1 files changed, 52 insertions, 121 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d746866ae3b6..0fc179a59830 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -39,8 +39,11 @@
 #include <linux/uaccess.h>
 #include <linux/sched/mm.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/hugetlbfs.h>
+
 static const struct address_space_operations hugetlbfs_aops;
-const struct file_operations hugetlbfs_file_operations;
+static const struct file_operations hugetlbfs_file_operations;
 static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
@@ -73,13 +76,13 @@ enum hugetlb_param {
 };
 
 static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
-	fsparam_u32   ("gid",		Opt_gid),
+	fsparam_gid   ("gid",		Opt_gid),
 	fsparam_string("min_size",	Opt_min_size),
 	fsparam_u32oct("mode",		Opt_mode),
 	fsparam_string("nr_inodes",	Opt_nr_inodes),
 	fsparam_string("pagesize",	Opt_pagesize),
 	fsparam_string("size",		Opt_size),
-	fsparam_u32   ("uid",		Opt_uid),
+	fsparam_uid   ("uid",		Opt_uid),
 	{}
 };
 
@@ -96,7 +99,6 @@ static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
-	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
@@ -113,10 +115,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND);
 	vma->vm_ops = &hugetlb_vm_ops;
 
-	ret = seal_check_write(info->seals, vma);
-	if (ret)
-		return ret;
-
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
 	 * overflow a loff_t when converted to byte offset.  This can
@@ -171,105 +169,29 @@ out:
  * Called under mmap_write_lock(mm).
  */
 
-static unsigned long
-hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
-
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = current->mm->mmap_base;
-	info.high_limit = arch_get_mmap_end(addr, len, flags);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	return vm_unmapped_area(&info);
-}
-
-static unsigned long
-hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (unlikely(offset_in_page(addr))) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = current->mm->mmap_base;
-		info.high_limit = arch_get_mmap_end(addr, len, flags);
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
 unsigned long
-generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-				  unsigned long len, unsigned long pgoff,
-				  unsigned long flags)
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+			    unsigned long len, unsigned long pgoff,
+			    unsigned long flags)
 {
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	unsigned long addr0 = 0;
 	struct hstate *h = hstate_file(file);
-	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (len > TASK_SIZE)
-		return -ENOMEM;
-
 	if (flags & MAP_FIXED) {
+		if (addr & ~huge_page_mask(h))
+			return -EINVAL;
 		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma(mm, addr);
-		if (mmap_end - len >= addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
-			return addr;
 	}
+	if (addr)
+		addr0 = ALIGN(addr, huge_page_size(h));
 
-	/*
-	 * Use mm->get_unmapped_area value as a hint to use topdown routine.
-	 * If architectures have special needs, they should define their own
-	 * version of hugetlb_get_unmapped_area.
-	 */
-	if (mm->get_unmapped_area == arch_get_unmapped_area_topdown)
-		return hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-	return hugetlb_get_unmapped_area_bottomup(file, addr, len,
-			pgoff, flags);
+	return mm_get_unmapped_area_vmflags(current->mm, file, addr0, len, pgoff,
+					    flags, 0);
 }
 
-#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-static unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-			  unsigned long len, unsigned long pgoff,
-			  unsigned long flags)
-{
-	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
-}
-#endif
-
 /*
  * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
  * Returns the maximum number of bytes one can read without touching the 1st raw
@@ -390,14 +312,14 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 static int hugetlbfs_write_begin(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	return -EINVAL;
 }
 
 static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	BUG();
 	return -EINVAL;
@@ -425,7 +347,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
 	if (!ptep)
 		return false;
 
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, addr, ptep);
 	if (huge_pte_none(pte) || !pte_present(pte))
 		return false;
 
@@ -689,6 +611,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 {
 	struct resv_map *resv_map;
 
+	trace_hugetlbfs_evict_inode(inode);
 	remove_inode_hugepages(inode, 0, LLONG_MAX);
 
 	/*
@@ -816,8 +739,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return hugetlbfs_punch_hole(inode, offset, len);
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		error = hugetlbfs_punch_hole(inode, offset, len);
+		goto out_nolock;
+	}
 
 	/*
 	 * Default preallocate case.
@@ -889,13 +814,13 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		 * folios in these areas, we need to consume the reserves
 		 * to keep reservation accounting consistent.
 		 */
-		folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
+		folio = alloc_hugetlb_folio(&pseudo_vma, addr, false);
 		if (IS_ERR(folio)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			error = PTR_ERR(folio);
 			goto out;
 		}
-		clear_huge_page(&folio->page, addr, pages_per_huge_page(h));
+		folio_zero_user(folio, addr);
 		__folio_mark_uptodate(folio);
 		error = hugetlb_add_to_page_cache(folio, mapping, index);
 		if (unlikely(error)) {
@@ -921,6 +846,9 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	inode_set_ctime_current(inode);
 out:
 	inode_unlock(inode);
+
+out_nolock:
+	trace_hugetlbfs_fallocate(inode, mode, offset, len, error);
 	return error;
 }
 
@@ -933,10 +861,12 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	error = setattr_prepare(idmap, dentry, attr);
 	if (error)
 		return error;
 
+	trace_hugetlbfs_setattr(inode, dentry, attr);
+
 	if (ia_valid & ATTR_SIZE) {
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
@@ -950,7 +880,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 		hugetlb_vmtruncate(inode, newsize);
 	}
 
-	setattr_copy(&nop_mnt_idmap, inode, attr);
+	setattr_copy(idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -985,6 +915,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+					struct mnt_idmap *idmap,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
 {
@@ -1006,7 +937,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
 		inode->i_ino = get_next_ino();
-		inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+		inode_init_owner(idmap, inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
@@ -1034,6 +965,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
+		trace_hugetlbfs_alloc_inode(inode, dir, mode);
 	} else {
 		if (resv_map)
 			kref_put(&resv_map->refs, resv_map_release);
@@ -1050,7 +982,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1062,7 +994,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			   struct dentry *dentry, umode_t mode)
 {
-	int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry,
+	int retval = hugetlbfs_mknod(idmap, dir, dentry,
 				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
@@ -1073,7 +1005,7 @@ static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
 			    umode_t mode, bool excl)
 {
-	return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
+	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }
 
 static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
@@ -1082,7 +1014,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1094,10 +1026,11 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 			     struct inode *dir, struct dentry *dentry,
 			     const char *symname)
 {
+	const umode_t mode = S_IFLNK|S_IRWXUGO;
 	struct inode *inode;
 	int error = -ENOSPC;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
@@ -1129,10 +1062,7 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 		hugetlb_set_folio_subpool(src, NULL);
 	}
 
-	if (mode != MIGRATE_SYNC_NO_COPY)
-		folio_migrate_copy(dst, src);
-	else
-		folio_migrate_flags(dst, src);
+	folio_migrate_flags(dst, src);
 
 	return MIGRATEPAGE_SUCCESS;
 }
@@ -1275,6 +1205,7 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 
 static void hugetlbfs_free_inode(struct inode *inode)
 {
+	trace_hugetlbfs_free_inode(inode);
 	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
 }
 
@@ -1299,13 +1230,14 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-const struct file_operations hugetlbfs_file_operations = {
+static const struct file_operations hugetlbfs_file_operations = {
 	.read_iter		= hugetlbfs_read_iter,
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
 	.llseek			= default_llseek,
 	.fallocate		= hugetlbfs_fallocate,
+	.fop_flags		= FOP_HUGE_PAGES,
 };
 
 static const struct inode_operations hugetlbfs_dir_inode_operations = {
@@ -1376,15 +1308,11 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	switch (opt) {
 	case Opt_uid:
-		ctx->uid = make_kuid(current_user_ns(), result.uint_32);
-		if (!uid_valid(ctx->uid))
-			goto bad_val;
+		ctx->uid = result.uid;
 		return 0;
 
 	case Opt_gid:
-		ctx->gid = make_kgid(current_user_ns(), result.uint_32);
-		if (!gid_valid(ctx->gid))
-			goto bad_val;
+		ctx->gid = result.gid;
 		return 0;
 
 	case Opt_mode:
@@ -1566,6 +1494,7 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.init_fs_context	= hugetlbfs_init_fs_context,
 	.parameters		= hugetlb_fs_parameters,
 	.kill_sb		= kill_litter_super,
+	.fs_flags               = FS_ALLOW_IDMAP,
 };
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -1619,7 +1548,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	}
 
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	/* hugetlbfs_vfsmount[] mounts do not use idmapped mounts.  */
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL,
+				    S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)