All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org, Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Matthew Wilcox <willy@infradead.org>,
	Shakeel Butt <shakeelb@google.com>,
	Yang Shi <yang.shi@linux.alibaba.com>,
	David Nellans <dnellans@nvidia.com>,
	linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 08/16] mm: page_vma_walk: teach it about PMD-mapped PUD THP.
Date: Wed,  2 Sep 2020 14:06:20 -0400	[thread overview]
Message-ID: <20200902180628.4052244-9-zi.yan@sent.com> (raw)
In-Reply-To: <20200902180628.4052244-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

We now have PMD-mapped PUD THP and PTE-mapped PUD THP, page_vma_walk
should handle them properly.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/page_vma_mapped.c | 116 ++++++++++++++++++++++++++++++-------------
 1 file changed, 82 insertions(+), 34 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index d9d39ec06e21..549e296287fd 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -52,6 +52,22 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 	return true;
 }
 
+static bool map_pmd(struct page_vma_mapped_walk *pvmw)
+{
+	pmd_t pmde;
+
+	pvmw->pmd = pmd_offset(pvmw->pud, pvmw->address);
+	pmde = READ_ONCE(*pvmw->pmd);
+	if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
+		pvmw->ptl = pmd_lock(pvmw->vma->vm_mm, pvmw->pmd);
+		return true;
+	} else if (!pmd_present(pmde))
+		return false;
+
+	pvmw->ptl = pmd_lock(pvmw->vma->vm_mm, pvmw->pmd);
+	return true;
+}
+
 static inline bool pfn_is_match(struct page *page, unsigned long pfn)
 {
 	unsigned long page_pfn = page_to_pfn(page);
@@ -115,6 +131,38 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 	return pfn_is_match(pvmw->page, pfn);
 }
 
+/* 0: not mapped, 1: pmd_page, 2: pmd  */
+static int check_pmd(struct page_vma_mapped_walk *pvmw)
+{
+	unsigned long pfn;
+
+	if (likely(pmd_trans_huge(*pvmw->pmd))) {
+		if (pvmw->flags & PVMW_MIGRATION)
+			return 0;
+		pfn = pmd_pfn(*pvmw->pmd);
+		if (!pfn_is_match(pvmw->page, pfn))
+			return 0;
+		return 1;
+	} else if (!pmd_present(*pvmw->pmd)) {
+		if (thp_migration_supported()) {
+			if (!(pvmw->flags & PVMW_MIGRATION))
+				return 0;
+			if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
+				swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
+
+				pfn = migration_entry_to_pfn(entry);
+				if (!pfn_is_match(pvmw->page, pfn))
+					return 0;
+				return 1;
+			}
+		}
+		return 0;
+	}
+	/* THP pmd was split under us: handle on pte level */
+	spin_unlock(pvmw->ptl);
+	pvmw->ptl = NULL;
+	return 2;
+}
 /**
  * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
  * @pvmw->address
@@ -146,14 +194,14 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t pude;
-	pmd_t pmde;
+	int pmd_res;
 
 	if (!pvmw->pte && !pvmw->pmd && pvmw->pud)
 		return not_found(pvmw);
 
 	/* The only possible pmd mapping has been handled on last iteration */
 	if (pvmw->pmd && !pvmw->pte)
-		return not_found(pvmw);
+		goto next_pmd;
 
 	if (pvmw->pte)
 		goto next_pte;
@@ -201,43 +249,43 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	} else if (!pud_present(pude))
 		return false;
 
-	pvmw->pmd = pmd_offset(pvmw->pud, pvmw->address);
-	/*
-	 * Make sure the pmd value isn't cached in a register by the
-	 * compiler and used as a stale value after we've observed a
-	 * subsequent update.
-	 */
-	pmde = READ_ONCE(*pvmw->pmd);
-	if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
-		pvmw->ptl = pmd_lock(mm, pvmw->pmd);
-		if (likely(pmd_trans_huge(*pvmw->pmd))) {
-			if (pvmw->flags & PVMW_MIGRATION)
-				return not_found(pvmw);
-			if (pmd_page(*pvmw->pmd) != page)
-				return not_found(pvmw);
+	if (!map_pmd(pvmw))
+		goto next_pmd;
+	/* pmd locked after map_pmd  */
+	while (1) {
+		pmd_res = check_pmd(pvmw);
+		if (pmd_res == 1) /* pmd_page */
 			return true;
-		} else if (!pmd_present(*pvmw->pmd)) {
-			if (thp_migration_supported()) {
-				if (!(pvmw->flags & PVMW_MIGRATION))
-					return not_found(pvmw);
-				if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
-					swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
-
-					if (migration_entry_to_page(entry) != page)
-						return not_found(pvmw);
-					return true;
+		else if (pmd_res == 2) /* pmd entry  */
+			goto pte_level;
+next_pmd:
+		/* Only PMD-mapped PUD THP has next pmd  */
+		if (!(PageTransHuge(pvmw->page) && compound_order(pvmw->page) == HPAGE_PUD_ORDER))
+			return not_found(pvmw);
+		do {
+			pvmw->address += HPAGE_PMD_SIZE;
+			if (pvmw->address >= pvmw->vma->vm_end ||
+			    pvmw->address >=
+					__vma_address(pvmw->page, pvmw->vma) +
+					thp_nr_pages(pvmw->page) * PAGE_SIZE)
+				return not_found(pvmw);
+			/* Did we cross page table boundary? */
+			if (pvmw->address % PUD_SIZE == 0) {
+				if (pvmw->ptl) {
+					spin_unlock(pvmw->ptl);
+					pvmw->ptl = NULL;
 				}
+				goto restart;
+			} else {
+				pvmw->pmd++;
 			}
-			return not_found(pvmw);
-		} else {
-			/* THP pmd was split under us: handle on pte level */
-			spin_unlock(pvmw->ptl);
-			pvmw->ptl = NULL;
-		}
-	} else if (!pmd_present(pmde)) {
-		return false;
+		} while (pmd_none(*pvmw->pmd));
+
+		if (!pvmw->ptl)
+			pvmw->ptl = pmd_lock(mm, pvmw->pmd);
 	}
 
+pte_level:
 	if (!map_pte(pvmw))
 		goto next_pte;
 	while (1) {
-- 
2.28.0



  parent reply	other threads:[~2020-09-02 18:06 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-02 18:06 [RFC PATCH 00/16] 1GB THP support on x86_64 Zi Yan
2020-09-02 18:06 ` [RFC PATCH 01/16] mm: add pagechain container for storing multiple pages Zi Yan
2020-09-02 20:29   ` Randy Dunlap
2020-09-02 20:48     ` Zi Yan
2020-09-03  3:15   ` Matthew Wilcox
2020-09-07 12:22   ` Kirill A. Shutemov
2020-09-07 15:11     ` Zi Yan
2020-09-09 13:46       ` Kirill A. Shutemov
2020-09-09 14:15         ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 02/16] mm: thp: 1GB anonymous page implementation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 03/16] mm: proc: add 1GB THP kpageflag Zi Yan
2020-09-09 13:46   ` Kirill A. Shutemov
2020-09-02 18:06 ` [RFC PATCH 04/16] mm: thp: 1GB THP copy on write implementation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 05/16] mm: thp: handling 1GB THP reference bit Zi Yan
2020-09-09 14:09   ` Kirill A. Shutemov
2020-09-09 14:36     ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 06/16] mm: thp: add 1GB THP split_huge_pud_page() function Zi Yan
2020-09-09 14:18   ` Kirill A. Shutemov
2020-09-09 14:19     ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 07/16] mm: stats: make smap stats understand PUD THPs Zi Yan
2020-09-02 18:06 ` Zi Yan [this message]
2020-09-02 18:06 ` [RFC PATCH 09/16] mm: thp: 1GB THP support in try_to_unmap() Zi Yan
2020-09-02 18:06 ` [RFC PATCH 10/16] mm: thp: split 1GB THPs at page reclaim Zi Yan
2020-09-02 18:06 ` [RFC PATCH 11/16] mm: thp: 1GB THP follow_p*d_page() support Zi Yan
2020-09-02 18:06 ` [RFC PATCH 12/16] mm: support 1GB THP pagemap support Zi Yan
2020-09-02 18:06 ` [RFC PATCH 13/16] mm: thp: add a knob to enable/disable 1GB THPs Zi Yan
2020-09-02 18:06 ` [RFC PATCH 14/16] mm: page_alloc: >=MAX_ORDER pages allocation an deallocation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 15/16] hugetlb: cma: move cma reserve function to cma.c Zi Yan
2020-09-02 18:06 ` [RFC PATCH 16/16] mm: thp: use cma reservation for pud thp allocation Zi Yan
2020-09-02 18:40 ` [RFC PATCH 00/16] 1GB THP support on x86_64 Jason Gunthorpe
2020-09-02 18:45   ` Zi Yan
2020-09-02 18:48     ` Jason Gunthorpe
2020-09-02 19:05       ` Zi Yan
2020-09-02 19:57         ` Jason Gunthorpe
2020-09-02 20:29           ` Zi Yan
2020-09-03 16:40             ` Jason Gunthorpe
2020-09-03 16:55               ` Matthew Wilcox
2020-09-03 17:08                 ` Jason Gunthorpe
2020-09-03  7:32 ` Michal Hocko
2020-09-03 16:25   ` Roman Gushchin
2020-09-03 16:50     ` Jason Gunthorpe
2020-09-03 17:01       ` Matthew Wilcox
2020-09-03 17:18         ` Jason Gunthorpe
2020-09-03 20:57     ` Mike Kravetz
2020-09-03 21:06       ` Roman Gushchin
2020-09-04  7:42     ` Michal Hocko
2020-09-04 21:10       ` Roman Gushchin
2020-09-07  7:20         ` Michal Hocko
2020-09-08 15:09           ` Zi Yan
2020-09-08 19:58             ` Roman Gushchin
2020-09-09  4:01               ` John Hubbard
2020-09-09  7:15               ` Michal Hocko
2020-09-03 14:23 ` Kirill A. Shutemov
2020-09-03 16:30   ` Roman Gushchin
2020-09-08 11:57     ` David Hildenbrand
2020-09-08 14:05       ` Zi Yan
2020-09-08 14:22         ` David Hildenbrand
2020-09-08 15:36           ` Zi Yan
2020-09-08 14:27         ` Matthew Wilcox
2020-09-08 15:50           ` Zi Yan
2020-09-09 12:11           ` Jason Gunthorpe
2020-09-09 12:32             ` Matthew Wilcox
2020-09-09 13:14               ` Jason Gunthorpe
2020-09-09 13:27                 ` David Hildenbrand
2020-09-10 10:02                   ` William Kucharski
2020-09-08 14:35         ` Michal Hocko
2020-09-08 14:41           ` Rik van Riel
2020-09-08 15:02             ` David Hildenbrand
2020-09-09  7:04             ` Michal Hocko
2020-09-09 13:19               ` Rik van Riel
2020-09-09 13:43                 ` David Hildenbrand
2020-09-09 13:49                   ` Rik van Riel
2020-09-09 13:54                     ` David Hildenbrand
2020-09-10  7:32                   ` Michal Hocko
2020-09-10  8:27                     ` David Hildenbrand
2020-09-10 14:21                       ` Zi Yan
2020-09-10 14:34                         ` David Hildenbrand
2020-09-10 14:41                           ` Zi Yan
2020-09-10 15:15                             ` David Hildenbrand
2020-09-10 13:32                     ` Rik van Riel
2020-09-10 14:30                       ` Zi Yan
2020-09-09 13:59                 ` Michal Hocko

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=20200902180628.4052244-9-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=dnellans@nvidia.com \
    --cc=guro@fb.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=riel@surriel.com \
    --cc=shakeelb@google.com \
    --cc=willy@infradead.org \
    --cc=yang.shi@linux.alibaba.com \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.