAPPINESS_ANON_ONLY, which restricts reclaim to anon folios. + * + * Return: + * The amount of memory actually reclaimed, in bytes (rounded to full + * pages), (unsigned long)-1 if @swappiness is out of range, or 0 if + * @size is smaller than a page or the calling task is already in a + * reclaim/freeing context (PF_MEMALLOC). + */ +__bpf_kfunc unsigned long +bpf_proactive_reclaim_swappiness(struct mem_cgroup *memcg, unsigned long size, + int swappiness) +{ + if (swappiness < MIN_SWAPPINESS || swappiness > SWAPPINESS_ANON_ONLY) + return (unsigned long)-1; + + return bpf_proactive_reclaim_pages(memcg, size / PAGE_SIZE, + &swappiness); +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_memcontrol_kfuncs) @@ -172,6 +287,9 @@ BTF_ID_FLAGS(func, bpf_mem_cgroup_usage) BTF_ID_FLAGS(func, bpf_mem_cgroup_page_state) BTF_ID_FLAGS(func, bpf_mem_cgroup_flush_stats, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_proactive_reclaim, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_proactive_reclaim_swappiness, KF_SLEEPABLE) + BTF_KFUNCS_END(bpf_memcontrol_kfuncs) static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = { From 9fa4eb9cfa567bd2c607819147c27596de4205fa Mon Sep 17 00:00:00 2001 From: Hui Zhu Date: Thu, 20 Aug 2026 14:12:27 +0800 Subject: [PATCH 2/2] selftests/bpf: add memcg async reclaim test Add memcg_async_reclaim selftest that verifies BPF-driven async proactive reclaim can mitigate refault-induced slowdown under memory pressure. The test creates a parent cgroup with a fixed memory.max, and two child cgroups (high/low) under it. Both children concurrently write and repeatedly read-fault a file larger than the shared limit. A BPF program monitors the "high" cgroup's WORKINGSET_REFAULT_FILE stat via a periodic timer, and when it detects refault growth beyond a threshold, triggers async reclaim on the "low" cgroup using bpf_proactive_reclaim(), expecting the "high" cgroup's workload to finish faster than without such reclaim. The reclaim work is queued asynchronously via bpf_wq. Signed-off-by: Hui Zhu --- .../bpf/prog_tests/memcg_async_reclaim.c | 480 ++++++++++++++++++ .../selftests/bpf/progs/memcg_async_reclaim.c | 181 +++++++ 2 files changed, 661 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c create mode 100644 tools/testing/selftests/bpf/progs/memcg_async_reclaim.c diff --git a/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c b/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c new file mode 100644 index 0000000000000..ece7bceaab3c4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Memory controller eBPF async reclaim test + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cgroup_helpers.h" + +struct bpf_args_s { + u64 high_cgroup_id; + u64 low_cgroup_id; + u64 event_delta_threshold; + u64 check_ns; +}; + +#include "memcg_async_reclaim.skel.h" + +#define FILE_SIZE (32 * 1024 * 1024ul) +#define BUFFER_SIZE (4096) +#define CG_LIMIT (32 * 1024 * 1024ul) +#define READ_TIMES 50 + +#define CG_DIR "/memcg_async_reclaim" +#define CG_HIGH_DIR CG_DIR "/high" +#define CG_LOW_DIR CG_DIR "/low" + +#define CHECK_PERIOD_NS (2 * 1000 * 1000ull) +#define EVENT_DELTA_THRESHOLD 1 + +/* + * The workload files must sit on a regular filesystem: with swap + * disabled for the cgroup, tmpfs/ramfs pages are unevictable and would + * OOM the cgroup instead of exercising reclaim; they are also charged + * as anonymous memory, so they never raise the WORKINGSET_REFAULT_FILE + * events the BPF program monitors. Fall back to the current directory + * when /tmp is backed by such a filesystem. + */ +static const char *workload_files_dir(void) +{ + struct statfs st; + + if (!statfs("/tmp", &st) && + (st.f_type == TMPFS_MAGIC || st.f_type == RAMFS_MAGIC)) + return "."; + return "/tmp"; +} + +/* + * The workload children run after test_progs hijacked stdio, so + * anything they print is lost with their private copy of the hijacked + * buffer. The exit status is the only diagnostics channel that reaches + * the parent, so each failing step gets its own code. + */ +enum child_exit_code { + CHILD_EXIT_OK = 0, + CHILD_EXIT_JOIN_CGROUP, + CHILD_EXIT_WRITE_FILE, + CHILD_EXIT_READ_FILE, + CHILD_EXIT_TIME_FILE, +}; + +static const char *child_exit_str(int code) +{ + switch (code) { + case CHILD_EXIT_OK: + return "success"; + case CHILD_EXIT_JOIN_CGROUP: + return "join cgroup"; + case CHILD_EXIT_WRITE_FILE: + return "write data file"; + case CHILD_EXIT_READ_FILE: + return "read data file"; + case CHILD_EXIT_TIME_FILE: + return "write time file"; + default: + return "unknown"; + } +} + +static int setup_high_low_cgroups(u64 *high_cgroup_id, u64 *low_cgroup_id) +{ + int ret; + char limit_buf[20]; + + ret = setup_cgroup_environment(); + if (!ASSERT_OK(ret, "setup_cgroup_environment")) + goto cleanup; + + ret = create_and_get_cgroup(CG_DIR); + if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_DIR)) + goto cleanup; + close(ret); + + ret = enable_controllers(CG_DIR, "memory"); + if (!ASSERT_OK(ret, "enable_controllers")) + goto cleanup; + + snprintf(limit_buf, sizeof(limit_buf), "%lu", CG_LIMIT); + ret = write_cgroup_file(CG_DIR, "memory.max", limit_buf); + if (!ASSERT_OK(ret, "write_cgroup_file memory.max")) + goto cleanup; + + /* + * Keep the workloads from swapping out. With CONFIG_SWAP=n the + * memory.swap.max file does not exist, and no swap can happen + * anyway, so skip the write. + */ + if (!access("/proc/swaps", F_OK)) { + ret = write_cgroup_file(CG_DIR, "memory.swap.max", "0"); + if (!ASSERT_OK(ret, "write_cgroup_file memory.swap.max")) + goto cleanup; + } + + ret = create_and_get_cgroup(CG_HIGH_DIR); + if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_HIGH_DIR)) + goto cleanup; + close(ret); + + *high_cgroup_id = get_cgroup_id(CG_HIGH_DIR); + if (!ASSERT_GT(*high_cgroup_id, 0, "get_cgroup_id")) + goto cleanup; + + ret = create_and_get_cgroup(CG_LOW_DIR); + if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_LOW_DIR)) + goto cleanup; + close(ret); + + *low_cgroup_id = get_cgroup_id(CG_LOW_DIR); + if (!ASSERT_GT(*low_cgroup_id, 0, "get_cgroup_id")) + goto cleanup; + + return 0; + +cleanup: + cleanup_cgroup_environment(); + return -1; +} + +static int write_file(const char *filename) +{ + int ret = -1; + size_t written = 0; + char *buffer; + FILE *fp; + + fp = fopen(filename, "wb"); + if (!fp) + goto out; + + buffer = malloc(BUFFER_SIZE); + if (!buffer) + goto cleanup_fp; + + memset(buffer, 'A', BUFFER_SIZE); + + while (written < FILE_SIZE) { + size_t to_write = FILE_SIZE - written < BUFFER_SIZE ? + FILE_SIZE - written : BUFFER_SIZE; + + if (fwrite(buffer, 1, to_write, fp) != to_write) + goto cleanup; + written += to_write; + } + + ret = 0; +cleanup: + free(buffer); +cleanup_fp: + fclose(fp); +out: + return ret; +} + +static int read_file(const char *filename, int iterations) +{ + int ret = -1; + long page_size = sysconf(_SC_PAGESIZE); + char *map; + size_t i; + int fd; + struct stat sb; + + fd = open(filename, O_RDONLY); + if (fd == -1) + goto out; + + if (fstat(fd, &sb) == -1) + goto cleanup_fd; + + if (sb.st_size != FILE_SIZE) { + fprintf(stderr, "File size mismatch: expected %lu, got %lu\n", + (unsigned long)FILE_SIZE, (unsigned long)sb.st_size); + goto cleanup_fd; + } + + map = mmap(NULL, FILE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0); + if (map == MAP_FAILED) + goto cleanup_fd; + + for (int iter = 0; iter < iterations; iter++) { + for (i = 0; i < FILE_SIZE; i += page_size) { + /* access a byte to trigger page fault */ + volatile char v = map[i]; + (void)v; + } + } + + if (munmap(map, FILE_SIZE) == -1) + goto cleanup_fd; + + ret = 0; + +cleanup_fd: + close(fd); +out: + return ret; +} + +static int real_test_child_work(const char *cgroup_path, char *data_filename, + char *time_filename, int read_times) +{ + struct timespec start, end; + double elapsed; + FILE *fp; + + if (join_parent_cgroup(cgroup_path)) + return CHILD_EXIT_JOIN_CGROUP; + + clock_gettime(CLOCK_MONOTONIC, &start); + + if (write_file(data_filename)) + return CHILD_EXIT_WRITE_FILE; + + if (read_file(data_filename, read_times)) + return CHILD_EXIT_READ_FILE; + + clock_gettime(CLOCK_MONOTONIC, &end); + + if (!time_filename) + return CHILD_EXIT_OK; + + elapsed = (end.tv_sec - start.tv_sec) + + (end.tv_nsec - start.tv_nsec) / 1000000000.0; + printf("%.6f\n", elapsed); + + fp = fopen(time_filename, "w"); + if (!fp) + return CHILD_EXIT_TIME_FILE; + fprintf(fp, "%.6f", elapsed); + fclose(fp); + + return CHILD_EXIT_OK; +} + +static int get_time(char *time_filename, double *time) +{ + int ret = -1; + FILE *fp; + char buf[64]; + + fp = fopen(time_filename, "r"); + if (!ASSERT_OK_PTR(fp, "fopen")) + goto out; + + if (!ASSERT_OK_PTR(fgets(buf, sizeof(buf), fp), "fgets")) + goto cleanup; + + if (sscanf(buf, "%lf", time) != 1) { + PRINT_FAIL("sscanf %s", buf); + goto cleanup; + } + + ret = 0; +cleanup: + fclose(fp); +out: + return ret; +} + +static int +run_high_low_workload(double *high_elapsed, double *low_elapsed, int read_times) +{ + char high_data_file[PATH_MAX]; + char low_data_file[PATH_MAX]; + char high_time_file[PATH_MAX]; + char low_time_file[PATH_MAX]; + const char *dir = workload_files_dir(); + pid_t high_pid = -1, low_pid = -1; + pid_t wait_ret; + int fd, status; + int ret = -1; + + snprintf(high_data_file, sizeof(high_data_file), + "%s/memcg_async_high_data_XXXXXX", dir); + snprintf(low_data_file, sizeof(low_data_file), + "%s/memcg_async_low_data_XXXXXX", dir); + snprintf(high_time_file, sizeof(high_time_file), + "%s/memcg_async_high_time_XXXXXX", dir); + snprintf(low_time_file, sizeof(low_time_file), + "%s/memcg_async_low_time_XXXXXX", dir); + + fd = mkstemp(high_data_file); + if (!ASSERT_GE(fd, 0, "mkstemp")) + goto cleanup; + close(fd); + + fd = mkstemp(low_data_file); + if (!ASSERT_GE(fd, 0, "mkstemp")) + goto cleanup; + close(fd); + + fd = mkstemp(high_time_file); + if (!ASSERT_GE(fd, 0, "mkstemp")) + goto cleanup; + close(fd); + + fd = mkstemp(low_time_file); + if (!ASSERT_GE(fd, 0, "mkstemp")) + goto cleanup; + close(fd); + + low_pid = fork(); + if (!ASSERT_GE(low_pid, 0, "fork low")) + goto cleanup; + if (low_pid == 0) + _exit(real_test_child_work(CG_LOW_DIR, low_data_file, + low_time_file, read_times)); + + high_pid = fork(); + if (!ASSERT_GE(high_pid, 0, "fork high")) + goto cleanup; + if (high_pid == 0) + _exit(real_test_child_work(CG_HIGH_DIR, high_data_file, + high_time_file, read_times)); + + wait_ret = waitpid(low_pid, &status, 0); + if (!ASSERT_GT(wait_ret, 0, "low waitpid")) + goto cleanup; + /* + * The child has been reaped and its PID can already be reused, + * so mark it to keep cleanup from signaling an unrelated process. + */ + low_pid = -1; + if (!ASSERT_TRUE(WIFEXITED(status), "low exited")) + goto cleanup; + if (WEXITSTATUS(status) != CHILD_EXIT_OK) { + PRINT_FAIL("low child failed at: %s (exit status %d)", + child_exit_str(WEXITSTATUS(status)), + WEXITSTATUS(status)); + goto cleanup; + } + + wait_ret = waitpid(high_pid, &status, 0); + if (!ASSERT_GT(wait_ret, 0, "high waitpid")) + goto cleanup; + /* Same as above: the reaped PID must not be signaled again. */ + high_pid = -1; + if (!ASSERT_TRUE(WIFEXITED(status), "high exited")) + goto cleanup; + if (WEXITSTATUS(status) != CHILD_EXIT_OK) { + PRINT_FAIL("high child failed at: %s (exit status %d)", + child_exit_str(WEXITSTATUS(status)), + WEXITSTATUS(status)); + goto cleanup; + } + + if (get_time(high_time_file, high_elapsed)) + goto cleanup; + if (get_time(low_time_file, low_elapsed)) + goto cleanup; + + ret = 0; + +cleanup: + /* On failure, make sure no child process is left behind */ + if (ret) { + if (high_pid > 0) { + kill(high_pid, SIGKILL); + (void)waitpid(high_pid, NULL, 0); + } + if (low_pid > 0) { + kill(low_pid, SIGKILL); + (void)waitpid(low_pid, NULL, 0); + } + } + unlink(low_time_file); + unlink(high_time_file); + unlink(low_data_file); + unlink(high_data_file); + return ret; +} + +static int +setup_bpf(u64 high_cgroup_id, u64 low_cgroup_id, + struct memcg_async_reclaim **skel_ptr) +{ + struct memcg_async_reclaim *skel; + struct bpf_args_s bpf_args = { + .high_cgroup_id = high_cgroup_id, + .low_cgroup_id = low_cgroup_id, + .event_delta_threshold = EVENT_DELTA_THRESHOLD, + .check_ns = CHECK_PERIOD_NS, + }; + LIBBPF_OPTS(bpf_test_run_opts, run_opts, + .ctx_in = &bpf_args, + .ctx_size_in = sizeof(bpf_args)); + int prog_init_fd, err; + + skel = memcg_async_reclaim__open_and_load(); + if (!ASSERT_OK_PTR(skel, "memcg_async_reclaim__open_and_load")) + return -1; + + prog_init_fd = bpf_program__fd(skel->progs.wq_prog_init); + + err = bpf_prog_test_run_opts(prog_init_fd, &run_opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + goto error_out; + if (!ASSERT_EQ(run_opts.retval, 0, "prog_init retval")) + goto error_out; + + *skel_ptr = skel; + return 0; + +error_out: + memcg_async_reclaim__destroy(skel); + return -1; +} + +void test_memcg_wq_async_reclaim(void) +{ + u64 high_cgroup_id, low_cgroup_id; + int err; + double high_time = 0.0, low_time = 0.0; + struct memcg_async_reclaim *skel = NULL; + + err = setup_high_low_cgroups(&high_cgroup_id, &low_cgroup_id); + if (!ASSERT_OK(err, "setup_high_low_cgroups reclaim")) + return; + + err = setup_bpf(high_cgroup_id, low_cgroup_id, &skel); + if (!ASSERT_OK(err, "setup_bpf")) + goto out; + + err = run_high_low_workload(&high_time, &low_time, READ_TIMES); + if (!ASSERT_OK(err, "run_high_low_workload reclaim")) + goto out; + + /* + * The timing comparison below alone cannot distinguish a working + * reclaim from a no-op one, so require that the BPF program + * actually reclaimed memory from the low cgroup. + */ + if (!ASSERT_GT(skel->bss->reclaim_calls, 0, "reclaim_calls")) + goto out; + if (!ASSERT_GT(skel->bss->reclaimed_bytes, 0, "reclaimed_bytes")) + goto out; + + if (high_time >= low_time) + PRINT_FAIL("high cgroup not improved with async reclaim: high_time=%f low_time=%f", + high_time, low_time); + +out: + if (skel) + memcg_async_reclaim__destroy(skel); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c b/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c new file mode 100644 index 0000000000000..f69bfac62939b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include "bpf_experimental.h" +#include +#include +#include + +#define CLOCK_MONOTONIC_ID 1 +#define PAGE_SIZE 4096UL +#define RECLAIM_SIZE (32 * PAGE_SIZE) +#define RECLAIM_MAX_ITER 32 + +struct bpf_args_s { + u64 high_cgroup_id; + u64 low_cgroup_id; + u64 event_delta_threshold; + u64 check_ns; +}; + +struct cgroup_memcg { + struct cgroup *cgrp; + struct mem_cgroup *memcg; +}; + +static u64 wq_high_cgroup_id; +static u64 wq_low_cgroup_id; + +/* + * Statistics exposed to userspace through .bss, so the test can verify + * that reclaim actually happened instead of relying on timing alone. + */ +u64 reclaim_calls; +u64 reclaimed_bytes; + +static int get_cgroup_memcg_from_id(u64 cgroup_id, struct cgroup_memcg *cm) +{ + cm->cgrp = bpf_cgroup_from_id(cgroup_id); + if (!cm->cgrp) + return -1; + + cm->memcg = bpf_get_mem_cgroup(&cm->cgrp->self); + if (!cm->memcg) { + bpf_cgroup_release(cm->cgrp); + return -1; + } + + return 0; +} + +static void put_cgroup_memcg(struct cgroup_memcg *cm) +{ + bpf_put_mem_cgroup(cm->memcg); + bpf_cgroup_release(cm->cgrp); +} + +static int get_cgroup_event(u64 cgroup_id, u64 *val) +{ + struct cgroup_memcg cm; + + if (get_cgroup_memcg_from_id(cgroup_id, &cm)) + return -1; + bpf_mem_cgroup_flush_stats(cm.memcg); + *val = bpf_mem_cgroup_page_state(cm.memcg, + bpf_core_enum_value(enum node_stat_item, + WORKINGSET_REFAULT_FILE)); + put_cgroup_memcg(&cm); + + return 0; +} + +static bool +should_reclaim_cgroup(u64 cgroup_id, u64 *prev_event, u64 event_delta_threshold) +{ + u64 cur, delta; + + if (get_cgroup_event(cgroup_id, &cur)) + return false; + + delta = cur - *prev_event; + *prev_event = cur; + + return delta >= event_delta_threshold; +} + +static int reclaim_cgroup(u64 cgroup_id) +{ + struct cgroup_memcg cm; + int i; + + if (get_cgroup_memcg_from_id(cgroup_id, &cm)) + return 0; + + reclaim_calls++; + for (i = 0; i < RECLAIM_MAX_ITER; i++) { + u64 nr = bpf_proactive_reclaim(cm.memcg, RECLAIM_SIZE); + + if (!nr) + break; + reclaimed_bytes += nr; + } + + put_cgroup_memcg(&cm); + + return 0; +} + +struct wq_elem { + struct bpf_timer timer; + struct bpf_wq work; + u64 prev_event; + u64 event_delta_threshold; + u64 check_ns; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct wq_elem); +} wq_map SEC(".maps"); + +static int async_free(void *map, int *key, void *value) +{ + struct wq_elem *elem = value; + + if (should_reclaim_cgroup(wq_high_cgroup_id, &elem->prev_event, + elem->event_delta_threshold)) { + reclaim_cgroup(wq_low_cgroup_id); + bpf_wq_start(&elem->work, 0); + } + + return 0; +} + +static int wq_timer_cb(void *map, int *key, struct wq_elem *elem) +{ + bpf_wq_start(&elem->work, 0); + bpf_timer_start(&elem->timer, elem->check_ns, 0); + + return 0; +} + +SEC("syscall") +int wq_prog_init(struct bpf_args_s *ctx) +{ + struct wq_elem *elem; + __u32 key = 0; + int ret; + + elem = bpf_map_lookup_elem(&wq_map, &key); + if (!elem) + return -1; + + ret = bpf_wq_init(&elem->work, &wq_map, 0); + if (ret) + return ret; + + ret = bpf_wq_set_callback(&elem->work, async_free, 0); + if (ret) + return ret; + + ret = bpf_timer_init(&elem->timer, &wq_map, CLOCK_MONOTONIC_ID); + if (ret) + return ret; + + ret = bpf_timer_set_callback(&elem->timer, wq_timer_cb); + if (ret) + return ret; + + elem->prev_event = 0; + elem->event_delta_threshold = ctx->event_delta_threshold; + elem->check_ns = ctx->check_ns; + + wq_high_cgroup_id = ctx->high_cgroup_id; + wq_low_cgroup_id = ctx->low_cgroup_id; + + return bpf_timer_start(&elem->timer, elem->check_ns, 0); +} + +char LICENSE[] SEC("license") = "GPL";