mm/hugetlbfs: update hugetlbfs to use mmap_prepare

Since we can now perform actions after the VMA is established via
mmap_prepare, use desc->action_success_hook to set up the hugetlb lock
once the VMA is setup.

We also make changes throughout hugetlbfs to make this possible.

Note that we must hide newly established hugetlb VMAs from the rmap until
the operation is entirely complete as we establish a hugetlb lock during
VMA setup that can be raced by rmap users.

Link: https://lkml.kernel.org/r/b1afa16d3cfa585a03df9ae215ae9f905b3f0ed7.1760959442.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chatre, Reinette <reinette.chatre@intel.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dave Martin <dave.martin@arm.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Morse <james.morse@arm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Robin Murohy <robin.murphy@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 33 insertions, 13 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ce8e40d35032..3919fca56553 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -96,8 +96,15 @@ 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_prepare_success(const struct vm_area_struct *vma)
 {
+	/* Unfortunate we have to reassign vma->vm_private_data. */
+	return hugetlb_vma_lock_alloc((struct vm_area_struct *)vma);
+}
+
+static int hugetlbfs_file_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *file = desc->file;
 	struct inode *inode = file_inode(file);
 	loff_t len, vma_len;
 	int ret;
@@ -112,8 +119,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * 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;
+	desc->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
+	desc->vm_ops = &hugetlb_vm_ops;
 
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
@@ -122,16 +129,16 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * sizeof(unsigned long).  So, only check in those instances.
 	 */
 	if (sizeof(unsigned long) == sizeof(loff_t)) {
-		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+		if (desc->pgoff & PGOFF_LOFFT_MAX)
 			return -EINVAL;
 	}
 
 	/* must be huge page aligned */
-	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
+	if (desc->pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
-	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	vma_len = (loff_t)vma_desc_size(desc);
+	len = vma_len + ((loff_t)desc->pgoff << PAGE_SHIFT);
 	/* check for overflow */
 	if (len < vma_len)
 		return -EINVAL;
@@ -141,7 +148,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = -ENOMEM;
 
-	vm_flags = vma->vm_flags;
+	vm_flags = desc->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
@@ -151,17 +158,30 @@ 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)
+			desc->pgoff >> huge_page_order(h),
+			len >> huge_page_shift(h), desc,
+			vm_flags) < 0)
 		goto out;
 
 	ret = 0;
-	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
+	if ((desc->vm_flags & VM_WRITE) && inode->i_size < len)
 		i_size_write(inode, len);
 out:
 	inode_unlock(inode);
 
+	if (!ret) {
+		/* Allocate the VMA lock after we set it up. */
+		desc->action.success_hook = hugetlb_file_mmap_prepare_success;
+		/*
+		 * We cannot permit the rmap finding this VMA in the time
+		 * between the VMA being inserted into the VMA tree and the
+		 * completion/success hook being invoked.
+		 *
+		 * This is because we establish a per-VMA hugetlb lock which can
+		 * be raced by rmap.
+		 */
+		desc->action.hide_from_rmap_until_complete = true;
+	}
 	return ret;
 }
 
@@ -1220,7 +1240,7 @@ 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,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
 	.llseek			= default_llseek,