@@ -7,6 +7,7 @@
#include <linux/mm.h>
#include <linux/sched.h>
+#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/numa_balancing.h>
#include <linux/highmem.h>
@@ -2927,16 +2928,14 @@ static struct shrinker deferred_split_shrinker = {
};
#ifdef CONFIG_DEBUG_FS
-static int split_huge_pages_set(void *data, u64 val)
+static void split_huge_pages_all(void)
{
struct zone *zone;
struct page *page;
unsigned long pfn, max_zone_pfn;
unsigned long total = 0, split = 0;
- if (val != 1)
- return -EINVAL;
-
+ pr_debug("Split all THPs\n");
for_each_populated_zone(zone) {
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
@@ -2960,15 +2959,155 @@ static int split_huge_pages_set(void *data, u64 val)
unlock_page(page);
next:
put_page(page);
+ cond_resched();
}
}
- pr_info("%lu of %lu THP split\n", split, total);
+ pr_debug("%lu of %lu THP split\n", split, total);
+}
- return 0;
+static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma)
+{
+ return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) ||
+ is_vm_hugetlb_page(vma);
+}
+
+static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
+ unsigned long vaddr_end)
+{
+ int ret = 0;
+ struct task_struct *task;
+ struct mm_struct *mm;
+ unsigned long total = 0, split = 0;
+ unsigned long addr;
+
+ vaddr_start &= PAGE_MASK;
+ vaddr_end &= PAGE_MASK;
+
+ /* Find the task_struct from pid */
+ rcu_read_lock();
+ task = find_task_by_vpid(pid);
+ if (!task) {
+ rcu_read_unlock();
+ ret = -ESRCH;
+ goto out;
+ }
+ get_task_struct(task);
+ rcu_read_unlock();
+
+ /* Find the mm_struct */
+ mm = get_task_mm(task);
+ put_task_struct(task);
+
+ if (!mm) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
+ pid, vaddr_start, vaddr_end);
+
+ mmap_read_lock(mm);
+ /*
+ * always increase addr by PAGE_SIZE, since we could have a PTE page
+ * table filled with PTE-mapped THPs, each of which is distinct.
+ */
+ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
+ struct vm_area_struct *vma = find_vma(mm, addr);
+ unsigned int follflags;
+ struct page *page;
+
+ if (!vma || addr < vma->vm_start)
+ break;
+
+ /* skip special VMA and hugetlb VMA */
+ if (vma_not_suitable_for_thp_split(vma)) {
+ addr = vma->vm_end;
+ continue;
+ }
+
+ /* FOLL_DUMP to ignore special (like zero) pages */
+ follflags = FOLL_GET | FOLL_DUMP;
+ page = follow_page(vma, addr, follflags);
+
+ if (IS_ERR(page))
+ continue;
+ if (!page)
+ continue;
+
+ if (!is_transparent_hugepage(page))
+ goto next;
+
+ total++;
+ if (!can_split_huge_page(compound_head(page), NULL))
+ goto next;
+
+ if (!trylock_page(page))
+ goto next;
+
+ if (!split_huge_page(page))
+ split++;
+
+ unlock_page(page);
+next:
+ put_page(page);
+ cond_resched();
+ }
+ mmap_read_unlock(mm);
+ mmput(mm);
+
+ pr_debug("%lu of %lu THP split\n", split, total);
+
+out:
+ return ret;
}
-DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
- "%llu\n");
+
+#define MAX_INPUT_BUF_SZ 255
+
+static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppops)
+{
+ static DEFINE_MUTEX(split_debug_mutex);
+ ssize_t ret;
+ char input_buf[MAX_INPUT_BUF_SZ]; /* hold pid, start_vaddr, end_vaddr */
+ int pid;
+ unsigned long vaddr_start, vaddr_end;
+
+ ret = mutex_lock_interruptible(&split_debug_mutex);
+ if (ret)
+ return ret;
+
+ ret = -EFAULT;
+
+ memset(input_buf, 0, MAX_INPUT_BUF_SZ);
+ if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ)))
+ goto out;
+
+ input_buf[MAX_INPUT_BUF_SZ - 1] = '\0';
+ ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
+ if (ret == 1 && pid == 1) {
+ split_huge_pages_all();
+ ret = strlen(input_buf);
+ goto out;
+ } else if (ret != 3) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
+ if (!ret)
+ ret = strlen(input_buf);
+out:
+ mutex_unlock(&split_debug_mutex);
+ return ret;
+
+}
+
+static const struct file_operations split_huge_pages_fops = {
+ .owner = THIS_MODULE,
+ .write = split_huge_pages_write,
+ .llseek = no_llseek,
+};
static int __init split_huge_pages_debugfs(void)
{
@@ -23,3 +23,4 @@ write_to_hugetlbfs
hmm-tests
memfd_secret
local_config.*
+split_huge_page_test
@@ -43,6 +43,7 @@ TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += userfaultfd
+TEST_GEN_FILES += split_huge_page_test
ifeq ($(MACHINE),x86_64)
CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
new file mode 100644
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual
+ * address range in a process via <debugfs>/split_huge_pages interface.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <malloc.h>
+#include <stdbool.h>
+
+uint64_t pagesize;
+unsigned int pageshift;
+uint64_t pmd_pagesize;
+
+#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size"
+#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
+#define SMAP_PATH "/proc/self/smaps"
+#define INPUT_MAX 80
+
+#define PFN_MASK ((1UL<<55)-1)
+#define KPF_THP (1UL<<22)
+
+int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
+{
+ uint64_t paddr;
+ uint64_t page_flags;
+
+ if (pagemap_file) {
+ pread(pagemap_file, &paddr, sizeof(paddr),
+ ((long)vaddr >> pageshift) * sizeof(paddr));
+
+ if (kpageflags_file) {
+ pread(kpageflags_file, &page_flags, sizeof(page_flags),
+ (paddr & PFN_MASK) * sizeof(page_flags));
+
+ return !!(page_flags & KPF_THP);
+ }
+ }
+ return 0;
+}
+
+
+static uint64_t read_pmd_pagesize(void)
+{
+ int fd;
+ char buf[20];
+ ssize_t num_read;
+
+ fd = open(PMD_SIZE_PATH, O_RDONLY);
+ if (fd == -1) {
+ perror("Open hpage_pmd_size failed");
+ exit(EXIT_FAILURE);
+ }
+ num_read = read(fd, buf, 19);
+ if (num_read < 1) {
+ close(fd);
+ perror("Read hpage_pmd_size failed");
+ exit(EXIT_FAILURE);
+ }
+ buf[num_read] = '\0';
+ close(fd);
+
+ return strtoul(buf, NULL, 10);
+}
+
+static int write_file(const char *path, const char *buf, size_t buflen)
+{
+ int fd;
+ ssize_t numwritten;
+
+ fd = open(path, O_WRONLY);
+ if (fd == -1)
+ return 0;
+
+ numwritten = write(fd, buf, buflen - 1);
+ close(fd);
+ if (numwritten < 1)
+ return 0;
+
+ return (unsigned int) numwritten;
+}
+
+static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end)
+{
+ char input[INPUT_MAX];
+ int ret;
+
+ ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
+ vaddr_end);
+ if (ret >= INPUT_MAX) {
+ printf("%s: Debugfs input is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+ if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) {
+ perror(SPLIT_DEBUGFS);
+ exit(EXIT_FAILURE);
+ }
+}
+
+#define MAX_LINE_LENGTH 500
+
+static bool check_for_pattern(FILE *fp, const char *pattern, char *buf)
+{
+ while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) {
+ if (!strncmp(buf, pattern, strlen(pattern)))
+ return true;
+ }
+ return false;
+}
+
+static uint64_t check_huge(void *addr)
+{
+ uint64_t thp = 0;
+ int ret;
+ FILE *fp;
+ char buffer[MAX_LINE_LENGTH];
+ char addr_pattern[MAX_LINE_LENGTH];
+
+ ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
+ (unsigned long) addr);
+ if (ret >= MAX_LINE_LENGTH) {
+ printf("%s: Pattern is too long\n", __func__);
+ exit(EXIT_FAILURE);
+ }
+
+
+ fp = fopen(SMAP_PATH, "r");
+ if (!fp) {
+ printf("%s: Failed to open file %s\n", __func__, SMAP_PATH);
+ exit(EXIT_FAILURE);
+ }
+ if (!check_for_pattern(fp, addr_pattern, buffer))
+ goto err_out;
+
+ /*
+ * Fetch the AnonHugePages: in the same block and check the number of
+ * hugepages.
+ */
+ if (!check_for_pattern(fp, "AnonHugePages:", buffer))
+ goto err_out;
+
+ if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) {
+ printf("Reading smap error\n");
+ exit(EXIT_FAILURE);
+ }
+
+err_out:
+ fclose(fp);
+ return thp;
+}
+
+void split_pmd_thp(void)
+{
+ char *one_page;
+ size_t len = 4 * pmd_pagesize;
+ uint64_t thp_size;
+ size_t i;
+
+ one_page = memalign(pmd_pagesize, len);
+
+ if (!one_page) {
+ printf("Fail to allocate memory\n");
+ exit(EXIT_FAILURE);
+ }
+
+ madvise(one_page, len, MADV_HUGEPAGE);
+
+ for (i = 0; i < len; i++)
+ one_page[i] = (char)i;
+
+ thp_size = check_huge(one_page);
+ if (!thp_size) {
+ printf("No THP is allocated\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /* split all THPs */
+ write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
+
+ for (i = 0; i < len; i++)
+ if (one_page[i] != (char)i) {
+ printf("%ld byte corrupted\n", i);
+ exit(EXIT_FAILURE);
+ }
+
+
+ thp_size = check_huge(one_page);
+ if (thp_size) {
+ printf("Still %ld kB AnonHugePages not split\n", thp_size);
+ exit(EXIT_FAILURE);
+ }
+
+ printf("Split huge pages successful\n");
+ free(one_page);
+}
+
+void split_pte_mapped_thp(void)
+{
+ char *one_page, *pte_mapped, *pte_mapped2;
+ size_t len = 4 * pmd_pagesize;
+ uint64_t thp_size;
+ size_t i;
+ const char *pagemap_template = "/proc/%d/pagemap";
+ const char *kpageflags_proc = "/proc/kpageflags";
+ char pagemap_proc[255];
+ int pagemap_fd;
+ int kpageflags_fd;
+
+ if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) {
+ perror("get pagemap proc error");
+ exit(EXIT_FAILURE);
+ }
+ pagemap_fd = open(pagemap_proc, O_RDONLY);
+
+ if (pagemap_fd == -1) {
+ perror("read pagemap:");
+ exit(EXIT_FAILURE);
+ }
+
+ kpageflags_fd = open(kpageflags_proc, O_RDONLY);
+
+ if (kpageflags_fd == -1) {
+ perror("read kpageflags:");
+ exit(EXIT_FAILURE);
+ }
+
+ one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+
+ madvise(one_page, len, MADV_HUGEPAGE);
+
+ for (i = 0; i < len; i++)
+ one_page[i] = (char)i;
+
+ thp_size = check_huge(one_page);
+ if (!thp_size) {
+ printf("No THP is allocated\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /* remap the first pagesize of first THP */
+ pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
+
+ /* remap the Nth pagesize of Nth THP */
+ for (i = 1; i < 4; i++) {
+ pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i,
+ pagesize, pagesize,
+ MREMAP_MAYMOVE|MREMAP_FIXED,
+ pte_mapped + pagesize * i);
+ if (pte_mapped2 == (char *)-1) {
+ perror("mremap failed");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ /* smap does not show THPs after mremap, use kpageflags instead */
+ thp_size = 0;
+ for (i = 0; i < pagesize * 4; i++)
+ if (i % pagesize == 0 &&
+ is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+ thp_size++;
+
+ if (thp_size != 4) {
+ printf("Some THPs are missing during mremap\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /* split all remapped THPs */
+ write_debugfs(getpid(), (uint64_t)pte_mapped,
+ (uint64_t)pte_mapped + pagesize * 4);
+
+ /* smap does not show THPs after mremap, use kpageflags instead */
+ thp_size = 0;
+ for (i = 0; i < pagesize * 4; i++) {
+ if (pte_mapped[i] != (char)i) {
+ printf("%ld byte corrupted\n", i);
+ exit(EXIT_FAILURE);
+ }
+ if (i % pagesize == 0 &&
+ is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+ thp_size++;
+ }
+
+ if (thp_size) {
+ printf("Still %ld THPs not split\n", thp_size);
+ exit(EXIT_FAILURE);
+ }
+
+ printf("Split PTE-mapped huge pages successful\n");
+ munmap(one_page, len);
+ close(pagemap_fd);
+ close(kpageflags_fd);
+}
+
+int main(int argc, char **argv)
+{
+ if (geteuid() != 0) {
+ printf("Please run the benchmark as root\n");
+ exit(EXIT_FAILURE);
+ }
+
+ pagesize = getpagesize();
+ pageshift = ffs(pagesize) - 1;
+ pmd_pagesize = read_pmd_pagesize();
+
+ split_pmd_thp();
+ split_pte_mapped_thp();
+
+ return 0;
+}