diff options
Diffstat (limited to 'fs')
102 files changed, 3832 insertions, 3108 deletions
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index eeb246845909..2341375386f8 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -297,20 +297,14 @@ static int validate_request(struct autofs_wait_queue **wait, */ if (notify == NFY_MOUNT) { /* - * If the dentry isn't hashed just go ahead and try the - * mount again with a new wait (not much else we can do). - */ - if (!d_unhashed(dentry)) { - /* - * But if the dentry is hashed, that means that we - * got here through the revalidate path. Thus, we - * need to check if the dentry has been mounted - * while we waited on the wq_mutex. If it has, - * simply return success. - */ - if (d_mountpoint(dentry)) - return 0; - } + * If the dentry was successfully mounted while we slept + * on the wait queue mutex we can return success. If it + * isn't mounted (doesn't have submounts for the case of + * a multi-mount with no mount at it's base) we can + * continue on and create a new request. + */ + if (have_submounts(dentry)) + return 0; } return 1; @@ -26,10 +26,9 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/blktrace_api.h> -#include <trace/block.h> #include <scsi/sg.h> /* for struct sg_iovec */ -DEFINE_TRACE(block_split); +#include <trace/events/block.h> /* * Test patch to inline a certain number of bi_io_vec's inside the bio @@ -499,11 +498,11 @@ int bio_get_nr_vecs(struct block_device *bdev) struct request_queue *q = bdev_get_queue(bdev); int nr_pages; - nr_pages = ((q->max_sectors << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (nr_pages > q->max_phys_segments) - nr_pages = q->max_phys_segments; - if (nr_pages > q->max_hw_segments) - nr_pages = q->max_hw_segments; + nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (nr_pages > queue_max_phys_segments(q)) + nr_pages = queue_max_phys_segments(q); + if (nr_pages > queue_max_hw_segments(q)) + nr_pages = queue_max_hw_segments(q); return nr_pages; } @@ -562,8 +561,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page * make this too complex. */ - while (bio->bi_phys_segments >= q->max_phys_segments - || bio->bi_phys_segments >= q->max_hw_segments) { + while (bio->bi_phys_segments >= queue_max_phys_segments(q) + || bio->bi_phys_segments >= queue_max_hw_segments(q)) { if (retried_segments) return 0; @@ -634,7 +633,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { - return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors); + return __bio_add_page(q, bio, page, len, offset, + queue_max_hw_sectors(q)); } /** @@ -654,7 +654,7 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - return __bio_add_page(q, bio, page, len, offset, q->max_sectors); + return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q)); } struct bio_map_data { @@ -721,7 +721,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs, while (bv_len && iov_idx < iov_count) { unsigned int bytes; - char *iov_addr; + char __user *iov_addr; bytes = min_t(unsigned int, iov[iov_idx].iov_len - iov_off, bv_len); @@ -1201,7 +1201,7 @@ static void bio_copy_kern_endio(struct bio *bio, int err) char *addr = page_address(bvec->bv_page); int len = bmd->iovecs[i].bv_len; - if (read && !err) + if (read) memcpy(p, addr, len); __free_page(bvec->bv_page); @@ -1490,11 +1490,12 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors) sector_t bio_sector_offset(struct bio *bio, unsigned short index, unsigned int offset) { - unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue); + unsigned int sector_sz; struct bio_vec *bv; sector_t sectors; int i; + sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue); sectors = 0; if (index >= bio->bi_idx) diff --git a/fs/block_dev.c b/fs/block_dev.c index f45dbc18dd17..931f6b8c4b2f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -25,6 +25,7 @@ #include <linux/uio.h> #include <linux/namei.h> #include <linux/log2.h> +#include <linux/kmemleak.h> #include <asm/uaccess.h> #include "internal.h" @@ -76,7 +77,7 @@ int set_blocksize(struct block_device *bdev, int size) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ - if (size < bdev_hardsect_size(bdev)) + if (size < bdev_logical_block_size(bdev)) return -EINVAL; /* Don't change the size if it is same as current */ @@ -106,7 +107,7 @@ EXPORT_SYMBOL(sb_set_blocksize); int sb_min_blocksize(struct super_block *sb, int size) { - int minsize = bdev_hardsect_size(sb->s_bdev); + int minsize = bdev_logical_block_size(sb->s_bdev); if (size < minsize) size = minsize; return sb_set_blocksize(sb, size); @@ -492,6 +493,11 @@ void __init bdev_cache_init(void) bd_mnt = kern_mount(&bd_type); if (IS_ERR(bd_mnt)) panic("Cannot create bdev pseudo-fs"); + /* + * This vfsmount structure is only used to obtain the + * blockdev_superblock, so tell kmemleak not to report it. + */ + kmemleak_not_leak(bd_mnt); blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ } @@ -1111,7 +1117,7 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { - unsigned bsize = bdev_hardsect_size(bdev); + unsigned bsize = bdev_logical_block_size(bdev); bdev->bd_inode->i_size = size; while (bsize < PAGE_CACHE_SIZE) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3e2c7c738f23..35af93355063 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2622,7 +2622,18 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, search_start); if (block_group && block_group_bits(block_group, data)) { down_read(&space_info->groups_sem); - goto have_block_group; + if (list_empty(&block_group->list) || + block_group->ro) { + /* + * someone is removing this block group, + * we can't jump into the have_block_group + * target because our list pointers are not + * valid + */ + btrfs_put_block_group(block_group); + up_read(&space_info->groups_sem); + } else + goto have_block_group; } else if (block_group) { btrfs_put_block_group(block_group); } @@ -2656,6 +2667,13 @@ have_block_group: * people trying to start a new cluster */ spin_lock(&last_ptr->refill_lock); + if (last_ptr->block_group && + (last_ptr->block_group->ro || + !block_group_bits(last_ptr->block_group, data))) { + offset = 0; + goto refill_cluster; + } + offset = btrfs_alloc_from_cluster(block_group, last_ptr, num_bytes, search_start); if (offset) { @@ -2681,10 +2699,17 @@ have_block_group: last_ptr_loop = 1; search_start = block_group->key.objectid; + /* + * we know this block group is properly + * in the list because + * btrfs_remove_block_group, drops the + * cluster before it removes the block + * group from the list + */ goto have_block_group; } spin_unlock(&last_ptr->lock); - +refill_cluster: /* * this cluster didn't work out, free it and * start over @@ -5968,6 +5993,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, { struct btrfs_path *path; struct btrfs_block_group_cache *block_group; + struct btrfs_free_cluster *cluster; struct btrfs_key key; int ret; @@ -5979,6 +6005,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, memcpy(&key, &block_group->key, sizeof(key)); + /* make sure this block group isn't part of an allocation cluster */ + cluster = &root->fs_info->data_alloc_cluster; + spin_lock(&cluster->refill_lock); + btrfs_return_cluster_to_free_space(block_group, cluster); + spin_unlock(&cluster->refill_lock); + + /* + * make sure this block group isn't part of a metadata + * allocation cluster + */ + cluster = &root->fs_info->meta_alloc_cluster; + spin_lock(&cluster->refill_lock); + btrfs_return_cluster_to_free_space(block_group, cluster); + spin_unlock(&cluster->refill_lock); + path = btrfs_alloc_path(); BUG_ON(!path); @@ -5988,7 +6029,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&root->fs_info->block_group_cache_lock); btrfs_remove_free_space_cache(block_group); down_write(&block_group->space_info->groups_sem); - list_del(&block_group->list); + /* + * we must use list_del_init so people can check to see if they + * are still on the list after taking the semaphore + */ + list_del_init(&block_group->list); up_write(&block_group->space_info->groups_sem); spin_lock(&block_group->space_info->lock); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5f01dad4b696..a6d35b0054ca 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1440,6 +1440,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) device->io_align = root->sectorsize; device->sector_size = root->sectorsize; device->total_bytes = i_size_read(bdev->bd_inode); + device->disk_total_bytes = device->total_bytes; device->dev_root = root->fs_info->dev_root; device->bdev = bdev; device->in_fs_metadata = 1; diff --git a/fs/buffer.c b/fs/buffer.c index aed297739eb0..a3ef091a45bd 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1085,12 +1085,12 @@ static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { /* Size must be multiple of hard sectorsize */ - if (unlikely(size & (bdev_hardsect_size(bdev)-1) || + if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); - printk(KERN_ERR "hardsect size: %d\n", - bdev_hardsect_size(bdev)); + printk(KERN_ERR "logical block size: %d\n", + bdev_logical_block_size(bdev)); dump_stack(); return NULL; @@ -2736,6 +2736,8 @@ has_buffers: pos += blocksize; } + map_bh.b_size = blocksize; + map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; @@ -2933,6 +2935,8 @@ int submit_bh(int rw, struct buffer_head * bh) BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); + BUG_ON(buffer_delay(bh)); + BUG_ON(buffer_unwritten(bh)); /* * Mask in barrier bit for a write (could be either a WRITE or a diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index f20c4069c220..b48689839428 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,12 @@ +Version 1.59 +------------ +Client uses server inode numbers (which are persistent) rather than +client generated ones by default (mount option "serverino" turned +on by default if server supports it). Add forceuid and forcegid +mount options (so that when negotiating unix extensions specifying +which uid mounted does not immediately force the server's reported +uids to be overridden). + Version 1.58 ------------ Guard against buffer overruns in various UCS-2 to UTF-8 string conversions @@ -10,6 +19,8 @@ we converted from). Fix endianness of the vcnum field used during session setup to distinguish multiple mounts to same server from different userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental flag to be set to 2, and mount must enable krb5 to turn on extended security). +Performance of file create to Samba improved (posix create on lookup +removes 1 of 2 network requests sent on file create) Version 1.57 ------------ diff --git a/fs/cifs/README b/fs/cifs/README index db208ddb9899..ad92921dbde4 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -262,7 +262,8 @@ A partial list of the supported mount options follows: mount. domain Set the SMB/CIFS workgroup name prepended to the username during CIFS session establishment - uid Set the default uid for inodes. For mounts to servers + forceuid Set the default uid for inodes based on the uid + passed in. For mounts to servers which do support the CIFS Unix extensions, such as a properly configured Samba server, the server provides the uid, gid and mode so this parameter should not be @@ -292,6 +293,12 @@ A partial list of the supported mount options follows: the client. Note that the mount.cifs helper must be at version 1.10 or higher to support specifying the uid (or gid) in non-numeric form. + forcegid (similar to above but for the groupid instead of uid) + uid Set the default uid for inodes, and indicate to the + cifs kernel driver which local user mounted . If the server + supports the unix extensions the default uid is + not used to fill in the owner fields of inodes (files) + unless the "forceuid" parameter is specified. gid Set the default gid for inodes (similar to above). file_mode If CIFS Unix extensions are not supported by the server this overrides the default mode for file inodes. @@ -388,8 +395,13 @@ A partial list of the supported mount options follows: or the CIFS Unix Extensions equivalent and for those this mount option will have no effect. Exporting cifs mounts under nfsd requires this mount option on the cifs mount. + This is now the default if server supports the + required network operation. noserverino Client generates inode numbers (rather than using the actual one - from the server) by default. + from the server). These inode numbers will vary after + unmount or reboot which can confuse some applications, + but not all server filesystems support unique inode + numbers. setuids If the CIFS Unix extensions are negotiated with the server the client will attempt to set the effective uid and gid of the local process on newly created files, directories, and diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 67bf93a40d2e..4a4581cb2b5e 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -23,6 +23,7 @@ #include <linux/string.h> #include <keys/user-type.h> #include <linux/key-type.h> +#include <linux/inet.h> #include "cifsglob.h" #include "cifs_spnego.h" #include "cifs_debug.h" @@ -73,9 +74,6 @@ struct key_type cifs_spnego_key_type = { * strlen(";sec=ntlmsspi") */ #define MAX_MECH_STR_LEN 13 -/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/128 */ -#define MAX_IPV6_ADDR_LEN 43 - /* strlen of "host=" */ #define HOST_KEY_LEN 5 @@ -102,7 +100,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) host=hostname sec=mechanism uid=0xFF user=username */ desc_len = MAX_VER_STR_LEN + HOST_KEY_LEN + strlen(hostname) + - IP_KEY_LEN + MAX_IPV6_ADDR_LEN + + IP_KEY_LEN + INET6_ADDRSTRLEN + MAX_MECH_STR_LEN + UID_KEY_LEN + (sizeof(uid_t) * 2) + USER_KEY_LEN + strlen(sesInfo->userName) + 1; diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 57ecdc83c26f..1403b5d86a73 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -552,130 +552,138 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, return rc; } - -/* Retrieve an ACL from the server */ -static struct cifs_ntsd *get_cifs_acl(u32 *pacllen, struct inode *inode, - const char *path, const __u16 *pfid) +static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, + __u16 fid, u32 *pacllen) { - struct cifsFileInfo *open_file = NULL; - bool unlock_file = false; - int xid; - int rc = -EIO; - __u16 fid; - struct super_block *sb; - struct cifs_sb_info *cifs_sb; struct cifs_ntsd *pntsd = NULL; + int xid, rc; + + xid = GetXid(); + rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen); + FreeXid(xid); - cFYI(1, ("get mode from ACL for %s", path)); - if (inode == NULL) - return NULL; + cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen)); + return pntsd; +} + +static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, + const char *path, u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + int oplock = 0; + int xid, rc; + __u16 fid; xid = GetXid(); - if (pfid == NULL) - open_file = find_readable_file(CIFS_I(inode)); - else - fid = *pfid; - sb = inode->i_sb; - if (sb == NULL) { - FreeXid(xid); - return NULL; - } - cifs_sb = CIFS_SB(sb); - - if (open_file) { - unlock_file = true; - fid = open_file->netfid; - } else if (pfid == NULL) { - int oplock = 0; - /* open file */ - rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, - READ_CONTROL, 0, &fid, &oplock, NULL, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc != 0) { - cERROR(1, ("Unable to open file to get ACL")); - FreeXid(xid); - return NULL; - } + rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, READ_CONTROL, 0, + &fid, &oplock, NULL, cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc) { + cERROR(1, ("Unable to open file to get ACL")); + goto out; } rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen); cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen)); - if (unlock_file == true) /* find_readable_file increments ref count */ - atomic_dec(&open_file->wrtPending); - else if (pfid == NULL) /* if opened above we have to close the handle */ - CIFSSMBClose(xid, cifs_sb->tcon, fid); - /* else handle was passed in by caller */ + CIFSSMBClose(xid, cifs_sb->tcon, fid); + out: FreeXid(xid); return pntsd; } -/* Set an ACL on the server */ -static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, - struct inode *inode, const char *path) +/* Retrieve an ACL from the server */ +static struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, + struct inode *inode, const char *path, + u32 *pacllen) { - struct cifsFileInfo *open_file; - bool unlock_file = false; - int xid; - int rc = -EIO; - __u16 fid; - struct super_block *sb; - struct cifs_sb_info *cifs_sb; + struct cifs_ntsd *pntsd = NULL; + struct cifsFileInfo *open_file = NULL; - cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode)); + if (inode) + open_file = find_readable_file(CIFS_I(inode)); + if (!open_file) + return get_cifs_acl_by_path(cifs_sb, path, pacllen); - if (!inode) - return rc; + pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->netfid, pacllen); + atomic_dec(&open_file->wrtPending); + return pntsd; +} - sb = inode->i_sb; - if (sb == NULL) - return rc; +static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid, + struct cifs_ntsd *pnntsd, u32 acllen) +{ + int xid, rc; - cifs_sb = CIFS_SB(sb); xid = GetXid(); + rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen); + FreeXid(xid); - open_file = find_readable_file(CIFS_I(inode)); - if (open_file) { - unlock_file = true; - fid = open_file->netfid; - } else { - int oplock = 0; - /* open file */ - rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, - WRITE_DAC, 0, &fid, &oplock, NULL, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc != 0) { - cERROR(1, ("Unable to open file to set ACL")); - FreeXid(xid); - return rc; - } + cFYI(DBG2, ("SetCIFSACL rc = %d", rc)); + return rc; +} + +static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path, + struct cifs_ntsd *pnntsd, u32 acllen) +{ + int oplock = 0; + int xid, rc; + __u16 fid; + + xid = GetXid(); + + rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, WRITE_DAC, 0, + &fid, &oplock, NULL, cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc) { + cERROR(1, ("Unable to open file to set ACL")); + goto out; } rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen); cFYI(DBG2, ("SetCIFSACL rc = %d", rc)); - if (unlock_file) - atomic_dec(&open_file->wrtPending); - else - CIFSSMBClose(xid, cifs_sb->tcon, fid); + CIFSSMBClose(xid, cifs_sb->tcon, fid); + out: FreeXid(xid); + return rc; +} +/* Set an ACL on the server */ +static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, + struct inode *inode, const char *path) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsFileInfo *open_file; + int rc; + + cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode)); + + open_file = find_readable_file(CIFS_I(inode)); + if (!open_file) + return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen); + + rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen); + atomic_dec(&open_file->wrtPending); return rc; } /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */ -void acl_to_uid_mode(struct inode *inode, const char *path, const __u16 *pfid) +void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode, + const char *path, const __u16 *pfid) { struct cifs_ntsd *pntsd = NULL; u32 acllen = 0; int rc = 0; cFYI(DBG2, ("converting ACL to mode for %s", path)); - pntsd = get_cifs_acl(&acllen, inode, path, pfid); + + if (pfid) + pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen); + else + pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen); /* if we can retrieve the ACL, now parse Access Control Entries, ACEs */ if (pntsd) @@ -698,7 +706,7 @@ int mode_to_acl(struct inode *inode, const char *path, __u64 nmode) cFYI(DBG2, ("set ACL from mode for %s", path)); /* Get the security descriptor */ - pntsd = get_cifs_acl(&secdesclen, inode, path, NULL); + pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen); /* Add three ACEs for owner, group, everyone getting rid of other ACEs as chmod disables ACEs and set the security descriptor */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5e6d35804d73..0a10a59b6392 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -146,7 +146,7 @@ cifs_read_super(struct super_block *sb, void *data, #endif sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ - inode = cifs_iget(sb, ROOT_I); + inode = cifs_root_iget(sb, ROOT_I); if (IS_ERR(inode)) { rc = PTR_ERR(inode); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 051b71cfdea9..9570a0e8023f 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -36,7 +36,7 @@ extern void cifs_read_inode(struct inode *); /* Functions related to inodes */ extern const struct inode_operations cifs_dir_inode_ops; -extern struct inode *cifs_iget(struct super_block *, unsigned long); +extern struct inode *cifs_root_iget(struct super_block *, unsigned long); extern int cifs_create(struct inode *, struct dentry *, int, struct nameidata *); extern struct dentry *cifs_lookup(struct inode *, struct dentry *, @@ -100,5 +100,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* EXPERIMENTAL */ -#define CIFS_VERSION "1.58" +#define CIFS_VERSION "1.59" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index fae083930eee..f9452329bcce 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -90,10 +90,10 @@ extern struct oplock_q_entry *AllocOplockQEntry(struct inode *, u16, struct cifsTconInfo *); extern void DeleteOplockQEntry(struct oplock_q_entry *); extern void DeleteTconOplockQEntries(struct cifsTconInfo *); -extern struct timespec cifs_NTtimeToUnix(u64 utc_nanoseconds_since_1601); +extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601); extern u64 cifs_UnixTimeToNT(struct timespec); -extern __le64 cnvrtDosCifsTm(__u16 date, __u16 time); -extern struct timespec cnvrtDosUnixTm(__u16 date, __u16 time); +extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, + int offset); extern int cifs_posix_open(char *full_path, struct inode **pinode, struct super_block *sb, int mode, int oflags, @@ -108,8 +108,8 @@ extern int cifs_get_inode_info(struct inode **pinode, extern int cifs_get_inode_info_unix(struct inode **pinode, const unsigned char *search_path, struct super_block *sb, int xid); -extern void acl_to_uid_mode(struct inode *inode, const char *path, - const __u16 *pfid); +extern void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode, + const char *path, const __u16 *pfid); extern int mode_to_acl(struct inode *inode, const char *path, __u64); extern int cifs_mount(struct super_block *, struct cifs_sb_info *, char *, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index d06260251c30..b84c61d5bca4 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -524,8 +524,8 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) int val, seconds, remain, result; struct timespec ts, utc; utc = CURRENT_TIME; - ts = cnvrtDosUnixTm(le16_to_cpu(rsp->SrvTime.Date), - le16_to_cpu(rsp->SrvTime.Time)); + ts = cnvrtDosUnixTm(rsp->SrvTime.Date, + rsp->SrvTime.Time, 0); cFYI(1, ("SrvTime %d sec since 1970 (utc: %d) diff: %d", (int)ts.tv_sec, (int)utc.tv_sec, (int)(utc.tv_sec - ts.tv_sec))); @@ -2427,8 +2427,7 @@ querySymLinkRetry: params = 2 /* level */ + 4 /* rsrvd */ + name_len /* incl null */ ; pSMB->TotalDataCount = 0; pSMB->MaxParameterCount = cpu_to_le16(2); - /* BB find exact max data count below from sess structure BB */ - pSMB->MaxDataCount = cpu_to_le16(4000); + pSMB->MaxDataCount = cpu_to_le16(CIFSMaxBufSize); pSMB->MaxSetupCount = 0; pSMB->Reserved = 0; pSMB->Flags = 0; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 4aa81a507b74..97f4311b9a8e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -35,6 +35,7 @@ #include <linux/namei.h> #include <asm/uaccess.h> #include <asm/processor.h> +#include <linux/inet.h> #include <net/ipv6.h> #include "cifspdu.h" #include "cifsglob.h" @@ -61,7 +62,6 @@ struct smb_vol { char *domainname; char *UNC; char *UNCip; - char *in6_addr; /* ipv6 address as human readable form of in6_addr */ char *iocharset; /* local code page for mapping to and from Unicode */ char source_rfc1001_name[16]; /* netbios name of client */ char target_rfc1001_name[16]; /* netbios name of server for Win9x/ME */ @@ -827,14 +827,16 @@ cifs_parse_mount_options(char *options, const char *devname, vol->target_rfc1001_name[0] = 0; vol->linux_uid = current_uid(); /* use current_euid() instead? */ vol->linux_gid = current_gid(); - vol->dir_mode = S_IRWXUGO; - /* 2767 perms indicate mandatory locking support */ - vol->file_mode = (S_IRWXUGO | S_ISGID) & (~S_IXGRP); + + /* default to only allowing write access to owner of the mount */ + vol->dir_mode = vol->file_mode = S_IRUGO | S_IXUGO | S_IWUSR; /* vol->retry default is 0 (i.e. "soft" limited retry not hard retry) */ vol->rw = true; /* default is always to request posix paths. */ vol->posix_paths = 1; + /* default to using server inode numbers where available */ + vol->server_ino = 1; if (!options) return 1; @@ -955,10 +957,12 @@ cifs_parse_mount_options(char *options, const char *devname, } strcpy(vol->password, value); } - } else if (strnicmp(data, "ip", 2) == 0) { + } else if (!strnicmp(data, "ip", 2) || + !strnicmp(data, "addr", 4)) { if (!value || !*value) { vol->UNCip = NULL; - } else if (strnlen(value, 35) < 35) { + } else if (strnlen(value, INET6_ADDRSTRLEN) < + INET6_ADDRSTRLEN) { vol->UNCip = value; } else { printk(KERN_WARNING "CIFS: ip address " @@ -1092,17 +1096,17 @@ cifs_parse_mount_options(char *options, const char *devname, return 1; } } else if (strnicmp(data, "uid", 3) == 0) { - if (value && *value) { + if (value && *value) vol->linux_uid = simple_strtoul(value, &value, 0); + } else if (strnicmp(data, "forceuid", 8) == 0) { vol->override_uid = 1; - } } else if (strnicmp(data, "gid", 3) == 0) { - if (value && *value) { + if (value && *value) vol->linux_gid = simple_strtoul(value, &value, 0); + } else if (strnicmp(data, "forcegid", 8) == 0) { vol->override_gid = 1; - } } else if (strnicmp(data, "file_mode", 4) == 0) { if (value && *value) { vol->file_mode = @@ -1315,16 +1319,6 @@ cifs_parse_mount_options(char *options, const char *devname, vol->direct_io = 1; } else if (strnicmp(data, "forcedirectio", 13) == 0) { vol->direct_io = 1; - } else if (strnicmp(data, "in6_addr", 8) == 0) { - if (!value || !*value) { - vol->in6_addr = NULL; - } else if (strnlen(value, 49) == 48) { - vol->in6_addr = value; - } else { - printk(KERN_WARNING "CIFS: ip v6 address not " - "48 characters long\n"); - return 1; - } } else if (strnicmp(data, "noac", 4) == 0) { printk(KERN_WARNING "CIFS: Mount option noac not " "supported. Instead set " diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 302ea15f02e6..06866841b97f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -241,7 +241,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file, /* BB need same check in cifs_create too? */ /* if not oplocked, invalidate inode pages if mtime or file size changed */ - temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime)); + temp = cifs_NTtimeToUnix(buf->LastWriteTime); if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) && (file->f_path.dentry->d_inode->i_size == (loff_t)le64_to_cpu(buf->EndOfFile))) { diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9c869a6dcba1..fad882b075ba 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -85,10 +85,10 @@ static void cifs_unix_info_to_inode(struct inode *inode, __u64 num_of_bytes = le64_to_cpu(info->NumOfBytes); __u64 end_of_file = le64_to_cpu(info->EndOfFile); - inode->i_atime = cifs_NTtimeToUnix(le64_to_cpu(info->LastAccessTime)); + inode->i_atime = cifs_NTtimeToUnix(info->LastAccessTime); inode->i_mtime = - cifs_NTtimeToUnix(le64_to_cpu(info->LastModificationTime)); - inode->i_ctime = cifs_NTtimeToUnix(le64_to_cpu(info->LastStatusChange)); + cifs_NTtimeToUnix(info->LastModificationTime); + inode->i_ctime = cifs_NTtimeToUnix(info->LastStatusChange); inode->i_mode = le64_to_cpu(info->Permissions); /* @@ -554,14 +554,11 @@ int cifs_get_inode_info(struct inode **pinode, /* Linux can not store file creation time so ignore it */ if (pfindData->LastAccessTime) - inode->i_atime = cifs_NTtimeToUnix - (le64_to_cpu(pfindData->LastAccessTime)); + inode->i_atime = cifs_NTtimeToUnix(pfindData->LastAccessTime); else /* do not need to use current_fs_time - time not stored */ inode->i_atime = CURRENT_TIME; - inode->i_mtime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime)); - inode->i_ctime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime)); + inode->i_mtime = cifs_NTtimeToUnix(pfindData->LastWriteTime); + inode->i_ctime = cifs_NTtimeToUnix(pfindData->ChangeTime); cFYI(DBG2, ("Attributes came in as 0x%x", attr)); if (adjustTZ && (pTcon->ses) && (pTcon->ses->server)) { inode->i_ctime.tv_sec += pTcon->ses->server->timeAdj; @@ -629,7 +626,7 @@ int cifs_get_inode_info(struct inode **pinode, /* fill in 0777 bits from ACL */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { cFYI(1, ("Getting mode bits from ACL")); - acl_to_uid_mode(inode, full_path, pfid); + acl_to_uid_mode(cifs_sb, inode, full_path, pfid); } #endif if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { @@ -699,7 +696,7 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb) } /* gets root inode */ -struct inode *cifs_iget(struct super_block *sb, unsigned long ino) +struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) { int xid; struct cifs_sb_info *cifs_sb; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index e2fe998989a3..32d6baa0a54f 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -853,12 +853,12 @@ smbCalcSize_LE(struct smb_hdr *ptr) #define NTFS_TIME_OFFSET ((u64)(369*365 + 89) * 24 * 3600 * 10000000) - /* - * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units) - * into Unix UTC (based 1970-01-01, in seconds). - */ +/* + * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units) + * into Unix UTC (based 1970-01-01, in seconds). + */ struct timespec -cifs_NTtimeToUnix(u64 ntutc) +cifs_NTtimeToUnix(__le64 ntutc) { struct timespec ts; /* BB what about the timezone? BB */ @@ -866,7 +866,7 @@ cifs_NTtimeToUnix(u64 ntutc) /* Subtract the NTFS time offset, then convert to 1s intervals. */ u64 t; - t = ntutc - NTFS_TIME_OFFSET; + t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET; ts.tv_nsec = do_div(t, 10000000) * 100; ts.tv_sec = t; return ts; @@ -883,16 +883,12 @@ cifs_UnixTimeToNT(struct timespec t) static int total_days_of_prev_months[] = {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334}; - -__le64 cnvrtDosCifsTm(__u16 date, __u16 time) -{ - return cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(date, time))); -} - -struct timespec cnvrtDosUnixTm(__u16 date, __u16 time) +struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset) { struct timespec ts; int sec, min, days, month, year; + u16 date = le16_to_cpu(le_date); + u16 time = le16_to_cpu(le_time); SMB_TIME *st = (SMB_TIME *)&time; SMB_DATE *sd = (SMB_DATE *)&date; @@ -933,7 +929,7 @@ struct timespec cnvrtDosUnixTm(__u16 date, __u16 time) days -= ((year & 0x03) == 0) && (month < 2 ? 1 : 0); sec += 24 * 60 * 60 * days; - ts.tv_sec = sec; + ts.tv_sec = sec + offset; /* cFYI(1,("sec after cnvrt dos to unix time %d",sec)); */ diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 964e097c8203..86d0055dc529 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -115,17 +115,6 @@ construct_dentry(struct qstr *qstring, struct file *file, return rc; } -static void AdjustForTZ(struct cifsTconInfo *tcon, struct inode *inode) -{ - if ((tcon) && (tcon->ses) && (tcon->ses->server)) { - inode->i_ctime.tv_sec += tcon->ses->server->timeAdj; - inode->i_mtime.tv_sec += tcon->ses->server->timeAdj; - inode->i_atime.tv_sec += tcon->ses->server->timeAdj; - } - return; -} - - static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, char *buf, unsigned int *pobject_type, int isNewInode) { @@ -150,26 +139,25 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, allocation_size = le64_to_cpu(pfindData->AllocationSize); end_of_file = le64_to_cpu(pfindData->EndOfFile); tmp_inode->i_atime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime)); + cifs_NTtimeToUnix(pfindData->LastAccessTime); tmp_inode->i_mtime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime)); + cifs_NTtimeToUnix(pfindData->LastWriteTime); tmp_inode->i_ctime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime)); + cifs_NTtimeToUnix(pfindData->ChangeTime); } else { /* legacy, OS2 and DOS style */ -/* struct timespec ts;*/ + int offset = cifs_sb->tcon->ses->server->timeAdj; FIND_FILE_STANDARD_INFO *pfindData = (FIND_FILE_STANDARD_INFO *)buf; - tmp_inode->i_mtime = cnvrtDosUnixTm( - le16_to_cpu(pfindData->LastWriteDate), - le16_to_cpu(pfindData->LastWriteTime)); - tmp_inode->i_atime = cnvrtDosUnixTm( - le16_to_cpu(pfindData->LastAccessDate), - le16_to_cpu(pfindData->LastAccessTime)); - tmp_inode->i_ctime = cnvrtDosUnixTm( - le16_to_cpu(pfindData->LastWriteDate), - le16_to_cpu(pfindData->LastWriteTime)); - AdjustForTZ(cifs_sb->tcon, tmp_inode); + tmp_inode->i_mtime = cnvrtDosUnixTm(pfindData->LastWriteDate, + pfindData->LastWriteTime, + offset); + tmp_inode->i_atime = cnvrtDosUnixTm(pfindData->LastAccessDate, + pfindData->LastAccessTime, + offset); + tmp_inode->i_ctime = cnvrtDosUnixTm(pfindData->LastWriteDate, + pfindData->LastWriteTime, + offset); attr = le16_to_cpu(pfindData->Attributes); allocation_size = le32_to_cpu(pfindData->AllocationSize); end_of_file = le32_to_cpu(pfindData->DataSize); @@ -331,11 +319,11 @@ static void unix_fill_in_inode(struct inode *tmp_inode, local_size = tmp_inode->i_size; tmp_inode->i_atime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime)); + cifs_NTtimeToUnix(pfindData->LastAccessTime); tmp_inode->i_mtime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastModificationTime)); + cifs_NTtimeToUnix(pfindData->LastModificationTime); tmp_inode->i_ctime = - cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastStatusChange)); + cifs_NTtimeToUnix(pfindData->LastStatusChange); tmp_inode->i_mode = le64_to_cpu(pfindData->Permissions); /* since we set the inode type below we need to mask off type diff --git a/fs/coda/file.c b/fs/coda/file.c index 6a347fbc998a..ffd42815fda1 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -47,6 +47,8 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos, struct pipe_inode_info *pipe, size_t count, unsigned int flags) { + ssize_t (*splice_read)(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); struct coda_file_info *cfi; struct file *host_file; @@ -54,10 +56,11 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos, BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); host_file = cfi->cfi_container; - if (!host_file->f_op || !host_file->f_op->splice_read) - return -EINVAL; + splice_read = host_file->f_op->splice_read; + if (!splice_read) + splice_read = default_file_splice_read; - return host_file->f_op->splice_read(host_file, ppos, pipe, count,flags); + return splice_read(host_file, ppos, pipe, count, flags); } static ssize_t diff --git a/fs/compat.c b/fs/compat.c index 681ed81e6be0..bb2a9b2e8173 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1488,7 +1488,7 @@ int compat_do_execve(char * filename, if (!bprm) goto out_files; - retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + retval = mutex_lock_interruptible(¤t->cred_guard_mutex); if (retval < 0) goto out_free; current->in_execve = 1; @@ -1550,7 +1550,7 @@ int compat_do_execve(char * filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; - mutex_unlock(¤t->cred_exec_mutex); + mutex_unlock(¤t->cred_guard_mutex); acct_update_integrals(current); free_bprm(bprm); if (displaced) @@ -1573,7 +1573,7 @@ out_unmark: out_unlock: current->in_execve = 0; - mutex_unlock(¤t->cred_exec_mutex); + mutex_unlock(¤t->cred_guard_mutex); out_free: free_bprm(bprm); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c68edb969441..9b1d285f9fe6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -557,8 +557,10 @@ static int __init init_devpts_fs(void) int err = register_filesystem(&devpts_fs_type); if (!err) { devpts_mnt = kern_mount(&devpts_fs_type); - if (IS_ERR(devpts_mnt)) + if (IS_ERR(devpts_mnt)) { err = PTR_ERR(devpts_mnt); + unregister_filesystem(&devpts_fs_type); + } } return err; } diff --git a/fs/direct-io.c b/fs/direct-io.c index 05763bbc2050..8b10b87dc01a 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1127,7 +1127,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, rw = WRITE_ODIRECT; if (bdev) - bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev)); + bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev)); if (offset & blocksize_mask) { if (bdev) diff --git a/fs/exec.c b/fs/exec.c index 895823d0149d..e639957d7a57 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> +#include <linux/perf_counter.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> @@ -922,6 +923,7 @@ void set_task_comm(struct task_struct *tsk, char *buf) task_lock(tsk); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); + perf_counter_comm(tsk); } int flush_old_exec(struct linux_binprm * bprm) @@ -990,6 +992,13 @@ int flush_old_exec(struct linux_binprm * bprm) current->personality &= ~bprm->per_clear; + /* + * Flush performance counters when crossing a + * security domain: + */ + if (!get_dumpable(current->mm)) + perf_counter_exit_task(current); + /* An exec changes our domain. We are no longer part of the thread group */ @@ -1016,7 +1025,7 @@ void install_exec_creds(struct linux_binprm *bprm) commit_creds(bprm->cred); bprm->cred = NULL; - /* cred_exec_mutex must be held at least to this point to prevent + /* cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked */ @@ -1026,7 +1035,7 @@ EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program - * - the caller must hold current->cred_exec_mutex to protect against + * - the caller must hold current->cred_guard_mutex to protect against * PTRACE_ATTACH */ int check_unsafe_exec(struct linux_binprm *bprm) @@ -1268,7 +1277,7 @@ int do_execve(char * filename, if (!bprm) goto out_files; - retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + retval = mutex_lock_interruptible(¤t->cred_guard_mutex); if (retval < 0) goto out_free; current->in_execve = 1; @@ -1331,7 +1340,7 @@ int do_execve(char * filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; - mutex_unlock(¤t->cred_exec_mutex); + mutex_unlock(¤t->cred_guard_mutex); acct_update_integrals(current); free_bprm(bprm); if (displaced) @@ -1354,7 +1363,7 @@ out_unmark: out_unlock: current->in_execve = 0; - mutex_unlock(¤t->cred_exec_mutex); + mutex_unlock(¤t->cred_guard_mutex); out_free: free_bprm(bprm); diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c index b249ae97fb15..06ca92672eb5 100644 --- a/fs/exofs/osd.c +++ b/fs/exofs/osd.c @@ -50,10 +50,10 @@ int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid) /* FIXME: should be include in osd_sense_info */ if (in_resid) - *in_resid = or->in.req ? or->in.req->data_len : 0; + *in_resid = or->in.req ? or->in.req->resid_len : 0; if (out_resid) - *out_resid = or->out.req ? or->out.req->data_len : 0; + *out_resid = or->out.req ? or->out.req->resid_len : 0; return ret; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 5c4afe652245..e3c748faf2db 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1093,6 +1093,7 @@ failed_mount: brelse(bh); failed_sbi: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); return ret; } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 599dbfe504c3..3c70d52afb10 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1696,7 +1696,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount; } - hblock = bdev_hardsect_size(sb->s_bdev); + hblock = bdev_logical_block_size(sb->s_bdev); if (sb->s_blocksize != blocksize) { /* * Make sure the blocksize for the filesystem is larger @@ -2021,6 +2021,7 @@ failed_mount: brelse(bh); out_fail: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); return ret; @@ -2119,7 +2120,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, } blocksize = sb->s_blocksize; - hblock = bdev_hardsect_size(bdev); + hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { printk(KERN_ERR "EXT3-fs: blocksize too small for journal device.\n"); diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index a8ff003a00f7..8a34710ecf40 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -5,8 +5,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ - ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o migrate.o mballoc.o + ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ + ext4_jbd2.o migrate.o mballoc.o block_validity.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 53c72ad85877..e2126d70dff5 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -19,7 +19,6 @@ #include <linux/buffer_head.h> #include "ext4.h" #include "ext4_jbd2.h" -#include "group.h" #include "mballoc.h" /* @@ -88,6 +87,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) { int bit, bit_max; + ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned free_blocks, group_blocks; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -123,7 +123,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, bit_max += ext4_bg_num_gdb(sb, block_group); } - if (block_group == sbi->s_groups_count - 1) { + if (block_group == ngroups - 1) { /* * Even though mke2fs always initialize first and last group * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need @@ -131,7 +131,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ group_blocks = ext4_blocks_count(sbi->s_es) - le32_to_cpu(sbi->s_es->s_first_data_block) - - (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1)); + (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1)); } else { group_blocks = EXT4_BLOCKS_PER_GROUP(sb); } @@ -205,18 +205,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, { unsigned int group_desc; unsigned int offset; + ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (block_group >= sbi->s_groups_count) { + if (block_group >= ngroups) { ext4_error(sb, "ext4_get_group_desc", "block_group >= groups_count - " "block_group = %u, groups_count = %u", - block_group, sbi->s_groups_count); + block_group, ngroups); return NULL; } - smp_rmb(); group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); @@ -326,16 +326,16 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -451,7 +451,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, down_write(&grp->alloc_sem); for (i = 0, blocks_freed = 0; i < count; i++) { BUFFER_TRACE(bitmap_bh, "clear bit"); - if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), + if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group), bit + i, bitmap_bh->b_data)) { ext4_error(sb, __func__, "bit already cleared for block %llu", @@ -461,11 +461,11 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, blocks_freed++; } } - spin_lock(sb_bgl_lock(sbi, block_group)); + ext4_lock_group(sb, block_group); blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc); ext4_free_blks_set(sb, desc, blk_free_count); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed); if (sbi->s_log_groups_per_flex) { @@ -665,7 +665,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) ext4_fsblk_t desc_count; struct ext4_group_desc *gdp; ext4_group_t i; - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; ext4_fsblk_t bitmap_count; @@ -677,7 +677,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) bitmap_count = 0; gdp = NULL; - smp_rmb(); for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) @@ -700,7 +699,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) return bitmap_count; #else desc_count = 0; - smp_rmb(); for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c new file mode 100644 index 000000000000..50784ef07563 --- /dev/null +++ b/fs/ext4/block_validity.c @@ -0,0 +1,244 @@ +/* + * linux/fs/ext4/block_validity.c + * + * Copyright (C) 2009 + * Theodore Ts'o (tytso@mit.edu) + * + * Track which blocks in the filesystem are metadata blocks that + * should never be used as data blocks by files or directories. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/quotaops.h> +#include <linux/buffer_head.h> +#include <linux/module.h> +#include <linux/swap.h> +#include <linux/pagemap.h> +#include <linux/version.h> +#include <linux/blkdev.h> +#include <linux/mutex.h> +#include "ext4.h" + +struct ext4_system_zone { + struct rb_node node; + ext4_fsblk_t start_blk; + unsigned int count; +}; + +static struct kmem_cache *ext4_system_zone_cachep; + +int __init init_ext4_system_zone(void) +{ + ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, + SLAB_RECLAIM_ACCOUNT); + if (ext4_system_zone_cachep == NULL) + return -ENOMEM; + return 0; +} + +void exit_ext4_system_zone(void) +{ + kmem_cache_destroy(ext4_system_zone_cachep); +} + +static inline int can_merge(struct ext4_system_zone *entry1, + struct ext4_system_zone *entry2) +{ + if ((entry1->start_blk + entry1->count) == entry2->start_blk) + return 1; + return 0; +} + +/* + * Mark a range of blocks as belonging to the "system zone" --- that + * is, filesystem metadata blocks which should never be used by + * inodes. + */ +static int add_system_zone(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *new_entry = NULL, *entry; + struct rb_node **n = &sbi->system_blks.rb_node, *node; + struct rb_node *parent = NULL, *new_node = NULL; + + while (*n) { + parent = *n; + entry = rb_entry(parent, struct ext4_system_zone, node); + if (start_blk < entry->start_blk) + n = &(*n)->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = &(*n)->rb_right; + else { + if (start_blk + count > (entry->start_blk + + entry->count)) + entry->count = (start_blk + count - + entry->start_blk); + new_node = *n; + new_entry = rb_entry(new_node, struct ext4_system_zone, + node); + break; + } + } + + if (!new_entry) { + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &sbi->system_blks); + } + + /* Can we merge to the left? */ + node = rb_prev(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(entry, new_entry)) { + new_entry->start_blk = entry->start_blk; + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + + /* Can we merge to the right? */ + node = rb_next(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(new_entry, entry)) { + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + return 0; +} + +static void debug_print_tree(struct ext4_sb_info *sbi) +{ + struct rb_node *node; + struct ext4_system_zone *entry; + int first = 1; + + printk(KERN_INFO "System zones: "); + node = rb_first(&sbi->system_blks); + while (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + printk("%s%llu-%llu", first ? "" : ", ", + entry->start_blk, entry->start_blk + entry->count - 1); + first = 0; + node = rb_next(node); + } + printk("\n"); +} + +int ext4_setup_system_zone(struct super_block *sb) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_group_t i; + int flex_size = ext4_flex_bg_size(sbi); + int ret; + + if (!test_opt(sb, BLOCK_VALIDITY)) { + if (EXT4_SB(sb)->system_blks.rb_node) + ext4_release_system_zone(sb); + return 0; + } + if (EXT4_SB(sb)->system_blks.rb_node) + return 0; + + for (i=0; i < ngroups; i++) { + if (ext4_bg_has_super(sb, i) && + ((i < 5) || ((i % flex_size) == 0))) + add_system_zone(sbi, ext4_group_first_block_no(sb, i), + sbi->s_gdb_count + 1); + gdp = ext4_get_group_desc(sb, i, NULL); + ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_table(sb, gdp), + sbi->s_itb_per_group); + if (ret) + return ret; + } + + if (test_opt(sb, DEBUG)) + debug_print_tree(EXT4_SB(sb)); + return 0; +} + +/* Called when the filesystem is unmounted */ +void ext4_release_system_zone(struct super_block *sb) +{ + struct rb_node *n = EXT4_SB(sb)->system_blks.rb_node; + struct rb_node *parent; + struct ext4_system_zone *entry; + + while (n) { + /* Do the node's children first */ + if (n->rb_left) { + n = n->rb_left; + continue; + } + if (n->rb_right) { + n = n->rb_right; + continue; + } + /* + * The node has no children; free it, and then zero + * out parent's link to it. Finally go to the + * beginning of the loop and try to free the parent + * node. + */ + parent = rb_parent(n); + entry = rb_entry(n, struct ext4_system_zone, node); + kmem_cache_free(ext4_system_zone_cachep, entry); + if (!parent) + EXT4_SB(sb)->system_blks.rb_node = NULL; + else if (parent->rb_left == n) + parent->rb_left = NULL; + else if (parent->rb_right == n) + parent->rb_right = NULL; + n = parent; + } + EXT4_SB(sb)->system_blks.rb_node = NULL; +} + +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with filesystem metadata blocks. + */ +int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *entry; + struct rb_node *n = sbi->system_blks.rb_node; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else + return 0; + } + return 1; +} + diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index b64789929a65..9dc93168e262 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -131,8 +131,7 @@ static int ext4_readdir(struct file *filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, - 0, 0, 0); + err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d0f15ef56de1..cc7d5edc38c9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -21,7 +21,14 @@ #include <linux/magic.h> #include <linux/jbd2.h> #include <linux/quota.h> -#include "ext4_i.h" +#include <linux/rwsem.h> +#include <linux/rbtree.h> +#include <linux/seqlock.h> +#include <linux/mutex.h> +#include <linux/timer.h> +#include <linux/wait.h> +#include <linux/blockgroup_lock.h> +#include <linux/percpu_counter.h> /* * The fourth extended filesystem constants/structures @@ -46,6 +53,19 @@ #define ext4_debug(f, a...) do {} while (0) #endif +/* data type for block offset of block group */ +typedef int ext4_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long long ext4_fsblk_t; + +/* data type for file logical block number */ +typedef __u32 ext4_lblk_t; + +/* data type for block group number */ +typedef unsigned int ext4_group_t; + + /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 1 /* blocks already reserved */ @@ -179,9 +199,6 @@ struct flex_groups { #define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */ #define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */ -#ifdef __KERNEL__ -#include "ext4_sb.h" -#endif /* * Macro-instructions used to manage group descriptors */ @@ -297,10 +314,23 @@ struct ext4_new_group_data { }; /* - * Following is used by preallocation code to tell get_blocks() that we - * want uninitialzed extents. + * Flags used by ext4_get_blocks() */ -#define EXT4_CREATE_UNINITIALIZED_EXT 2 + /* Allocate any needed blocks and/or convert an unitialized + extent to be an initialized ext4 */ +#define EXT4_GET_BLOCKS_CREATE 0x0001 + /* Request the creation of an unitialized extent */ +#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 +#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ + EXT4_GET_BLOCKS_CREATE) + /* Caller is from the delayed allocation writeout path, + so set the magic i_delalloc_reserve_flag after taking the + inode allocation semaphore for */ +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 + /* Call ext4_da_update_reserve_space() after successfully + allocating the blocks */ +#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008 + /* * ioctl commands @@ -516,6 +546,110 @@ do { \ #endif /* defined(__KERNEL__) || defined(__linux__) */ /* + * storage for cached extent + */ +struct ext4_ext_cache { + ext4_fsblk_t ec_start; + ext4_lblk_t ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; +}; + +/* + * fourth extended file system inode data in memory + */ +struct ext4_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; + ext4_fsblk_t i_file_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is ued for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + ext4_group_t i_block_group; + __u32 i_state; /* Dynamic state flags for ext4 */ + + ext4_lblk_t i_dir_start_lookup; +#ifdef CONFIG_EXT4_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif +#ifdef CONFIG_EXT4_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext4_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext4_get_block (growth) and ext4_truncate (shrinkth). + */ + loff_t i_disksize; + + /* + * i_data_sem is for serialising ext4_truncate() against + * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext4 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have i_data_sem. + */ + struct rw_semaphore i_data_sem; + struct inode vfs_inode; + struct jbd2_inode jinode; + + struct ext4_ext_cache i_cached_extent; + /* + * File creation time. Its function is same as that of + * struct timespec i_{a,c,m}time in the generic inode. + */ + struct timespec i_crtime; + + /* mballoc */ + struct list_head i_prealloc_list; + spinlock_t i_prealloc_lock; + + /* ialloc */ + ext4_group_t i_last_alloc_group; + + /* allocation reservation info for delalloc */ + unsigned int i_reserved_data_blocks; + unsigned int i_reserved_meta_blocks; + unsigned int i_allocated_meta_blocks; + unsigned short i_delalloc_reserved_flag; + + /* on-disk additional length */ + __u16 i_extra_isize; + + spinlock_t i_block_reservation_lock; +}; + +/* * File system states */ #define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ @@ -560,6 +694,7 @@ do { \ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ +#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H @@ -689,6 +824,137 @@ struct ext4_super_block { }; #ifdef __KERNEL__ +/* + * fourth extended-fs super-block data in memory + */ +struct ext4_sb_info { + unsigned long s_desc_size; /* Size of a group descriptor in bytes */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + unsigned long s_gdb_count; /* Number of group descriptor blocks */ + unsigned long s_desc_per_block; /* Number of group descriptors per block */ + ext4_group_t s_groups_count; /* Number of groups in the fs */ + unsigned long s_overhead_last; /* Last calculated overhead */ + unsigned long s_blocks_last; /* Last seen block count */ + loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ + struct buffer_head **s_group_desc; + unsigned long s_mount_opt; + ext4_fsblk_t s_sb_block; + uid_t s_resuid; + gid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + unsigned int s_inode_readahead_blks; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + u32 s_hash_seed[4]; + int s_def_hash_version; + int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct percpu_counter s_dirtyblocks_counter; + struct blockgroup_lock *s_blockgroup_lock; + struct proc_dir_entry *s_proc; + struct kobject s_kobj; + struct completion s_kobj_unregister; + + /* Journaling */ + struct inode *s_journal_inode; + struct journal_s *s_journal; + struct list_head s_orphan; + struct mutex s_orphan_lock; + struct mutex s_resize_lock; + unsigned long s_commit_interval; + u32 s_max_batch_time; + u32 s_min_batch_time; + struct block_device *journal_bdev; +#ifdef CONFIG_JBD2_DEBUG + struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ + wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ +#endif +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif + unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ + struct rb_root system_blks; + +#ifdef EXTENTS_STATS + /* ext4 extents stats */ + unsigned long s_ext_min; + unsigned long s_ext_max; + unsigned long s_depth_max; + spinlock_t s_ext_stats_lock; + unsigned long s_ext_blocks; + unsigned long s_ext_extents; +#endif + + /* for buddy allocator */ + struct ext4_group_info ***s_group_info; + struct inode *s_buddy_cache; + long s_blocks_reserved; + spinlock_t s_reserve_lock; + spinlock_t s_md_lock; + tid_t s_last_transaction; + unsigned short *s_mb_offsets; + unsigned int *s_mb_maxs; + + /* tunables */ + unsigned long s_stripe; + unsigned int s_mb_stream_request; + unsigned int s_mb_max_to_scan; + unsigned int s_mb_min_to_scan; + unsigned int s_mb_stats; + unsigned int s_mb_order2_reqs; + unsigned int s_mb_group_prealloc; + /* where last allocation was done - for stream allocation */ + unsigned long s_mb_last_group; + unsigned long s_mb_last_start; + + /* history to debug policy */ + struct ext4_mb_history *s_mb_history; + int s_mb_history_cur; + int s_mb_history_max; + int s_mb_history_num; + spinlock_t s_mb_history_lock; + int s_mb_history_filter; + + /* stats for buddy allocator */ + spinlock_t s_mb_pa_lock; + atomic_t s_bal_reqs; /* number of reqs with len > 1 */ + atomic_t s_bal_success; /* we found long enough chunks */ + atomic_t s_bal_allocated; /* in blocks */ + atomic_t s_bal_ex_scanned; /* total extents scanned */ + atomic_t s_bal_goals; /* goal hits */ + atomic_t s_bal_breaks; /* too long searches */ + atomic_t s_bal_2orders; /* 2^order hits */ + spinlock_t s_bal_lock; + unsigned long s_mb_buddies_generated; + unsigned long long s_mb_generation_time; + atomic_t s_mb_lost_chunks; + atomic_t s_mb_preallocated; + atomic_t s_mb_discarded; + + /* locality groups */ + struct ext4_locality_group *s_locality_groups; + + /* for write statistics */ + unsigned long s_sectors_written_start; + u64 s_kbytes_written; + + unsigned int s_log_groups_per_flex; + struct flex_groups *s_flex_groups; +}; + static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) { return sb->s_fs_info; @@ -704,7 +970,6 @@ static inline struct timespec ext4_current_time(struct inode *inode) current_fs_time(inode->i_sb) : CURRENT_TIME_SEC; } - static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || @@ -1014,6 +1279,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); +struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, + ext4_group_t block_group); +extern unsigned ext4_init_block_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t group, + struct ext4_group_desc *desc); +#define ext4_free_blocks_after_init(sb, group, desc) \ + ext4_init_block_bitmap(sb, NULL, group, desc) /* dir.c */ extern int ext4_check_dir_entry(const char *, struct inode *, @@ -1038,6 +1311,11 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); extern void ext4_check_inodes_bitmap(struct super_block *); +extern unsigned ext4_init_inode_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t group, + struct ext4_group_desc *desc); +extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); /* mballoc.c */ extern long ext4_mb_stats; @@ -1123,6 +1401,8 @@ extern void ext4_abort(struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); extern void ext4_warning(struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); +extern void ext4_msg(struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); extern void ext4_grp_locked_error(struct super_block *, ext4_group_t, const char *, const char *, ...) __attribute__ ((format (printf, 4, 5))); @@ -1161,6 +1441,10 @@ extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); +extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); +extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { @@ -1228,6 +1512,18 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb, return grp_info[indexv][indexh]; } +/* + * Reading s_groups_count requires using smp_rmb() afterwards. See + * the locking protocol documented in the comments of ext4_group_add() + * in resize.c + */ +static inline ext4_group_t ext4_get_groups_count(struct super_block *sb) +{ + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + + smp_rmb(); + return ngroups; +} static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi, ext4_group_t block_group) @@ -1283,33 +1579,25 @@ struct ext4_group_info { }; #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 -#define EXT4_GROUP_INFO_LOCKED_BIT 1 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) -static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) +static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb, + ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state)); + return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group); } -static inline void ext4_unlock_group(struct super_block *sb, - ext4_group_t group) +static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state)); + spin_lock(ext4_group_lock_ptr(sb, group)); } -static inline int ext4_is_group_locked(struct super_block *sb, +static inline void ext4_unlock_group(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT, - &(grinfo->bb_state)); + spin_unlock(ext4_group_lock_ptr(sb, group)); } /* @@ -1326,11 +1614,21 @@ extern const struct file_operations ext4_file_operations; /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; extern const struct inode_operations ext4_special_inode_operations; +extern struct dentry *ext4_get_parent(struct dentry *child); /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; +/* block_validity */ +extern void ext4_release_system_zone(struct super_block *sb); +extern int ext4_setup_system_zone(struct super_block *sb); +extern int __init init_ext4_system_zone(void); +extern void exit_ext4_system_zone(void); +extern int ext4_data_block_valid(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count); + /* extents.c */ extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); @@ -1338,17 +1636,15 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, - struct buffer_head *bh_result, - int create, int extend_disksize); + struct buffer_head *bh_result, int flags); extern void ext4_ext_truncate(struct inode *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); -extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, - sector_t block, unsigned int max_blocks, - struct buffer_head *bh, int create, - int extend_disksize, int flag); +extern int ext4_get_blocks(handle_t *handle, struct inode *inode, + sector_t block, unsigned int max_blocks, + struct buffer_head *bh, int flags); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h deleted file mode 100644 index 4ce2187123aa..000000000000 --- a/fs/ext4/ext4_i.h +++ /dev/null @@ -1,140 +0,0 @@ -/* - * ext4_i.h - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/include/linux/minix_fs_i.h - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -#ifndef _EXT4_I -#define _EXT4_I - -#include <linux/rwsem.h> -#include <linux/rbtree.h> -#include <linux/seqlock.h> -#include <linux/mutex.h> - -/* data type for block offset of block group */ -typedef int ext4_grpblk_t; - -/* data type for filesystem-wide blocks number */ -typedef unsigned long long ext4_fsblk_t; - -/* data type for file logical block number */ -typedef __u32 ext4_lblk_t; - -/* data type for block group number */ -typedef unsigned int ext4_group_t; - -/* - * storage for cached extent - */ -struct ext4_ext_cache { - ext4_fsblk_t ec_start; - ext4_lblk_t ec_block; - __u32 ec_len; /* must be 32bit to return holes */ - __u32 ec_type; -}; - -/* - * fourth extended file system inode data in memory - */ -struct ext4_inode_info { - __le32 i_data[15]; /* unconverted */ - __u32 i_flags; - ext4_fsblk_t i_file_acl; - __u32 i_dtime; - - /* - * i_block_group is the number of the block group which contains - * this file's inode. Constant across the lifetime of the inode, - * it is ued for making block allocation decisions - we try to - * place a file's data blocks near its inode block, and new inodes - * near to their parent directory's inode. - */ - ext4_group_t i_block_group; - __u32 i_state; /* Dynamic state flags for ext4 */ - - ext4_lblk_t i_dir_start_lookup; -#ifdef CONFIG_EXT4_FS_XATTR - /* - * Extended attributes can be read independently of the main file - * data. Taking i_mutex even when reading would cause contention - * between readers of EAs and writers of regular file data, so - * instead we synchronize on xattr_sem when reading or changing - * EAs. - */ - struct rw_semaphore xattr_sem; -#endif -#ifdef CONFIG_EXT4_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif - - struct list_head i_orphan; /* unlinked but open inodes */ - - /* - * i_disksize keeps track of what the inode size is ON DISK, not - * in memory. During truncate, i_size is set to the new size by - * the VFS prior to calling ext4_truncate(), but the filesystem won't - * set i_disksize to 0 until the truncate is actually under way. - * - * The intent is that i_disksize always represents the blocks which - * are used by this file. This allows recovery to restart truncate - * on orphans if we crash during truncate. We actually write i_disksize - * into the on-disk inode when writing inodes out, instead of i_size. - * - * The only time when i_disksize and i_size may be different is when - * a truncate is in progress. The only things which change i_disksize - * are ext4_get_block (growth) and ext4_truncate (shrinkth). - */ - loff_t i_disksize; - - /* - * i_data_sem is for serialising ext4_truncate() against - * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's - * data tree are chopped off during truncate. We can't do that in - * ext4 because whenever we perform intermediate commits during - * truncate, the inode and all the metadata blocks *must* be in a - * consistent state which allows truncation of the orphans to restart - * during recovery. Hence we must fix the get_block-vs-truncate race - * by other means, so we have i_data_sem. - */ - struct rw_semaphore i_data_sem; - struct inode vfs_inode; - struct jbd2_inode jinode; - - struct ext4_ext_cache i_cached_extent; - /* - * File creation time. Its function is same as that of - * struct timespec i_{a,c,m}time in the generic inode. - */ - struct timespec i_crtime; - - /* mballoc */ - struct list_head i_prealloc_list; - spinlock_t i_prealloc_lock; - - /* ialloc */ - ext4_group_t i_last_alloc_group; - - /* allocation reservation info for delalloc */ - unsigned int i_reserved_data_blocks; - unsigned int i_reserved_meta_blocks; - unsigned int i_allocated_meta_blocks; - unsigned short i_delalloc_reserved_flag; - - /* on-disk additional length */ - __u16 i_extra_isize; - - spinlock_t i_block_reservation_lock; -}; - -#endif /* _EXT4_I */ diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h deleted file mode 100644 index 57b71fefbccf..000000000000 --- a/fs/ext4/ext4_sb.h +++ /dev/null @@ -1,161 +0,0 @@ -/* - * ext4_sb.h - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/include/linux/minix_fs_sb.h - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -#ifndef _EXT4_SB -#define _EXT4_SB - -#ifdef __KERNEL__ -#include <linux/timer.h> -#include <linux/wait.h> -#include <linux/blockgroup_lock.h> -#include <linux/percpu_counter.h> -#endif -#include <linux/rbtree.h> - -/* - * fourth extended-fs super-block data in memory - */ -struct ext4_sb_info { - unsigned long s_desc_size; /* Size of a group descriptor in bytes */ - unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_blocks_per_group;/* Number of blocks in a group */ - unsigned long s_inodes_per_group;/* Number of inodes in a group */ - unsigned long s_itb_per_group; /* Number of inode table blocks per group */ - unsigned long s_gdb_count; /* Number of group descriptor blocks */ - unsigned long s_desc_per_block; /* Number of group descriptors per block */ - ext4_group_t s_groups_count; /* Number of groups in the fs */ - unsigned long s_overhead_last; /* Last calculated overhead */ - unsigned long s_blocks_last; /* Last seen block count */ - loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ - struct buffer_head * s_sbh; /* Buffer containing the super block */ - struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; - unsigned long s_mount_opt; - ext4_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; - unsigned short s_mount_state; - unsigned short s_pad; - int s_addr_per_block_bits; - int s_desc_per_block_bits; - int s_inode_size; - int s_first_ino; - unsigned int s_inode_readahead_blks; - spinlock_t s_next_gen_lock; - u32 s_next_generation; - u32 s_hash_seed[4]; - int s_def_hash_version; - int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ - struct percpu_counter s_freeblocks_counter; - struct percpu_counter s_freeinodes_counter; - struct percpu_counter s_dirs_counter; - struct percpu_counter s_dirtyblocks_counter; - struct blockgroup_lock *s_blockgroup_lock; - struct proc_dir_entry *s_proc; - struct kobject s_kobj; - struct completion s_kobj_unregister; - - /* Journaling */ - struct inode *s_journal_inode; - struct journal_s *s_journal; - struct list_head s_orphan; - unsigned long s_commit_interval; - u32 s_max_batch_time; - u32 s_min_batch_time; - struct block_device *journal_bdev; -#ifdef CONFIG_JBD2_DEBUG - struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ - wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ -#endif -#ifdef CONFIG_QUOTA - char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ - int s_jquota_fmt; /* Format of quota to use */ -#endif - unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ - -#ifdef EXTENTS_STATS - /* ext4 extents stats */ - unsigned long s_ext_min; - unsigned long s_ext_max; - unsigned long s_depth_max; - spinlock_t s_ext_stats_lock; - unsigned long s_ext_blocks; - unsigned long s_ext_extents; -#endif - - /* for buddy allocator */ - struct ext4_group_info ***s_group_info; - struct inode *s_buddy_cache; - long s_blocks_reserved; - spinlock_t s_reserve_lock; - spinlock_t s_md_lock; - tid_t s_last_transaction; - unsigned short *s_mb_offsets; - unsigned int *s_mb_maxs; - - /* tunables */ - unsigned long s_stripe; - unsigned int s_mb_stream_request; - unsigned int s_mb_max_to_scan; - unsigned int s_mb_min_to_scan; - unsigned int s_mb_stats; - unsigned int s_mb_order2_reqs; - unsigned int s_mb_group_prealloc; - /* where last allocation was done - for stream allocation */ - unsigned long s_mb_last_group; - unsigned long s_mb_last_start; - - /* history to debug policy */ - struct ext4_mb_history *s_mb_history; - int s_mb_history_cur; - int s_mb_history_max; - int s_mb_history_num; - spinlock_t s_mb_history_lock; - int s_mb_history_filter; - - /* stats for buddy allocator */ - spinlock_t s_mb_pa_lock; - atomic_t s_bal_reqs; /* number of reqs with len > 1 */ - atomic_t s_bal_success; /* we found long enough chunks */ - atomic_t s_bal_allocated; /* in blocks */ - atomic_t s_bal_ex_scanned; /* total extents scanned */ - atomic_t s_bal_goals; /* goal hits */ - atomic_t s_bal_breaks; /* too long searches */ - atomic_t s_bal_2orders; /* 2^order hits */ - spinlock_t s_bal_lock; - unsigned long s_mb_buddies_generated; - unsigned long long s_mb_generation_time; - atomic_t s_mb_lost_chunks; - atomic_t s_mb_preallocated; - atomic_t s_mb_discarded; - - /* locality groups */ - struct ext4_locality_group *s_locality_groups; - - /* for write statistics */ - unsigned long s_sectors_written_start; - u64 s_kbytes_written; - - unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; -}; - -static inline spinlock_t * -sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group) -{ - return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); -} - -#endif /* _EXT4_SB */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e3a55eb8b26a..2593f748c3a4 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -326,32 +326,18 @@ ext4_ext_max_entries(struct inode *inode, int depth) static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { - ext4_fsblk_t block = ext_pblock(ext), valid_block; + ext4_fsblk_t block = ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - ((block + len) > ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { - ext4_fsblk_t block = idx_pblock(ext_idx), valid_block; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + ext4_fsblk_t block = idx_pblock(ext_idx); - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - (block >= ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); } static int ext4_valid_extent_entries(struct inode *inode, @@ -2097,12 +2083,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); - if (ext4_ext_is_uninitialized(ex)) - uninitialized = 1; ex_ee_len = ext4_ext_get_actual_len(ex); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { + + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + else + uninitialized = 0; + ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); path[depth].p_ext = ex; @@ -2784,7 +2774,7 @@ fix_extent_len: int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; @@ -2793,7 +2783,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; - loff_t disksize; __clear_bit(BH_New, &bh_result->b_state); ext_debug("blocks %u/%u requested for inode %u\n", @@ -2803,7 +2792,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, cache_type = ext4_ext_in_cache(inode, iblock, &newex); if (cache_type) { if (cache_type == EXT4_EXT_CACHE_GAP) { - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * block isn't allocated yet and * user doesn't want to allocate it @@ -2869,9 +2858,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, EXT4_EXT_CACHE_EXTENT); goto out; } - if (create == EXT4_CREATE_UNINITIALIZED_EXT) + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) goto out; - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { + if (allocated > max_blocks) + allocated = max_blocks; /* * We have blocks reserved already. We * return allocated blocks so that delalloc @@ -2879,8 +2870,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * the buffer head will be unmapped so that * a read from the block returns 0s. */ - if (allocated > max_blocks) - allocated = max_blocks; set_buffer_unwritten(bh_result); bh_result->b_bdev = inode->i_sb->s_bdev; bh_result->b_blocknr = newblock; @@ -2903,7 +2892,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero */ - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * put just found gap into cache to speed up * subsequent requests @@ -2932,10 +2921,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * EXT_UNINIT_MAX_LEN. */ if (max_blocks > EXT_INIT_MAX_LEN && - create != EXT4_CREATE_UNINITIALIZED_EXT) + !(flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_INIT_MAX_LEN; else if (max_blocks > EXT_UNINIT_MAX_LEN && - create == EXT4_CREATE_UNINITIALIZED_EXT) + (flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_UNINIT_MAX_LEN; /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */ @@ -2966,7 +2955,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(ar.len); - if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */ + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) /* Mark uninitialized */ ext4_ext_mark_uninitialized(&newex); err = ext4_ext_insert_extent(handle, inode, path, &newex); if (err) { @@ -2983,18 +2972,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); outnew: - if (extend_disksize) { - disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = disksize; - } - set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ - if (create != EXT4_CREATE_UNINITIALIZED_EXT) + if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) ext4_ext_put_in_cache(inode, iblock, allocated, newblock, EXT4_EXT_CACHE_EXTENT); out: @@ -3150,9 +3131,10 @@ retry: ret = PTR_ERR(handle); break; } - ret = ext4_get_blocks_wrap(handle, inode, block, - max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); + map_bh.b_state = 0; + ret = ext4_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_GET_BLOCKS_CREATE_UNINIT_EXT); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); @@ -3195,7 +3177,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, void *data) { struct fiemap_extent_info *fieinfo = data; - unsigned long blksize_bits = inode->i_sb->s_blocksize_bits; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; __u64 logical; __u64 physical; __u64 length; @@ -3242,9 +3224,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, * * XXX this might miss a single-block extent at EXT_MAX_BLOCK */ - if (logical + length - 1 == EXT_MAX_BLOCK || - ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK) + if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) { + loff_t size = i_size_read(inode); + loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb); + flags |= FIEMAP_EXTENT_LAST; + if ((flags & FIEMAP_EXTENT_DELALLOC) && + logical+length > size) + length = (size - logical + bs - 1) & ~(bs-1); + } error = fiemap_fill_next_extent(fieinfo, logical, physical, length, flags); @@ -3318,10 +3307,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * Walk the extent tree gathering extent information. * ext4_ext_fiemap_cb will push extents back to user. */ - down_write(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); error = ext4_ext_walk_space(inode, start_blk, len_blks, ext4_ext_fiemap_cb, fieinfo); - up_write(&EXT4_I(inode)->i_data_sem); + up_read(&EXT4_I(inode)->i_data_sem); } return error; diff --git a/fs/ext4/group.h b/fs/ext4/group.h deleted file mode 100644 index c2c0a8d06d0e..000000000000 --- a/fs/ext4/group.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * linux/fs/ext4/group.h - * - * Copyright (C) 2007 Cluster File Systems, Inc - * - * Author: Andreas Dilger <adilger@clusterfs.com> - */ - -#ifndef _LINUX_EXT4_GROUP_H -#define _LINUX_EXT4_GROUP_H - -extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, - ext4_group_t block_group); -extern unsigned ext4_init_block_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -#define ext4_free_blocks_after_init(sb, group, desc) \ - ext4_init_block_bitmap(sb, NULL, group, desc) -extern unsigned ext4_init_inode_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); -#endif /* _LINUX_EXT4_GROUP_H */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f18e0a08a6b5..3743bd849bce 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -27,7 +27,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "group.h" /* * ialloc.c contains the inodes allocation and deallocation routines @@ -123,16 +122,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { ext4_init_inode_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -247,9 +246,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ - spin_lock(sb_bgl_lock(sbi, block_group)); - cleared = ext4_clear_bit(bit, bitmap_bh->b_data); - spin_unlock(sb_bgl_lock(sbi, block_group)); + cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group), + bit, bitmap_bh->b_data); if (!cleared) ext4_error(sb, "ext4_free_inode", "bit already cleared for inode %lu", ino); @@ -261,7 +259,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) if (fatal) goto error_return; if (gdp) { - spin_lock(sb_bgl_lock(sbi, block_group)); + ext4_lock_group(sb, block_group); count = ext4_free_inodes_count(sb, gdp) + 1; ext4_free_inodes_set(sb, gdp, count); if (is_directory) { @@ -277,7 +275,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) } gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); @@ -316,7 +314,7 @@ error_return: static int find_group_dir(struct super_block *sb, struct inode *parent, ext4_group_t *best_group) { - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned int freei, avefreei; struct ext4_group_desc *desc, *best_desc = NULL; ext4_group_t group; @@ -349,11 +347,10 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *desc; - struct buffer_head *bh; struct flex_groups *flex_group = sbi->s_flex_groups; ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); int flex_size = ext4_flex_bg_size(sbi); ext4_group_t best_flex = parent_fbg_group; int blocks_per_flex = sbi->s_blocks_per_group * flex_size; @@ -362,7 +359,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, ext4_group_t n_fbg_groups; ext4_group_t i; - n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >> + n_fbg_groups = (ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; find_close_to_parent: @@ -404,7 +401,7 @@ find_close_to_parent: found_flexbg: for (i = best_flex * flex_size; i < ngroups && i < (best_flex + 1) * flex_size; i++) { - desc = ext4_get_group_desc(sb, i, &bh); + desc = ext4_get_group_desc(sb, i, NULL); if (ext4_free_inodes_count(sb, desc)) { *best_group = i; goto out; @@ -478,20 +475,21 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext4_fsblk_t freeb, avefreeb; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_blocks; - ext4_group_t i, grp, g; + ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; struct orlov_stats stats; int flex_size = ext4_flex_bg_size(sbi); + ngroups = real_ngroups; if (flex_size > 1) { - ngroups = (ngroups + flex_size - 1) >> + ngroups = (real_ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; parent_group >>= sbi->s_log_groups_per_flex; } @@ -543,7 +541,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, */ grp *= flex_size; for (i = 0; i < flex_size; i++) { - if (grp+i >= sbi->s_groups_count) + if (grp+i >= real_ngroups) break; desc = ext4_get_group_desc(sb, grp+i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { @@ -583,7 +581,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, } fallback: - ngroups = sbi->s_groups_count; + ngroups = real_ngroups; avefreei = freei / ngroups; fallback_retry: parent_group = EXT4_I(parent)->i_block_group; @@ -613,9 +611,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent, ext4_group_t *group, int mode) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t i, last, ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; - ext4_group_t i, last; int flex_size = ext4_flex_bg_size(EXT4_SB(sb)); /* @@ -708,10 +705,10 @@ static int find_group_other(struct super_block *sb, struct inode *parent, /* * claim the inode from the inode bitmap. If the group - * is uninit we need to take the groups's sb_bgl_lock + * is uninit we need to take the groups's ext4_group_lock * and clear the uninit flag. The inode bitmap update * and group desc uninit flag clear should be done - * after holding sb_bgl_lock so that ext4_read_inode_bitmap + * after holding ext4_group_lock so that ext4_read_inode_bitmap * doesn't race with the ext4_claim_inode */ static int ext4_claim_inode(struct super_block *sb, @@ -722,7 +719,7 @@ static int ext4_claim_inode(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); - spin_lock(sb_bgl_lock(sbi, group)); + ext4_lock_group(sb, group); if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) { /* not a free inode */ retval = 1; @@ -731,7 +728,7 @@ static int ext4_claim_inode(struct super_block *sb, ino++; if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || ino > EXT4_INODES_PER_GROUP(sb)) { - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); ext4_error(sb, __func__, "reserved inode or inode > inodes count - " "block_group = %u, inode=%lu", group, @@ -780,7 +777,7 @@ static int ext4_claim_inode(struct super_block *sb, } gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); err_ret: - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); return retval; } @@ -799,11 +796,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; struct buffer_head *group_desc_bh; - ext4_group_t group = 0; + ext4_group_t ngroups, group = 0; unsigned long ino = 0; struct inode *inode; struct ext4_group_desc *gdp = NULL; - struct ext4_super_block *es; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; int ret2, err = 0; @@ -818,15 +814,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) return ERR_PTR(-EPERM); sb = dir->i_sb; + ngroups = ext4_get_groups_count(sb); trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id, dir->i_ino, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); - sbi = EXT4_SB(sb); - es = sbi->s_es; if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) { ret2 = find_group_flex(sb, dir, &group); @@ -856,7 +851,7 @@ got_group: if (ret2 == -1) goto out; - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); @@ -917,7 +912,7 @@ repeat_in_this_group: * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ - if (++group == sbi->s_groups_count) + if (++group == ngroups) group = 0; } err = -ENOSPC; @@ -938,7 +933,7 @@ got: } free = 0; - spin_lock(sb_bgl_lock(sbi, group)); + ext4_lock_group(sb, group); /* recheck and clear flag under lock if we still need to */ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { free = ext4_free_blocks_after_init(sb, group, gdp); @@ -947,7 +942,7 @@ got: gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); } - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); /* Don't need to dirty bitmap block if we didn't change it */ if (free) { @@ -1158,7 +1153,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) { unsigned long desc_count; struct ext4_group_desc *gdp; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; unsigned long bitmap_count, x; @@ -1168,7 +1163,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) desc_count = 0; bitmap_count = 0; gdp = NULL; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1190,7 +1185,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) return desc_count; #else desc_count = 0; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1205,9 +1200,9 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) unsigned long ext4_count_dirs(struct super_block * sb) { unsigned long count = 0; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2a9ffd528dd1..875db944b22f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -372,20 +372,21 @@ static int ext4_block_to_path(struct inode *inode, } static int __ext4_check_blockref(const char *function, struct inode *inode, - __le32 *p, unsigned int max) { - - unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es); + __le32 *p, unsigned int max) +{ __le32 *bref = p; + unsigned int blk; + while (bref < p+max) { - if (unlikely(le32_to_cpu(*bref) >= maxblocks)) { + blk = le32_to_cpu(*bref++); + if (blk && + unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), + blk, 1))) { ext4_error(inode->i_sb, function, - "block reference %u >= max (%u) " - "in inode #%lu, offset=%d", - le32_to_cpu(*bref), maxblocks, - inode->i_ino, (int)(bref-p)); + "invalid block reference %u " + "in inode #%lu", blk, inode->i_ino); return -EIO; } - bref++; } return 0; } @@ -892,6 +893,10 @@ err_out: } /* + * The ext4_ind_get_blocks() function handles non-extents inodes + * (i.e., using the traditional indirect/double-indirect i_blocks + * scheme) for ext4_get_blocks(). + * * Allocation strategy is simple: if we have to allocate something, we will * have to go the whole way to leaf. So let's do it before attaching anything * to tree, set linkage between the newborn blocks, write them if sync is @@ -909,15 +914,16 @@ err_out: * return = 0, if plain lookup failed. * return < 0, error case. * - * - * Need to be called with - * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block - * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) + * The ext4_ind_get_blocks() function should be called with + * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem + * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or + * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system + * blocks. */ -static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, +static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int maxblocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { int err = -EIO; ext4_lblk_t offsets[4]; @@ -927,14 +933,11 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, int indirect_blks; int blocks_to_boundary = 0; int depth; - struct ext4_inode_info *ei = EXT4_I(inode); int count = 0; ext4_fsblk_t first_block = 0; - loff_t disksize; - J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); - J_ASSERT(handle != NULL || create == 0); + J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, iblock, offsets, &blocks_to_boundary); @@ -963,7 +966,7 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, } /* Next simple case - plain lookup or failed read of indirect block */ - if (!create || err == -EIO) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO) goto cleanup; /* @@ -997,19 +1000,7 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, if (!err) err = ext4_splice_branch(handle, inode, iblock, partial, indirect_blks, count); - /* - * i_disksize growing is protected by i_data_sem. Don't forget to - * protect it if you're about to implement concurrent - * ext4_get_block() -bzzz - */ - if (!err && extend_disksize) { - disksize = ((loff_t) iblock + count) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > ei->i_disksize) - ei->i_disksize = disksize; - } - if (err) + else goto cleanup; set_buffer_new(bh_result); @@ -1120,8 +1111,23 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) ext4_discard_preallocations(inode); } +static int check_block_validity(struct inode *inode, sector_t logical, + sector_t phys, int len) +{ + if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) { + ext4_error(inode->i_sb, "check_block_validity", + "inode #%lu logical block %llu mapped to %llu " + "(size %d)", inode->i_ino, + (unsigned long long) logical, + (unsigned long long) phys, len); + WARN_ON(1); + return -EIO; + } + return 0; +} + /* - * The ext4_get_blocks_wrap() function try to look up the requested blocks, + * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks @@ -1129,7 +1135,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) * mapped. * * If file type is extents based, it will call ext4_ext_get_blocks(), - * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping + * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocate. @@ -1142,9 +1148,9 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) * * It returns the error in case of allocation failure. */ -int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, - unsigned int max_blocks, struct buffer_head *bh, - int create, int extend_disksize, int flag) +int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, + unsigned int max_blocks, struct buffer_head *bh, + int flags) { int retval; @@ -1152,21 +1158,28 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, clear_buffer_unwritten(bh); /* - * Try to see if we can get the block without requesting - * for new file system block. + * Try to see if we can get the block without requesting a new + * file system block. */ down_read((&EXT4_I(inode)->i_data_sem)); if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, 0, 0); + bh, 0); } else { - retval = ext4_get_blocks_handle(handle, - inode, block, max_blocks, bh, 0, 0); + retval = ext4_ind_get_blocks(handle, inode, block, max_blocks, + bh, 0); } up_read((&EXT4_I(inode)->i_data_sem)); + if (retval > 0 && buffer_mapped(bh)) { + int ret = check_block_validity(inode, block, + bh->b_blocknr, retval); + if (ret != 0) + return ret; + } + /* If it is only a block(s) look up */ - if (!create) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* @@ -1205,7 +1218,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, * let the underlying get_block() function know to * avoid double accounting */ - if (flag) + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) EXT4_I(inode)->i_delalloc_reserved_flag = 1; /* * We need to check for EXT4 here because migrate @@ -1213,10 +1226,10 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, */ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, create, extend_disksize); + bh, flags); } else { - retval = ext4_get_blocks_handle(handle, inode, block, - max_blocks, bh, create, extend_disksize); + retval = ext4_ind_get_blocks(handle, inode, block, + max_blocks, bh, flags); if (retval > 0 && buffer_new(bh)) { /* @@ -1229,18 +1242,23 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, } } - if (flag) { + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) EXT4_I(inode)->i_delalloc_reserved_flag = 0; - /* - * Update reserved blocks/metadata blocks - * after successful block allocation - * which were deferred till now - */ - if ((retval > 0) && buffer_delay(bh)) - ext4_da_update_reserve_space(inode, retval); - } + + /* + * Update reserved blocks/metadata blocks after successful + * block allocation which had been deferred till now. + */ + if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE)) + ext4_da_update_reserve_space(inode, retval); up_write((&EXT4_I(inode)->i_data_sem)); + if (retval > 0 && buffer_mapped(bh)) { + int ret = check_block_validity(inode, block, + bh->b_blocknr, retval); + if (ret != 0) + return ret; + } return retval; } @@ -1268,8 +1286,8 @@ int ext4_get_block(struct inode *inode, sector_t iblock, started = 1; } - ret = ext4_get_blocks_wrap(handle, inode, iblock, - max_blocks, bh_result, create, 0, 0); + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, + create ? EXT4_GET_BLOCKS_CREATE : 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1288,17 +1306,19 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, { struct buffer_head dummy; int fatal = 0, err; + int flags = 0; J_ASSERT(handle != NULL || create == 0); dummy.b_state = 0; dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); - err = ext4_get_blocks_wrap(handle, inode, block, 1, - &dummy, create, 1, 0); + if (create) + flags |= EXT4_GET_BLOCKS_CREATE; + err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags); /* - * ext4_get_blocks_handle() returns number of blocks - * mapped. 0 in case of a HOLE. + * ext4_get_blocks() returns number of blocks mapped. 0 in + * case of a HOLE. */ if (err > 0) { if (err > 1) @@ -1439,7 +1459,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; - int ret, needed_blocks = ext4_writepage_trans_blocks(inode); + int ret, needed_blocks; handle_t *handle; int retries = 0; struct page *page; @@ -1450,6 +1470,11 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, "dev %s ino %lu pos %llu len %u flags %u", inode->i_sb->s_id, inode->i_ino, (unsigned long long) pos, len, flags); + /* + * Reserve one block more for addition to orphan list in case + * we allocate blocks but write fails for some reason + */ + needed_blocks = ext4_writepage_trans_blocks(inode) + 1; index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; @@ -1483,15 +1508,30 @@ retry: if (ret) { unlock_page(page); - ext4_journal_stop(handle); page_cache_release(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. + * + * Add inode to orphan list in case we crash before + * truncate finishes */ if (pos + len > inode->i_size) + ext4_orphan_add(handle, inode); + + ext4_journal_stop(handle); + if (pos + len > inode->i_size) { vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might + * still be on the orphan list; we need to + * make sure the inode is removed from the + * orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -1509,6 +1549,52 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh) return ext4_handle_dirty_metadata(handle, NULL, bh); } +static int ext4_generic_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + int i_size_changed = 0; + struct inode *inode = mapping->host; + handle_t *handle = ext4_journal_current_handle(); + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* + * No need to use i_size_read() here, the i_size + * cannot change under us because we hold i_mutex. + * + * But it's important to update i_size while still holding page lock: + * page writeout could otherwise come in and zero beyond i_size. + */ + if (pos + copied > inode->i_size) { + i_size_write(inode, pos + copied); + i_size_changed = 1; + } + + if (pos + copied > EXT4_I(inode)->i_disksize) { + /* We need to mark inode dirty even if + * new_i_size is less that inode->i_size + * bu greater than i_disksize.(hint delalloc) + */ + ext4_update_i_disksize(inode, (pos + copied)); + i_size_changed = 1; + } + unlock_page(page); + page_cache_release(page); + + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (i_size_changed) + ext4_mark_inode_dirty(handle, inode); + + return copied; +} + /* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). @@ -1532,21 +1618,15 @@ static int ext4_ordered_write_end(struct file *file, ret = ext4_jbd2_file_inode(handle, inode); if (ret == 0) { - loff_t new_i_size; - - new_i_size = pos + copied; - if (new_i_size > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); - } - - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); if (ret2 < 0) ret = ret2; } @@ -1554,6 +1634,18 @@ static int ext4_ordered_write_end(struct file *file, if (!ret) ret = ret2; + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + + return ret ? ret : copied; } @@ -1565,25 +1657,21 @@ static int ext4_writeback_write_end(struct file *file, handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; - loff_t new_i_size; trace_mark(ext4_writeback_write_end, "dev %s ino %lu pos %llu len %u copied %u", inode->i_sb->s_id, inode->i_ino, (unsigned long long) pos, len, copied); - new_i_size = pos + copied; - if (new_i_size > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); - } - - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); + if (ret2 < 0) ret = ret2; @@ -1591,6 +1679,17 @@ static int ext4_writeback_write_end(struct file *file, if (!ret) ret = ret2; + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + return ret ? ret : copied; } @@ -1635,10 +1734,27 @@ static int ext4_journalled_write_end(struct file *file, } unlock_page(page); + page_cache_release(page); + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; - page_cache_release(page); + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } return ret ? ret : copied; } @@ -1852,7 +1968,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) * @logical - first logical block to start assignment with * * the function goes through all passed space and put actual disk - * block numbers into buffer heads, dropping BH_Delay + * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten */ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, struct buffer_head *exbh) @@ -1902,16 +2018,24 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, do { if (cur_logical >= logical + blocks) break; - if (buffer_delay(bh)) { - bh->b_blocknr = pblock; - clear_buffer_delay(bh); - bh->b_bdev = inode->i_sb->s_bdev; - } else if (buffer_unwritten(bh)) { - bh->b_blocknr = pblock; - clear_buffer_unwritten(bh); - set_buffer_mapped(bh); - set_buffer_new(bh); - bh->b_bdev = inode->i_sb->s_bdev; + + if (buffer_delay(bh) || + buffer_unwritten(bh)) { + + BUG_ON(bh->b_bdev != inode->i_sb->s_bdev); + + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock; + } else { + /* + * unwritten already should have + * blocknr assigned. Verify that + */ + clear_buffer_unwritten(bh); + BUG_ON(bh->b_blocknr != pblock); + } + } else if (buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -1990,51 +2114,6 @@ static void ext4_print_free_blocks(struct inode *inode) return; } -#define EXT4_DELALLOC_RSVED 1 -static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - int ret; - unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; - loff_t disksize = EXT4_I(inode)->i_disksize; - handle_t *handle = NULL; - - handle = ext4_journal_current_handle(); - BUG_ON(!handle); - ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, create, 0, EXT4_DELALLOC_RSVED); - if (ret <= 0) - return ret; - - bh_result->b_size = (ret << inode->i_blkbits); - - if (ext4_should_order_data(inode)) { - int retval; - retval = ext4_jbd2_file_inode(handle, inode); - if (retval) - /* - * Failed to add inode for ordered mode. Don't - * update file size - */ - return retval; - } - - /* - * Update on-disk size along with block allocation we don't - * use 'extend_disksize' as size may change within already - * allocated block -bzzz - */ - disksize = ((loff_t) iblock + ret) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, disksize); - ret = ext4_mark_inode_dirty(handle, inode); - return ret; - } - return 0; -} - /* * mpage_da_map_blocks - go through given space * @@ -2045,29 +2124,57 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, */ static int mpage_da_map_blocks(struct mpage_da_data *mpd) { - int err = 0; + int err, blks, get_blocks_flags; struct buffer_head new; - sector_t next; + sector_t next = mpd->b_blocknr; + unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; + loff_t disksize = EXT4_I(mpd->inode)->i_disksize; + handle_t *handle = NULL; /* * We consider only non-mapped and non-allocated blocks */ if ((mpd->b_state & (1 << BH_Mapped)) && - !(mpd->b_state & (1 << BH_Delay))) + !(mpd->b_state & (1 << BH_Delay)) && + !(mpd->b_state & (1 << BH_Unwritten))) return 0; - new.b_state = mpd->b_state; - new.b_blocknr = 0; - new.b_size = mpd->b_size; - next = mpd->b_blocknr; + /* - * If we didn't accumulate anything - * to write simply return + * If we didn't accumulate anything to write simply return */ - if (!new.b_size) + if (!mpd->b_size) return 0; - err = ext4_da_get_block_write(mpd->inode, next, &new, 1); - if (err) { + handle = ext4_journal_current_handle(); + BUG_ON(!handle); + + /* + * Call ext4_get_blocks() to allocate any delayed allocation + * blocks, or to convert an uninitialized extent to be + * initialized (in the case where we have written into + * one or more preallocated blocks). + * + * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to + * indicate that we are on the delayed allocation path. This + * affects functions in many different parts of the allocation + * call path. This flag exists primarily because we don't + * want to change *many* call functions, so ext4_get_blocks() + * will set the magic i_delalloc_reserved_flag once the + * inode's allocation semaphore is taken. + * + * If the blocks in questions were delalloc blocks, set + * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting + * variables are updated after the blocks have been allocated. + */ + new.b_state = 0; + get_blocks_flags = (EXT4_GET_BLOCKS_CREATE | + EXT4_GET_BLOCKS_DELALLOC_RESERVE); + if (mpd->b_state & (1 << BH_Delay)) + get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE; + blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks, + &new, get_blocks_flags); + if (blks < 0) { + err = blks; /* * If get block returns with error we simply * return. Later writepage will redirty the page and @@ -2100,12 +2207,14 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) if (err == -ENOSPC) { ext4_print_free_blocks(mpd->inode); } - /* invlaidate all the pages */ + /* invalidate all the pages */ ext4_da_block_invalidatepages(mpd, next, mpd->b_size >> mpd->inode->i_blkbits); return err; } - BUG_ON(new.b_size == 0); + BUG_ON(blks == 0); + + new.b_size = (blks << mpd->inode->i_blkbits); if (buffer_new(&new)) __unmap_underlying_blocks(mpd->inode, &new); @@ -2118,6 +2227,23 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) (mpd->b_state & (1 << BH_Unwritten))) mpage_put_bnr_to_bhs(mpd, next, &new); + if (ext4_should_order_data(mpd->inode)) { + err = ext4_jbd2_file_inode(handle, mpd->inode); + if (err) + return err; + } + + /* + * Update on-disk size along with block allocation. + */ + disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; + if (disksize > i_size_read(mpd->inode)) + disksize = i_size_read(mpd->inode); + if (disksize > EXT4_I(mpd->inode)->i_disksize) { + ext4_update_i_disksize(mpd->inode, disksize); + return ext4_mark_inode_dirty(handle, mpd->inode); + } + return 0; } @@ -2192,6 +2318,17 @@ flush_it: return; } +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + /* + * unmapped buffer is possible for holes. + * delay buffer is possible with delayed allocation. + * We also need to consider unwritten buffer as unmapped. + */ + return (!buffer_mapped(bh) || buffer_delay(bh) || + buffer_unwritten(bh)) && buffer_dirty(bh); +} + /* * __mpage_da_writepage - finds extent of pages and blocks * @@ -2276,8 +2413,7 @@ static int __mpage_da_writepage(struct page *page, * Otherwise we won't make progress * with the page in ext4_da_writepage */ - if (buffer_dirty(bh) && - (!buffer_mapped(bh) || buffer_delay(bh))) { + if (ext4_bh_unmapped_or_delay(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); @@ -2303,8 +2439,16 @@ static int __mpage_da_writepage(struct page *page, } /* - * this is a special callback for ->write_begin() only - * it's intention is to return mapped block or reserve space + * This is a special get_blocks_t callback which is used by + * ext4_da_write_begin(). It will either return mapped block or + * reserve space for a single block. + * + * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. + * We also have b_blocknr = -1 and b_bdev initialized properly + * + * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. + * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev + * initialized properly. */ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -2323,7 +2467,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0); if ((ret == 0) && !buffer_delay(bh_result)) { /* the block isn't (pre)allocated yet, let's reserve space */ /* @@ -2340,40 +2484,53 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, set_buffer_delay(bh_result); } else if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); - /* - * With sub-block writes into unwritten extents - * we also need to mark the buffer as new so that - * the unwritten parts of the buffer gets correctly zeroed. - */ - if (buffer_unwritten(bh_result)) + if (buffer_unwritten(bh_result)) { + /* A delayed write to unwritten bh should + * be marked new and mapped. Mapped ensures + * that we don't do get_block multiple times + * when we write to the same offset and new + * ensures that we do proper zero out for + * partial write. + */ set_buffer_new(bh_result); + set_buffer_mapped(bh_result); + } ret = 0; } return ret; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) -{ - /* - * unmapped buffer is possible for holes. - * delay buffer is possible with delayed allocation - */ - return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)); -} - -static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, +/* + * This function is used as a standard get_block_t calback function + * when there is no desire to allocate any blocks. It is used as a + * callback function for block_prepare_write(), nobh_writepage(), and + * block_write_full_page(). These functions should only try to map a + * single block at a time. + * + * Since this function doesn't do block allocations even if the caller + * requests it by passing in create=1, it is critically important that + * any caller checks to make sure that any buffer heads are returned + * by this function are either all already mapped or marked for + * delayed allocation before calling nobh_writepage() or + * block_write_full_page(). Otherwise, b_blocknr could be left + * unitialized, and the page write functions will be taken by + * surprise. + */ +static int noalloc_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize); + /* * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks, - bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); + BUG_ON(create && ret == 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -2382,10 +2539,11 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, } /* - * get called vi ext4_da_writepages after taking page lock (have journal handle) - * get called via journal_submit_inode_data_buffers (no journal handle) - * get called via shrink_page_list via pdflush (no journal handle) - * or grab_page_cache when doing write_begin (have journal handle) + * This function can get called via... + * - ext4_da_writepages after taking page lock (have journal handle) + * - journal_submit_inode_data_buffers (no journal handle) + * - shrink_page_list via pdflush (no journal handle) + * - grab_page_cache when doing write_begin (have journal handle) */ static int ext4_da_writepage(struct page *page, struct writeback_control *wbc) @@ -2436,7 +2594,7 @@ static int ext4_da_writepage(struct page *page, * do block allocation here. */ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext4_normal_get_block_write); + noalloc_get_block_write); if (!ret) { page_bufs = page_buffers(page); /* check whether all are mapped and non delay */ @@ -2461,11 +2619,10 @@ static int ext4_da_writepage(struct page *page, } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) - ret = nobh_writepage(page, ext4_normal_get_block_write, wbc); + ret = nobh_writepage(page, noalloc_get_block_write, wbc); else - ret = block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + ret = block_write_full_page(page, noalloc_get_block_write, + wbc); return ret; } @@ -2777,7 +2934,7 @@ retry: *pagep = page; ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - ext4_da_get_block_prep); + ext4_da_get_block_prep); if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); @@ -2815,7 +2972,7 @@ static int ext4_da_should_update_i_disksize(struct page *page, for (i = 0; i < idx; i++) bh = bh->b_this_page; - if (!buffer_mapped(bh) || (buffer_delay(bh))) + if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh)) return 0; return 1; } @@ -3085,12 +3242,10 @@ static int __ext4_normal_writepage(struct page *page, struct inode *inode = page->mapping->host; if (test_opt(inode->i_sb, NOBH)) - return nobh_writepage(page, - ext4_normal_get_block_write, wbc); + return nobh_writepage(page, noalloc_get_block_write, wbc); else - return block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + return block_write_full_page(page, noalloc_get_block_write, + wbc); } static int ext4_normal_writepage(struct page *page, @@ -3142,7 +3297,7 @@ static int __ext4_journalled_writepage(struct page *page, int err; ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext4_normal_get_block_write); + noalloc_get_block_write); if (ret != 0) goto out_unlock; @@ -3227,9 +3382,8 @@ static int ext4_journalled_writepage(struct page *page, * really know unless we go poke around in the buffer_heads. * But block_write_full_page will do the right thing. */ - return block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + return block_write_full_page(page, noalloc_get_block_write, + wbc); } no_write: redirty_page_for_writepage(wbc, page); @@ -3973,7 +4127,8 @@ void ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return; - if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) + if (ei->i_disksize && inode->i_size == 0 && + !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE; if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { @@ -4715,25 +4870,6 @@ int ext4_write_inode(struct inode *inode, int wait) return ext4_force_commit(inode->i_sb); } -int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh) -{ - int err = 0; - - mark_buffer_dirty(bh); - if (inode && inode_needs_sync(inode)) { - sync_dirty_buffer(bh); - if (buffer_req(bh) && !buffer_uptodate(bh)) { - ext4_error(inode->i_sb, __func__, - "IO error syncing inode, " - "inode=%lu, block=%llu", - inode->i_ino, - (unsigned long long)bh->b_blocknr); - err = -EIO; - } - } - return err; -} - /* * ext4_setattr() * @@ -4930,7 +5066,8 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) */ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) { - int groups, gdpblocks; + ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); + int gdpblocks; int idxblocks; int ret = 0; @@ -4957,8 +5094,8 @@ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) groups += nrblocks; gdpblocks = groups; - if (groups > EXT4_SB(inode->i_sb)->s_groups_count) - groups = EXT4_SB(inode->i_sb)->s_groups_count; + if (groups > ngroups) + groups = ngroups; if (groups > EXT4_SB(inode->i_sb)->s_gdb_count) gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; @@ -4998,7 +5135,7 @@ int ext4_writepage_trans_blocks(struct inode *inode) * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling - * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks. + * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f871677a7984..ed8482e22c0e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -372,24 +372,12 @@ static inline void mb_set_bit(int bit, void *addr) ext4_set_bit(bit, addr); } -static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr) -{ - addr = mb_correct_addr_and_bit(&bit, addr); - ext4_set_bit_atomic(lock, bit, addr); -} - static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } -static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr) -{ - addr = mb_correct_addr_and_bit(&bit, addr); - ext4_clear_bit_atomic(lock, bit, addr); -} - static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; @@ -448,7 +436,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; - BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; @@ -472,7 +460,7 @@ static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); @@ -739,6 +727,7 @@ static void ext4_mb_generate_buddy(struct super_block *sb, static int ext4_mb_init_cache(struct page *page, char *incore) { + ext4_group_t ngroups; int blocksize; int blocks_per_page; int groups_per_page; @@ -757,6 +746,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) inode = page->mapping->host; sb = inode->i_sb; + ngroups = ext4_get_groups_count(sb); blocksize = 1 << inode->i_blkbits; blocks_per_page = PAGE_CACHE_SIZE / blocksize; @@ -780,7 +770,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) for (i = 0; i < groups_per_page; i++) { struct ext4_group_desc *desc; - if (first_group + i >= EXT4_SB(sb)->s_groups_count) + if (first_group + i >= ngroups) break; err = -EIO; @@ -801,17 +791,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore) unlock_buffer(bh[i]); continue; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_lock_group(sb, first_group + i); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { ext4_init_block_bitmap(sb, bh[i], first_group + i, desc); set_bitmap_uptodate(bh[i]); set_buffer_uptodate(bh[i]); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_unlock_group(sb, first_group + i); unlock_buffer(bh[i]); continue; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_unlock_group(sb, first_group + i); if (buffer_uptodate(bh[i])) { /* * if not uninit if bh is uptodate, @@ -852,7 +842,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) struct ext4_group_info *grinfo; group = (first_block + i) >> 1; - if (group >= EXT4_SB(sb)->s_groups_count) + if (group >= ngroups) break; /* @@ -1078,7 +1068,7 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) return 0; } -static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len) +static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1091,15 +1081,12 @@ static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len) cur += 32; continue; } - if (lock) - mb_clear_bit_atomic(lock, cur, bm); - else - mb_clear_bit(cur, bm); + mb_clear_bit(cur, bm); cur++; } } -static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len) +static void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1112,10 +1099,7 @@ static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len) cur += 32; continue; } - if (lock) - mb_set_bit_atomic(lock, cur, bm); - else - mb_set_bit(cur, bm); + mb_set_bit(cur, bm); cur++; } } @@ -1131,7 +1115,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct super_block *sb = e4b->bd_sb; BUG_ON(first + count > (sb->s_blocksize << 3)); - BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); @@ -1212,7 +1196,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, int ord; void *buddy; - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, order, &max); @@ -1276,7 +1260,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); @@ -1330,8 +1314,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) e4b->bd_info->bb_counters[ord]++; } - mb_set_bits(sb_bgl_lock(EXT4_SB(e4b->bd_sb), ex->fe_group), - EXT4_MB_BITMAP(e4b), ex->fe_start, len0); + mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0); mb_check_buddy(e4b); return ret; @@ -1726,7 +1709,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, unsigned free, fragments; unsigned i, bits; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); - struct ext4_group_desc *desc; struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < 0 || cr >= 4); @@ -1742,10 +1724,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, switch (cr) { case 0: BUG_ON(ac->ac_2order == 0); - /* If this group is uninitialized, skip it initially */ - desc = ext4_get_group_desc(ac->ac_sb, group, NULL); - if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) - return 0; /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && @@ -1788,6 +1766,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group) int block, pnum; int blocks_per_page; int groups_per_page; + ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t first_group; struct ext4_group_info *grp; @@ -1807,7 +1786,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group) /* read all groups the page covers into the cache */ for (i = 0; i < groups_per_page; i++) { - if ((first_group + i) >= EXT4_SB(sb)->s_groups_count) + if ((first_group + i) >= ngroups) break; grp = ext4_get_group_info(sb, first_group + i); /* take all groups write allocation @@ -1945,8 +1924,7 @@ err: static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { - ext4_group_t group; - ext4_group_t i; + ext4_group_t ngroups, group, i; int cr; int err = 0; int bsbits; @@ -1957,6 +1935,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) sb = ac->ac_sb; sbi = EXT4_SB(sb); + ngroups = ext4_get_groups_count(sb); BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ @@ -2017,11 +1996,11 @@ repeat: */ group = ac->ac_g_ex.fe_group; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; group++, i++) { + for (i = 0; i < ngroups; group++, i++) { struct ext4_group_info *grp; struct ext4_group_desc *desc; - if (group == EXT4_SB(sb)->s_groups_count) + if (group == ngroups) group = 0; /* quick check to skip empty groups */ @@ -2064,9 +2043,7 @@ repeat: ac->ac_groups_scanned++; desc = ext4_get_group_desc(sb, group, NULL); - if (cr == 0 || (desc->bg_flags & - cpu_to_le16(EXT4_BG_BLOCK_UNINIT) && - ac->ac_2order != 0)) + if (cr == 0) ext4_mb_simple_scan_group(ac, &e4b); else if (cr == 1 && ac->ac_g_ex.fe_len == sbi->s_stripe) @@ -2315,12 +2292,10 @@ static struct file_operations ext4_mb_seq_history_fops = { static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = seq->private; - struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; - if (*pos < 0 || *pos >= sbi->s_groups_count) + if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; - group = *pos + 1; return (void *) ((unsigned long) group); } @@ -2328,11 +2303,10 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = seq->private; - struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ++*pos; - if (*pos < 0 || *pos >= sbi->s_groups_count) + if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); @@ -2420,7 +2394,8 @@ static void ext4_mb_history_release(struct super_block *sb) if (sbi->s_proc != NULL) { remove_proc_entry("mb_groups", sbi->s_proc); - remove_proc_entry("mb_history", sbi->s_proc); + if (sbi->s_mb_history_max) + remove_proc_entry("mb_history", sbi->s_proc); } kfree(sbi->s_mb_history); } @@ -2431,17 +2406,17 @@ static void ext4_mb_history_init(struct super_block *sb) int i; if (sbi->s_proc != NULL) { - proc_create_data("mb_history", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_history_fops, sb); + if (sbi->s_mb_history_max) + proc_create_data("mb_history", S_IRUGO, sbi->s_proc, + &ext4_mb_seq_history_fops, sb); proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, &ext4_mb_seq_groups_fops, sb); } - sbi->s_mb_history_max = 1000; sbi->s_mb_history_cur = 0; spin_lock_init(&sbi->s_mb_history_lock); i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history); - sbi->s_mb_history = kzalloc(i, GFP_KERNEL); + sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL; /* if we can't allocate history, then we simple won't use it */ } @@ -2451,7 +2426,7 @@ ext4_mb_store_history(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_mb_history h; - if (unlikely(sbi->s_mb_history == NULL)) + if (sbi->s_mb_history == NULL) return; if (!(ac->ac_op & sbi->s_mb_history_filter)) @@ -2587,6 +2562,7 @@ void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add) static int ext4_mb_init_backend(struct super_block *sb) { + ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int metalen; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2598,7 +2574,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_group_desc *desc; /* This is the number of blocks used by GDT */ - num_meta_group_infos = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - + num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); /* @@ -2644,7 +2620,7 @@ static int ext4_mb_init_backend(struct super_block *sb) for (i = 0; i < num_meta_group_infos; i++) { if ((i + 1) == num_meta_group_infos) metalen = sizeof(*meta_group_info) * - (sbi->s_groups_count - + (ngroups - (i << EXT4_DESC_PER_BLOCK_BITS(sb))); meta_group_info = kmalloc(metalen, GFP_KERNEL); if (meta_group_info == NULL) { @@ -2655,7 +2631,7 @@ static int ext4_mb_init_backend(struct super_block *sb) sbi->s_group_info[i] = meta_group_info; } - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { printk(KERN_ERR @@ -2761,7 +2737,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) return 0; } -/* need to called with ext4 group lock (ext4_lock_group) */ +/* need to called with the ext4 group lock held */ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; @@ -2781,13 +2757,14 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) int ext4_mb_release(struct super_block *sb) { + ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo; struct ext4_sb_info *sbi = EXT4_SB(sb); if (sbi->s_group_info) { - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { grinfo = ext4_get_group_info(sb, i); #ifdef DOUBLE_CHECK kfree(grinfo->bb_bitmap); @@ -2797,7 +2774,7 @@ int ext4_mb_release(struct super_block *sb) ext4_unlock_group(sb, i); kfree(grinfo); } - num_meta_group_infos = (sbi->s_groups_count + + num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); for (i = 0; i < num_meta_group_infos; i++) @@ -2984,27 +2961,25 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, + le32_to_cpu(es->s_first_data_block); len = ac->ac_b_ex.fe_len; - if (in_range(ext4_block_bitmap(sb, gdp), block, len) || - in_range(ext4_inode_bitmap(sb, gdp), block, len) || - in_range(block, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group) || - in_range(block + len - 1, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group)) { + if (!ext4_data_block_valid(sbi, block, len)) { ext4_error(sb, __func__, - "Allocating block %llu in system zone of %d group\n", - block, ac->ac_b_ex.fe_group); + "Allocating blocks %llu-%llu which overlap " + "fs metadata\n", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and repeat the block allocation * We leak some of the blocks here. */ - mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group), - bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); + ext4_lock_group(sb, ac->ac_b_ex.fe_group); + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len); + ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) err = -EAGAIN; goto out_err; } + + ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK { int i; @@ -3014,9 +2989,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } } #endif - spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); - mb_set_bits(NULL, bitmap_bh->b_data, - ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_blks_set(sb, gdp, @@ -3026,7 +2999,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_blks_set(sb, gdp, len); gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); - spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); + + ext4_unlock_group(sb, ac->ac_b_ex.fe_group); percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative @@ -3459,7 +3433,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) * the function goes through all block freed in the group * but not yet committed and marks them used in in-core bitmap. * buddy must be generated from this bitmap - * Need to be called with ext4 group lock (ext4_lock_group) + * Need to be called with the ext4 group lock held */ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group) @@ -3473,9 +3447,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, node); - mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group), - bitmap, entry->start_blk, - entry->count); + mb_set_bits(bitmap, entry->start_blk, entry->count); n = rb_next(n); } return; @@ -3484,7 +3456,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap - * Need to be called with ext4 group lock (ext4_lock_group) + * Need to be called with ext4 group lock held */ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) @@ -3516,8 +3488,7 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); - mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group), - bitmap, start, len); + mb_set_bits(bitmap, start, len); preallocated += len; count++; } @@ -4121,7 +4092,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode, static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - ext4_group_t i; + ext4_group_t ngroups, i; printk(KERN_ERR "EXT4-fs: Can't allocate:" " Allocation context details:\n"); @@ -4145,7 +4116,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned, ac->ac_found); printk(KERN_ERR "EXT4-fs: groups: \n"); - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + ngroups = ext4_get_groups_count(sb); + for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; @@ -4469,13 +4441,13 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0; trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d", sb->s_id, needed); - for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) { + for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, needed); freed += ret; needed -= ret; @@ -4859,29 +4831,25 @@ do_more: new_entry->group = block_group; new_entry->count = count; new_entry->t_tid = handle->h_transaction->t_tid; + ext4_lock_group(sb, block_group); - mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data, - bit, count); + mb_clear_bits(bitmap_bh->b_data, bit, count); ext4_mb_free_metadata(handle, &e4b, new_entry); - ext4_unlock_group(sb, block_group); } else { - ext4_lock_group(sb, block_group); /* need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ - mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data, - bit, count); + ext4_lock_group(sb, block_group); + mb_clear_bits(bitmap_bh->b_data, bit, count); mb_free_blocks(inode, &e4b, bit, count); ext4_mb_return_to_preallocation(inode, &e4b, block, count); - ext4_unlock_group(sb, block_group); } - spin_lock(sb_bgl_lock(sbi, block_group)); ret = ext4_free_blks_count(sb, gdp) + count; ext4_free_blks_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeblocks_counter, count); if (sbi->s_log_groups_per_flex) { diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index dd9e6cd5f6cf..75e34f69215b 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -23,7 +23,6 @@ #include <linux/mutex.h> #include "ext4_jbd2.h" #include "ext4.h" -#include "group.h" /* * with AGGRESSIVE_CHECK allocator runs consistency checks over diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 22098e1cd085..07eb6649e4fa 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -37,7 +37,6 @@ #include "ext4.h" #include "ext4_jbd2.h" -#include "namei.h" #include "xattr.h" #include "acl.h" @@ -750,7 +749,7 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, ext4fs_dirhash(de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; - map_tail->offs = (u16) ((char *) de - base); + map_tail->offs = ((char *) de - base)>>2; map_tail->size = le16_to_cpu(de->rec_len); count++; cond_resched(); @@ -1148,7 +1147,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, unsigned rec_len = 0; while (count--) { - struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs); + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) + (from + (map->offs<<2)); rec_len = EXT4_DIR_REC_LEN(de->name_len); memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = @@ -1997,7 +1997,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) if (!ext4_handle_valid(handle)) return 0; - lock_super(sb); + mutex_lock(&EXT4_SB(sb)->s_orphan_lock); if (!list_empty(&EXT4_I(inode)->i_orphan)) goto out_unlock; @@ -2006,9 +2006,13 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* @@@ FIXME: Observation from aviro: * I think I can trigger J_ASSERT in ext4_orphan_add(). We block - * here (on lock_super()), so race with ext4_link() which might bump + * here (on s_orphan_lock), so race with ext4_link() which might bump * ->i_nlink. For, say it, character device. Not a regular file, * not a directory, not a symlink and ->i_nlink > 0. + * + * tytso, 4/25/2009: I'm not sure how that could happen; + * shouldn't the fs core protect us from these sort of + * unlink()/link() races? */ J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); @@ -2045,7 +2049,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out_unlock: - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_orphan_lock); ext4_std_error(inode->i_sb, err); return err; } @@ -2066,11 +2070,9 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (!ext4_handle_valid(handle)) return 0; - lock_super(inode->i_sb); - if (list_empty(&ei->i_orphan)) { - unlock_super(inode->i_sb); - return 0; - } + mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock); + if (list_empty(&ei->i_orphan)) + goto out; ino_next = NEXT_ORPHAN(inode); prev = ei->i_orphan.prev; @@ -2120,7 +2122,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) out_err: ext4_std_error(inode->i_sb, err); out: - unlock_super(inode->i_sb); + mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock); return err; out_brelse: @@ -2533,6 +2535,7 @@ const struct inode_operations ext4_dir_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext4_permission, + .fiemap = ext4_fiemap, }; const struct inode_operations ext4_special_inode_operations = { diff --git a/fs/ext4/namei.h b/fs/ext4/namei.h deleted file mode 100644 index 5e4dfff36a00..000000000000 --- a/fs/ext4/namei.h +++ /dev/null @@ -1,8 +0,0 @@ -/* linux/fs/ext4/namei.h - * - * Copyright (C) 2005 Simtec Electronics - * Ben Dooks <ben@simtec.co.uk> - * -*/ - -extern struct dentry *ext4_get_parent(struct dentry *child); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 546c7dd869e1..27eb289eea37 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include "ext4_jbd2.h" -#include "group.h" #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) @@ -193,7 +192,7 @@ static int setup_new_group_blocks(struct super_block *sb, if (IS_ERR(handle)) return PTR_ERR(handle); - lock_super(sb); + mutex_lock(&sbi->s_resize_lock); if (input->group != sbi->s_groups_count) { err = -EBUSY; goto exit_journal; @@ -302,7 +301,7 @@ exit_bh: brelse(bh); exit_journal: - unlock_super(sb); + mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; @@ -643,11 +642,12 @@ exit_free: * important part is that the new block and inode counts are in the backup * superblocks, and the location of the new group metadata in the GDT backups. * - * We do not need lock_super() for this, because these blocks are not - * otherwise touched by the filesystem code when it is mounted. We don't - * need to worry about last changing from sbi->s_groups_count, because the - * worst that can happen is that we do not copy the full number of backups - * at this time. The resize which changed s_groups_count will backup again. + * We do not need take the s_resize_lock for this, because these + * blocks are not otherwise touched by the filesystem code when it is + * mounted. We don't need to worry about last changing from + * sbi->s_groups_count, because the worst that can happen is that we + * do not copy the full number of backups at this time. The resize + * which changed s_groups_count will backup again. */ static void update_backups(struct super_block *sb, int blk_off, char *data, int size) @@ -809,7 +809,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) goto exit_put; } - lock_super(sb); + mutex_lock(&sbi->s_resize_lock); if (input->group != sbi->s_groups_count) { ext4_warning(sb, __func__, "multiple resizers run on filesystem!"); @@ -840,7 +840,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) /* * OK, now we've set up the new group. Time to make it active. * - * Current kernels don't lock all allocations via lock_super(), + * We do not lock all allocations via s_resize_lock * so we have to be safe wrt. concurrent accesses the group * data. So we need to be careful to set all of the relevant * group descriptor data etc. *before* we enable the group. @@ -900,12 +900,12 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * * The precise rules we use are: * - * * Writers of s_groups_count *must* hold lock_super + * * Writers of s_groups_count *must* hold s_resize_lock * AND * * Writers must perform a smp_wmb() after updating all dependent * data and before modifying the groups count * - * * Readers must hold lock_super() over the access + * * Readers must hold s_resize_lock over the access * OR * * Readers must perform an smp_rmb() after reading the groups count * and before reading any dependent data. @@ -948,7 +948,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) sb->s_dirt = 1; exit_journal: - unlock_super(sb); + mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; if (!err) { @@ -986,7 +986,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, /* We don't need to worry about locking wrt other resizers just * yet: we're going to revalidate es->s_blocks_count after - * taking lock_super() below. */ + * taking the s_resize_lock below. */ o_blocks_count = ext4_blocks_count(es); o_groups_count = EXT4_SB(sb)->s_groups_count; @@ -1056,11 +1056,11 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, goto exit_put; } - lock_super(sb); + mutex_lock(&EXT4_SB(sb)->s_resize_lock); if (o_blocks_count != ext4_blocks_count(es)) { ext4_warning(sb, __func__, "multiple resizers run on filesystem!"); - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_journal_stop(handle); err = -EBUSY; goto exit_put; @@ -1070,14 +1070,14 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, EXT4_SB(sb)->s_sbh))) { ext4_warning(sb, __func__, "error %d on journal write access", err); - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_journal_stop(handle); goto exit_put; } ext4_blocks_count_set(es, o_blocks_count + add); ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); sb->s_dirt = 1; - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2958f4e6f222..f016707597a7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -20,6 +20,7 @@ #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> +#include <linux/vmalloc.h> #include <linux/jbd2.h> #include <linux/slab.h> #include <linux/init.h> @@ -45,16 +46,20 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "namei.h" -#include "group.h" + +static int default_mb_history_length = 1000; + +module_param_named(default_mb_history_length, default_mb_history_length, + int, 0644); +MODULE_PARM_DESC(default_mb_history_length, + "Default number of entries saved for mb_history"); struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); -static int ext4_commit_super(struct super_block *sb, - struct ext4_super_block *es, int sync); +static int ext4_commit_super(struct super_block *sb, int sync); static void ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static void ext4_clear_journal_err(struct super_block *sb, @@ -74,7 +79,7 @@ ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -82,7 +87,7 @@ ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, @@ -90,7 +95,7 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb, { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_blks_count(struct super_block *sb, @@ -98,7 +103,7 @@ __u32 ext4_free_blks_count(struct super_block *sb, { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, @@ -106,7 +111,7 @@ __u32 ext4_free_inodes_count(struct super_block *sb, { return le16_to_cpu(bg->bg_free_inodes_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, @@ -114,7 +119,7 @@ __u32 ext4_used_dirs_count(struct super_block *sb, { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, @@ -122,7 +127,7 @@ __u32 ext4_itable_unused_count(struct super_block *sb, { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, @@ -202,8 +207,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) journal = EXT4_SB(sb)->s_journal; if (journal) { if (is_journal_aborted(journal)) { - ext4_abort(sb, __func__, - "Detected aborted journal"); + ext4_abort(sb, __func__, "Detected aborted journal"); return ERR_PTR(-EROFS); } return jbd2_journal_start(journal, nblocks); @@ -302,10 +306,10 @@ static void ext4_handle_error(struct super_block *sb) jbd2_journal_abort(journal, -EIO); } if (test_opt(sb, ERRORS_RO)) { - printk(KERN_CRIT "Remounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); sb->s_flags |= MS_RDONLY; } - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); if (test_opt(sb, ERRORS_PANIC)) panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); @@ -395,8 +399,6 @@ void ext4_abort(struct super_block *sb, const char *function, { va_list args; - printk(KERN_CRIT "ext4_abort called.\n"); - va_start(args, fmt); printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function); vprintk(fmt, args); @@ -409,7 +411,7 @@ void ext4_abort(struct super_block *sb, const char *function, if (sb->s_flags & MS_RDONLY) return; - printk(KERN_CRIT "Remounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; @@ -417,6 +419,18 @@ void ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); } +void ext4_msg (struct super_block * sb, const char *prefix, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + printk("%sEXT4-fs (%s): ", prefix, sb->s_id); + vprintk(fmt, args); + printk("\n"); + va_end(args); +} + void ext4_warning(struct super_block *sb, const char *function, const char *fmt, ...) { @@ -431,7 +445,7 @@ void ext4_warning(struct super_block *sb, const char *function, } void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp, - const char *function, const char *fmt, ...) + const char *function, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { @@ -447,7 +461,7 @@ __acquires(bitlock) if (test_opt(sb, ERRORS_CONT)) { EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 0); + ext4_commit_super(sb, 0); return; } ext4_unlock_group(sb, grp); @@ -467,7 +481,6 @@ __acquires(bitlock) return; } - void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -496,7 +509,7 @@ void ext4_update_dynamic_rev(struct super_block *sb) /* * Open the external journal device */ -static struct block_device *ext4_blkdev_get(dev_t dev) +static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; char b[BDEVNAME_SIZE]; @@ -507,7 +520,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev) return bdev; fail: - printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n", + ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld", __bdevname(dev, b), PTR_ERR(bdev)); return NULL; } @@ -543,8 +556,8 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; - printk(KERN_ERR "sb orphan head is %d\n", - le32_to_cpu(sbi->s_es->s_last_orphan)); + ext4_msg(sb, KERN_ERR, "sb orphan head is %d", + le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { @@ -563,6 +576,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); ext4_xattr_put_super(sb); @@ -576,7 +590,7 @@ static void ext4_put_super(struct super_block *sb) if (!(sb->s_flags & MS_RDONLY)) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } if (sbi->s_proc) { remove_proc_entry(sb->s_id, ext4_proc_root); @@ -586,7 +600,10 @@ static void ext4_put_super(struct super_block *sb) for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); kfree(sbi->s_group_desc); - kfree(sbi->s_flex_groups); + if (is_vmalloc_addr(sbi->s_flex_groups)) + vfree(sbi->s_flex_groups); + else + kfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -629,7 +646,6 @@ static void ext4_put_super(struct super_block *sb) lock_kernel(); kfree(sbi->s_blockgroup_lock); kfree(sbi); - return; } static struct kmem_cache *ext4_inode_cachep; @@ -644,6 +660,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; + #ifdef CONFIG_EXT4_FS_POSIX_ACL ei->i_acl = EXT4_ACL_NOT_CACHED; ei->i_default_acl = EXT4_ACL_NOT_CACHED; @@ -664,14 +681,16 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_allocated_meta_blocks = 0; ei->i_delalloc_reserved_flag = 0; spin_lock_init(&(ei->i_block_reservation_lock)); + return &ei->vfs_inode; } static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { - printk("EXT4 Inode %p: orphan list check failed!\n", - EXT4_I(inode)); + ext4_msg(inode->i_sb, KERN_ERR, + "Inode %lu (%p): orphan list check failed!", + inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); @@ -870,12 +889,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",noauto_da_alloc"); ext4_show_quota_options(seq, sb); + return 0; } - static struct inode *ext4_nfs_get_inode(struct super_block *sb, - u64 ino, u32 generation) + u64 ino, u32 generation) { struct inode *inode; @@ -904,14 +923,14 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) + int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) + int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); @@ -923,7 +942,8 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, * which would prevent try_to_free_buffers() from freeing them, we must use * jbd2 layer's try_to_free_buffers() function to release them. */ -static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait) +static int bdev_try_to_free_page(struct super_block *sb, struct page *page, + gfp_t wait) { journal_t *journal = EXT4_SB(sb)->s_journal; @@ -992,7 +1012,6 @@ static const struct super_operations ext4_sops = { .dirty_inode = ext4_dirty_inode, .delete_inode = ext4_delete_inode, .put_super = ext4_put_super, - .write_super = ext4_write_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, @@ -1007,6 +1026,25 @@ static const struct super_operations ext4_sops = { .bdev_try_to_free_page = bdev_try_to_free_page, }; +static const struct super_operations ext4_nojournal_sops = { + .alloc_inode = ext4_alloc_inode, + .destroy_inode = ext4_destroy_inode, + .write_inode = ext4_write_inode, + .dirty_inode = ext4_dirty_inode, + .delete_inode = ext4_delete_inode, + .write_super = ext4_write_super, + .put_super = ext4_put_super, + .statfs = ext4_statfs, + .remount_fs = ext4_remount, + .clear_inode = ext4_clear_inode, + .show_options = ext4_show_options, +#ifdef CONFIG_QUOTA + .quota_read = ext4_quota_read, + .quota_write = ext4_quota_write, +#endif + .bdev_try_to_free_page = bdev_try_to_free_page, +}; + static const struct export_operations ext4_export_ops = { .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, @@ -1023,12 +1061,13 @@ enum { Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, + Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, + Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio }; @@ -1069,6 +1108,7 @@ static const match_table_t tokens = { {Opt_data_writeback, "data=writeback"}, {Opt_data_err_abort, "data_err=abort"}, {Opt_data_err_ignore, "data_err=ignore"}, + {Opt_mb_history_length, "mb_history_length=%u"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, @@ -1087,6 +1127,8 @@ static const match_table_t tokens = { {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_block_validity, "block_validity"}, + {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, {Opt_journal_ioprio, "journal_ioprio=%u"}, {Opt_auto_da_alloc, "auto_da_alloc=%u"}, @@ -1102,8 +1144,9 @@ static ext4_fsblk_t get_sb_block(void **data) if (!options || strncmp(options, "sb=", 3) != 0) return 1; /* Default location */ + options += 3; - /*todo: use simple_strtoll with >32bit ext4 */ + /* TODO: use simple_strtoll with >32bit ext4 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n", @@ -1113,6 +1156,7 @@ static ext4_fsblk_t get_sb_block(void **data) if (*options == ',') options++; *data = (void *) options; + return sb_block; } @@ -1206,8 +1250,7 @@ static int parse_options(char *options, struct super_block *sb, #else case Opt_user_xattr: case Opt_nouser_xattr: - printk(KERN_ERR "EXT4 (no)user_xattr options " - "not supported\n"); + ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported"); break; #endif #ifdef CONFIG_EXT4_FS_POSIX_ACL @@ -1220,8 +1263,7 @@ static int parse_options(char *options, struct super_block *sb, #else case Opt_acl: case Opt_noacl: - printk(KERN_ERR "EXT4 (no)acl options " - "not supported\n"); + ext4_msg(sb, KERN_ERR, "(no)acl options not supported"); break; #endif case Opt_journal_update: @@ -1231,16 +1273,16 @@ static int parse_options(char *options, struct super_block *sb, user to specify an existing inode to be the journal file. */ if (is_remount) { - printk(KERN_ERR "EXT4-fs: cannot specify " - "journal on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); return 0; } set_opt(sbi->s_mount_opt, UPDATE_JOURNAL); break; case Opt_journal_dev: if (is_remount) { - printk(KERN_ERR "EXT4-fs: cannot specify " - "journal on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); return 0; } if (match_int(&args[0], &option)) @@ -1294,9 +1336,8 @@ static int parse_options(char *options, struct super_block *sb, if (is_remount) { if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS) != data_opt) { - printk(KERN_ERR - "EXT4-fs: cannot change data " - "mode on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot change data mode on remount"); return 0; } } else { @@ -1310,6 +1351,13 @@ static int parse_options(char *options, struct super_block *sb, case Opt_data_err_ignore: clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT); break; + case Opt_mb_history_length: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + sbi->s_mb_history_max = option; + break; #ifdef CONFIG_QUOTA case Opt_usrjquota: qtype = USRQUOTA; @@ -1319,31 +1367,31 @@ static int parse_options(char *options, struct super_block *sb, set_qf_name: if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { - printk(KERN_ERR - "EXT4-fs: Cannot change journaled " - "quota options when quota turned on.\n"); + ext4_msg(sb, KERN_ERR, + "Cannot change journaled " + "quota options when quota turned on"); return 0; } qname = match_strdup(&args[0]); if (!qname) { - printk(KERN_ERR - "EXT4-fs: not enough memory for " - "storing quotafile name.\n"); + ext4_msg(sb, KERN_ERR, + "Not enough memory for " + "storing quotafile name"); return 0; } if (sbi->s_qf_names[qtype] && strcmp(sbi->s_qf_names[qtype], qname)) { - printk(KERN_ERR - "EXT4-fs: %s quota file already " - "specified.\n", QTYPE2NAME(qtype)); + ext4_msg(sb, KERN_ERR, + "%s quota file already " + "specified", QTYPE2NAME(qtype)); kfree(qname); return 0; } sbi->s_qf_names[qtype] = qname; if (strchr(sbi->s_qf_names[qtype], '/')) { - printk(KERN_ERR - "EXT4-fs: quotafile must be on " - "filesystem root.\n"); + ext4_msg(sb, KERN_ERR, + "quotafile must be on " + "filesystem root"); kfree(sbi->s_qf_names[qtype]); sbi->s_qf_names[qtype] = NULL; return 0; @@ -1358,9 +1406,9 @@ set_qf_name: clear_qf_name: if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { - printk(KERN_ERR "EXT4-fs: Cannot change " + ext4_msg(sb, KERN_ERR, "Cannot change " "journaled quota options when " - "quota turned on.\n"); + "quota turned on"); return 0; } /* @@ -1377,9 +1425,9 @@ clear_qf_name: set_qf_format: if (sb_any_quota_loaded(sb) && sbi->s_jquota_fmt != qfmt) { - printk(KERN_ERR "EXT4-fs: Cannot change " + ext4_msg(sb, KERN_ERR, "Cannot change " "journaled quota options when " - "quota turned on.\n"); + "quota turned on"); return 0; } sbi->s_jquota_fmt = qfmt; @@ -1395,8 +1443,8 @@ set_qf_format: break; case Opt_noquota: if (sb_any_quota_loaded(sb)) { - printk(KERN_ERR "EXT4-fs: Cannot change quota " - "options when quota turned on.\n"); + ext4_msg(sb, KERN_ERR, "Cannot change quota " + "options when quota turned on"); return 0; } clear_opt(sbi->s_mount_opt, QUOTA); @@ -1407,8 +1455,8 @@ set_qf_format: case Opt_quota: case Opt_usrquota: case Opt_grpquota: - printk(KERN_ERR - "EXT4-fs: quota options not supported.\n"); + ext4_msg(sb, KERN_ERR, + "quota options not supported"); break; case Opt_usrjquota: case Opt_grpjquota: @@ -1416,9 +1464,8 @@ set_qf_format: case Opt_offgrpjquota: case Opt_jqfmt_vfsold: case Opt_jqfmt_vfsv0: - printk(KERN_ERR - "EXT4-fs: journaled quota options not " - "supported.\n"); + ext4_msg(sb, KERN_ERR, + "journaled quota options not supported"); break; case Opt_noquota: break; @@ -1443,8 +1490,9 @@ set_qf_format: break; case Opt_resize: if (!is_remount) { - printk("EXT4-fs: resize option only available " - "for remount\n"); + ext4_msg(sb, KERN_ERR, + "resize option only available " + "for remount"); return 0; } if (match_int(&args[0], &option) != 0) @@ -1474,14 +1522,21 @@ set_qf_format: case Opt_delalloc: set_opt(sbi->s_mount_opt, DELALLOC); break; + case Opt_block_validity: + set_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; + case Opt_noblock_validity: + clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; case Opt_inode_readahead_blks: if (match_int(&args[0], &option)) return 0; if (option < 0 || option > (1 << 30)) return 0; - if (option & (option - 1)) { - printk(KERN_ERR "EXT4-fs: inode_readahead_blks" - " must be a power of 2\n"); + if (!is_power_of_2(option)) { + ext4_msg(sb, KERN_ERR, + "EXT4-fs: inode_readahead_blks" + " must be a power of 2"); return 0; } sbi->s_inode_readahead_blks = option; @@ -1508,9 +1563,9 @@ set_qf_format: set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC); break; default: - printk(KERN_ERR - "EXT4-fs: Unrecognized mount option \"%s\" " - "or missing value\n", p); + ext4_msg(sb, KERN_ERR, + "Unrecognized mount option \"%s\" " + "or missing value", p); return 0; } } @@ -1528,21 +1583,21 @@ set_qf_format: (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) || (sbi->s_qf_names[GRPQUOTA] && (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) { - printk(KERN_ERR "EXT4-fs: old and new quota " - "format mixing.\n"); + ext4_msg(sb, KERN_ERR, "old and new quota " + "format mixing"); return 0; } if (!sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journaled quota format " - "not specified.\n"); + ext4_msg(sb, KERN_ERR, "journaled quota format " + "not specified"); return 0; } } else { if (sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journaled quota format " + ext4_msg(sb, KERN_ERR, "journaled quota format " "specified with no journaling " - "enabled.\n"); + "enabled"); return 0; } } @@ -1557,32 +1612,32 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int res = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { - printk(KERN_ERR "EXT4-fs warning: revision level too high, " - "forcing read-only mode\n"); + ext4_msg(sb, KERN_ERR, "revision level too high, " + "forcing read-only mode"); res = MS_RDONLY; } if (read_only) return res; if (!(sbi->s_mount_state & EXT4_VALID_FS)) - printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " + "running e2fsck is recommended"); else if ((sbi->s_mount_state & EXT4_ERROR_FS)) - printk(KERN_WARNING - "EXT4-fs warning: mounting fs with errors, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "warning: mounting fs with errors, " + "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) - printk(KERN_WARNING - "EXT4-fs warning: maximal mount count reached, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "warning: maximal mount count reached, " + "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds())) - printk(KERN_WARNING - "EXT4-fs warning: checktime reached, " - "running e2fsck is recommended\n"); - if (!sbi->s_journal) + ext4_msg(sb, KERN_WARNING, + "warning: checktime reached, " + "running e2fsck is recommended"); + if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); @@ -1592,7 +1647,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04lx]\n", @@ -1603,11 +1658,11 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, sbi->s_mount_opt); if (EXT4_SB(sb)->s_journal) { - printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n", - sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" : + ext4_msg(sb, KERN_INFO, "%s journal on %s", + EXT4_SB(sb)->s_journal->j_inode ? "internal" : "external", EXT4_SB(sb)->s_journal->j_devname); } else { - printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id); + ext4_msg(sb, KERN_INFO, "no journal"); } return res; } @@ -1616,10 +1671,10 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; - struct buffer_head *bh; ext4_group_t flex_group_count; ext4_group_t flex_group; int groups_per_flex = 0; + size_t size; int i; if (!sbi->s_es->s_log_groups_per_flex) { @@ -1634,16 +1689,21 @@ static int ext4_fill_flex_info(struct super_block *sb) flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex; - sbi->s_flex_groups = kzalloc(flex_group_count * - sizeof(struct flex_groups), GFP_KERNEL); + size = flex_group_count * sizeof(struct flex_groups); + sbi->s_flex_groups = kzalloc(size, GFP_KERNEL); + if (sbi->s_flex_groups == NULL) { + sbi->s_flex_groups = vmalloc(size); + if (sbi->s_flex_groups) + memset(sbi->s_flex_groups, 0, size); + } if (sbi->s_flex_groups == NULL) { - printk(KERN_ERR "EXT4-fs: not enough memory for " - "%u flex groups\n", flex_group_count); + ext4_msg(sb, KERN_ERR, "not enough memory for " + "%u flex groups", flex_group_count); goto failed; } for (i = 0; i < sbi->s_groups_count; i++) { - gdp = ext4_get_group_desc(sb, i, &bh); + gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); atomic_set(&sbi->s_flex_groups[flex_group].free_inodes, @@ -1724,44 +1784,44 @@ static int ext4_check_descriptors(struct super_block *sb) block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " - "(block %llu)!\n", i, block_bitmap); + "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap < first_block || inode_bitmap > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " - "(block %llu)!\n", i, inode_bitmap); + "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " - "(block %llu)!\n", i, inode_table); + "(block %llu)!", i, inode_table); return 0; } - spin_lock(sb_bgl_lock(sbi, i)); + ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " - "Checksum for group %u failed (%u!=%u)\n", - i, le16_to_cpu(ext4_group_desc_csum(sbi, i, - gdp)), le16_to_cpu(gdp->bg_checksum)); + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Checksum for group %u failed (%u!=%u)", + i, le16_to_cpu(ext4_group_desc_csum(sbi, i, + gdp)), le16_to_cpu(gdp->bg_checksum)); if (!(sb->s_flags & MS_RDONLY)) { - spin_unlock(sb_bgl_lock(sbi, i)); + ext4_unlock_group(sb, i); return 0; } } - spin_unlock(sb_bgl_lock(sbi, i)); + ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); - sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb)); + sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } @@ -1796,8 +1856,8 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (bdev_read_only(sb->s_bdev)) { - printk(KERN_ERR "EXT4-fs: write access " - "unavailable, skipping orphan cleanup.\n"); + ext4_msg(sb, KERN_ERR, "write access " + "unavailable, skipping orphan cleanup"); return; } @@ -1811,8 +1871,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n", - sb->s_id); + ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); sb->s_flags &= ~MS_RDONLY; } #ifdef CONFIG_QUOTA @@ -1823,9 +1882,9 @@ static void ext4_orphan_cleanup(struct super_block *sb, if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); if (ret < 0) - printk(KERN_ERR - "EXT4-fs: Cannot turn on journaled " - "quota: error %d\n", ret); + ext4_msg(sb, KERN_ERR, + "Cannot turn on journaled " + "quota: error %d", ret); } } #endif @@ -1842,16 +1901,16 @@ static void ext4_orphan_cleanup(struct super_block *sb, list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); vfs_dq_init(inode); if (inode->i_nlink) { - printk(KERN_DEBUG - "%s: truncating inode %lu to %lld bytes\n", + ext4_msg(sb, KERN_DEBUG, + "%s: truncating inode %lu to %lld bytes", __func__, inode->i_ino, inode->i_size); jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); ext4_truncate(inode); nr_truncates++; } else { - printk(KERN_DEBUG - "%s: deleting unreferenced inode %lu\n", + ext4_msg(sb, KERN_DEBUG, + "%s: deleting unreferenced inode %lu", __func__, inode->i_ino); jbd_debug(2, "deleting unreferenced inode %lu\n", inode->i_ino); @@ -1863,11 +1922,11 @@ static void ext4_orphan_cleanup(struct super_block *sb, #define PLURAL(x) (x), ((x) == 1) ? "" : "s" if (nr_orphans) - printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n", - sb->s_id, PLURAL(nr_orphans)); + ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted", + PLURAL(nr_orphans)); if (nr_truncates) - printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n", - sb->s_id, PLURAL(nr_truncates)); + ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", + PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA /* Turn quotas off */ for (i = 0; i < MAXQUOTAS; i++) { @@ -1877,6 +1936,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ } + /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk @@ -1927,19 +1987,19 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) loff_t res = EXT4_NDIR_BLOCKS; int meta_blocks; loff_t upper_limit; - /* This is calculated to be the largest file size for a - * dense, bitmapped file such that the total number of - * sectors in the file, including data and all indirect blocks, - * does not exceed 2^48 -1 - * __u32 i_blocks_lo and _u16 i_blocks_high representing the - * total number of 512 bytes blocks of the file + /* This is calculated to be the largest file size for a dense, block + * mapped file such that the file's total number of 512-byte sectors, + * including data and all indirect blocks, does not exceed (2^48 - 1). + * + * __u32 i_blocks_lo and _u16 i_blocks_high represent the total + * number of 512-byte sectors of the file. */ if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { /* - * !has_huge_files or CONFIG_LBD is not enabled - * implies the inode i_block represent total blocks in - * 512 bytes 32 == size of vfs inode i_blocks * 8 + * !has_huge_files or CONFIG_LBD not enabled implies that + * the inode i_block field represents total file blocks in + * 2^32 512-byte sectors == size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; @@ -1981,7 +2041,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) } static ext4_fsblk_t descriptor_loc(struct super_block *sb, - ext4_fsblk_t logical_sb_block, int nr) + ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; @@ -1995,6 +2055,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb, bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; + return (has_super + ext4_group_first_block_no(sb, bg)); } @@ -2091,8 +2152,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, if (parse_strtoul(buf, 0x40000000, &t)) return -EINVAL; - /* inode_readahead_blks must be a power of 2 */ - if (t & (t-1)) + if (!is_power_of_2(t)) return -EINVAL; sbi->s_inode_readahead_blks = t; @@ -2100,7 +2160,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, } static ssize_t sbi_ui_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) + struct ext4_sb_info *sbi, char *buf) { unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); @@ -2205,7 +2265,6 @@ static struct kobj_type ext4_ktype = { static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) - { struct buffer_head *bh; struct ext4_super_block *es = NULL; @@ -2256,7 +2315,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { - printk(KERN_ERR "EXT4-fs: unable to set blocksize\n"); + ext4_msg(sb, KERN_ERR, "unable to set blocksize"); goto out_fail; } @@ -2272,7 +2331,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (!(bh = sb_bread(sb, logical_sb_block))) { - printk(KERN_ERR "EXT4-fs: unable to read superblock\n"); + ext4_msg(sb, KERN_ERR, "unable to read superblock"); goto out_fail; } /* @@ -2321,6 +2380,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; + sbi->s_mb_history_max = default_mb_history_length; set_opt(sbi->s_mount_opt, BARRIER); @@ -2330,7 +2390,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ set_opt(sbi->s_mount_opt, DELALLOC); - if (!parse_options((char *) data, sb, &journal_devnum, &journal_ioprio, NULL, 0)) goto failed_mount; @@ -2342,9 +2401,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) || EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) || EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U))) - printk(KERN_WARNING - "EXT4-fs warning: feature flags set on rev 0 fs, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "feature flags set on rev 0 fs, " + "running e2fsck is recommended"); /* * Check feature flags regardless of the revision level, since we @@ -2353,16 +2412,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP); if (features) { - printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of " - "unsupported optional features (%x).\n", sb->s_id, + ext4_msg(sb, KERN_ERR, + "Couldn't mount because of " + "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & ~EXT4_FEATURE_INCOMPAT_SUPP)); goto failed_mount; } features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP); if (!(sb->s_flags & MS_RDONLY) && features) { - printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of " - "unsupported optional features (%x).\n", sb->s_id, + ext4_msg(sb, KERN_ERR, + "Couldn't mount RDWR because of " + "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); goto failed_mount; @@ -2376,9 +2437,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ if (sizeof(root->i_blocks) < sizeof(u64) && !(sb->s_flags & MS_RDONLY)) { - printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge " + ext4_msg(sb, KERN_ERR, "Filesystem with huge " "files cannot be mounted read-write " - "without CONFIG_LBD.\n", sb->s_id); + "without CONFIG_LBD"); goto failed_mount; } } @@ -2386,17 +2447,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { - printk(KERN_ERR - "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n", - blocksize, sb->s_id); + ext4_msg(sb, KERN_ERR, + "Unsupported filesystem blocksize %d", blocksize); goto failed_mount; } if (sb->s_blocksize != blocksize) { - /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { - printk(KERN_ERR "EXT4-fs: bad block size %d.\n", + ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); goto failed_mount; } @@ -2406,15 +2465,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) offset = do_div(logical_sb_block, blocksize); bh = sb_bread(sb, logical_sb_block); if (!bh) { - printk(KERN_ERR - "EXT4-fs: Can't read superblock on 2nd try.\n"); + ext4_msg(sb, KERN_ERR, + "Can't read superblock on 2nd try"); goto failed_mount; } es = (struct ext4_super_block *)(((char *)bh->b_data) + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { - printk(KERN_ERR - "EXT4-fs: Magic mismatch, very weird !\n"); + ext4_msg(sb, KERN_ERR, + "Magic mismatch, very weird!"); goto failed_mount; } } @@ -2432,30 +2491,33 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > blocksize)) { - printk(KERN_ERR - "EXT4-fs: unsupported inode size: %d\n", + ext4_msg(sb, KERN_ERR, + "unsupported inode size: %d", sbi->s_inode_size); goto failed_mount; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); } + sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { - printk(KERN_ERR - "EXT4-fs: unsupported descriptor size %lu\n", + ext4_msg(sb, KERN_ERR, + "unsupported descriptor size %lu", sbi->s_desc_size); goto failed_mount; } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; + sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0) goto cantfind_ext4; + sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) goto cantfind_ext4; @@ -2466,6 +2528,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_mount_state = le16_to_cpu(es->s_state); sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); + for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; @@ -2483,25 +2546,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (sbi->s_blocks_per_group > blocksize * 8) { - printk(KERN_ERR - "EXT4-fs: #blocks per group too big: %lu\n", + ext4_msg(sb, KERN_ERR, + "#blocks per group too big: %lu", sbi->s_blocks_per_group); goto failed_mount; } if (sbi->s_inodes_per_group > blocksize * 8) { - printk(KERN_ERR - "EXT4-fs: #inodes per group too big: %lu\n", + ext4_msg(sb, KERN_ERR, + "#inodes per group too big: %lu", sbi->s_inodes_per_group); goto failed_mount; } if (ext4_blocks_count(es) > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { - printk(KERN_ERR "EXT4-fs: filesystem on %s:" - " too large to mount safely\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "filesystem" + " too large to mount safely"); if (sizeof(sector_t) < 8) - printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not " - "enabled\n"); + ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled"); goto failed_mount; } @@ -2511,21 +2573,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* check blocks count against device size */ blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits; if (blocks_count && ext4_blocks_count(es) > blocks_count) { - printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu " - "exceeds size of device (%llu blocks)\n", + ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " + "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); goto failed_mount; } - /* - * It makes no sense for the first data block to be beyond the end - * of the filesystem. - */ - if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { - printk(KERN_WARNING "EXT4-fs: bad geometry: first data" - "block %u is beyond end of filesystem (%llu)\n", - le32_to_cpu(es->s_first_data_block), - ext4_blocks_count(es)); + /* + * It makes no sense for the first data block to be beyond the end + * of the filesystem. + */ + if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { + ext4_msg(sb, KERN_WARNING, "bad geometry: first data" + "block %u is beyond end of filesystem (%llu)", + le32_to_cpu(es->s_first_data_block), + ext4_blocks_count(es)); goto failed_mount; } blocks_count = (ext4_blocks_count(es) - @@ -2533,9 +2595,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { - printk(KERN_WARNING "EXT4-fs: groups count too large: %u " + ext4_msg(sb, KERN_WARNING, "groups count too large: %u " "(block count %llu, first data block %u, " - "blocks per group %lu)\n", sbi->s_groups_count, + "blocks per group %lu)", sbi->s_groups_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); @@ -2547,7 +2609,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { - printk(KERN_ERR "EXT4-fs: not enough memory\n"); + ext4_msg(sb, KERN_ERR, "not enough memory"); goto failed_mount; } @@ -2562,21 +2624,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) block = descriptor_loc(sb, logical_sb_block, i); sbi->s_group_desc[i] = sb_bread(sb, block); if (!sbi->s_group_desc[i]) { - printk(KERN_ERR "EXT4-fs: " - "can't read group descriptor %d\n", i); + ext4_msg(sb, KERN_ERR, + "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } } if (!ext4_check_descriptors(sb)) { - printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n"); + ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); goto failed_mount2; } if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) if (!ext4_fill_flex_info(sb)) { - printk(KERN_ERR - "EXT4-fs: unable to initialize " - "flex_bg meta info!\n"); + ext4_msg(sb, KERN_ERR, + "unable to initialize " + "flex_bg meta info!"); goto failed_mount2; } @@ -2598,7 +2660,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); } if (err) { - printk(KERN_ERR "EXT4-fs: insufficient memory\n"); + ext4_msg(sb, KERN_ERR, "insufficient memory"); goto failed_mount3; } @@ -2607,7 +2669,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* * set up enough so that it can read an inode */ - sb->s_op = &ext4_sops; + if (!test_opt(sb, NOLOAD) && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) + sb->s_op = &ext4_sops; + else + sb->s_op = &ext4_nojournal_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_QUOTA @@ -2615,6 +2681,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->dq_op = &ext4_quota_operations; #endif INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ + mutex_init(&sbi->s_orphan_lock); + mutex_init(&sbi->s_resize_lock); sb->s_root = NULL; @@ -2632,13 +2700,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount3; if (!(sb->s_flags & MS_RDONLY) && EXT4_SB(sb)->s_journal->j_failed_commit) { - printk(KERN_CRIT "EXT4-fs error (device %s): " + ext4_msg(sb, KERN_CRIT, "error: " "ext4_fill_super: Journal transaction " - "%u is corrupt\n", sb->s_id, + "%u is corrupt", EXT4_SB(sb)->s_journal->j_failed_commit); if (test_opt(sb, ERRORS_RO)) { - printk(KERN_CRIT - "Mounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, + "Mounting filesystem read-only"); sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); @@ -2646,14 +2714,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (test_opt(sb, ERRORS_PANIC)) { EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); goto failed_mount4; } } } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { - printk(KERN_ERR "EXT4-fs: required journal recovery " - "suppressed and not mounted read-only\n"); + ext4_msg(sb, KERN_ERR, "required journal recovery " + "suppressed and not mounted read-only"); goto failed_mount4; } else { clear_opt(sbi->s_mount_opt, DATA_FLAGS); @@ -2666,7 +2734,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (ext4_blocks_count(es) > 0xffffffffULL && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { - printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n"); + ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto failed_mount4; } @@ -2704,8 +2772,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { - printk(KERN_ERR "EXT4-fs: Journal does not support " - "requested data journaling mode\n"); + ext4_msg(sb, KERN_ERR, "Journal does not support " + "requested data journaling mode"); goto failed_mount4; } default: @@ -2717,8 +2785,8 @@ no_journal: if (test_opt(sb, NOBH)) { if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) { - printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - " - "its supported only with writeback mode\n"); + ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - " + "its supported only with writeback mode"); clear_opt(sbi->s_mount_opt, NOBH); } } @@ -2729,18 +2797,18 @@ no_journal: root = ext4_iget(sb, EXT4_ROOT_INO); if (IS_ERR(root)) { - printk(KERN_ERR "EXT4-fs: get root inode failed\n"); + ext4_msg(sb, KERN_ERR, "get root inode failed"); ret = PTR_ERR(root); goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { iput(root); - printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n"); + ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); goto failed_mount4; } sb->s_root = d_alloc_root(root); if (!sb->s_root) { - printk(KERN_ERR "EXT4-fs: get root dentry failed\n"); + ext4_msg(sb, KERN_ERR, "get root dentry failed"); iput(root); ret = -ENOMEM; goto failed_mount4; @@ -2769,22 +2837,29 @@ no_journal: sbi->s_inode_size) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; - printk(KERN_INFO "EXT4-fs: required extra inode space not" - "available.\n"); + ext4_msg(sb, KERN_INFO, "required extra inode space not" + "available"); } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - " - "requested data journaling mode\n"); + ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - " + "requested data journaling mode"); clear_opt(sbi->s_mount_opt, DELALLOC); } else if (test_opt(sb, DELALLOC)) - printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); + ext4_msg(sb, KERN_INFO, "delayed allocation enabled"); + + err = ext4_setup_system_zone(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)\n", err); + goto failed_mount4; + } ext4_ext_init(sb); err = ext4_mb_init(sb, needs_recovery); if (err) { - printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n", - err); + ext4_msg(sb, KERN_ERR, "failed to initalize mballoc (%d)", + err); goto failed_mount4; } @@ -2798,19 +2873,11 @@ no_journal: goto failed_mount4; }; - /* - * akpm: core read_super() calls in here with the superblock locked. - * That deadlocks, because orphan cleanup needs to lock the superblock - * in numerous places. Here we just pop the lock - it's relatively - * harmless, because we are now ready to accept write_super() requests, - * and aviro says that's the only reason for hanging onto the - * superblock lock. - */ EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { - printk(KERN_INFO "EXT4-fs: recovery complete.\n"); + ext4_msg(sb, KERN_INFO, "recovery complete"); ext4_mark_recovery_complete(sb, es); } if (EXT4_SB(sb)->s_journal) { @@ -2823,25 +2890,30 @@ no_journal: } else descr = "out journal"; - printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n", - sb->s_id, descr); + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr); lock_kernel(); return 0; cantfind_ext4: if (!silent) - printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n", - sb->s_id); + ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; failed_mount4: - printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "mount failed"); + ext4_release_system_zone(sb); if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3: + if (sbi->s_flex_groups) { + if (is_vmalloc_addr(sbi->s_flex_groups)) + vfree(sbi->s_flex_groups); + else + kfree(sbi->s_flex_groups); + } percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -2862,6 +2934,7 @@ failed_mount: brelse(bh); out_fail: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); return ret; @@ -2906,27 +2979,27 @@ static journal_t *ext4_get_journal(struct super_block *sb, journal_inode = ext4_iget(sb, journal_inum); if (IS_ERR(journal_inode)) { - printk(KERN_ERR "EXT4-fs: no journal found.\n"); + ext4_msg(sb, KERN_ERR, "no journal found"); return NULL; } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); - printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n"); + ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return NULL; } jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode)) { - printk(KERN_ERR "EXT4-fs: invalid journal inode.\n"); + ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return NULL; } journal = jbd2_journal_init_inode(journal_inode); if (!journal) { - printk(KERN_ERR "EXT4-fs: Could not load journal inode\n"); + ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return NULL; } @@ -2950,22 +3023,22 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); - bdev = ext4_blkdev_get(j_dev); + bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) return NULL; if (bd_claim(bdev, sb)) { - printk(KERN_ERR - "EXT4-fs: failed to claim external journal device.\n"); + ext4_msg(sb, KERN_ERR, + "failed to claim external journal device"); blkdev_put(bdev, FMODE_READ|FMODE_WRITE); return NULL; } blocksize = sb->s_blocksize; - hblock = bdev_hardsect_size(bdev); + hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { - printk(KERN_ERR - "EXT4-fs: blocksize too small for journal device.\n"); + ext4_msg(sb, KERN_ERR, + "blocksize too small for journal device"); goto out_bdev; } @@ -2973,8 +3046,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev, blocksize); if (!(bh = __bread(bdev, sb_block, blocksize))) { - printk(KERN_ERR "EXT4-fs: couldn't read superblock of " - "external journal\n"); + ext4_msg(sb, KERN_ERR, "couldn't read superblock of " + "external journal"); goto out_bdev; } @@ -2982,14 +3055,14 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { - printk(KERN_ERR "EXT4-fs: external journal has " - "bad superblock\n"); + ext4_msg(sb, KERN_ERR, "external journal has " + "bad superblock"); brelse(bh); goto out_bdev; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { - printk(KERN_ERR "EXT4-fs: journal UUID does not match\n"); + ext4_msg(sb, KERN_ERR, "journal UUID does not match"); brelse(bh); goto out_bdev; } @@ -3001,25 +3074,26 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, journal = jbd2_journal_init_dev(bdev, sb->s_bdev, start, len, blocksize); if (!journal) { - printk(KERN_ERR "EXT4-fs: failed to create device journal\n"); + ext4_msg(sb, KERN_ERR, "failed to create device journal"); goto out_bdev; } journal->j_private = sb; ll_rw_block(READ, 1, &journal->j_sb_buffer); wait_on_buffer(journal->j_sb_buffer); if (!buffer_uptodate(journal->j_sb_buffer)) { - printk(KERN_ERR "EXT4-fs: I/O error on journal device\n"); + ext4_msg(sb, KERN_ERR, "I/O error on journal device"); goto out_journal; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { - printk(KERN_ERR "EXT4-fs: External journal has more than one " - "user (unsupported) - %d\n", + ext4_msg(sb, KERN_ERR, "External journal has more than one " + "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); goto out_journal; } EXT4_SB(sb)->journal_bdev = bdev; ext4_init_journal_params(sb, journal); return journal; + out_journal: jbd2_journal_destroy(journal); out_bdev: @@ -3041,8 +3115,8 @@ static int ext4_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { - printk(KERN_INFO "EXT4-fs: external journal device major/minor " - "numbers have changed\n"); + ext4_msg(sb, KERN_INFO, "external journal device major/minor " + "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); @@ -3054,24 +3128,23 @@ static int ext4_load_journal(struct super_block *sb, * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { if (sb->s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT4-fs: INFO: recovery " - "required on readonly filesystem.\n"); + ext4_msg(sb, KERN_INFO, "INFO: recovery " + "required on readonly filesystem"); if (really_read_only) { - printk(KERN_ERR "EXT4-fs: write access " - "unavailable, cannot proceed.\n"); + ext4_msg(sb, KERN_ERR, "write access " + "unavailable, cannot proceed"); return -EROFS; } - printk(KERN_INFO "EXT4-fs: write access will " - "be enabled during recovery.\n"); + ext4_msg(sb, KERN_INFO, "write access will " + "be enabled during recovery"); } } if (journal_inum && journal_dev) { - printk(KERN_ERR "EXT4-fs: filesystem has both journal " - "and inode journals!\n"); + ext4_msg(sb, KERN_ERR, "filesystem has both journal " + "and inode journals!"); return -EINVAL; } @@ -3084,14 +3157,14 @@ static int ext4_load_journal(struct super_block *sb, } if (journal->j_flags & JBD2_BARRIER) - printk(KERN_INFO "EXT4-fs: barriers enabled\n"); + ext4_msg(sb, KERN_INFO, "barriers enabled"); else - printk(KERN_INFO "EXT4-fs: barriers disabled\n"); + ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { err = jbd2_journal_update_format(journal); if (err) { - printk(KERN_ERR "EXT4-fs: error updating journal.\n"); + ext4_msg(sb, KERN_ERR, "error updating journal"); jbd2_journal_destroy(journal); return err; } @@ -3103,7 +3176,7 @@ static int ext4_load_journal(struct super_block *sb, err = jbd2_journal_load(journal); if (err) { - printk(KERN_ERR "EXT4-fs: error loading journal.\n"); + ext4_msg(sb, KERN_ERR, "error loading journal"); jbd2_journal_destroy(journal); return err; } @@ -3114,18 +3187,17 @@ static int ext4_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); - sb->s_dirt = 1; /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } return 0; } -static int ext4_commit_super(struct super_block *sb, - struct ext4_super_block *es, int sync) +static int ext4_commit_super(struct super_block *sb, int sync) { + struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; @@ -3140,8 +3212,8 @@ static int ext4_commit_super(struct super_block *sb, * be remapped. Nothing we can do but to retry the * write and hope for the best. */ - printk(KERN_ERR "EXT4-fs: previous I/O error to " - "superblock detected for %s.\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "previous I/O error to " + "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } @@ -3154,7 +3226,7 @@ static int ext4_commit_super(struct super_block *sb, &EXT4_SB(sb)->s_freeblocks_counter)); es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); - + sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) { @@ -3164,8 +3236,8 @@ static int ext4_commit_super(struct super_block *sb, error = buffer_write_io_error(sbh); if (error) { - printk(KERN_ERR "EXT4-fs: I/O error while writing " - "superblock for %s.\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } @@ -3173,7 +3245,6 @@ static int ext4_commit_super(struct super_block *sb, return error; } - /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a @@ -3192,14 +3263,11 @@ static void ext4_mark_recovery_complete(struct super_block *sb, if (jbd2_journal_flush(journal) < 0) goto out; - lock_super(sb); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - sb->s_dirt = 0; - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } - unlock_super(sb); out: jbd2_journal_unlock_updates(journal); @@ -3238,7 +3306,7 @@ static void ext4_clear_journal_err(struct super_block *sb, EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); } @@ -3257,29 +3325,15 @@ int ext4_force_commit(struct super_block *sb) return 0; journal = EXT4_SB(sb)->s_journal; - if (journal) { - sb->s_dirt = 0; + if (journal) ret = ext4_journal_force_commit(journal); - } return ret; } -/* - * Ext4 always journals updates to the superblock itself, so we don't - * have to propagate any other updates to the superblock on disk at this - * point. (We can probably nuke this function altogether, and remove - * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...) - */ static void ext4_write_super(struct super_block *sb) { - if (EXT4_SB(sb)->s_journal) { - if (mutex_trylock(&sb->s_lock) != 0) - BUG(); - sb->s_dirt = 0; - } else { - ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); - } + ext4_commit_super(sb, 1); } static int ext4_sync_fs(struct super_block *sb, int wait) @@ -3288,16 +3342,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait) tid_t target; trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait); - sb->s_dirt = 0; - if (EXT4_SB(sb)->s_journal) { - if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, - &target)) { - if (wait) - jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, - target); - } - } else { - ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait); + if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { + if (wait) + jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target); } return ret; } @@ -3310,34 +3357,32 @@ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal; - sb->s_dirt = 0; - if (!(sb->s_flags & MS_RDONLY)) { - journal = EXT4_SB(sb)->s_journal; + if (sb->s_flags & MS_RDONLY) + return 0; - if (journal) { - /* Now we set up the journal barrier. */ - jbd2_journal_lock_updates(journal); + journal = EXT4_SB(sb)->s_journal; - /* - * We don't want to clear needs_recovery flag when we - * failed to flush the journal. - */ - error = jbd2_journal_flush(journal); - if (error < 0) - goto out; - } + /* Now we set up the journal barrier. */ + jbd2_journal_lock_updates(journal); - /* Journal blocked and flushed, clear needs_recovery flag. */ - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); - if (error) - goto out; + /* + * Don't clear the needs_recovery flag if we failed to flush + * the journal. + */ + error = jbd2_journal_flush(journal); + if (error < 0) { + out: + jbd2_journal_unlock_updates(journal); + return error; } + + /* Journal blocked and flushed, clear needs_recovery flag. */ + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + error = ext4_commit_super(sb, 1); + if (error) + goto out; return 0; -out: - jbd2_journal_unlock_updates(journal); - return error; } /* @@ -3346,14 +3391,15 @@ out: */ static int ext4_unfreeze(struct super_block *sb) { - if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) { - lock_super(sb); - /* Reser the needs_recovery flag before the fs is unlocked. */ - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); - unlock_super(sb); - jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); - } + if (sb->s_flags & MS_RDONLY) + return 0; + + lock_super(sb); + /* Reset the needs_recovery flag before the fs is unlocked. */ + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_commit_super(sb, 1); + unlock_super(sb); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return 0; } @@ -3432,22 +3478,15 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - /* - * We have to unlock super so that we can wait for - * transactions. - */ - if (sbi->s_journal) { - unlock_super(sb); + if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); - lock_super(sb); - } } else { int ret; if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP))) { - printk(KERN_WARNING "EXT4-fs: %s: couldn't " + ext4_msg(sb, KERN_WARNING, "couldn't " "remount RDWR because of unsupported " - "optional features (%x).\n", sb->s_id, + "optional features (%x)", (le32_to_cpu(sbi->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); err = -EROFS; @@ -3456,17 +3495,15 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) /* * Make sure the group descriptor checksums - * are sane. If they aren't, refuse to - * remount r/w. + * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sbi, g, gdp)) { - printk(KERN_ERR - "EXT4-fs: ext4_remount: " - "Checksum for group %u failed (%u!=%u)\n", + ext4_msg(sb, KERN_ERR, + "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EINVAL; @@ -3480,11 +3517,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * require a full umount/remount for now. */ if (es->s_last_orphan) { - printk(KERN_WARNING "EXT4-fs: %s: couldn't " + ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " - "umount/remount instead.\n", - sb->s_id); + "umount/remount instead"); err = -EINVAL; goto restore_opts; } @@ -3504,8 +3540,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sb->s_flags &= ~MS_RDONLY; } } + ext4_setup_system_zone(sb); if (sbi->s_journal == NULL) - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); #ifdef CONFIG_QUOTA /* Release old quota file names */ @@ -3515,6 +3552,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) kfree(old_opts.s_qf_names[i]); #endif return 0; + restore_opts: sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; @@ -3545,9 +3583,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) if (test_opt(sb, MINIX_DF)) { sbi->s_overhead_last = 0; } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { - ext4_group_t ngroups = sbi->s_groups_count, i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; - smp_rmb(); /* * Compute the overhead (FS structures). This is constant @@ -3599,11 +3636,12 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) le64_to_cpup((void *)es->s_uuid + sizeof(u64)); buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL; buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL; + return 0; } -/* Helper function for writing quotas on sync - we need to start transaction before quota file - * is locked for write. Otherwise the are possible deadlocks: +/* Helper function for writing quotas on sync - we need to start transaction + * before quota file is locked for write. Otherwise the are possible deadlocks: * Process 1 Process 2 * ext4_create() quota_sync() * jbd2_journal_start() write_dquot() @@ -3627,7 +3665,7 @@ static int ext4_write_dquot(struct dquot *dquot) inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, - EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); @@ -3643,7 +3681,7 @@ static int ext4_acquire_dquot(struct dquot *dquot) handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), - EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); @@ -3659,7 +3697,7 @@ static int ext4_release_dquot(struct dquot *dquot) handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), - EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); @@ -3707,7 +3745,7 @@ static int ext4_write_info(struct super_block *sb, int type) static int ext4_quota_on_mount(struct super_block *sb, int type) { return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], - EXT4_SB(sb)->s_jquota_fmt, type); + EXT4_SB(sb)->s_jquota_fmt, type); } /* @@ -3738,9 +3776,9 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path.dentry->d_parent != sb->s_root) - printk(KERN_WARNING - "EXT4-fs: Quota file not on filesystem root. " - "Journaled quota will not work.\n"); + ext4_msg(sb, KERN_WARNING, + "Quota file not on filesystem root. " + "Journaled quota will not work"); } /* @@ -3823,8 +3861,8 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, handle_t *handle = journal_current_handle(); if (EXT4_SB(sb)->s_journal && !handle) { - printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)" - " cancelled because transaction is not started.\n", + ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" + " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } @@ -3878,10 +3916,10 @@ out: #endif -static int ext4_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static int ext4_get_sb(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, struct vfsmount *mnt) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); } static struct file_system_type ext4_fs_type = { @@ -3893,14 +3931,14 @@ static struct file_system_type ext4_fs_type = { }; #ifdef CONFIG_EXT4DEV_COMPAT -static int ext4dev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static int ext4dev_get_sb(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data,struct vfsmount *mnt) { - printk(KERN_WARNING "EXT4-fs: Update your userspace programs " - "to mount using ext4\n"); - printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility " - "will go away by 2.6.31\n"); - return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); + printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs " + "to mount using ext4\n", dev_name); + printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility " + "will go away by 2.6.31\n", dev_name); + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); } static struct file_system_type ext4dev_fs_type = { @@ -3917,13 +3955,16 @@ static int __init init_ext4_fs(void) { int err; + err = init_ext4_system_zone(); + if (err) + return err; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); if (!ext4_kset) - return -ENOMEM; + goto out4; ext4_proc_root = proc_mkdir("fs/ext4", NULL); err = init_ext4_mballoc(); if (err) - return err; + goto out3; err = init_ext4_xattr(); if (err) @@ -3948,6 +3989,11 @@ out1: exit_ext4_xattr(); out2: exit_ext4_mballoc(); +out3: + remove_proc_entry("fs/ext4", NULL); + kset_unregister(ext4_kset); +out4: + exit_ext4_system_zone(); return err; } @@ -3962,6 +4008,7 @@ static void __exit exit_ext4_fs(void) exit_ext4_mballoc(); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); + exit_ext4_system_zone(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 3a981b7f64ca..cad957cdb1e5 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -7,6 +7,7 @@ config GFS2_FS select IP_SCTP if DLM_SCTP select FS_POSIX_ACL select CRC32 + select SLOW_WORK help A cluster filesystem. diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile index a851ea4bdf70..d53a9bea1c2f 100644 --- a/fs/gfs2/Makefile +++ b/fs/gfs2/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_GFS2_FS) += gfs2.o gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \ glops.o inode.o log.o lops.o main.o meta_io.o \ - mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \ - ops_fstype.o ops_inode.o ops_super.o quota.o \ + aops.o dentry.o export.o file.o \ + ops_fstype.o ops_inode.o quota.o \ recovery.o rgrp.o super.o sys.o trans.o util.o gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/aops.c index a6dde1751e17..03ebb439ace0 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/aops.c @@ -28,7 +28,6 @@ #include "inode.h" #include "log.h" #include "meta_io.h" -#include "ops_address.h" #include "quota.h" #include "trans.h" #include "rgrp.h" @@ -781,10 +780,12 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, unlock_page(page); page_cache_release(page); - if (inode->i_size < to) { - i_size_write(inode, to); - ip->i_disksize = inode->i_size; - di->di_size = cpu_to_be64(inode->i_size); + if (copied) { + if (inode->i_size < to) { + i_size_write(inode, to); + ip->i_disksize = inode->i_size; + } + gfs2_dinode_out(ip, di); mark_inode_dirty(inode); } @@ -824,7 +825,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh; struct gfs2_alloc *al = ip->i_alloc; - struct gfs2_dinode *di; unsigned int from = pos & (PAGE_CACHE_SIZE - 1); unsigned int to = from + len; int ret; @@ -847,11 +847,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, gfs2_page_add_databufs(ip, page, from, to); ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - - if (likely(ret >= 0) && (inode->i_size > ip->i_disksize)) { - di = (struct gfs2_dinode *)dibh->b_data; - ip->i_disksize = inode->i_size; - di->di_size = cpu_to_be64(inode->i_size); + if (ret > 0) { + if (inode->i_size > ip->i_disksize) + ip->i_disksize = inode->i_size; + gfs2_dinode_out(ip, dibh->b_data); mark_inode_dirty(inode); } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 3a5d3f883e10..329763530dc0 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -25,7 +25,6 @@ #include "trans.h" #include "dir.h" #include "util.h" -#include "ops_address.h" /* This doesn't need to be that large as max 64 bit pointers in a 4k * block is 512, so __u16 is fine for that. It saves stack space to @@ -136,7 +135,9 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) and write it out to disk */ unsigned int n = 1; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + goto out_brelse; if (isdir) { gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1); error = gfs2_dir_get_new_buffer(ip, block, &bh); @@ -476,8 +477,11 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, blks = dblks + iblks; i = sheight; do { + int error; n = blks - alloced; - bn = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &bn, &n); + if (error) + return error; alloced += n; if (state != ALLOC_DATA || gfs2_is_jdata(ip)) gfs2_trans_add_unrevoke(sdp, bn, n); @@ -1008,7 +1012,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) gfs2_trans_add_bh(ip->i_gl, bh, 0); zero_user(page, offset, length); - + mark_buffer_dirty(bh); unlock: unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/dentry.c index 022c66cd5606..022c66cd5606 100644 --- a/fs/gfs2/ops_dentry.c +++ b/fs/gfs2/dentry.c diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index aef4d0c06748..297d7e5cebad 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -803,13 +803,20 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, { struct gfs2_inode *ip = GFS2_I(inode); unsigned int n = 1; - u64 bn = gfs2_alloc_block(ip, &n); - struct buffer_head *bh = gfs2_meta_new(ip->i_gl, bn); + u64 bn; + int error; + struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; struct qstr name = { .name = "", .len = 0, .hash = 0 }; + + error = gfs2_alloc_block(ip, &bn, &n); + if (error) + return NULL; + bh = gfs2_meta_new(ip->i_gl, bn); if (!bh) return NULL; + gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1); gfs2_trans_add_bh(ip->i_gl, bh, 1); gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF); diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index 899763aed217..07ea9529adda 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -582,8 +582,11 @@ static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp) struct gfs2_ea_header *ea; unsigned int n = 1; u64 block; + int error; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, block, 1); *bhp = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_bh(ip->i_gl, *bhp, 1); @@ -617,6 +620,7 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea, struct gfs2_ea_request *er) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + int error; ea->ea_data_len = cpu_to_be32(er->er_data_len); ea->ea_name_len = er->er_name_len; @@ -642,7 +646,9 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea, int mh_size = sizeof(struct gfs2_meta_header); unsigned int n = 1; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, block, 1); bh = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_bh(ip->i_gl, bh, 1); @@ -963,7 +969,9 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er, } else { u64 blk; unsigned int n = 1; - blk = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &blk, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, blk, 1); indbh = gfs2_meta_new(ip->i_gl, blk); gfs2_trans_add_bh(ip->i_gl, indbh, 1); diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/export.c index 9200ef221716..9200ef221716 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/export.c diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/file.c index 5d82e91887e3..73318a3ce6f1 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/file.c @@ -39,7 +39,6 @@ #include "trans.h" #include "util.h" #include "eaops.h" -#include "ops_address.h" /** * gfs2_llseek - seek to a location in a file @@ -425,33 +424,36 @@ static struct vm_operations_struct gfs2_vm_ops = { .page_mkwrite = gfs2_page_mkwrite, }; - /** * gfs2_mmap - * @file: The file to map * @vma: The VMA which described the mapping * - * Returns: 0 or error code + * There is no need to get a lock here unless we should be updating + * atime. We ignore any locking errors since the only consequence is + * a missed atime update (which will just be deferred until later). + * + * Returns: 0 */ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) { struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - struct gfs2_holder i_gh; - int error; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error) { - gfs2_holder_uninit(&i_gh); - return error; - } + if (!(file->f_flags & O_NOATIME)) { + struct gfs2_holder i_gh; + int error; + gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); + error = gfs2_glock_nq(&i_gh); + file_accessed(file); + if (error == 0) + gfs2_glock_dq_uninit(&i_gh); + } vma->vm_ops = &gfs2_vm_ops; + vma->vm_flags |= VM_CAN_NONLINEAR; - gfs2_glock_dq_uninit(&i_gh); - - return error; + return 0; } /** @@ -692,12 +694,10 @@ static void do_unflock(struct file *file, struct file_lock *fl) static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) { - struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - if (__mandatory_lock(&ip->i_inode)) - return -ENOLCK; + if (fl->fl_type & LOCK_MAND) + return -EOPNOTSUPP; if (fl->fl_type == F_UNLCK) { do_unflock(file, fl); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ff4981090489..2bf62bcc5181 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -796,22 +796,37 @@ void gfs2_holder_uninit(struct gfs2_holder *gh) gh->gh_ip = 0; } -static int just_schedule(void *word) +/** + * gfs2_glock_holder_wait + * @word: unused + * + * This function and gfs2_glock_demote_wait both show up in the WCHAN + * field. Thus I've separated these otherwise identical functions in + * order to be more informative to the user. + */ + +static int gfs2_glock_holder_wait(void *word) { schedule(); return 0; } +static int gfs2_glock_demote_wait(void *word) +{ + schedule(); + return 0; +} + static void wait_on_holder(struct gfs2_holder *gh) { might_sleep(); - wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE); } static void wait_on_demote(struct gfs2_glock *gl) { might_sleep(); - wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); } /** diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 70f87f43afa2..d5e4ab155ca0 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -310,24 +310,6 @@ static void rgrp_go_unlock(struct gfs2_holder *gh) } /** - * rgrp_go_dump - print out an rgrp - * @seq: The iterator - * @gl: The glock in question - * - */ - -static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl) -{ - const struct gfs2_rgrpd *rgd = gl->gl_object; - if (rgd == NULL) - return 0; - gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n", - (unsigned long long)rgd->rd_addr, rgd->rd_flags, - rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes); - return 0; -} - -/** * trans_go_sync - promote/demote the transaction glock * @gl: the glock * @state: the requested state @@ -410,7 +392,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_demote_ok = rgrp_go_demote_ok, .go_lock = rgrp_go_lock, .go_unlock = rgrp_go_unlock, - .go_dump = rgrp_go_dump, + .go_dump = gfs2_rgrp_dump, .go_type = LM_TYPE_RGRP, .go_min_hold_time = HZ / 5, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 399d1b978049..225347fbff3c 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/workqueue.h> +#include <linux/slow-work.h> #include <linux/dlm.h> #include <linux/buffer_head.h> @@ -63,9 +64,12 @@ struct gfs2_log_element { const struct gfs2_log_operations *le_ops; }; +#define GBF_FULL 1 + struct gfs2_bitmap { struct buffer_head *bi_bh; char *bi_clone; + unsigned long bi_flags; u32 bi_offset; u32 bi_start; u32 bi_len; @@ -90,10 +94,11 @@ struct gfs2_rgrpd { struct gfs2_sbd *rd_sbd; unsigned int rd_bh_count; u32 rd_last_alloc; - unsigned char rd_flags; -#define GFS2_RDF_CHECK 0x01 /* Need to check for unlinked inodes */ -#define GFS2_RDF_NOALLOC 0x02 /* rg prohibits allocation */ -#define GFS2_RDF_UPTODATE 0x04 /* rg is up to date */ + u32 rd_flags; +#define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */ +#define GFS2_RDF_UPTODATE 0x20000000 /* rg is up to date */ +#define GFS2_RDF_ERROR 0x40000000 /* error in rg */ +#define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */ }; enum gfs2_state_bits { @@ -376,11 +381,11 @@ struct gfs2_journal_extent { struct gfs2_jdesc { struct list_head jd_list; struct list_head extent_list; - + struct slow_work jd_work; struct inode *jd_inode; + unsigned long jd_flags; +#define JDF_RECOVERY 1 unsigned int jd_jid; - int jd_dirty; - unsigned int jd_blocks; }; @@ -390,9 +395,6 @@ struct gfs2_statfs_change_host { s64 sc_dinodes; }; -#define GFS2_GLOCKD_DEFAULT 1 -#define GFS2_GLOCKD_MAX 16 - #define GFS2_QUOTA_DEFAULT GFS2_QUOTA_OFF #define GFS2_QUOTA_OFF 0 #define GFS2_QUOTA_ACCOUNT 1 @@ -418,6 +420,7 @@ struct gfs2_args { unsigned int ar_data:2; /* ordered/writeback */ unsigned int ar_meta:1; /* mount metafs */ unsigned int ar_discard:1; /* discard requests */ + int ar_commit; /* Commit interval */ }; struct gfs2_tune { @@ -426,7 +429,6 @@ struct gfs2_tune { unsigned int gt_incore_log_blocks; unsigned int gt_log_flush_secs; - unsigned int gt_recoverd_secs; unsigned int gt_logd_secs; unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */ @@ -447,6 +449,7 @@ enum { SDF_JOURNAL_LIVE = 1, SDF_SHUTDOWN = 2, SDF_NOBARRIERS = 3, + SDF_NORECOVERY = 4, }; #define GFS2_FSNAME_LEN 256 @@ -493,7 +496,6 @@ struct lm_lockstruct { unsigned long ls_flags; dlm_lockspace_t *ls_dlm; - int ls_recover_jid; int ls_recover_jid_done; int ls_recover_jid_status; }; @@ -582,7 +584,6 @@ struct gfs2_sbd { /* Daemon stuff */ - struct task_struct *sd_recoverd_process; struct task_struct *sd_logd_process; struct task_struct *sd_quotad_process; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5a31d426116f..2f94bd723698 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -30,7 +30,6 @@ #include "inode.h" #include "log.h" #include "meta_io.h" -#include "ops_address.h" #include "quota.h" #include "rgrp.h" #include "trans.h" @@ -1047,154 +1046,7 @@ fail: return ERR_PTR(error); } -/** - * gfs2_rmdiri - Remove a directory - * @dip: The parent directory of the directory to be removed - * @name: The name of the directory to be removed - * @ip: The GFS2 inode of the directory to be removed - * - * Assumes Glocks on dip and ip are held - * - * Returns: errno - */ - -int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip) -{ - struct qstr dotname; - int error; - - if (ip->i_entries != 2) { - if (gfs2_consist_inode(ip)) - gfs2_dinode_print(ip); - return -EIO; - } - - error = gfs2_dir_del(dip, name); - if (error) - return error; - - error = gfs2_change_nlink(dip, -1); - if (error) - return error; - - gfs2_str2qstr(&dotname, "."); - error = gfs2_dir_del(ip, &dotname); - if (error) - return error; - - gfs2_str2qstr(&dotname, ".."); - error = gfs2_dir_del(ip, &dotname); - if (error) - return error; - - /* It looks odd, but it really should be done twice */ - error = gfs2_change_nlink(ip, -1); - if (error) - return error; - - error = gfs2_change_nlink(ip, -1); - if (error) - return error; - - return error; -} - -/* - * gfs2_unlink_ok - check to see that a inode is still in a directory - * @dip: the directory - * @name: the name of the file - * @ip: the inode - * - * Assumes that the lock on (at least) @dip is held. - * - * Returns: 0 if the parent/child relationship is correct, errno if it isn't - */ - -int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - const struct gfs2_inode *ip) -{ - int error; - - if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode)) - return -EPERM; - - if ((dip->i_inode.i_mode & S_ISVTX) && - dip->i_inode.i_uid != current_fsuid() && - ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER)) - return -EPERM; - - if (IS_APPEND(&dip->i_inode)) - return -EPERM; - - error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); - if (error) - return error; - - error = gfs2_dir_check(&dip->i_inode, name, ip); - if (error) - return error; - - return 0; -} - -/** - * gfs2_readlinki - return the contents of a symlink - * @ip: the symlink's inode - * @buf: a pointer to the buffer to be filled - * @len: a pointer to the length of @buf - * - * If @buf is too small, a piece of memory is kmalloc()ed and needs - * to be freed by the caller. - * - * Returns: errno - */ - -int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len) -{ - struct gfs2_holder i_gh; - struct buffer_head *dibh; - unsigned int x; - int error; - - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error) { - gfs2_holder_uninit(&i_gh); - return error; - } - - if (!ip->i_disksize) { - gfs2_consist_inode(ip); - error = -EIO; - goto out; - } - - error = gfs2_meta_inode_buffer(ip, &dibh); - if (error) - goto out; - - x = ip->i_disksize + 1; - if (x > *len) { - *buf = kmalloc(x, GFP_NOFS); - if (!*buf) { - error = -ENOMEM; - goto out_brelse; - } - } - - memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x); - *len = x; - -out_brelse: - brelse(dibh); -out: - gfs2_glock_dq_uninit(&i_gh); - return error; -} - -static int -__gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr) +static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr) { struct buffer_head *dibh; int error; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index c30be2b66580..c341aaf67adb 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -11,8 +11,16 @@ #define __INODE_DOT_H__ #include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/mm.h> #include "util.h" +extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); +extern int gfs2_internal_read(struct gfs2_inode *ip, + struct file_ra_state *ra_state, + char *buf, loff_t *pos, unsigned size); +extern void gfs2_set_aops(struct inode *inode); + static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) { return !ip->i_height; @@ -73,30 +81,26 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip, } -void gfs2_set_iop(struct inode *inode); -struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, - u64 no_addr, u64 no_formal_ino, - int skip_freeing); -struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); - -int gfs2_inode_refresh(struct gfs2_inode *ip); - -int gfs2_dinode_dealloc(struct gfs2_inode *inode); -int gfs2_change_nlink(struct gfs2_inode *ip, int diff); -struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, - int is_root); -struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, - unsigned int mode, dev_t dev); -int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip); -int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - const struct gfs2_inode *ip); -int gfs2_permission(struct inode *inode, int mask); -int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len); -int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr); -struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); -void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); -void gfs2_dinode_print(const struct gfs2_inode *ip); +extern void gfs2_set_iop(struct inode *inode); +extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, + u64 no_addr, u64 no_formal_ino, + int skip_freeing); +extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); + +extern int gfs2_inode_refresh(struct gfs2_inode *ip); + +extern int gfs2_dinode_dealloc(struct gfs2_inode *inode); +extern int gfs2_change_nlink(struct gfs2_inode *ip, int diff); +extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, + int is_root); +extern struct inode *gfs2_createi(struct gfs2_holder *ghs, + const struct qstr *name, + unsigned int mode, dev_t dev); +extern int gfs2_permission(struct inode *inode, int mask); +extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr); +extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); +extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); +extern void gfs2_dinode_print(const struct gfs2_inode *ip); extern const struct inode_operations gfs2_file_iops; extern const struct inode_operations gfs2_dir_iops; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 98918a756410..aa62cf5976e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -120,7 +120,7 @@ __acquires(&sdp->sd_log_lock) lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } else { unlock_buffer(bh); brelse(bh); @@ -604,7 +604,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) goto skip_barrier; get_bh(bh); - submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh); + submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh); wait_on_buffer(bh); if (buffer_eopnotsupp(bh)) { clear_buffer_eopnotsupp(bh); @@ -664,7 +664,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) lock_buffer(bh); if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } else { unlock_buffer(bh); brelse(bh); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 80e4f5f898bb..00315f50fa46 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -13,6 +13,8 @@ #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> +#include <linux/bio.h> +#include <linux/fs.h> #include "gfs2.h" #include "incore.h" @@ -189,7 +191,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_log_unlock(sdp); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); n = 0; @@ -199,7 +201,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); lock_buffer(bd2->bd_bh); bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); if (++n >= num) break; @@ -341,7 +343,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); bh = gfs2_log_get_buf(sdp); mh = (struct gfs2_meta_header *)bh->b_data; @@ -358,7 +360,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, @@ -560,7 +562,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, ptr = bh_log_ptr(bh); get_bh(bh); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); while(!list_empty(list)) { bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); @@ -586,7 +588,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, } else { bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); } - submit_bh(WRITE, bh1); + submit_bh(WRITE_SYNC_PLUG, bh1); gfs2_log_lock(sdp); ptr += 2; } diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index a6892ed0840a..eacd78a5d082 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/gfs2_ondisk.h> #include <asm/atomic.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -113,12 +114,18 @@ static int __init init_gfs2_fs(void) if (error) goto fail_unregister; + error = slow_work_register_user(); + if (error) + goto fail_slow; + gfs2_register_debugfs(); printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__); return 0; +fail_slow: + unregister_filesystem(&gfs2meta_fs_type); fail_unregister: unregister_filesystem(&gfs2_fs_type); fail: @@ -156,6 +163,7 @@ static void __exit exit_gfs2_fs(void) gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); + slow_work_unregister_user(); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 8d6f13256b26..cb8d7a93d5ec 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -31,19 +31,66 @@ #include "rgrp.h" #include "trans.h" #include "util.h" -#include "ops_address.h" -static int aspace_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create) +static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc) { - gfs2_assert_warn(inode->i_sb->s_fs_info, 0); - return -EOPNOTSUPP; -} + int err; + struct buffer_head *bh, *head; + int nr_underway = 0; + int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC_PLUG : WRITE)); + + BUG_ON(!PageLocked(page)); + BUG_ON(!page_has_buffers(page)); + + head = page_buffers(page); + bh = head; + + do { + if (!buffer_mapped(bh)) + continue; + /* + * If it's a fully non-blocking write attempt and we cannot + * lock the buffer then redirty the page. Note that this can + * potentially cause a busy-wait loop from pdflush and kswapd + * activity, but those code paths have their own higher-level + * throttling. + */ + if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + lock_buffer(bh); + } else if (!trylock_buffer(bh)) { + redirty_page_for_writepage(wbc, page); + continue; + } + if (test_clear_buffer_dirty(bh)) { + mark_buffer_async_write(bh); + } else { + unlock_buffer(bh); + } + } while ((bh = bh->b_this_page) != head); + + /* + * The page and its buffers are protected by PageWriteback(), so we can + * drop the bh refcounts early. + */ + BUG_ON(PageWriteback(page)); + set_page_writeback(page); + + do { + struct buffer_head *next = bh->b_this_page; + if (buffer_async_write(bh)) { + submit_bh(write_op, bh); + nr_underway++; + } + bh = next; + } while (bh != head); + unlock_page(page); -static int gfs2_aspace_writepage(struct page *page, - struct writeback_control *wbc) -{ - return block_write_full_page(page, aspace_get_block, wbc); + err = 0; + if (nr_underway == 0) + end_page_writeback(page); + + return err; } static const struct address_space_operations aspace_aops = { @@ -201,16 +248,32 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head **bhp) { - *bhp = gfs2_getbuf(gl, blkno, CREATE); - if (!buffer_uptodate(*bhp)) { - ll_rw_block(READ_META, 1, bhp); - if (flags & DIO_WAIT) { - int error = gfs2_meta_wait(gl->gl_sbd, *bhp); - if (error) { - brelse(*bhp); - return error; - } - } + struct gfs2_sbd *sdp = gl->gl_sbd; + struct buffer_head *bh; + + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + return -EIO; + + *bhp = bh = gfs2_getbuf(gl, blkno, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + return 0; + } + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + submit_bh(READ_SYNC | (1 << BIO_RW_META), bh); + if (!(flags & DIO_WAIT)) + return 0; + + wait_on_buffer(bh); + if (unlikely(!buffer_uptodate(bh))) { + struct gfs2_trans *tr = current->journal_info; + if (tr && tr->tr_touched) + gfs2_io_error_bh(sdp, bh); + brelse(bh); + return -EIO; } return 0; @@ -404,7 +467,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_META, 1, &first_bh); + ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c deleted file mode 100644 index f7e8527a21e0..000000000000 --- a/fs/gfs2/mount.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/completion.h> -#include <linux/buffer_head.h> -#include <linux/gfs2_ondisk.h> -#include <linux/parser.h> - -#include "gfs2.h" -#include "incore.h" -#include "super.h" -#include "sys.h" -#include "util.h" - -enum { - Opt_lockproto, - Opt_locktable, - Opt_hostdata, - Opt_spectator, - Opt_ignore_local_fs, - Opt_localflocks, - Opt_localcaching, - Opt_debug, - Opt_nodebug, - Opt_upgrade, - Opt_acl, - Opt_noacl, - Opt_quota_off, - Opt_quota_account, - Opt_quota_on, - Opt_quota, - Opt_noquota, - Opt_suiddir, - Opt_nosuiddir, - Opt_data_writeback, - Opt_data_ordered, - Opt_meta, - Opt_discard, - Opt_nodiscard, - Opt_err, -}; - -static const match_table_t tokens = { - {Opt_lockproto, "lockproto=%s"}, - {Opt_locktable, "locktable=%s"}, - {Opt_hostdata, "hostdata=%s"}, - {Opt_spectator, "spectator"}, - {Opt_ignore_local_fs, "ignore_local_fs"}, - {Opt_localflocks, "localflocks"}, - {Opt_localcaching, "localcaching"}, - {Opt_debug, "debug"}, - {Opt_nodebug, "nodebug"}, - {Opt_upgrade, "upgrade"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_quota_off, "quota=off"}, - {Opt_quota_account, "quota=account"}, - {Opt_quota_on, "quota=on"}, - {Opt_quota, "quota"}, - {Opt_noquota, "noquota"}, - {Opt_suiddir, "suiddir"}, - {Opt_nosuiddir, "nosuiddir"}, - {Opt_data_writeback, "data=writeback"}, - {Opt_data_ordered, "data=ordered"}, - {Opt_meta, "meta"}, - {Opt_discard, "discard"}, - {Opt_nodiscard, "nodiscard"}, - {Opt_err, NULL} -}; - -/** - * gfs2_mount_args - Parse mount options - * @sdp: - * @data: - * - * Return: errno - */ - -int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) -{ - char *o; - int token; - substring_t tmp[MAX_OPT_ARGS]; - - /* Split the options into tokens with the "," character and - process them */ - - while (1) { - o = strsep(&options, ","); - if (o == NULL) - break; - if (*o == '\0') - continue; - - token = match_token(o, tokens, tmp); - switch (token) { - case Opt_lockproto: - match_strlcpy(args->ar_lockproto, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_locktable: - match_strlcpy(args->ar_locktable, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_hostdata: - match_strlcpy(args->ar_hostdata, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_spectator: - args->ar_spectator = 1; - break; - case Opt_ignore_local_fs: - args->ar_ignore_local_fs = 1; - break; - case Opt_localflocks: - args->ar_localflocks = 1; - break; - case Opt_localcaching: - args->ar_localcaching = 1; - break; - case Opt_debug: - args->ar_debug = 1; - break; - case Opt_nodebug: - args->ar_debug = 0; - break; - case Opt_upgrade: - args->ar_upgrade = 1; - break; - case Opt_acl: - args->ar_posix_acl = 1; - break; - case Opt_noacl: - args->ar_posix_acl = 0; - break; - case Opt_quota_off: - case Opt_noquota: - args->ar_quota = GFS2_QUOTA_OFF; - break; - case Opt_quota_account: - args->ar_quota = GFS2_QUOTA_ACCOUNT; - break; - case Opt_quota_on: - case Opt_quota: - args->ar_quota = GFS2_QUOTA_ON; - break; - case Opt_suiddir: - args->ar_suiddir = 1; - break; - case Opt_nosuiddir: - args->ar_suiddir = 0; - break; - case Opt_data_writeback: - args->ar_data = GFS2_DATA_WRITEBACK; - break; - case Opt_data_ordered: - args->ar_data = GFS2_DATA_ORDERED; - break; - case Opt_meta: - args->ar_meta = 1; - break; - case Opt_discard: - args->ar_discard = 1; - break; - case Opt_nodiscard: - args->ar_discard = 0; - break; - case Opt_err: - default: - fs_info(sdp, "invalid mount option: %s\n", o); - return -EINVAL; - } - } - - return 0; -} - diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h deleted file mode 100644 index 5da21285bba4..000000000000 --- a/fs/gfs2/ops_address.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __OPS_ADDRESS_DOT_H__ -#define __OPS_ADDRESS_DOT_H__ - -#include <linux/fs.h> -#include <linux/buffer_head.h> -#include <linux/mm.h> - -extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); -extern int gfs2_internal_read(struct gfs2_inode *ip, - struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size); -extern void gfs2_set_aops(struct inode *inode); - -#endif /* __OPS_ADDRESS_DOT_H__ */ diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1ff9473ea753..cc34f271b3e7 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -17,6 +17,7 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/gfs2_ondisk.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -55,8 +56,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt) spin_lock_init(>->gt_spin); gt->gt_incore_log_blocks = 1024; - gt->gt_log_flush_secs = 60; - gt->gt_recoverd_secs = 60; gt->gt_logd_secs = 1; gt->gt_quota_simul_sync = 64; gt->gt_quota_warn_period = 10; @@ -526,11 +525,11 @@ static int init_sb(struct gfs2_sbd *sdp, int silent) } /* Set up the buffer cache and SB for real */ - if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) { + if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) { ret = -EINVAL; fs_err(sdp, "FS block size (%u) is too small for device " "block size (%u)\n", - sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev)); + sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev)); goto out; } if (sdp->sd_sb.sb_bsize > PAGE_SIZE) { @@ -676,6 +675,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) break; INIT_LIST_HEAD(&jd->extent_list); + slow_work_init(&jd->jd_work, &gfs2_recover_ops); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1); if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { if (!jd->jd_inode) @@ -701,14 +701,13 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) { struct inode *master = sdp->sd_master_dir->d_inode; struct gfs2_holder ji_gh; - struct task_struct *p; struct gfs2_inode *ip; int jindex = 1; int error = 0; if (undo) { jindex = 0; - goto fail_recoverd; + goto fail_jinode_gh; } sdp->sd_jindex = gfs2_lookup_simple(master, "jindex"); @@ -801,18 +800,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) gfs2_glock_dq_uninit(&ji_gh); jindex = 0; - p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd"); - error = IS_ERR(p); - if (error) { - fs_err(sdp, "can't start recoverd thread: %d\n", error); - goto fail_jinode_gh; - } - sdp->sd_recoverd_process = p; - return 0; -fail_recoverd: - kthread_stop(sdp->sd_recoverd_process); fail_jinode_gh: if (!sdp->sd_args.ar_spectator) gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); @@ -1165,6 +1154,7 @@ static int fill_super(struct super_block *sb, void *data, int silent) sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT; sdp->sd_args.ar_data = GFS2_DATA_DEFAULT; + sdp->sd_args.ar_commit = 60; error = gfs2_mount_args(sdp, &sdp->sd_args, data); if (error) { @@ -1172,8 +1162,10 @@ static int fill_super(struct super_block *sb, void *data, int silent) goto fail; } - if (sdp->sd_args.ar_spectator) + if (sdp->sd_args.ar_spectator) { sb->s_flags |= MS_RDONLY; + set_bit(SDF_NORECOVERY, &sdp->sd_flags); + } if (sdp->sd_args.ar_posix_acl) sb->s_flags |= MS_POSIXACL; @@ -1191,6 +1183,8 @@ static int fill_super(struct super_block *sb, void *data, int silent) GFS2_BASIC_BLOCK_SHIFT; sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift; + sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit; + error = init_names(sdp, silent); if (error) goto fail; @@ -1279,9 +1273,22 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt); } -static struct super_block *get_gfs2_sb(const char *dev_name) +static int test_meta_super(struct super_block *s, void *ptr) +{ + struct block_device *bdev = ptr; + return (bdev == s->s_bdev); +} + +static int set_meta_super(struct super_block *s, void *ptr) { - struct super_block *sb; + return -EINVAL; +} + +static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, struct vfsmount *mnt) +{ + struct super_block *s; + struct gfs2_sbd *sdp; struct path path; int error; @@ -1289,30 +1296,17 @@ static struct super_block *get_gfs2_sb(const char *dev_name) if (error) { printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n", dev_name, error); - return NULL; + return error; } - sb = path.dentry->d_inode->i_sb; - if (sb && (sb->s_type == &gfs2_fs_type)) - atomic_inc(&sb->s_active); - else - sb = NULL; + s = sget(&gfs2_fs_type, test_meta_super, set_meta_super, + path.dentry->d_inode->i_sb->s_bdev); path_put(&path); - return sb; -} - -static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) -{ - struct super_block *sb = NULL; - struct gfs2_sbd *sdp; - - sb = get_gfs2_sb(dev_name); - if (!sb) { + if (IS_ERR(s)) { printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n"); - return -ENOENT; + return PTR_ERR(s); } - sdp = sb->s_fs_info; - mnt->mnt_sb = sb; + sdp = s->s_fs_info; + mnt->mnt_sb = s; mnt->mnt_root = dget(sdp->sd_master_dir); return 0; } diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 1c70fa5168d6..f8bd20baf99c 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -262,6 +262,44 @@ out_parent: return error; } +/* + * gfs2_unlink_ok - check to see that a inode is still in a directory + * @dip: the directory + * @name: the name of the file + * @ip: the inode + * + * Assumes that the lock on (at least) @dip is held. + * + * Returns: 0 if the parent/child relationship is correct, errno if it isn't + */ + +static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, + const struct gfs2_inode *ip) +{ + int error; + + if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode)) + return -EPERM; + + if ((dip->i_inode.i_mode & S_ISVTX) && + dip->i_inode.i_uid != current_fsuid() && + ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER)) + return -EPERM; + + if (IS_APPEND(&dip->i_inode)) + return -EPERM; + + error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); + if (error) + return error; + + error = gfs2_dir_check(&dip->i_inode, name, ip); + if (error) + return error; + + return 0; +} + /** * gfs2_unlink - Unlink a file * @dir: The inode of the directory containing the file to unlink @@ -473,6 +511,59 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode) } /** + * gfs2_rmdiri - Remove a directory + * @dip: The parent directory of the directory to be removed + * @name: The name of the directory to be removed + * @ip: The GFS2 inode of the directory to be removed + * + * Assumes Glocks on dip and ip are held + * + * Returns: errno + */ + +static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, + struct gfs2_inode *ip) +{ + struct qstr dotname; + int error; + + if (ip->i_entries != 2) { + if (gfs2_consist_inode(ip)) + gfs2_dinode_print(ip); + return -EIO; + } + + error = gfs2_dir_del(dip, name); + if (error) + return error; + + error = gfs2_change_nlink(dip, -1); + if (error) + return error; + + gfs2_str2qstr(&dotname, "."); + error = gfs2_dir_del(ip, &dotname); + if (error) + return error; + + gfs2_str2qstr(&dotname, ".."); + error = gfs2_dir_del(ip, &dotname); + if (error) + return error; + + /* It looks odd, but it really should be done twice */ + error = gfs2_change_nlink(ip, -1); + if (error) + return error; + + error = gfs2_change_nlink(ip, -1); + if (error) + return error; + + return error; +} + +/** * gfs2_rmdir - Remove a directory * @dir: The parent directory of the directory to be removed * @dentry: The dentry of the directory to remove @@ -885,6 +976,61 @@ out: } /** + * gfs2_readlinki - return the contents of a symlink + * @ip: the symlink's inode + * @buf: a pointer to the buffer to be filled + * @len: a pointer to the length of @buf + * + * If @buf is too small, a piece of memory is kmalloc()ed and needs + * to be freed by the caller. + * + * Returns: errno + */ + +static int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len) +{ + struct gfs2_holder i_gh; + struct buffer_head *dibh; + unsigned int x; + int error; + + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); + error = gfs2_glock_nq(&i_gh); + if (error) { + gfs2_holder_uninit(&i_gh); + return error; + } + + if (!ip->i_disksize) { + gfs2_consist_inode(ip); + error = -EIO; + goto out; + } + + error = gfs2_meta_inode_buffer(ip, &dibh); + if (error) + goto out; + + x = ip->i_disksize + 1; + if (x > *len) { + *buf = kmalloc(x, GFP_NOFS); + if (!*buf) { + error = -ENOMEM; + goto out_brelse; + } + } + + memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x); + *len = x; + +out_brelse: + brelse(dibh); +out: + gfs2_glock_dq_uninit(&i_gh); + return error; +} + +/** * gfs2_readlink - Read the value of a symlink * @dentry: the symlink * @buf: the buffer to read the symlink data into diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c deleted file mode 100644 index 458019569dcb..000000000000 --- a/fs/gfs2/ops_super.c +++ /dev/null @@ -1,723 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/completion.h> -#include <linux/buffer_head.h> -#include <linux/statfs.h> -#include <linux/seq_file.h> -#include <linux/mount.h> -#include <linux/kthread.h> -#include <linux/delay.h> -#include <linux/gfs2_ondisk.h> -#include <linux/crc32.h> -#include <linux/time.h> - -#include "gfs2.h" -#include "incore.h" -#include "glock.h" -#include "inode.h" -#include "log.h" -#include "quota.h" -#include "recovery.h" -#include "rgrp.h" -#include "super.h" -#include "sys.h" -#include "util.h" -#include "trans.h" -#include "dir.h" -#include "eattr.h" -#include "bmap.h" -#include "meta_io.h" - -#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) - -/** - * gfs2_write_inode - Make sure the inode is stable on the disk - * @inode: The inode - * @sync: synchronous write flag - * - * Returns: errno - */ - -static int gfs2_write_inode(struct inode *inode, int sync) -{ - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_holder gh; - struct buffer_head *bh; - struct timespec atime; - struct gfs2_dinode *di; - int ret = 0; - - /* Check this is a "normal" inode, etc */ - if (!test_bit(GIF_USER, &ip->i_flags) || - (current->flags & PF_MEMALLOC)) - return 0; - ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - if (ret) - goto do_flush; - ret = gfs2_trans_begin(sdp, RES_DINODE, 0); - if (ret) - goto do_unlock; - ret = gfs2_meta_inode_buffer(ip, &bh); - if (ret == 0) { - di = (struct gfs2_dinode *)bh->b_data; - atime.tv_sec = be64_to_cpu(di->di_atime); - atime.tv_nsec = be32_to_cpu(di->di_atime_nsec); - if (timespec_compare(&inode->i_atime, &atime) > 0) { - gfs2_trans_add_bh(ip->i_gl, bh, 1); - gfs2_dinode_out(ip, bh->b_data); - } - brelse(bh); - } - gfs2_trans_end(sdp); -do_unlock: - gfs2_glock_dq_uninit(&gh); -do_flush: - if (sync != 0) - gfs2_log_flush(GFS2_SB(inode), ip->i_gl); - return ret; -} - -/** - * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one - * @sdp: the filesystem - * - * Returns: errno - */ - -static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) -{ - struct gfs2_holder t_gh; - int error; - - gfs2_quota_sync(sdp); - gfs2_statfs_sync(sdp); - - error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, - &t_gh); - if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return error; - - gfs2_meta_syncfs(sdp); - gfs2_log_shutdown(sdp); - - clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - - if (t_gh.gh_gl) - gfs2_glock_dq_uninit(&t_gh); - - gfs2_quota_cleanup(sdp); - - return error; -} - -/** - * gfs2_put_super - Unmount the filesystem - * @sb: The VFS superblock - * - */ - -static void gfs2_put_super(struct super_block *sb) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - int error; - - /* Unfreeze the filesystem, if we need to */ - - mutex_lock(&sdp->sd_freeze_lock); - if (sdp->sd_freeze_count) - gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); - mutex_unlock(&sdp->sd_freeze_lock); - - kthread_stop(sdp->sd_quotad_process); - kthread_stop(sdp->sd_logd_process); - kthread_stop(sdp->sd_recoverd_process); - - if (!(sb->s_flags & MS_RDONLY)) { - error = gfs2_make_fs_ro(sdp); - if (error) - gfs2_io_error(sdp); - } - /* At this point, we're through modifying the disk */ - - /* Release stuff */ - - iput(sdp->sd_jindex); - iput(sdp->sd_inum_inode); - iput(sdp->sd_statfs_inode); - iput(sdp->sd_rindex); - iput(sdp->sd_quota_inode); - - gfs2_glock_put(sdp->sd_rename_gl); - gfs2_glock_put(sdp->sd_trans_gl); - - if (!sdp->sd_args.ar_spectator) { - gfs2_glock_dq_uninit(&sdp->sd_journal_gh); - gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); - gfs2_glock_dq_uninit(&sdp->sd_ir_gh); - gfs2_glock_dq_uninit(&sdp->sd_sc_gh); - gfs2_glock_dq_uninit(&sdp->sd_qc_gh); - iput(sdp->sd_ir_inode); - iput(sdp->sd_sc_inode); - iput(sdp->sd_qc_inode); - } - - gfs2_glock_dq_uninit(&sdp->sd_live_gh); - gfs2_clear_rgrpd(sdp); - gfs2_jindex_free(sdp); - /* Take apart glock structures and buffer lists */ - gfs2_gl_hash_clear(sdp); - /* Unmount the locking protocol */ - gfs2_lm_unmount(sdp); - - /* At this point, we're through participating in the lockspace */ - gfs2_sys_fs_del(sdp); -} - -/** - * gfs2_write_super - * @sb: the superblock - * - */ - -static void gfs2_write_super(struct super_block *sb) -{ - sb->s_dirt = 0; -} - -/** - * gfs2_sync_fs - sync the filesystem - * @sb: the superblock - * - * Flushes the log to disk. - */ - -static int gfs2_sync_fs(struct super_block *sb, int wait) -{ - sb->s_dirt = 0; - if (wait && sb->s_fs_info) - gfs2_log_flush(sb->s_fs_info, NULL); - return 0; -} - -/** - * gfs2_freeze - prevent further writes to the filesystem - * @sb: the VFS structure for the filesystem - * - */ - -static int gfs2_freeze(struct super_block *sb) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - int error; - - if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return -EINVAL; - - for (;;) { - error = gfs2_freeze_fs(sdp); - if (!error) - break; - - switch (error) { - case -EBUSY: - fs_err(sdp, "waiting for recovery before freeze\n"); - break; - - default: - fs_err(sdp, "error freezing FS: %d\n", error); - break; - } - - fs_err(sdp, "retrying...\n"); - msleep(1000); - } - return 0; -} - -/** - * gfs2_unfreeze - reallow writes to the filesystem - * @sb: the VFS structure for the filesystem - * - */ - -static int gfs2_unfreeze(struct super_block *sb) -{ - gfs2_unfreeze_fs(sb->s_fs_info); - return 0; -} - -/** - * statfs_fill - fill in the sg for a given RG - * @rgd: the RG - * @sc: the sc structure - * - * Returns: 0 on success, -ESTALE if the LVB is invalid - */ - -static int statfs_slow_fill(struct gfs2_rgrpd *rgd, - struct gfs2_statfs_change_host *sc) -{ - gfs2_rgrp_verify(rgd); - sc->sc_total += rgd->rd_data; - sc->sc_free += rgd->rd_free; - sc->sc_dinodes += rgd->rd_dinodes; - return 0; -} - -/** - * gfs2_statfs_slow - Stat a filesystem using asynchronous locking - * @sdp: the filesystem - * @sc: the sc info that will be returned - * - * Any error (other than a signal) will cause this routine to fall back - * to the synchronous version. - * - * FIXME: This really shouldn't busy wait like this. - * - * Returns: errno - */ - -static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) -{ - struct gfs2_holder ri_gh; - struct gfs2_rgrpd *rgd_next; - struct gfs2_holder *gha, *gh; - unsigned int slots = 64; - unsigned int x; - int done; - int error = 0, err; - - memset(sc, 0, sizeof(struct gfs2_statfs_change_host)); - gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL); - if (!gha) - return -ENOMEM; - - error = gfs2_rindex_hold(sdp, &ri_gh); - if (error) - goto out; - - rgd_next = gfs2_rgrpd_get_first(sdp); - - for (;;) { - done = 1; - - for (x = 0; x < slots; x++) { - gh = gha + x; - - if (gh->gh_gl && gfs2_glock_poll(gh)) { - err = gfs2_glock_wait(gh); - if (err) { - gfs2_holder_uninit(gh); - error = err; - } else { - if (!error) - error = statfs_slow_fill( - gh->gh_gl->gl_object, sc); - gfs2_glock_dq_uninit(gh); - } - } - - if (gh->gh_gl) - done = 0; - else if (rgd_next && !error) { - error = gfs2_glock_nq_init(rgd_next->rd_gl, - LM_ST_SHARED, - GL_ASYNC, - gh); - rgd_next = gfs2_rgrpd_get_next(rgd_next); - done = 0; - } - - if (signal_pending(current)) - error = -ERESTARTSYS; - } - - if (done) - break; - - yield(); - } - - gfs2_glock_dq_uninit(&ri_gh); - -out: - kfree(gha); - return error; -} - -/** - * gfs2_statfs_i - Do a statfs - * @sdp: the filesystem - * @sg: the sg structure - * - * Returns: errno - */ - -static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) -{ - struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; - struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; - - spin_lock(&sdp->sd_statfs_spin); - - *sc = *m_sc; - sc->sc_total += l_sc->sc_total; - sc->sc_free += l_sc->sc_free; - sc->sc_dinodes += l_sc->sc_dinodes; - - spin_unlock(&sdp->sd_statfs_spin); - - if (sc->sc_free < 0) - sc->sc_free = 0; - if (sc->sc_free > sc->sc_total) - sc->sc_free = sc->sc_total; - if (sc->sc_dinodes < 0) - sc->sc_dinodes = 0; - - return 0; -} - -/** - * gfs2_statfs - Gather and return stats about the filesystem - * @sb: The superblock - * @statfsbuf: The buffer - * - * Returns: 0 on success or error code - */ - -static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) -{ - struct super_block *sb = dentry->d_inode->i_sb; - struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_statfs_change_host sc; - int error; - - if (gfs2_tune_get(sdp, gt_statfs_slow)) - error = gfs2_statfs_slow(sdp, &sc); - else - error = gfs2_statfs_i(sdp, &sc); - - if (error) - return error; - - buf->f_type = GFS2_MAGIC; - buf->f_bsize = sdp->sd_sb.sb_bsize; - buf->f_blocks = sc.sc_total; - buf->f_bfree = sc.sc_free; - buf->f_bavail = sc.sc_free; - buf->f_files = sc.sc_dinodes + sc.sc_free; - buf->f_ffree = sc.sc_free; - buf->f_namelen = GFS2_FNAMESIZE; - - return 0; -} - -/** - * gfs2_remount_fs - called when the FS is remounted - * @sb: the filesystem - * @flags: the remount flags - * @data: extra data passed in (not used right now) - * - * Returns: errno - */ - -static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_args args = sdp->sd_args; /* Default to current settings */ - int error; - - error = gfs2_mount_args(sdp, &args, data); - if (error) - return error; - - /* Not allowed to change locking details */ - if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) || - strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) || - strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata)) - return -EINVAL; - - /* Some flags must not be changed */ - if (args_neq(&args, &sdp->sd_args, spectator) || - args_neq(&args, &sdp->sd_args, ignore_local_fs) || - args_neq(&args, &sdp->sd_args, localflocks) || - args_neq(&args, &sdp->sd_args, localcaching) || - args_neq(&args, &sdp->sd_args, meta)) - return -EINVAL; - - if (sdp->sd_args.ar_spectator) - *flags |= MS_RDONLY; - - if ((sb->s_flags ^ *flags) & MS_RDONLY) { - if (*flags & MS_RDONLY) - error = gfs2_make_fs_ro(sdp); - else - error = gfs2_make_fs_rw(sdp); - if (error) - return error; - } - - sdp->sd_args = args; - if (sdp->sd_args.ar_posix_acl) - sb->s_flags |= MS_POSIXACL; - else - sb->s_flags &= ~MS_POSIXACL; - return 0; -} - -/** - * gfs2_drop_inode - Drop an inode (test for remote unlink) - * @inode: The inode to drop - * - * If we've received a callback on an iopen lock then its because a - * remote node tried to deallocate the inode but failed due to this node - * still having the inode open. Here we mark the link count zero - * since we know that it must have reached zero if the GLF_DEMOTE flag - * is set on the iopen glock. If we didn't do a disk read since the - * remote node removed the final link then we might otherwise miss - * this event. This check ensures that this node will deallocate the - * inode's blocks, or alternatively pass the baton on to another - * node for later deallocation. - */ - -static void gfs2_drop_inode(struct inode *inode) -{ - struct gfs2_inode *ip = GFS2_I(inode); - - if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) { - struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; - if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags)) - clear_nlink(inode); - } - generic_drop_inode(inode); -} - -/** - * gfs2_clear_inode - Deallocate an inode when VFS is done with it - * @inode: The VFS inode - * - */ - -static void gfs2_clear_inode(struct inode *inode) -{ - struct gfs2_inode *ip = GFS2_I(inode); - - /* This tells us its a "real" inode and not one which only - * serves to contain an address space (see rgrp.c, meta_io.c) - * which therefore doesn't have its own glocks. - */ - if (test_bit(GIF_USER, &ip->i_flags)) { - ip->i_gl->gl_object = NULL; - gfs2_glock_put(ip->i_gl); - ip->i_gl = NULL; - if (ip->i_iopen_gh.gh_gl) { - ip->i_iopen_gh.gh_gl->gl_object = NULL; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); - } - } -} - -static int is_ancestor(const struct dentry *d1, const struct dentry *d2) -{ - do { - if (d1 == d2) - return 1; - d1 = d1->d_parent; - } while (!IS_ROOT(d1)); - return 0; -} - -/** - * gfs2_show_options - Show mount options for /proc/mounts - * @s: seq_file structure - * @mnt: vfsmount - * - * Returns: 0 on success or error code - */ - -static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) -{ - struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info; - struct gfs2_args *args = &sdp->sd_args; - - if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir)) - seq_printf(s, ",meta"); - if (args->ar_lockproto[0]) - seq_printf(s, ",lockproto=%s", args->ar_lockproto); - if (args->ar_locktable[0]) - seq_printf(s, ",locktable=%s", args->ar_locktable); - if (args->ar_hostdata[0]) - seq_printf(s, ",hostdata=%s", args->ar_hostdata); - if (args->ar_spectator) - seq_printf(s, ",spectator"); - if (args->ar_ignore_local_fs) - seq_printf(s, ",ignore_local_fs"); - if (args->ar_localflocks) - seq_printf(s, ",localflocks"); - if (args->ar_localcaching) - seq_printf(s, ",localcaching"); - if (args->ar_debug) - seq_printf(s, ",debug"); - if (args->ar_upgrade) - seq_printf(s, ",upgrade"); - if (args->ar_posix_acl) - seq_printf(s, ",acl"); - if (args->ar_quota != GFS2_QUOTA_DEFAULT) { - char *state; - switch (args->ar_quota) { - case GFS2_QUOTA_OFF: - state = "off"; - break; - case GFS2_QUOTA_ACCOUNT: - state = "account"; - break; - case GFS2_QUOTA_ON: - state = "on"; - break; - default: - state = "unknown"; - break; - } - seq_printf(s, ",quota=%s", state); - } - if (args->ar_suiddir) - seq_printf(s, ",suiddir"); - if (args->ar_data != GFS2_DATA_DEFAULT) { - char *state; - switch (args->ar_data) { - case GFS2_DATA_WRITEBACK: - state = "writeback"; - break; - case GFS2_DATA_ORDERED: - state = "ordered"; - break; - default: - state = "unknown"; - break; - } - seq_printf(s, ",data=%s", state); - } - if (args->ar_discard) - seq_printf(s, ",discard"); - - return 0; -} - -/* - * We have to (at the moment) hold the inodes main lock to cover - * the gap between unlocking the shared lock on the iopen lock and - * taking the exclusive lock. I'd rather do a shared -> exclusive - * conversion on the iopen lock, but we can change that later. This - * is safe, just less efficient. - */ - -static void gfs2_delete_inode(struct inode *inode) -{ - struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - int error; - - if (!test_bit(GIF_USER, &ip->i_flags)) - goto out; - - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - if (unlikely(error)) { - gfs2_glock_dq_uninit(&ip->i_iopen_gh); - goto out; - } - - gfs2_glock_dq_wait(&ip->i_iopen_gh); - gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh); - error = gfs2_glock_nq(&ip->i_iopen_gh); - if (error) - goto out_truncate; - - if (S_ISDIR(inode->i_mode) && - (ip->i_diskflags & GFS2_DIF_EXHASH)) { - error = gfs2_dir_exhash_dealloc(ip); - if (error) - goto out_unlock; - } - - if (ip->i_eattr) { - error = gfs2_ea_dealloc(ip); - if (error) - goto out_unlock; - } - - if (!gfs2_is_stuffed(ip)) { - error = gfs2_file_dealloc(ip); - if (error) - goto out_unlock; - } - - error = gfs2_dinode_dealloc(ip); - if (error) - goto out_unlock; - -out_truncate: - error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); - if (error) - goto out_unlock; - /* Needs to be done before glock release & also in a transaction */ - truncate_inode_pages(&inode->i_data, 0); - gfs2_trans_end(sdp); - -out_unlock: - if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) - gfs2_glock_dq(&ip->i_iopen_gh); - gfs2_holder_uninit(&ip->i_iopen_gh); - gfs2_glock_dq_uninit(&gh); - if (error && error != GLR_TRYFAILED) - fs_warn(sdp, "gfs2_delete_inode: %d\n", error); -out: - truncate_inode_pages(&inode->i_data, 0); - clear_inode(inode); -} - -static struct inode *gfs2_alloc_inode(struct super_block *sb) -{ - struct gfs2_inode *ip; - - ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL); - if (ip) { - ip->i_flags = 0; - ip->i_gl = NULL; - } - return &ip->i_inode; -} - -static void gfs2_destroy_inode(struct inode *inode) -{ - kmem_cache_free(gfs2_inode_cachep, inode); -} - -const struct super_operations gfs2_super_ops = { - .alloc_inode = gfs2_alloc_inode, - .destroy_inode = gfs2_destroy_inode, - .write_inode = gfs2_write_inode, - .delete_inode = gfs2_delete_inode, - .put_super = gfs2_put_super, - .write_super = gfs2_write_super, - .sync_fs = gfs2_sync_fs, - .freeze_fs = gfs2_freeze, - .unfreeze_fs = gfs2_unfreeze, - .statfs = gfs2_statfs, - .remount_fs = gfs2_remount_fs, - .clear_inode = gfs2_clear_inode, - .drop_inode = gfs2_drop_inode, - .show_options = gfs2_show_options, -}; - diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 152e6c4a0dca..2e9b9326bfc9 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -60,7 +60,6 @@ #include "super.h" #include "trans.h" #include "inode.h" -#include "ops_address.h" #include "util.h" #define QUOTA_USER 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 247e8f7d6b3d..59d2695509d3 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -13,8 +13,7 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/kthread.h> -#include <linux/freezer.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -441,18 +440,25 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); } -/** - * gfs2_recover_journal - recover a given journal - * @jd: the struct gfs2_jdesc describing the journal - * - * Acquire the journal's lock, check to see if the journal is clean, and - * do recovery if necessary. - * - * Returns: errno - */ +static int gfs2_recover_get_ref(struct slow_work *work) +{ + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); + if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags)) + return -EBUSY; + return 0; +} -int gfs2_recover_journal(struct gfs2_jdesc *jd) +static void gfs2_recover_put_ref(struct slow_work *work) +{ + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); + clear_bit(JDF_RECOVERY, &jd->jd_flags); + smp_mb__after_clear_bit(); + wake_up_bit(&jd->jd_flags, JDF_RECOVERY); +} + +static void gfs2_recover_work(struct slow_work *work) { + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); struct gfs2_inode *ip = GFS2_I(jd->jd_inode); struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); struct gfs2_log_header_host head; @@ -569,7 +575,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) gfs2_glock_dq_uninit(&j_gh); fs_info(sdp, "jid=%u: Done\n", jd->jd_jid); - return 0; + return; fail_gunlock_tr: gfs2_glock_dq_uninit(&t_gh); @@ -584,70 +590,28 @@ fail_gunlock_j: fail: gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP); - return error; } -static struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp) -{ - struct gfs2_jdesc *jd; - int found = 0; - - spin_lock(&sdp->sd_jindex_spin); +struct slow_work_ops gfs2_recover_ops = { + .get_ref = gfs2_recover_get_ref, + .put_ref = gfs2_recover_put_ref, + .execute = gfs2_recover_work, +}; - list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { - if (jd->jd_dirty) { - jd->jd_dirty = 0; - found = 1; - break; - } - } - spin_unlock(&sdp->sd_jindex_spin); - - if (!found) - jd = NULL; - return jd; -} - -/** - * gfs2_check_journals - Recover any dirty journals - * @sdp: the filesystem - * - */ - -static void gfs2_check_journals(struct gfs2_sbd *sdp) +static int gfs2_recovery_wait(void *word) { - struct gfs2_jdesc *jd; - - for (;;) { - jd = gfs2_jdesc_find_dirty(sdp); - if (!jd) - break; - - if (jd != sdp->sd_jdesc) - gfs2_recover_journal(jd); - } + schedule(); + return 0; } -/** - * gfs2_recoverd - Recover dead machine's journals - * @sdp: Pointer to GFS2 superblock - * - */ - -int gfs2_recoverd(void *data) +int gfs2_recover_journal(struct gfs2_jdesc *jd) { - struct gfs2_sbd *sdp = data; - unsigned long t; - - while (!kthread_should_stop()) { - gfs2_check_journals(sdp); - t = gfs2_tune_get(sdp, gt_recoverd_secs) * HZ; - if (freezing(current)) - refrigerator(); - schedule_timeout_interruptible(t); - } - + int rv; + rv = slow_work_enqueue(&jd->jd_work); + if (rv) + return rv; + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE); return 0; } diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index a8218ea15b57..1616ac22569a 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -28,7 +28,7 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd); -extern int gfs2_recoverd(void *data); +extern struct slow_work_ops gfs2_recover_ops; #endif /* __RECOVERY_DOT_H__ */ diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 565038243fa2..de3239731db8 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -29,7 +29,6 @@ #include "util.h" #include "log.h" #include "inode.h" -#include "ops_address.h" #define BFITNOENT ((u32)~0) #define NO_BLOCK ((u64)~0) @@ -442,6 +441,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; + bi->bi_flags = 0; /* small rgrp; bitmap stored completely in header block */ if (length == 1) { bytes = bytes_left; @@ -580,7 +580,6 @@ static int read_rindex_entry(struct gfs2_inode *ip, rgd->rd_gl->gl_object = rgd; rgd->rd_flags &= ~GFS2_RDF_UPTODATE; - rgd->rd_flags |= GFS2_RDF_CHECK; return error; } @@ -701,10 +700,9 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf) u32 rg_flags; rg_flags = be32_to_cpu(str->rg_flags); - if (rg_flags & GFS2_RGF_NOALLOC) - rgd->rd_flags |= GFS2_RDF_NOALLOC; - else - rgd->rd_flags &= ~GFS2_RDF_NOALLOC; + rg_flags &= ~GFS2_RDF_MASK; + rgd->rd_flags &= GFS2_RDF_MASK; + rgd->rd_flags |= rg_flags; rgd->rd_free = be32_to_cpu(str->rg_free); rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes); rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration); @@ -713,11 +711,8 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf) static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf) { struct gfs2_rgrp *str = buf; - u32 rg_flags = 0; - if (rgd->rd_flags & GFS2_RDF_NOALLOC) - rg_flags |= GFS2_RGF_NOALLOC; - str->rg_flags = cpu_to_be32(rg_flags); + str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK); str->rg_free = cpu_to_be32(rgd->rd_free); str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes); str->__pad = cpu_to_be32(0); @@ -775,8 +770,10 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) } if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) { + for (x = 0; x < length; x++) + clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags); gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data); - rgd->rd_flags |= GFS2_RDF_UPTODATE; + rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); } spin_lock(&sdp->sd_rindex_spin); @@ -845,7 +842,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, struct super_block *sb = sdp->sd_vfs; struct block_device *bdev = sb->s_bdev; const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize / - bdev_hardsect_size(sb->s_bdev); + bdev_logical_block_size(sb->s_bdev); u64 blk; sector_t start = 0; sector_t nr_sects = 0; @@ -903,6 +900,7 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) continue; if (sdp->sd_args.ar_discard) gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi); + clear_bit(GBF_FULL, &bi->bi_flags); memcpy(bi->bi_clone + bi->bi_offset, bi->bi_bh->b_data + bi->bi_offset, bi->bi_len); } @@ -942,7 +940,7 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al) struct gfs2_sbd *sdp = rgd->rd_sbd; int ret = 0; - if (rgd->rd_flags & GFS2_RDF_NOALLOC) + if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) return 0; spin_lock(&sdp->sd_rindex_spin); @@ -1315,30 +1313,37 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, { struct gfs2_bitmap *bi = NULL; const u32 length = rgd->rd_length; - u32 blk = 0; + u32 blk = BFITNOENT; unsigned int buf, x; const unsigned int elen = *n; - const u8 *buffer; + const u8 *buffer = NULL; *n = 0; /* Find bitmap block that contains bits for goal block */ for (buf = 0; buf < length; buf++) { bi = rgd->rd_bits + buf; - if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) - break; + /* Convert scope of "goal" from rgrp-wide to within found bit block */ + if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) { + goal -= bi->bi_start * GFS2_NBBY; + goto do_search; + } } + buf = 0; + goal = 0; - gfs2_assert(rgd->rd_sbd, buf < length); - - /* Convert scope of "goal" from rgrp-wide to within found bit block */ - goal -= bi->bi_start * GFS2_NBBY; - +do_search: /* Search (up to entire) bitmap in this rgrp for allocatable block. "x <= length", instead of "x < length", because we typically start the search in the middle of a bit block, but if we can't find an allocatable block anywhere else, we want to be able wrap around and search in the first part of our first-searched bit block. */ for (x = 0; x <= length; x++) { + bi = rgd->rd_bits + buf; + + if (test_bit(GBF_FULL, &bi->bi_flags) && + (old_state == GFS2_BLKST_FREE)) + goto skip; + /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone bitmaps, so we must search the originals for that. */ buffer = bi->bi_bh->b_data + bi->bi_offset; @@ -1349,33 +1354,39 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, if (blk != BFITNOENT) break; + if ((goal == 0) && (old_state == GFS2_BLKST_FREE)) + set_bit(GBF_FULL, &bi->bi_flags); + /* Try next bitmap block (wrap back to rgrp header if at end) */ - buf = (buf + 1) % length; - bi = rgd->rd_bits + buf; +skip: + buf++; + buf %= length; goal = 0; } - if (blk != BFITNOENT && old_state != new_state) { - *n = 1; - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); + if (blk == BFITNOENT) + return blk; + *n = 1; + if (old_state == new_state) + goto out; + + gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); + gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, + bi->bi_len, blk, new_state); + goal = blk; + while (*n < elen) { + goal++; + if (goal >= (bi->bi_len * GFS2_NBBY)) + break; + if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != + GFS2_BLKST_FREE) + break; gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi->bi_len, blk, new_state); - goal = blk; - while (*n < elen) { - goal++; - if (goal >= (bi->bi_len * GFS2_NBBY)) - break; - if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != - GFS2_BLKST_FREE) - break; - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, - bi->bi_offset, bi->bi_len, goal, - new_state); - (*n)++; - } + bi->bi_len, goal, new_state); + (*n)++; } - - return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk; +out: + return (bi->bi_start * GFS2_NBBY) + blk; } /** @@ -1435,13 +1446,33 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, } /** - * gfs2_alloc_block - Allocate a block + * gfs2_rgrp_dump - print out an rgrp + * @seq: The iterator + * @gl: The glock in question + * + */ + +int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl) +{ + const struct gfs2_rgrpd *rgd = gl->gl_object; + if (rgd == NULL) + return 0; + gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n", + (unsigned long long)rgd->rd_addr, rgd->rd_flags, + rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes); + return 0; +} + +/** + * gfs2_alloc_block - Allocate one or more blocks * @ip: the inode to allocate the block for + * @bn: Used to return the starting block number + * @n: requested number of blocks/extent length (value/result) * - * Returns: the allocated block + * Returns: 0 or error */ -u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) +int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head *dibh; @@ -1457,7 +1488,10 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) goal = rgd->rd_last_alloc; blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n); - BUG_ON(blk == BFITNOENT); + + /* Since all blocks are reserved in advance, this shouldn't happen */ + if (blk == BFITNOENT) + goto rgrp_error; rgd->rd_last_alloc = blk; block = rgd->rd_data0 + blk; @@ -1469,7 +1503,9 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal); brelse(dibh); } - gfs2_assert_withdraw(sdp, rgd->rd_free >= *n); + if (rgd->rd_free < *n) + goto rgrp_error; + rgd->rd_free -= *n; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1484,7 +1520,16 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) rgd->rd_free_clone -= *n; spin_unlock(&sdp->sd_rindex_spin); - return block; + *bn = block; + return 0; + +rgrp_error: + fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n", + (unsigned long long)rgd->rd_addr); + fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n"); + gfs2_rgrp_dump(NULL, rgd->rd_gl); + rgd->rd_flags |= GFS2_RDF_ERROR; + return -EIO; } /** diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 3181c7e624bf..1e76ff0f3e00 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -14,22 +14,22 @@ struct gfs2_rgrpd; struct gfs2_sbd; struct gfs2_holder; -void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd); struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk); struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp); struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd); -void gfs2_clear_rgrpd(struct gfs2_sbd *sdp); -int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh); +extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp); +extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh); -int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd); +extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd); -struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); +extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); static inline void gfs2_alloc_put(struct gfs2_inode *ip) { BUG_ON(ip->i_alloc == NULL); @@ -37,22 +37,22 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip) ip->i_alloc = NULL; } -int gfs2_inplace_reserve_i(struct gfs2_inode *ip, - char *file, unsigned int line); +extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, + unsigned int line); #define gfs2_inplace_reserve(ip) \ gfs2_inplace_reserve_i((ip), __FILE__, __LINE__) -void gfs2_inplace_release(struct gfs2_inode *ip); +extern void gfs2_inplace_release(struct gfs2_inode *ip); -unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block); +extern unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block); -u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n); -u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation); +extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n); +extern u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation); -void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); -void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); -void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); -void gfs2_unlink_di(struct inode *inode); +extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); +extern void gfs2_unlink_di(struct inode *inode); struct gfs2_rgrp_list { unsigned int rl_rgrps; @@ -61,10 +61,11 @@ struct gfs2_rgrp_list { struct gfs2_holder *rl_ghs; }; -void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, - u64 block); -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); -void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); -u64 gfs2_ri_total(struct gfs2_sbd *sdp); +extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, + u64 block); +extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); +extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); +extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); +extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl); #endif /* __RGRP_DOT_H__ */ diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 601913e0a482..40bcc37e5a70 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -7,14 +7,20 @@ * of the GNU General Public License version 2. */ +#include <linux/bio.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> -#include <linux/crc32.h> +#include <linux/statfs.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/kthread.h> +#include <linux/delay.h> #include <linux/gfs2_ondisk.h> -#include <linux/bio.h> +#include <linux/crc32.h> +#include <linux/time.h> #include "gfs2.h" #include "incore.h" @@ -31,6 +37,183 @@ #include "super.h" #include "trans.h" #include "util.h" +#include "sys.h" +#include "eattr.h" + +#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) + +enum { + Opt_lockproto, + Opt_locktable, + Opt_hostdata, + Opt_spectator, + Opt_ignore_local_fs, + Opt_localflocks, + Opt_localcaching, + Opt_debug, + Opt_nodebug, + Opt_upgrade, + Opt_acl, + Opt_noacl, + Opt_quota_off, + Opt_quota_account, + Opt_quota_on, + Opt_quota, + Opt_noquota, + Opt_suiddir, + Opt_nosuiddir, + Opt_data_writeback, + Opt_data_ordered, + Opt_meta, + Opt_discard, + Opt_nodiscard, + Opt_commit, + Opt_error, +}; + +static const match_table_t tokens = { + {Opt_lockproto, "lockproto=%s"}, + {Opt_locktable, "locktable=%s"}, + {Opt_hostdata, "hostdata=%s"}, + {Opt_spectator, "spectator"}, + {Opt_ignore_local_fs, "ignore_local_fs"}, + {Opt_localflocks, "localflocks"}, + {Opt_localcaching, "localcaching"}, + {Opt_debug, "debug"}, + {Opt_nodebug, "nodebug"}, + {Opt_upgrade, "upgrade"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_quota_off, "quota=off"}, + {Opt_quota_account, "quota=account"}, + {Opt_quota_on, "quota=on"}, + {Opt_quota, "quota"}, + {Opt_noquota, "noquota"}, + {Opt_suiddir, "suiddir"}, + {Opt_nosuiddir, "nosuiddir"}, + {Opt_data_writeback, "data=writeback"}, + {Opt_data_ordered, "data=ordered"}, + {Opt_meta, "meta"}, + {Opt_discard, "discard"}, + {Opt_nodiscard, "nodiscard"}, + {Opt_commit, "commit=%d"}, + {Opt_error, NULL} +}; + +/** + * gfs2_mount_args - Parse mount options + * @sdp: + * @data: + * + * Return: errno + */ + +int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) +{ + char *o; + int token; + substring_t tmp[MAX_OPT_ARGS]; + int rv; + + /* Split the options into tokens with the "," character and + process them */ + + while (1) { + o = strsep(&options, ","); + if (o == NULL) + break; + if (*o == '\0') + continue; + + token = match_token(o, tokens, tmp); + switch (token) { + case Opt_lockproto: + match_strlcpy(args->ar_lockproto, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_locktable: + match_strlcpy(args->ar_locktable, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_hostdata: + match_strlcpy(args->ar_hostdata, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_spectator: + args->ar_spectator = 1; + break; + case Opt_ignore_local_fs: + args->ar_ignore_local_fs = 1; + break; + case Opt_localflocks: + args->ar_localflocks = 1; + break; + case Opt_localcaching: + args->ar_localcaching = 1; + break; + case Opt_debug: + args->ar_debug = 1; + break; + case Opt_nodebug: + args->ar_debug = 0; + break; + case Opt_upgrade: + args->ar_upgrade = 1; + break; + case Opt_acl: + args->ar_posix_acl = 1; + break; + case Opt_noacl: + args->ar_posix_acl = 0; + break; + case Opt_quota_off: + case Opt_noquota: + args->ar_quota = GFS2_QUOTA_OFF; + break; + case Opt_quota_account: + args->ar_quota = GFS2_QUOTA_ACCOUNT; + break; + case Opt_quota_on: + case Opt_quota: + args->ar_quota = GFS2_QUOTA_ON; + break; + case Opt_suiddir: + args->ar_suiddir = 1; + break; + case Opt_nosuiddir: + args->ar_suiddir = 0; + break; + case Opt_data_writeback: + args->ar_data = GFS2_DATA_WRITEBACK; + break; + case Opt_data_ordered: + args->ar_data = GFS2_DATA_ORDERED; + break; + case Opt_meta: + args->ar_meta = 1; + break; + case Opt_discard: + args->ar_discard = 1; + break; + case Opt_nodiscard: + args->ar_discard = 0; + break; + case Opt_commit: + rv = match_int(&tmp[0], &args->ar_commit); + if (rv || args->ar_commit <= 0) { + fs_info(sdp, "commit mount option requires a positive numeric argument\n"); + return rv ? rv : -EINVAL; + } + break; + case Opt_error: + default: + fs_info(sdp, "invalid mount option: %s\n", o); + return -EINVAL; + } + } + + return 0; +} /** * gfs2_jindex_free - Clear all the journal index information @@ -436,3 +619,719 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp) mutex_unlock(&sdp->sd_freeze_lock); } + +/** + * gfs2_write_inode - Make sure the inode is stable on the disk + * @inode: The inode + * @sync: synchronous write flag + * + * Returns: errno + */ + +static int gfs2_write_inode(struct inode *inode, int sync) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + struct gfs2_holder gh; + struct buffer_head *bh; + struct timespec atime; + struct gfs2_dinode *di; + int ret = 0; + + /* Check this is a "normal" inode, etc */ + if (!test_bit(GIF_USER, &ip->i_flags) || + (current->flags & PF_MEMALLOC)) + return 0; + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (ret) + goto do_flush; + ret = gfs2_trans_begin(sdp, RES_DINODE, 0); + if (ret) + goto do_unlock; + ret = gfs2_meta_inode_buffer(ip, &bh); + if (ret == 0) { + di = (struct gfs2_dinode *)bh->b_data; + atime.tv_sec = be64_to_cpu(di->di_atime); + atime.tv_nsec = be32_to_cpu(di->di_atime_nsec); + if (timespec_compare(&inode->i_atime, &atime) > 0) { + gfs2_trans_add_bh(ip->i_gl, bh, 1); + gfs2_dinode_out(ip, bh->b_data); + } + brelse(bh); + } + gfs2_trans_end(sdp); +do_unlock: + gfs2_glock_dq_uninit(&gh); +do_flush: + if (sync != 0) + gfs2_log_flush(GFS2_SB(inode), ip->i_gl); + return ret; +} + +/** + * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one + * @sdp: the filesystem + * + * Returns: errno + */ + +static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) +{ + struct gfs2_holder t_gh; + int error; + + gfs2_quota_sync(sdp); + gfs2_statfs_sync(sdp); + + error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, + &t_gh); + if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + return error; + + gfs2_meta_syncfs(sdp); + gfs2_log_shutdown(sdp); + + clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); + + if (t_gh.gh_gl) + gfs2_glock_dq_uninit(&t_gh); + + gfs2_quota_cleanup(sdp); + + return error; +} + +static int gfs2_umount_recovery_wait(void *word) +{ + schedule(); + return 0; +} + +/** + * gfs2_put_super - Unmount the filesystem + * @sb: The VFS superblock + * + */ + +static void gfs2_put_super(struct super_block *sb) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + int error; + struct gfs2_jdesc *jd; + + /* Unfreeze the filesystem, if we need to */ + + mutex_lock(&sdp->sd_freeze_lock); + if (sdp->sd_freeze_count) + gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); + mutex_unlock(&sdp->sd_freeze_lock); + + /* No more recovery requests */ + set_bit(SDF_NORECOVERY, &sdp->sd_flags); + smp_mb(); + + /* Wait on outstanding recovery */ +restart: + spin_lock(&sdp->sd_jindex_spin); + list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { + if (!test_bit(JDF_RECOVERY, &jd->jd_flags)) + continue; + spin_unlock(&sdp->sd_jindex_spin); + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, + gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE); + goto restart; + } + spin_unlock(&sdp->sd_jindex_spin); + + kthread_stop(sdp->sd_quotad_process); + kthread_stop(sdp->sd_logd_process); + + if (!(sb->s_flags & MS_RDONLY)) { + error = gfs2_make_fs_ro(sdp); + if (error) + gfs2_io_error(sdp); + } + /* At this point, we're through modifying the disk */ + + /* Release stuff */ + + iput(sdp->sd_jindex); + iput(sdp->sd_inum_inode); + iput(sdp->sd_statfs_inode); + iput(sdp->sd_rindex); + iput(sdp->sd_quota_inode); + + gfs2_glock_put(sdp->sd_rename_gl); + gfs2_glock_put(sdp->sd_trans_gl); + + if (!sdp->sd_args.ar_spectator) { + gfs2_glock_dq_uninit(&sdp->sd_journal_gh); + gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); + gfs2_glock_dq_uninit(&sdp->sd_ir_gh); + gfs2_glock_dq_uninit(&sdp->sd_sc_gh); + gfs2_glock_dq_uninit(&sdp->sd_qc_gh); + iput(sdp->sd_ir_inode); + iput(sdp->sd_sc_inode); + iput(sdp->sd_qc_inode); + } + + gfs2_glock_dq_uninit(&sdp->sd_live_gh); + gfs2_clear_rgrpd(sdp); + gfs2_jindex_free(sdp); + /* Take apart glock structures and buffer lists */ + gfs2_gl_hash_clear(sdp); + /* Unmount the locking protocol */ + gfs2_lm_unmount(sdp); + + /* At this point, we're through participating in the lockspace */ + gfs2_sys_fs_del(sdp); +} + +/** + * gfs2_write_super + * @sb: the superblock + * + */ + +static void gfs2_write_super(struct super_block *sb) +{ + sb->s_dirt = 0; +} + +/** + * gfs2_sync_fs - sync the filesystem + * @sb: the superblock + * + * Flushes the log to disk. + */ + +static int gfs2_sync_fs(struct super_block *sb, int wait) +{ + sb->s_dirt = 0; + if (wait && sb->s_fs_info) + gfs2_log_flush(sb->s_fs_info, NULL); + return 0; +} + +/** + * gfs2_freeze - prevent further writes to the filesystem + * @sb: the VFS structure for the filesystem + * + */ + +static int gfs2_freeze(struct super_block *sb) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + int error; + + if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + return -EINVAL; + + for (;;) { + error = gfs2_freeze_fs(sdp); + if (!error) + break; + + switch (error) { + case -EBUSY: + fs_err(sdp, "waiting for recovery before freeze\n"); + break; + + default: + fs_err(sdp, "error freezing FS: %d\n", error); + break; + } + + fs_err(sdp, "retrying...\n"); + msleep(1000); + } + return 0; +} + +/** + * gfs2_unfreeze - reallow writes to the filesystem + * @sb: the VFS structure for the filesystem + * + */ + +static int gfs2_unfreeze(struct super_block *sb) +{ + gfs2_unfreeze_fs(sb->s_fs_info); + return 0; +} + +/** + * statfs_fill - fill in the sg for a given RG + * @rgd: the RG + * @sc: the sc structure + * + * Returns: 0 on success, -ESTALE if the LVB is invalid + */ + +static int statfs_slow_fill(struct gfs2_rgrpd *rgd, + struct gfs2_statfs_change_host *sc) +{ + gfs2_rgrp_verify(rgd); + sc->sc_total += rgd->rd_data; + sc->sc_free += rgd->rd_free; + sc->sc_dinodes += rgd->rd_dinodes; + return 0; +} + +/** + * gfs2_statfs_slow - Stat a filesystem using asynchronous locking + * @sdp: the filesystem + * @sc: the sc info that will be returned + * + * Any error (other than a signal) will cause this routine to fall back + * to the synchronous version. + * + * FIXME: This really shouldn't busy wait like this. + * + * Returns: errno + */ + +static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) +{ + struct gfs2_holder ri_gh; + struct gfs2_rgrpd *rgd_next; + struct gfs2_holder *gha, *gh; + unsigned int slots = 64; + unsigned int x; + int done; + int error = 0, err; + + memset(sc, 0, sizeof(struct gfs2_statfs_change_host)); + gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL); + if (!gha) + return -ENOMEM; + + error = gfs2_rindex_hold(sdp, &ri_gh); + if (error) + goto out; + + rgd_next = gfs2_rgrpd_get_first(sdp); + + for (;;) { + done = 1; + + for (x = 0; x < slots; x++) { + gh = gha + x; + + if (gh->gh_gl && gfs2_glock_poll(gh)) { + err = gfs2_glock_wait(gh); + if (err) { + gfs2_holder_uninit(gh); + error = err; + } else { + if (!error) + error = statfs_slow_fill( + gh->gh_gl->gl_object, sc); + gfs2_glock_dq_uninit(gh); + } + } + + if (gh->gh_gl) + done = 0; + else if (rgd_next && !error) { + error = gfs2_glock_nq_init(rgd_next->rd_gl, + LM_ST_SHARED, + GL_ASYNC, + gh); + rgd_next = gfs2_rgrpd_get_next(rgd_next); + done = 0; + } + + if (signal_pending(current)) + error = -ERESTARTSYS; + } + + if (done) + break; + + yield(); + } + + gfs2_glock_dq_uninit(&ri_gh); + +out: + kfree(gha); + return error; +} + +/** + * gfs2_statfs_i - Do a statfs + * @sdp: the filesystem + * @sg: the sg structure + * + * Returns: errno + */ + +static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) +{ + struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; + struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; + + spin_lock(&sdp->sd_statfs_spin); + + *sc = *m_sc; + sc->sc_total += l_sc->sc_total; + sc->sc_free += l_sc->sc_free; + sc->sc_dinodes += l_sc->sc_dinodes; + + spin_unlock(&sdp->sd_statfs_spin); + + if (sc->sc_free < 0) + sc->sc_free = 0; + if (sc->sc_free > sc->sc_total) + sc->sc_free = sc->sc_total; + if (sc->sc_dinodes < 0) + sc->sc_dinodes = 0; + + return 0; +} + +/** + * gfs2_statfs - Gather and return stats about the filesystem + * @sb: The superblock + * @statfsbuf: The buffer + * + * Returns: 0 on success or error code + */ + +static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_inode->i_sb; + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_statfs_change_host sc; + int error; + + if (gfs2_tune_get(sdp, gt_statfs_slow)) + error = gfs2_statfs_slow(sdp, &sc); + else + error = gfs2_statfs_i(sdp, &sc); + + if (error) + return error; + + buf->f_type = GFS2_MAGIC; + buf->f_bsize = sdp->sd_sb.sb_bsize; + buf->f_blocks = sc.sc_total; + buf->f_bfree = sc.sc_free; + buf->f_bavail = sc.sc_free; + buf->f_files = sc.sc_dinodes + sc.sc_free; + buf->f_ffree = sc.sc_free; + buf->f_namelen = GFS2_FNAMESIZE; + + return 0; +} + +/** + * gfs2_remount_fs - called when the FS is remounted + * @sb: the filesystem + * @flags: the remount flags + * @data: extra data passed in (not used right now) + * + * Returns: errno + */ + +static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_args args = sdp->sd_args; /* Default to current settings */ + struct gfs2_tune *gt = &sdp->sd_tune; + int error; + + spin_lock(>->gt_spin); + args.ar_commit = gt->gt_log_flush_secs; + spin_unlock(>->gt_spin); + error = gfs2_mount_args(sdp, &args, data); + if (error) + return error; + + /* Not allowed to change locking details */ + if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) || + strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) || + strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata)) + return -EINVAL; + + /* Some flags must not be changed */ + if (args_neq(&args, &sdp->sd_args, spectator) || + args_neq(&args, &sdp->sd_args, ignore_local_fs) || + args_neq(&args, &sdp->sd_args, localflocks) || + args_neq(&args, &sdp->sd_args, localcaching) || + args_neq(&args, &sdp->sd_args, meta)) + return -EINVAL; + + if (sdp->sd_args.ar_spectator) + *flags |= MS_RDONLY; + + if ((sb->s_flags ^ *flags) & MS_RDONLY) { + if (*flags & MS_RDONLY) + error = gfs2_make_fs_ro(sdp); + else + error = gfs2_make_fs_rw(sdp); + if (error) + return error; + } + + sdp->sd_args = args; + if (sdp->sd_args.ar_posix_acl) + sb->s_flags |= MS_POSIXACL; + else + sb->s_flags &= ~MS_POSIXACL; + spin_lock(>->gt_spin); + gt->gt_log_flush_secs = args.ar_commit; + spin_unlock(>->gt_spin); + + return 0; +} + +/** + * gfs2_drop_inode - Drop an inode (test for remote unlink) + * @inode: The inode to drop + * + * If we've received a callback on an iopen lock then its because a + * remote node tried to deallocate the inode but failed due to this node + * still having the inode open. Here we mark the link count zero + * since we know that it must have reached zero if the GLF_DEMOTE flag + * is set on the iopen glock. If we didn't do a disk read since the + * remote node removed the final link then we might otherwise miss + * this event. This check ensures that this node will deallocate the + * inode's blocks, or alternatively pass the baton on to another + * node for later deallocation. + */ + +static void gfs2_drop_inode(struct inode *inode) +{ + struct gfs2_inode *ip = GFS2_I(inode); + + if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) { + struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; + if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags)) + clear_nlink(inode); + } + generic_drop_inode(inode); +} + +/** + * gfs2_clear_inode - Deallocate an inode when VFS is done with it + * @inode: The VFS inode + * + */ + +static void gfs2_clear_inode(struct inode *inode) +{ + struct gfs2_inode *ip = GFS2_I(inode); + + /* This tells us its a "real" inode and not one which only + * serves to contain an address space (see rgrp.c, meta_io.c) + * which therefore doesn't have its own glocks. + */ + if (test_bit(GIF_USER, &ip->i_flags)) { + ip->i_gl->gl_object = NULL; + gfs2_glock_put(ip->i_gl); + ip->i_gl = NULL; + if (ip->i_iopen_gh.gh_gl) { + ip->i_iopen_gh.gh_gl->gl_object = NULL; + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + } + } +} + +static int is_ancestor(const struct dentry *d1, const struct dentry *d2) +{ + do { + if (d1 == d2) + return 1; + d1 = d1->d_parent; + } while (!IS_ROOT(d1)); + return 0; +} + +/** + * gfs2_show_options - Show mount options for /proc/mounts + * @s: seq_file structure + * @mnt: vfsmount + * + * Returns: 0 on success or error code + */ + +static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) +{ + struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info; + struct gfs2_args *args = &sdp->sd_args; + int lfsecs; + + if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir)) + seq_printf(s, ",meta"); + if (args->ar_lockproto[0]) + seq_printf(s, ",lockproto=%s", args->ar_lockproto); + if (args->ar_locktable[0]) + seq_printf(s, ",locktable=%s", args->ar_locktable); + if (args->ar_hostdata[0]) + seq_printf(s, ",hostdata=%s", args->ar_hostdata); + if (args->ar_spectator) + seq_printf(s, ",spectator"); + if (args->ar_ignore_local_fs) + seq_printf(s, ",ignore_local_fs"); + if (args->ar_localflocks) + seq_printf(s, ",localflocks"); + if (args->ar_localcaching) + seq_printf(s, ",localcaching"); + if (args->ar_debug) + seq_printf(s, ",debug"); + if (args->ar_upgrade) + seq_printf(s, ",upgrade"); + if (args->ar_posix_acl) + seq_printf(s, ",acl"); + if (args->ar_quota != GFS2_QUOTA_DEFAULT) { + char *state; + switch (args->ar_quota) { + case GFS2_QUOTA_OFF: + state = "off"; + break; + case GFS2_QUOTA_ACCOUNT: + state = "account"; + break; + case GFS2_QUOTA_ON: + state = "on"; + break; + default: + state = "unknown"; + break; + } + seq_printf(s, ",quota=%s", state); + } + if (args->ar_suiddir) + seq_printf(s, ",suiddir"); + if (args->ar_data != GFS2_DATA_DEFAULT) { + char *state; + switch (args->ar_data) { + case GFS2_DATA_WRITEBACK: + state = "writeback"; + break; + case GFS2_DATA_ORDERED: + state = "ordered"; + break; + default: + state = "unknown"; + break; + } + seq_printf(s, ",data=%s", state); + } + if (args->ar_discard) + seq_printf(s, ",discard"); + lfsecs = sdp->sd_tune.gt_log_flush_secs; + if (lfsecs != 60) + seq_printf(s, ",commit=%d", lfsecs); + return 0; +} + +/* + * We have to (at the moment) hold the inodes main lock to cover + * the gap between unlocking the shared lock on the iopen lock and + * taking the exclusive lock. I'd rather do a shared -> exclusive + * conversion on the iopen lock, but we can change that later. This + * is safe, just less efficient. + */ + +static void gfs2_delete_inode(struct inode *inode) +{ + struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + int error; + + if (!test_bit(GIF_USER, &ip->i_flags)) + goto out; + + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (unlikely(error)) { + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + goto out; + } + + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh); + error = gfs2_glock_nq(&ip->i_iopen_gh); + if (error) + goto out_truncate; + + if (S_ISDIR(inode->i_mode) && + (ip->i_diskflags & GFS2_DIF_EXHASH)) { + error = gfs2_dir_exhash_dealloc(ip); + if (error) + goto out_unlock; + } + + if (ip->i_eattr) { + error = gfs2_ea_dealloc(ip); + if (error) + goto out_unlock; + } + + if (!gfs2_is_stuffed(ip)) { + error = gfs2_file_dealloc(ip); + if (error) + goto out_unlock; + } + + error = gfs2_dinode_dealloc(ip); + if (error) + goto out_unlock; + +out_truncate: + error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); + if (error) + goto out_unlock; + /* Needs to be done before glock release & also in a transaction */ + truncate_inode_pages(&inode->i_data, 0); + gfs2_trans_end(sdp); + +out_unlock: + if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) + gfs2_glock_dq(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_uninit(&gh); + if (error && error != GLR_TRYFAILED && error != -EROFS) + fs_warn(sdp, "gfs2_delete_inode: %d\n", error); +out: + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); +} + +static struct inode *gfs2_alloc_inode(struct super_block *sb) +{ + struct gfs2_inode *ip; + + ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL); + if (ip) { + ip->i_flags = 0; + ip->i_gl = NULL; + } + return &ip->i_inode; +} + +static void gfs2_destroy_inode(struct inode *inode) +{ + kmem_cache_free(gfs2_inode_cachep, inode); +} + +const struct super_operations gfs2_super_ops = { + .alloc_inode = gfs2_alloc_inode, + .destroy_inode = gfs2_destroy_inode, + .write_inode = gfs2_write_inode, + .delete_inode = gfs2_delete_inode, + .put_super = gfs2_put_super, + .write_super = gfs2_write_super, + .sync_fs = gfs2_sync_fs, + .freeze_fs = gfs2_freeze, + .unfreeze_fs = gfs2_unfreeze, + .statfs = gfs2_statfs, + .remount_fs = gfs2_remount_fs, + .clear_inode = gfs2_clear_inode, + .drop_inode = gfs2_drop_inode, + .show_options = gfs2_show_options, +}; + diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 7655f5025fec..23419dc3027b 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -26,6 +26,36 @@ #include "util.h" #include "glops.h" +struct gfs2_attr { + struct attribute attr; + ssize_t (*show)(struct gfs2_sbd *, char *); + ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); +}; + +static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); + return a->show ? a->show(sdp, buf) : 0; +} + +static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); + return a->store ? a->store(sdp, buf, len) : len; +} + +static struct sysfs_ops gfs2_attr_ops = { + .show = gfs2_attr_show, + .store = gfs2_attr_store, +}; + + +static struct kset *gfs2_kset; + static ssize_t id_show(struct gfs2_sbd *sdp, char *buf) { return snprintf(buf, PAGE_SIZE, "%u:%u\n", @@ -212,11 +242,6 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len return len; } -struct gfs2_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); - ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); -}; #define GFS2_ATTR(name, mode, show, store) \ static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store) @@ -246,58 +271,11 @@ static struct attribute *gfs2_attrs[] = { NULL, }; -static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr, - char *buf) -{ - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); - return a->show ? a->show(sdp, buf) : 0; -} - -static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t len) -{ - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); - return a->store ? a->store(sdp, buf, len) : len; -} - -static struct sysfs_ops gfs2_attr_ops = { - .show = gfs2_attr_show, - .store = gfs2_attr_store, -}; - static struct kobj_type gfs2_ktype = { .default_attrs = gfs2_attrs, .sysfs_ops = &gfs2_attr_ops, }; -static struct kset *gfs2_kset; - -/* - * display struct lm_lockstruct fields - */ - -struct lockstruct_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); -}; - -#define LOCKSTRUCT_ATTR(name, fmt) \ -static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ -{ \ - return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \ -} \ -static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name) - -LOCKSTRUCT_ATTR(jid, "%u\n"); -LOCKSTRUCT_ATTR(first, "%u\n"); - -static struct attribute *lockstruct_attrs[] = { - &lockstruct_attr_jid.attr, - &lockstruct_attr_first.attr, - NULL, -}; /* * lock_module. Originally from lock_dlm @@ -359,34 +337,33 @@ static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf) return sprintf(buf, "%d\n", ls->ls_first_done); } -static ssize_t recover_show(struct gfs2_sbd *sdp, char *buf) -{ - struct lm_lockstruct *ls = &sdp->sd_lockstruct; - return sprintf(buf, "%d\n", ls->ls_recover_jid); -} - -static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid) +static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { + unsigned jid; struct gfs2_jdesc *jd; + int rv; + + rv = sscanf(buf, "%u", &jid); + if (rv != 1) + return -EINVAL; + rv = -ESHUTDOWN; spin_lock(&sdp->sd_jindex_spin); + if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) + goto out; + rv = -EBUSY; + if (sdp->sd_jdesc->jd_jid == jid) + goto out; + rv = -ENOENT; list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { if (jd->jd_jid != jid) continue; - jd->jd_dirty = 1; + rv = slow_work_enqueue(&jd->jd_work); break; } +out: spin_unlock(&sdp->sd_jindex_spin); -} - -static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) -{ - struct lm_lockstruct *ls = &sdp->sd_lockstruct; - ls->ls_recover_jid = simple_strtol(buf, NULL, 0); - gfs2_jdesc_make_dirty(sdp, ls->ls_recover_jid); - if (sdp->sd_recoverd_process) - wake_up_process(sdp->sd_recoverd_process); - return len; + return rv ? rv : len; } static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf) @@ -401,31 +378,31 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf) return sprintf(buf, "%d\n", ls->ls_recover_jid_status); } -struct gdlm_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *sdp, char *); - ssize_t (*store)(struct gfs2_sbd *sdp, const char *, size_t); -}; +static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf) +{ + return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid); +} #define GDLM_ATTR(_name,_mode,_show,_store) \ -static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) - -GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); -GDLM_ATTR(block, 0644, block_show, block_store); -GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); -GDLM_ATTR(id, 0444, lkid_show, NULL); -GDLM_ATTR(first, 0444, lkfirst_show, NULL); -GDLM_ATTR(first_done, 0444, first_done_show, NULL); -GDLM_ATTR(recover, 0644, recover_show, recover_store); -GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); -GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); +static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) + +GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); +GDLM_ATTR(block, 0644, block_show, block_store); +GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); +GDLM_ATTR(id, 0444, lkid_show, NULL); +GDLM_ATTR(jid, 0444, jid_show, NULL); +GDLM_ATTR(first, 0444, lkfirst_show, NULL); +GDLM_ATTR(first_done, 0444, first_done_show, NULL); +GDLM_ATTR(recover, 0200, NULL, recover_store); +GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); +GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); static struct attribute *lock_module_attrs[] = { &gdlm_attr_proto_name.attr, &gdlm_attr_block.attr, &gdlm_attr_withdraw.attr, &gdlm_attr_id.attr, - &lockstruct_attr_jid.attr, + &gdlm_attr_jid.attr, &gdlm_attr_first.attr, &gdlm_attr_first_done.attr, &gdlm_attr_recover.attr, @@ -435,53 +412,6 @@ static struct attribute *lock_module_attrs[] = { }; /* - * display struct gfs2_args fields - */ - -struct args_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); -}; - -#define ARGS_ATTR(name, fmt) \ -static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ -{ \ - return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name); \ -} \ -static struct args_attr args_attr_##name = __ATTR_RO(name) - -ARGS_ATTR(lockproto, "%s\n"); -ARGS_ATTR(locktable, "%s\n"); -ARGS_ATTR(hostdata, "%s\n"); -ARGS_ATTR(spectator, "%d\n"); -ARGS_ATTR(ignore_local_fs, "%d\n"); -ARGS_ATTR(localcaching, "%d\n"); -ARGS_ATTR(localflocks, "%d\n"); -ARGS_ATTR(debug, "%d\n"); -ARGS_ATTR(upgrade, "%d\n"); -ARGS_ATTR(posix_acl, "%d\n"); -ARGS_ATTR(quota, "%u\n"); -ARGS_ATTR(suiddir, "%d\n"); -ARGS_ATTR(data, "%d\n"); - -static struct attribute *args_attrs[] = { - &args_attr_lockproto.attr, - &args_attr_locktable.attr, - &args_attr_hostdata.attr, - &args_attr_spectator.attr, - &args_attr_ignore_local_fs.attr, - &args_attr_localcaching.attr, - &args_attr_localflocks.attr, - &args_attr_debug.attr, - &args_attr_upgrade.attr, - &args_attr_posix_acl.attr, - &args_attr_quota.attr, - &args_attr_suiddir.attr, - &args_attr_data.attr, - NULL, -}; - -/* * get and set struct gfs2_tune fields */ @@ -531,14 +461,8 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field, return len; } -struct tune_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); - ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); -}; - #define TUNE_ATTR_3(name, show, store) \ -static struct tune_attr tune_attr_##name = __ATTR(name, 0644, show, store) +static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store) #define TUNE_ATTR_2(name, store) \ static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ @@ -554,15 +478,6 @@ static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\ } \ TUNE_ATTR_2(name, name##_store) -#define TUNE_ATTR_DAEMON(name, process) \ -static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\ -{ \ - ssize_t r = tune_set(sdp, &sdp->sd_tune.gt_##name, 1, buf, len); \ - wake_up_process(sdp->sd_##process); \ - return r; \ -} \ -TUNE_ATTR_2(name, name##_store) - TUNE_ATTR(incore_log_blocks, 0); TUNE_ATTR(log_flush_secs, 0); TUNE_ATTR(quota_warn_period, 0); @@ -574,8 +489,6 @@ TUNE_ATTR(new_files_jdata, 0); TUNE_ATTR(quota_simul_sync, 1); TUNE_ATTR(stall_secs, 1); TUNE_ATTR(statfs_quantum, 1); -TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process); -TUNE_ATTR_DAEMON(logd_secs, logd_process); TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store); static struct attribute *tune_attrs[] = { @@ -589,23 +502,11 @@ static struct attribute *tune_attrs[] = { &tune_attr_quota_simul_sync.attr, &tune_attr_stall_secs.attr, &tune_attr_statfs_quantum.attr, - &tune_attr_recoverd_secs.attr, - &tune_attr_logd_secs.attr, &tune_attr_quota_scale.attr, &tune_attr_new_files_jdata.attr, NULL, }; -static struct attribute_group lockstruct_group = { - .name = "lockstruct", - .attrs = lockstruct_attrs, -}; - -static struct attribute_group args_group = { - .name = "args", - .attrs = args_attrs, -}; - static struct attribute_group tune_group = { .name = "tune", .attrs = tune_attrs, @@ -626,17 +527,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail; - error = sysfs_create_group(&sdp->sd_kobj, &lockstruct_group); - if (error) - goto fail_reg; - - error = sysfs_create_group(&sdp->sd_kobj, &args_group); - if (error) - goto fail_lockstruct; - error = sysfs_create_group(&sdp->sd_kobj, &tune_group); if (error) - goto fail_args; + goto fail_reg; error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group); if (error) @@ -647,10 +540,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) fail_tune: sysfs_remove_group(&sdp->sd_kobj, &tune_group); -fail_args: - sysfs_remove_group(&sdp->sd_kobj, &args_group); -fail_lockstruct: - sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); fail_reg: kobject_put(&sdp->sd_kobj); fail: @@ -661,8 +550,6 @@ fail: void gfs2_sys_fs_del(struct gfs2_sbd *sdp) { sysfs_remove_group(&sdp->sd_kobj, &tune_group); - sysfs_remove_group(&sdp->sd_kobj, &args_group); - sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); sysfs_remove_group(&sdp->sd_kobj, &lock_module_group); kobject_put(&sdp->sd_kobj); } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 053752d4b27f..4ef0e9fa3549 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -33,6 +33,9 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, BUG_ON(current->journal_info); BUG_ON(blocks == 0 && revokes == 0); + if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + return -EROFS; + tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS); if (!tr) return -ENOMEM; @@ -54,12 +57,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, if (error) goto fail_holder_uninit; - if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { - tr->tr_t_gh.gh_flags |= GL_NOCACHE; - error = -EROFS; - goto fail_gunlock; - } - error = gfs2_log_reserve(sdp, tr->tr_reserved); if (error) goto fail_gunlock; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c1462d43e721..941c8425c10b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -30,6 +30,7 @@ #include <linux/dnotify.h> #include <linux/statfs.h> #include <linux/security.h> +#include <linux/ima.h> #include <asm/uaccess.h> @@ -986,6 +987,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag) &hugetlbfs_file_operations); if (!file) goto out_dentry; /* inode is already attached */ + ima_counts_get(file); return file; diff --git a/fs/inode.c b/fs/inode.c index 0571983755dc..bca0c618fdb3 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -219,6 +219,7 @@ static struct inode *alloc_inode(struct super_block *sb) void destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); + ima_inode_free(inode); security_inode_free(inode); if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); @@ -1053,13 +1054,22 @@ int insert_inode_locked(struct inode *inode) struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); - struct inode *old; inode->i_state |= I_LOCK|I_NEW; while (1) { + struct hlist_node *node; + struct inode *old = NULL; spin_lock(&inode_lock); - old = find_inode_fast(sb, head, ino); - if (likely(!old)) { + hlist_for_each_entry(old, node, head, i_hash) { + if (old->i_ino != ino) + continue; + if (old->i_sb != sb) + continue; + if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) + continue; + break; + } + if (likely(!node)) { hlist_add_head(&inode->i_hash, head); spin_unlock(&inode_lock); return 0; @@ -1081,14 +1091,24 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, { struct super_block *sb = inode->i_sb; struct hlist_head *head = inode_hashtable + hash(sb, hashval); - struct inode *old; inode->i_state |= I_LOCK|I_NEW; while (1) { + struct hlist_node *node; + struct inode *old = NULL; + spin_lock(&inode_lock); - old = find_inode(sb, head, test, data); - if (likely(!old)) { + hlist_for_each_entry(old, node, head, i_hash) { + if (old->i_sb != sb) + continue; + if (!test(old, data)) + continue; + if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) + continue; + break; + } + if (likely(!node)) { hlist_add_head(&inode->i_hash, head); spin_unlock(&inode_lock); return 0; diff --git a/fs/ioctl.c b/fs/ioctl.c index 82d9c42b8bac..286f38dfc6c0 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -414,10 +414,6 @@ static int file_ioctl(struct file *filp, unsigned int cmd, switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); - case FS_IOC_FIEMAP: - return ioctl_fiemap(filp, arg); - case FIGETBSZ: - return put_user(inode->i_sb->s_blocksize, p); case FIONREAD: return put_user(i_size_read(inode) - filp->f_pos, p); } @@ -557,6 +553,16 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, error = ioctl_fsthaw(filp); break; + case FS_IOC_FIEMAP: + return ioctl_fiemap(filp, arg); + + case FIGETBSZ: + { + struct inode *inode = filp->f_path.dentry->d_inode; + int __user *p = (int __user *)arg; + return put_user(inode->i_sb->s_blocksize, p); + } + default: if (S_ISREG(filp->f_path.dentry->d_inode->i_mode)) error = file_ioctl(filp, cmd, arg); diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 06560c520f49..618e21c0b7a3 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -241,7 +241,7 @@ write_out_data: spin_lock(&journal->j_list_lock); } /* Someone already cleaned up the buffer? */ - if (!buffer_jbd(bh) + if (!buffer_jbd(bh) || bh2jh(bh) != jh || jh->b_transaction != commit_transaction || jh->b_jlist != BJ_SyncData) { jbd_unlock_bh_state(bh); @@ -478,7 +478,9 @@ void journal_commit_transaction(journal_t *journal) spin_lock(&journal->j_list_lock); continue; } - if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) { + if (buffer_jbd(bh) && bh2jh(bh) == jh && + jh->b_transaction == commit_transaction && + jh->b_jlist == BJ_Locked) { __journal_unfile_buffer(jh); jbd_unlock_bh_state(bh); journal_remove_journal_head(bh); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 58144102bf25..62be7d294ec2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1781,7 +1781,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) * Journal abort has very specific semantics, which we describe * for journal abort. * - * Two internal function, which provide abort to te jbd layer + * Two internal functions, which provide abort to the jbd layer * itself are here. */ @@ -1879,7 +1879,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) * int jbd2_journal_errno () - returns the journal's error state. * @journal: journal to examine. * - * This is the errno numbet set with jbd2_journal_abort(), the last + * This is the errno number set with jbd2_journal_abort(), the last * time the journal was mounted - if the journal was stopped * without calling abort this will be 0. * @@ -1903,7 +1903,7 @@ int jbd2_journal_errno(journal_t *journal) * int jbd2_journal_clear_err () - clears the journal's error state * @journal: journal to act on. * - * An error must be cleared or Acked to take a FS out of readonly + * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) @@ -1923,7 +1923,7 @@ int jbd2_journal_clear_err(journal_t *journal) * void jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * - * An error must be cleared or Acked to take a FS out of readonly + * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 346057218edc..0fc30407f039 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2571,6 +2571,7 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) txAbort(tid, 0); txEnd(tid); + mutex_unlock(&JFS_IP(ipimap)->commit_mutex); /* release the inode map lock */ IWRITE_UNLOCK(ipimap); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 6f21adf9479a..d9b0e92b3602 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -720,8 +720,10 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) + if (len == towrite) { + mutex_unlock(&inode->i_mutex); return err; + } if (inode->i_size < off+len-towrite) i_size_write(inode, off+len-towrite); inode->i_version++; diff --git a/fs/mpage.c b/fs/mpage.c index 680ba60863ff..42381bd6543b 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -379,7 +379,8 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, struct buffer_head map_bh; unsigned long first_logical_block = 0; - clear_buffer_mapped(&map_bh); + map_bh.b_state = 0; + map_bh.b_size = 0; for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = list_entry(pages->prev, struct page, lru); @@ -412,7 +413,8 @@ int mpage_readpage(struct page *page, get_block_t get_block) struct buffer_head map_bh; unsigned long first_logical_block = 0; - clear_buffer_mapped(&map_bh); + map_bh.b_state = 0; + map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, &map_bh, &first_logical_block, get_block); if (bio) diff --git a/fs/namei.c b/fs/namei.c index 967c3db92724..c82805d088e1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -853,7 +853,8 @@ static int __link_path_walk(const char *name, struct nameidata *nd) err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC); if (!err) - err = ima_path_check(&nd->path, MAY_EXEC); + err = ima_path_check(&nd->path, MAY_EXEC, + IMA_COUNT_UPDATE); if (err) break; @@ -1515,7 +1516,8 @@ int may_open(struct path *path, int acc_mode, int flag) return error; error = ima_path_check(path, - acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC)); + acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC), + IMA_COUNT_UPDATE); if (error) return error; /* diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b660435978d2..bd584bcf1d9f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -55,6 +55,7 @@ #include <linux/security.h> #endif /* CONFIG_NFSD_V4 */ #include <linux/jhash.h> +#include <linux/ima.h> #include <asm/uaccess.h> @@ -735,6 +736,8 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, flags, cred); if (IS_ERR(*filp)) host_err = PTR_ERR(*filp); + else + ima_counts_get(*filp); out_nfserr: err = nfserrno(host_err); out: @@ -2024,6 +2027,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, struct dentry *dentry, int acc) { struct inode *inode = dentry->d_inode; + struct path path; int err; if (acc == NFSD_MAY_NOP) @@ -2096,7 +2100,17 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, if (err == -EACCES && S_ISREG(inode->i_mode) && acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE)) err = inode_permission(inode, MAY_EXEC); + if (err) + goto nfsd_out; + /* Do integrity (permission) checking now, but defer incrementing + * IMA counts to the actual file open. + */ + path.mnt = exp->ex_path.mnt; + path.dentry = dentry; + err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC), + IMA_COUNT_LEAVE); +nfsd_out: return err? nfserrno(err) : 0; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 7f65b3be4aa9..a91f15b8673c 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -515,7 +515,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data) blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size); if (sb->s_blocksize != blocksize) { - int hw_blocksize = bdev_hardsect_size(sb->s_bdev); + int hw_blocksize = bdev_logical_block_size(sb->s_bdev); if (blocksize < hw_blocksize) { printk(KERN_ERR diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index f76951dcd4a6..6aa7c4713536 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -25,7 +25,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/spinlock.h> -#include <linux/blkdev.h> /* For bdev_hardsect_size(). */ +#include <linux/blkdev.h> /* For bdev_logical_block_size(). */ #include <linux/backing-dev.h> #include <linux/buffer_head.h> #include <linux/vfs.h> @@ -2785,13 +2785,13 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto err_out_now; /* We support sector sizes up to the PAGE_CACHE_SIZE. */ - if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) { + if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) { if (!silent) ntfs_error(sb, "Device has unsupported sector size " "(%i). The maximum supported sector " "size on this architecture is %lu " "bytes.", - bdev_hardsect_size(sb->s_bdev), + bdev_logical_block_size(sb->s_bdev), PAGE_CACHE_SIZE); goto err_out_now; } diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 4f85eceab376..09cc25d04611 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1371,7 +1371,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, bdevname(reg->hr_bdev, reg->hr_dev_name); - sectsize = bdev_hardsect_size(reg->hr_bdev); + sectsize = bdev_logical_block_size(reg->hr_bdev); if (sectsize != reg->hr_block_bytes) { mlog(ML_ERROR, "blocksize %u incorrect for device, expected %d", diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 79ff8d9d37e0..5c6163f55039 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -713,7 +713,7 @@ static int ocfs2_sb_probe(struct super_block *sb, *bh = NULL; /* may be > 512 */ - *sector_size = bdev_hardsect_size(sb->s_bdev); + *sector_size = bdev_logical_block_size(sb->s_bdev); if (*sector_size > OCFS2_MAX_BLOCKSIZE) { mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n", *sector_size, OCFS2_MAX_BLOCKSIZE); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 99e33ef40be4..0af36085eb28 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -219,6 +219,13 @@ ssize_t part_size_show(struct device *dev, return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects); } +ssize_t part_alignment_offset_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset); +} + ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -272,6 +279,7 @@ ssize_t part_fail_store(struct device *dev, static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL); static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); +static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = @@ -282,6 +290,7 @@ static struct attribute *part_attrs[] = { &dev_attr_partition.attr, &dev_attr_start.attr, &dev_attr_size.attr, + &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, @@ -383,6 +392,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev = part_to_dev(p); p->start_sect = start; + p->alignment_offset = queue_sector_alignment_offset(disk->queue, start); p->nr_sects = len; p->partno = partno; p->policy = get_disk_ro(disk); diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c index 46297683cd34..fc71aab08460 100644 --- a/fs/partitions/ibm.c +++ b/fs/partitions/ibm.c @@ -76,7 +76,7 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev) Sector sect; res = 0; - blocksize = bdev_hardsect_size(bdev); + blocksize = bdev_logical_block_size(bdev); if (blocksize <= 0) goto out_exit; i_size = i_size_read(bdev->bd_inode); diff --git a/fs/partitions/msdos.c b/fs/partitions/msdos.c index 796511886f28..0028d2ef0662 100644 --- a/fs/partitions/msdos.c +++ b/fs/partitions/msdos.c @@ -110,7 +110,7 @@ parse_extended(struct parsed_partitions *state, struct block_device *bdev, Sector sect; unsigned char *data; u32 this_sector, this_size; - int sector_size = bdev_hardsect_size(bdev) / 512; + int sector_size = bdev_logical_block_size(bdev) / 512; int loopct = 0; /* number of links followed without finding a data partition */ int i; @@ -415,7 +415,7 @@ static struct { int msdos_partition(struct parsed_partitions *state, struct block_device *bdev) { - int sector_size = bdev_hardsect_size(bdev) / 512; + int sector_size = bdev_logical_block_size(bdev) / 512; Sector sect; unsigned char *data; struct partition *p; diff --git a/fs/pipe.c b/fs/pipe.c index 13414ec45b8d..f7dd21ad85a6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -302,6 +302,20 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info, return 0; } +/** + * generic_pipe_buf_release - put a reference to a &struct pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to put a reference to + * + * Description: + * This function releases a reference to @buf. + */ +void generic_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + page_cache_release(buf->page); +} + static const struct pipe_buf_operations anon_pipe_buf_ops = { .can_merge = 1, .map = generic_pipe_buf_map, diff --git a/fs/proc/base.c b/fs/proc/base.c index 3326bbf9ab95..1539e630c47d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2128,9 +2128,15 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, if (copy_from_user(page, buf, count)) goto out_free; + /* Guard against adverse ptrace interaction */ + length = mutex_lock_interruptible(&task->cred_guard_mutex); + if (length < 0) + goto out_free; + length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, (void*)page, count); + mutex_unlock(&task->cred_guard_mutex); out_free: free_page((unsigned long) page); out: diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 9bca39cf99ee..1afa4dd4cae2 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -12,20 +12,14 @@ static int loadavg_proc_show(struct seq_file *m, void *v) { - int a, b, c; - unsigned long seq; + unsigned long avnrun[3]; - do { - seq = read_seqbegin(&xtime_lock); - a = avenrun[0] + (FIXED_1/200); - b = avenrun[1] + (FIXED_1/200); - c = avenrun[2] + (FIXED_1/200); - } while (read_seqretry(&xtime_lock, seq)); + get_avenrun(avnrun, FIXED_1/200, 0); - seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n", - LOAD_INT(a), LOAD_FRAC(a), - LOAD_INT(b), LOAD_FRAC(b), - LOAD_INT(c), LOAD_FRAC(c), + seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n", + LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]), + LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]), + LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]), nr_running(), nr_threads, task_active_pid_ns(current)->last_pid); return 0; diff --git a/fs/read_write.c b/fs/read_write.c index 9d1e76bb9ee1..6c8c55dec2bc 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -805,12 +805,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, goto out; if (!(in_file->f_mode & FMODE_READ)) goto fput_in; - retval = -EINVAL; - in_inode = in_file->f_path.dentry->d_inode; - if (!in_inode) - goto fput_in; - if (!in_file->f_op || !in_file->f_op->splice_read) - goto fput_in; retval = -ESPIPE; if (!ppos) ppos = &in_file->f_pos; @@ -834,6 +828,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = -EINVAL; if (!out_file->f_op || !out_file->f_op->sendpage) goto fput_out; + in_inode = in_file->f_path.dentry->d_inode; out_inode = out_file->f_path.dentry->d_inode; retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count); if (retval < 0) diff --git a/fs/splice.c b/fs/splice.c index 666953d59a35..73766d24f97b 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -507,9 +507,131 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, return ret; } - EXPORT_SYMBOL(generic_file_splice_read); +static const struct pipe_buf_operations default_pipe_buf_ops = { + .can_merge = 0, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, + .release = generic_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + +static ssize_t kernel_readv(struct file *file, const struct iovec *vec, + unsigned long vlen, loff_t offset) +{ + mm_segment_t old_fs; + loff_t pos = offset; + ssize_t res; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos); + set_fs(old_fs); + + return res; +} + +static ssize_t kernel_write(struct file *file, const char *buf, size_t count, + loff_t pos) +{ + mm_segment_t old_fs; + ssize_t res; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = vfs_write(file, (const char __user *)buf, count, &pos); + set_fs(old_fs); + + return res; +} + +ssize_t default_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + unsigned int nr_pages; + unsigned int nr_freed; + size_t offset; + struct page *pages[PIPE_BUFFERS]; + struct partial_page partial[PIPE_BUFFERS]; + struct iovec vec[PIPE_BUFFERS]; + pgoff_t index; + ssize_t res; + size_t this_len; + int error; + int i; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .flags = flags, + .ops = &default_pipe_buf_ops, + .spd_release = spd_release_page, + }; + + index = *ppos >> PAGE_CACHE_SHIFT; + offset = *ppos & ~PAGE_CACHE_MASK; + nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) { + struct page *page; + + page = alloc_page(GFP_USER); + error = -ENOMEM; + if (!page) + goto err; + + this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset); + vec[i].iov_base = (void __user *) page_address(page); + vec[i].iov_len = this_len; + pages[i] = page; + spd.nr_pages++; + len -= this_len; + offset = 0; + } + + res = kernel_readv(in, vec, spd.nr_pages, *ppos); + if (res < 0) { + error = res; + goto err; + } + + error = 0; + if (!res) + goto err; + + nr_freed = 0; + for (i = 0; i < spd.nr_pages; i++) { + this_len = min_t(size_t, vec[i].iov_len, res); + partial[i].offset = 0; + partial[i].len = this_len; + if (!this_len) { + __free_page(pages[i]); + pages[i] = NULL; + nr_freed++; + } + res -= this_len; + } + spd.nr_pages -= nr_freed; + + res = splice_to_pipe(pipe, &spd); + if (res > 0) + *ppos += res; + + return res; + +err: + for (i = 0; i < spd.nr_pages; i++) + __free_page(pages[i]); + + return error; +} +EXPORT_SYMBOL(default_file_splice_read); + /* * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos' * using sendpage(). Return the number of bytes sent. @@ -881,6 +1003,36 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, EXPORT_SYMBOL(generic_file_splice_write); +static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) +{ + int ret; + void *data; + + ret = buf->ops->confirm(pipe, buf); + if (ret) + return ret; + + data = buf->ops->map(pipe, buf, 0); + ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos); + buf->ops->unmap(pipe, buf, data); + + return ret; +} + +static ssize_t default_file_splice_write(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, + size_t len, unsigned int flags) +{ + ssize_t ret; + + ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf); + if (ret > 0) + *ppos += ret; + + return ret; +} + /** * generic_splice_sendpage - splice data from a pipe to a socket * @pipe: pipe to splice from @@ -908,11 +1060,10 @@ EXPORT_SYMBOL(generic_splice_sendpage); static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, + loff_t *, size_t, unsigned int); int ret; - if (unlikely(!out->f_op || !out->f_op->splice_write)) - return -EINVAL; - if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; @@ -923,7 +1074,11 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, if (unlikely(ret < 0)) return ret; - return out->f_op->splice_write(pipe, out, ppos, len, flags); + splice_write = out->f_op->splice_write; + if (!splice_write) + splice_write = default_file_splice_write; + + return splice_write(pipe, out, ppos, len, flags); } /* @@ -933,11 +1088,10 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + ssize_t (*splice_read)(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); int ret; - if (unlikely(!in->f_op || !in->f_op->splice_read)) - return -EINVAL; - if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; @@ -945,7 +1099,11 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; - return in->f_op->splice_read(in, ppos, pipe, len, flags); + splice_read = in->f_op->splice_read; + if (!splice_read) + splice_read = default_file_splice_read; + + return splice_read(in, ppos, pipe, len, flags); } /** @@ -1112,6 +1270,9 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, return ret; } +static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, + struct pipe_inode_info *opipe, + size_t len, unsigned int flags); /* * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same * location, so checking ->i_pipe is not enough to verify that this is a @@ -1132,12 +1293,32 @@ static long do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags) { - struct pipe_inode_info *pipe; + struct pipe_inode_info *ipipe; + struct pipe_inode_info *opipe; loff_t offset, *off; long ret; - pipe = pipe_info(in->f_path.dentry->d_inode); - if (pipe) { + ipipe = pipe_info(in->f_path.dentry->d_inode); + opipe = pipe_info(out->f_path.dentry->d_inode); + + if (ipipe && opipe) { + if (off_in || off_out) + return -ESPIPE; + + if (!(in->f_mode & FMODE_READ)) + return -EBADF; + + if (!(out->f_mode & FMODE_WRITE)) + return -EBADF; + + /* Splicing to self would be fun, but... */ + if (ipipe == opipe) + return -EINVAL; + + return splice_pipe_to_pipe(ipipe, opipe, len, flags); + } + + if (ipipe) { if (off_in) return -ESPIPE; if (off_out) { @@ -1149,7 +1330,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, } else off = &out->f_pos; - ret = do_splice_from(pipe, out, off, len, flags); + ret = do_splice_from(ipipe, out, off, len, flags); if (off_out && copy_to_user(off_out, off, sizeof(loff_t))) ret = -EFAULT; @@ -1157,8 +1338,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, return ret; } - pipe = pipe_info(out->f_path.dentry->d_inode); - if (pipe) { + if (opipe) { if (off_out) return -ESPIPE; if (off_in) { @@ -1170,7 +1350,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, } else off = &in->f_pos; - ret = do_splice_to(in, off, pipe, len, flags); + ret = do_splice_to(in, off, opipe, len, flags); if (off_in && copy_to_user(off_in, off, sizeof(loff_t))) ret = -EFAULT; @@ -1511,7 +1691,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, * Make sure there's data to read. Wait for input if we can, otherwise * return an appropriate error. */ -static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) +static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; @@ -1549,7 +1729,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) * Make sure there's writeable room. Wait for room if we can, otherwise * return an appropriate error. */ -static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) +static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; @@ -1587,6 +1767,124 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) } /* + * Splice contents of ipipe to opipe. + */ +static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, + struct pipe_inode_info *opipe, + size_t len, unsigned int flags) +{ + struct pipe_buffer *ibuf, *obuf; + int ret = 0, nbuf; + bool input_wakeup = false; + + +retry: + ret = ipipe_prep(ipipe, flags); + if (ret) + return ret; + + ret = opipe_prep(opipe, flags); + if (ret) + return ret; + + /* + * Potential ABBA deadlock, work around it by ordering lock + * grabbing by pipe info address. Otherwise two different processes + * could deadlock (one doing tee from A -> B, the other from B -> A). + */ + pipe_double_lock(ipipe, opipe); + + do { + if (!opipe->readers) { + send_sig(SIGPIPE, current, 0); + if (!ret) + ret = -EPIPE; + break; + } + + if (!ipipe->nrbufs && !ipipe->writers) + break; + + /* + * Cannot make any progress, because either the input + * pipe is empty or the output pipe is full. + */ + if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) { + /* Already processed some buffers, break */ + if (ret) + break; + + if (flags & SPLICE_F_NONBLOCK) { + ret = -EAGAIN; + break; + } + + /* + * We raced with another reader/writer and haven't + * managed to process any buffers. A zero return + * value means EOF, so retry instead. + */ + pipe_unlock(ipipe); + pipe_unlock(opipe); + goto retry; + } + + ibuf = ipipe->bufs + ipipe->curbuf; + nbuf = (opipe->curbuf + opipe->nrbufs) % PIPE_BUFFERS; + obuf = opipe->bufs + nbuf; + + if (len >= ibuf->len) { + /* + * Simply move the whole buffer from ipipe to opipe + */ + *obuf = *ibuf; + ibuf->ops = NULL; + opipe->nrbufs++; + ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS; + ipipe->nrbufs--; + input_wakeup = true; + } else { + /* + * Get a reference to this pipe buffer, + * so we can copy the contents over. + */ + ibuf->ops->get(ipipe, ibuf); + *obuf = *ibuf; + + /* + * Don't inherit the gift flag, we need to + * prevent multiple steals of this page. + */ + obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + + obuf->len = len; + opipe->nrbufs++; + ibuf->offset += obuf->len; + ibuf->len -= obuf->len; + } + ret += obuf->len; + len -= obuf->len; + } while (len); + + pipe_unlock(ipipe); + pipe_unlock(opipe); + + /* + * If we put data in the output pipe, wakeup any potential readers. + */ + if (ret > 0) { + smp_mb(); + if (waitqueue_active(&opipe->wait)) + wake_up_interruptible(&opipe->wait); + kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN); + } + if (input_wakeup) + wakeup_pipe_writers(ipipe); + + return ret; +} + +/* * Link contents of ipipe to opipe. */ static int link_pipe(struct pipe_inode_info *ipipe, @@ -1690,9 +1988,9 @@ static long do_tee(struct file *in, struct file *out, size_t len, * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. */ - ret = link_ipipe_prep(ipipe, flags); + ret = ipipe_prep(ipipe, flags); if (!ret) { - ret = link_opipe_prep(opipe, flags); + ret = opipe_prep(opipe, flags); if (!ret) ret = link_pipe(ipipe, opipe, len, flags); } diff --git a/fs/udf/super.c b/fs/udf/super.c index 72348cc855a4..0ba44107d8f1 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1915,7 +1915,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (uopt.flags & (1 << UDF_FLAG_BLOCKSIZE_SET)) { ret = udf_load_vrs(sb, &uopt, silent, &fileset); } else { - uopt.blocksize = bdev_hardsect_size(sb->s_bdev); + uopt.blocksize = bdev_logical_block_size(sb->s_bdev); ret = udf_load_vrs(sb, &uopt, silent, &fileset); if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) { if (!silent) diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h index af6843c7ee4b..179cbd630f69 100644 --- a/fs/xfs/linux-2.6/kmem.h +++ b/fs/xfs/linux-2.6/kmem.h @@ -103,7 +103,7 @@ extern void *kmem_zone_zalloc(kmem_zone_t *, unsigned int __nocast); static inline int kmem_shake_allow(gfp_t gfp_mask) { - return (gfp_mask & __GFP_WAIT) != 0; + return ((gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)); } #endif /* __XFS_SUPPORT_KMEM_H__ */ diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index e28800a9f2b5..1418b916fc27 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1501,7 +1501,7 @@ xfs_setsize_buftarg_early( struct block_device *bdev) { return xfs_setsize_buftarg_flags(btp, - PAGE_CACHE_SIZE, bdev_hardsect_size(bdev), 0); + PAGE_CACHE_SIZE, bdev_logical_block_size(bdev), 0); } int diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index e6d839bddbf0..7465f9ee125f 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -347,13 +347,15 @@ xfs_swap_extents( error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT); -out_unlock: - xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); - xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); out: kmem_free(tempifp); return error; +out_unlock: + xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); + xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); + goto out; + out_trans_cancel: xfs_trans_cancel(tp, 0); goto out_unlock; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 8379e3bca26c..cbd451bb4848 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -160,7 +160,7 @@ xfs_growfs_data_private( nagcount = new + (nb_mod != 0); if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) { nagcount--; - nb = nagcount * mp->m_sb.sb_agblocks; + nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks; if (nb < mp->m_sb.sb_dblocks) return XFS_ERROR(EINVAL); } |