Commit dbf789ce authored by Jinshan Xiong's avatar Jinshan Xiong Committed by Greg Kroah-Hartman
Browse files

staging: lustre: llite: allow setting stripes to specify OSTs 



Extend the llite layer to support specifying individual target
OSTs. Support specifying OSTs for regular files only. Directory
support will be implemented later in a separate project. With
this a file could have for example a OST index layout of
2,4,5,9,11. In addition, duplicate indices will be eliminated
automatically. Calculate the max easize by ld_active_tgt_count
instead of ld_tgt_count. However this may introduce problems
when the OSTs are in recovery because non sufficient buffer
may be allocated to store EA.

Signed-off-by: default avatarJian Yu <jian.yu@intel.com>
Signed-off-by: default avatarJinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: default avatarJames Simmons <uja.ornl@gmail.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4665
Reviewed-on: http://review.whamcloud.com/9383


Reviewed-by: default avatarAndreas Dilger <andreas.dilger@intel.com>
Reviewed-by: default avatarJohn L. Hammond <john.hammond@intel.com>
Reviewed-by: default avatarOleg Drokin <oleg.drokin@intel.com>
Signed-off-by: default avatarJames Simmons <jsimmons@infradead.org>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent a6d879fd

drivers/staging/lustre/lustre/include/lustre/lustre_idl.h

+2 −0
Original line number Diff line number Diff line
@@ -1483,6 +1483,8 @@ enum obdo_flags { 
#define LOV_MAGIC_JOIN_V1	(0x0BD20000 | LOV_MAGIC_MAGIC)

#define LOV_MAGIC_V3		(0x0BD30000 | LOV_MAGIC_MAGIC)

#define LOV_MAGIC_MIGRATE	(0x0BD40000 | LOV_MAGIC_MAGIC)

/* reserved for specifying OSTs */

#define LOV_MAGIC_SPECIFIC	(0x0BD50000 | LOV_MAGIC_MAGIC)

#define LOV_MAGIC		LOV_MAGIC_V1



/*

drivers/staging/lustre/lustre/include/lustre/lustre_user.h

+9 −8
Original line number Diff line number Diff line
@@ -284,6 +284,8 @@ enum ll_lease_type { 
#define LOV_USER_MAGIC		LOV_USER_MAGIC_V1

#define LOV_USER_MAGIC_JOIN_V1	0x0BD20BD0

#define LOV_USER_MAGIC_V3	0x0BD30BD0

/* 0x0BD40BD0 is occupied by LOV_MAGIC_MIGRATE */

#define LOV_USER_MAGIC_SPECIFIC	0x0BD50BD0	/* for specific OSTs */



#define LMV_USER_MAGIC    0x0CD30CD0    /*default lmv magic*/
@@ -361,12 +363,11 @@ struct lov_user_md_v3 { /* LOV EA user data (host-endian) */ 


static inline __u32 lov_user_md_size(__u16 stripes, __u32 lmm_magic)

{

	if (lmm_magic == LOV_USER_MAGIC_V3)

		return sizeof(struct lov_user_md_v3) +

				stripes * sizeof(struct lov_user_ost_data_v1);

	else

	if (lmm_magic == LOV_USER_MAGIC_V1)

		return sizeof(struct lov_user_md_v1) +

				stripes * sizeof(struct lov_user_ost_data_v1);

	return sizeof(struct lov_user_md_v3) +

	       stripes * sizeof(struct lov_user_ost_data_v1);

}



/* Compile with -D_LARGEFILE64_SOURCE or -D_GNU_SOURCE (or #define) to

drivers/staging/lustre/lustre/llite/file.c

+11 −17
Original line number Diff line number Diff line
@@ -1540,39 +1540,33 @@ static int ll_lov_setea(struct inode *inode, struct file *file, 
static int ll_lov_setstripe(struct inode *inode, struct file *file,

			    unsigned long arg)

{

	struct lov_user_md_v3 lumv3;

	struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;

	struct lov_user_md_v1 __user *lumv1p = (void __user *)arg;

	struct lov_user_md_v3 __user *lumv3p = (void __user *)arg;

	struct lov_user_md __user *lum = (struct lov_user_md __user *)arg;

	struct lov_user_md *klum;

	int lum_size, rc;

	__u64 flags = FMODE_WRITE;



	/* first try with v1 which is smaller than v3 */

	lum_size = sizeof(struct lov_user_md_v1);

	if (copy_from_user(lumv1, lumv1p, lum_size))

		return -EFAULT;



	if (lumv1->lmm_magic == LOV_USER_MAGIC_V3) {

		lum_size = sizeof(struct lov_user_md_v3);

		if (copy_from_user(&lumv3, lumv3p, lum_size))

			return -EFAULT;

	}

	rc = ll_copy_user_md(lum, &klum);

	if (rc < 0)

		return rc;



	rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lumv1,

	lum_size = rc;

	rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, klum,

				      lum_size);

	cl_lov_delay_create_clear(&file->f_flags);

	if (rc == 0) {

		struct lov_stripe_md *lsm;

		__u32 gen;



		put_user(0, &lumv1p->lmm_stripe_count);

		put_user(0, &lum->lmm_stripe_count);



		ll_layout_refresh(inode, &gen);

		lsm = ccc_inode_lsm_get(inode);

		rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode),

				   0, lsm, (void __user *)arg);

				   0, lsm, lum);

		ccc_inode_lsm_put(inode, lsm);

	}



	kfree(klum);

	return rc;

}

drivers/staging/lustre/lustre/llite/llite_internal.h

+20 −0
Original line number Diff line number Diff line
@@ -875,6 +875,26 @@ int ll_get_obd_name(struct inode *inode, unsigned int cmd, unsigned long arg); 
char *ll_get_fsname(struct super_block *sb, char *buf, int buflen);

void ll_compute_rootsquash_state(struct ll_sb_info *sbi);

void ll_open_cleanup(struct super_block *sb, struct ptlrpc_request *open_req);

ssize_t ll_copy_user_md(const struct lov_user_md __user *md,

			struct lov_user_md **kbuf);



/* Compute expected user md size when passing in a md from user space */

static inline ssize_t ll_lov_user_md_size(const struct lov_user_md *lum)

{

	switch (lum->lmm_magic) {

	case LOV_USER_MAGIC_V1:

		return sizeof(struct lov_user_md_v1);

	case LOV_USER_MAGIC_V3:

		return sizeof(struct lov_user_md_v3);

	case LOV_USER_MAGIC_SPECIFIC:

		if (lum->lmm_stripe_count > LOV_MAX_STRIPE_COUNT)

			return -EINVAL;



		return lov_user_md_size(lum->lmm_stripe_count,

					LOV_USER_MAGIC_SPECIFIC);

	}

	return -EINVAL;

}



/* llite/llite_nfs.c */

extern const struct export_operations lustre_export_operations;

drivers/staging/lustre/lustre/llite/llite_lib.c

+30 −0
Original line number Diff line number Diff line
@@ -2507,6 +2507,36 @@ void ll_dirty_page_discard_warn(struct page *page, int ioret) 
		free_page((unsigned long)buf);

}



ssize_t ll_copy_user_md(const struct lov_user_md __user *md,

			struct lov_user_md **kbuf)

{

	struct lov_user_md lum;

	ssize_t lum_size;



	if (copy_from_user(&lum, md, sizeof(lum))) {

		lum_size = -EFAULT;

		goto no_kbuf;

	}



	lum_size = ll_lov_user_md_size(&lum);

	if (lum_size < 0)

		goto no_kbuf;



	*kbuf = kzalloc(lum_size, GFP_NOFS);

	if (!*kbuf) {

		lum_size = -ENOMEM;

		goto no_kbuf;

	}



	if (copy_from_user(*kbuf, md, lum_size) != 0) {

		kfree(*kbuf);

		*kbuf = NULL;

		lum_size = -EFAULT;

	}

no_kbuf:

	return lum_size;

}



/*

 * Compute llite root squash state after a change of root squash

 * configuration setting or add/remove of a lnet nid