[PATCH v4 03/13] mm/khugepaged: dedup and simplify hugepage alloc and charging

["Zach O'Keefe" <zokeefe@google.com>]

The following code is duplicated in collapse_huge_page() and
collapse_file():

         /* Only allocate from the target node */
        gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;

        new_page = khugepaged_alloc_page(hpage, gfp, node);
        if (!new_page) {
                result = SCAN_ALLOC_HUGE_PAGE_FAIL;
                goto out;
        }

        if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
                result = SCAN_CGROUP_CHARGE_FAIL;
                goto out;
        }
        count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);

Also, "node" is passed as an argument to both collapse_huge_page() and
collapse_file() and obtained the same way, via
khugepaged_find_target_node().

Move all this into a new helper, alloc_charge_hpage(), and remove the
duplicate code from collapse_huge_page() and collapse_file().  Also,
simplify khugepaged_alloc_page() by returning a bool indicating
allocation success instead of a copy of the (possibly) allocated
struct page.

Suggested-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Zach O'Keefe <zokeefe@google.com>

---
This patch currently depends on 'mm/khugepaged: sched to numa node when
collapse huge page' currently being discussed upstream[1], and
anticipates that this functionality would be equally applicable to
file-backed collapse.  It also goes ahead and wraps this code in a
CONFIF_NUMA #ifdef.

[1] https://lore.kernel.org/linux-mm/20220317065024.2635069-1-maobibo@loongson.cn/

 mm/khugepaged.c | 99 +++++++++++++++++++++++--------------------------
 1 file changed, 46 insertions(+), 53 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 59357e34e7ce..b05fb9a85eab 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -866,8 +866,7 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 	return true;
 }
 
-static struct page *
-khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
+static bool khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
 {
 	VM_BUG_ON_PAGE(*hpage, *hpage);
 
@@ -875,12 +874,12 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
 	if (unlikely(!*hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		*hpage = ERR_PTR(-ENOMEM);
-		return NULL;
+		return false;
 	}
 
 	prep_transhuge_page(*hpage);
 	count_vm_event(THP_COLLAPSE_ALLOC);
-	return *hpage;
+	return true;
 }
 #else
 static int khugepaged_find_target_node(struct collapse_control *cc)
@@ -942,12 +941,11 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 	return true;
 }
 
-static struct page *
-khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
+static bool khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
 {
 	VM_BUG_ON(!*hpage);
 
-	return  *hpage;
+	return true;
 }
 #endif
 
@@ -1069,10 +1067,34 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 	return true;
 }
 
-static void collapse_huge_page(struct mm_struct *mm,
-				   unsigned long address,
-				   struct page **hpage,
-				   int node, int referenced, int unmapped)
+static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
+			      struct collapse_control *cc)
+{
+#ifdef CONFIG_NUMA
+	const struct cpumask *cpumask;
+#endif
+	gfp_t gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
+	int node = khugepaged_find_target_node(cc);
+
+#ifdef CONFIG_NUMA
+	/* sched to specified node before huge page memory copy */
+	if (task_node(current) != node) {
+		cpumask = cpumask_of_node(node);
+		if (!cpumask_empty(cpumask))
+			set_cpus_allowed_ptr(current, cpumask);
+	}
+#endif
+	if (!khugepaged_alloc_page(hpage, gfp, node))
+		return SCAN_ALLOC_HUGE_PAGE_FAIL;
+	if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp)))
+		return SCAN_CGROUP_CHARGE_FAIL;
+	count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC);
+	return SCAN_SUCCEED;
+}
+
+static void collapse_huge_page(struct mm_struct *mm, unsigned long address,
+			       struct page **hpage, int referenced,
+			       int unmapped, struct collapse_control *cc)
 {
 	LIST_HEAD(compound_pagelist);
 	pmd_t *pmd, _pmd;
@@ -1083,14 +1105,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 	int isolated = 0, result = 0;
 	struct vm_area_struct *vma;
 	struct mmu_notifier_range range;
-	gfp_t gfp;
-	const struct cpumask *cpumask;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
-	/* Only allocate from the target node */
-	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
-
 	/*
 	 * Before allocating the hugepage, release the mmap_lock read lock.
 	 * The allocation can take potentially a long time if it involves
@@ -1099,23 +1116,11 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	mmap_read_unlock(mm);
 
-	/* sched to specified node before huage page memory copy */
-	if (task_node(current) != node) {
-		cpumask = cpumask_of_node(node);
-		if (!cpumask_empty(cpumask))
-			set_cpus_allowed_ptr(current, cpumask);
-	}
-	new_page = khugepaged_alloc_page(hpage, gfp, node);
-	if (!new_page) {
-		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+	result = alloc_charge_hpage(hpage, mm, cc);
+	if (result != SCAN_SUCCEED)
 		goto out_nolock;
-	}
 
-	if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
-		result = SCAN_CGROUP_CHARGE_FAIL;
-		goto out_nolock;
-	}
-	count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
+	new_page = *hpage;
 
 	mmap_read_lock(mm);
 	result = hugepage_vma_revalidate(mm, address, &vma);
@@ -1388,10 +1393,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
 	if (ret) {
-		node = khugepaged_find_target_node(cc);
 		/* collapse_huge_page will return with the mmap_lock released */
-		collapse_huge_page(mm, address, hpage, node,
-				referenced, unmapped);
+		collapse_huge_page(mm, address, hpage, referenced, unmapped,
+				   cc);
 	}
 out:
 	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
@@ -1657,7 +1661,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * @file: file that collapse on
  * @start: collapse start address
  * @hpage: new allocated huge page for collapse
- * @node: appointed node the new huge page allocate from
+ * @cc: collapse context and scratchpad
  *
  * Basic scheme is simple, details are more complex:
  *  - allocate and lock a new huge page;
@@ -1674,12 +1678,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *    + restore gaps in the page cache;
  *    + unlock and free huge page;
  */
-static void collapse_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start,
-		struct page **hpage, int node)
+static void collapse_file(struct mm_struct *mm, struct file *file,
+			  pgoff_t start, struct page **hpage,
+			  struct collapse_control *cc)
 {
 	struct address_space *mapping = file->f_mapping;
-	gfp_t gfp;
 	struct page *new_page;
 	pgoff_t index, end = start + HPAGE_PMD_NR;
 	LIST_HEAD(pagelist);
@@ -1691,20 +1694,11 @@ static void collapse_file(struct mm_struct *mm,
 	VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
 
-	/* Only allocate from the target node */
-	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
-
-	new_page = khugepaged_alloc_page(hpage, gfp, node);
-	if (!new_page) {
-		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+	result = alloc_charge_hpage(hpage, mm, cc);
+	if (result != SCAN_SUCCEED)
 		goto out;
-	}
 
-	if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
-		result = SCAN_CGROUP_CHARGE_FAIL;
-		goto out;
-	}
-	count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
+	new_page = *hpage;
 
 	/*
 	 * Ensure we have slots for all the pages in the range.  This is
@@ -2114,8 +2108,7 @@ static void khugepaged_scan_file(struct mm_struct *mm,
 			result = SCAN_EXCEED_NONE_PTE;
 			count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
 		} else {
-			node = khugepaged_find_target_node(cc);
-			collapse_file(mm, file, start, hpage, node);
+			collapse_file(mm, file, start, hpage, cc);
 		}
 	}
 
-- 
2.36.0.464.gb9c8b46e94-goog