[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20221021163703.3218176-11-jthoughton@google.com>
Date: Fri, 21 Oct 2022 16:36:26 +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 10/47] hugetlb: add hugetlb_pte to track HugeTLB page
table entries
After high-granularity mapping, page table entries for HugeTLB pages can
be of any size/type. (For example, we can have a 1G page mapped with a
mix of PMDs and PTEs.) This struct is to help keep track of a HugeTLB
PTE after we have done a page table walk.
Without this, we'd have to pass around the "size" of the PTE everywhere.
We effectively did this before; it could be fetched from the hstate,
which we pass around pretty much everywhere.
hugetlb_pte_present_leaf is included here as a helper function that will
be used frequently later on.
Signed-off-by: James Houghton <jthoughton@...gle.com>
---
include/linux/hugetlb.h | 88 +++++++++++++++++++++++++++++++++++++++++
mm/hugetlb.c | 29 ++++++++++++++
2 files changed, 117 insertions(+)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index db3ed6095b1c..d30322108b34 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -50,6 +50,75 @@ enum {
__NR_USED_SUBPAGE,
};
+enum hugetlb_level {
+ HUGETLB_LEVEL_PTE = 1,
+ /*
+ * We always include PMD, PUD, and P4D in this enum definition so that,
+ * when logged as an integer, we can easily tell which level it is.
+ */
+ HUGETLB_LEVEL_PMD,
+ HUGETLB_LEVEL_PUD,
+ HUGETLB_LEVEL_P4D,
+ HUGETLB_LEVEL_PGD,
+};
+
+struct hugetlb_pte {
+ pte_t *ptep;
+ unsigned int shift;
+ enum hugetlb_level level;
+ spinlock_t *ptl;
+};
+
+static inline
+void hugetlb_pte_populate(struct hugetlb_pte *hpte, pte_t *ptep,
+ unsigned int shift, enum hugetlb_level level)
+{
+ WARN_ON_ONCE(!ptep);
+ hpte->ptep = ptep;
+ hpte->shift = shift;
+ hpte->level = level;
+ hpte->ptl = NULL;
+}
+
+static inline
+unsigned long hugetlb_pte_size(const struct hugetlb_pte *hpte)
+{
+ WARN_ON_ONCE(!hpte->ptep);
+ return 1UL << hpte->shift;
+}
+
+static inline
+unsigned long hugetlb_pte_mask(const struct hugetlb_pte *hpte)
+{
+ WARN_ON_ONCE(!hpte->ptep);
+ return ~(hugetlb_pte_size(hpte) - 1);
+}
+
+static inline
+unsigned int hugetlb_pte_shift(const struct hugetlb_pte *hpte)
+{
+ WARN_ON_ONCE(!hpte->ptep);
+ return hpte->shift;
+}
+
+static inline
+enum hugetlb_level hugetlb_pte_level(const struct hugetlb_pte *hpte)
+{
+ WARN_ON_ONCE(!hpte->ptep);
+ return hpte->level;
+}
+
+static inline
+void hugetlb_pte_copy(struct hugetlb_pte *dest, const struct hugetlb_pte *src)
+{
+ dest->ptep = src->ptep;
+ dest->shift = src->shift;
+ dest->level = src->level;
+ dest->ptl = src->ptl;
+}
+
+bool hugetlb_pte_present_leaf(const struct hugetlb_pte *hpte, pte_t pte);
+
struct hugepage_subpool {
spinlock_t lock;
long count;
@@ -1210,6 +1279,25 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h,
return ptl;
}
+static inline
+spinlock_t *hugetlb_pte_lockptr(struct mm_struct *mm, struct hugetlb_pte *hpte)
+{
+
+ BUG_ON(!hpte->ptep);
+ if (hpte->ptl)
+ return hpte->ptl;
+ return huge_pte_lockptr(hugetlb_pte_shift(hpte), mm, hpte->ptep);
+}
+
+static inline
+spinlock_t *hugetlb_pte_lock(struct mm_struct *mm, struct hugetlb_pte *hpte)
+{
+ spinlock_t *ptl = hugetlb_pte_lockptr(mm, hpte);
+
+ spin_lock(ptl);
+ return ptl;
+}
+
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
extern void __init hugetlb_cma_reserve(int order);
#else
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ef7662bd0068..a0e46d35dabc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1127,6 +1127,35 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
return false;
}
+bool hugetlb_pte_present_leaf(const struct hugetlb_pte *hpte, pte_t pte)
+{
+ pgd_t pgd;
+ p4d_t p4d;
+ pud_t pud;
+ pmd_t pmd;
+
+ WARN_ON_ONCE(!hpte->ptep);
+ switch (hugetlb_pte_level(hpte)) {
+ case HUGETLB_LEVEL_PGD:
+ pgd = __pgd(pte_val(pte));
+ return pgd_present(pgd) && pgd_leaf(pgd);
+ case HUGETLB_LEVEL_P4D:
+ p4d = __p4d(pte_val(pte));
+ return p4d_present(p4d) && p4d_leaf(p4d);
+ case HUGETLB_LEVEL_PUD:
+ pud = __pud(pte_val(pte));
+ return pud_present(pud) && pud_leaf(pud);
+ case HUGETLB_LEVEL_PMD:
+ pmd = __pmd(pte_val(pte));
+ return pmd_present(pmd) && pmd_leaf(pmd);
+ case HUGETLB_LEVEL_PTE:
+ return pte_present(pte);
+ default:
+ WARN_ON_ONCE(1);
+ return false;
+ }
+}
+
static void enqueue_huge_page(struct hstate *h, struct page *page)
{
int nid = page_to_nid(page);
--
2.38.0.135.g90850a2211-goog
Powered by blists - more mailing lists