linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Zach O'Keefe" <zokeefe@google.com>
To: Alex Shi <alex.shi@linux.alibaba.com>,
	David Hildenbrand <david@redhat.com>,
	 David Rientjes <rientjes@google.com>,
	Matthew Wilcox <willy@infradead.org>,
	 Michal Hocko <mhocko@suse.com>,
	Pasha Tatashin <pasha.tatashin@soleen.com>,
	 SeongJae Park <sj@kernel.org>, Song Liu <songliubraving@fb.com>,
	Vlastimil Babka <vbabka@suse.cz>,  Yang Shi <shy828301@gmail.com>,
	Zi Yan <ziy@nvidia.com>,
	linux-mm@kvack.org
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	 Arnd Bergmann <arnd@arndb.de>,
	Axel Rasmussen <axelrasmussen@google.com>,
	 Chris Kennelly <ckennelly@google.com>,
	Chris Zankel <chris@zankel.net>, Helge Deller <deller@gmx.de>,
	 Hugh Dickins <hughd@google.com>,
	Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
	 "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>,
	Jens Axboe <axboe@kernel.dk>,
	 "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Matt Turner <mattst88@gmail.com>,
	 Max Filippov <jcmvbkbc@gmail.com>,
	Miaohe Lin <linmiaohe@huawei.com>,
	 Minchan Kim <minchan@kernel.org>,
	Patrick Xia <patrickx@google.com>,
	 Pavel Begunkov <asml.silence@gmail.com>,
	Peter Xu <peterx@redhat.com>,
	 Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
	"Zach O'Keefe" <zokeefe@google.com>
Subject: [PATCH 02/12] mm/khugepaged: add struct collapse_control
Date: Sun, 10 Apr 2022 06:54:35 -0700	[thread overview]
Message-ID: <20220410135445.3897054-3-zokeefe@google.com> (raw)
In-Reply-To: <20220410135445.3897054-1-zokeefe@google.com>

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.

Signed-off-by: Zach O'Keefe <zokeefe@google.com>
---
 mm/khugepaged.c | 79 ++++++++++++++++++++++++++++---------------------
 1 file changed, 46 insertions(+), 33 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b403f056a847..eca61eb88dda 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() for this scan */
+	int last_target_node;
+};
+
 /**
  * struct mm_slot - hash lookup from mm to mm_slot
  * @hash: hash collision list
@@ -796,9 +804,7 @@ 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;
 
@@ -810,11 +816,11 @@ 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;
@@ -829,28 +835,28 @@ 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;
 }
 
@@ -888,7 +894,7 @@ 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;
 }
@@ -1248,7 +1254,8 @@ 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 page **hpage,
+			       struct collapse_control *cc)
 {
 	pmd_t *pmd;
 	pte_t *pte, *_pte;
@@ -1266,7 +1273,7 @@ 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) {
@@ -1332,16 +1339,16 @@ 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;
@@ -1392,7 +1399,7 @@ 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);
@@ -2032,7 +2039,8 @@ static void collapse_file(struct mm_struct *mm,
 }
 
 static void khugepaged_scan_file(struct mm_struct *mm,
-		struct file *file, pgoff_t start, struct page **hpage)
+		struct file *file, pgoff_t start, struct page **hpage,
+		struct collapse_control *cc)
 {
 	struct page *page = NULL;
 	struct address_space *mapping = file->f_mapping;
@@ -2043,7 +2051,7 @@ 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))
@@ -2068,11 +2076,11 @@ 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;
@@ -2105,7 +2113,7 @@ 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);
 		}
 	}
@@ -2114,7 +2122,8 @@ 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 file *file, pgoff_t start, struct page **hpage,
+		struct collapse_control *cc)
 {
 	BUILD_BUG();
 }
@@ -2125,7 +2134,8 @@ 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)
 {
@@ -2201,12 +2211,12 @@ 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;
@@ -2262,7 +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;
@@ -2286,7 +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);
@@ -2325,12 +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();
 	}
 
-- 
2.35.1.1178.g4f1659d476-goog



  parent reply	other threads:[~2022-04-10 13:55 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-10 13:54 [PATCH 00/12] mm: userspace hugepage collapse Zach O'Keefe
2022-04-10 13:54 ` [PATCH 01/12] mm/khugepaged: record SCAN_PMD_MAPPED when scan_pmd() finds THP Zach O'Keefe
2022-04-10 13:54 ` Zach O'Keefe [this message]
2022-04-10 13:54 ` [PATCH 03/12] mm/khugepaged: make hugepage allocation context-specific Zach O'Keefe
2022-04-10 17:47   ` kernel test robot
2022-04-10 17:47   ` kernel test robot
2022-04-11 17:28     ` Zach O'Keefe
2022-04-10 13:54 ` [PATCH 04/12] mm/khugepaged: add struct collapse_result Zach O'Keefe
2022-04-10 13:54 ` [PATCH 05/12] mm/madvise: introduce MADV_COLLAPSE sync hugepage collapse Zach O'Keefe
2022-04-10 16:04   ` kernel test robot
2022-04-10 16:14   ` kernel test robot
2022-04-11 17:18     ` Zach O'Keefe
2022-04-10 13:54 ` [PATCH 06/12] mm/khugepaged: remove khugepaged prefix from shared collapse functions Zach O'Keefe
2022-04-10 17:06   ` kernel test robot
2022-04-11 17:42     ` Zach O'Keefe
2022-04-10 13:54 ` [PATCH 07/12] mm/khugepaged: add flag to ignore khugepaged_max_ptes_* Zach O'Keefe
2022-04-10 13:54 ` [PATCH 08/12] mm/khugepaged: add flag to ignore page young/referenced requirement Zach O'Keefe
2022-04-10 13:54 ` [PATCH 09/12] mm/madvise: add MADV_COLLAPSE to process_madvise() Zach O'Keefe
2022-04-10 13:54 ` [PATCH 10/12] selftests/vm: modularize collapse selftests Zach O'Keefe
2022-04-10 13:54 ` [PATCH 11/12] selftests/vm: add MADV_COLLAPSE collapse context to selftests Zach O'Keefe
2022-04-10 13:54 ` [PATCH 12/12] selftests/vm: add test to verify recollapse of THPs Zach O'Keefe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220410135445.3897054-3-zokeefe@google.com \
    --to=zokeefe@google.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@linux.alibaba.com \
    --cc=arnd@arndb.de \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=axelrasmussen@google.com \
    --cc=chris@zankel.net \
    --cc=ckennelly@google.com \
    --cc=david@redhat.com \
    --cc=deller@gmx.de \
    --cc=hughd@google.com \
    --cc=ink@jurassic.park.msu.ru \
    --cc=jcmvbkbc@gmail.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-mm@kvack.org \
    --cc=mattst88@gmail.com \
    --cc=mhocko@suse.com \
    --cc=minchan@kernel.org \
    --cc=pasha.tatashin@soleen.com \
    --cc=patrickx@google.com \
    --cc=peterx@redhat.com \
    --cc=rientjes@google.com \
    --cc=shy828301@gmail.com \
    --cc=sj@kernel.org \
    --cc=songliubraving@fb.com \
    --cc=tsbogend@alpha.franken.de \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).