| 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: <346e2d1e768a2e5bf344c772cfbb0cd1d6f2fd15.1757329751.git.lorenzo.stoakes@oracle.com>
Date: Mon, 8 Sep 2025 12:10:41 +0100
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Jonathan Corbet <corbet@....net>, Matthew Wilcox <willy@...radead.org>,
Guo Ren <guoren@...nel.org>,
Thomas Bogendoerfer <tsbogend@...ha.franken.de>,
Heiko Carstens <hca@...ux.ibm.com>, Vasily Gorbik <gor@...ux.ibm.com>,
Alexander Gordeev <agordeev@...ux.ibm.com>,
Christian Borntraeger <borntraeger@...ux.ibm.com>,
Sven Schnelle <svens@...ux.ibm.com>,
"David S . Miller" <davem@...emloft.net>,
Andreas Larsson <andreas@...sler.com>, Arnd Bergmann <arnd@...db.de>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Dan Williams <dan.j.williams@...el.com>,
Vishal Verma <vishal.l.verma@...el.com>,
Dave Jiang <dave.jiang@...el.com>, Nicolas Pitre <nico@...xnic.net>,
Muchun Song <muchun.song@...ux.dev>,
Oscar Salvador <osalvador@...e.de>,
David Hildenbrand <david@...hat.com>,
Konstantin Komarov <almaz.alexandrovich@...agon-software.com>,
Baoquan He <bhe@...hat.com>, Vivek Goyal <vgoyal@...hat.com>,
Dave Young <dyoung@...hat.com>, Tony Luck <tony.luck@...el.com>,
Reinette Chatre <reinette.chatre@...el.com>,
Dave Martin <Dave.Martin@....com>, James Morse <james.morse@....com>,
Alexander Viro <viro@...iv.linux.org.uk>,
Christian Brauner <brauner@...nel.org>, Jan Kara <jack@...e.cz>,
"Liam R . Howlett" <Liam.Howlett@...cle.com>,
Vlastimil Babka <vbabka@...e.cz>, Mike Rapoport <rppt@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>, Michal Hocko <mhocko@...e.com>,
Hugh Dickins <hughd@...gle.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
Uladzislau Rezki <urezki@...il.com>,
Dmitry Vyukov <dvyukov@...gle.com>,
Andrey Konovalov <andreyknvl@...il.com>, Jann Horn <jannh@...gle.com>,
Pedro Falcato <pfalcato@...e.de>, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
linux-csky@...r.kernel.org, linux-mips@...r.kernel.org,
linux-s390@...r.kernel.org, sparclinux@...r.kernel.org,
nvdimm@...ts.linux.dev, linux-cxl@...r.kernel.org, linux-mm@...ck.org,
ntfs3@...ts.linux.dev, kexec@...ts.infradead.org,
kasan-dev@...glegroups.com, Jason Gunthorpe <jgg@...dia.com>
Subject: [PATCH 10/16] mm/hugetlb: update hugetlbfs to use mmap_prepare, mmap_complete
We can now update hugetlb to make sure of the new .mmap_prepare() hook, by
deferring the reservation of pages until the VMA is fully established and
handle this in the f_op->mmap_complete() hook.
We hold the VMA write lock throughout so we can't race with faults. rmap
can discover the VMA, but this should not cause a problem.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
fs/hugetlbfs/inode.c | 86 ++++++++++++++++++++++++--------------------
1 file changed, 47 insertions(+), 39 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 3cfdf4091001..46d1ddc654c2 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -96,39 +96,14 @@ static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
#define PGOFF_LOFFT_MAX \
(((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1)))
-static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int hugetlb_file_mmap_complete(struct file *file, struct vm_area_struct *vma,
+ const void *context)
{
struct inode *inode = file_inode(file);
- loff_t len, vma_len;
- int ret;
struct hstate *h = hstate_file(file);
- vm_flags_t vm_flags;
-
- /*
- * vma address alignment (but not the pgoff alignment) has
- * already been checked by prepare_hugepage_range. If you add
- * any error returns here, do so after setting VM_HUGETLB, so
- * is_vm_hugetlb_page tests below unmap_region go the right
- * way when do_mmap unwinds (may be important on powerpc
- * and ia64).
- */
- vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND);
- vma->vm_ops = &hugetlb_vm_ops;
-
- /*
- * page based offset in vm_pgoff could be sufficiently large to
- * overflow a loff_t when converted to byte offset. This can
- * only happen on architectures where sizeof(loff_t) ==
- * sizeof(unsigned long). So, only check in those instances.
- */
- if (sizeof(unsigned long) == sizeof(loff_t)) {
- if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
- return -EINVAL;
- }
-
- /* must be huge page aligned */
- if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
- return -EINVAL;
+ vm_flags_t vm_flags = vma->vm_flags;
+ loff_t len, vma_len;
+ int ret = 0;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
@@ -139,9 +114,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
inode_lock(inode);
file_accessed(file);
- ret = -ENOMEM;
-
- vm_flags = vma->vm_flags;
/*
* for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
* reserving here. Note: only for SHM hugetlbfs file, the inode
@@ -151,20 +123,55 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
vm_flags |= VM_NORESERVE;
if (hugetlb_reserve_pages(inode,
- vma->vm_pgoff >> huge_page_order(h),
- len >> huge_page_shift(h), vma,
- vm_flags) < 0)
+ vma->vm_pgoff >> huge_page_order(h),
+ len >> huge_page_shift(h), vma,
+ vm_flags) < 0) {
+ ret = -ENOMEM;
goto out;
+ }
- ret = 0;
if (vma->vm_flags & VM_WRITE && inode->i_size < len)
i_size_write(inode, len);
+
out:
inode_unlock(inode);
-
return ret;
}
+static int hugetlbfs_file_mmap_prepare(struct vm_area_desc *desc)
+{
+ struct file *file = desc->file;
+ struct hstate *h = hstate_file(file);
+
+ /*
+ * vma address alignment (but not the pgoff alignment) has
+ * already been checked by prepare_hugepage_range. If you add
+ * any error returns here, do so after setting VM_HUGETLB, so
+ * is_vm_hugetlb_page tests below unmap_region go the right
+ * way when do_mmap unwinds (may be important on powerpc
+ * and ia64).
+ */
+ desc->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
+ desc->vm_ops = &hugetlb_vm_ops;
+
+ /*
+ * page based offset in vm_pgoff could be sufficiently large to
+ * overflow a loff_t when converted to byte offset. This can
+ * only happen on architectures where sizeof(loff_t) ==
+ * sizeof(unsigned long). So, only check in those instances.
+ */
+ if (sizeof(unsigned long) == sizeof(loff_t)) {
+ if (desc->pgoff & PGOFF_LOFFT_MAX)
+ return -EINVAL;
+ }
+
+ /* must be huge page aligned */
+ if (desc->pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
+ return -EINVAL;
+
+ return 0;
+}
+
/*
* Called under mmap_write_lock(mm).
*/
@@ -1219,7 +1226,8 @@ static void init_once(void *foo)
static const struct file_operations hugetlbfs_file_operations = {
.read_iter = hugetlbfs_read_iter,
- .mmap = hugetlbfs_file_mmap,
+ .mmap_prepare = hugetlbfs_file_mmap_prepare,
+ .mmap_complete = hugetlb_file_mmap_complete,
.fsync = noop_fsync,
.get_unmapped_area = hugetlb_get_unmapped_area,
.llseek = default_llseek,
--
2.51.0
Powered by blists - more mailing lists