[PATCH v2 03/12] mm/khugepaged: make hugepage allocation context-specific

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

Add hugepage allocation context to struct collapse_context, allowing
different collapse contexts to allocate hugepages differently.  For
example, khugepaged decides to allocate differently in NUMA and UMA
configurations, and other collapse contexts shouldn't be coupled to this
decision.

Additionally, move [pre]allocated hugepage pointer into
struct collapse_context.

Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Reported-by: kernel test robot <lkp@intel.com>
---
 mm/khugepaged.c | 96 ++++++++++++++++++++++++-------------------------
 1 file changed, 48 insertions(+), 48 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 25f45ac7f6bd..21c8436fa73c 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -92,6 +92,10 @@ struct collapse_control {
 
 	/* Last target selected in khugepaged_find_target_node() for this scan */
 	int last_target_node;
+
+	struct page *hpage;
+	struct page* (*alloc_hpage)(struct collapse_control *cc, gfp_t gfp,
+				    int node);
 };
 
 /**
@@ -877,21 +881,21 @@ 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 struct page *khugepaged_alloc_page(struct collapse_control *cc,
+					  gfp_t gfp, int node)
 {
-	VM_BUG_ON_PAGE(*hpage, *hpage);
+	VM_BUG_ON_PAGE(cc->hpage, cc->hpage);
 
-	*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
-	if (unlikely(!*hpage)) {
+	cc->hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
+	if (unlikely(!cc->hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
-		*hpage = ERR_PTR(-ENOMEM);
+		cc->hpage = ERR_PTR(-ENOMEM);
 		return NULL;
 	}
 
-	prep_transhuge_page(*hpage);
+	prep_transhuge_page(cc->hpage);
 	count_vm_event(THP_COLLAPSE_ALLOC);
-	return *hpage;
+	return cc->hpage;
 }
 #else
 static int khugepaged_find_target_node(struct collapse_control *cc)
@@ -953,12 +957,12 @@ 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 struct page *khugepaged_alloc_page(struct collapse_control *cc,
+					  gfp_t gfp, int node)
 {
-	VM_BUG_ON(!*hpage);
+	VM_BUG_ON(!cc->hpage);
 
-	return  *hpage;
+	return cc->hpage;
 }
 #endif
 
@@ -1080,10 +1084,9 @@ 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 void collapse_huge_page(struct mm_struct *mm, unsigned long address,
+			       struct collapse_control *cc, int referenced,
+			       int unmapped)
 {
 	LIST_HEAD(compound_pagelist);
 	pmd_t *pmd, _pmd;
@@ -1096,6 +1099,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	struct mmu_notifier_range range;
 	gfp_t gfp;
 	const struct cpumask *cpumask;
+	int node;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
@@ -1110,13 +1114,14 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	mmap_read_unlock(mm);
 
+	node = khugepaged_find_target_node(cc);
 	/* 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);
+	new_page = cc->alloc_hpage(cc, gfp, node);
 	if (!new_page) {
 		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
 		goto out_nolock;
@@ -1238,15 +1243,15 @@ static void collapse_huge_page(struct mm_struct *mm,
 	update_mmu_cache_pmd(vma, address, pmd);
 	spin_unlock(pmd_ptl);
 
-	*hpage = NULL;
+	cc->hpage = NULL;
 
 	khugepaged_pages_collapsed++;
 	result = SCAN_SUCCEED;
 out_up_write:
 	mmap_write_unlock(mm);
 out_nolock:
-	if (!IS_ERR_OR_NULL(*hpage))
-		mem_cgroup_uncharge(page_folio(*hpage));
+	if (!IS_ERR_OR_NULL(cc->hpage))
+		mem_cgroup_uncharge(page_folio(cc->hpage));
 	trace_mm_collapse_huge_page(mm, isolated, result);
 	return;
 }
@@ -1254,7 +1259,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 static int khugepaged_scan_pmd(struct mm_struct *mm,
 			       struct vm_area_struct *vma,
 			       unsigned long address,
-			       struct page **hpage,
 			       struct collapse_control *cc)
 {
 	pmd_t *pmd;
@@ -1399,10 +1403,8 @@ 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, cc, referenced, unmapped);
 	}
 out:
 	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
@@ -1667,8 +1669,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * @mm: process address space where collapse happens
  * @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;
@@ -1686,8 +1687,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *    + unlock and free huge page;
  */
 static void collapse_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start,
-		struct page **hpage, int node)
+			  struct file *file, pgoff_t start,
+			  struct collapse_control *cc)
 {
 	struct address_space *mapping = file->f_mapping;
 	gfp_t gfp;
@@ -1697,15 +1698,16 @@ static void collapse_file(struct mm_struct *mm,
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
 	int nr_none = 0, result = SCAN_SUCCEED;
 	bool is_shmem = shmem_file(file);
-	int nr;
+	int nr, node;
 
 	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;
+	node = khugepaged_find_target_node(cc);
 
-	new_page = khugepaged_alloc_page(hpage, gfp, node);
+	new_page = cc->alloc_hpage(cc, gfp, node);
 	if (!new_page) {
 		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
 		goto out;
@@ -1998,7 +2000,7 @@ static void collapse_file(struct mm_struct *mm,
 		 * Remove pte page tables, so we can re-fault the page as huge.
 		 */
 		retract_page_tables(mapping, start);
-		*hpage = NULL;
+		cc->hpage = NULL;
 
 		khugepaged_pages_collapsed++;
 	} else {
@@ -2045,14 +2047,14 @@ static void collapse_file(struct mm_struct *mm,
 	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
-	if (!IS_ERR_OR_NULL(*hpage))
-		mem_cgroup_uncharge(page_folio(*hpage));
+	if (!IS_ERR_OR_NULL(cc->hpage))
+		mem_cgroup_uncharge(page_folio(cc->hpage));
 	/* TODO: tracepoints */
 }
 
 static void khugepaged_scan_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start, struct page **hpage,
-		struct collapse_control *cc)
+				 struct file *file, pgoff_t start,
+				 struct collapse_control *cc)
 {
 	struct page *page = NULL;
 	struct address_space *mapping = file->f_mapping;
@@ -2125,8 +2127,7 @@ 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, cc);
 		}
 	}
 
@@ -2134,8 +2135,8 @@ static void khugepaged_scan_file(struct mm_struct *mm,
 }
 #else
 static void khugepaged_scan_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start, struct page **hpage,
-		struct collapse_control *cc)
+				 struct file *file, pgoff_t start,
+				 struct collapse_control *cc)
 {
 	BUILD_BUG();
 }
@@ -2146,7 +2147,6 @@ static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
 #endif
 
 static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
-					    struct page **hpage,
 					    struct collapse_control *cc)
 	__releases(&khugepaged_mm_lock)
 	__acquires(&khugepaged_mm_lock)
@@ -2223,12 +2223,11 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 
 				mmap_read_unlock(mm);
 				ret = 1;
-				khugepaged_scan_file(mm, file, pgoff, hpage, cc);
+				khugepaged_scan_file(mm, file, pgoff, cc);
 				fput(file);
 			} else {
 				ret = khugepaged_scan_pmd(mm, vma,
-						khugepaged_scan.address,
-						hpage, cc);
+						khugepaged_scan.address, cc);
 			}
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
@@ -2286,15 +2285,15 @@ static int khugepaged_wait_event(void)
 
 static void khugepaged_do_scan(struct collapse_control *cc)
 {
-	struct page *hpage = NULL;
 	unsigned int progress = 0, pass_through_head = 0;
 	unsigned int pages = READ_ONCE(khugepaged_pages_to_scan);
 	bool wait = true;
 
+	cc->hpage = NULL;
 	lru_add_drain_all();
 
 	while (progress < pages) {
-		if (!khugepaged_prealloc_page(&hpage, &wait))
+		if (!khugepaged_prealloc_page(&cc->hpage, &wait))
 			break;
 
 		cond_resched();
@@ -2308,14 +2307,14 @@ static void khugepaged_do_scan(struct collapse_control *cc)
 		if (khugepaged_has_work() &&
 		    pass_through_head < 2)
 			progress += khugepaged_scan_mm_slot(pages - progress,
-							    &hpage, cc);
+							    cc);
 		else
 			progress = pages;
 		spin_unlock(&khugepaged_mm_lock);
 	}
 
-	if (!IS_ERR_OR_NULL(hpage))
-		put_page(hpage);
+	if (!IS_ERR_OR_NULL(cc->hpage))
+		put_page(cc->hpage);
 }
 
 static bool khugepaged_should_wakeup(void)
@@ -2349,6 +2348,7 @@ static int khugepaged(void *none)
 	struct mm_slot *mm_slot;
 	struct collapse_control cc = {
 		.last_target_node = NUMA_NO_NODE,
+		.alloc_hpage = &khugepaged_alloc_page,
 	};
 
 	set_freezable();
-- 
2.36.0.rc0.470.gd361397f0d-goog