| 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
| ||
|
Message-ID: <20260127192936.1250096-9-rppt@kernel.org>
Date: Tue, 27 Jan 2026 21:29:27 +0200
From: Mike Rapoport <rppt@...nel.org>
To: linux-mm@...ck.org
Cc: Andrea Arcangeli <aarcange@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Axel Rasmussen <axelrasmussen@...gle.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
David Hildenbrand <david@...hat.com>,
Hugh Dickins <hughd@...gle.com>,
James Houghton <jthoughton@...gle.com>,
"Liam R. Howlett" <Liam.Howlett@...cle.com>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Michal Hocko <mhocko@...e.com>,
Mike Rapoport <rppt@...nel.org>,
Muchun Song <muchun.song@...ux.dev>,
Nikita Kalyazin <kalyazin@...zon.com>,
Oscar Salvador <osalvador@...e.de>,
Paolo Bonzini <pbonzini@...hat.com>,
Peter Xu <peterx@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Shuah Khan <shuah@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>,
Vlastimil Babka <vbabka@...e.cz>,
linux-kernel@...r.kernel.org,
kvm@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: [PATCH RFC 08/17] userfaultfd, shmem: use a VMA callback to handle UFFDIO_CONTINUE
From: "Mike Rapoport (Microsoft)" <rppt@...nel.org>
When userspace resolves a page fault in a shmem VMA with UFFDIO_CONTINUE
it needs to get a folio that already exists in the pagecache backing
that VMA.
Instead of using shmem_get_folio() for that, add a get_folio_noalloc()
method to 'struct vm_uffd_ops' that will return a folio if it exists in
the VMA's pagecache at given pgoff.
Implement get_folio_noalloc() method for shmem and slightly refactor
userfaultfd's mfill_get_vma() and mfill_atomic_pte_continue() to support
this new API.
Signed-off-by: Mike Rapoport (Microsoft) <rppt@...nel.org>
---
include/linux/userfaultfd_k.h | 7 +++++++
mm/shmem.c | 15 ++++++++++++++-
mm/userfaultfd.c | 32 ++++++++++++++++----------------
3 files changed, 37 insertions(+), 17 deletions(-)
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 56e85ab166c7..66dfc3c164e6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -84,6 +84,13 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
struct vm_uffd_ops {
/* Checks if a VMA can support userfaultfd */
bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags);
+ /*
+ * Called to resolve UFFDIO_CONTINUE request.
+ * Should return the folio found at pgoff in the VMA's pagecache if it
+ * exists or ERR_PTR otherwise.
+ * The returned folio is locked and with reference held.
+ */
+ struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff);
};
/* A combined operation mode + behavior flags. */
diff --git a/mm/shmem.c b/mm/shmem.c
index 9b82cda271c4..87cd8d2fdb97 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -5291,6 +5291,18 @@ static const struct super_operations shmem_ops = {
};
#ifdef CONFIG_USERFAULTFD
+static struct folio *shmem_get_folio_noalloc(struct inode *inode, pgoff_t pgoff)
+{
+ struct folio *folio;
+ int err;
+
+ err = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+ if (err)
+ return ERR_PTR(err);
+
+ return folio;
+}
+
static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
{
/*
@@ -5303,7 +5315,8 @@ static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
}
static const struct vm_uffd_ops shmem_uffd_ops = {
- .can_userfault = shmem_can_userfault,
+ .can_userfault = shmem_can_userfault,
+ .get_folio_noalloc = shmem_get_folio_noalloc,
};
#endif
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d035f5e17f07..f0e6336015f1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -188,6 +188,7 @@ static int mfill_get_vma(struct mfill_state *state)
struct userfaultfd_ctx *ctx = state->ctx;
uffd_flags_t flags = state->flags;
struct vm_area_struct *dst_vma;
+ const struct vm_uffd_ops *ops;
int err;
/*
@@ -228,10 +229,12 @@ static int mfill_get_vma(struct mfill_state *state)
if (is_vm_hugetlb_page(dst_vma))
goto out;
- if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
+ ops = vma_uffd_ops(dst_vma);
+ if (!ops)
goto out_unlock;
- if (!vma_is_shmem(dst_vma) &&
- uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
+
+ if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) &&
+ !ops->get_folio_noalloc)
goto out_unlock;
out:
@@ -568,6 +571,7 @@ static int mfill_atomic_pte_zeropage(struct mfill_state *state)
static int mfill_atomic_pte_continue(struct mfill_state *state)
{
struct vm_area_struct *dst_vma = state->vma;
+ const struct vm_uffd_ops *ops = vma_uffd_ops(dst_vma);
unsigned long dst_addr = state->dst_addr;
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
struct inode *inode = file_inode(dst_vma->vm_file);
@@ -577,16 +581,13 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
struct page *page;
int ret;
- ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+ if (!ops)
+ return -EOPNOTSUPP;
+
+ folio = ops->get_folio_noalloc(inode, pgoff);
/* Our caller expects us to return -EFAULT if we failed to find folio */
- if (ret == -ENOENT)
- ret = -EFAULT;
- if (ret)
- goto out;
- if (!folio) {
- ret = -EFAULT;
- goto out;
- }
+ if (IS_ERR_OR_NULL(folio))
+ return -EFAULT;
page = folio_file_page(folio, pgoff);
if (PageHWPoison(page)) {
@@ -600,13 +601,12 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
goto out_release;
folio_unlock(folio);
- ret = 0;
-out:
- return ret;
+ return 0;
+
out_release:
folio_unlock(folio);
folio_put(folio);
- goto out;
+ return ret;
}
/* Handles UFFDIO_POISON for all non-hugetlb VMAs. */
--
2.51.0
Powered by blists - more mailing lists