-/*
+/* -*- mode: c; c-basic-offset: 8; indent-tabs-mode: nil; -*-
+ * vim:expandtab:shiftwidth=8:tabstop=8:
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
*
* All code that works with directory layout had been switched to pagecache
* and moved here. AV
- *
+ *
* Adapted for Lustre Light
- * Copyright (C) 2002, Cluster File Systems, Inc.
- *
+ * Copyright (C) 2002-2003, Cluster File Systems, Inc.
+ *
*/
#include <linux/fs.h>
#include <linux/ext2_fs.h>
#include <linux/pagemap.h>
#include <linux/mm.h>
-#include <linux/locks.h>
+#include <linux/version.h>
+#include <linux/smp_lock.h>
#include <asm/uaccess.h>
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,5,0))
+# include <linux/locks.h> // for wait_on_buffer
+#else
+# include <linux/buffer_head.h> // for wait_on_buffer
+#endif
-#define DEBUG_SUBSYSTEM S_LLIGHT
+#define DEBUG_SUBSYSTEM S_LLITE
#include <linux/obd_support.h>
#include <linux/obd_class.h>
#include <linux/lustre_lib.h>
#include <linux/lustre_idl.h>
#include <linux/lustre_mds.h>
-#include <linux/lustre_light.h>
+#include <linux/lustre_lite.h>
+#include <linux/lustre_dlm.h>
+#include "llite_internal.h"
typedef struct ext2_dir_entry_2 ext2_dirent;
#define PageChecked(page) test_bit(PG_checked, &(page)->flags)
#define SetPageChecked(page) set_bit(PG_checked, &(page)->flags)
-
-static int ll_dir_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to)
-{
- return 0;
-}
-
/* returns the page unlocked, but with a reference */
static int ll_dir_readpage(struct file *file, struct page *page)
{
- struct inode *inode = page->mapping->host;
- struct ll_sb_info *sbi = ll_i2sbi(inode);
- char *buf;
- __u64 offset;
+ struct inode *inode = page->mapping->host;
+ struct ll_fid mdc_fid;
+ __u64 offset;
+ struct ptlrpc_request *request;
+ struct mds_body *body;
int rc = 0;
- struct ptlrpc_request *request;
-
ENTRY;
- if ( ((inode->i_size + PAGE_CACHE_SIZE -1)>>PAGE_SHIFT)
- <= page->index) {
- memset(kmap(page), 0, PAGE_CACHE_SIZE);
- kunmap(page);
- EXIT;
- goto readpage_out;
- }
-
- if (Page_Uptodate(page)) {
- CERROR("Explain this please?\n");
- EXIT;
- goto readpage_out;
- }
-
- offset = page->index << PAGE_SHIFT;
- buf = kmap(page);
- rc = mdc_readpage(&sbi->ll_mds_client, inode->i_ino, S_IFDIR, offset,
- buf, &request);
- kunmap(page);
- ptlrpc_free_req(request);
- EXIT;
+ CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p)\n", inode->i_ino,
+ inode->i_generation, inode);
+
+ mdc_pack_fid(&mdc_fid, inode->i_ino, inode->i_generation, S_IFDIR);
- readpage_out:
- if ( !rc )
+ offset = page->index << PAGE_SHIFT;
+ rc = mdc_readpage(ll_i2sbi(inode)->ll_mdc_exp, &mdc_fid,
+ offset, page, &request);
+ if (!rc) {
+ body = lustre_msg_buf(request->rq_repmsg, 0, sizeof (*body));
+ LASSERT (body != NULL); /* checked by mdc_readpage() */
+ LASSERT_REPSWABBED (request, 0); /* swabbed by mdc_readpage() */
+
+ inode->i_size = body->size;
SetPageUptodate(page);
+ }
+ ptlrpc_req_finished(request);
- UnlockPage(page);
+ unlock_page(page);
+ EXIT;
return rc;
-} /* ll_dir_readpage */
+}
struct address_space_operations ll_dir_aops = {
- readpage: ll_dir_readpage,
- prepare_write: ll_dir_prepare_write
+ .readpage = ll_dir_readpage,
};
-int waitfor_one_page(struct page *page)
-{
- int error = 0;
- struct buffer_head *bh, *head = page->buffers;
-
- bh = head;
- do {
- wait_on_buffer(bh);
- if (buffer_req(bh) && !buffer_uptodate(bh))
- error = -EIO;
- } while ((bh = bh->b_this_page) != head);
- return error;
-}
-
/*
* ext2 uses block-sized chunks. Arguably, sector-sized ones would be
* more robust, but we have what we have
*/
static inline unsigned ext2_chunk_size(struct inode *inode)
{
- //return inode->i_sb->s_blocksize;
- return PAGE_SIZE;
+ return inode->i_sb->s_blocksize;
}
static inline void ext2_put_page(struct page *page)
{
- kunmap(page);
- page_cache_release(page);
+ kunmap(page);
+ page_cache_release(page);
}
static inline unsigned long dir_pages(struct inode *inode)
{
- return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
+ return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
}
-extern void set_page_clean(struct page *page);
-
-static int ext2_commit_chunk(struct page *page, unsigned from, unsigned to)
-{
- struct inode *dir = page->mapping->host;
- int err = 0;
-
- dir->i_version = ++event;
- dir->i_size = (page->index << PAGE_CACHE_SHIFT) + to;
- SetPageUptodate(page);
- set_page_clean(page);
-
- //page->mapping->a_ops->commit_write(NULL, page, from, to);
- //if (IS_SYNC(dir))
- // err = waitfor_one_page(page);
- return err;
-}
static void ext2_check_page(struct page *page)
{
- struct inode *dir = page->mapping->host;
- unsigned chunk_size = ext2_chunk_size(dir);
- char *kaddr = page_address(page);
- // u32 max_inumber = le32_to_cpu(sb->u.ext2_sb.s_es->s_inodes_count);
- unsigned offs, rec_len;
- unsigned limit = PAGE_CACHE_SIZE;
- ext2_dirent *p;
- char *error;
-
- if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
- limit = dir->i_size & ~PAGE_CACHE_MASK;
- if (limit & (chunk_size - 1)) {
- CERROR("limit %d dir size %lld index %ld\n",
- limit, dir->i_size, page->index);
- goto Ebadsize;
- }
- for (offs = limit; offs<PAGE_CACHE_SIZE; offs += chunk_size) {
- ext2_dirent *p = (ext2_dirent*)(kaddr + offs);
- p->rec_len = cpu_to_le16(chunk_size);
- }
- if (!limit)
- goto out;
- }
- for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
- p = (ext2_dirent *)(kaddr + offs);
- rec_len = le16_to_cpu(p->rec_len);
-
- if (rec_len < EXT2_DIR_REC_LEN(1))
- goto Eshort;
- if (rec_len & 3)
- goto Ealign;
- if (rec_len < EXT2_DIR_REC_LEN(p->name_len))
- goto Enamelen;
- if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
- goto Espan;
- // if (le32_to_cpu(p->inode) > max_inumber)
- //goto Einumber;
- }
- if (offs != limit)
- goto Eend;
+ struct inode *dir = page->mapping->host;
+ unsigned chunk_size = ext2_chunk_size(dir);
+ char *kaddr = page_address(page);
+ // u32 max_inumber = le32_to_cpu(sb->u.ext2_sb.s_es->s_inodes_count);
+ unsigned offs, rec_len;
+ unsigned limit = PAGE_CACHE_SIZE;
+ ext2_dirent *p;
+ char *error;
+
+ if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
+ limit = dir->i_size & ~PAGE_CACHE_MASK;
+ if (limit & (chunk_size - 1)) {
+ CERROR("limit %d dir size %lld index %ld\n",
+ limit, dir->i_size, page->index);
+ goto Ebadsize;
+ }
+ for (offs = limit; offs<PAGE_CACHE_SIZE; offs += chunk_size) {
+ ext2_dirent *p = (ext2_dirent*)(kaddr + offs);
+ p->rec_len = cpu_to_le16(chunk_size);
+ p->name_len = 0;
+ p->inode = 0;
+ }
+ if (!limit)
+ goto out;
+ }
+ for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
+ p = (ext2_dirent *)(kaddr + offs);
+ rec_len = le16_to_cpu(p->rec_len);
+
+ if (rec_len < EXT2_DIR_REC_LEN(1))
+ goto Eshort;
+ if (rec_len & 3)
+ goto Ealign;
+ if (rec_len < EXT2_DIR_REC_LEN(p->name_len))
+ goto Enamelen;
+ if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
+ goto Espan;
+ // if (le32_to_cpu(p->inode) > max_inumber)
+ //goto Einumber;
+ }
+ if (offs != limit)
+ goto Eend;
out:
- SetPageChecked(page);
- return;
+ SetPageChecked(page);
+ return;
- /* Too bad, we had an error */
+ /* Too bad, we had an error */
Ebadsize:
- CERROR("ext2_check_page"
- "size of directory #%lu is not a multiple of chunk size\n",
- dir->i_ino
- );
- goto fail;
+ CERROR("ext2_check_page"
+ "size of directory #%lu is not a multiple of chunk size\n",
+ dir->i_ino
+ );
+ goto fail;
Eshort:
- error = "rec_len is smaller than minimal";
- goto bad_entry;
+ error = "rec_len is smaller than minimal";
+ goto bad_entry;
Ealign:
- error = "unaligned directory entry";
- goto bad_entry;
+ error = "unaligned directory entry";
+ goto bad_entry;
Enamelen:
- error = "rec_len is too small for name_len";
- goto bad_entry;
+ error = "rec_len is too small for name_len";
+ goto bad_entry;
Espan:
- error = "directory entry across blocks";
- goto bad_entry;
- //Einumber:
- // error = "inode out of bounds";
+ error = "directory entry across blocks";
+ goto bad_entry;
+ //Einumber:
+ // error = "inode out of bounds";
bad_entry:
- CERROR("ext2_check_page: bad entry in directory #%lu: %s - "
- "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
- dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
- (unsigned long) le32_to_cpu(p->inode),
- rec_len, p->name_len);
- goto fail;
+ CERROR("ext2_check_page: bad entry in directory #%lu: %s - "
+ "offset=%lu+%u, inode=%lu, rec_len=%d, name_len=%d",
+ dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT), offs,
+ (unsigned long) le32_to_cpu(p->inode),
+ rec_len, p->name_len);
+ goto fail;
Eend:
- p = (ext2_dirent *)(kaddr + offs);
- CERROR("ext2_check_page"
- "entry in directory #%lu spans the page boundary"
- "offset=%lu, inode=%lu",
- dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
- (unsigned long) le32_to_cpu(p->inode));
+ p = (ext2_dirent *)(kaddr + offs);
+ CERROR("ext2_check_page"
+ "entry in directory #%lu spans the page boundary"
+ "offset=%lu, inode=%lu",
+ dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+ (unsigned long) le32_to_cpu(p->inode));
fail:
- SetPageChecked(page);
- SetPageError(page);
- BUG();
+ SetPageChecked(page);
+ SetPageError(page);
}
-static struct page * ext2_get_page(struct inode *dir, unsigned long n)
+static struct page *ll_get_dir_page(struct inode *dir, unsigned long n)
{
- struct address_space *mapping = dir->i_mapping;
- struct page *page = read_cache_page(mapping, n,
- (filler_t*)mapping->a_ops->readpage, NULL);
- if (!IS_ERR(page)) {
- wait_on_page(page);
- kmap(page);
- if (!Page_Uptodate(page))
- goto fail;
- if (!PageChecked(page))
- ext2_check_page(page);
- if (PageError(page))
- goto fail;
- }
- return page;
+ struct ldlm_res_id res_id =
+ { .name = { dir->i_ino, (__u64)dir->i_generation} };
+ struct lustre_handle lockh;
+ struct obd_device *obddev = class_exp2obd(ll_i2sbi(dir)->ll_mdc_exp);
+ struct address_space *mapping = dir->i_mapping;
+ struct page *page;
+ ldlm_policy_data_t policy = { .l_inodebits = { MDS_INODELOCK_UPDATE } };
+ int rc;
+
+ rc = ldlm_lock_match(obddev->obd_namespace, LDLM_FL_BLOCK_GRANTED,
+ &res_id, LDLM_IBITS, &policy, LCK_PR, &lockh);
+ if (!rc) {
+ struct lookup_intent it = { .it_op = IT_READDIR };
+ struct ptlrpc_request *request;
+ struct mdc_op_data data;
+
+ ll_prepare_mdc_op_data(&data, dir, NULL, NULL, 0, 0);
+
+ rc = mdc_enqueue(ll_i2sbi(dir)->ll_mdc_exp, LDLM_IBITS, &it,
+ LCK_PR, &data, &lockh, NULL, 0,
+ ldlm_completion_ast, ll_mdc_blocking_ast, dir);
+
+ request = (struct ptlrpc_request *)it.d.lustre.it_data;
+ if (request)
+ ptlrpc_req_finished(request);
+ if (rc < 0) {
+ CERROR("lock enqueue: rc: %d\n", rc);
+ return ERR_PTR(rc);
+ }
+ }
+ ldlm_lock_dump_handle(D_OTHER, &lockh);
+
+ page = read_cache_page(mapping, n,
+ (filler_t*)mapping->a_ops->readpage, NULL);
+ if (!IS_ERR(page)) {
+ wait_on_page(page);
+ (void)kmap(page);
+ if (!PageUptodate(page))
+ goto fail;
+ if (!PageChecked(page))
+ ext2_check_page(page);
+ if (PageError(page))
+ goto fail;
+ }
-fail:
- ext2_put_page(page);
- return ERR_PTR(-EIO);
-}
+out_unlock:
+ ldlm_lock_decref(&lockh, LCK_PR);
+ return page;
-/*
- * NOTE! unlike strncmp, ext2_match returns 1 for success, 0 for failure.
- *
- * len <= EXT2_NAME_LEN and de != NULL are guaranteed by caller.
- */
-static inline int ext2_match (int len, const char * const name,
- struct ext2_dir_entry_2 * de)
-{
- if (len != de->name_len)
- return 0;
- if (!de->inode)
- return 0;
- return !memcmp(name, de->name, len);
+fail:
+ ext2_put_page(page);
+ page = ERR_PTR(-EIO);
+ goto out_unlock;
}
/*
*/
static inline ext2_dirent *ext2_next_entry(ext2_dirent *p)
{
- return (ext2_dirent *)((char*)p + le16_to_cpu(p->rec_len));
+ return (ext2_dirent *)((char*)p + le16_to_cpu(p->rec_len));
}
-static inline unsigned
+static inline unsigned
ext2_validate_entry(char *base, unsigned offset, unsigned mask)
{
- ext2_dirent *de = (ext2_dirent*)(base + offset);
- ext2_dirent *p = (ext2_dirent*)(base + (offset&mask));
- while ((char*)p < (char*)de)
- p = ext2_next_entry(p);
- return (char *)p - base;
+ ext2_dirent *de = (ext2_dirent*)(base + offset);
+ ext2_dirent *p = (ext2_dirent*)(base + (offset&mask));
+ while ((char*)p < (char*)de)
+ p = ext2_next_entry(p);
+ return (char *)p - base;
}
static unsigned char ext2_filetype_table[EXT2_FT_MAX] = {
- [EXT2_FT_UNKNOWN] DT_UNKNOWN,
- [EXT2_FT_REG_FILE] DT_REG,
- [EXT2_FT_DIR] DT_DIR,
- [EXT2_FT_CHRDEV] DT_CHR,
- [EXT2_FT_BLKDEV] DT_BLK,
- [EXT2_FT_FIFO] DT_FIFO,
- [EXT2_FT_SOCK] DT_SOCK,
- [EXT2_FT_SYMLINK] DT_LNK,
+ [EXT2_FT_UNKNOWN] DT_UNKNOWN,
+ [EXT2_FT_REG_FILE] DT_REG,
+ [EXT2_FT_DIR] DT_DIR,
+ [EXT2_FT_CHRDEV] DT_CHR,
+ [EXT2_FT_BLKDEV] DT_BLK,
+ [EXT2_FT_FIFO] DT_FIFO,
+ [EXT2_FT_SOCK] DT_SOCK,
+ [EXT2_FT_SYMLINK] DT_LNK,
};
-static unsigned int ll_dt2fmt[DT_WHT + 1] = {
- [EXT2_FT_UNKNOWN] 0,
- [EXT2_FT_REG_FILE] S_IFREG,
- [EXT2_FT_DIR] S_IFDIR,
- [EXT2_FT_CHRDEV] S_IFCHR,
- [EXT2_FT_BLKDEV] S_IFBLK,
- [EXT2_FT_FIFO] S_IFIFO,
- [EXT2_FT_SOCK] S_IFSOCK,
- [EXT2_FT_SYMLINK] S_IFLNK
-};
-
-#define S_SHIFT 12
-static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = {
- [S_IFREG >> S_SHIFT] EXT2_FT_REG_FILE,
- [S_IFDIR >> S_SHIFT] EXT2_FT_DIR,
- [S_IFCHR >> S_SHIFT] EXT2_FT_CHRDEV,
- [S_IFBLK >> S_SHIFT] EXT2_FT_BLKDEV,
- [S_IFIFO >> S_SHIFT] EXT2_FT_FIFO,
- [S_IFSOCK >> S_SHIFT] EXT2_FT_SOCK,
- [S_IFLNK >> S_SHIFT] EXT2_FT_SYMLINK,
-};
-static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
+int ll_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- mode_t mode = inode->i_mode;
- de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
-}
+ struct inode *inode = filp->f_dentry->d_inode;
+ loff_t pos = filp->f_pos;
+ // XXX struct super_block *sb = inode->i_sb;
+ unsigned offset = pos & ~PAGE_CACHE_MASK;
+ unsigned long n = pos >> PAGE_CACHE_SHIFT;
+ unsigned long npages = dir_pages(inode);
+ unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
+ unsigned char *types = NULL;
+ int need_revalidate = (filp->f_version != inode->i_version);
+ int rc = 0;
+ ENTRY;
-int
-new_ll_readdir (struct file * filp, void * dirent, filldir_t filldir)
-{
- loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_dentry->d_inode;
- // XXX struct super_block *sb = inode->i_sb;
- unsigned offset = pos & ~PAGE_CACHE_MASK;
- unsigned long n = pos >> PAGE_CACHE_SHIFT;
- unsigned long npages = dir_pages(inode);
- unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
- unsigned char *types = NULL;
- int need_revalidate = (filp->f_version != inode->i_version);
-
- if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
- goto done;
-
- types = ext2_filetype_table;
-
- for ( ; n < npages; n++, offset = 0) {
- char *kaddr, *limit;
- ext2_dirent *de;
- struct page *page = ext2_get_page(inode, n);
-
- if (IS_ERR(page))
- continue;
- kaddr = page_address(page);
- if (need_revalidate) {
- offset = ext2_validate_entry(kaddr, offset, chunk_mask);
- need_revalidate = 0;
- }
- de = (ext2_dirent *)(kaddr+offset);
- limit = kaddr + PAGE_CACHE_SIZE - EXT2_DIR_REC_LEN(1);
- for ( ;(char*)de <= limit; de = ext2_next_entry(de))
- if (de->inode) {
- int over;
- unsigned char d_type = DT_UNKNOWN;
-
- if (types && de->file_type < EXT2_FT_MAX)
- d_type = types[de->file_type];
-
- offset = (char *)de - kaddr;
- over = filldir(dirent, de->name, de->name_len,
- (n<<PAGE_CACHE_SHIFT) | offset,
- le32_to_cpu(de->inode), d_type);
- if (over) {
- ext2_put_page(page);
- goto done;
- }
- }
- ext2_put_page(page);
- }
+ CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p) pos %llu/%llu\n",
+ inode->i_ino, inode->i_generation, inode, pos, inode->i_size);
+
+ if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
+ RETURN(0);
+
+ types = ext2_filetype_table;
+
+ for ( ; n < npages; n++, offset = 0) {
+ char *kaddr, *limit;
+ ext2_dirent *de;
+ struct page *page;
+
+ CDEBUG(D_EXT2,"read %lu of dir %lu/%u page %lu/%lu size %llu\n",
+ PAGE_CACHE_SIZE, inode->i_ino, inode->i_generation,
+ n, npages, inode->i_size);
+ page = ll_get_dir_page(inode, n);
+
+ /* size might have been updated by mdc_readpage */
+ npages = dir_pages(inode);
+
+ if (IS_ERR(page)) {
+ rc = PTR_ERR(page);
+ CERROR("error reading dir %lu/%u page %lu: rc %d\n",
+ inode->i_ino, inode->i_generation, n, rc);
+ continue;
+ }
+
+ kaddr = page_address(page);
+ if (need_revalidate) {
+ offset = ext2_validate_entry(kaddr, offset, chunk_mask);
+ need_revalidate = 0;
+ }
+ de = (ext2_dirent *)(kaddr+offset);
+ limit = kaddr + PAGE_CACHE_SIZE - EXT2_DIR_REC_LEN(1);
+ for ( ;(char*)de <= limit; de = ext2_next_entry(de)) {
+ if (de->inode) {
+ int over;
+ unsigned char d_type = DT_UNKNOWN;
+
+ rc = 0; /* no error if we return something */
+ if (types && de->file_type < EXT2_FT_MAX)
+ d_type = types[de->file_type];
+
+ offset = (char *)de - kaddr;
+ over = filldir(dirent, de->name, de->name_len,
+ (n<<PAGE_CACHE_SHIFT) | offset,
+ le32_to_cpu(de->inode), d_type);
+ if (over) {
+ ext2_put_page(page);
+ GOTO(done, rc);
+ }
+ }
+ }
+ ext2_put_page(page);
+ }
done:
- filp->f_pos = (n << PAGE_CACHE_SHIFT) | offset;
- filp->f_version = inode->i_version;
- UPDATE_ATIME(inode);
- return 0;
+ filp->f_pos = (n << PAGE_CACHE_SHIFT) | offset;
+ filp->f_version = inode->i_version;
+ update_atime(inode);
+ RETURN(rc);
}
-/*
- * ext2_find_entry()
- *
- * finds an entry in the specified directory with the wanted name. It
- * returns the page in which the entry was found, and the entry itself
- * (as a parameter - res_dir). Page is returned mapped and unlocked.
- * Entry is guaranteed to be valid.
- */
-struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
- struct dentry *dentry, struct page ** res_page)
-{
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
- unsigned reclen = EXT2_DIR_REC_LEN(namelen);
- unsigned long start, n;
- unsigned long npages = dir_pages(dir);
- struct page *page = NULL;
- ext2_dirent * de;
-
- /* OFFSET_CACHE */
- *res_page = NULL;
-
- // start = dir->u.ext2_i.i_dir_start_lookup;
- start = 0;
- if (start >= npages)
- start = 0;
- n = start;
- do {
- char *kaddr;
- page = ext2_get_page(dir, n);
- if (!IS_ERR(page)) {
- kaddr = page_address(page);
- de = (ext2_dirent *) kaddr;
- kaddr += PAGE_CACHE_SIZE - reclen;
- while ((char *) de <= kaddr) {
- if (ext2_match (namelen, name, de))
- goto found;
- de = ext2_next_entry(de);
- }
- ext2_put_page(page);
- }
- if (++n >= npages)
- n = 0;
- } while (n != start);
- return NULL;
-
-found:
- *res_page = page;
- // dir->u.ext2_i.i_dir_start_lookup = n;
- return de;
-}
-
-struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
-{
- struct page *page = ext2_get_page(dir, 0);
- ext2_dirent *de = NULL;
-
- if (!IS_ERR(page)) {
- de = ext2_next_entry((ext2_dirent *) page_address(page));
- *p = page;
- }
- return de;
-}
-
-ino_t ll_inode_by_name(struct inode * dir, struct dentry *dentry, int *type)
+static int ll_dir_ioctl(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long arg)
{
- ino_t res = 0;
- struct ext2_dir_entry_2 * de;
- struct page *page;
-
- de = ext2_find_entry (dir, dentry, &page);
- if (de) {
- res = le32_to_cpu(de->inode);
- *type = ll_dt2fmt[de->file_type];
- kunmap(page);
- page_cache_release(page);
- }
- return res;
-}
+ struct ll_sb_info *sbi = ll_i2sbi(inode);
+ struct obd_ioctl_data *data;
+ ENTRY;
-/* Releases the page */
-void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
- struct page *page, struct inode *inode)
-{
- unsigned from = (char *) de - (char *) page_address(page);
- unsigned to = from + le16_to_cpu(de->rec_len);
- int err;
-
- lock_page(page);
- err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
- if (err)
- BUG();
- de->inode = cpu_to_le32(inode->i_ino);
- ext2_set_de_type (de, inode);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- err = ext2_commit_chunk(page, from, to);
- UnlockPage(page);
- ext2_put_page(page);
-}
+ CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p), cmd=%#x\n",
+ inode->i_ino, inode->i_generation, inode, cmd);
+
+ if (_IOC_TYPE(cmd) == 'T') /* tty ioctls */
+ return -ENOTTY;
+
+ lprocfs_counter_incr(ll_i2sbi(inode)->ll_stats, LPROC_LL_IOCTL);
+ switch(cmd) {
+ case EXT3_IOC_GETFLAGS:
+ case EXT3_IOC_SETFLAGS:
+ RETURN(ll_iocontrol(inode, file, cmd, arg));
+ case IOC_MDC_LOOKUP: {
+ struct ptlrpc_request *request = NULL;
+ struct ll_fid fid;
+ char *buf = NULL;
+ char *filename;
+ int namelen, rc, len = 0;
+ unsigned long valid;
+
+ rc = obd_ioctl_getdata(&buf, &len, (void *)arg);
+ if (rc)
+ RETURN(rc);
+ data = (void *)buf;
+
+ filename = data->ioc_inlbuf1;
+ namelen = data->ioc_inllen1;
+
+ if (namelen < 1) {
+ CDEBUG(D_INFO, "IOC_MDC_LOOKUP missing filename\n");
+ GOTO(out, rc = -EINVAL);
+ }
+
+ valid = OBD_MD_FLID;
+ ll_inode2fid(&fid, inode);
+ rc = mdc_getattr_name(sbi->ll_mdc_exp, &fid,
+ filename, namelen, valid, 0, &request);
+ if (rc < 0) {
+ CDEBUG(D_INFO, "mdc_getattr_name: %d\n", rc);
+ GOTO(out, rc);
+ }
+
+ ptlrpc_req_finished(request);
-/*
- * Parent is locked.
- */
-int ll_add_link (struct dentry *dentry, struct inode *inode)
-{
- struct inode *dir = dentry->d_parent->d_inode;
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
- unsigned reclen = EXT2_DIR_REC_LEN(namelen);
- unsigned short rec_len, name_len;
- struct page *page = NULL;
- ext2_dirent * de;
- unsigned long npages = dir_pages(dir);
- unsigned long n;
- char *kaddr;
- unsigned from, to;
- int err;
-
- /* We take care of directory expansion in the same loop */
- for (n = 0; n <= npages; n++) {
- page = ext2_get_page(dir, n);
- err = PTR_ERR(page);
- if (IS_ERR(page))
- goto out;
- kaddr = page_address(page);
- de = (ext2_dirent *)kaddr;
- kaddr += PAGE_CACHE_SIZE - reclen;
- while ((char *)de <= kaddr) {
- err = -EEXIST;
- if (ext2_match (namelen, name, de))
- goto out_page;
- name_len = EXT2_DIR_REC_LEN(de->name_len);
- rec_len = le16_to_cpu(de->rec_len);
- if ( n==npages && rec_len == 0) {
- CERROR("Fatal dir behaviour\n");
- goto out_page;
- }
- if (!de->inode && rec_len >= reclen)
- goto got_it;
- if (rec_len >= name_len + reclen)
- goto got_it;
- de = (ext2_dirent *) ((char *) de + rec_len);
- }
- ext2_put_page(page);
- }
- BUG();
- return -EINVAL;
-
-got_it:
- from = (char*)de - (char*)page_address(page);
- to = from + rec_len;
- lock_page(page);
- err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
- if (err)
- goto out_unlock;
- if (de->inode) {
- ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len);
- de1->rec_len = cpu_to_le16(rec_len - name_len);
- de->rec_len = cpu_to_le16(name_len);
- de = de1;
- }
- de->name_len = namelen;
- memcpy (de->name, name, namelen);
- de->inode = cpu_to_le32(inode->i_ino);
- ext2_set_de_type (de, inode);
- CDEBUG(D_INODE, "type set to %o\n", de->file_type);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- err = ext2_commit_chunk(page, from, to);
-
- // change_inode happens with the commit_chunk
- /* XXX OFFSET_CACHE */
+ EXIT;
+ out:
+ obd_ioctl_freedata(buf, len);
+ return rc;
+ }
+ case LL_IOC_LOV_SETSTRIPE: {
+ struct ptlrpc_request *request = NULL;
+ struct mdc_op_data op_data;
+ struct iattr attr = { 0 };
+ struct lov_user_md lum, *lump = (struct lov_user_md *)arg;
+ int rc = 0;
+
+ ll_prepare_mdc_op_data(&op_data, inode, NULL, NULL, 0, 0);
+
+ LASSERT(sizeof(lum) == sizeof(*lump));
+ LASSERT(sizeof(lum.lmm_objects[0]) ==
+ sizeof(lump->lmm_objects[0]));
+ rc = copy_from_user(&lum, lump, sizeof(lum));
+ if (rc)
+ return(-EFAULT);
+
+ if (lum.lmm_magic != LOV_USER_MAGIC)
+ RETURN(-EINVAL);
+
+ rc = mdc_setattr(sbi->ll_mdc_exp, &op_data,
+ &attr, &lum, sizeof(lum), NULL, 0, &request);
+ if (rc) {
+ ptlrpc_req_finished(request);
+ if (rc != -EPERM && rc != -EACCES)
+ CERROR("mdc_setattr fails: rc = %d\n", rc);
+ return rc;
+ }
+ ptlrpc_req_finished(request);
+
+ return rc;
+ }
+ case LL_IOC_LOV_GETSTRIPE: {
+ struct ptlrpc_request *request = NULL;
+ struct lov_user_md *lump = (struct lov_user_md *)arg;
+ struct lov_mds_md *lmm;
+ struct ll_fid fid;
+ struct mds_body *body;
+ unsigned long valid = 0;
+ int rc, lmmsize;
+
+ valid |= OBD_MD_FLDIREA;
+
+ ll_inode2fid(&fid, inode);
+ rc = mdc_getattr(sbi->ll_mdc_exp, &fid, valid,
+ obd_size_diskmd(sbi->ll_osc_exp, NULL),
+ &request);
+ if (rc < 0) {
+ CDEBUG(D_INFO, "mdc_getattr failed: rc = %d\n", rc);
+ RETURN(rc);
+ }
+
+ body = lustre_msg_buf(request->rq_repmsg, 0, sizeof(*body));
+ LASSERT(body != NULL); /* checked by mdc_getattr_name */
+ LASSERT_REPSWABBED(request, 0);/* swabbed by mdc_getattr_name */
+
+ lmmsize = body->eadatasize;
+ if (lmmsize == 0)
+ GOTO(out_get, rc = -ENODATA);
+
+ lmm = lustre_msg_buf(request->rq_repmsg, 1, lmmsize);
+ LASSERT(lmm != NULL);
+ LASSERT_REPSWABBED(request, 1);
+ rc = copy_to_user(lump, lmm, lmmsize);
+ if (rc)
+ GOTO(out_get, rc = -EFAULT);
-out_unlock:
- UnlockPage(page);
-out_page:
- ext2_put_page(page);
-out:
- return err;
-}
+ EXIT;
+ out_get:
+ ptlrpc_req_finished(request);
+ RETURN(rc);
+ }
+ case IOC_MDC_GETSTRIPE: {
+ struct ptlrpc_request *request = NULL;
+ struct ll_fid fid;
+ struct mds_body *body;
+ struct lov_user_md *lump = (struct lov_user_md *)arg;
+ struct lov_mds_md *lmm;
+ char *filename;
+ int rc, lmmsize;
+
+ filename = getname((const char *)arg);
+ if (IS_ERR(filename))
+ RETURN(PTR_ERR(filename));
+
+ ll_inode2fid(&fid, inode);
+ rc = mdc_getattr_name(sbi->ll_mdc_exp, &fid, filename,
+ strlen(filename)+1, OBD_MD_FLEASIZE,
+ obd_size_diskmd(sbi->ll_osc_exp, NULL),
+ &request);
+ if (rc < 0) {
+ CDEBUG(D_INFO, "mdc_getattr_name failed on %s: rc %d\n",
+ filename, rc);
+ GOTO(out_name, rc);
+ }
+
+ body = lustre_msg_buf(request->rq_repmsg, 0, sizeof (*body));
+ LASSERT(body != NULL); /* checked by mdc_getattr_name */
+ LASSERT_REPSWABBED(request, 0);/* swabbed by mdc_getattr_name */
+
+ lmmsize = body->eadatasize;
+
+ if (!(body->valid & OBD_MD_FLEASIZE) || lmmsize == 0)
+ GOTO(out_req, rc = -ENODATA);
+
+ if (lmmsize > 4096)
+ GOTO(out_req, rc = -EFBIG);
+
+ lmm = lustre_msg_buf(request->rq_repmsg, 1, lmmsize);
+ LASSERT(lmm != NULL);
+ LASSERT_REPSWABBED(request, 1);
+
+ rc = copy_to_user(lump, lmm, lmmsize);
+ if (rc)
+ GOTO(out_req, rc = -EFAULT);
-/*
- * ext2_delete_entry deletes a directory entry by merging it with the
- * previous entry. Page is up-to-date. Releases the page.
- */
-int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
-{
- struct address_space *mapping = page->mapping;
- struct inode *inode = mapping->host;
- char *kaddr = page_address(page);
- unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
- unsigned to = ((char*)dir - kaddr) + le16_to_cpu(dir->rec_len);
- ext2_dirent * pde = NULL;
- ext2_dirent * de = (ext2_dirent *) (kaddr + from);
- int err;
-
- while ((char*)de < (char*)dir) {
- pde = de;
- de = ext2_next_entry(de);
- }
- if (pde)
- from = (char*)pde - (char*)page_address(page);
- lock_page(page);
- err = mapping->a_ops->prepare_write(NULL, page, from, to);
- if (err)
- BUG();
- if (pde)
- pde->rec_len = cpu_to_le16(to-from);
- dir->inode = 0;
- inode->i_ctime = inode->i_mtime = CURRENT_TIME;
- err = ext2_commit_chunk(page, from, to);
- UnlockPage(page);
- ext2_put_page(page);
- return err;
+ EXIT;
+ out_req:
+ ptlrpc_req_finished(request);
+ out_name:
+ putname(filename);
+ return rc;
+ }
+ case OBD_IOC_PING: {
+ struct ptlrpc_request *req = NULL;
+ char *buf = NULL;
+ int rc, len=0;
+ struct client_obd *cli;
+ struct obd_device *obd;
+
+ rc = obd_ioctl_getdata(&buf, &len, (void *)arg);
+ if (rc)
+ RETURN(rc);
+ data = (void *)buf;
+
+ obd = class_name2obd(data->ioc_inlbuf1);
+
+ if (!obd )
+ GOTO(out_ping, rc = -ENODEV);
+
+ if (!obd->obd_attached) {
+ CERROR("Device %d not attached\n", obd->obd_minor);
+ GOTO(out_ping, rc = -ENODEV);
+ }
+ if (!obd->obd_set_up) {
+ CERROR("Device %d still not setup\n", obd->obd_minor);
+ GOTO(out_ping, rc = -ENODEV);
+ }
+ cli = &obd->u.cli;
+ req = ptlrpc_prep_req(cli->cl_import, OBD_PING, 0, NULL, NULL);
+ if (!req)
+ GOTO(out_ping, rc = -ENOMEM);
+
+ req->rq_replen = lustre_msg_size(0, NULL);
+ req->rq_send_state = LUSTRE_IMP_FULL;
+
+ rc = ptlrpc_queue_wait(req);
+
+ ptlrpc_req_finished(req);
+ out_ping:
+ obd_ioctl_freedata(buf, len);
+ return rc;
+ }
+ case OBD_IOC_LLOG_CATINFO: {
+ struct ptlrpc_request *req = NULL;
+ char *buf = NULL;
+ int rc, len = 0;
+ char *bufs[2], *str;
+ int lens[2], size;
+
+ rc = obd_ioctl_getdata(&buf, &len, (void *)arg);
+ if (rc)
+ RETURN(rc);
+ data = (void *)buf;
+
+ if (!data->ioc_inlbuf1) {
+ obd_ioctl_freedata(buf, len);
+ RETURN(-EINVAL);
+ }
+
+ lens[0] = data->ioc_inllen1;
+ bufs[0] = data->ioc_inlbuf1;
+ if (data->ioc_inllen2) {
+ lens[1] = data->ioc_inllen2;
+ bufs[1] = data->ioc_inlbuf2;
+ } else {
+ lens[1] = 0;
+ bufs[1] = NULL;
+ }
+ size = data->ioc_plen1;
+ req = ptlrpc_prep_req(sbi2mdc(sbi)->cl_import, LLOG_CATINFO,
+ 2, lens, bufs);
+ if (!req)
+ GOTO(out_catinfo, rc = -ENOMEM);
+ req->rq_replen = lustre_msg_size(1, &size);
+
+ rc = ptlrpc_queue_wait(req);
+ str = lustre_msg_string(req->rq_repmsg, 0, data->ioc_plen1);
+ if (!rc)
+ rc = copy_to_user(data->ioc_pbuf1, str,
+ data->ioc_plen1);
+ ptlrpc_req_finished(req);
+ out_catinfo:
+ obd_ioctl_freedata(buf, len);
+ RETURN(rc);
+ }
+ default:
+ return obd_iocontrol(cmd, sbi->ll_osc_exp,0,NULL,(void *)arg);
+ }
}
-/*
- * Set the first fragment of directory.
- */
-int ext2_make_empty(struct inode *inode, struct inode *parent)
+int ll_dir_open(struct inode *inode, struct file *file)
{
- struct address_space *mapping = inode->i_mapping;
- struct page *page = grab_cache_page(mapping, 0);
- unsigned chunk_size = ext2_chunk_size(inode);
- struct ext2_dir_entry_2 * de;
- char *base;
- int err;
- ENTRY;
-
- if (!page)
- return -ENOMEM;
- err = mapping->a_ops->prepare_write(NULL, page, 0, chunk_size);
- if (err)
- goto fail;
-
- base = page_address(page);
-
- de = (struct ext2_dir_entry_2 *) base;
- de->name_len = 1;
- de->rec_len = cpu_to_le16(EXT2_DIR_REC_LEN(1));
- memcpy (de->name, ".\0\0", 4);
- de->inode = cpu_to_le32(inode->i_ino);
- ext2_set_de_type (de, inode);
-
- de = (struct ext2_dir_entry_2 *) (base + EXT2_DIR_REC_LEN(1));
- de->name_len = 2;
- de->rec_len = cpu_to_le16(chunk_size - EXT2_DIR_REC_LEN(1));
- de->inode = cpu_to_le32(parent->i_ino);
- memcpy (de->name, "..\0", 4);
- ext2_set_de_type (de, inode);
-
- err = ext2_commit_chunk(page, 0, chunk_size);
-fail:
- UnlockPage(page);
- page_cache_release(page);
- ENTRY;
- return err;
+ ENTRY;
+ RETURN(ll_file_open(inode, file));
}
-/*
- * routine to check that the specified directory is empty (for rmdir)
- */
-int ext2_empty_dir (struct inode * inode)
+int ll_dir_release(struct inode *inode, struct file *file)
{
- struct page *page = NULL;
- unsigned long i, npages = dir_pages(inode);
-
- for (i = 0; i < npages; i++) {
- char *kaddr;
- ext2_dirent * de;
- page = ext2_get_page(inode, i);
-
- if (IS_ERR(page))
- continue;
-
- kaddr = page_address(page);
- de = (ext2_dirent *)kaddr;
- kaddr += PAGE_CACHE_SIZE-EXT2_DIR_REC_LEN(1);
-
- while ((char *)de <= kaddr) {
- if (de->inode != 0) {
- /* check for . and .. */
- if (de->name[0] != '.')
- goto not_empty;
- if (de->name_len > 2)
- goto not_empty;
- if (de->name_len < 2) {
- if (de->inode !=
- cpu_to_le32(inode->i_ino))
- goto not_empty;
- } else if (de->name[1] != '.')
- goto not_empty;
- }
- de = ext2_next_entry(de);
- }
- ext2_put_page(page);
- }
- return 1;
-
-not_empty:
- ext2_put_page(page);
- return 0;
+ ENTRY;
+ RETURN(ll_file_release(inode, file));
}
struct file_operations ll_dir_operations = {
- read: generic_read_dir,
- readdir: new_ll_readdir
+ .open = ll_dir_open,
+ .release = ll_dir_release,
+ .read = generic_read_dir,
+ .readdir = ll_readdir,
+ .ioctl = ll_dir_ioctl
};
+