mm: huge_memory: a new debugfs interface for splitting THP tests

We did not have a direct user interface of splitting the compound page
backing a THP and there is no need unless we want to expose the THP
implementation details to users.  Make <debugfs>/split_huge_pages accept a
new command to do that.

By writing "<pid>,<vaddr_start>,<vaddr_end>" to
<debugfs>/split_huge_pages, THPs within the given virtual address range
from the process with the given pid are split. It is used to test
split_huge_page function. In addition, a selftest program is added to
tools/testing/selftests/vm to utilize the interface by splitting
PMD THPs and PTE-mapped THPs.

This does not change the old behavior, i.e., writing 1 to the interface
to split all THPs in the system.

Link: https://lkml.kernel.org/r/20210331235309.332292-1-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mika Penttila <mika.penttila@nextfour.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/huge_memory.c

@@ -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>
@@ -2915,16 +2916,14 @@ 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++) {
@@ -2948,15 +2947,155 @@ 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)
 {

tools/testing/selftests/vm/.gitignore

@@ -22,3 +22,4 @@ map_fixed_noreplace
 write_to_hugetlbfs
 hmm-tests
 local_config.*
+split_huge_page_test

tools/testing/selftests/vm/Makefile

@@ -42,6 +42,7 @@ 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)