summaryrefslogtreecommitdiffstats
path: root/fs/hugetlbfs
diff options
context:
space:
mode:
authorAndi Kleen <ak@linux.intel.com>2012-12-11 16:01:34 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2012-12-11 17:22:25 -0800
commit42d7395feb56f0655cd8b68e06fc6063823449f8 (patch)
tree47cfbad1737d98d9752a2aab7e525f1fe5194d27 /fs/hugetlbfs
parentff604cf6d41f1e05f34762e1d764fe14a0f5f964 (diff)
downloadlinux-42d7395feb56f0655cd8b68e06fc6063823449f8.tar.gz
linux-42d7395feb56f0655cd8b68e06fc6063823449f8.tar.bz2
linux-42d7395feb56f0655cd8b68e06fc6063823449f8.zip
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB
There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/hugetlbfs')
-rw-r--r--fs/hugetlbfs/inode.c63
1 files changed, 50 insertions, 13 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c5bc355d8243..21b8a4875237 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -923,7 +923,7 @@ static struct file_system_type hugetlbfs_fs_type = {
.kill_sb = kill_litter_super,
};
-static struct vfsmount *hugetlbfs_vfsmount;
+static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
static int can_do_hugetlb_shm(void)
{
@@ -932,9 +932,22 @@ static int can_do_hugetlb_shm(void)
return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
}
+static int get_hstate_idx(int page_size_log)
+{
+ struct hstate *h;
+
+ if (!page_size_log)
+ return default_hstate_idx;
+ h = size_to_hstate(1 << page_size_log);
+ if (!h)
+ return -1;
+ return h - hstates;
+}
+
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acctflag,
- struct user_struct **user, int creat_flags)
+ struct user_struct **user,
+ int creat_flags, int page_size_log)
{
int error = -ENOMEM;
struct file *file;
@@ -944,9 +957,14 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
struct qstr quick_string;
struct hstate *hstate;
unsigned long num_pages;
+ int hstate_idx;
+
+ hstate_idx = get_hstate_idx(page_size_log);
+ if (hstate_idx < 0)
+ return ERR_PTR(-ENODEV);
*user = NULL;
- if (!hugetlbfs_vfsmount)
+ if (!hugetlbfs_vfsmount[hstate_idx])
return ERR_PTR(-ENOENT);
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -963,7 +981,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
}
}
- root = hugetlbfs_vfsmount->mnt_root;
+ root = hugetlbfs_vfsmount[hstate_idx]->mnt_root;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
@@ -971,7 +989,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
if (!path.dentry)
goto out_shm_unlock;
- path.mnt = mntget(hugetlbfs_vfsmount);
+ path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
error = -ENOSPC;
inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
@@ -1011,8 +1029,9 @@ out_shm_unlock:
static int __init init_hugetlbfs_fs(void)
{
+ struct hstate *h;
int error;
- struct vfsmount *vfsmount;
+ int i;
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
@@ -1029,14 +1048,26 @@ static int __init init_hugetlbfs_fs(void)
if (error)
goto out;
- vfsmount = kern_mount(&hugetlbfs_fs_type);
+ i = 0;
+ for_each_hstate(h) {
+ char buf[50];
+ unsigned ps_kb = 1U << (h->order + PAGE_SHIFT - 10);
- if (!IS_ERR(vfsmount)) {
- hugetlbfs_vfsmount = vfsmount;
- return 0;
- }
+ snprintf(buf, sizeof(buf), "pagesize=%uK", ps_kb);
+ hugetlbfs_vfsmount[i] = kern_mount_data(&hugetlbfs_fs_type,
+ buf);
- error = PTR_ERR(vfsmount);
+ if (IS_ERR(hugetlbfs_vfsmount[i])) {
+ pr_err("hugetlb: Cannot mount internal hugetlbfs for "
+ "page size %uK", ps_kb);
+ error = PTR_ERR(hugetlbfs_vfsmount[i]);
+ hugetlbfs_vfsmount[i] = NULL;
+ }
+ i++;
+ }
+ /* Non default hstates are optional */
+ if (!IS_ERR_OR_NULL(hugetlbfs_vfsmount[default_hstate_idx]))
+ return 0;
out:
kmem_cache_destroy(hugetlbfs_inode_cachep);
@@ -1047,13 +1078,19 @@ static int __init init_hugetlbfs_fs(void)
static void __exit exit_hugetlbfs_fs(void)
{
+ struct hstate *h;
+ int i;
+
+
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(hugetlbfs_inode_cachep);
- kern_unmount(hugetlbfs_vfsmount);
+ i = 0;
+ for_each_hstate(h)
+ kern_unmount(hugetlbfs_vfsmount[i++]);
unregister_filesystem(&hugetlbfs_fs_type);
bdi_destroy(&hugetlbfs_backing_dev_info);
}