From: Mike Kravetz <mike.kravetz@oracle.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-s390@vger.kernel.org
Cc: shu wang <malate_wangshu@hotmail.com>,
Axel Rasmussen <axelrasmussen@google.com>,
Peter Xu <peterx@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Heiko Carstens <hca@linux.ibm.com>,
Alexey Dobriyan <adobriyan@gmail.com>,
Matthew Wilcox <willy@infradead.org>,
Michel Lespinasse <walken@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
Mike Kravetz <mike.kravetz@oracle.com>
Subject: [RFC PATCH 5/5] mm proc/task_mmu.c: add hugetlb specific routine for clear_refs
Date: Wed, 10 Feb 2021 16:03:22 -0800 [thread overview]
Message-ID: <20210211000322.159437-6-mike.kravetz@oracle.com> (raw)
In-Reply-To: <20210211000322.159437-1-mike.kravetz@oracle.com>
There was is no hugetlb specific routine for clearing soft dirty and
other referrences. The 'default' routines would only clear the
VM_SOFTDIRTY flag in the vma.
Add new routine specifically for hugetlb vmas.
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
fs/proc/task_mmu.c | 110 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 110 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 829b35016aaa..f06cf9b131a8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1116,6 +1116,115 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
}
#endif
+#ifdef CONFIG_HUGETLB_PAGE
+static inline bool huge_pte_is_pinned(struct vm_area_struct *vma,
+ unsigned long addr, pte_t pte)
+{
+ struct page *page;
+
+ if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
+ return false;
+ page = pte_page(pte);
+ if (!page)
+ return false;
+ return page_maybe_dma_pinned(page);
+}
+
+static int clear_refs_hugetlb_range(pte_t *ptep, unsigned long hmask,
+ unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct clear_refs_private *cp = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ struct hstate *h = hstate_vma(walk->vma);
+ unsigned long adj_start = addr, adj_end = end;
+ spinlock_t *ptl;
+ pte_t old_pte, pte;
+
+ /*
+ * clear_refs should only operate on complete vmas. Therefore,
+ * values passed here should be huge page aligned and huge page
+ * size in length. Quick validation before taking any action in
+ * case upstream code is changed.
+ */
+ if ((addr & hmask) != addr || end - addr != huge_page_size(h)) {
+ WARN_ONCE(1, "%s passed unaligned address\n", __func__);
+ return 1;
+ }
+
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep);
+
+ /* Soft dirty and pmd sharing do not mix */
+
+ pte = huge_ptep_get(ptep);
+ if (!pte_present(pte))
+ goto out;
+ if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+ goto out;
+
+ if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+ if (huge_pte_is_pinned(vma, addr, pte))
+ goto out;
+
+ /*
+ * soft dirty and pmd sharing do not work together as
+ * per-process is tracked in ptes, and pmd sharing allows
+ * processed to share ptes. We unshare any pmds here.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &adj_start, &adj_end);
+ flush_cache_range(vma, adj_start, adj_end);
+ /*
+ * Only atttempt unshare if sharing possible. If we unshare,
+ * then pte's for a PUD sized area are effectively removed for
+ * this process. That clears soft dirty.
+ */
+ if (adj_start != addr || adj_end != end) {
+ struct mmu_notifier_range range;
+ int unshared;
+
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR,
+ 0, vma, vma->vm_mm, adj_start, adj_end);
+ mmu_notifier_invalidate_range_start(&range);
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+ unshared = huge_pmd_unshare(vma->vm_mm, vma,
+ &addr, ptep);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+ mmu_notifier_invalidate_range_end(&range);
+ if (unshared)
+ goto unshare_done;
+ }
+
+ if (is_hugetlb_entry_migration(pte)) {
+ pte = huge_pte_swp_clear_soft_dirty(pte);
+ set_huge_pte_at(walk->mm, addr, ptep, pte);
+ } else {
+ old_pte = huge_ptep_modify_prot_start(vma, addr, ptep);
+ pte = pte_mkhuge(huge_pte_wrprotect(pte));
+ pte = arch_make_huge_pte(pte, vma, NULL, 0);
+ pte = huge_pte_clear_soft_dirty(pte);
+ pte = huge_pte_mkyoung(pte);
+ huge_ptep_modify_prot_commit(vma, addr, ptep,
+ old_pte, pte);
+ }
+
+unshare_done:
+ flush_hugetlb_tlb_range(vma, addr, end);
+ }
+
+ /* reference bits in hugetlb pages are not reset/used */
+out:
+ spin_unlock(ptl);
+ return 0;
+}
+#else /* CONFIG_HUGETLB_PAGE */
+static int clear_refs_hugetlb_range(pte_t *ptep, unsigned long hmask,
+ unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ return 1;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
@@ -1198,6 +1307,7 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end,
}
static const struct mm_walk_ops clear_refs_walk_ops = {
+ .hugetlb_entry = clear_refs_hugetlb_range,
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
};
--
2.29.2
next prev parent reply other threads:[~2021-02-11 0:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-11 0:03 [RFC PATCH 0/5] Add hugetlb soft dirty support Mike Kravetz
2021-02-11 0:03 ` [RFC PATCH 1/5] hugetlb: add hugetlb helpers for " Mike Kravetz
2021-02-17 16:24 ` Peter Xu
2021-02-18 22:58 ` Mike Kravetz
2021-02-24 16:46 ` Gerald Schaefer
2021-02-24 16:55 ` Gerald Schaefer
2021-02-11 0:03 ` [RFC PATCH 2/5] hugetlb: enhance hugetlb fault processing to support soft dirty Mike Kravetz
2021-02-17 19:32 ` Peter Xu
2021-02-18 23:26 ` Mike Kravetz
2021-02-11 0:03 ` [RFC PATCH 3/5] mm proc/task_mmu.c: add soft dirty pte checks for hugetlb Mike Kravetz
2021-02-17 19:35 ` Peter Xu
2021-02-18 23:59 ` Mike Kravetz
2021-02-11 0:03 ` [RFC PATCH 4/5] hugetlb: don't permit pmd sharing if soft dirty in use Mike Kravetz
2021-02-17 19:44 ` Peter Xu
2021-02-11 0:03 ` Mike Kravetz [this message]
2021-02-17 20:25 ` [RFC PATCH 5/5] mm proc/task_mmu.c: add hugetlb specific routine for clear_refs Peter Xu
2021-02-19 0:14 ` Mike Kravetz
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=20210211000322.159437-6-mike.kravetz@oracle.com \
--to=mike.kravetz@oracle.com \
--cc=aarcange@redhat.com \
--cc=adobriyan@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=hca@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=malate_wangshu@hotmail.com \
--cc=peterx@redhat.com \
--cc=walken@google.com \
--cc=willy@infradead.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).