linux-kernel - [RFC PATCH v2 26/47] hugetlb: make move_hugetlb_page

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20221021163703.3218176-27-jthoughton@google.com>
Date:   Fri, 21 Oct 2022 16:36:42 +0000
From:   James Houghton <jthoughton@...gle.com>
To:     Mike Kravetz <mike.kravetz@...cle.com>,
        Muchun Song <songmuchun@...edance.com>,
        Peter Xu <peterx@...hat.com>
Cc:     David Hildenbrand <david@...hat.com>,
        David Rientjes <rientjes@...gle.com>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        Mina Almasry <almasrymina@...gle.com>,
        "Zach O'Keefe" <zokeefe@...gle.com>,
        Manish Mishra <manish.mishra@...anix.com>,
        Naoya Horiguchi <naoya.horiguchi@....com>,
        "Dr . David Alan Gilbert" <dgilbert@...hat.com>,
        "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Baolin Wang <baolin.wang@...ux.alibaba.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Yang Shi <shy828301@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org,
        James Houghton <jthoughton@...gle.com>
Subject: [RFC PATCH v2 26/47] hugetlb: make move_hugetlb_page_tables
 compatible with HGM

This is very similar to the support that was added to
copy_hugetlb_page_range. We simply do a high-granularity walk now, and
most of the rest of the code stays the same.

Signed-off-by: James Houghton <jthoughton@...gle.com>
---
 mm/hugetlb.c | 47 ++++++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 15 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7d692907cbf3..16b0d192445c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5174,16 +5174,16 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	return ret;
 }
 
-static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
-			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
+static void move_hugetlb_pte(struct vm_area_struct *vma, unsigned long old_addr,
+			     unsigned long new_addr, struct hugetlb_pte *src_hpte,
+			     struct hugetlb_pte *dst_hpte)
 {
-	struct hstate *h = hstate_vma(vma);
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *src_ptl, *dst_ptl;
 	pte_t pte;
 
-	dst_ptl = huge_pte_lock(h, mm, dst_pte);
-	src_ptl = huge_pte_lockptr(huge_page_shift(h), mm, src_pte);
+	dst_ptl = hugetlb_pte_lock(mm, dst_hpte);
+	src_ptl = hugetlb_pte_lockptr(mm, src_hpte);
 
 	/*
 	 * We don't have to worry about the ordering of src and dst ptlocks
@@ -5192,8 +5192,8 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
-	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
-	set_huge_pte_at(mm, new_addr, dst_pte, pte);
+	pte = huge_ptep_get_and_clear(mm, old_addr, src_hpte->ptep);
+	set_huge_pte_at(mm, new_addr, dst_hpte->ptep, pte);
 
 	if (src_ptl != dst_ptl)
 		spin_unlock(src_ptl);
@@ -5214,6 +5214,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	pte_t *src_pte, *dst_pte;
 	struct mmu_notifier_range range;
 	bool shared_pmd = false;
+	struct hugetlb_pte src_hpte, dst_hpte;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr,
 				old_end);
@@ -5229,20 +5230,28 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	/* Prevent race with file truncation */
 	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(mapping);
-	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
+	while (old_addr < old_end) {
 		src_pte = huge_pte_offset(mm, old_addr, sz);
 		if (!src_pte) {
-			old_addr |= last_addr_mask;
-			new_addr |= last_addr_mask;
+			old_addr = (old_addr | last_addr_mask) + sz;
+			new_addr = (new_addr | last_addr_mask) + sz;
 			continue;
 		}
-		if (huge_pte_none(huge_ptep_get(src_pte)))
+
+		hugetlb_pte_populate(&src_hpte, src_pte, huge_page_shift(h),
+				     hpage_size_to_level(sz));
+		hugetlb_hgm_walk(mm, vma, &src_hpte, old_addr,
+				PAGE_SIZE, /*stop_at_none=*/true);
+		if (huge_pte_none(huge_ptep_get(src_hpte.ptep))) {
+			old_addr += hugetlb_pte_size(&src_hpte);
+			new_addr += hugetlb_pte_size(&src_hpte);
 			continue;
+		}
 
-		if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) {
+		if (huge_pmd_unshare(mm, vma, old_addr, src_hpte.ptep)) {
 			shared_pmd = true;
-			old_addr |= last_addr_mask;
-			new_addr |= last_addr_mask;
+			old_addr = (old_addr | last_addr_mask) + sz;
+			new_addr = (new_addr | last_addr_mask) + sz;
 			continue;
 		}
 
@@ -5250,7 +5259,15 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 		if (!dst_pte)
 			break;
 
-		move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
+		hugetlb_pte_populate(&dst_hpte, dst_pte, huge_page_shift(h),
+				     hpage_size_to_level(sz));
+		if (hugetlb_hgm_walk(mm, vma, &dst_hpte, new_addr,
+				     hugetlb_pte_size(&src_hpte),
+				     /*stop_at_none=*/false))
+			break;
+		move_hugetlb_pte(vma, old_addr, new_addr, &src_hpte, &dst_hpte);
+		old_addr += hugetlb_pte_size(&src_hpte);
+		new_addr += hugetlb_pte_size(&src_hpte);
 	}
 
 	if (shared_pmd)
-- 
2.38.0.135.g90850a2211-goog