Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 24 Jun 2022 17:36:41 +0000
In-Reply-To: <20220624173656.2033256-1-jthoughton@google.com>
Message-Id: <20220624173656.2033256-12-jthoughton@google.com>
Mime-Version: 1.0
References: <20220624173656.2033256-1-jthoughton@google.com>
Subject: [RFC PATCH 11/26] hugetlb: add hugetlb_walk_to to do PT walks
From:   James Houghton <jthoughton@google.com>
To:     Mike Kravetz <mike.kravetz@oracle.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Peter Xu <peterx@redhat.com>
Cc:     David Hildenbrand <david@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Mina Almasry <almasrymina@google.com>,
        Jue Wang <juew@google.com>,
        Manish Mishra <manish.mishra@nutanix.com>,
        "Dr . David Alan Gilbert" <dgilbert@redhat.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        James Houghton <jthoughton@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

This adds it for architectures that use GENERAL_HUGETLB, including x86.

Signed-off-by: James Houghton <jthoughton@google.com>
---
 include/linux/hugetlb.h |  2 ++
 mm/hugetlb.c            | 45 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index e7a6b944d0cc..605aa19d8572 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -258,6 +258,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
+int hugetlb_walk_to(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		    unsigned long addr, unsigned long sz, bool stop_at_none);
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long *addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 557b0afdb503..3ec2a921ee6f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6981,6 +6981,51 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return (pte_t *)pmd;
 }
 
+int hugetlb_walk_to(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		    unsigned long addr, unsigned long sz, bool stop_at_none)
+{
+	pte_t *ptep;
+
+	if (!hpte->ptep) {
+		pgd_t *pgd = pgd_offset(mm, addr);
+
+		if (!pgd)
+			return -ENOMEM;
+		ptep = (pte_t *)p4d_alloc(mm, pgd, addr);
+		if (!ptep)
+			return -ENOMEM;
+		hugetlb_pte_populate(hpte, ptep, P4D_SHIFT);
+	}
+
+	while (hugetlb_pte_size(hpte) > sz &&
+			!hugetlb_pte_present_leaf(hpte) &&
+			!(stop_at_none && hugetlb_pte_none(hpte))) {
+		if (hpte->shift == PMD_SHIFT) {
+			ptep = pte_alloc_map(mm, (pmd_t *)hpte->ptep, addr);
+			if (!ptep)
+				return -ENOMEM;
+			hpte->shift = PAGE_SHIFT;
+			hpte->ptep = ptep;
+		} else if (hpte->shift == PUD_SHIFT) {
+			ptep = (pte_t *)pmd_alloc(mm, (pud_t *)hpte->ptep,
+						  addr);
+			if (!ptep)
+				return -ENOMEM;
+			hpte->shift = PMD_SHIFT;
+			hpte->ptep = ptep;
+		} else if (hpte->shift == P4D_SHIFT) {
+			ptep = (pte_t *)pud_alloc(mm, (p4d_t *)hpte->ptep,
+						  addr);
+			if (!ptep)
+				return -ENOMEM;
+			hpte->shift = PUD_SHIFT;
+			hpte->ptep = ptep;
+		} else
+			BUG();
+	}
+	return 0;
+}
+
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
 #ifdef CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING
-- 
2.37.0.rc0.161.g10f37bed90-goog