3.8-stable review patch. If anyone has any objections, please let me know.
------------------
From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
commit af73e4d9506d3b797509f3c030e7dcd554f7d9c4 upstream.
The current kernel returns -EINVAL unless a given mmap length is
"almost" hugepage aligned. This is because in sys_mmap_pgoff() the
given length is passed to vm_mmap_pgoff() as it is without being aligned
with hugepage boundary.
This is a regression introduced in commit 40716e29243d ("hugetlbfs: fix
alignment of huge page requests"), where alignment code is pushed into
hugetlb_file_setup() and the variable len in caller side is not changed.
To fix this, this patch partially reverts that commit, and adds
alignment code in caller side. And it also introduces hstate_sizelog()
in order to get proper hstate to specified hugepage size.
Addresses https://bugzilla.kernel.org/show_bug.cgi?id=56881
[akpm@xxxxxxxxxxxxxxxxxxxx: fix warning when CONFIG_HUGETLB_PAGE=n]
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reported-by: <iceman_dvd@xxxxxxxxx>
Cc: Steven Truelove <steven.truelove@xxxxxxxxxxx>
Cc: Jianguo Wu <wujianguo@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/hugetlbfs/inode.c | 24 ++++++++++--------------
include/linux/hugetlb.h | 19 +++++++++++++------
ipc/shm.c | 6 +++++-
mm/mmap.c | 7 ++++++-
4 files changed, 34 insertions(+), 22 deletions(-)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -908,19 +908,19 @@ static int can_do_hugetlb_shm(void)
static int get_hstate_idx(int page_size_log)
{
- struct hstate *h;
+ struct hstate *h = hstate_sizelog(page_size_log);
- 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,
+/*
+ * Note that size should be aligned to proper hugepage size in caller side,
+ * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
+ */
+struct file *hugetlb_file_setup(const char *name, size_t size,
+ vm_flags_t acctflag, struct user_struct **user,
int creat_flags, int page_size_log)
{
int error = -ENOMEM;
@@ -929,8 +929,6 @@ struct file *hugetlb_file_setup(const ch
struct path path;
struct dentry *root;
struct qstr quick_string;
- struct hstate *hstate;
- unsigned long num_pages;
int hstate_idx;
hstate_idx = get_hstate_idx(page_size_log);
@@ -969,12 +967,10 @@ struct file *hugetlb_file_setup(const ch
if (!inode)
goto out_dentry;
- hstate = hstate_inode(inode);
- size += addr & ~huge_page_mask(hstate);
- num_pages = ALIGN(size, huge_page_size(hstate)) >>
- huge_page_shift(hstate);
error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
+ if (hugetlb_reserve_pages(inode, 0,
+ size >> huge_page_shift(hstate_inode(inode)), NULL,
+ acctflag))
goto out_inode;
d_instantiate(path.dentry, inode);
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -185,8 +185,7 @@ static inline struct hugetlbfs_sb_info *
extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, unsigned long addr,
- size_t size, vm_flags_t acct,
+struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
struct user_struct **user, int creat_flags,
int page_size_log);
@@ -205,8 +204,8 @@ static inline int is_file_hugepages(stru
#define is_file_hugepages(file) 0
static inline 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,
+hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
+ struct user_struct **user, int creat_flags,
int page_size_log)
{
return ERR_PTR(-ENOSYS);
@@ -284,6 +283,13 @@ static inline struct hstate *hstate_file
return hstate_inode(f->f_dentry->d_inode);
}
+static inline struct hstate *hstate_sizelog(int page_size_log)
+{
+ if (!page_size_log)
+ return &default_hstate;
+ return size_to_hstate(1 << page_size_log);
+}
+
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return hstate_file(vma->vm_file);
@@ -348,11 +354,12 @@ static inline int hstate_index(struct hs
return h - hstates;
}
-#else
+#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
+#define hstate_sizelog(s) NULL
#define hstate_vma(v) NULL
#define hstate_inode(i) NULL
#define huge_page_size(h) PAGE_SIZE
@@ -367,6 +374,6 @@ static inline unsigned int pages_per_hug
}
#define hstate_index_to_shift(index) 0
#define hstate_index(h) 0
-#endif
+#endif /* CONFIG_HUGETLB_PAGE */
#endif /* _LINUX_HUGETLB_H */
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -491,10 +491,14 @@ static int newseg(struct ipc_namespace *
sprintf (name, "SYSV%08x", key);
if (shmflg & SHM_HUGETLB) {
+ struct hstate *hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT)
+ & SHM_HUGE_MASK);
+ size_t hugesize = ALIGN(size, huge_page_size(hs));
+
/* hugetlb_file_setup applies strict accounting */
if (shmflg & SHM_NORESERVE)
acctflag = VM_NORESERVE;
- file = hugetlb_file_setup(name, 0, size, acctflag,
+ file = hugetlb_file_setup(name, hugesize, acctflag,
&shp->mlock_user, HUGETLB_SHMFS_INODE,
(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
} else {
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1296,15 +1296,20 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned lon
file = fget(fd);
if (!file)
goto out;
+ if (is_file_hugepages(file))
+ len = ALIGN(len, huge_page_size(hstate_file(file)));
} else if (flags & MAP_HUGETLB) {
struct user_struct *user = NULL;
+
+ len = ALIGN(len, huge_page_size(hstate_sizelog(
+ (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK)));
/*
* VM_NORESERVE is used because the reservations will be
* taken when vm_ops->mmap() is called
* A dummy user value is used because we are not locking
* memory so no accounting is necessary
*/
- file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
+ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
VM_NORESERVE,
&user, HUGETLB_ANONHUGE_INODE,
(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html