diff mbox series

[v5,02/13] mm/khugepaged: add struct collapse_control

Message ID 20220504214437.2850685-3-zokeefe@google.com (mailing list archive)
State New
Headers show
Series mm: userspace hugepage collapse | expand

Commit Message

Zach O'Keefe May 4, 2022, 9:44 p.m. UTC
Modularize hugepage collapse by introducing struct collapse_control.
This structure serves to describe the properties of the requested
collapse, as well as serve as a local scratch pad to use during the
collapse itself.

Start by moving global per-node khugepaged statistics into this
new structure, and stack allocate one for khugepaged collapse
context.

Signed-off-by: Zach O'Keefe <zokeefe@google.com>
---
 mm/khugepaged.c | 87 ++++++++++++++++++++++++++++---------------------
 1 file changed, 49 insertions(+), 38 deletions(-)

Comments

David Rientjes May 12, 2022, 8:02 p.m. UTC | #1
On Wed, 4 May 2022, Zach O'Keefe wrote:

> Modularize hugepage collapse by introducing struct collapse_control.
> This structure serves to describe the properties of the requested
> collapse, as well as serve as a local scratch pad to use during the
> collapse itself.
> 
> Start by moving global per-node khugepaged statistics into this
> new structure, and stack allocate one for khugepaged collapse
> context.
> 
> Signed-off-by: Zach O'Keefe <zokeefe@google.com>

Acked-by: David Rientjes <rientjes@google.com>
Peter Xu May 18, 2022, 8:03 p.m. UTC | #2
On Wed, May 04, 2022 at 02:44:26PM -0700, Zach O'Keefe wrote:
> Modularize hugepage collapse by introducing struct collapse_control.
> This structure serves to describe the properties of the requested
> collapse, as well as serve as a local scratch pad to use during the
> collapse itself.
> 
> Start by moving global per-node khugepaged statistics into this
> new structure, and stack allocate one for khugepaged collapse
> context.
> 
> Signed-off-by: Zach O'Keefe <zokeefe@google.com>

Reviewed-by: Peter Xu <peterx@redhat.com>

There's already some UMA changes that seems to be not needed if you're
going with Yang's UMA patch as pre-requisite.  And I also see that there's
some other changes to settle and rebase (e.g. -mm temporarily removed the
khugepaged patch to move the thread around in next patch), so I figured
maybe I'll just stop here and read you next version.

Thanks,
Zach O'Keefe May 18, 2022, 8:11 p.m. UTC | #3
On Wed, May 18, 2022 at 1:03 PM Peter Xu <peterx@redhat.com> wrote:
>
> On Wed, May 04, 2022 at 02:44:26PM -0700, Zach O'Keefe wrote:
> > Modularize hugepage collapse by introducing struct collapse_control.
> > This structure serves to describe the properties of the requested
> > collapse, as well as serve as a local scratch pad to use during the
> > collapse itself.
> >
> > Start by moving global per-node khugepaged statistics into this
> > new structure, and stack allocate one for khugepaged collapse
> > context.
> >
> > Signed-off-by: Zach O'Keefe <zokeefe@google.com>
>
> Reviewed-by: Peter Xu <peterx@redhat.com>
>
> There's already some UMA changes that seems to be not needed if you're
> going with Yang's UMA patch as pre-requisite.  And I also see that there's
> some other changes to settle and rebase (e.g. -mm temporarily removed the
> khugepaged patch to move the thread around in next patch), so I figured
> maybe I'll just stop here and read you next version.
>

Yep that makes sense to me - I should be getting v6 out
today/tomorrow. Thanks for taking the time!

Best,
Zach

> Thanks,
>
> --
> Peter Xu
>
diff mbox series

Patch

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 2c2ed6b4d96c..d3cb670921cd 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -86,6 +86,14 @@  static struct kmem_cache *mm_slot_cache __read_mostly;
 
 #define MAX_PTE_MAPPED_THP 8
 
+struct collapse_control {
+	/* Num pages scanned per node */
+	int node_load[MAX_NUMNODES];
+
+	/* Last target selected in khugepaged_find_target_node() */
+	int last_target_node;
+};
+
 /**
  * struct mm_slot - hash lookup from mm to mm_slot
  * @hash: hash collision list
@@ -786,9 +794,7 @@  static void khugepaged_alloc_sleep(void)
 	remove_wait_queue(&khugepaged_wait, &wait);
 }
 
-static int khugepaged_node_load[MAX_NUMNODES];
-
-static bool khugepaged_scan_abort(int nid)
+static bool khugepaged_scan_abort(int nid, struct collapse_control *cc)
 {
 	int i;
 
@@ -800,11 +806,11 @@  static bool khugepaged_scan_abort(int nid)
 		return false;
 
 	/* If there is a count for this node already, it must be acceptable */
-	if (khugepaged_node_load[nid])
+	if (cc->node_load[nid])
 		return false;
 
 	for (i = 0; i < MAX_NUMNODES; i++) {
-		if (!khugepaged_node_load[i])
+		if (!cc->node_load[i])
 			continue;
 		if (node_distance(nid, i) > node_reclaim_distance)
 			return true;
@@ -819,28 +825,27 @@  static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
 }
 
 #ifdef CONFIG_NUMA
-static int khugepaged_find_target_node(void)
+static int khugepaged_find_target_node(struct collapse_control *cc)
 {
-	static int last_khugepaged_target_node = NUMA_NO_NODE;
 	int nid, target_node = 0, max_value = 0;
 
 	/* find first node with max normal pages hit */
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
-		if (khugepaged_node_load[nid] > max_value) {
-			max_value = khugepaged_node_load[nid];
+		if (cc->node_load[nid] > max_value) {
+			max_value = cc->node_load[nid];
 			target_node = nid;
 		}
 
 	/* do some balance if several nodes have the same hit record */
-	if (target_node <= last_khugepaged_target_node)
-		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
-				nid++)
-			if (max_value == khugepaged_node_load[nid]) {
+	if (target_node <= cc->last_target_node)
+		for (nid = cc->last_target_node + 1; nid < MAX_NUMNODES;
+		     nid++)
+			if (max_value == cc->node_load[nid]) {
 				target_node = nid;
 				break;
 			}
 
-	last_khugepaged_target_node = target_node;
+	cc->last_target_node = target_node;
 	return target_node;
 }
 
@@ -878,7 +883,7 @@  khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
 	return *hpage;
 }
 #else
-static int khugepaged_find_target_node(void)
+static int khugepaged_find_target_node(struct collapse_control *cc)
 {
 	return 0;
 }
@@ -1235,10 +1240,9 @@  static void collapse_huge_page(struct mm_struct *mm,
 	return;
 }
 
-static int khugepaged_scan_pmd(struct mm_struct *mm,
-			       struct vm_area_struct *vma,
-			       unsigned long address,
-			       struct page **hpage)
+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;
 	pte_t *pte, *_pte;
@@ -1256,7 +1260,7 @@  static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (result != SCAN_SUCCEED)
 		goto out;
 
-	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
+	memset(cc->node_load, 0, sizeof(cc->node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -1322,16 +1326,16 @@  static int khugepaged_scan_pmd(struct mm_struct *mm,
 
 		/*
 		 * Record which node the original page is from and save this
-		 * information to khugepaged_node_load[].
+		 * information to cc->node_load[].
 		 * Khugepaged will allocate hugepage from the node has the max
 		 * hit record.
 		 */
 		node = page_to_nid(page);
-		if (khugepaged_scan_abort(node)) {
+		if (khugepaged_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
 			goto out_unmap;
 		}
-		khugepaged_node_load[node]++;
+		cc->node_load[node]++;
 		if (!PageLRU(page)) {
 			result = SCAN_PAGE_LRU;
 			goto out_unmap;
@@ -1382,7 +1386,7 @@  static int khugepaged_scan_pmd(struct mm_struct *mm,
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
 	if (ret) {
-		node = khugepaged_find_target_node();
+		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);
@@ -2033,8 +2037,9 @@  static void collapse_file(struct mm_struct *mm,
 	/* TODO: tracepoints */
 }
 
-static void khugepaged_scan_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start, struct page **hpage)
+static void khugepaged_scan_file(struct mm_struct *mm, struct file *file,
+				 pgoff_t start, struct page **hpage,
+				 struct collapse_control *cc)
 {
 	struct page *page = NULL;
 	struct address_space *mapping = file->f_mapping;
@@ -2045,7 +2050,7 @@  static void khugepaged_scan_file(struct mm_struct *mm,
 
 	present = 0;
 	swap = 0;
-	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
+	memset(cc->node_load, 0, sizeof(cc->node_load));
 	rcu_read_lock();
 	xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) {
 		if (xas_retry(&xas, page))
@@ -2070,11 +2075,11 @@  static void khugepaged_scan_file(struct mm_struct *mm,
 		}
 
 		node = page_to_nid(page);
-		if (khugepaged_scan_abort(node)) {
+		if (khugepaged_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
 			break;
 		}
-		khugepaged_node_load[node]++;
+		cc->node_load[node]++;
 
 		if (!PageLRU(page)) {
 			result = SCAN_PAGE_LRU;
@@ -2107,7 +2112,7 @@  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();
+			node = khugepaged_find_target_node(cc);
 			collapse_file(mm, file, start, hpage, node);
 		}
 	}
@@ -2115,8 +2120,9 @@  static void khugepaged_scan_file(struct mm_struct *mm,
 	/* TODO: tracepoints */
 }
 #else
-static void khugepaged_scan_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start, struct page **hpage)
+static void khugepaged_scan_file(struct mm_struct *mm, struct file *file,
+				 pgoff_t start, struct page **hpage,
+				 struct collapse_control *cc)
 {
 	BUILD_BUG();
 }
@@ -2127,7 +2133,8 @@  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 page **hpage,
+					    struct collapse_control *cc)
 	__releases(&khugepaged_mm_lock)
 	__acquires(&khugepaged_mm_lock)
 {
@@ -2203,12 +2210,13 @@  static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 
 				mmap_read_unlock(mm);
 				ret = 1;
-				khugepaged_scan_file(mm, file, pgoff, hpage);
+				khugepaged_scan_file(mm, file, pgoff, hpage,
+						     cc);
 				fput(file);
 			} else {
 				ret = khugepaged_scan_pmd(mm, vma,
 						khugepaged_scan.address,
-						hpage);
+						hpage, cc);
 			}
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
@@ -2264,7 +2272,7 @@  static int khugepaged_wait_event(void)
 		kthread_should_stop();
 }
 
-static void khugepaged_do_scan(void)
+static void khugepaged_do_scan(struct collapse_control *cc)
 {
 	struct page *hpage = NULL;
 	unsigned int progress = 0, pass_through_head = 0;
@@ -2288,7 +2296,7 @@  static void khugepaged_do_scan(void)
 		if (khugepaged_has_work() &&
 		    pass_through_head < 2)
 			progress += khugepaged_scan_mm_slot(pages - progress,
-							    &hpage);
+							    &hpage, cc);
 		else
 			progress = pages;
 		spin_unlock(&khugepaged_mm_lock);
@@ -2327,12 +2335,15 @@  static void khugepaged_wait_work(void)
 static int khugepaged(void *none)
 {
 	struct mm_slot *mm_slot;
+	struct collapse_control cc = {
+		.last_target_node = NUMA_NO_NODE,
+	};
 
 	set_freezable();
 	set_user_nice(current, MAX_NICE);
 
 	while (!kthread_should_stop()) {
-		khugepaged_do_scan();
+		khugepaged_do_scan(&cc);
 		khugepaged_wait_work();
 	}