From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To: Suren Baghdasaryan <surenb@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
Punit Agrawal <punit.agrawal@bytedance.com>
Subject: [PATCH 2/6] mm: Move FAULT_FLAG_VMA_LOCK check from handle_mm_fault()
Date: Tue, 4 Apr 2023 14:58:46 +0100 [thread overview]
Message-ID: <20230404135850.3673404-3-willy@infradead.org> (raw)
In-Reply-To: <20230404135850.3673404-1-willy@infradead.org>
Handle a little more of the page fault path outside the mmap sem.
The hugetlb path doesn't need to check whether the VMA is anonymous;
the VM_HUGETLB flag is only set on hugetlbfs VMAs. There should be no
performance change from the previous commit; this is simply a step to
ease bisection of any problems.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
mm/hugetlb.c | 4 ++++
mm/memory.c | 14 +++++++-------
2 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index efc443a906fa..39f168e3518f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6052,6 +6052,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
int need_wait_lock = 0;
unsigned long haddr = address & huge_page_mask(h);
+ /* TODO: Handle faults under the VMA lock */
+ if (flags & FAULT_FLAG_VMA_LOCK)
+ return VM_FAULT_RETRY;
+
/*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
diff --git a/mm/memory.c b/mm/memory.c
index f726f85f0081..fc1f0ef9a7a5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4992,10 +4992,10 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
}
/*
- * By the time we get here, we already hold the mm semaphore
- *
- * The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __folio_lock_or_retry().
+ * On entry, we hold either the VMA lock or the mmap_lock
+ * (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in
+ * the result, the mmap_lock is not held on exit. See filemap_fault()
+ * and __folio_lock_or_retry().
*/
static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
@@ -5014,6 +5014,9 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
p4d_t *p4d;
vm_fault_t ret;
+ if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma))
+ return VM_FAULT_RETRY;
+
pgd = pgd_offset(mm, address);
p4d = p4d_alloc(mm, pgd, address);
if (!p4d)
@@ -5223,9 +5226,6 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
flags & FAULT_FLAG_REMOTE))
return VM_FAULT_SIGSEGV;
- if ((flags & FAULT_FLAG_VMA_LOCK) && !vma_is_anonymous(vma))
- return VM_FAULT_RETRY;
-
/*
* Enable the memcg OOM handling for faults triggered in user
* space. Kernel faults are handled more gracefully.
--
2.39.2
next prev parent reply other threads:[~2023-04-04 13:59 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-04 13:58 [PATCH 0/6] Avoid the mmap lock for fault-around Matthew Wilcox (Oracle)
2023-04-04 13:58 ` [PATCH 1/6] mm: Allow per-VMA locks on file-backed VMAs Matthew Wilcox (Oracle)
2023-04-07 17:54 ` Suren Baghdasaryan
2023-04-07 20:12 ` Matthew Wilcox
2023-04-07 20:26 ` Suren Baghdasaryan
2023-04-07 21:36 ` Matthew Wilcox
2023-04-07 22:40 ` Suren Baghdasaryan
2023-04-07 22:49 ` Suren Baghdasaryan
2023-04-14 18:02 ` Suren Baghdasaryan
2023-04-04 13:58 ` Matthew Wilcox (Oracle) [this message]
2023-04-04 13:58 ` [PATCH 3/6] mm: Move FAULT_FLAG_VMA_LOCK check into handle_pte_fault() Matthew Wilcox (Oracle)
2023-04-04 13:58 ` [PATCH 4/6] mm: Move FAULT_FLAG_VMA_LOCK check down in handle_pte_fault() Matthew Wilcox (Oracle)
2023-04-04 13:58 ` [PATCH 5/6] mm: Move the FAULT_FLAG_VMA_LOCK check down from do_pte_missing() Matthew Wilcox (Oracle)
2023-04-04 13:58 ` [PATCH 6/6] mm: Run the fault-around code under the VMA lock Matthew Wilcox (Oracle)
2023-04-04 15:23 ` Matthew Wilcox
2023-04-07 18:20 ` Suren Baghdasaryan
2023-04-10 4:53 ` Yin, Fengwei
2023-04-10 14:11 ` Matthew Wilcox
2023-04-12 7:35 ` Yin, Fengwei
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=20230404135850.3673404-3-willy@infradead.org \
--to=willy@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=punit.agrawal@bytedance.com \
--cc=surenb@google.com \
/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).