Re: [PATCH] sched/deadline: Reject debugfs dl_server writes for offline CPUs

[abaci-kreproducer <abaci@linux.alibaba.com>]

From: abaci-kreproducer <abaci@linux.alibaba.com>

This is an AI-generated validation of this patch. AI successfully
reproduced the issue and confirmed the fix is valid. The results were
verified by D. Wythe <alibuda@linux.alibaba.com>.

Tested-by: abaci-kreproducer <abaci@linux.alibaba.com>
---
We reproduced this issue on the unpatched kernel:

Writing dl_server debugfs parameters (runtime/period) on an offline CPU
triggers WARN_ON_ONCE in dl_server_start(). dmesg shows: "WARNING:
kernel/sched/deadline.c:1804 at dl_server_start+0xa6/0x120".

sched_server_write_common() did not check cpu_online() before calling
dl_server_stop(), dl_server_apply_params(), and dl_server_start(). When
the target CPU is offline, dl_server_start() hits
WARN_ON_ONCE(!cpu_online(cpu_of(rq))). Additionally, if the CPU has been
removed from the root-domain span, dl_bw_cpus() returns 0, causing a
divide-by-zero in __dl_sub()/__dl_add().

The reproducer offlines a non-boot CPU via sysfs, then writes to
/sys/kernel/debug/sched/fair_server/cpuN/runtime and period. This
exercises the unguarded path in sched_server_write_common().

On the patched kernel, writes to an offline CPU's dl_server debugfs
files return -EBUSY. No WARNING or Oops appears in dmesg.
---
Key configuration
* kconfig:
CONFIG_SMP=y
CONFIG_SCHED_DEBUG=y
* kernel_cmdline: -
* rpm package: -
--
run.sh
#!/bin/bash
set -x

echo "=== Kernel Bug Reproducer ==="
echo "Bug: sched/deadline - Divide-by-zero and WARN_ON_ONCE when writing dl_server"
echo "     debugfs params on offline CPUs"
echo "Commit: 7b63735b609891e9dd441361df3ed42a404a5cc6"
echo "Fix: Reject debugfs dl_server writes for offline CPUs with -EBUSY"
echo

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"

# Build the reproducer
echo "Building reproducer..."
make -C "$SCRIPT_DIR/bin" clean
make -C "$SCRIPT_DIR/bin"
if [ $? -ne 0 ]; then
    echo "ERROR: Failed to build reproducer"
    exit 2
fi

# Check prerequisites
echo "Checking prerequisites..."

# Check for debugfs sched path
if [ ! -d "/sys/kernel/debug/sched/fair_server" ]; then
    echo "ERROR: /sys/kernel/debug/sched/fair_server not found."
    echo "  Kernel needs CONFIG_SCHED_DEBUG=y and debugfs mounted."
    exit 2
fi
echo "  debugfs fair_server path: OK"

# Check for at least 2 CPUs
NUM_CPUS=$(nproc)
if [ "$NUM_CPUS" -lt 2 ]; then
    echo "ERROR: Need at least 2 CPUs (have $NUM_CPUS)"
    exit 2
fi
echo "  CPU count: $NUM_CPUS (>= 2): OK"

# Clear dmesg before running
echo "Clearing dmesg..."
dmesg -c > /dev/null || true

# Run the reproducer
echo ""
echo "Running reproducer..."
echo "========================="
"$SCRIPT_DIR/bin/reproducer"
REPRODUCER_EXIT=$?
echo "========================="
echo ""

# Capture dmesg errors after run
echo "Capturing kernel messages..."
mkdir -p "$SCRIPT_DIR/results" || true
dmesg 2>&1 | grep -iE "divide error|Oops|panic|BUG|WARNING|dl_server" > "$SCRIPT_DIR/results/dmesg-errors.txt" || true

# Print dmesg errors if any
if [ -s "$SCRIPT_DIR/results/dmesg-errors.txt" ]; then
    echo ""
    echo "=== Kernel messages detected ==="
    cat "$SCRIPT_DIR/results/dmesg-errors.txt"
    echo ""
fi

# Save test output
echo "Reproducer exit code: $REPRODUCER_EXIT"

echo ""
echo "Reproducer completed."
echo "Exit code: $REPRODUCER_EXIT"
echo "  0 = bug not triggered (possibly fixed)"
echo "  1 = bug triggered"
echo "  2 = prerequisite failure"

exit $REPRODUCER_EXIT
--
reproducer.c
/*
 * reproducer.c - Reproducer for sched/deadline dl_server offline CPU bug
 *
 * Bug: Writing runtime or period via per-CPU dl_server debugfs files
 *      (/sys/kernel/debug/sched/fair_server/cpuN/{runtime,period})
 *      on an offline CPU triggers:
 *
 *   1) Divide-by-zero in dl_server_apply_params():
 *      __dl_sub() and __dl_add() divide by cpus, which can be 0
 *      when the CPU has been removed from any active root-domain span.
 *
 *   2) WARN_ON_ONCE in dl_server_start():
 *      Catches enqueueing the server on an offline rq.
 *
 * Reproducer strategy:
 *   - Find an available CPU (not CPU0, which usually can't be offlined)
 *   - Offline the CPU
 *   - Write to the dl_server debugfs runtime/period files for that CPU
 *   - Check for kernel warnings, Oops, or divide errors in dmesg
 *
 * Fix: commit 7b63735b609891e9dd441361df3ed42a404a5cc6 adds
 *      `if (!cpu_online(cpu_of(rq))) return -EBUSY;` check.
 */

#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <dirent.h>
#include <sched.h>
#include <time.h>

#define DEBUGFS_SCHED_PATH "/sys/kernel/debug/sched/fair_server"
#define CPU_OFFLINE_PATH "/sys/devices/system/cpu/cpu%d/online"
#define MAX_CPUS 256

/*
 * Check if debugfs fair_server path exists (requires CONFIG_SCHED_DEBUG)
 */
static int check_debugfs_available(void)
{
    struct stat st;
    return stat(DEBUGFS_SCHED_PATH, &st) == 0;
}

/*
 * Get number of online CPUs
 */
static int get_num_cpus(void)
{
    int n = sysconf(_SC_NPROCESSORS_ONLN);
    if (n < 0) {
        perror("sysconf(_SC_NPROCESSORS_ONLN)");
        return -1;
    }
    return n;
}

/*
 * Check if a specific CPU directory exists in sysfs
 */
static int cpu_dir_exists(int cpu)
{
    char path[256];
    struct stat st;
    snprintf(path, sizeof(path), "/sys/devices/system/cpu/cpu%d", cpu);
    return stat(path, &st) == 0;
}

/*
 * Read the online status of a CPU from sysfs
 * Returns: 1 if online, 0 if offline, -1 if error or no online file (CPU0)
 */
static int cpu_is_online(int cpu)
{
    char path[256];
    char buf[16];
    int fd;
    ssize_t n;

    snprintf(path, sizeof(path), CPU_OFFLINE_PATH, cpu);
    fd = open(path, O_RDONLY);
    if (fd < 0) {
        /* No online file (e.g., CPU0 or boot CPU) - always online */
        return 1;
    }

    n = read(fd, buf, sizeof(buf) - 1);
    close(fd);
    if (n < 0) {
        perror("read cpu online status");
        return -1;
    }

    buf[n] = '\0';
    return atoi(buf);
}

/*
 * Offline a CPU by writing 0 to its online sysfs file
 */
static int offline_cpu(int cpu)
{
    char path[256];
    int fd;
    ssize_t n;

    snprintf(path, sizeof(path), CPU_OFFLINE_PATH, cpu);
    fd = open(path, O_WRONLY);
    if (fd < 0) {
        fprintf(stderr, "Cannot open %s: %s\n", path, strerror(errno));
        return -1;
    }

    n = write(fd, "0\n", 2);
    close(fd);
    if (n < 0) {
        fprintf(stderr, "Failed to offline CPU %d: %s\n", cpu, strerror(errno));
        return -1;
    }

    printf("CPU %d offlined successfully\n", cpu);
    return 0;
}

/*
 * Online a CPU by writing 1 to its online sysfs file
 */
static int online_cpu(int cpu)
{
    char path[256];
    int fd;
    ssize_t n;

    snprintf(path, sizeof(path), CPU_OFFLINE_PATH, cpu);
    fd = open(path, O_WRONLY);
    if (fd < 0) {
        fprintf(stderr, "Cannot open %s: %s\n", path, strerror(errno));
        return -1;
    }

    n = write(fd, "1\n", 2);
    close(fd);
    if (n < 0) {
        fprintf(stderr, "Failed to online CPU %d: %s\n", cpu, strerror(errno));
        return -1;
    }

    printf("CPU %d onlined successfully\n", cpu);
    return 0;
}

/*
 * Write a value to the dl_server debugfs runtime file for a given CPU
 */
static int write_dl_runtime(int cpu, const char *value)
{
    char path[512];
    int fd;
    ssize_t n;

    snprintf(path, sizeof(path), DEBUGFS_SCHED_PATH "/cpu%d/runtime", cpu);

    fd = open(path, O_WRONLY);
    if (fd < 0) {
        fprintf(stderr, "Cannot open %s: %s\n", path, strerror(errno));
        return -1;
    }

    n = write(fd, value, strlen(value));
    close(fd);

    if (n < 0) {
        fprintf(stderr, "Write to %s failed: %s\n", path, strerror(errno));
        return -1;
    }

    printf("Wrote '%s' to %s (success, wrote %zd bytes)\n", value, path, n);
    return 0;
}

/*
 * Write a value to the dl_server debugfs period file for a given CPU
 */
static int write_dl_period(int cpu, const char *value)
{
    char path[512];
    int fd;
    ssize_t n;

    snprintf(path, sizeof(path), DEBUGFS_SCHED_PATH "/cpu%d/period", cpu);

    fd = open(path, O_WRONLY);
    if (fd < 0) {
        fprintf(stderr, "Cannot open %s: %s\n", path, strerror(errno));
        return -1;
    }

    n = write(fd, value, strlen(value));
    close(fd);

    if (n < 0) {
        fprintf(stderr, "Write to %s failed: %s\n", path, strerror(errno));
        return -1;
    }

    printf("Wrote '%s' to %s (success, wrote %zd bytes)\n", value, path, n);
    return 0;
}

/*
 * Clear dmesg buffer
 */
static void clear_dmesg(void)
{
    /* Use system call to clear dmesg */
    int ret = system("dmesg -c > /dev/null 2>&1");
    (void)ret;
}

/*
 * Check dmesg for kernel error indicators
 * Returns 1 if bug symptoms found, 0 otherwise
 */
static int check_dmesg_for_bug(void)
{
    int ret;

    /* Check for divide error, Oops, panic, WARNING in dmesg */
    ret = system("dmesg 2>&1 | grep -qiE 'divide error|Oops|panic|BUG|WARNING.*deadline'");
    if (ret == 0) {
        return 1;
    }

    return 0;
}

/*
 * Print relevant dmesg output for debugging
 */
static void print_dmesg_errors(void)
{
    system("dmesg 2>&1 | grep -iE 'divide error|Oops|panic|BUG|WARNING|dl_server|EBUSY'");
}

int main(void)
{
    int num_cpus;
    int target_cpu = -1;
    int i;
    int ret;
    int bug_triggered = 0;

    printf("=== sched/deadline dl_server offline CPU bug reproducer ===\n\n");

    /* Step 1: Check prerequisites */
    printf("[Step 1] Checking prerequisites...\n");

    if (!check_debugfs_available()) {
        fprintf(stderr, "ERROR: %s not found. Kernel needs CONFIG_SCHED_DEBUG=y.\n",
                DEBUGFS_SCHED_PATH);
        return 2;
    }
    printf("  debugfs fair_server path exists: OK\n");

    num_cpus = get_num_cpus();
    if (num_cpus < 2) {
        fprintf(stderr, "ERROR: Need at least 2 CPUs to reproduce (have %d)\n", num_cpus);
        return 2;
    }
    printf("  Number of CPUs: %d (need >= 2)\n", num_cpus);

    /* Step 2: Find a target CPU that can be offlined */
    printf("\n[Step 2] Finding offlinable CPU...\n");

    for (i = num_cpus - 1; i > 0; i--) {
        if (!cpu_dir_exists(i)) {
            continue;
        }

        int online = cpu_is_online(i);
        if (online < 0) {
            printf("  CPU %d: error checking status, skipping\n", i);
            continue;
        }

        if (online == 0) {
            /* Already offline, use this one */
            target_cpu = i;
            printf("  CPU %d: already offline, using it\n", target_cpu);
            break;
        }

        /* Try to offline this CPU */
        if (offline_cpu(i) == 0) {
            target_cpu = i;
            break;
        }
        printf("  CPU %d: cannot be offlined, trying next...\n", i);
    }

    if (target_cpu < 0) {
        fprintf(stderr, "ERROR: Could not find any CPU that can be offlined\n");
        return 2;
    }

    /* If we found an already-offline CPU, we need to make sure it's the one
     * we'll use. Otherwise we already offlined it above. */
    if (cpu_is_online(target_cpu)) {
        /* Shouldn't happen, but just in case */
        if (offline_cpu(target_cpu) != 0) {
            fprintf(stderr, "ERROR: Could not offline CPU %d\n", target_cpu);
            return 2;
        }
    }

    printf("  Target CPU for reproducer: %d\n", target_cpu);

    /* Step 3: Clear dmesg before test */
    printf("\n[Step 3] Clearing dmesg...\n");
    clear_dmesg();

    /* Step 4: Trigger the bug - write to dl_server debugfs on offline CPU */
    printf("\n[Step 4] Triggering bug by writing dl_server params on offline CPU %d...\n\n",
           target_cpu);

    /*
     * Try writing runtime first. This should trigger:
     *   - Before fix: divide-by-zero in dl_server_apply_params() -> Oops
     *   - Before fix: WARN_ON_ONCE in dl_server_start()
     *   - After fix: -EBUSY error returned
     */
    printf("--- Writing runtime to offline CPU %d ---\n", target_cpu);
    ret = write_dl_runtime(target_cpu, "1000000000");  /* 1 second in ns */

    if (ret == 0) {
        /* Write succeeded - this means the kernel accepted the write,
         * but the bug may have been triggered internally. Check dmesg. */
        printf("  Write returned success, checking dmesg for kernel messages...\n");
        sleep(1);  /* Give kernel time to log */

        if (check_dmesg_for_bug()) {
            printf("  BUG DETECTED: Kernel error found in dmesg!\n");
            bug_triggered = 1;
        } else {
            printf("  No kernel errors detected in dmesg (bug may be fixed)\n");
        }
    } else {
        /* Write failed - check if it's -EBUSY (fixed) or another error */
        printf("  Write failed. Checking dmesg for any kernel messages...\n");
        sleep(1);

        if (check_dmesg_for_bug()) {
            printf("  BUG DETECTED: Kernel error found in dmesg despite write failure!\n");
            bug_triggered = 1;
        }
    }

    /* Also try writing period */
    printf("\n--- Writing period to offline CPU %d ---\n", target_cpu);
    ret = write_dl_period(target_cpu, "2000000000");  /* 2 seconds in ns */

    if (ret == 0) {
        printf("  Write returned success, checking dmesg...\n");
        sleep(1);

        if (check_dmesg_for_bug() && !bug_triggered) {
            printf("  BUG DETECTED: Kernel error found in dmesg!\n");
            bug_triggered = 1;
        }
    } else {
        printf("  Write failed. Checking dmesg...\n");
        sleep(1);

        if (check_dmesg_for_bug() && !bug_triggered) {
            printf("  BUG DETECTED: Kernel error found in dmesg despite write failure!\n");
            bug_triggered = 1;
        }
    }

    /* Step 5: Print dmesg for debugging */
    printf("\n[Step 5] Relevant kernel messages:\n");
    print_dmesg_errors();

    /* Step 6: Cleanup - bring the CPU back online */
    printf("\n[Step 6] Cleanup - onlining CPU %d...\n", target_cpu);
    if (cpu_is_online(target_cpu) <= 0) {
        online_cpu(target_cpu);
    }

    /* Summary */
    printf("\n=== Summary ===\n");
    if (bug_triggered) {
        printf("BUG TRIGGERED: The kernel bug was successfully reproduced.\n");
        printf("Expected behavior: divide-by-zero Oops or WARN_ON_ONCE in dl_server_start()\n");
        return 1;  /* Return non-zero to indicate bug triggered */
    } else {
        printf("BUG NOT TRIGGERED: No kernel errors detected.\n");
        printf("Possible reasons:\n");
        printf("  - The fix patch is applied (write returns -EBUSY)\n");
        printf("  - The CPU could not be fully offlined from root-domain span\n");
        printf("  - Race condition: CPU came back online before write\n");
        return 0;
    }
}