hugetlbfs: per mount huge page sizes
Add the ability to configure the hugetlb hstate used on a per mount basis. - Add a new pagesize= option to the hugetlbfs mount that allows setting the page size - This option causes the mount code to find the hstate corresponding to the specified size, and sets up a pointer to the hstate in the mount's superblock. - Change the hstate accessors to use this information rather than the global_hstate they were using (requires a slight change in mm/memory.c so we don't NULL deref in the error-unmap path -- see comments). [np: take hstate out of hugetlbfs inode and vma->vm_private_data] Acked-by: Adam Litke <agl@us.ibm.com> Acked-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Andi Kleen
Linus Torvalds
parent
e5ff215941
commit
a137e1cc6d
|
|
@ -53,6 +53,7 @@ int sysctl_hugetlb_shm_group;
|
|||
enum {
|
||||
Opt_size, Opt_nr_inodes,
|
||||
Opt_mode, Opt_uid, Opt_gid,
|
||||
Opt_pagesize,
|
||||
Opt_err,
|
||||
};
|
||||
|
||||
|
|
@ -62,6 +63,7 @@ static match_table_t tokens = {
|
|||
{Opt_mode, "mode=%o"},
|
||||
{Opt_uid, "uid=%u"},
|
||||
{Opt_gid, "gid=%u"},
|
||||
{Opt_pagesize, "pagesize=%s"},
|
||||
{Opt_err, NULL},
|
||||
};
|
||||
|
||||
|
|
@ -750,6 +752,8 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
|
|||
char *p, *rest;
|
||||
substring_t args[MAX_OPT_ARGS];
|
||||
int option;
|
||||
unsigned long long size = 0;
|
||||
enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;
|
||||
|
||||
if (!options)
|
||||
return 0;
|
||||
|
|
@ -780,17 +784,13 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
|
|||
break;
|
||||
|
||||
case Opt_size: {
|
||||
unsigned long long size;
|
||||
/* memparse() will accept a K/M/G without a digit */
|
||||
if (!isdigit(*args[0].from))
|
||||
goto bad_val;
|
||||
size = memparse(args[0].from, &rest);
|
||||
if (*rest == '%') {
|
||||
size <<= HPAGE_SHIFT;
|
||||
size *= max_huge_pages;
|
||||
do_div(size, 100);
|
||||
}
|
||||
pconfig->nr_blocks = (size >> HPAGE_SHIFT);
|
||||
setsize = SIZE_STD;
|
||||
if (*rest == '%')
|
||||
setsize = SIZE_PERCENT;
|
||||
break;
|
||||
}
|
||||
|
||||
|
|
@ -801,6 +801,19 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
|
|||
pconfig->nr_inodes = memparse(args[0].from, &rest);
|
||||
break;
|
||||
|
||||
case Opt_pagesize: {
|
||||
unsigned long ps;
|
||||
ps = memparse(args[0].from, &rest);
|
||||
pconfig->hstate = size_to_hstate(ps);
|
||||
if (!pconfig->hstate) {
|
||||
printk(KERN_ERR
|
||||
"hugetlbfs: Unsupported page size %lu MB\n",
|
||||
ps >> 20);
|
||||
return -EINVAL;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
|
||||
p);
|
||||
|
|
@ -808,6 +821,18 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
|
|||
break;
|
||||
}
|
||||
}
|
||||
|
||||
/* Do size after hstate is set up */
|
||||
if (setsize > NO_SIZE) {
|
||||
struct hstate *h = pconfig->hstate;
|
||||
if (setsize == SIZE_PERCENT) {
|
||||
size <<= huge_page_shift(h);
|
||||
size *= h->max_huge_pages;
|
||||
do_div(size, 100);
|
||||
}
|
||||
pconfig->nr_blocks = (size >> huge_page_shift(h));
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
bad_val:
|
||||
|
|
@ -832,6 +857,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
|
|||
config.uid = current->fsuid;
|
||||
config.gid = current->fsgid;
|
||||
config.mode = 0755;
|
||||
config.hstate = &default_hstate;
|
||||
ret = hugetlbfs_parse_options(data, &config);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
|
@ -840,14 +866,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
|
|||
if (!sbinfo)
|
||||
return -ENOMEM;
|
||||
sb->s_fs_info = sbinfo;
|
||||
sbinfo->hstate = config.hstate;
|
||||
spin_lock_init(&sbinfo->stat_lock);
|
||||
sbinfo->max_blocks = config.nr_blocks;
|
||||
sbinfo->free_blocks = config.nr_blocks;
|
||||
sbinfo->max_inodes = config.nr_inodes;
|
||||
sbinfo->free_inodes = config.nr_inodes;
|
||||
sb->s_maxbytes = MAX_LFS_FILESIZE;
|
||||
sb->s_blocksize = HPAGE_SIZE;
|
||||
sb->s_blocksize_bits = HPAGE_SHIFT;
|
||||
sb->s_blocksize = huge_page_size(config.hstate);
|
||||
sb->s_blocksize_bits = huge_page_shift(config.hstate);
|
||||
sb->s_magic = HUGETLBFS_MAGIC;
|
||||
sb->s_op = &hugetlbfs_ops;
|
||||
sb->s_time_gran = 1;
|
||||
|
|
|
|||
|
|
@ -100,6 +100,7 @@ struct hugetlbfs_config {
|
|||
umode_t mode;
|
||||
long nr_blocks;
|
||||
long nr_inodes;
|
||||
struct hstate *hstate;
|
||||
};
|
||||
|
||||
struct hugetlbfs_sb_info {
|
||||
|
|
@ -108,6 +109,7 @@ struct hugetlbfs_sb_info {
|
|||
long max_inodes; /* inodes allowed */
|
||||
long free_inodes; /* inodes free */
|
||||
spinlock_t stat_lock;
|
||||
struct hstate *hstate;
|
||||
};
|
||||
|
||||
|
||||
|
|
@ -191,19 +193,21 @@ extern unsigned int default_hstate_idx;
|
|||
|
||||
#define default_hstate (hstates[default_hstate_idx])
|
||||
|
||||
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
|
||||
static inline struct hstate *hstate_inode(struct inode *i)
|
||||
{
|
||||
return &default_hstate;
|
||||
struct hugetlbfs_sb_info *hsb;
|
||||
hsb = HUGETLBFS_SB(i->i_sb);
|
||||
return hsb->hstate;
|
||||
}
|
||||
|
||||
static inline struct hstate *hstate_file(struct file *f)
|
||||
{
|
||||
return &default_hstate;
|
||||
return hstate_inode(f->f_dentry->d_inode);
|
||||
}
|
||||
|
||||
static inline struct hstate *hstate_inode(struct inode *i)
|
||||
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
|
||||
{
|
||||
return &default_hstate;
|
||||
return hstate_file(vma->vm_file);
|
||||
}
|
||||
|
||||
static inline unsigned long huge_page_size(struct hstate *h)
|
||||
|
|
|
|||
10
mm/hugetlb.c
10
mm/hugetlb.c
|
|
@ -1439,20 +1439,10 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
|
|||
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
|
||||
unsigned long end, struct page *ref_page)
|
||||
{
|
||||
/*
|
||||
* It is undesirable to test vma->vm_file as it should be non-null
|
||||
* for valid hugetlb area. However, vm_file will be NULL in the error
|
||||
* cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
|
||||
* do_mmap_pgoff() nullifies vma->vm_file before calling this function
|
||||
* to clean up. Since no pte has actually been setup, it is safe to
|
||||
* do nothing in this case.
|
||||
*/
|
||||
if (vma->vm_file) {
|
||||
spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
|
||||
__unmap_hugepage_range(vma, start, end, ref_page);
|
||||
spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* This is called when the original mapper is failing to COW a MAP_PRIVATE
|
||||
|
|
|
|||
14
mm/memory.c
14
mm/memory.c
|
|
@ -901,9 +901,23 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
|
|||
}
|
||||
|
||||
if (unlikely(is_vm_hugetlb_page(vma))) {
|
||||
/*
|
||||
* It is undesirable to test vma->vm_file as it
|
||||
* should be non-null for valid hugetlb area.
|
||||
* However, vm_file will be NULL in the error
|
||||
* cleanup path of do_mmap_pgoff. When
|
||||
* hugetlbfs ->mmap method fails,
|
||||
* do_mmap_pgoff() nullifies vma->vm_file
|
||||
* before calling this function to clean up.
|
||||
* Since no pte has actually been setup, it is
|
||||
* safe to do nothing in this case.
|
||||
*/
|
||||
if (vma->vm_file) {
|
||||
unmap_hugepage_range(vma, start, end, NULL);
|
||||
zap_work -= (end - start) /
|
||||
pages_per_huge_page(hstate_vma(vma));
|
||||
}
|
||||
|
||||
start = end;
|
||||
} else
|
||||
start = unmap_page_range(*tlbp, vma,
|
||||
|
|
|
|||
Loading…
Reference in New Issue