linux-kernel - [RFC PATCH v2 11/47] hugetlb: add hugetlb_pmd_alloc and hugetlb_pte

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: <20221021163703.3218176-12-jthoughton@google.com>
Date:   Fri, 21 Oct 2022 16:36:27 +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 11/47] hugetlb: add hugetlb_pmd_alloc and hugetlb_pte_alloc

These functions are used to allocate new PTEs below the hstate PTE. This
will be used by hugetlb_walk_step, which implements stepping forwards in
a HugeTLB high-granularity page table walk.

The reasons that we don't use the standard pmd_alloc/pte_alloc*
functions are:
 1) This prevents us from accidentally overwriting swap entries or
    attempting to use swap entries as present non-leaf PTEs (see
    pmd_alloc(); we assume that !pte_none means pte_present and
    non-leaf).
 2) Locking hugetlb PTEs can different than regular PTEs. (Although, as
    implemented right now, locking is the same.)
 3) We can maintain compatibility with CONFIG_HIGHPTE. That is, HugeTLB
    HGM won't use HIGHPTE, but the kernel can still be built with it,
    and other mm code will use it.

When GENERAL_HUGETLB supports P4D-based hugepages, we will need to
implement hugetlb_pud_alloc to implement hugetlb_walk_step.

Signed-off-by: James Houghton <jthoughton@...gle.com>
---
 include/linux/hugetlb.h |  5 +++
 mm/hugetlb.c            | 94 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d30322108b34..003255b0e40f 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -119,6 +119,11 @@ void hugetlb_pte_copy(struct hugetlb_pte *dest, const struct hugetlb_pte *src)
 
 bool hugetlb_pte_present_leaf(const struct hugetlb_pte *hpte, pte_t pte);
 
+pmd_t *hugetlb_pmd_alloc(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		unsigned long addr);
+pte_t *hugetlb_pte_alloc(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		unsigned long addr);
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a0e46d35dabc..e3733388adee 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -341,6 +341,100 @@ static bool has_same_uncharge_info(struct file_region *rg,
 #endif
 }
 
+pmd_t *hugetlb_pmd_alloc(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		unsigned long addr)
+{
+	spinlock_t *ptl = hugetlb_pte_lockptr(mm, hpte);
+	pmd_t *new;
+	pud_t *pudp;
+	pud_t pud;
+
+	if (hpte->level != HUGETLB_LEVEL_PUD)
+		return ERR_PTR(-EINVAL);
+
+	pudp = (pud_t *)hpte->ptep;
+retry:
+	pud = *pudp;
+	if (likely(pud_present(pud)))
+		return unlikely(pud_leaf(pud))
+			? ERR_PTR(-EEXIST)
+			: pmd_offset(pudp, addr);
+	else if (!huge_pte_none(huge_ptep_get(hpte->ptep)))
+		/*
+		 * Not present and not none means that a swap entry lives here,
+		 * and we can't get rid of it.
+		 */
+		return ERR_PTR(-EEXIST);
+
+	new = pmd_alloc_one(mm, addr);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock(ptl);
+	if (!pud_same(pud, *pudp)) {
+		spin_unlock(ptl);
+		pmd_free(mm, new);
+		goto retry;
+	}
+
+	mm_inc_nr_pmds(mm);
+	smp_wmb(); /* See comment in pmd_install() */
+	pud_populate(mm, pudp, new);
+	spin_unlock(ptl);
+	return pmd_offset(pudp, addr);
+}
+
+pte_t *hugetlb_pte_alloc(struct mm_struct *mm, struct hugetlb_pte *hpte,
+		unsigned long addr)
+{
+	spinlock_t *ptl = hugetlb_pte_lockptr(mm, hpte);
+	pgtable_t new;
+	pmd_t *pmdp;
+	pmd_t pmd;
+
+	if (hpte->level != HUGETLB_LEVEL_PMD)
+		return ERR_PTR(-EINVAL);
+
+	pmdp = (pmd_t *)hpte->ptep;
+retry:
+	pmd = *pmdp;
+	if (likely(pmd_present(pmd)))
+		return unlikely(pmd_leaf(pmd))
+			? ERR_PTR(-EEXIST)
+			: pte_offset_kernel(pmdp, addr);
+	else if (!huge_pte_none(huge_ptep_get(hpte->ptep)))
+		/*
+		 * Not present and not none means that a swap entry lives here,
+		 * and we can't get rid of it.
+		 */
+		return ERR_PTR(-EEXIST);
+
+	/*
+	 * With CONFIG_HIGHPTE, calling `pte_alloc_one` directly may result
+	 * in page tables being allocated in high memory, needing a kmap to
+	 * access. Instead, we call __pte_alloc_one directly with
+	 * GFP_PGTABLE_USER to prevent these PTEs being allocated in high
+	 * memory.
+	 */
+	new = __pte_alloc_one(mm, GFP_PGTABLE_USER);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock(ptl);
+	if (!pmd_same(pmd, *pmdp)) {
+		spin_unlock(ptl);
+		pgtable_pte_page_dtor(new);
+		__free_page(new);
+		goto retry;
+	}
+
+	mm_inc_nr_ptes(mm);
+	smp_wmb(); /* See comment in pmd_install() */
+	pmd_populate(mm, pmdp, new);
+	spin_unlock(ptl);
+	return pte_offset_kernel(pmdp, addr);
+}
+
 static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 {
 	struct file_region *nrg, *prg;
-- 
2.38.0.135.g90850a2211-goog