| 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: <20250620190342.1780170-2-peterx@redhat.com>
Date: Fri, 20 Jun 2025 15:03:39 -0400
From: Peter Xu <peterx@...hat.com>
To: linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Cc: Nikita Kalyazin <kalyazin@...zon.com>,
peterx@...hat.com,
Hugh Dickins <hughd@...gle.com>,
Oscar Salvador <osalvador@...e.de>,
Michal Hocko <mhocko@...e.com>,
David Hildenbrand <david@...hat.com>,
Muchun Song <muchun.song@...ux.dev>,
Andrea Arcangeli <aarcange@...hat.com>,
Ujwal Kundur <ujwal.kundur@...il.com>,
Suren Baghdasaryan <surenb@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>,
"Liam R . Howlett" <Liam.Howlett@...cle.com>,
James Houghton <jthoughton@...gle.com>,
Mike Rapoport <rppt@...nel.org>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Axel Rasmussen <axelrasmussen@...gle.com>
Subject: [PATCH 1/4] mm: Introduce vm_uffd_ops API
Introduce a generic userfaultfd API for vm_operations_struct, so that one
vma, especially when as a module, can support userfaults without modifying
the core files. More importantly, when the module can be compiled out of
the kernel.
So, instead of having core mm referencing modules that may not ever exist,
we need to have modules opt-in on core mm hooks instead.
After this API applied, if a module wants to support userfaultfd, the
module should only need to touch its own file and properly define
vm_uffd_ops, instead of changing anything in core mm.
Note that such API will not work for anonymous. Core mm will process
anonymous memory separately for userfault operations like before.
This patch only introduces the API alone so that we can start to move
existing users over but without breaking them.
Currently the uffd_copy() API is almost designed to be the simplistic with
minimum mm changes to move over to the API.
Signed-off-by: Peter Xu <peterx@...hat.com>
---
include/linux/mm.h | 71 +++++++++++++++++++++++++++++++++++
include/linux/userfaultfd_k.h | 12 ------
2 files changed, 71 insertions(+), 12 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 98a606908307..8dfd83f01d3d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -576,6 +576,70 @@ struct vm_fault {
*/
};
+#ifdef CONFIG_USERFAULTFD
+/* A combined operation mode + behavior flags. */
+typedef unsigned int __bitwise uffd_flags_t;
+
+enum mfill_atomic_mode {
+ MFILL_ATOMIC_COPY,
+ MFILL_ATOMIC_ZEROPAGE,
+ MFILL_ATOMIC_CONTINUE,
+ MFILL_ATOMIC_POISON,
+ NR_MFILL_ATOMIC_MODES,
+};
+
+/* VMA userfaultfd operations */
+typedef struct {
+ /**
+ * @uffd_features: features supported in bitmask.
+ *
+ * When the ops is defined, the driver must set non-zero features
+ * to be a subset (or all) of: VM_UFFD_MISSING|WP|MINOR.
+ */
+ unsigned long uffd_features;
+ /**
+ * @uffd_ioctls: ioctls supported in bitmask.
+ *
+ * Userfaultfd ioctls supported by the module. Below will always
+ * be supported by default whenever a module provides vm_uffd_ops:
+ *
+ * _UFFDIO_API, _UFFDIO_REGISTER, _UFFDIO_UNREGISTER, _UFFDIO_WAKE
+ *
+ * The module needs to provide all the rest optionally supported
+ * ioctls. For example, when VM_UFFD_MISSING was supported,
+ * _UFFDIO_COPY must be supported as ioctl, while _UFFDIO_ZEROPAGE
+ * is optional.
+ */
+ unsigned long uffd_ioctls;
+ /**
+ * uffd_get_folio: Handler to resolve UFFDIO_CONTINUE request.
+ *
+ * @inode: the inode for folio lookup
+ * @pgoff: the pgoff of the folio
+ * @folio: returned folio pointer
+ *
+ * Return: zero if succeeded, negative for errors.
+ */
+ int (*uffd_get_folio)(struct inode *inode, pgoff_t pgoff,
+ struct folio **folio);
+ /**
+ * uffd_copy: Handler to resolve UFFDIO_COPY|ZEROPAGE request.
+ *
+ * @dst_pmd: target pmd to resolve page fault
+ * @dst_vma: target vma
+ * @dst_addr: target virtual address
+ * @src_addr: source address to copy from
+ * @flags: userfaultfd request flags
+ * @foliop: previously allocated folio
+ *
+ * Return: zero if succeeded, negative for errors.
+ */
+ int (*uffd_copy)(pmd_t *dst_pmd, struct vm_area_struct *dst_vma,
+ unsigned long dst_addr, unsigned long src_addr,
+ uffd_flags_t flags, struct folio **foliop);
+} vm_uffd_ops;
+#endif
+
/*
* These are the virtual MM functions - opening of an area, closing and
* unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -653,6 +717,13 @@ struct vm_operations_struct {
*/
struct page *(*find_special_page)(struct vm_area_struct *vma,
unsigned long addr);
+#ifdef CONFIG_USERFAULTFD
+ /*
+ * Userfaultfd related ops. Modules need to define this to support
+ * userfaultfd.
+ */
+ const vm_uffd_ops *userfaultfd_ops;
+#endif
};
#ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index ccad58602846..e79c724b3b95 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -80,18 +80,6 @@ struct userfaultfd_ctx {
extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
-/* A combined operation mode + behavior flags. */
-typedef unsigned int __bitwise uffd_flags_t;
-
-/* Mutually exclusive modes of operation. */
-enum mfill_atomic_mode {
- MFILL_ATOMIC_COPY,
- MFILL_ATOMIC_ZEROPAGE,
- MFILL_ATOMIC_CONTINUE,
- MFILL_ATOMIC_POISON,
- NR_MFILL_ATOMIC_MODES,
-};
-
#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1)
#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr))
#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr))
--
2.49.0
Powered by blists - more mailing lists