[PATCH] tightening hugetlb strict accounting
Current hugetlb strict accounting for shared mapping always assume mapping
starts at zero file offset and reserves pages between zero and size of the
file. This assumption often reserves (or lock down) a lot more pages then
necessary if application maps at none zero file offset. libhugetlbfs is
one example that requires proper reservation on shared mapping starts at
none zero offset.
This patch extends the reservation and hugetlb strict accounting to support
any arbitrary pair of (offset, len), resulting a much more robust and
accurate scheme. More importantly, it won't lock down any hugetlb pages
outside file mapping.
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Acked-by: Adam Litke <agl@us.ibm.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 678fc72..e6410d8 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -59,7 +59,6 @@
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file->f_dentry->d_inode;
- struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
loff_t len, vma_len;
int ret;
@@ -87,9 +86,10 @@
if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
goto out;
- if (vma->vm_flags & VM_MAYSHARE)
- if (hugetlb_extend_reservation(info, len >> HPAGE_SHIFT) != 0)
- goto out;
+ if (vma->vm_flags & VM_MAYSHARE &&
+ hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
+ len >> HPAGE_SHIFT))
+ goto out;
ret = 0;
hugetlb_prefault_arch_hook(vma->vm_mm);
@@ -195,12 +195,8 @@
const pgoff_t start = lstart >> HPAGE_SHIFT;
struct pagevec pvec;
pgoff_t next;
- int i;
+ int i, freed = 0;
- hugetlb_truncate_reservation(HUGETLBFS_I(inode),
- lstart >> HPAGE_SHIFT);
- if (!mapping->nrpages)
- return;
pagevec_init(&pvec, 0);
next = start;
while (1) {
@@ -221,10 +217,12 @@
truncate_huge_page(page);
unlock_page(page);
hugetlb_put_quota(mapping);
+ freed++;
}
huge_pagevec_release(&pvec);
}
BUG_ON(!lstart && mapping->nrpages);
+ hugetlb_unreserve_pages(inode, start, freed);
}
static void hugetlbfs_delete_inode(struct inode *inode)
@@ -366,6 +364,7 @@
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ INIT_LIST_HEAD(&inode->i_mapping->private_list);
info = HUGETLBFS_I(inode);
mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, NULL);
switch (mode & S_IFMT) {
@@ -538,7 +537,6 @@
hugetlbfs_inc_free_inodes(sbinfo);
return NULL;
}
- p->prereserved_hpages = 0;
return &p->vfs_inode;
}
@@ -781,8 +779,7 @@
goto out_file;
error = -ENOMEM;
- if (hugetlb_extend_reservation(HUGETLBFS_I(inode),
- size >> HPAGE_SHIFT) != 0)
+ if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT))
goto out_inode;
d_instantiate(dentry, inode);