From 349457ccf2592c14bdf13b6706170ae2e94931b1 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Fri, 8 Sep 2006 14:22:21 -0700 Subject: [PATCH] Allow file systems to manually d_move() inside of ->rename() Some file systems want to manually d_move() the dentries involved in a rename. We can do this by making use of the FS_ODD_RENAME flag if we just have nfs_rename() unconditionally do the d_move(). While there, we rename the flag to be more descriptive. OCFS2 uses this to protect that part of the rename operation with a cluster lock. Signed-off-by: Mark Fasheh Cc: Trond Myklebust Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/fs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 555bc195c420..1d3e601ece73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -92,9 +92,10 @@ extern int dir_notify_enable; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */ -#define FS_ODD_RENAME 32768 /* Temporary stuff; will go away as soon - * as nfs_rename() will be cleaned up - */ +#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() + * during rename() internally. + */ + /* * These are the fs-independent mount-flags: up to 32 flags are supported */ -- cgit v1.3-8-gc7d7 From 8e18e2941c53416aa219708e7dcad21fb4bd6794 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:46 -0700 Subject: [PATCH] inode_diet: Replace inode.u.generic_ip with inode.i_private The following patches reduce the size of the VFS inode structure by 28 bytes on a UP x86. (It would be more on an x86_64 system). This is a 10% reduction in the inode size on a UP kernel that is configured in a production mode (i.e., with no spinlock or other debugging functions enabled; if you want to save memory taken up by in-core inodes, the first thing you should do is disable the debugging options; they are responsible for a huge amount of bloat in the VFS inode structure). This patch: The filesystem or device-specific pointer in the inode is inside a union, which is pretty pointless given that all 30+ users of this field have been using the void pointer. Get rid of the union and rename it to i_private, with a comment to explain who is allowed to use the void pointer. This is just a cleanup, but it allows us to reuse the union 'u' for something something where the union will actually be used. [judith@osdl.org: powerpc build fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Judith Lebzelter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- arch/powerpc/platforms/pseries/hvCall_inst.c | 2 +- arch/s390/hypfs/inode.c | 6 ++--- arch/s390/kernel/debug.c | 2 +- block/blktrace.c | 2 +- drivers/i2c/chips/tps65010.c | 2 +- drivers/infiniband/hw/ipath/ipath_fs.c | 12 ++++----- drivers/infiniband/ulp/ipoib/ipoib_fs.c | 4 +-- drivers/misc/ibmasm/ibmasmfs.c | 16 ++++++------ drivers/net/irda/vlsi_ir.h | 2 +- drivers/net/wireless/bcm43xx/bcm43xx_debugfs.c | 2 +- drivers/oprofile/oprofilefs.c | 10 ++++---- drivers/pci/hotplug/cpqphp_sysfs.c | 2 +- drivers/usb/core/devio.c | 2 +- drivers/usb/core/inode.c | 6 ++--- drivers/usb/gadget/inode.c | 6 ++--- drivers/usb/host/isp116x-hcd.c | 2 +- drivers/usb/host/uhci-debug.c | 2 +- drivers/usb/mon/mon_stat.c | 2 +- drivers/usb/mon/mon_text.c | 4 +-- fs/autofs/inode.c | 2 +- fs/autofs/symlink.c | 2 +- fs/binfmt_misc.c | 8 +++--- fs/debugfs/file.c | 4 +-- fs/debugfs/inode.c | 4 +-- fs/devpts/inode.c | 4 +-- fs/freevxfs/vxfs.h | 2 +- fs/freevxfs/vxfs_inode.c | 4 +-- fs/fuse/control.c | 6 ++--- fs/inode.c | 2 +- fs/jffs/inode-v23.c | 34 +++++++++++++------------- fs/libfs.c | 2 +- fs/ocfs2/dlmglue.c | 2 +- include/linux/fs.h | 4 +-- kernel/relay.c | 2 +- security/inode.c | 8 +++--- 36 files changed, 88 insertions(+), 90 deletions(-) (limited to 'include/linux/fs.h') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 7b4572805db9..b837f12a84ae 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -120,7 +120,7 @@ spufs_new_file(struct super_block *sb, struct dentry *dentry, ret = 0; inode->i_op = &spufs_file_iops; inode->i_fop = fops; - inode->u.generic_ip = SPUFS_I(inode)->i_ctx = get_spu_context(ctx); + inode->i_private = SPUFS_I(inode)->i_ctx = get_spu_context(ctx); d_add(dentry, inode); out: return ret; diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 641e6511cf06..446e17d162a5 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -85,7 +85,7 @@ static int hcall_inst_seq_open(struct inode *inode, struct file *file) rc = seq_open(file, &hcall_inst_seq_ops); seq = file->private_data; - seq->private = file->f_dentry->d_inode->u.generic_ip; + seq->private = file->f_dentry->d_inode->i_private; return rc; } diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index bdade5f2e325..8735024d235b 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -104,13 +104,13 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode) static void hypfs_drop_inode(struct inode *inode) { - kfree(inode->u.generic_ip); + kfree(inode->i_private); generic_delete_inode(inode); } static int hypfs_open(struct inode *inode, struct file *filp) { - char *data = filp->f_dentry->d_inode->u.generic_ip; + char *data = filp->f_dentry->d_inode->i_private; struct hypfs_sb_info *fs_info; if (filp->f_mode & FMODE_WRITE) { @@ -352,7 +352,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb, parent->d_inode->i_nlink++; } else BUG(); - inode->u.generic_ip = data; + inode->i_private = data; d_instantiate(dentry, inode); dget(dentry); return dentry; diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 7ba20922a535..43f3d0c7e132 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -603,7 +603,7 @@ debug_open(struct inode *inode, struct file *file) debug_info_t *debug_info, *debug_info_snapshot; down(&debug_lock); - debug_info = (struct debug_info*)file->f_dentry->d_inode->u.generic_ip; + debug_info = file->f_dentry->d_inode->i_private; /* find debug view */ for (i = 0; i < DEBUG_MAX_VIEWS; i++) { if (!debug_info->views[i]) diff --git a/block/blktrace.c b/block/blktrace.c index 265f7a830619..2b4ef2b89b8d 100644 --- a/block/blktrace.c +++ b/block/blktrace.c @@ -217,7 +217,7 @@ static int blk_trace_remove(request_queue_t *q) static int blk_dropped_open(struct inode *inode, struct file *filp) { - filp->private_data = inode->u.generic_ip; + filp->private_data = inode->i_private; return 0; } diff --git a/drivers/i2c/chips/tps65010.c b/drivers/i2c/chips/tps65010.c index 0be6fd6a267d..6a7578217177 100644 --- a/drivers/i2c/chips/tps65010.c +++ b/drivers/i2c/chips/tps65010.c @@ -305,7 +305,7 @@ static int dbg_show(struct seq_file *s, void *_) static int dbg_tps_open(struct inode *inode, struct file *file) { - return single_open(file, dbg_show, inode->u.generic_ip); + return single_open(file, dbg_show, inode->i_private); } static struct file_operations debug_fops = { diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index a5eb30a06a5c..055cdd089b28 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -64,7 +64,7 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->u.generic_ip = data; + inode->i_private = data; if ((mode & S_IFMT) == S_IFDIR) { inode->i_op = &simple_dir_inode_operations; inode->i_nlink++; @@ -119,7 +119,7 @@ static ssize_t atomic_counters_read(struct file *file, char __user *buf, u16 i; struct ipath_devdata *dd; - dd = file->f_dentry->d_inode->u.generic_ip; + dd = file->f_dentry->d_inode->i_private; for (i = 0; i < NUM_COUNTERS; i++) counters[i] = ipath_snap_cntr(dd, i); @@ -139,7 +139,7 @@ static ssize_t atomic_node_info_read(struct file *file, char __user *buf, struct ipath_devdata *dd; u64 guid; - dd = file->f_dentry->d_inode->u.generic_ip; + dd = file->f_dentry->d_inode->i_private; guid = be64_to_cpu(dd->ipath_guid); @@ -178,7 +178,7 @@ static ssize_t atomic_port_info_read(struct file *file, char __user *buf, u32 tmp, tmp2; struct ipath_devdata *dd; - dd = file->f_dentry->d_inode->u.generic_ip; + dd = file->f_dentry->d_inode->i_private; /* so we only initialize non-zero fields. */ memset(portinfo, 0, sizeof portinfo); @@ -325,7 +325,7 @@ static ssize_t flash_read(struct file *file, char __user *buf, goto bail; } - dd = file->f_dentry->d_inode->u.generic_ip; + dd = file->f_dentry->d_inode->i_private; if (ipath_eeprom_read(dd, pos, tmp, count)) { ipath_dev_err(dd, "failed to read from flash\n"); ret = -ENXIO; @@ -381,7 +381,7 @@ static ssize_t flash_write(struct file *file, const char __user *buf, goto bail_tmp; } - dd = file->f_dentry->d_inode->u.generic_ip; + dd = file->f_dentry->d_inode->i_private; if (ipath_eeprom_write(dd, pos, tmp, count)) { ret = -ENXIO; ipath_dev_err(dd, "failed to write to flash\n"); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c index 5dde380e8dbe..f1cb83688b31 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c @@ -141,7 +141,7 @@ static int ipoib_mcg_open(struct inode *inode, struct file *file) return ret; seq = file->private_data; - seq->private = inode->u.generic_ip; + seq->private = inode->i_private; return 0; } @@ -247,7 +247,7 @@ static int ipoib_path_open(struct inode *inode, struct file *file) return ret; seq = file->private_data; - seq->private = inode->u.generic_ip; + seq->private = inode->i_private; return 0; } diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index 4a35caff5d02..0e909b617226 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -175,7 +175,7 @@ static struct dentry *ibmasmfs_create_file (struct super_block *sb, } inode->i_fop = fops; - inode->u.generic_ip = data; + inode->i_private = data; d_add(dentry, inode); return dentry; @@ -244,7 +244,7 @@ static int command_file_open(struct inode *inode, struct file *file) { struct ibmasmfs_command_data *command_data; - if (!inode->u.generic_ip) + if (!inode->i_private) return -ENODEV; command_data = kmalloc(sizeof(struct ibmasmfs_command_data), GFP_KERNEL); @@ -252,7 +252,7 @@ static int command_file_open(struct inode *inode, struct file *file) return -ENOMEM; command_data->command = NULL; - command_data->sp = inode->u.generic_ip; + command_data->sp = inode->i_private; file->private_data = command_data; return 0; } @@ -351,10 +351,10 @@ static int event_file_open(struct inode *inode, struct file *file) struct ibmasmfs_event_data *event_data; struct service_processor *sp; - if (!inode->u.generic_ip) + if (!inode->i_private) return -ENODEV; - sp = inode->u.generic_ip; + sp = inode->i_private; event_data = kmalloc(sizeof(struct ibmasmfs_event_data), GFP_KERNEL); if (!event_data) @@ -439,14 +439,14 @@ static int r_heartbeat_file_open(struct inode *inode, struct file *file) { struct ibmasmfs_heartbeat_data *rhbeat; - if (!inode->u.generic_ip) + if (!inode->i_private) return -ENODEV; rhbeat = kmalloc(sizeof(struct ibmasmfs_heartbeat_data), GFP_KERNEL); if (!rhbeat) return -ENOMEM; - rhbeat->sp = (struct service_processor *)inode->u.generic_ip; + rhbeat->sp = inode->i_private; rhbeat->active = 0; ibmasm_init_reverse_heartbeat(rhbeat->sp, &rhbeat->heartbeat); file->private_data = rhbeat; @@ -508,7 +508,7 @@ static ssize_t r_heartbeat_file_write(struct file *file, const char __user *buf, static int remote_settings_file_open(struct inode *inode, struct file *file) { - file->private_data = inode->u.generic_ip; + file->private_data = inode->i_private; return 0; } diff --git a/drivers/net/irda/vlsi_ir.h b/drivers/net/irda/vlsi_ir.h index a82a4ba8de4f..c37f0bc4c7f9 100644 --- a/drivers/net/irda/vlsi_ir.h +++ b/drivers/net/irda/vlsi_ir.h @@ -58,7 +58,7 @@ typedef void irqreturn_t; /* PDE() introduced in 2.5.4 */ #ifdef CONFIG_PROC_FS -#define PDE(inode) ((inode)->u.generic_ip) +#define PDE(inode) ((inode)->i_private) #endif /* irda crc16 calculation exported in 2.5.42 */ diff --git a/drivers/net/wireless/bcm43xx/bcm43xx_debugfs.c b/drivers/net/wireless/bcm43xx/bcm43xx_debugfs.c index 923275ea0789..b9df06a06ea9 100644 --- a/drivers/net/wireless/bcm43xx/bcm43xx_debugfs.c +++ b/drivers/net/wireless/bcm43xx/bcm43xx_debugfs.c @@ -54,7 +54,7 @@ static ssize_t write_file_dummy(struct file *file, const char __user *buf, static int open_file_generic(struct inode *inode, struct file *file) { - file->private_data = inode->u.generic_ip; + file->private_data = inode->i_private; return 0; } diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index 71c2da277d6e..deb37354785b 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -110,8 +110,8 @@ static ssize_t ulong_write_file(struct file * file, char const __user * buf, siz static int default_open(struct inode * inode, struct file * filp) { - if (inode->u.generic_ip) - filp->private_data = inode->u.generic_ip; + if (inode->i_private) + filp->private_data = inode->i_private; return 0; } @@ -158,7 +158,7 @@ int oprofilefs_create_ulong(struct super_block * sb, struct dentry * root, if (!d) return -EFAULT; - d->d_inode->u.generic_ip = val; + d->d_inode->i_private = val; return 0; } @@ -171,7 +171,7 @@ int oprofilefs_create_ro_ulong(struct super_block * sb, struct dentry * root, if (!d) return -EFAULT; - d->d_inode->u.generic_ip = val; + d->d_inode->i_private = val; return 0; } @@ -197,7 +197,7 @@ int oprofilefs_create_ro_atomic(struct super_block * sb, struct dentry * root, if (!d) return -EFAULT; - d->d_inode->u.generic_ip = val; + d->d_inode->i_private = val; return 0; } diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c index 8b3da007e859..5bab666cd67e 100644 --- a/drivers/pci/hotplug/cpqphp_sysfs.c +++ b/drivers/pci/hotplug/cpqphp_sysfs.c @@ -140,7 +140,7 @@ struct ctrl_dbg { static int open(struct inode *inode, struct file *file) { - struct controller *ctrl = inode->u.generic_ip; + struct controller *ctrl = inode->i_private; struct ctrl_dbg *dbg; int retval = -ENOMEM; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 218621b9958e..32e03000420c 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -555,7 +555,7 @@ static int usbdev_open(struct inode *inode, struct file *file) if (imajor(inode) == USB_DEVICE_MAJOR) dev = usbdev_lookup_minor(iminor(inode)); if (!dev) - dev = inode->u.generic_ip; + dev = inode->i_private; if (!dev) { kfree(ps); goto out; diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 3182c2224ba2..482f253085e5 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -402,8 +402,8 @@ static loff_t default_file_lseek (struct file *file, loff_t offset, int orig) static int default_open (struct inode *inode, struct file *file) { - if (inode->u.generic_ip) - file->private_data = inode->u.generic_ip; + if (inode->i_private) + file->private_data = inode->i_private; return 0; } @@ -509,7 +509,7 @@ static struct dentry *fs_create_file (const char *name, mode_t mode, } else { if (dentry->d_inode) { if (data) - dentry->d_inode->u.generic_ip = data; + dentry->d_inode->i_private = data; if (fops) dentry->d_inode->i_fop = fops; dentry->d_inode->i_uid = uid; diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 3bdc5e3ba234..ffaa8c1afad8 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -844,7 +844,7 @@ fail1: static int ep_open (struct inode *inode, struct file *fd) { - struct ep_data *data = inode->u.generic_ip; + struct ep_data *data = inode->i_private; int value = -EBUSY; if (down_interruptible (&data->lock) != 0) @@ -1909,7 +1909,7 @@ fail: static int dev_open (struct inode *inode, struct file *fd) { - struct dev_data *dev = inode->u.generic_ip; + struct dev_data *dev = inode->i_private; int value = -EBUSY; if (dev->state == STATE_DEV_DISABLED) { @@ -1970,7 +1970,7 @@ gadgetfs_make_inode (struct super_block *sb, inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->u.generic_ip = data; + inode->i_private = data; inode->i_fop = fops; } return inode; diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c index 5147ed4a6662..8c6b38a0b5bb 100644 --- a/drivers/usb/host/isp116x-hcd.c +++ b/drivers/usb/host/isp116x-hcd.c @@ -1204,7 +1204,7 @@ static int isp116x_show_dbg(struct seq_file *s, void *unused) static int isp116x_open_seq(struct inode *inode, struct file *file) { - return single_open(file, isp116x_show_dbg, inode->u.generic_ip); + return single_open(file, isp116x_show_dbg, inode->i_private); } static struct file_operations isp116x_debug_fops = { diff --git a/drivers/usb/host/uhci-debug.c b/drivers/usb/host/uhci-debug.c index dc286a48cafd..d1372cb27f33 100644 --- a/drivers/usb/host/uhci-debug.c +++ b/drivers/usb/host/uhci-debug.c @@ -428,7 +428,7 @@ struct uhci_debug { static int uhci_debug_open(struct inode *inode, struct file *file) { - struct uhci_hcd *uhci = inode->u.generic_ip; + struct uhci_hcd *uhci = inode->i_private; struct uhci_debug *up; int ret = -ENOMEM; unsigned long flags; diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c index 1fe01d994a79..86ad2b381c4b 100644 --- a/drivers/usb/mon/mon_stat.c +++ b/drivers/usb/mon/mon_stat.c @@ -28,7 +28,7 @@ static int mon_stat_open(struct inode *inode, struct file *file) if ((sp = kmalloc(sizeof(struct snap), GFP_KERNEL)) == NULL) return -ENOMEM; - mbus = inode->u.generic_ip; + mbus = inode->i_private; sp->slen = snprintf(sp->str, STAT_BUF_SIZE, "nreaders %d events %u text_lost %u\n", diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c index f961a770cee2..2fd39b4fa166 100644 --- a/drivers/usb/mon/mon_text.c +++ b/drivers/usb/mon/mon_text.c @@ -238,7 +238,7 @@ static int mon_text_open(struct inode *inode, struct file *file) int rc; mutex_lock(&mon_lock); - mbus = inode->u.generic_ip; + mbus = inode->i_private; ubus = mbus->u_bus; rp = kzalloc(sizeof(struct mon_reader_text), GFP_KERNEL); @@ -401,7 +401,7 @@ static int mon_text_release(struct inode *inode, struct file *file) struct mon_event_text *ep; mutex_lock(&mon_lock); - mbus = inode->u.generic_ip; + mbus = inode->i_private; if (mbus->nreaders <= 0) { printk(KERN_ERR TAG ": consistency error on close\n"); diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c81d6b8c2828..d39d2acd9b38 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -241,7 +241,7 @@ static void autofs_read_inode(struct inode *inode) inode->i_op = &autofs_symlink_inode_operations; sl = &sbi->symlink[n]; - inode->u.generic_ip = sl; + inode->i_private = sl; inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = sl->mtime; inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; diff --git a/fs/autofs/symlink.c b/fs/autofs/symlink.c index 52e8772b066e..c74f2eb65775 100644 --- a/fs/autofs/symlink.c +++ b/fs/autofs/symlink.c @@ -15,7 +15,7 @@ /* Nothing to release.. */ static void *autofs_follow_link(struct dentry *dentry, struct nameidata *nd) { - char *s=((struct autofs_symlink *)dentry->d_inode->u.generic_ip)->data; + char *s=((struct autofs_symlink *)dentry->d_inode->i_private)->data; nd_set_link(nd, s); return NULL; } diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 34ebbc191e46..6759b9839ce8 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -517,7 +517,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_clear_inode(struct inode *inode) { - kfree(inode->u.generic_ip); + kfree(inode->i_private); } static void kill_node(Node *e) @@ -545,7 +545,7 @@ static void kill_node(Node *e) static ssize_t bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos) { - Node *e = file->f_dentry->d_inode->u.generic_ip; + Node *e = file->f_dentry->d_inode->i_private; loff_t pos = *ppos; ssize_t res; char *page; @@ -579,7 +579,7 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct dentry *root; - Node *e = file->f_dentry->d_inode->u.generic_ip; + Node *e = file->f_dentry->d_inode->i_private; int res = parse_command(buffer, count); switch (res) { @@ -646,7 +646,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, } e->dentry = dget(dentry); - inode->u.generic_ip = e; + inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index e4b430552c88..bf3901ab1744 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -32,8 +32,8 @@ static ssize_t default_write_file(struct file *file, const char __user *buf, static int default_open(struct inode *inode, struct file *file) { - if (inode->u.generic_ip) - file->private_data = inode->u.generic_ip; + if (inode->i_private) + file->private_data = inode->i_private; return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3ca268d2e5a2..717f4821ed02 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -168,7 +168,7 @@ static int debugfs_create_by_name(const char *name, mode_t mode, * directory dentry if set. If this paramater is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later - * on. The inode.u.generic_ip pointer will point to this value on + * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. @@ -209,7 +209,7 @@ struct dentry *debugfs_create_file(const char *name, mode_t mode, if (dentry->d_inode) { if (data) - dentry->d_inode->u.generic_ip = data; + dentry->d_inode->i_private = data; if (fops) dentry->d_inode->i_fop = fops; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index f7aef5bb584a..5bf06a10dddf 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -177,7 +177,7 @@ int devpts_pty_new(struct tty_struct *tty) inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|config.mode, device); - inode->u.generic_ip = tty; + inode->i_private = tty; dentry = get_node(number); if (!IS_ERR(dentry) && !dentry->d_inode) @@ -196,7 +196,7 @@ struct tty_struct *devpts_get_tty(int number) tty = NULL; if (!IS_ERR(dentry)) { if (dentry->d_inode) - tty = dentry->d_inode->u.generic_ip; + tty = dentry->d_inode->i_private; dput(dentry); } diff --git a/fs/freevxfs/vxfs.h b/fs/freevxfs/vxfs.h index d35979a58743..c8a92652612a 100644 --- a/fs/freevxfs/vxfs.h +++ b/fs/freevxfs/vxfs.h @@ -252,7 +252,7 @@ enum { * Get filesystem private data from VFS inode. */ #define VXFS_INO(ip) \ - ((struct vxfs_inode_info *)(ip)->u.generic_ip) + ((struct vxfs_inode_info *)(ip)->i_private) /* * Get filesystem private data from VFS superblock. diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ca6a39714771..32a82ed108e4 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -243,7 +243,7 @@ vxfs_iinit(struct inode *ip, struct vxfs_inode_info *vip) ip->i_blocks = vip->vii_blocks; ip->i_generation = vip->vii_gen; - ip->u.generic_ip = (void *)vip; + ip->i_private = vip; } @@ -338,5 +338,5 @@ vxfs_read_inode(struct inode *ip) void vxfs_clear_inode(struct inode *ip) { - kmem_cache_free(vxfs_inode_cachep, ip->u.generic_ip); + kmem_cache_free(vxfs_inode_cachep, ip->i_private); } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 46fe60b2da23..79ec1f23d4d2 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -23,7 +23,7 @@ static struct fuse_conn *fuse_ctl_file_conn_get(struct file *file) { struct fuse_conn *fc; mutex_lock(&fuse_mutex); - fc = file->f_dentry->d_inode->u.generic_ip; + fc = file->f_dentry->d_inode->i_private; if (fc) fc = fuse_conn_get(fc); mutex_unlock(&fuse_mutex); @@ -98,7 +98,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, inode->i_op = iop; inode->i_fop = fop; inode->i_nlink = nlink; - inode->u.generic_ip = fc; + inode->i_private = fc; d_add(dentry, inode); return dentry; } @@ -150,7 +150,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc) for (i = fc->ctl_ndents - 1; i >= 0; i--) { struct dentry *dentry = fc->ctl_dentry[i]; - dentry->d_inode->u.generic_ip = NULL; + dentry->d_inode->i_private = NULL; d_drop(dentry); dput(dentry); } diff --git a/fs/inode.c b/fs/inode.c index 0bf9f0444a96..77e254792025 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -163,7 +163,7 @@ static struct inode *alloc_inode(struct super_block *sb) bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; mapping->backing_dev_info = bdi; } - memset(&inode->u, 0, sizeof(inode->u)); + inode->i_private = 0; inode->i_mapping = mapping; } return inode; diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index b59553d28d13..7358ef87f16b 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -369,7 +369,7 @@ jffs_new_inode(const struct inode * dir, struct jffs_raw_inode *raw_inode, f = jffs_find_file(c, raw_inode->ino); - inode->u.generic_ip = (void *)f; + inode->i_private = (void *)f; insert_inode_hash(inode); return inode; @@ -442,7 +442,7 @@ jffs_rename(struct inode *old_dir, struct dentry *old_dentry, }); result = -ENOTDIR; - if (!(old_dir_f = (struct jffs_file *)old_dir->u.generic_ip)) { + if (!(old_dir_f = old_dir->i_private)) { D(printk("jffs_rename(): Old dir invalid.\n")); goto jffs_rename_end; } @@ -456,7 +456,7 @@ jffs_rename(struct inode *old_dir, struct dentry *old_dentry, /* Find the new directory. */ result = -ENOTDIR; - if (!(new_dir_f = (struct jffs_file *)new_dir->u.generic_ip)) { + if (!(new_dir_f = new_dir->i_private)) { D(printk("jffs_rename(): New dir invalid.\n")); goto jffs_rename_end; } @@ -593,7 +593,7 @@ jffs_readdir(struct file *filp, void *dirent, filldir_t filldir) } else { ddino = ((struct jffs_file *) - inode->u.generic_ip)->pino; + inode->i_private)->pino; } D3(printk("jffs_readdir(): \"..\" %u\n", ddino)); if (filldir(dirent, "..", 2, filp->f_pos, ddino, DT_DIR) < 0) { @@ -604,7 +604,7 @@ jffs_readdir(struct file *filp, void *dirent, filldir_t filldir) } filp->f_pos++; } - f = ((struct jffs_file *)inode->u.generic_ip)->children; + f = ((struct jffs_file *)inode->i_private)->children; j = 2; while(f && (f->deleted || j++ < filp->f_pos )) { @@ -668,7 +668,7 @@ jffs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) } r = -EACCES; - if (!(d = (struct jffs_file *)dir->u.generic_ip)) { + if (!(d = (struct jffs_file *)dir->i_private)) { D(printk("jffs_lookup(): No such inode! (%lu)\n", dir->i_ino)); goto jffs_lookup_end; @@ -739,7 +739,7 @@ jffs_do_readpage_nolock(struct file *file, struct page *page) unsigned long read_len; int result; struct inode *inode = (struct inode*)page->mapping->host; - struct jffs_file *f = (struct jffs_file *)inode->u.generic_ip; + struct jffs_file *f = (struct jffs_file *)inode->i_private; struct jffs_control *c = (struct jffs_control *)inode->i_sb->s_fs_info; int r; loff_t offset; @@ -828,7 +828,7 @@ jffs_mkdir(struct inode *dir, struct dentry *dentry, int mode) }); lock_kernel(); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_mkdir(): No reference to a " @@ -972,7 +972,7 @@ jffs_remove(struct inode *dir, struct dentry *dentry, int type) kfree(_name); }); - dir_f = (struct jffs_file *) dir->u.generic_ip; + dir_f = dir->i_private; c = dir_f->c; result = -ENOENT; @@ -1082,7 +1082,7 @@ jffs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev) if (!old_valid_dev(rdev)) return -EINVAL; lock_kernel(); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; c = dir_f->c; D3(printk (KERN_NOTICE "mknod(): down biglock\n")); @@ -1186,7 +1186,7 @@ jffs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) kfree(_symname); }); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_symlink(): No reference to a " "jffs_file struct in inode.\n"); @@ -1289,7 +1289,7 @@ jffs_create(struct inode *dir, struct dentry *dentry, int mode, kfree(s); }); - dir_f = (struct jffs_file *)dir->u.generic_ip; + dir_f = dir->i_private; ASSERT(if (!dir_f) { printk(KERN_ERR "jffs_create(): No reference to a " "jffs_file struct in inode.\n"); @@ -1403,9 +1403,9 @@ jffs_file_write(struct file *filp, const char *buf, size_t count, goto out_isem; } - if (!(f = (struct jffs_file *)inode->u.generic_ip)) { - D(printk("jffs_file_write(): inode->u.generic_ip = 0x%p\n", - inode->u.generic_ip)); + if (!(f = inode->i_private)) { + D(printk("jffs_file_write(): inode->i_private = 0x%p\n", + inode->i_private)); goto out_isem; } @@ -1693,7 +1693,7 @@ jffs_read_inode(struct inode *inode) mutex_unlock(&c->fmc->biglock); return; } - inode->u.generic_ip = (void *)f; + inode->i_private = f; inode->i_mode = f->mode; inode->i_nlink = f->nlink; inode->i_uid = f->uid; @@ -1748,7 +1748,7 @@ jffs_delete_inode(struct inode *inode) lock_kernel(); inode->i_size = 0; inode->i_blocks = 0; - inode->u.generic_ip = NULL; + inode->i_private = NULL; clear_inode(inode); if (inode->i_nlink == 0) { c = (struct jffs_control *) inode->i_sb->s_fs_info; diff --git a/fs/libfs.c b/fs/libfs.c index ac02ea602c3d..2751793beeaa 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -547,7 +547,7 @@ int simple_attr_open(struct inode *inode, struct file *file, attr->get = get; attr->set = set; - attr->data = inode->u.generic_ip; + attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index de887063dcfc..8801e41afe80 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2052,7 +2052,7 @@ static int ocfs2_dlm_debug_open(struct inode *inode, struct file *file) mlog_errno(ret); goto out; } - osb = (struct ocfs2_super *) inode->u.generic_ip; + osb = inode->i_private; ocfs2_get_dlm_debug(osb->osb_dlm_debug); priv->p_dlm_debug = osb->osb_dlm_debug; INIT_LIST_HEAD(&priv->p_iter_res.l_debug_list); diff --git a/include/linux/fs.h b/include/linux/fs.h index 1d3e601ece73..4f77ec9c3353 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -554,9 +554,7 @@ struct inode { atomic_t i_writecount; void *i_security; - union { - void *generic_ip; - } u; + void *i_private; /* fs or device private pointer */ #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif diff --git a/kernel/relay.c b/kernel/relay.c index 33345e73485c..85786ff2a4f9 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -669,7 +669,7 @@ EXPORT_SYMBOL_GPL(relay_flush); */ static int relay_file_open(struct inode *inode, struct file *filp) { - struct rchan_buf *buf = inode->u.generic_ip; + struct rchan_buf *buf = inode->i_private; kref_get(&buf->kref); filp->private_data = buf; diff --git a/security/inode.c b/security/inode.c index 47eb63480dac..176aacea8ca4 100644 --- a/security/inode.c +++ b/security/inode.c @@ -44,8 +44,8 @@ static ssize_t default_write_file(struct file *file, const char __user *buf, static int default_open(struct inode *inode, struct file *file) { - if (inode->u.generic_ip) - file->private_data = inode->u.generic_ip; + if (inode->i_private) + file->private_data = inode->i_private; return 0; } @@ -194,7 +194,7 @@ static int create_by_name(const char *name, mode_t mode, * directory dentry if set. If this paramater is NULL, then the * file will be created in the root of the securityfs filesystem. * @data: a pointer to something that the caller will want to get to later - * on. The inode.u.generic_ip pointer will point to this value on + * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. @@ -240,7 +240,7 @@ struct dentry *securityfs_create_file(const char *name, mode_t mode, if (fops) dentry->d_inode->i_fop = fops; if (data) - dentry->d_inode->u.generic_ip = data; + dentry->d_inode->i_private = data; } exit: return dentry; -- cgit v1.3-8-gc7d7 From 4c1541680f8d189d21dd07b053bc12996574646e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:47 -0700 Subject: [PATCH] inode-diet: Move i_pipe into a union Move the i_pipe pointer into a union that will be shared with i_bdev and i_cdev. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f77ec9c3353..ca695fc8d69c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -528,9 +528,10 @@ struct inode { #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif - /* These three should probably be a union */ struct list_head i_devices; - struct pipe_inode_info *i_pipe; + union { + struct pipe_inode_info *i_pipe; + }; struct block_device *i_bdev; struct cdev *i_cdev; int i_cindex; -- cgit v1.3-8-gc7d7 From eaf796e7ef6014f208c409b2b14fddcfaafe7e3a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:48 -0700 Subject: [PATCH] inode-diet: Move i_bdev into a union Move the i_bdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/inode.c b/fs/inode.c index 77e254792025..41b462232f7f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -254,7 +254,7 @@ void clear_inode(struct inode *inode) DQUOT_DROP(inode); if (inode->i_sb && inode->i_sb->s_op->clear_inode) inode->i_sb->s_op->clear_inode(inode); - if (inode->i_bdev) + if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (inode->i_cdev) cd_forget(inode); diff --git a/include/linux/fs.h b/include/linux/fs.h index ca695fc8d69c..98ff684a5b1c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -531,8 +531,8 @@ struct inode { struct list_head i_devices; union { struct pipe_inode_info *i_pipe; + struct block_device *i_bdev; }; - struct block_device *i_bdev; struct cdev *i_cdev; int i_cindex; -- cgit v1.3-8-gc7d7 From 577c4eb09d1034d0739e3135fd2cff50588024be Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Move i_cdev into a union Move the i_cdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file_table.c | 2 +- fs/inode.c | 2 +- include/linux/fs.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/file_table.c b/fs/file_table.c index 0131ba06e1ee..bc35a40417d7 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -169,7 +169,7 @@ void fastcall __fput(struct file *file) if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); - if (unlikely(inode->i_cdev != NULL)) + if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); if (file->f_mode & FMODE_WRITE) diff --git a/fs/inode.c b/fs/inode.c index 41b462232f7f..f5c04dd9ae8a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -256,7 +256,7 @@ void clear_inode(struct inode *inode) inode->i_sb->s_op->clear_inode(inode); if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); - if (inode->i_cdev) + if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); inode->i_state = I_CLEAR; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 98ff684a5b1c..192e69bb55b5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -532,8 +532,8 @@ struct inode { union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; + struct cdev *i_cdev; }; - struct cdev *i_cdev; int i_cindex; __u32 i_generation; -- cgit v1.3-8-gc7d7 From ba52de123d454b57369f291348266d86f4b35070 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Eliminate i_blksize from the inode structure This eliminates the i_blksize field from struct inode. Filesystems that want to provide a per-inode st_blksize can do so by providing their own getattr routine instead of using the generic_fillattr() function. Note that some filesystems were providing pretty much random (and incorrect) values for i_blksize. [bunk@stusta.de: cleanup] [akpm@osdl.org: generic_fillattr() fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/cell/spufs/inode.c | 1 - arch/s390/hypfs/inode.c | 1 - drivers/block/loop.c | 7 +++++-- drivers/infiniband/hw/ipath/ipath_fs.c | 1 - drivers/isdn/capi/capifs.c | 2 -- drivers/misc/ibmasm/ibmasmfs.c | 1 - drivers/oprofile/oprofilefs.c | 1 - drivers/usb/core/inode.c | 1 - drivers/usb/gadget/inode.c | 1 - fs/9p/vfs_inode.c | 4 +--- fs/adfs/inode.c | 1 - fs/afs/inode.c | 1 - fs/autofs/inode.c | 1 - fs/autofs4/inode.c | 1 - fs/befs/linuxvfs.c | 1 - fs/bfs/dir.c | 2 +- fs/bfs/inode.c | 1 - fs/binfmt_misc.c | 1 - fs/cifs/cifsfs.c | 1 - fs/cifs/readdir.c | 5 ++--- fs/coda/coda_linux.c | 2 -- fs/configfs/inode.c | 1 - fs/cramfs/inode.c | 1 - fs/debugfs/inode.c | 1 - fs/devpts/inode.c | 2 -- fs/eventpoll.c | 1 - fs/ext2/ialloc.c | 1 - fs/ext2/inode.c | 1 - fs/ext3/ialloc.c | 1 - fs/ext3/inode.c | 3 --- fs/fat/inode.c | 3 --- fs/freevxfs/vxfs_inode.c | 1 - fs/fuse/inode.c | 1 - fs/hfs/inode.c | 2 -- fs/hfsplus/inode.c | 2 -- fs/hostfs/hostfs_kern.c | 1 - fs/hpfs/inode.c | 1 - fs/hppfs/hppfs_kern.c | 1 - fs/hugetlbfs/inode.c | 1 - fs/isofs/inode.c | 3 +-- fs/jffs/inode-v23.c | 2 -- fs/jffs2/fs.c | 2 -- fs/jfs/jfs_extent.c | 2 +- fs/jfs/jfs_imap.c | 1 - fs/jfs/jfs_inode.c | 1 - fs/jfs/jfs_metapage.c | 2 +- fs/libfs.c | 2 -- fs/minix/bitmap.c | 2 +- fs/minix/inode.c | 4 ++-- fs/ncpfs/inode.c | 1 - fs/nfs/inode.c | 4 ---- fs/ntfs/inode.c | 4 ---- fs/ntfs/mft.c | 5 ----- fs/ocfs2/dlm/dlmfs.c | 2 -- fs/ocfs2/inode.c | 4 ---- fs/pipe.c | 1 - fs/qnx4/inode.c | 1 - fs/ramfs/inode.c | 1 - fs/reiserfs/inode.c | 4 ---- fs/smbfs/inode.c | 2 -- fs/smbfs/proc.c | 1 - fs/stat.c | 3 ++- fs/sysfs/inode.c | 1 - fs/sysv/ialloc.c | 2 +- fs/sysv/inode.c | 2 +- fs/udf/ialloc.c | 1 - fs/udf/inode.c | 2 -- fs/ufs/ialloc.c | 1 - fs/ufs/inode.c | 1 - fs/xfs/linux-2.6/xfs_super.c | 1 - fs/xfs/linux-2.6/xfs_vnode.c | 1 - include/linux/fs.h | 1 - include/linux/nfsd/nfsfh.h | 10 ++-------- include/linux/smb.h | 1 - ipc/mqueue.c | 1 - kernel/cpuset.c | 1 - mm/shmem.c | 1 - net/sunrpc/rpc_pipe.c | 1 - security/inode.c | 1 - security/selinux/selinuxfs.c | 1 - 80 files changed, 21 insertions(+), 125 deletions(-) (limited to 'include/linux/fs.h') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index b837f12a84ae..3950ddccb2c8 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -82,7 +82,6 @@ spufs_new_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; out: diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 8735024d235b..813fc21358f9 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -91,7 +91,6 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode) ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; - ret->i_blksize = PAGE_CACHE_SIZE; ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; if (mode & S_IFDIR) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 7b3b94ddddcc..c774121684d7 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -662,7 +662,8 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; - lo->lo_blocksize = mapping->host->i_blksize; + lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ? + mapping->host->i_bdev->bd_block_size : PAGE_SIZE; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); complete(&p->wait); @@ -794,7 +795,9 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write) lo_flags |= LO_FLAGS_READ_ONLY; - lo_blocksize = inode->i_blksize; + lo_blocksize = S_ISBLK(inode->i_mode) ? + inode->i_bdev->bd_block_size : PAGE_SIZE; + error = 0; } else { goto out_putf; diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index 055cdd089b28..c8a8af0fe471 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -61,7 +61,6 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_private = data; diff --git a/drivers/isdn/capi/capifs.c b/drivers/isdn/capi/capifs.c index 9ea6bd0ddc35..2dd1b57b0ba4 100644 --- a/drivers/isdn/capi/capifs.c +++ b/drivers/isdn/capi/capifs.c @@ -104,7 +104,6 @@ capifs_fill_super(struct super_block *s, void *data, int silent) inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_blocks = 0; - inode->i_blksize = 1024; inode->i_uid = inode->i_gid = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; @@ -149,7 +148,6 @@ void capifs_new_ncci(unsigned int number, dev_t device) if (!inode) return; inode->i_ino = number+2; - inode->i_blksize = 1024; inode->i_uid = config.setuid ? config.uid : current->fsuid; inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index 0e909b617226..b99dc507de2e 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -147,7 +147,6 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode) if (ret) { ret->i_mode = mode; ret->i_uid = ret->i_gid = 0; - ret->i_blksize = PAGE_CACHE_SIZE; ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index deb37354785b..5756401fb15b 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -31,7 +31,6 @@ static struct inode * oprofilefs_get_inode(struct super_block * sb, int mode) inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 482f253085e5..58b4b1012120 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -249,7 +249,6 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index ffaa8c1afad8..2a7162d89799 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -1966,7 +1966,6 @@ gadgetfs_make_inode (struct super_block *sb, inode->i_mode = mode; inode->i_uid = default_uid; inode->i_gid = default_gid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index eae50c9d6dc4..7a7ec2d1d2f4 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -204,7 +204,6 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = 0; inode->i_rdev = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -950,9 +949,8 @@ v9fs_stat2inode(struct v9fs_stat *stat, struct inode *inode, inode->i_size = stat->length; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = - (inode->i_size + inode->i_blksize - 1) >> sb->s_blocksize_bits; + (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } /** diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 534f3eecc985..7e7a04be1278 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -269,7 +269,6 @@ adfs_iget(struct super_block *sb, struct object_info *obj) inode->i_ino = obj->file_id; inode->i_size = obj->size; inode->i_nlink = 2; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 4ebb30a50ed5..6f37754906c2 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -72,7 +72,6 @@ static int afs_inode_map_status(struct afs_vnode *vnode) inode->i_ctime.tv_sec = vnode->status.mtime_server; inode->i_ctime.tv_nsec = 0; inode->i_atime = inode->i_mtime = inode->i_ctime; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_version = vnode->fid.unique; inode->i_mapping->a_ops = &afs_fs_aops; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index d39d2acd9b38..2c9759baad61 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -216,7 +216,6 @@ static void autofs_read_inode(struct inode *inode) inode->i_nlink = 2; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_blocks = 0; - inode->i_blksize = 1024; if ( ino == AUTOFS_ROOT_INO ) { inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 11a6a9ae51b7..800ce876caec 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -447,7 +447,6 @@ struct inode *autofs4_get_inode(struct super_block *sb, inode->i_uid = 0; inode->i_gid = 0; } - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index f6676fbe9484..57020c7a7e65 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -365,7 +365,6 @@ befs_read_inode(struct inode *inode) inode->i_mtime.tv_nsec = 0; /* lower 16 bits are not a time */ inode->i_ctime = inode->i_mtime; inode->i_atime = inode->i_mtime; - inode->i_blksize = befs_sb->block_size; befs_ino->i_inode_num = fsrun_to_cpu(sb, raw_inode->inode_num); befs_ino->i_parent = fsrun_to_cpu(sb, raw_inode->parent); diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 26fad9621738..dcf04cb13283 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -102,7 +102,7 @@ static int bfs_create(struct inode * dir, struct dentry * dentry, int mode, inode->i_uid = current->fsuid; inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 8fc2e8e49dbe..ed27ffb3459e 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -76,7 +76,6 @@ static void bfs_read_inode(struct inode * inode) inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); if (inode->i_size || inode->i_blocks) dprintf("Registered inode with %lld size, %ld blocks\n", inode->i_size, inode->i_blocks); - inode->i_blksize = PAGE_SIZE; inode->i_atime.tv_sec = le32_to_cpu(di->i_atime); inode->i_mtime.tv_sec = le32_to_cpu(di->i_mtime); inode->i_ctime.tv_sec = le32_to_cpu(di->i_ctime); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 6759b9839ce8..66ba137f8661 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -507,7 +507,6 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 4197a5043f13..22bcf4d7e7ae 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -253,7 +253,6 @@ cifs_alloc_inode(struct super_block *sb) file data or metadata */ cifs_inode->clientCanCacheRead = FALSE; cifs_inode->clientCanCacheAll = FALSE; - cifs_inode->vfs_inode.i_blksize = CIFS_MAX_MSGSIZE; cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ cifs_inode->vfs_inode.i_flags = S_NOATIME | S_NOCMTIME; INIT_LIST_HEAD(&cifs_inode->openFileList); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 9aeb58a7d369..b27b34537bf2 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -216,10 +216,9 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, if (allocation_size < end_of_file) cFYI(1, ("May be sparse file, allocation less than file size")); - cFYI(1, ("File Size %ld and blocks %llu and blocksize %ld", + cFYI(1, ("File Size %ld and blocks %llu", (unsigned long)tmp_inode->i_size, - (unsigned long long)tmp_inode->i_blocks, - tmp_inode->i_blksize)); + (unsigned long long)tmp_inode->i_blocks)); if (S_ISREG(tmp_inode->i_mode)) { cFYI(1, ("File inode")); tmp_inode->i_op = &cifs_file_inode_ops; diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index 5597080cb811..95a54253c047 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -110,8 +110,6 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) inode->i_nlink = attr->va_nlink; if (attr->va_size != -1) inode->i_size = attr->va_size; - if (attr->va_blocksize != -1) - inode->i_blksize = attr->va_blocksize; if (attr->va_size != -1) inode->i_blocks = (attr->va_size + 511) >> 9; if (attr->va_atime.tv_sec != -1) diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 5047e6a7581e..fb18917954a9 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -135,7 +135,6 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d09b6777c41a..ad96b6990715 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -73,7 +73,6 @@ static int cramfs_iget5_set(struct inode *inode, void *opaque) inode->i_uid = cramfs_inode->uid; inode->i_size = cramfs_inode->size; inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_gid = cramfs_inode->gid; /* Struct copy intentional */ inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 717f4821ed02..269e649e6dc6 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -40,7 +40,6 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 5bf06a10dddf..5f7b5a6025bf 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -113,7 +113,6 @@ devpts_fill_super(struct super_block *s, void *data, int silent) inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_blocks = 0; - inode->i_blksize = 1024; inode->i_uid = inode->i_gid = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; @@ -172,7 +171,6 @@ int devpts_pty_new(struct tty_struct *tty) return -ENOMEM; inode->i_ino = number+2; - inode->i_blksize = 1024; inode->i_uid = config.setuid ? config.uid : current->fsuid; inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3a3567433b92..8d544334bcd2 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1590,7 +1590,6 @@ static struct inode *ep_eventpoll_inode(void) inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_blksize = PAGE_SIZE; return inode; eexit_1: diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 695f69ccf908..2cb545bf0f3c 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -574,7 +574,6 @@ got: inode->i_mode = mode; inode->i_ino = ino; - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; memset(ei->i_data, 0, sizeof(ei->i_data)); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index fb4d3220eb8d..dd4e14c221e0 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1094,7 +1094,6 @@ void ext2_read_inode (struct inode * inode) brelse (bh); goto bad_inode; } - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 1e4ded8aa3cd..e45dbd651736 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -559,7 +559,6 @@ got: inode->i_ino = ino; /* This is the optimal IO size (for stat), not the fs block size */ - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index c9fc15f8b609..dcf4f1dd108b 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2632,9 +2632,6 @@ void ext3_read_inode(struct inode * inode) * recovery code: that's fine, we're about to complete * the process of deleting those. */ } - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size - * (for stat), not the fs block - * size */ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); #ifdef EXT3_FRAGMENTS diff --git a/fs/fat/inode.c b/fs/fat/inode.c index e1035a590664..ab96ae823753 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -370,8 +370,6 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) inode->i_flags |= S_IMMUTABLE; } MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED; - /* this is as close to the truth as we can get ... */ - inode->i_blksize = sbi->cluster_size; inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; inode->i_mtime.tv_sec = @@ -1131,7 +1129,6 @@ static int fat_read_root(struct inode *inode) MSDOS_I(inode)->i_start = 0; inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); } - inode->i_blksize = sbi->cluster_size; inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; MSDOS_I(inode)->i_logstart = 0; diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 32a82ed108e4..4786d51ad3bd 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -239,7 +239,6 @@ vxfs_iinit(struct inode *ip, struct vxfs_inode_info *vip) ip->i_ctime.tv_nsec = 0; ip->i_mtime.tv_nsec = 0; - ip->i_blksize = PAGE_SIZE; ip->i_blocks = vip->vii_blocks; ip->i_generation = vip->vii_gen; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 7d25092262ae..cb7cadb0b790 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -118,7 +118,6 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) inode->i_uid = attr->uid; inode->i_gid = attr->gid; i_size_write(inode, attr->size); - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 315cf44a90b2..d05641c35fc9 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -154,7 +154,6 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode) inode->i_gid = current->fsgid; inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blksize = HFS_SB(sb)->alloc_blksz; HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; HFS_I(inode)->fs_blocks = 0; @@ -284,7 +283,6 @@ static int hfs_read_inode(struct inode *inode, void *data) inode->i_uid = hsb->s_uid; inode->i_gid = hsb->s_gid; inode->i_nlink = 1; - inode->i_blksize = HFS_SB(inode->i_sb)->alloc_blksz; if (idata->key) HFS_I(inode)->cat_key = *idata->key; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 924ecdef8091..0eb1a6092668 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -304,7 +304,6 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode) inode->i_gid = current->fsgid; inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blksize = HFSPLUS_SB(sb).alloc_blksz; INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list); init_MUTEX(&HFSPLUS_I(inode).extents_lock); atomic_set(&HFSPLUS_I(inode).opencnt, 0); @@ -407,7 +406,6 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) type = hfs_bnode_read_u16(fd->bnode, fd->entryoffset); HFSPLUS_I(inode).dev = 0; - inode->i_blksize = HFSPLUS_SB(inode->i_sb).alloc_blksz; if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index b82e3d9c8790..322e876c35ed 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -156,7 +156,6 @@ static int read_name(struct inode *ino, char *name) ino->i_mode = i_mode; ino->i_nlink = i_nlink; ino->i_size = i_size; - ino->i_blksize = i_blksize; ino->i_blocks = i_blocks; return(0); } diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 56f2c338c4d9..bcf6ee36e065 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -17,7 +17,6 @@ void hpfs_init_inode(struct inode *i) i->i_gid = hpfs_sb(sb)->sb_gid; i->i_mode = hpfs_sb(sb)->sb_mode; hpfs_inode->i_conv = hpfs_sb(sb)->sb_conv; - i->i_blksize = 512; i->i_size = -1; i->i_blocks = -1; diff --git a/fs/hppfs/hppfs_kern.c b/fs/hppfs/hppfs_kern.c index 3a9bdf58166f..dcb6d2e988b8 100644 --- a/fs/hppfs/hppfs_kern.c +++ b/fs/hppfs/hppfs_kern.c @@ -152,7 +152,6 @@ static void hppfs_read_inode(struct inode *ino) ino->i_mode = proc_ino->i_mode; ino->i_nlink = proc_ino->i_nlink; ino->i_size = proc_ino->i_size; - ino->i_blksize = proc_ino->i_blksize; ino->i_blocks = proc_ino->i_blocks; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c3920c96dadf..e025a31b4c64 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -357,7 +357,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; - inode->i_blksize = HPAGE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 10e47897bac7..4527692f432b 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1235,7 +1235,7 @@ static void isofs_read_inode(struct inode *inode) } inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; ei->i_format_parm[0] = 0; ei->i_format_parm[1] = 0; @@ -1291,7 +1291,6 @@ static void isofs_read_inode(struct inode *inode) isonum_711 (de->ext_attr_length)); /* Set the number of blocks for stat() - should be done before RR */ - inode->i_blksize = PAGE_CACHE_SIZE; /* For stat() only */ inode->i_blocks = (inode->i_size + 511) >> 9; /* diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index 7358ef87f16b..f5cf9c93e243 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -364,7 +364,6 @@ jffs_new_inode(const struct inode * dir, struct jffs_raw_inode *raw_inode, inode->i_ctime.tv_nsec = 0; inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; f = jffs_find_file(c, raw_inode->ino); @@ -1706,7 +1705,6 @@ jffs_read_inode(struct inode *inode) inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; if (S_ISREG(inode->i_mode)) { inode->i_op = &jffs_file_inode_operations; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 4780f82825d6..72d9909d95ff 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -263,7 +263,6 @@ void jffs2_read_inode (struct inode *inode) inode->i_nlink = f->inocache->nlink; - inode->i_blksize = PAGE_SIZE; inode->i_blocks = (inode->i_size + 511) >> 9; switch (inode->i_mode & S_IFMT) { @@ -449,7 +448,6 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i inode->i_atime = inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; ri->atime = ri->mtime = ri->ctime = cpu_to_je32(I_SEC(inode->i_mtime)); - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; inode->i_size = 0; diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 4d52593a5fc6..4c74f0944f7e 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -468,7 +468,7 @@ int extRecord(struct inode *ip, xad_t * xp) int extFill(struct inode *ip, xad_t * xp) { int rc, nbperpage = JFS_SBI(ip->i_sb)->nbperpage; - s64 blkno = offsetXAD(xp) >> ip->i_blksize; + s64 blkno = offsetXAD(xp) >> ip->i_blkbits; // assert(ISSPARSE(ip)); diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index ccbe60aff83d..369d7f39c040 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -3115,7 +3115,6 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip) ip->i_mtime.tv_nsec = le32_to_cpu(dip->di_mtime.tv_nsec); ip->i_ctime.tv_sec = le32_to_cpu(dip->di_ctime.tv_sec); ip->i_ctime.tv_nsec = le32_to_cpu(dip->di_ctime.tv_nsec); - ip->i_blksize = ip->i_sb->s_blocksize; ip->i_blocks = LBLK2PBLK(ip->i_sb, le64_to_cpu(dip->di_nblocks)); ip->i_generation = le32_to_cpu(dip->di_gen); diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 495df402916d..bffaca9ae3a2 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -115,7 +115,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode) } jfs_inode->mode2 |= mode; - inode->i_blksize = sb->s_blocksize; inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; jfs_inode->otime = inode->i_ctime.tv_sec; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index e1e0a6e6ebdf..f5afc129d6b1 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -257,7 +257,7 @@ static sector_t metapage_get_blocks(struct inode *inode, sector_t lblock, int rc = 0; int xflag; s64 xaddr; - sector_t file_blocks = (inode->i_size + inode->i_blksize - 1) >> + sector_t file_blocks = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_blkbits; if (lblock >= file_blocks) diff --git a/fs/libfs.c b/fs/libfs.c index 2751793beeaa..8db5afb7b0a7 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -383,7 +383,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files return -ENOMEM; inode->i_mode = S_IFDIR | 0755; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_op = &simple_dir_inode_operations; @@ -405,7 +404,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files goto out; inode->i_mode = S_IFREG | files->mode; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_fop = files->ops; diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 4a6abc49418e..df6b1075b549 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -254,7 +254,7 @@ struct inode * minix_new_inode(const struct inode * dir, int * error) inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; inode->i_ino = j; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; memset(&minix_i(inode)->u, 0, sizeof(minix_i(inode)->u)); insert_inode_hash(inode); mark_inode_dirty(inode); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 826b9d830650..c11a4b9fb863 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -396,7 +396,7 @@ static void V1_minix_read_inode(struct inode * inode) inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_ctime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; for (i = 0; i < 9; i++) minix_inode->u.i1_data[i] = raw_inode->i_zone[i]; minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0])); @@ -429,7 +429,7 @@ static void V2_minix_read_inode(struct inode * inode) inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_ctime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; for (i = 0; i < 10; i++) minix_inode->u.i2_data[i] = raw_inode->i_zone[i]; minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0])); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 8244710e97dd..42e3bef270c9 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -223,7 +223,6 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) inode->i_nlink = 1; inode->i_uid = server->m.uid; inode->i_gid = server->m.gid; - inode->i_blksize = NCP_BLOCK_SIZE; ncp_update_dates(inode, &nwinfo->i); ncp_update_inode(inode, nwinfo); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 931f52a19579..bc9376ca86cd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -277,10 +277,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - inode->i_blksize = inode->i_sb->s_blocksize; } else { inode->i_blocks = fattr->du.nfs2.blocks; - inode->i_blksize = fattr->du.nfs2.blocksize; } nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; @@ -969,10 +967,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - inode->i_blksize = inode->i_sb->s_blocksize; } else { inode->i_blocks = fattr->du.nfs2.blocks; - inode->i_blksize = fattr->du.nfs2.blocksize; } if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 31852121b3f5..933dbd89c2a4 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -556,8 +556,6 @@ static int ntfs_read_locked_inode(struct inode *vi) /* Setup the generic vfs inode parts now. */ - /* This is the optimal IO size (for stat), not the fs block size. */ - vi->i_blksize = PAGE_CACHE_SIZE; /* * This is for checking whether an inode has changed w.r.t. a file so * that the file can be updated if necessary (compare with f_version). @@ -1234,7 +1232,6 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; @@ -1504,7 +1501,6 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) ni = NTFS_I(vi); base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 578fb3d5e803..584260fd6848 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -2637,11 +2637,6 @@ mft_rec_already_initialized: goto undo_mftbmp_alloc; } vi->i_ino = bit; - /* - * This is the optimal IO size (for stat), not the fs block - * size. - */ - vi->i_blksize = PAGE_CACHE_SIZE; /* * This is for checking whether an inode has changed w.r.t. a * file so that the file can be updated if necessary (compare diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 0ff0898a0b9c..0368c6402182 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -335,7 +335,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -362,7 +361,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 69d3db569166..16e8e74dc966 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -269,7 +269,6 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, inode->i_mode = le16_to_cpu(fe->i_mode); inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); - inode->i_blksize = (u32)osb->s_clustersize; /* Fast symlinks will have i_size but no allocated clusters. */ if (S_ISLNK(inode->i_mode) && !fe->i_clusters) @@ -1258,8 +1257,6 @@ leave: void ocfs2_refresh_inode(struct inode *inode, struct ocfs2_dinode *fe) { - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - spin_lock(&OCFS2_I(inode)->ip_lock); OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); @@ -1270,7 +1267,6 @@ void ocfs2_refresh_inode(struct inode *inode, inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); inode->i_mode = le16_to_cpu(fe->i_mode); - inode->i_blksize = (u32) osb->s_clustersize; if (S_ISLNK(inode->i_mode) && le32_to_cpu(fe->i_clusters) == 0) inode->i_blocks = 0; else diff --git a/fs/pipe.c b/fs/pipe.c index 20352573e025..f3b6f71e9d0b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -879,7 +879,6 @@ static struct inode * get_pipe_inode(void) inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_blksize = PAGE_SIZE; return inode; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index fddbd61c68d0..5a41db2a218d 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -496,7 +496,6 @@ static void qnx4_read_inode(struct inode *inode) inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->di_ctime); inode->i_ctime.tv_nsec = 0; inode->i_blocks = le32_to_cpu(raw_inode->di_first_xtnt.xtnt_size); - inode->i_blksize = QNX4_DIR_ENTRY_SIZE; memcpy(qnx4_inode, raw_inode, QNX4_DIR_ENTRY_SIZE); if (S_ISREG(inode->i_mode)) { diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index b9677335cc8d..bc0e51662424 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -58,7 +58,6 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 52f1e2136546..8810fda0da46 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -17,8 +17,6 @@ #include #include -extern int reiserfs_default_io_size; /* default io size devuned in super.c */ - static int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); static int reiserfs_prepare_write(struct file *f, struct page *page, @@ -1122,7 +1120,6 @@ static void init_inode(struct inode *inode, struct path *path) ih = PATH_PITEM_HEAD(path); copy_key(INODE_PKEY(inode), &(ih->ih_key)); - inode->i_blksize = reiserfs_default_io_size; INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list)); REISERFS_I(inode)->i_flags = 0; @@ -1877,7 +1874,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, } // these do not go to on-disk stat data inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid); - inode->i_blksize = reiserfs_default_io_size; // store in in-core inode the key of stat data and version all // object items will have (directory items will have old offset diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 92cf60aa6121..2c122ee83adb 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -166,7 +166,6 @@ smb_get_inode_attr(struct inode *inode, struct smb_fattr *fattr) fattr->f_mtime = inode->i_mtime; fattr->f_ctime = inode->i_ctime; fattr->f_atime = inode->i_atime; - fattr->f_blksize= inode->i_blksize; fattr->f_blocks = inode->i_blocks; fattr->attr = SMB_I(inode)->attr; @@ -200,7 +199,6 @@ smb_set_inode_attr(struct inode *inode, struct smb_fattr *fattr) inode->i_uid = fattr->f_uid; inode->i_gid = fattr->f_gid; inode->i_ctime = fattr->f_ctime; - inode->i_blksize= fattr->f_blksize; inode->i_blocks = fattr->f_blocks; inode->i_size = fattr->f_size; inode->i_mtime = fattr->f_mtime; diff --git a/fs/smbfs/proc.c b/fs/smbfs/proc.c index c3495059889d..40e174db9872 100644 --- a/fs/smbfs/proc.c +++ b/fs/smbfs/proc.c @@ -1826,7 +1826,6 @@ smb_init_dirent(struct smb_sb_info *server, struct smb_fattr *fattr) fattr->f_nlink = 1; fattr->f_uid = server->mnt->uid; fattr->f_gid = server->mnt->gid; - fattr->f_blksize = SMB_ST_BLKSIZE; fattr->f_unix = 0; } diff --git a/fs/stat.c b/fs/stat.c index 3a44dcf97da2..60a31d5e5966 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -32,7 +33,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->ctime = inode->i_ctime; stat->size = i_size_read(inode); stat->blocks = inode->i_blocks; - stat->blksize = inode->i_blksize; + stat->blksize = (1 << inode->i_blkbits); } EXPORT_SYMBOL(generic_fillattr); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index fd7cd5f843d2..e79e38d52c00 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -125,7 +125,6 @@ struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent * sd) { struct inode * inode = new_inode(sysfs_sb); if (inode) { - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &sysfs_aops; inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 9b585d1081c0..115ab0d6f4bc 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -170,7 +170,7 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode) inode->i_uid = current->fsuid; inode->i_ino = fs16_to_cpu(sbi, ino); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; memset(SYSV_I(inode)->i_data, 0, sizeof(SYSV_I(inode)->i_data)); SYSV_I(inode)->i_dir_start_lookup = 0; insert_inode_hash(inode); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 58b2d22142ba..d63c5e48b050 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -201,7 +201,7 @@ static void sysv_read_inode(struct inode *inode) inode->i_ctime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_mtime.tv_nsec = 0; - inode->i_blocks = inode->i_blksize = 0; + inode->i_blocks = 0; si = SYSV_I(inode); for (block = 0; block < 10+1+1+1; block++) diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index d1d38238ce65..8206983f2ebf 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -121,7 +121,6 @@ struct inode * udf_new_inode (struct inode *dir, int mode, int * err) UDF_I_LOCATION(inode).logicalBlockNum = block; UDF_I_LOCATION(inode).partitionReferenceNum = UDF_I_LOCATION(dir).partitionReferenceNum; inode->i_ino = udf_get_lb_pblock(sb, UDF_I_LOCATION(inode), 0); - inode->i_blksize = PAGE_SIZE; inode->i_blocks = 0; UDF_I_LENEATTR(inode) = 0; UDF_I_LENALLOC(inode) = 0; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 605f5111b6d8..b223b32db991 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -916,8 +916,6 @@ __udf_read_inode(struct inode *inode) * i_nlink = 1 * i_op = NULL; */ - inode->i_blksize = PAGE_SIZE; - bh = udf_read_ptagged(inode->i_sb, UDF_I_LOCATION(inode), 0, &ident); if (!bh) diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 9501dcd3b213..2ad1259c6eca 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -255,7 +255,6 @@ cg_found: inode->i_gid = current->fsgid; inode->i_ino = cg * uspi->s_ipg + bit; - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; ufsi->i_flags = UFS_I(dir)->i_flags; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 30c6e8a9446c..ee1eaa6f4ec2 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -741,7 +741,6 @@ void ufs_read_inode(struct inode * inode) ufs1_read_inode(inode, ufs_inode + ufs_inotofsbo(inode->i_ino)); } - inode->i_blksize = PAGE_SIZE;/*This is the optimal IO size (for stat)*/ inode->i_version++; ufsi->i_lastfrag = (inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 4754f342a5d3..9df9ed37d219 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -171,7 +171,6 @@ xfs_revalidate_inode( break; } - inode->i_blksize = xfs_preferred_iosize(mp); inode->i_generation = ip->i_d.di_gen; i_size_write(inode, ip->i_d.di_size); inode->i_blocks = diff --git a/fs/xfs/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c index 6628d96b6fd6..553fa731ade5 100644 --- a/fs/xfs/linux-2.6/xfs_vnode.c +++ b/fs/xfs/linux-2.6/xfs_vnode.c @@ -122,7 +122,6 @@ vn_revalidate_core( inode->i_blocks = vap->va_nblocks; inode->i_mtime = vap->va_mtime; inode->i_ctime = vap->va_ctime; - inode->i_blksize = vap->va_blocksize; if (vap->va_xflags & XFS_XFLAG_IMMUTABLE) inode->i_flags |= S_IMMUTABLE; else diff --git a/include/linux/fs.h b/include/linux/fs.h index 192e69bb55b5..8f74dfbb2edd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -512,7 +512,6 @@ struct inode { struct timespec i_mtime; struct timespec i_ctime; unsigned int i_blkbits; - unsigned long i_blksize; unsigned long i_version; blkcnt_t i_blocks; unsigned short i_bytes; diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index f9edcd2ff3c8..31a3cb617ce0 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -269,14 +269,8 @@ fill_post_wcc(struct svc_fh *fhp) fhp->fh_post_uid = inode->i_uid; fhp->fh_post_gid = inode->i_gid; fhp->fh_post_size = inode->i_size; - if (inode->i_blksize) { - fhp->fh_post_blksize = inode->i_blksize; - fhp->fh_post_blocks = inode->i_blocks; - } else { - fhp->fh_post_blksize = BLOCK_SIZE; - /* how much do we care for accuracy with MinixFS? */ - fhp->fh_post_blocks = (inode->i_size+511) >> 9; - } + fhp->fh_post_blksize = BLOCK_SIZE; + fhp->fh_post_blocks = inode->i_blocks; fhp->fh_post_rdev[0] = htonl((u32)imajor(inode)); fhp->fh_post_rdev[1] = htonl((u32)iminor(inode)); fhp->fh_post_atime = inode->i_atime; diff --git a/include/linux/smb.h b/include/linux/smb.h index 6df3b1501559..f098dff93f6b 100644 --- a/include/linux/smb.h +++ b/include/linux/smb.h @@ -89,7 +89,6 @@ struct smb_fattr { struct timespec f_atime; struct timespec f_mtime; struct timespec f_ctime; - unsigned long f_blksize; unsigned long f_blocks; int f_unix; }; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index f8381f0660b2..840f8a6fb85f 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -115,7 +115,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index cff41511269f..1b32c2c04c15 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -289,7 +289,6 @@ static struct inode *cpuset_new_inode(mode_t mode) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info; diff --git a/mm/shmem.c b/mm/shmem.c index 0a8e29cf87e0..eda907c3a86a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1351,7 +1351,6 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_mapping->a_ops = &shmem_aops; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index f65bea74734d..700c6e061a04 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -488,7 +488,6 @@ rpc_get_inode(struct super_block *sb, int mode) return NULL; inode->i_mode = mode; inode->i_uid = inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch(mode & S_IFMT) { diff --git a/security/inode.c b/security/inode.c index 176aacea8ca4..49ee51529396 100644 --- a/security/inode.c +++ b/security/inode.c @@ -64,7 +64,6 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 00534c302ba2..bab7b386cb8d 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -771,7 +771,6 @@ static struct inode *sel_make_inode(struct super_block *sb, int mode) if (ret) { ret->i_mode = mode; ret->i_uid = ret->i_gid = 0; - ret->i_blksize = PAGE_CACHE_SIZE; ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } -- cgit v1.3-8-gc7d7 From 0e51a720b9d9ea5ebf0fda39108919c6626bffa3 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 01:59:56 -0700 Subject: [PATCH] ifdef ->quota_read, ->quota_write All suppliers of ->quota_read, ->quota_write (I've found ext2, ext3, UFS, reiserfs) already have them properly ifdeffed. All callers of ->quota_read, ->quota_write are under CONFIG_QUOTA umbrella, so... Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8f74dfbb2edd..4caec6cebc42 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1143,9 +1143,10 @@ struct super_operations { int (*show_options)(struct seq_file *, struct vfsmount *); int (*show_stats)(struct seq_file *, struct vfsmount *); - +#ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); +#endif }; /* Inode state bits. Protected by inode_lock. */ -- cgit v1.3-8-gc7d7 From 50462062a02226a698a211d5bd535376c89b8603 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 02:00:01 -0700 Subject: [PATCH] fs.h: ifdef security fields [assuming BSD security levels are deleted] The only user of i_security, f_security, s_security fields is SELinux, however, quite a few security modules are trying to get into kernel. So, wrap them under CONFIG_SECURITY. Adding config option for each security field is likely an overkill. Following Stephen Smalley's suggestion, i_security initialization is moved to security_inode_alloc() to not clutter core code with ifdefs and make alloc_inode() codepath tiny little bit smaller and faster. The user of (highly greppable) struct fown_struct::security field is still to be found. I've checked every "fown_struct" and every "f_owner" occurence. Additionally it's removal doesn't break i386 allmodconfig build. struct inode, struct file, struct super_block, struct fown_struct become smaller. P.S. Combined with two reiserfs inode shrinking patches sent to linux-fsdevel, I can finally suck 12 reiserfs inodes into one page. /proc/slabinfo -ext2_inode_cache 388 10 +ext2_inode_cache 384 10 -inode_cache 280 14 +inode_cache 276 14 -proc_inode_cache 296 13 +proc_inode_cache 292 13 -reiser_inode_cache 336 11 +reiser_inode_cache 332 12 <= -shmem_inode_cache 372 10 +shmem_inode_cache 368 10 Signed-off-by: Alexey Dobriyan Cc: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 1 - include/linux/fs.h | 8 ++++++-- include/linux/security.h | 1 + 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/inode.c b/fs/inode.c index f5c04dd9ae8a..abf77471e6c4 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -133,7 +133,6 @@ static struct inode *alloc_inode(struct super_block *sb) inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_rdev = 0; - inode->i_security = NULL; inode->dirtied_when = 0; if (security_inode_alloc(inode)) { if (inode->i_sb->s_op->destroy_inode) diff --git a/include/linux/fs.h b/include/linux/fs.h index 4caec6cebc42..6eafbe309483 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -553,7 +553,9 @@ struct inode { unsigned int i_flags; atomic_t i_writecount; +#ifdef CONFIG_SECURITY void *i_security; +#endif void *i_private; /* fs or device private pointer */ #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; @@ -645,7 +647,6 @@ struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ int pid; /* pid or -pgrp where SIGIO should be sent */ uid_t uid, euid; /* uid/euid of process setting the owner */ - void *security; int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -688,8 +689,9 @@ struct file { struct file_ra_state f_ra; unsigned long f_version; +#ifdef CONFIG_SECURITY void *f_security; - +#endif /* needed for tty driver, and maybe others */ void *private_data; @@ -877,7 +879,9 @@ struct super_block { int s_syncing; int s_need_sync_fs; atomic_t s_active; +#ifdef CONFIG_SECURITY void *s_security; +#endif struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ diff --git a/include/linux/security.h b/include/linux/security.h index 9f56fb8a4a6c..9b5fea81f55e 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1595,6 +1595,7 @@ static inline void security_sb_post_pivotroot (struct nameidata *old_nd, static inline int security_inode_alloc (struct inode *inode) { + inode->i_security = NULL; return security_ops->inode_alloc_security (inode); } -- cgit v1.3-8-gc7d7 From a3b05e8f58c95dfccbf2c824d0c68e5990571f24 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:36:46 +0200 Subject: [PATCH] Kill various deprecated/unused block layer defines/functions Signed-off-by: Jens Axboe --- drivers/block/cciss.c | 1 - drivers/block/cpqarray.c | 1 - include/linux/blkdev.h | 29 ----------------------------- include/linux/fs.h | 1 - 4 files changed, 32 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 2cd3391ff878..c211065ad829 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1229,7 +1229,6 @@ static inline void complete_buffers(struct bio *bio, int status) int nr_sectors = bio_sectors(bio); bio->bi_next = NULL; - blk_finished_io(len); bio_endio(bio, nr_sectors << 9, status ? 0 : -EIO); bio = xbh; } diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index 78082edc14b4..4abc193314ee 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -989,7 +989,6 @@ static inline void complete_buffers(struct bio *bio, int ok) xbh = bio->bi_next; bio->bi_next = NULL; - blk_finished_io(nr_sectors); bio_endio(bio, nr_sectors << 9, ok ? 0 : -EIO); bio = xbh; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79cb9fa8034a..593386162f47 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -578,12 +578,6 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq))) -/* - * noop, requests are automagically marked as active/inactive by I/O - * scheduler -- see elv_next_request - */ -#define blk_queue_headactive(q, head_active) - /* * q->prep_rq_fn return values */ @@ -621,11 +615,6 @@ static inline void blk_queue_bounce(request_queue_t *q, struct bio **bio) if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) -struct sec_size { - unsigned block_size; - unsigned block_size_bits; -}; - extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern void register_disk(struct gendisk *dev); @@ -690,16 +679,6 @@ extern void end_that_request_last(struct request *, int); extern void end_request(struct request *req, int uptodate); extern void blk_complete_request(struct request *); -static inline int rq_all_done(struct request *rq, unsigned int nr_bytes) -{ - if (blk_fs_request(rq)) - return (nr_bytes >= (rq->hard_nr_sectors << 9)); - else if (blk_pc_request(rq)) - return nr_bytes >= rq->data_len; - - return 0; -} - /* * end_that_request_first/chunk() takes an uptodate argument. we account * any value <= as an io error. 0 means -EIO for compatability reasons, @@ -807,14 +786,6 @@ static inline int queue_dma_alignment(request_queue_t *q) return retval; } -static inline int bdev_dma_aligment(struct block_device *bdev) -{ - return queue_dma_alignment(bdev_get_queue(bdev)); -} - -#define blk_finished_io(nsects) do { } while (0) -#define blk_started_io(nsects) do { } while (0) - /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 6eafbe309483..9306f63bf77e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,7 +79,6 @@ extern int dir_notify_enable; #define WRITE 1 #define READA 2 /* read-ahead - don't block if no resources */ #define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ -#define SPECIAL 4 /* For non-blockdevice requests in request queue */ #define READ_SYNC (READ | (1 << BIO_RW_SYNC)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC)) #define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER)) -- cgit v1.3-8-gc7d7 From 5404bc7a87b9949cf61e0174b21f80e73239ab25 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2006 09:01:02 +0200 Subject: [PATCH] Allow file systems to differentiate between data and meta reads We can use this information for making more intelligent priority decisions, and it will also be useful for blktrace. Signed-off-by: Jens Axboe --- block/ll_rw_blk.c | 2 ++ include/linux/bio.h | 2 ++ include/linux/blkdev.h | 3 +++ include/linux/fs.h | 1 + 4 files changed, 8 insertions(+) (limited to 'include/linux/fs.h') diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c index e3980ec747c1..57992ae511c2 100644 --- a/block/ll_rw_blk.c +++ b/block/ll_rw_blk.c @@ -2884,6 +2884,8 @@ static void init_request_from_bio(struct request *req, struct bio *bio) if (bio_sync(bio)) req->cmd_flags |= REQ_RW_SYNC; + if (bio_rw_meta(bio)) + req->cmd_flags |= REQ_RW_META; req->errors = 0; req->hard_sector = req->sector = bio->bi_sector; diff --git a/include/linux/bio.h b/include/linux/bio.h index 76bdaeab6f62..711c321a7011 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -148,6 +148,7 @@ struct bio { #define BIO_RW_BARRIER 2 #define BIO_RW_FAILFAST 3 #define BIO_RW_SYNC 4 +#define BIO_RW_META 5 /* * upper 16 bits of bi_rw define the io priority of this bio @@ -178,6 +179,7 @@ struct bio { #define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC)) #define bio_failfast(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST)) #define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD)) +#define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META)) /* * will die diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d8e288db163..2c01a90998a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -180,6 +180,7 @@ enum rq_flag_bits { __REQ_ORDERED_COLOR, /* is before or after barrier */ __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_RW_META, /* metadata io request */ __REQ_NR_BITS, /* stops here */ }; @@ -200,6 +201,7 @@ enum rq_flag_bits { #define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) #define REQ_RW_SYNC (1 << __REQ_RW_SYNC) #define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_RW_META (1 << __REQ_RW_META) #define BLK_MAX_CDB 16 @@ -543,6 +545,7 @@ enum { * We regard a request as sync, if it's a READ or a SYNC write. */ #define rq_is_sync(rq) (rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC) +#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) static inline int blk_queue_full(struct request_queue *q, int rw) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 9306f63bf77e..d68c37af4dfb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -80,6 +80,7 @@ extern int dir_notify_enable; #define READA 2 /* read-ahead - don't block if no resources */ #define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ #define READ_SYNC (READ | (1 << BIO_RW_SYNC)) +#define READ_META (READ | (1 << BIO_RW_META)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC)) #define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER)) -- cgit v1.3-8-gc7d7 From cf9a2ae8d49948f861b56e5333530e491a9da190 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:05:54 +0100 Subject: [PATCH] BLOCK: Move functions out of buffer code [try #6] Move some functions out of the buffering code that aren't strictly buffering specific. This is a precursor to being able to disable the block layer. (*) Moved some stuff out of fs/buffer.c: (*) The file sync and general sync stuff moved to fs/sync.c. (*) The superblock sync stuff moved to fs/super.c. (*) do_invalidatepage() moved to mm/truncate.c. (*) try_to_release_page() moved to mm/filemap.c. (*) Moved some related declarations between header files: (*) declarations for do_invalidatepage() and try_to_release_page() moved to linux/mm.h. (*) __set_page_dirty_buffers() moved to linux/buffer_head.h. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- fs/buffer.c | 174 -------------------------------------------- fs/super.c | 31 ++++++++ fs/sync.c | 113 ++++++++++++++++++++++++++++ include/linux/buffer_head.h | 3 +- include/linux/fs.h | 1 + include/linux/mm.h | 4 +- mm/filemap.c | 30 ++++++++ mm/page-writeback.c | 1 + mm/truncate.c | 24 ++++++ 9 files changed, 204 insertions(+), 177 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/buffer.c b/fs/buffer.c index 3b6d701073e7..16cfbcd254f1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -159,31 +159,6 @@ int sync_blockdev(struct block_device *bdev) } EXPORT_SYMBOL(sync_blockdev); -static void __fsync_super(struct super_block *sb) -{ - sync_inodes_sb(sb, 0); - DQUOT_SYNC(sb); - lock_super(sb); - if (sb->s_dirt && sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); - sync_inodes_sb(sb, 1); -} - -/* - * Write out and wait upon all dirty data associated with this - * superblock. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_super(struct super_block *sb) -{ - __fsync_super(sb); - return sync_blockdev(sb->s_bdev); -} - /* * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block @@ -259,118 +234,6 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) } EXPORT_SYMBOL(thaw_bdev); -/* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. - */ -static void do_sync(unsigned long wait) -{ - wakeup_pdflush(0); - sync_inodes(0); /* All mappings, inodes and their blockdevs */ - DQUOT_SYNC(NULL); - sync_supers(); /* Write the superblocks */ - sync_filesystems(0); /* Start syncing the filesystems */ - sync_filesystems(wait); /* Waitingly sync the filesystems */ - sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ - if (!wait) - printk("Emergency Sync complete\n"); - if (unlikely(laptop_mode)) - laptop_sync_completion(); -} - -asmlinkage long sys_sync(void) -{ - do_sync(1); - return 0; -} - -void emergency_sync(void) -{ - pdflush_operation(do_sync, 0); -} - -/* - * Generic function to fsync a file. - * - * filp may be NULL if called via the msync of a vma. - */ - -int file_fsync(struct file *filp, struct dentry *dentry, int datasync) -{ - struct inode * inode = dentry->d_inode; - struct super_block * sb; - int ret, err; - - /* sync the inode to buffers */ - ret = write_inode_now(inode, 0); - - /* sync the superblock to buffers */ - sb = inode->i_sb; - lock_super(sb); - if (sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - - /* .. finally sync the buffers to disk */ - err = sync_blockdev(sb->s_bdev); - if (!ret) - ret = err; - return ret; -} - -long do_fsync(struct file *file, int datasync) -{ - int ret; - int err; - struct address_space *mapping = file->f_mapping; - - if (!file->f_op || !file->f_op->fsync) { - /* Why? We can still call filemap_fdatawrite */ - ret = -EINVAL; - goto out; - } - - ret = filemap_fdatawrite(mapping); - - /* - * We need to protect against concurrent writers, which could cause - * livelocks in fsync_buffers_list(). - */ - mutex_lock(&mapping->host->i_mutex); - err = file->f_op->fsync(file, file->f_dentry, datasync); - if (!ret) - ret = err; - mutex_unlock(&mapping->host->i_mutex); - err = filemap_fdatawait(mapping); - if (!ret) - ret = err; -out: - return ret; -} - -static long __do_fsync(unsigned int fd, int datasync) -{ - struct file *file; - int ret = -EBADF; - - file = fget(fd); - if (file) { - ret = do_fsync(file, datasync); - fput(file); - } - return ret; -} - -asmlinkage long sys_fsync(unsigned int fd) -{ - return __do_fsync(fd, 0); -} - -asmlinkage long sys_fdatasync(unsigned int fd) -{ - return __do_fsync(fd, 1); -} - /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, @@ -1550,35 +1413,6 @@ static void discard_buffer(struct buffer_head * bh) unlock_buffer(bh); } -/** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) - * - * The address_space is to try to release any data against the page - * (presumably at page->private). If the release was successful, return `1'. - * Otherwise return zero. - * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). - * - * NOTE: @gfp_mask may go away, and this function may become non-blocking. - */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) -{ - struct address_space * const mapping = page->mapping; - - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; - - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); -} -EXPORT_SYMBOL(try_to_release_page); - /** * block_invalidatepage - invalidate part of all of a buffer-backed page * @@ -1630,14 +1464,6 @@ out: } EXPORT_SYMBOL(block_invalidatepage); -void do_invalidatepage(struct page *page, unsigned long offset) -{ - void (*invalidatepage)(struct page *, unsigned long); - invalidatepage = page->mapping->a_ops->invalidatepage ? : - block_invalidatepage; - (*invalidatepage)(page, offset); -} - /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers diff --git a/fs/super.c b/fs/super.c index 6987824d0dce..15671cd048b1 100644 --- a/fs/super.c +++ b/fs/super.c @@ -220,6 +220,37 @@ static int grab_super(struct super_block *s) __releases(sb_lock) return 0; } +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. Requires a second blkdev + * flush by the caller to complete the operation. + */ +void __fsync_super(struct super_block *sb) +{ + sync_inodes_sb(sb, 0); + DQUOT_SYNC(sb); + lock_super(sb); + if (sb->s_dirt && sb->s_op->write_super) + sb->s_op->write_super(sb); + unlock_super(sb); + if (sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, 1); + sync_blockdev(sb->s_bdev); + sync_inodes_sb(sb, 1); +} + +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. + */ +int fsync_super(struct super_block *sb) +{ + __fsync_super(sb); + return sync_blockdev(sb->s_bdev); +} + /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill diff --git a/fs/sync.c b/fs/sync.c index 955aef04da28..1de747b5ddb9 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -10,10 +10,123 @@ #include #include #include +#include +#include #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER) +/* + * sync everything. Start out by waking pdflush, because that writes back + * all queues in parallel. + */ +static void do_sync(unsigned long wait) +{ + wakeup_pdflush(0); + sync_inodes(0); /* All mappings, inodes and their blockdevs */ + DQUOT_SYNC(NULL); + sync_supers(); /* Write the superblocks */ + sync_filesystems(0); /* Start syncing the filesystems */ + sync_filesystems(wait); /* Waitingly sync the filesystems */ + sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ + if (!wait) + printk("Emergency Sync complete\n"); + if (unlikely(laptop_mode)) + laptop_sync_completion(); +} + +asmlinkage long sys_sync(void) +{ + do_sync(1); + return 0; +} + +void emergency_sync(void) +{ + pdflush_operation(do_sync, 0); +} + +/* + * Generic function to fsync a file. + * + * filp may be NULL if called via the msync of a vma. + */ +int file_fsync(struct file *filp, struct dentry *dentry, int datasync) +{ + struct inode * inode = dentry->d_inode; + struct super_block * sb; + int ret, err; + + /* sync the inode to buffers */ + ret = write_inode_now(inode, 0); + + /* sync the superblock to buffers */ + sb = inode->i_sb; + lock_super(sb); + if (sb->s_op->write_super) + sb->s_op->write_super(sb); + unlock_super(sb); + + /* .. finally sync the buffers to disk */ + err = sync_blockdev(sb->s_bdev); + if (!ret) + ret = err; + return ret; +} + +long do_fsync(struct file *file, int datasync) +{ + int ret; + int err; + struct address_space *mapping = file->f_mapping; + + if (!file->f_op || !file->f_op->fsync) { + /* Why? We can still call filemap_fdatawrite */ + ret = -EINVAL; + goto out; + } + + ret = filemap_fdatawrite(mapping); + + /* + * We need to protect against concurrent writers, which could cause + * livelocks in fsync_buffers_list(). + */ + mutex_lock(&mapping->host->i_mutex); + err = file->f_op->fsync(file, file->f_dentry, datasync); + if (!ret) + ret = err; + mutex_unlock(&mapping->host->i_mutex); + err = filemap_fdatawait(mapping); + if (!ret) + ret = err; +out: + return ret; +} + +static long __do_fsync(unsigned int fd, int datasync) +{ + struct file *file; + int ret = -EBADF; + + file = fget(fd); + if (file) { + ret = do_fsync(file, datasync); + fput(file); + } + return ret; +} + +asmlinkage long sys_fsync(unsigned int fd) +{ + return __do_fsync(fd, 0); +} + +asmlinkage long sys_fdatasync(unsigned int fd) +{ + return __do_fsync(fd, 1); +} + /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 737e407d0cd1..64b508e35d2a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -190,9 +190,7 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -int try_to_release_page(struct page * page, gfp_t gfp_mask); void block_invalidatepage(struct page *page, unsigned long offset); -void do_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); @@ -302,4 +300,5 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } +extern int __set_page_dirty_buffers(struct page *page); #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index d68c37af4dfb..1728142ec4b6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1546,6 +1546,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); +extern void __fsync_super(struct super_block *sb); extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b703b6d4358..4edf1934e5ca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -743,7 +743,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); -int __set_page_dirty_buffers(struct page *page); +extern int try_to_release_page(struct page * page, gfp_t gfp_mask); +extern void do_invalidatepage(struct page *page, unsigned long offset); + int __set_page_dirty_nobuffers(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); diff --git a/mm/filemap.c b/mm/filemap.c index 3277f3b23524..d6846de08887 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2491,3 +2491,33 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, } return retval; } + +/** + * try_to_release_page() - release old fs-specific metadata on a page + * + * @page: the page which the kernel is trying to free + * @gfp_mask: memory allocation flags (and I/O mode) + * + * The address_space is to try to release any data against the page + * (presumably at page->private). If the release was successful, return `1'. + * Otherwise return zero. + * + * The @gfp_mask argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). + * + * NOTE: @gfp_mask may go away, and this function may become non-blocking. + */ +int try_to_release_page(struct page *page, gfp_t gfp_mask) +{ + struct address_space * const mapping = page->mapping; + + BUG_ON(!PageLocked(page)); + if (PageWriteback(page)) + return 0; + + if (mapping && mapping->a_ops->releasepage) + return mapping->a_ops->releasepage(page, gfp_mask); + return try_to_free_buffers(page); +} + +EXPORT_SYMBOL(try_to_release_page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 488b7088557c..9fdcc7903956 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * The maximum number of pages to writeout in a single bdflush/kupdate diff --git a/mm/truncate.c b/mm/truncate.c index a654928323dc..cd3e34b816db 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -17,6 +17,30 @@ do_invalidatepage */ +/** + * do_invalidatepage - invalidate part of all of a page + * @page: the page which is affected + * @offset: the index of the truncation point + * + * do_invalidatepage() is called when all or part of the page has become + * invalidated by a truncate operation. + * + * do_invalidatepage() does not have to release all buffers, but it must + * ensure that no dirty buffer is left outside @offset and that no I/O + * is underway against any of the blocks which are outside the truncation + * point. Because the caller is about to free (and possibly reuse) those + * blocks on-disk. + */ +void do_invalidatepage(struct page *page, unsigned long offset) +{ + void (*invalidatepage)(struct page *, unsigned long); + invalidatepage = page->mapping->a_ops->invalidatepage; + if (!invalidatepage) + invalidatepage = block_invalidatepage; + if (invalidatepage) + (*invalidatepage)(page, offset); +} + static inline void truncate_partial_page(struct page *page, unsigned partial) { memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial); -- cgit v1.3-8-gc7d7 From 36695673b012096228ebdc1b39a6a5850daa474e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:16 +0100 Subject: [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6] Move common FS-specific ioctls from linux/ext2_fs.h to linux/fs.h as FS_IOC_* and FS_IOC32_* and have the users of them use those as a base. Also move the GETFLAGS/SETFLAGS flags to linux/fs.h as FS_*_FL macros, and then have the other users use them as a base. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- fs/cifs/ioctl.c | 7 +++-- fs/compat_ioctl.c | 15 ----------- fs/hfsplus/hfsplus_fs.h | 8 ++---- fs/hfsplus/ioctl.c | 17 ++++++------ fs/jfs/ioctl.c | 15 +++++------ include/linux/ext2_fs.h | 64 +++++++++++++++++++++++++-------------------- include/linux/ext3_fs.h | 20 +++++++++++--- include/linux/fs.h | 39 +++++++++++++++++++++++++++ include/linux/reiserfs_fs.h | 28 +++++++++----------- 9 files changed, 124 insertions(+), 89 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index b0ea6687ab55..e34c7db00f6f 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -22,7 +22,6 @@ */ #include -#include #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" @@ -74,7 +73,7 @@ int cifs_ioctl (struct inode * inode, struct file * filep, } break; #ifdef CONFIG_CIFS_POSIX - case EXT2_IOC_GETFLAGS: + case FS_IOC_GETFLAGS: if(CIFS_UNIX_EXTATTR_CAP & caps) { if (pSMBFile == NULL) break; @@ -82,12 +81,12 @@ int cifs_ioctl (struct inode * inode, struct file * filep, &ExtAttrBits, &ExtAttrMask); if(rc == 0) rc = put_user(ExtAttrBits & - EXT2_FL_USER_VISIBLE, + FS_FL_USER_VISIBLE, (int __user *)arg); } break; - case EXT2_IOC_SETFLAGS: + case FS_IOC_SETFLAGS: if(CIFS_UNIX_EXTATTR_CAP & caps) { if(get_user(ExtAttrBits,(int __user *)arg)) { rc = -EFAULT; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 3b0cf7fbd95a..bd9c4f49d4e5 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -123,21 +123,6 @@ #include #include -/* Aiee. Someone does not find a difference between int and long */ -#define EXT2_IOC32_GETFLAGS _IOR('f', 1, int) -#define EXT2_IOC32_SETFLAGS _IOW('f', 2, int) -#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) -#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) -#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) -#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) -#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) -#ifdef CONFIG_JBD_DEBUG -#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) -#endif - -#define EXT2_IOC32_GETVERSION _IOR('v', 1, int) -#define EXT2_IOC32_SETVERSION _IOW('v', 2, int) - static int do_ioctl32_pointer(unsigned int fd, unsigned int cmd, unsigned long arg, struct file *f) { diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 8a1ca5ef7ada..3915635b4470 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -246,12 +246,8 @@ struct hfsplus_readdir_data { /* ext2 ioctls (EXT2_IOC_GETFLAGS and EXT2_IOC_SETFLAGS) to support * chattr/lsattr */ -#define HFSPLUS_IOC_EXT2_GETFLAGS _IOR('f', 1, long) -#define HFSPLUS_IOC_EXT2_SETFLAGS _IOW('f', 2, long) - -#define EXT2_FLAG_IMMUTABLE 0x00000010 /* Immutable file */ -#define EXT2_FLAG_APPEND 0x00000020 /* writes to file may only append */ -#define EXT2_FLAG_NODUMP 0x00000040 /* do not dump file */ +#define HFSPLUS_IOC_EXT2_GETFLAGS FS_IOC_GETFLAGS +#define HFSPLUS_IOC_EXT2_SETFLAGS FS_IOC_SETFLAGS /* diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 13cf848ac833..79fd10402ea3 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -28,11 +28,11 @@ int hfsplus_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, case HFSPLUS_IOC_EXT2_GETFLAGS: flags = 0; if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_IMMUTABLE) - flags |= EXT2_FLAG_IMMUTABLE; /* EXT2_IMMUTABLE_FL */ + flags |= FS_IMMUTABLE_FL; /* EXT2_IMMUTABLE_FL */ if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_APPEND) - flags |= EXT2_FLAG_APPEND; /* EXT2_APPEND_FL */ + flags |= FS_APPEND_FL; /* EXT2_APPEND_FL */ if (HFSPLUS_I(inode).userflags & HFSPLUS_FLG_NODUMP) - flags |= EXT2_FLAG_NODUMP; /* EXT2_NODUMP_FL */ + flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */ return put_user(flags, (int __user *)arg); case HFSPLUS_IOC_EXT2_SETFLAGS: { if (IS_RDONLY(inode)) @@ -44,32 +44,31 @@ int hfsplus_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, if (get_user(flags, (int __user *)arg)) return -EFAULT; - if (flags & (EXT2_FLAG_IMMUTABLE|EXT2_FLAG_APPEND) || + if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) || HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) { if (!capable(CAP_LINUX_IMMUTABLE)) return -EPERM; } /* don't silently ignore unsupported ext2 flags */ - if (flags & ~(EXT2_FLAG_IMMUTABLE|EXT2_FLAG_APPEND| - EXT2_FLAG_NODUMP)) + if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) return -EOPNOTSUPP; - if (flags & EXT2_FLAG_IMMUTABLE) { /* EXT2_IMMUTABLE_FL */ + if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */ inode->i_flags |= S_IMMUTABLE; HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE; } else { inode->i_flags &= ~S_IMMUTABLE; HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_IMMUTABLE; } - if (flags & EXT2_FLAG_APPEND) { /* EXT2_APPEND_FL */ + if (flags & FS_APPEND_FL) { /* EXT2_APPEND_FL */ inode->i_flags |= S_APPEND; HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_APPEND; } else { inode->i_flags &= ~S_APPEND; HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_APPEND; } - if (flags & EXT2_FLAG_NODUMP) /* EXT2_NODUMP_FL */ + if (flags & FS_NODUMP_FL) /* EXT2_NODUMP_FL */ HFSPLUS_I(inode).userflags |= HFSPLUS_FLG_NODUMP; else HFSPLUS_I(inode).userflags &= ~HFSPLUS_FLG_NODUMP; diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 67b3774820eb..37db52488262 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -6,7 +6,6 @@ */ #include -#include #include #include #include @@ -22,13 +21,13 @@ static struct { long jfs_flag; long ext2_flag; } jfs_map[] = { - {JFS_NOATIME_FL, EXT2_NOATIME_FL}, - {JFS_DIRSYNC_FL, EXT2_DIRSYNC_FL}, - {JFS_SYNC_FL, EXT2_SYNC_FL}, - {JFS_SECRM_FL, EXT2_SECRM_FL}, - {JFS_UNRM_FL, EXT2_UNRM_FL}, - {JFS_APPEND_FL, EXT2_APPEND_FL}, - {JFS_IMMUTABLE_FL, EXT2_IMMUTABLE_FL}, + {JFS_NOATIME_FL, FS_NOATIME_FL}, + {JFS_DIRSYNC_FL, FS_DIRSYNC_FL}, + {JFS_SYNC_FL, FS_SYNC_FL}, + {JFS_SECRM_FL, FS_SECRM_FL}, + {JFS_UNRM_FL, FS_UNRM_FL}, + {JFS_APPEND_FL, FS_APPEND_FL}, + {JFS_IMMUTABLE_FL, FS_IMMUTABLE_FL}, {0, 0}, }; diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 33a1aa107329..153d755376a4 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -165,41 +165,49 @@ struct ext2_group_desc #define EXT2_N_BLOCKS (EXT2_TIND_BLOCK + 1) /* - * Inode flags + * Inode flags (GETFLAGS/SETFLAGS) */ -#define EXT2_SECRM_FL 0x00000001 /* Secure deletion */ -#define EXT2_UNRM_FL 0x00000002 /* Undelete */ -#define EXT2_COMPR_FL 0x00000004 /* Compress file */ -#define EXT2_SYNC_FL 0x00000008 /* Synchronous updates */ -#define EXT2_IMMUTABLE_FL 0x00000010 /* Immutable file */ -#define EXT2_APPEND_FL 0x00000020 /* writes to file may only append */ -#define EXT2_NODUMP_FL 0x00000040 /* do not dump file */ -#define EXT2_NOATIME_FL 0x00000080 /* do not update atime */ +#define EXT2_SECRM_FL FS_SECRM_FL /* Secure deletion */ +#define EXT2_UNRM_FL FS_UNRM_FL /* Undelete */ +#define EXT2_COMPR_FL FS_COMPR_FL /* Compress file */ +#define EXT2_SYNC_FL FS_SYNC_FL /* Synchronous updates */ +#define EXT2_IMMUTABLE_FL FS_IMMUTABLE_FL /* Immutable file */ +#define EXT2_APPEND_FL FS_APPEND_FL /* writes to file may only append */ +#define EXT2_NODUMP_FL FS_NODUMP_FL /* do not dump file */ +#define EXT2_NOATIME_FL FS_NOATIME_FL /* do not update atime */ /* Reserved for compression usage... */ -#define EXT2_DIRTY_FL 0x00000100 -#define EXT2_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ -#define EXT2_NOCOMP_FL 0x00000400 /* Don't compress */ -#define EXT2_ECOMPR_FL 0x00000800 /* Compression error */ +#define EXT2_DIRTY_FL FS_DIRTY_FL +#define EXT2_COMPRBLK_FL FS_COMPRBLK_FL /* One or more compressed clusters */ +#define EXT2_NOCOMP_FL FS_NOCOMP_FL /* Don't compress */ +#define EXT2_ECOMPR_FL FS_ECOMPR_FL /* Compression error */ /* End compression flags --- maybe not all used */ -#define EXT2_BTREE_FL 0x00001000 /* btree format dir */ -#define EXT2_INDEX_FL 0x00001000 /* hash-indexed directory */ -#define EXT2_IMAGIC_FL 0x00002000 /* AFS directory */ -#define EXT2_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ -#define EXT2_NOTAIL_FL 0x00008000 /* file tail should not be merged */ -#define EXT2_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ -#define EXT2_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define EXT2_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ - -#define EXT2_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -#define EXT2_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +#define EXT2_BTREE_FL FS_BTREE_FL /* btree format dir */ +#define EXT2_INDEX_FL FS_INDEX_FL /* hash-indexed directory */ +#define EXT2_IMAGIC_FL FS_IMAGIC_FL /* AFS directory */ +#define EXT2_JOURNAL_DATA_FL FS_JOURNAL_DATA_FL /* Reserved for ext3 */ +#define EXT2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */ +#define EXT2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */ +#define EXT2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/ +#define EXT2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */ + +#define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ +#define EXT2_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */ /* * ioctl commands */ -#define EXT2_IOC_GETFLAGS _IOR('f', 1, long) -#define EXT2_IOC_SETFLAGS _IOW('f', 2, long) -#define EXT2_IOC_GETVERSION _IOR('v', 1, long) -#define EXT2_IOC_SETVERSION _IOW('v', 2, long) +#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION +#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION +#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION /* * Structure of an inode on the disk diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index cc08f56750da..a7a01ff44669 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -216,20 +216,32 @@ struct ext3_new_group_data { /* * ioctl commands */ -#define EXT3_IOC_GETFLAGS _IOR('f', 1, long) -#define EXT3_IOC_SETFLAGS _IOW('f', 2, long) +#define EXT3_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT3_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT3_IOC_GETVERSION _IOR('f', 3, long) #define EXT3_IOC_SETVERSION _IOW('f', 4, long) #define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) -#define EXT3_IOC_GETVERSION_OLD _IOR('v', 1, long) -#define EXT3_IOC_SETVERSION_OLD _IOW('v', 2, long) +#define EXT3_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT3_IOC_SETVERSION_OLD FS_IOC_SETVERSION #ifdef CONFIG_JBD_DEBUG #define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif #define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) #define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) +/* + * ioctl commands in 32 bit emulation + */ +#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif + /* * Mount options */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 1728142ec4b6..b73a47582dbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -217,6 +217,45 @@ extern int dir_notify_enable; #define FIBMAP _IO(0x00,1) /* bmap access */ #define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ +#define FS_IOC_GETFLAGS _IOR('f', 1, long) +#define FS_IOC_SETFLAGS _IOW('f', 2, long) +#define FS_IOC_GETVERSION _IOR('v', 1, long) +#define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC32_GETFLAGS _IOR('f', 1, int) +#define FS_IOC32_SETFLAGS _IOW('f', 2, int) +#define FS_IOC32_GETVERSION _IOR('v', 1, int) +#define FS_IOC32_SETVERSION _IOW('v', 2, int) + +/* + * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) + */ +#define FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define FS_UNRM_FL 0x00000002 /* Undelete */ +#define FS_COMPR_FL 0x00000004 /* Compress file */ +#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define FS_DIRTY_FL 0x00000100 +#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ +#define FS_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define FS_BTREE_FL 0x00001000 /* btree format dir */ +#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ +#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ + +#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + + #define SYNC_FILE_RANGE_WAIT_BEFORE 1 #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 28493ffaafe7..0100d6d1d84c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -807,21 +807,19 @@ struct stat_data_v1 { #define set_sd_v1_first_direct_byte(sdp,v) \ ((sdp)->sd_first_direct_byte = cpu_to_le32(v)) -#include - /* inode flags stored in sd_attrs (nee sd_reserved) */ /* we want common flags to have the same values as in ext2, so chattr(1) will work without problems */ -#define REISERFS_IMMUTABLE_FL EXT2_IMMUTABLE_FL -#define REISERFS_APPEND_FL EXT2_APPEND_FL -#define REISERFS_SYNC_FL EXT2_SYNC_FL -#define REISERFS_NOATIME_FL EXT2_NOATIME_FL -#define REISERFS_NODUMP_FL EXT2_NODUMP_FL -#define REISERFS_SECRM_FL EXT2_SECRM_FL -#define REISERFS_UNRM_FL EXT2_UNRM_FL -#define REISERFS_COMPR_FL EXT2_COMPR_FL -#define REISERFS_NOTAIL_FL EXT2_NOTAIL_FL +#define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL +#define REISERFS_APPEND_FL FS_APPEND_FL +#define REISERFS_SYNC_FL FS_SYNC_FL +#define REISERFS_NOATIME_FL FS_NOATIME_FL +#define REISERFS_NODUMP_FL FS_NODUMP_FL +#define REISERFS_SECRM_FL FS_SECRM_FL +#define REISERFS_UNRM_FL FS_UNRM_FL +#define REISERFS_COMPR_FL FS_COMPR_FL +#define REISERFS_NOTAIL_FL FS_NOTAIL_FL /* persistent flags that file inherits from the parent directory */ #define REISERFS_INHERIT_MASK ( REISERFS_IMMUTABLE_FL | \ @@ -2168,10 +2166,10 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, #define REISERFS_IOC_UNPACK _IOW(0xCD,1,long) /* define following flags to be the same as in ext2, so that chattr(1), lsattr(1) will work with us. */ -#define REISERFS_IOC_GETFLAGS EXT2_IOC_GETFLAGS -#define REISERFS_IOC_SETFLAGS EXT2_IOC_SETFLAGS -#define REISERFS_IOC_GETVERSION EXT2_IOC_GETVERSION -#define REISERFS_IOC_SETVERSION EXT2_IOC_SETVERSION +#define REISERFS_IOC_GETFLAGS FS_IOC_GETFLAGS +#define REISERFS_IOC_SETFLAGS FS_IOC_SETFLAGS +#define REISERFS_IOC_GETVERSION FS_IOC_GETVERSION +#define REISERFS_IOC_SETVERSION FS_IOC_SETVERSION /* Locking primitives */ /* Right now we are still falling back to (un)lock_kernel, but eventually that -- cgit v1.3-8-gc7d7 From 9361401eb7619c033e2394e4f9f6d410d6719ac7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 30 Sep 2006 20:45:40 +0200 Subject: [PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- block/Kconfig | 20 ++++++++++++++++++ block/Kconfig.iosched | 3 +++ block/Makefile | 2 +- drivers/block/Kconfig | 4 ++++ drivers/cdrom/Kconfig | 2 +- drivers/char/Kconfig | 1 + drivers/char/random.c | 4 ++++ drivers/ide/Kconfig | 4 ++++ drivers/md/Kconfig | 3 +++ drivers/message/i2o/Kconfig | 2 +- drivers/mmc/Kconfig | 2 +- drivers/mmc/Makefile | 3 ++- drivers/mtd/Kconfig | 12 +++++------ drivers/mtd/devices/Kconfig | 2 +- drivers/s390/block/Kconfig | 2 +- drivers/scsi/Kconfig | 2 ++ fs/Kconfig | 31 ++++++++++++++++++++------- fs/Makefile | 14 +++++++++---- fs/compat_ioctl.c | 18 ++++++++++++++++ fs/internal.h | 6 ++++++ fs/no-block.c | 22 +++++++++++++++++++ fs/partitions/Makefile | 2 +- fs/proc/proc_misc.c | 11 +++++++++- fs/quota.c | 44 ++++++++++++++++++++++++++------------ fs/super.c | 4 ++++ fs/xfs/Kconfig | 1 + include/linux/blkdev.h | 50 +++++++++++++++++++++++++++++++------------- include/linux/buffer_head.h | 16 ++++++++++++++ include/linux/compat_ioctl.h | 2 ++ include/linux/elevator.h | 3 +++ include/linux/fs.h | 25 +++++++++++++++++++--- include/linux/genhd.h | 4 ++++ include/linux/mpage.h | 3 +++ include/linux/raid/md.h | 3 +++ include/linux/raid/md_k.h | 3 +++ include/scsi/scsi_tcq.h | 3 ++- init/Kconfig | 2 +- init/do_mounts.c | 13 +++++++++++- kernel/sys_ni.c | 5 +++++ mm/Makefile | 2 +- mm/filemap.c | 4 ++++ mm/migrate.c | 2 ++ mm/page-writeback.c | 8 ++++--- mm/truncate.c | 2 ++ 44 files changed, 308 insertions(+), 63 deletions(-) create mode 100644 fs/no-block.c (limited to 'include/linux/fs.h') diff --git a/block/Kconfig b/block/Kconfig index b6f5f0a79655..9af6c614dfde 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -1,6 +1,24 @@ # # Block layer core configuration # +config BLOCK + bool "Enable the block layer" + default y + help + This permits the block layer to be removed from the kernel if it's not + needed (on some embedded devices for example). If this option is + disabled, then blockdev files will become unusable and some + filesystems (such as ext3) will become unavailable. + + This option will also disable SCSI character devices and USB storage + since they make use of various block layer definitions and + facilities. + + Say Y here unless you know you really don't want to mount disks and + suchlike. + +if BLOCK + #XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64 #for instance. config LBD @@ -33,4 +51,6 @@ config LSF If unsure, say Y. +endif + source block/Kconfig.iosched diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 48d090e266fc..903f0d3b6852 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -1,3 +1,4 @@ +if BLOCK menu "IO Schedulers" @@ -67,3 +68,5 @@ config DEFAULT_IOSCHED default "noop" if DEFAULT_NOOP endmenu + +endif diff --git a/block/Makefile b/block/Makefile index c05de0e0037f..4b84d0d5947b 100644 --- a/block/Makefile +++ b/block/Makefile @@ -2,7 +2,7 @@ # Makefile for the kernel block layer # -obj-y := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o +obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_AS) += as-iosched.o diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index b5382cedf0c0..422e31d5f8e5 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -2,6 +2,8 @@ # Block device driver configuration # +if BLOCK + menu "Block devices" config BLK_DEV_FD @@ -468,3 +470,5 @@ config ATA_OVER_ETH devices like the Coraid EtherDrive (R) Storage Blade. endmenu + +endif diff --git a/drivers/cdrom/Kconfig b/drivers/cdrom/Kconfig index ff5652d40619..4b12e9031fb3 100644 --- a/drivers/cdrom/Kconfig +++ b/drivers/cdrom/Kconfig @@ -3,7 +3,7 @@ # menu "Old CD-ROM drivers (not SCSI, not IDE)" - depends on ISA + depends on ISA && BLOCK config CD_NO_IDESCSI bool "Support non-SCSI/IDE/ATAPI CDROM drives" diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 4cc619edf424..bde1c665d9f4 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -1006,6 +1006,7 @@ config GPIO_VR41XX config RAW_DRIVER tristate "RAW driver (/dev/raw/rawN) (OBSOLETE)" + depends on BLOCK help The raw driver permits block devices to be bound to /dev/raw/rawN. Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O. diff --git a/drivers/char/random.c b/drivers/char/random.c index 4c3a5ca9d8f7..b430a12eb819 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -655,6 +655,7 @@ void add_interrupt_randomness(int irq) add_timer_randomness(irq_timer_state[irq], 0x100 + irq); } +#ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) @@ -667,6 +668,7 @@ void add_disk_randomness(struct gendisk *disk) } EXPORT_SYMBOL(add_disk_randomness); +#endif #define EXTRACT_SIZE 10 @@ -918,6 +920,7 @@ void rand_initialize_irq(int irq) } } +#ifdef CONFIG_BLOCK void rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; @@ -932,6 +935,7 @@ void rand_initialize_disk(struct gendisk *disk) disk->random = state; } } +#endif static ssize_t random_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos) diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index b6fb167e20f6..69d627bd537a 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -4,6 +4,8 @@ # Andre Hedrick # +if BLOCK + menu "ATA/ATAPI/MFM/RLL support" config IDE @@ -1082,3 +1084,5 @@ config BLK_DEV_HD endif endmenu + +endif diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index bf869ed03eed..6dd31a291d84 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -2,6 +2,8 @@ # Block device driver configuration # +if BLOCK + menu "Multi-device support (RAID and LVM)" config MD @@ -251,3 +253,4 @@ config DM_MULTIPATH_EMC endmenu +endif diff --git a/drivers/message/i2o/Kconfig b/drivers/message/i2o/Kconfig index fef677103880..6443392bffff 100644 --- a/drivers/message/i2o/Kconfig +++ b/drivers/message/i2o/Kconfig @@ -88,7 +88,7 @@ config I2O_BUS config I2O_BLOCK tristate "I2O Block OSM" - depends on I2O + depends on I2O && BLOCK ---help--- Include support for the I2O Block OSM. The Block OSM presents disk and other structured block devices to the operating system. If you diff --git a/drivers/mmc/Kconfig b/drivers/mmc/Kconfig index 45bcf098e762..f540bd88dc5a 100644 --- a/drivers/mmc/Kconfig +++ b/drivers/mmc/Kconfig @@ -21,7 +21,7 @@ config MMC_DEBUG config MMC_BLOCK tristate "MMC block device driver" - depends on MMC + depends on MMC && BLOCK default y help Say Y here to enable the MMC block device driver support. diff --git a/drivers/mmc/Makefile b/drivers/mmc/Makefile index d2957e35cc6f..b1f6e03e7aa9 100644 --- a/drivers/mmc/Makefile +++ b/drivers/mmc/Makefile @@ -24,7 +24,8 @@ obj-$(CONFIG_MMC_AU1X) += au1xmmc.o obj-$(CONFIG_MMC_OMAP) += omap.o obj-$(CONFIG_MMC_AT91RM9200) += at91_mci.o -mmc_core-y := mmc.o mmc_queue.o mmc_sysfs.o +mmc_core-y := mmc.o mmc_sysfs.o +mmc_core-$(CONFIG_BLOCK) += mmc_queue.o ifeq ($(CONFIG_MMC_DEBUG),y) EXTRA_CFLAGS += -DDEBUG diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index a03e862851db..a304b34c2632 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -166,7 +166,7 @@ config MTD_CHAR config MTD_BLOCK tristate "Caching block device access to MTD devices" - depends on MTD + depends on MTD && BLOCK ---help--- Although most flash chips have an erase size too large to be useful as block devices, it is possible to use MTD devices which are based @@ -188,7 +188,7 @@ config MTD_BLOCK config MTD_BLOCK_RO tristate "Readonly block device access to MTD devices" - depends on MTD_BLOCK!=y && MTD + depends on MTD_BLOCK!=y && MTD && BLOCK help This allows you to mount read-only file systems (such as cramfs) from an MTD device, without the overhead (and danger) of the caching @@ -199,7 +199,7 @@ config MTD_BLOCK_RO config FTL tristate "FTL (Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the original Flash Translation Layer which is part of the PCMCIA specification. It uses a kind of pseudo- @@ -215,7 +215,7 @@ config FTL config NFTL tristate "NFTL (NAND Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the NAND Flash Translation Layer which is used on M-Systems' DiskOnChip devices. It uses a kind of pseudo- @@ -238,7 +238,7 @@ config NFTL_RW config INFTL tristate "INFTL (Inverse NAND Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the Inverse NAND Flash Translation Layer which is used on M-Systems' newer DiskOnChip devices. It @@ -255,7 +255,7 @@ config INFTL config RFD_FTL tristate "Resident Flash Disk (Flash Translation Layer) support" - depends on MTD + depends on MTD && BLOCK ---help--- This provides support for the flash translation layer known as the Resident Flash Disk (RFD), as used by the Embedded BIOS diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 16c02b5ccf7e..440f6851da69 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -136,7 +136,7 @@ config MTDRAM_ABS_POS config MTD_BLOCK2MTD tristate "MTD using block device" - depends on MTD + depends on MTD && BLOCK help This driver allows a block device to appear as an MTD. It would generally be used in the following cases: diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index 929d6fff6152..b250c5354503 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -1,4 +1,4 @@ -if S390 +if S390 && BLOCK comment "S/390 block device drivers" depends on S390 diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index c4dfcc91ddda..dab082002e6f 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -3,11 +3,13 @@ menu "SCSI device support" config RAID_ATTRS tristate "RAID Transport Class" default n + depends on BLOCK ---help--- Provides RAID config SCSI tristate "SCSI device support" + depends on BLOCK ---help--- If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or any other SCSI device under Linux, say Y and make sure that you know diff --git a/fs/Kconfig b/fs/Kconfig index 4fd9efac29ab..1453d2d164f7 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -4,6 +4,8 @@ menu "File systems" +if BLOCK + config EXT2_FS tristate "Second extended fs support" help @@ -399,6 +401,8 @@ config ROMFS_FS If you don't know whether you need it, then you don't need it: answer N. +endif + config INOTIFY bool "Inotify file change notification support" default y @@ -530,6 +534,7 @@ config FUSE_FS If you want to develop a userspace FS, or if you want to use a filesystem based on FUSE, answer Y or M. +if BLOCK menu "CD-ROM/DVD Filesystems" config ISO9660_FS @@ -597,7 +602,9 @@ config UDF_NLS depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y) endmenu +endif +if BLOCK menu "DOS/FAT/NT Filesystems" config FAT_FS @@ -782,6 +789,7 @@ config NTFS_RW It is perfectly safe to say N here. endmenu +endif menu "Pseudo filesystems" @@ -939,7 +947,7 @@ menu "Miscellaneous filesystems" config ADFS_FS tristate "ADFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help The Acorn Disc Filing System is the standard file system of the RiscOS operating system which runs on Acorn's ARM-based Risc PC @@ -967,7 +975,7 @@ config ADFS_FS_RW config AFFS_FS tristate "Amiga FFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help The Fast File System (FFS) is the common file system used on hard disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y @@ -989,7 +997,7 @@ config AFFS_FS config HFS_FS tristate "Apple Macintosh file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL select NLS help If you say Y here, you will be able to mount Macintosh-formatted @@ -1002,6 +1010,7 @@ config HFS_FS config HFSPLUS_FS tristate "Apple Extended HFS file system support" + depends on BLOCK select NLS select NLS_UTF8 help @@ -1015,7 +1024,7 @@ config HFSPLUS_FS config BEFS_FS tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL select NLS help The BeOS File System (BeFS) is the native file system of Be, Inc's @@ -1042,7 +1051,7 @@ config BEFS_DEBUG config BFS_FS tristate "BFS file system support (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help Boot File System (BFS) is a file system used under SCO UnixWare to allow the bootloader access to the kernel image and other important @@ -1064,7 +1073,7 @@ config BFS_FS config EFS_FS tristate "EFS file system support (read only) (EXPERIMENTAL)" - depends on EXPERIMENTAL + depends on BLOCK && EXPERIMENTAL help EFS is an older file system used for non-ISO9660 CD-ROMs and hard disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer @@ -1079,7 +1088,7 @@ config EFS_FS config JFFS_FS tristate "Journalling Flash File System (JFFS) support" - depends on MTD + depends on MTD && BLOCK help JFFS is the Journaling Flash File System developed by Axis Communications in Sweden, aimed at providing a crash/powerdown-safe @@ -1264,6 +1273,7 @@ endchoice config CRAMFS tristate "Compressed ROM file system support (cramfs)" + depends on BLOCK select ZLIB_INFLATE help Saying Y here includes support for CramFs (Compressed ROM File @@ -1283,6 +1293,7 @@ config CRAMFS config VXFS_FS tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" + depends on BLOCK help FreeVxFS is a file system driver that support the VERITAS VxFS(TM) file system format. VERITAS VxFS(TM) is the standard file system @@ -1300,6 +1311,7 @@ config VXFS_FS config HPFS_FS tristate "OS/2 HPFS file system support" + depends on BLOCK help OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS is the file system used for organizing files on OS/2 hard disk @@ -1316,6 +1328,7 @@ config HPFS_FS config QNX4FS_FS tristate "QNX4 file system support (read only)" + depends on BLOCK help This is the file system used by the real-time operating systems QNX 4 and QNX 6 (the latter is also called QNX RTP). @@ -1343,6 +1356,7 @@ config QNX4FS_RW config SYSV_FS tristate "System V/Xenix/V7/Coherent file system support" + depends on BLOCK help SCO, Xenix and Coherent are commercial Unix systems for Intel machines, and Version 7 was used on the DEC PDP-11. Saying Y @@ -1381,6 +1395,7 @@ config SYSV_FS config UFS_FS tristate "UFS file system support (read only)" + depends on BLOCK help BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD, OpenBSD and NeXTstep) use a file system called UFS. Some System V @@ -1959,11 +1974,13 @@ config GENERIC_ACL endmenu +if BLOCK menu "Partition Types" source "fs/partitions/Kconfig" endmenu +endif source "fs/nls/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 46b8cfe497b2..a503e6ce0f32 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -5,12 +5,18 @@ # Rewritten to use lists instead of if-statements. # -obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \ - block_dev.o char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ +obj-y := open.o read_write.o file_table.o super.o \ + char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \ - seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \ - ioprio.o pnode.o drop_caches.o splice.o sync.o + seq_file.o xattr.o libfs.o fs-writeback.o \ + pnode.o drop_caches.o splice.o sync.o + +ifeq ($(CONFIG_BLOCK),y) +obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o +else +obj-y += no-block.o +endif obj-$(CONFIG_INOTIFY) += inotify.o obj-$(CONFIG_INOTIFY_USER) += inotify_user.o diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index e1a56437040a..64b34533edea 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -645,6 +645,7 @@ out: } #endif +#ifdef CONFIG_BLOCK struct hd_geometry32 { unsigned char heads; unsigned char sectors; @@ -869,6 +870,7 @@ static int sg_grt_trans(unsigned int fd, unsigned int cmd, unsigned long arg) } return err; } +#endif /* CONFIG_BLOCK */ struct sock_fprog32 { unsigned short len; @@ -992,6 +994,7 @@ static int ppp_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg) } +#ifdef CONFIG_BLOCK struct mtget32 { compat_long_t mt_type; compat_long_t mt_resid; @@ -1164,6 +1167,7 @@ static int cdrom_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long ar return err; } +#endif /* CONFIG_BLOCK */ #ifdef CONFIG_VT @@ -1491,6 +1495,7 @@ ret_einval(unsigned int fd, unsigned int cmd, unsigned long arg) return -EINVAL; } +#ifdef CONFIG_BLOCK static int broken_blkgetsize(unsigned int fd, unsigned int cmd, unsigned long arg) { /* The mkswap binary hard codes it to Intel value :-((( */ @@ -1525,12 +1530,14 @@ static int blkpg_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long ar return sys_ioctl(fd, cmd, (unsigned long)a); } +#endif static int ioc_settimeout(unsigned int fd, unsigned int cmd, unsigned long arg) { return rw_long(fd, AUTOFS_IOC_SETTIMEOUT, arg); } +#ifdef CONFIG_BLOCK /* Fix sizeof(sizeof()) breakage */ #define BLKBSZGET_32 _IOR(0x12,112,int) #define BLKBSZSET_32 _IOW(0x12,113,int) @@ -1551,6 +1558,7 @@ static int do_blkgetsize64(unsigned int fd, unsigned int cmd, { return sys_ioctl(fd, BLKGETSIZE64, (unsigned long)compat_ptr(arg)); } +#endif /* Bluetooth ioctls */ #define HCIUARTSETPROTO _IOW('U', 200, int) @@ -1571,6 +1579,7 @@ static int do_blkgetsize64(unsigned int fd, unsigned int cmd, #define HIDPGETCONNLIST _IOR('H', 210, int) #define HIDPGETCONNINFO _IOR('H', 211, int) +#ifdef CONFIG_BLOCK struct floppy_struct32 { compat_uint_t size; compat_uint_t sect; @@ -1895,6 +1904,7 @@ out: kfree(karg); return err; } +#endif struct mtd_oob_buf32 { u_int32_t start; @@ -1936,6 +1946,7 @@ static int mtd_rw_oob(unsigned int fd, unsigned int cmd, unsigned long arg) return err; } +#ifdef CONFIG_BLOCK struct raw32_config_request { compat_int_t raw_minor; @@ -2000,6 +2011,7 @@ static int raw_ioctl(unsigned fd, unsigned cmd, unsigned long arg) } return ret; } +#endif /* CONFIG_BLOCK */ struct serial_struct32 { compat_int_t type; @@ -2606,6 +2618,7 @@ HANDLE_IOCTL(SIOCBRDELIF, dev_ifsioc) HANDLE_IOCTL(SIOCRTMSG, ret_einval) HANDLE_IOCTL(SIOCGSTAMP, do_siocgstamp) #endif +#ifdef CONFIG_BLOCK HANDLE_IOCTL(HDIO_GETGEO, hdio_getgeo) HANDLE_IOCTL(BLKRAGET, w_long) HANDLE_IOCTL(BLKGETSIZE, w_long) @@ -2631,14 +2644,17 @@ HANDLE_IOCTL(FDGETFDCSTAT32, fd_ioctl_trans) HANDLE_IOCTL(FDWERRORGET32, fd_ioctl_trans) HANDLE_IOCTL(SG_IO,sg_ioctl_trans) HANDLE_IOCTL(SG_GET_REQUEST_TABLE, sg_grt_trans) +#endif HANDLE_IOCTL(PPPIOCGIDLE32, ppp_ioctl_trans) HANDLE_IOCTL(PPPIOCSCOMPRESS32, ppp_ioctl_trans) HANDLE_IOCTL(PPPIOCSPASS32, ppp_sock_fprog_ioctl_trans) HANDLE_IOCTL(PPPIOCSACTIVE32, ppp_sock_fprog_ioctl_trans) +#ifdef CONFIG_BLOCK HANDLE_IOCTL(MTIOCGET32, mt_ioctl_trans) HANDLE_IOCTL(MTIOCPOS32, mt_ioctl_trans) HANDLE_IOCTL(CDROMREADAUDIO, cdrom_ioctl_trans) HANDLE_IOCTL(CDROM_SEND_PACKET, cdrom_ioctl_trans) +#endif #define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,unsigned int) HANDLE_IOCTL(AUTOFS_IOC_SETTIMEOUT32, ioc_settimeout) #ifdef CONFIG_VT @@ -2677,12 +2693,14 @@ HANDLE_IOCTL(SONET_SETFRAMING, do_atm_ioctl) HANDLE_IOCTL(SONET_GETFRAMING, do_atm_ioctl) HANDLE_IOCTL(SONET_GETFRSENSE, do_atm_ioctl) /* block stuff */ +#ifdef CONFIG_BLOCK HANDLE_IOCTL(BLKBSZGET_32, do_blkbszget) HANDLE_IOCTL(BLKBSZSET_32, do_blkbszset) HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgetsize64) /* Raw devices */ HANDLE_IOCTL(RAW_SETBIND, raw_ioctl) HANDLE_IOCTL(RAW_GETBIND, raw_ioctl) +#endif /* Serial */ HANDLE_IOCTL(TIOCGSERIAL, serial_struct_ioctl) HANDLE_IOCTL(TIOCSSERIAL, serial_struct_ioctl) diff --git a/fs/internal.h b/fs/internal.h index f662b703bb97..f07147d63255 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -14,10 +14,16 @@ /* * block_dev.c */ +#ifdef CONFIG_BLOCK extern struct super_block *blockdev_superblock; extern void __init bdev_cache_init(void); #define sb_is_blkdev_sb(sb) ((sb) == blockdev_superblock) +#else +static inline void bdev_cache_init(void) {} + +#define sb_is_blkdev_sb(sb) 0 +#endif /* * char_dev.c diff --git a/fs/no-block.c b/fs/no-block.c new file mode 100644 index 000000000000..d269a93d3467 --- /dev/null +++ b/fs/no-block.c @@ -0,0 +1,22 @@ +/* no-block.c: implementation of routines required for non-BLOCK configuration + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include + +static int no_blkdev_open(struct inode * inode, struct file * filp) +{ + return -ENODEV; +} + +const struct file_operations def_blk_fops = { + .open = no_blkdev_open, +}; diff --git a/fs/partitions/Makefile b/fs/partitions/Makefile index d713ce6b3e12..67e665fdb7fc 100644 --- a/fs/partitions/Makefile +++ b/fs/partitions/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y := check.o +obj-$(CONFIG_BLOCK) := check.o obj-$(CONFIG_ACORN_PARTITION) += acorn.o obj-$(CONFIG_AMIGA_PARTITION) += amiga.o diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 5bbd60896050..66bc425f2f3d 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -277,12 +277,15 @@ static int devinfo_show(struct seq_file *f, void *v) if (i == 0) seq_printf(f, "Character devices:\n"); chrdev_show(f, i); - } else { + } +#ifdef CONFIG_BLOCK + else { i -= CHRDEV_MAJOR_HASH_SIZE; if (i == 0) seq_printf(f, "\nBlock devices:\n"); blkdev_show(f, i); } +#endif return 0; } @@ -355,6 +358,7 @@ static int stram_read_proc(char *page, char **start, off_t off, } #endif +#ifdef CONFIG_BLOCK extern struct seq_operations partitions_op; static int partitions_open(struct inode *inode, struct file *file) { @@ -378,6 +382,7 @@ static struct file_operations proc_diskstats_operations = { .llseek = seq_lseek, .release = seq_release, }; +#endif #ifdef CONFIG_MODULES extern struct seq_operations modules_op; @@ -695,7 +700,9 @@ void __init proc_misc_init(void) entry->proc_fops = &proc_kmsg_operations; create_seq_entry("devices", 0, &proc_devinfo_operations); create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations); +#ifdef CONFIG_BLOCK create_seq_entry("partitions", 0, &proc_partitions_operations); +#endif create_seq_entry("stat", 0, &proc_stat_operations); create_seq_entry("interrupts", 0, &proc_interrupts_operations); #ifdef CONFIG_SLAB @@ -707,7 +714,9 @@ void __init proc_misc_init(void) create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations); create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations); create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations); +#ifdef CONFIG_BLOCK create_seq_entry("diskstats", 0, &proc_diskstats_operations); +#endif #ifdef CONFIG_MODULES create_seq_entry("modules", 0, &proc_modules_operations); #endif diff --git a/fs/quota.c b/fs/quota.c index d6a2be826e29..b9dae76a0b6e 100644 --- a/fs/quota.c +++ b/fs/quota.c @@ -337,6 +337,34 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void return 0; } +/* + * look up a superblock on which quota ops will be performed + * - use the name of a block device to find the superblock thereon + */ +static inline struct super_block *quotactl_block(const char __user *special) +{ +#ifdef CONFIG_BLOCK + struct block_device *bdev; + struct super_block *sb; + char *tmp = getname(special); + + if (IS_ERR(tmp)) + return ERR_PTR(PTR_ERR(tmp)); + bdev = lookup_bdev(tmp); + putname(tmp); + if (IS_ERR(bdev)) + return ERR_PTR(PTR_ERR(bdev)); + sb = get_super(bdev); + bdput(bdev); + if (!sb) + return ERR_PTR(-ENODEV); + + return sb; +#else + return ERR_PTR(-ENODEV); +#endif +} + /* * This is the system call interface. This communicates with * the user-level programs. Currently this only supports diskquota @@ -347,25 +375,15 @@ asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t { uint cmds, type; struct super_block *sb = NULL; - struct block_device *bdev; - char *tmp; int ret; cmds = cmd >> SUBCMDSHIFT; type = cmd & SUBCMDMASK; if (cmds != Q_SYNC || special) { - tmp = getname(special); - if (IS_ERR(tmp)) - return PTR_ERR(tmp); - bdev = lookup_bdev(tmp); - putname(tmp); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - sb = get_super(bdev); - bdput(bdev); - if (!sb) - return -ENODEV; + sb = quotactl_block(special); + if (IS_ERR(sb)) + return PTR_ERR(sb); } ret = check_quotactl_valid(sb, type, cmds, id); diff --git a/fs/super.c b/fs/super.c index 15671cd048b1..aec99ddbe53f 100644 --- a/fs/super.c +++ b/fs/super.c @@ -571,8 +571,10 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; +#ifdef CONFIG_BLOCK if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; +#endif if (flags & MS_RDONLY) acct_auto_close(sb); shrink_dcache_sb(sb); @@ -692,6 +694,7 @@ void kill_litter_super(struct super_block *sb) EXPORT_SYMBOL(kill_litter_super); +#ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; @@ -787,6 +790,7 @@ void kill_block_super(struct super_block *sb) } EXPORT_SYMBOL(kill_block_super); +#endif int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 26b364c9d62c..35115bca036e 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,5 +1,6 @@ config XFS_FS tristate "XFS filesystem support" + depends on BLOCK help XFS is a high performance journaling filesystem which originated on the SGI IRIX platform. It is completely multi-threaded, can diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c01a90998a7..3e36107d342a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -16,6 +16,22 @@ #include +#ifdef CONFIG_LBD +# include +# define sector_div(a, b) do_div(a, b) +#else +# define sector_div(n, b)( \ +{ \ + int _res; \ + _res = (n) % (b); \ + (n) /= (b); \ + _res; \ +} \ +) +#endif + +#ifdef CONFIG_BLOCK + struct scsi_ioctl_command; struct request_queue; @@ -818,24 +834,30 @@ struct work_struct; int kblockd_schedule_work(struct work_struct *work); void kblockd_flush(void); -#ifdef CONFIG_LBD -# include -# define sector_div(a, b) do_div(a, b) -#else -# define sector_div(n, b)( \ -{ \ - int _res; \ - _res = (n) % (b); \ - (n) /= (b); \ - _res; \ -} \ -) -#endif - #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") +#else /* CONFIG_BLOCK */ +/* + * stubs for when the block layer is configured out + */ +#define buffer_heads_over_limit 0 + +static inline long blk_congestion_wait(int rw, long timeout) +{ + return timeout; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} + +static inline void exit_io_context(void) {} + +#endif /* CONFIG_BLOCK */ + #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 64b508e35d2a..131ffd37e716 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -14,6 +14,8 @@ #include #include +#ifdef CONFIG_BLOCK + enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ @@ -301,4 +303,18 @@ static inline void lock_buffer(struct buffer_head *bh) } extern int __set_page_dirty_buffers(struct page *page); + +#else /* CONFIG_BLOCK */ + +static inline void buffer_init(void) {} +static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline int inode_has_buffers(struct inode *inode) { return 0; } +static inline void invalidate_inode_buffers(struct inode *inode) {} +static inline int remove_inode_buffers(struct inode *inode) { return 1; } +static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) {} + + +#endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 98d40e08ba6e..d61ef5951538 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -90,6 +90,7 @@ COMPATIBLE_IOCTL(FDTWADDLE) COMPATIBLE_IOCTL(FDFMTTRK) COMPATIBLE_IOCTL(FDRAWCMD) /* 0x12 */ +#ifdef CONFIG_BLOCK COMPATIBLE_IOCTL(BLKRASET) COMPATIBLE_IOCTL(BLKROSET) COMPATIBLE_IOCTL(BLKROGET) @@ -103,6 +104,7 @@ COMPATIBLE_IOCTL(BLKTRACESETUP) COMPATIBLE_IOCTL(BLKTRACETEARDOWN) ULONG_IOCTL(BLKRASET) ULONG_IOCTL(BLKFRASET) +#endif /* RAID */ COMPATIBLE_IOCTL(RAID_VERSION) COMPATIBLE_IOCTL(GET_ARRAY_INFO) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 9c5a04f6114c..b3370ef5164d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -3,6 +3,8 @@ #include +#ifdef CONFIG_BLOCK + typedef int (elevator_merge_fn) (request_queue_t *, struct request **, struct bio *); @@ -203,4 +205,5 @@ enum { __val; \ }) +#endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index b73a47582dbe..5baf3a153403 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1482,6 +1482,7 @@ extern void __init vfs_caches_init(unsigned long); extern void putname(const char *name); #endif +#ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern int unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); @@ -1490,11 +1491,15 @@ extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); extern struct block_device *open_partition_by_devnum(dev_t, unsigned); -extern const struct file_operations def_blk_fops; extern const struct address_space_operations def_blk_aops; +#else +static inline void bd_forget(struct inode *inode) {} +#endif +extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; extern const struct file_operations bad_sock_fops; extern const struct file_operations def_fifo_fops; +#ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); @@ -1510,6 +1515,7 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); #define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) #define bd_release_from_disk(bdev, disk) bd_release(bdev) #endif +#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_HASH_SIZE 255 @@ -1523,14 +1529,19 @@ extern int chrdev_open(struct inode *, struct file *); extern void chrdev_show(struct seq_file *,off_t); /* fs/block_dev.c */ -#define BLKDEV_MAJOR_HASH_SIZE 255 #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ + +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_HASH_SIZE 255 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_excl(const char *, int, void *); extern void close_bdev_excl(struct block_device *); extern void blkdev_show(struct seq_file *,off_t); +#else +#define BLKDEV_MAJOR_HASH_SIZE 0 +#endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1544,6 +1555,7 @@ extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); +#ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE */ @@ -1555,9 +1567,10 @@ extern int fs_may_remount_ro(struct super_block *); #define bio_data_dir(bio) ((bio)->bi_rw & 1) extern int check_disk_change(struct block_device *); -extern int invalidate_inodes(struct super_block *); extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); +#endif +extern int invalidate_inodes(struct super_block *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); unsigned long invalidate_inode_pages(struct address_space *mapping); @@ -1590,7 +1603,9 @@ extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); +#ifdef CONFIG_BLOCK extern sector_t bmap(struct inode *, sector_t); +#endif extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); extern int generic_permission(struct inode *, int, @@ -1673,9 +1688,11 @@ static inline void insert_inode_hash(struct inode *inode) { extern struct file * get_empty_filp(void); extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); +#ifdef CONFIG_BLOCK struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); +#endif extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); @@ -1756,6 +1773,7 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos, actor); } +#ifdef CONFIG_BLOCK ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, @@ -1793,6 +1811,7 @@ static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, nr_segs, get_block, end_io, DIO_OWN_LOCKING); } +#endif extern const struct file_operations generic_ro_fops; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e4af57e87c17..41f276fdd185 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -11,6 +11,8 @@ #include +#ifdef CONFIG_BLOCK + enum { /* These three have identical behaviour; use the second one if DOS FDISK gets confused about extended/logical partitions starting past cylinder 1023. */ @@ -420,3 +422,5 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index) #endif #endif + +#endif diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 517c098fde20..cc5fb75af78a 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -9,6 +9,7 @@ * (And no, it doesn't do the #ifdef __MPAGE_H thing, and it doesn't do * nested includes. Get it right in the .c file). */ +#ifdef CONFIG_BLOCK struct writeback_control; typedef int (writepage_t)(struct page *page, struct writeback_control *wbc); @@ -20,3 +21,5 @@ int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); + +#endif diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index eb3e547c8fee..c588709acbbc 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -53,6 +53,8 @@ #include #include +#ifdef CONFIG_MD + /* * Different major versions are not compatible. * Different minor versions are only downward compatible. @@ -95,5 +97,6 @@ extern void md_new_event(mddev_t *mddev); extern void md_update_sb(mddev_t * mddev); +#endif /* CONFIG_MD */ #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index d28890295852..920b94fe31fa 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -18,6 +18,8 @@ /* and dm-bio-list.h is not under include/linux because.... ??? */ #include "../../../drivers/md/dm-bio-list.h" +#ifdef CONFIG_BLOCK + #define LEVEL_MULTIPATH (-4) #define LEVEL_LINEAR (-1) #define LEVEL_FAULTY (-5) @@ -362,5 +364,6 @@ static inline void safe_put_page(struct page *p) if (p) put_page(p); } +#endif /* CONFIG_BLOCK */ #endif diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h index bbf66219b769..c247a28259bc 100644 --- a/include/scsi/scsi_tcq.h +++ b/include/scsi/scsi_tcq.h @@ -6,7 +6,6 @@ #include #include - #define MSG_SIMPLE_TAG 0x20 #define MSG_HEAD_TAG 0x21 #define MSG_ORDERED_TAG 0x22 @@ -14,6 +13,7 @@ #define SCSI_NO_TAG (-1) /* identify no tag in use */ +#ifdef CONFIG_BLOCK /** * scsi_get_tag_type - get the type of tag the device supports @@ -144,4 +144,5 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth) return shost->bqt ? 0 : -ENOMEM; } +#endif /* CONFIG_BLOCK */ #endif /* _SCSI_SCSI_TCQ_H */ diff --git a/init/Kconfig b/init/Kconfig index 4381006dd666..d2eb7a84a264 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -92,7 +92,7 @@ config LOCALVERSION_AUTO config SWAP bool "Support for paging of anonymous memory (swap)" - depends on MMU + depends on MMU && BLOCK default y help This option allows you to choose whether you want to have support diff --git a/init/do_mounts.c b/init/do_mounts.c index b290aadb1d3f..dc1ec0803ef9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -285,7 +285,11 @@ void __init mount_block_root(char *name, int flags) { char *fs_names = __getname(); char *p; +#ifdef CONFIG_BLOCK char b[BDEVNAME_SIZE]; +#else + const char *b = name; +#endif get_fs_names(fs_names); retry: @@ -304,7 +308,9 @@ retry: * Allow the user to distinguish between failed sys_open * and bad superblock on root device. */ +#ifdef CONFIG_BLOCK __bdevname(ROOT_DEV, b); +#endif printk("VFS: Cannot open root device \"%s\" or %s\n", root_device_name, b); printk("Please append a correct \"root=\" boot option\n"); @@ -316,7 +322,10 @@ retry: for (p = fs_names; *p; p += strlen(p)+1) printk(" %s", p); printk("\n"); - panic("VFS: Unable to mount root fs on %s", __bdevname(ROOT_DEV, b)); +#ifdef CONFIG_BLOCK + __bdevname(ROOT_DEV, b); +#endif + panic("VFS: Unable to mount root fs on %s", b); out: putname(fs_names); } @@ -387,8 +396,10 @@ void __init mount_root(void) change_floppy("root floppy"); } #endif +#ifdef CONFIG_BLOCK create_dev("/dev/root", ROOT_DEV); mount_block_root("/dev/root", root_mountflags); +#endif } /* diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 6991bece67e8..7a3b2e75f040 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -134,3 +134,8 @@ cond_syscall(sys_madvise); cond_syscall(sys_mremap); cond_syscall(sys_remap_file_pages); cond_syscall(compat_sys_move_pages); + +/* block-layer dependent */ +cond_syscall(sys_bdflush); +cond_syscall(sys_ioprio_set); +cond_syscall(sys_ioprio_get); diff --git a/mm/Makefile b/mm/Makefile index 4f2166a833b9..12b3a4eee88d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -12,7 +12,7 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o \ prio_tree.o util.o mmzone.o vmstat.o $(mmu-y) -ifeq ($(CONFIG_MMU),y) +ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy) obj-y += bounce.o endif obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o diff --git a/mm/filemap.c b/mm/filemap.c index d6846de08887..c4fe97f5ace0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2020,6 +2020,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) *count = inode->i_sb->s_maxbytes - *pos; } else { +#ifdef CONFIG_BLOCK loff_t isize; if (bdev_read_only(I_BDEV(inode))) return -EPERM; @@ -2031,6 +2032,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (*pos + *count > isize) *count = isize - *pos; +#else + return -EPERM; +#endif } return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index 7f50e3ff54cd..ba2453f9483d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -409,6 +409,7 @@ int migrate_page(struct address_space *mapping, } EXPORT_SYMBOL(migrate_page); +#ifdef CONFIG_BLOCK /* * Migration function for pages with buffers. This function can only be used * if the underlying filesystem guarantees that no other references to "page" @@ -466,6 +467,7 @@ int buffer_migrate_page(struct address_space *mapping, return 0; } EXPORT_SYMBOL(buffer_migrate_page); +#endif /* * Writeback a page to clean the dirty state diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ecf27839c203..c0d4ce144dec 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -807,9 +807,11 @@ int fastcall set_page_dirty(struct page *page) if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; - if (spd) - return (*spd)(page); - return __set_page_dirty_buffers(page); +#ifdef CONFIG_BLOCK + if (!spd) + spd = __set_page_dirty_buffers; +#endif + return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) diff --git a/mm/truncate.c b/mm/truncate.c index cd3e34b816db..8fde6580657e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -35,8 +35,10 @@ void do_invalidatepage(struct page *page, unsigned long offset) { void (*invalidatepage)(struct page *, unsigned long); invalidatepage = page->mapping->a_ops->invalidatepage; +#ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; +#endif if (invalidatepage) (*invalidatepage)(page, offset); } -- cgit v1.3-8-gc7d7 From 027445c37282bc1ed26add45e573ad2d3e4860a5 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:46 -0700 Subject: [PATCH] Vectorize aio_read/aio_write fileop methods This patch vectorizes aio_read() and aio_write() methods to prepare for collapsing all aio & vectored operations into one interface - which is aio_read()/aio_write(). Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 5 +-- Documentation/filesystems/vfs.txt | 4 +- arch/s390/hypfs/inode.c | 17 +++++++-- drivers/char/raw.c | 14 +------ drivers/usb/gadget/inode.c | 80 +++++++++++++++++++++++++++------------ fs/aio.c | 15 ++++++-- fs/block_dev.c | 10 +---- fs/cifs/cifsfs.c | 6 +-- fs/ext3/file.c | 5 ++- fs/nfs/direct.c | 26 ++++++++++--- fs/nfs/file.c | 34 +++++++++-------- fs/ntfs/file.c | 8 ++-- fs/ocfs2/file.c | 28 +++++++------- fs/read_write.c | 20 ++++++++-- fs/reiserfs/file.c | 4 +- fs/xfs/linux-2.6/xfs_file.c | 46 +++++++++++----------- include/linux/aio.h | 2 + include/linux/fs.h | 10 ++--- include/linux/nfs_fs.h | 10 +++-- include/net/sock.h | 1 - mm/filemap.c | 39 +++++++++---------- net/socket.c | 49 +++++++++++------------- 22 files changed, 242 insertions(+), 191 deletions(-) (limited to 'include/linux/fs.h') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 247d7f619aa2..eb1a6cad21e6 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -356,10 +356,9 @@ The last two are called only from check_disk_change(). prototypes: loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, - loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 1cb7e8be927a..cd07c21b8400 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -699,9 +699,9 @@ This describes how the VFS can manipulate an open file. As of kernel struct file_operations { loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 813fc21358f9..cd702ae45d6d 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -134,12 +134,20 @@ static int hypfs_open(struct inode *inode, struct file *filp) return 0; } -static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, - size_t count, loff_t offset) +static ssize_t hypfs_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { char *data; size_t len; struct file *filp = iocb->ki_filp; + /* XXX: temporary */ + char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; + + if (nr_segs != 1) { + count = -EINVAL; + goto out; + } data = filp->private_data; len = strlen(data); @@ -158,12 +166,13 @@ static ssize_t hypfs_aio_read(struct kiocb *iocb, __user char *buf, out: return count; } -static ssize_t hypfs_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t offset) { int rc; struct super_block *sb; struct hypfs_sb_info *fs_info; + size_t count = iov_length(iov, nr_segs); sb = iocb->ki_filp->f_dentry->d_inode->i_sb; fs_info = sb->s_fs_info; diff --git a/drivers/char/raw.c b/drivers/char/raw.c index c596a08c07b3..173fb08555d5 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -249,23 +249,11 @@ static ssize_t raw_file_write(struct file *file, const char __user *buf, return generic_file_write_nolock(file, &local_iov, 1, ppos); } -static ssize_t raw_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - - static const struct file_operations raw_fops = { .read = generic_file_read, .aio_read = generic_file_aio_read, .write = raw_file_write, - .aio_write = raw_file_aio_write, + .aio_write = generic_file_aio_write_nolock, .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 4a000d846a93..86924f9cdd7e 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -533,7 +533,8 @@ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; void *buf; - char __user *ubuf; /* NULL for writes */ + const struct iovec *iv; + unsigned long nr_segs; unsigned actual; }; @@ -561,17 +562,32 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e) static ssize_t ep_aio_read_retry(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; - ssize_t status = priv->actual; - - /* we "retry" to get the right mm context for this: */ - status = copy_to_user(priv->ubuf, priv->buf, priv->actual); - if (unlikely(0 != status)) - status = -EFAULT; - else - status = priv->actual; - kfree(priv->buf); - kfree(priv); - return status; + ssize_t len, total; + int i; + + /* we "retry" to get the right mm context for this: */ + + /* copy stuff into user buffers */ + total = priv->actual; + len = 0; + for (i=0; i < priv->nr_segs; i++) { + ssize_t this = min((ssize_t)(priv->iv[i].iov_len), total); + + if (copy_to_user(priv->iv[i].iov_base, priv->buf, this)) { + if (len == 0) + len = -EFAULT; + break; + } + + total -= this; + len += this; + if (total == 0) + break; + } + kfree(priv->buf); + kfree(priv); + aio_put_req(iocb); + return len; } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) @@ -584,7 +600,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; - if (priv->ubuf == NULL + if (priv->iv == NULL || unlikely(req->actual == 0) || unlikely(kiocbIsCancelled(iocb))) { kfree(req->buf); @@ -619,7 +635,8 @@ ep_aio_rwtail( char *buf, size_t len, struct ep_data *epdata, - char __user *ubuf + const struct iovec *iv, + unsigned long nr_segs ) { struct kiocb_priv *priv; @@ -634,7 +651,8 @@ fail: return value; } iocb->private = priv; - priv->ubuf = ubuf; + priv->iv = iv; + priv->nr_segs = nr_segs; value = get_ready_ep(iocb->ki_filp->f_flags, epdata); if (unlikely(value < 0)) { @@ -674,41 +692,53 @@ fail: kfree(priv); put_ep(epdata); } else - value = (ubuf ? -EIOCBRETRY : -EIOCBQUEUED); + value = (iv ? -EIOCBRETRY : -EIOCBQUEUED); return value; } static ssize_t -ep_aio_read(struct kiocb *iocb, char __user *ubuf, size_t len, loff_t o) +ep_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; if (unlikely(epdata->desc.bEndpointAddress & USB_DIR_IN)) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; + iocb->ki_retry = ep_aio_read_retry; - return ep_aio_rwtail(iocb, buf, len, epdata, ubuf); + return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs); } static ssize_t -ep_aio_write(struct kiocb *iocb, const char __user *ubuf, size_t len, loff_t o) +ep_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t o) { struct ep_data *epdata = iocb->ki_filp->private_data; char *buf; + size_t len = 0; + int i = 0; if (unlikely(!(epdata->desc.bEndpointAddress & USB_DIR_IN))) return -EINVAL; - buf = kmalloc(len, GFP_KERNEL); + + buf = kmalloc(iocb->ki_left, GFP_KERNEL); if (unlikely(!buf)) return -ENOMEM; - if (unlikely(copy_from_user(buf, ubuf, len) != 0)) { - kfree(buf); - return -EFAULT; + + for (i=0; i < nr_segs; i++) { + if (unlikely(copy_from_user(&buf[len], iov[i].iov_base, + iov[i].iov_len) != 0)) { + kfree(buf); + return -EFAULT; + } + len += iov[i].iov_len; } - return ep_aio_rwtail(iocb, buf, len, epdata, NULL); + return ep_aio_rwtail(iocb, buf, len, epdata, NULL, 0); } /*----------------------------------------------------------------------*/ diff --git a/fs/aio.c b/fs/aio.c index 950630187acc..27ff56540c73 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -15,6 +15,7 @@ #include #include #include +#include #define DEBUG 0 @@ -1315,8 +1316,11 @@ static ssize_t aio_pread(struct kiocb *iocb) ssize_t ret = 0; do { - ret = file->f_op->aio_read(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); + iocb->ki_inline_vec.iov_base = iocb->ki_buf; + iocb->ki_inline_vec.iov_len = iocb->ki_left; + + ret = file->f_op->aio_read(iocb, &iocb->ki_inline_vec, + 1, iocb->ki_pos); /* * Can't just depend on iocb->ki_left to determine * whether we are done. This may have been a short read. @@ -1349,8 +1353,11 @@ static ssize_t aio_pwrite(struct kiocb *iocb) ssize_t ret = 0; do { - ret = file->f_op->aio_write(iocb, iocb->ki_buf, - iocb->ki_left, iocb->ki_pos); + iocb->ki_inline_vec.iov_base = iocb->ki_buf; + iocb->ki_inline_vec.iov_len = iocb->ki_left; + + ret = file->f_op->aio_write(iocb, &iocb->ki_inline_vec, + 1, iocb->ki_pos); if (ret > 0) { iocb->ki_buf += ret; iocb->ki_left -= ret; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0c361ea7e5a6..8c819117310b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1162,14 +1162,6 @@ static ssize_t blkdev_file_write(struct file *file, const char __user *buf, return generic_file_write_nolock(file, &local_iov, 1, ppos); } -static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); -} - static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); @@ -1192,7 +1184,7 @@ const struct file_operations def_blk_fops = { .read = generic_file_read, .write = blkdev_file_write, .aio_read = generic_file_aio_read, - .aio_write = blkdev_file_aio_write, + .aio_write = generic_file_aio_write_nolock, .mmap = generic_file_mmap, .fsync = block_fsync, .unlocked_ioctl = block_ioctl, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 22bcf4d7e7ae..5abb42a7c53e 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -492,13 +492,13 @@ static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov, return written; } -static ssize_t cifs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_dentry->d_inode; ssize_t written; - written = generic_file_aio_write(iocb, buf, count, pos); + written = generic_file_aio_write(iocb, iov, nr_segs, pos); if (!CIFS_I(inode)->clientCanCacheAll) filemap_fdatawrite(inode->i_mapping); return written; diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 74ff20f9d09b..5c762457bc89 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -48,14 +48,15 @@ static int ext3_release_file (struct inode * inode, struct file * filp) } static ssize_t -ext3_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ext3_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; ssize_t ret; int err; - ret = generic_file_aio_write(iocb, buf, count, pos); + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); /* * Skip flushing if there was an error, or if nothing was written. diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 377839bed172..9f7f8b9ea1e2 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -707,8 +707,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz /** * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer into which to read data - * @count: number of bytes to read + * @iov: vector of user buffers into which to read data + * @nr_segs: size of iov vector * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling @@ -725,17 +725,24 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dprintk("nfs: direct read(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + if (count < 0) goto out; retval = -EFAULT; @@ -760,8 +767,8 @@ out: /** * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block - * @buf: user's buffer from which to write data - * @count: number of bytes to write + * @iov: vector of user buffers from which to write data + * @nr_segs: size of iov vector * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling @@ -782,17 +789,24 @@ out: * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t retval; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; + /* XXX: temporary */ + const char __user *buf = iov[0].iov_base; + size_t count = iov[0].iov_len; dfprintk(VFS, "nfs: direct write(%s/%s, %lu@%Ld)\n", file->f_dentry->d_parent->d_name.name, file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); + if (nr_segs != 1) + return -EINVAL; + retval = generic_write_checks(file, &pos, &count, 0); if (retval) goto out; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index be997d649127..cc93865cea93 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -41,8 +41,10 @@ static int nfs_file_release(struct inode *, struct file *); static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin); static int nfs_file_mmap(struct file *, struct vm_area_struct *); static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); -static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t); -static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t); +static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int nfs_file_flush(struct file *, fl_owner_t id); static int nfs_fsync(struct file *, struct dentry *dentry, int datasync); static int nfs_check_flags(int flags); @@ -53,8 +55,8 @@ const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, .read = do_sync_read, .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs_file_open, .flush = nfs_file_flush, @@ -196,15 +198,17 @@ nfs_file_flush(struct file *file, fl_owner_t id) } static ssize_t -nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) +nfs_file_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, buf, count, pos); + return nfs_file_direct_read(iocb, iov, nr_segs, pos); #endif dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n", @@ -214,7 +218,7 @@ nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count); if (!result) - result = generic_file_aio_read(iocb, buf, count, pos); + result = generic_file_aio_read(iocb, iov, nr_segs, pos); return result; } @@ -336,24 +340,22 @@ const struct address_space_operations nfs_file_aops = { #endif }; -/* - * Write to a file (through the page cache). - */ -static ssize_t -nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos) +static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_dentry; struct inode * inode = dentry->d_inode; ssize_t result; + size_t count = iov_length(iov, nr_segs); #ifdef CONFIG_NFS_DIRECTIO if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, buf, count, pos); + return nfs_file_direct_write(iocb, iov, nr_segs, pos); #endif - dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n", + dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n", dentry->d_parent->d_name.name, dentry->d_name.name, - inode->i_ino, (unsigned long) count, (unsigned long) pos); + inode->i_ino, (unsigned long) count, (long long) pos); result = -EBUSY; if (IS_SWAPFILE(inode)) @@ -372,7 +374,7 @@ nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t goto out; nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count); - result = generic_file_aio_write(iocb, buf, count, pos); + result = generic_file_aio_write(iocb, iov, nr_segs, pos); out: return result; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 585a79d39c9d..0c46f5c86b71 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2176,20 +2176,18 @@ out: /** * ntfs_file_aio_write - */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = ntfs_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err = sync_page_range(inode, mapping, pos, ret); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2bbfa17090cf..d9ba0a931a03 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -961,25 +961,23 @@ static inline int ocfs2_write_should_remove_suid(struct inode *inode) } static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; int ret, rw_level = -1, meta_level = -1, have_alloc_sem = 0; u32 clusters; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; loff_t newsize, saved_pos; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); /* happy write of zero bytes */ - if (count == 0) + if (iocb->ki_left == 0) return 0; if (!inode) { @@ -1048,7 +1046,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, } else { saved_pos = iocb->ki_pos; } - newsize = count + saved_pos; + newsize = iocb->ki_left + saved_pos; mlog(0, "pos=%lld newsize=%lld cursize=%lld\n", (long long) saved_pos, (long long) newsize, @@ -1081,7 +1079,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, if (!clusters) break; - ret = ocfs2_extend_file(inode, NULL, newsize, count); + ret = ocfs2_extend_file(inode, NULL, newsize, iocb->ki_left); if (ret < 0) { if (ret != -ENOSPC) mlog_errno(ret); @@ -1098,7 +1096,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb); - ret = generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); + ret = generic_file_aio_write_nolock(iocb, iov, nr_segs, iocb->ki_pos); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT)); @@ -1132,16 +1130,16 @@ out: } static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int ret = 0, rw_level = -1, have_alloc_sem = 0; struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; - mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", filp, buf, - (unsigned int)count, + mlog_entry("(0x%p, %u, '%.*s')\n", filp, + (unsigned int)nr_segs, filp->f_dentry->d_name.len, filp->f_dentry->d_name.name); @@ -1185,7 +1183,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, } ocfs2_meta_unlock(inode, 0); - ret = generic_file_aio_read(iocb, buf, count, iocb->ki_pos); + ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos); if (ret == -EINVAL) mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n"); diff --git a/fs/read_write.c b/fs/read_write.c index d4cb3183c99c..679dd535380f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -227,14 +227,20 @@ static void wait_on_retry_sync_kiocb(struct kiocb *iocb) ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); @@ -279,14 +285,20 @@ EXPORT_SYMBOL(vfs_read); ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { + struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - while (-EIOCBRETRY == - (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos))) + kiocb.ki_left = len; + + for (;;) { + ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; wait_on_retry_sync_kiocb(&kiocb); + } if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index c11f6118c9ca..41f24369e47a 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -1334,7 +1334,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t if (err) return err; } - result = generic_file_write(file, buf, count, ppos); + result = do_sync_write(file, buf, count, ppos); if (after_file_end) { /* Now update i_size and remove the savelink */ struct reiserfs_transaction_handle th; @@ -1566,7 +1566,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t } const struct file_operations reiserfs_file_operations = { - .read = generic_file_read, + .read = do_sync_read, .write = reiserfs_file_write, .ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 41cfcba7ce49..4737971c6a39 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -49,50 +49,49 @@ static struct vm_operations_struct xfs_dmapi_file_vm_ops; STATIC inline ssize_t __xfs_file_read( struct kiocb *iocb, - char __user *buf, + const struct iovec *iov, + unsigned long nr_segs, int ioflags, - size_t count, loff_t pos) { - struct iovec iov = {buf, count}; struct file *file = iocb->ki_filp; bhv_vnode_t *vp = vn_from_inode(file->f_dentry->d_inode); BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_read(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_read(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_read( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_read_invis( struct kiocb *iocb, - char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_read(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); + return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC inline ssize_t __xfs_file_write( - struct kiocb *iocb, - const char __user *buf, - int ioflags, - size_t count, - loff_t pos) + struct kiocb *iocb, + const struct iovec *iov, + unsigned long nr_segs, + int ioflags, + loff_t pos) { - struct iovec iov = {(void __user *)buf, count}; struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; bhv_vnode_t *vp = vn_from_inode(inode); @@ -100,27 +99,28 @@ __xfs_file_write( BUG_ON(iocb->ki_pos != pos); if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; - return bhv_vop_write(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL); + return bhv_vop_write(vp, iocb, iov, nr_segs, &iocb->ki_pos, + ioflags, NULL); } STATIC ssize_t xfs_file_aio_write( struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_write(iocb, buf, IO_ISAIO, count, pos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO, pos); } STATIC ssize_t xfs_file_aio_write_invis( struct kiocb *iocb, - const char __user *buf, - size_t count, + const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - return __xfs_file_write(iocb, buf, IO_ISAIO|IO_INVIS, count, pos); + return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } STATIC inline ssize_t diff --git a/include/linux/aio.h b/include/linux/aio.h index 8a0193385a9b..58349e58b749 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -4,6 +4,7 @@ #include #include #include +#include #include @@ -112,6 +113,7 @@ struct kiocb { long ki_retried; /* just for testing */ long ki_kicked; /* just for testing */ long ki_queued; /* just for testing */ + struct iovec ki_inline_vec; /* inline vector */ struct list_head ki_list; /* the aio core uses this * for cancellation */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 5baf3a153403..257bae16f545 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1097,9 +1097,9 @@ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); @@ -1704,11 +1704,11 @@ extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t *); + unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 98c9b9f667a5..76ff54846ada 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -367,10 +367,12 @@ extern int nfs3_removexattr (struct dentry *, const char *name); */ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, unsigned long); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, - size_t count, loff_t pos); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos); +extern ssize_t nfs_file_direct_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); +extern ssize_t nfs_file_direct_write(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); /* * linux/fs/nfs/dir.c diff --git a/include/net/sock.h b/include/net/sock.h index edd4d73ce7f5..40bb90ebb2d1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -665,7 +665,6 @@ struct sock_iocb { struct sock *sk; struct scm_cookie *scm; struct msghdr *msg, async_msg; - struct iovec async_iov; struct kiocb *kiocb; }; diff --git a/mm/filemap.c b/mm/filemap.c index c4fe97f5ace0..f6c1d22b504f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1226,12 +1226,11 @@ out: EXPORT_SYMBOL(__generic_file_aio_read); ssize_t -generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos); + return __generic_file_aio_read(iocb, iov, nr_segs, &iocb->ki_pos); } EXPORT_SYMBOL(generic_file_aio_read); @@ -2315,22 +2314,22 @@ out: current->backing_dev_info = NULL; return written ? written : err; } -EXPORT_SYMBOL(generic_file_aio_write_nolock); -ssize_t -generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - loff_t pos = *ppos; - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos); + BUG_ON(iocb->ki_pos != pos); + + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; + ssize_t err; err = sync_page_range_nolock(inode, mapping, pos, ret); if (err < 0) @@ -2338,6 +2337,7 @@ generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, } return ret; } +EXPORT_SYMBOL(generic_file_aio_write_nolock); static ssize_t __generic_file_write_nolock(struct file *file, const struct iovec *iov, @@ -2347,8 +2347,9 @@ __generic_file_write_nolock(struct file *file, const struct iovec *iov, ssize_t ret; init_sync_kiocb(&kiocb, file); + kiocb.ki_pos = *ppos; ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (ret == -EIOCBQUEUED) + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); return ret; } @@ -2361,28 +2362,28 @@ generic_file_write_nolock(struct file *file, const struct iovec *iov, ssize_t ret; init_sync_kiocb(&kiocb, file); - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); + kiocb.ki_pos = *ppos; + ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, *ppos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; return ret; } EXPORT_SYMBOL(generic_file_write_nolock); -ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, - &iocb->ki_pos); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { diff --git a/net/socket.c b/net/socket.c index 1bc4167e0da8..df92e4252749 100644 --- a/net/socket.c +++ b/net/socket.c @@ -95,10 +95,10 @@ #include static int sock_no_open(struct inode *irrelevant, struct file *dontcare); -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf, - size_t size, loff_t pos); -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf, - size_t size, loff_t pos); +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); @@ -664,7 +664,6 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, - char __user *ubuf, size_t size, struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { @@ -675,16 +674,13 @@ static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, } siocb->kiocb = iocb; - siocb->async_iov.iov_base = ubuf; - siocb->async_iov.iov_len = size; - iocb->private = siocb; return siocb; } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -715,32 +711,33 @@ static ssize_t sock_readv(struct file *file, const struct iovec *iov, init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; - ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs); + ret = do_sock_read(&msg, &iocb, file, iov, nr_segs); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } -static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, ubuf, count, &siocb); + + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, - unsigned long nr_segs) + struct file *file, const struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; @@ -773,28 +770,28 @@ static ssize_t sock_writev(struct file *file, const struct iovec *iov, init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; - ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs); + ret = do_sock_write(&msg, &iocb, file, iov, nr_segs); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&iocb); return ret; } -static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, - size_t count, loff_t pos) +static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct sock_iocb siocb, *x; if (pos != 0) return -ESPIPE; - if (count == 0) /* Match SYS5 behaviour */ + + if (iocb->ki_left == 0) /* Match SYS5 behaviour */ return 0; - x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb); + x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; - return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs); } /* -- cgit v1.3-8-gc7d7 From ee0b3e671baff681d69fbf0db33b47603c0a8280 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:47 -0700 Subject: [PATCH] Remove readv/writev methods and use aio_read/aio_write instead This patch removes readv() and writev() methods and replaces them with aio_read()/aio_write() methods. Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/raw.c | 2 - drivers/net/tun.c | 37 +++++----------- fs/bad_inode.c | 2 - fs/block_dev.c | 2 - fs/cifs/cifsfs.c | 16 ------- fs/compat.c | 44 +++++-------------- fs/ext2/file.c | 2 - fs/ext3/file.c | 2 - fs/fat/file.c | 2 - fs/fuse/dev.c | 37 +++++----------- fs/hostfs/hostfs_kern.c | 2 - fs/jfs/file.c | 2 - fs/ntfs/file.c | 2 - fs/pipe.c | 59 ++++++++++---------------- fs/read_write.c | 101 +++++++++++++++++++++++++++++--------------- fs/read_write.h | 14 ++++++ fs/xfs/linux-2.6/xfs_file.c | 94 ----------------------------------------- include/linux/fs.h | 6 --- mm/filemap.c | 36 ---------------- net/socket.c | 40 ------------------ sound/core/pcm_native.c | 40 +++++++++--------- 21 files changed, 154 insertions(+), 388 deletions(-) create mode 100644 fs/read_write.h (limited to 'include/linux/fs.h') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 173fb08555d5..490db531e2d8 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -257,8 +257,6 @@ static const struct file_operations raw_fops = { .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, - .readv = generic_file_readv, - .writev = generic_file_writev, .owner = THIS_MODULE, }; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index de8da6dee1b0..bc0face01d25 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -288,11 +288,10 @@ static inline size_t iov_total(const struct iovec *iv, unsigned long count) return len; } -/* Writev */ -static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { - struct tun_struct *tun = file->private_data; + struct tun_struct *tun = iocb->ki_filp->private_data; if (!tun) return -EBADFD; @@ -302,14 +301,6 @@ static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv, return tun_get_user(tun, (struct iovec *) iv, iov_total(iv, count)); } -/* Write */ -static ssize_t tun_chr_write(struct file * file, const char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { (void __user *) buf, count }; - return tun_chr_writev(file, &iv, 1, pos); -} - /* Put packet to the user space buffer */ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, struct sk_buff *skb, @@ -343,10 +334,10 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, return total; } -/* Readv */ -static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, - unsigned long count, loff_t *pos) +static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) { + struct file *file = iocb->ki_filp; struct tun_struct *tun = file->private_data; DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; @@ -426,14 +417,6 @@ static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv, return ret; } -/* Read */ -static ssize_t tun_chr_read(struct file * file, char __user * buf, - size_t count, loff_t *pos) -{ - struct iovec iv = { buf, count }; - return tun_chr_readv(file, &iv, 1, pos); -} - static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -764,10 +747,10 @@ static int tun_chr_close(struct inode *inode, struct file *file) static struct file_operations tun_fops = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = tun_chr_read, - .readv = tun_chr_readv, - .write = tun_chr_write, - .writev = tun_chr_writev, + .read = do_sync_read, + .aio_read = tun_chr_aio_read, + .write = do_sync_write, + .aio_write = tun_chr_aio_write, .poll = tun_chr_poll, .ioctl = tun_chr_ioctl, .open = tun_chr_open, diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 80599ae33966..34e6d7b220c3 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -40,8 +40,6 @@ static const struct file_operations bad_file_ops = .aio_fsync = EIO_ERROR, .fasync = EIO_ERROR, .lock = EIO_ERROR, - .readv = EIO_ERROR, - .writev = EIO_ERROR, .sendfile = EIO_ERROR, .sendpage = EIO_ERROR, .get_unmapped_area = EIO_ERROR, diff --git a/fs/block_dev.c b/fs/block_dev.c index 8c819117310b..0f143094ef1d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1191,8 +1191,6 @@ const struct file_operations def_blk_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif - .readv = generic_file_readv, - .writev = generic_file_write_nolock, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5abb42a7c53e..c00c654f2e11 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -480,18 +480,6 @@ cifs_get_sb(struct file_system_type *fs_type, return simple_set_mnt(mnt, sb); } -static ssize_t cifs_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct inode *inode = file->f_dentry->d_inode; - ssize_t written; - - written = generic_file_writev(file, iov, nr_segs, ppos); - if (!CIFS_I(inode)->clientCanCacheAll) - filemap_fdatawrite(inode->i_mapping); - return written; -} - static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -577,8 +565,6 @@ struct inode_operations cifs_symlink_inode_ops = { const struct file_operations cifs_file_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, @@ -620,8 +606,6 @@ const struct file_operations cifs_file_direct_ops = { const struct file_operations cifs_file_nobrl_ops = { .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = cifs_file_writev, .aio_read = generic_file_aio_read, .aio_write = cifs_file_aio_write, .open = cifs_open, diff --git a/fs/compat.c b/fs/compat.c index 122b4e3992b5..6b90bf35f61d 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -70,6 +70,8 @@ int compat_printk(const char *fmt, ...) return ret; } +#include "read_write.h" + /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. @@ -1149,9 +1151,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, const struct compat_iovec __user *uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov=iovstack, *vector; @@ -1234,39 +1233,18 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; + fnv = file->f_op->aio_write; } - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -1294,7 +1272,7 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) goto out; ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); @@ -1317,7 +1295,7 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig goto out; ret = -EINVAL; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) goto out; ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e8bbed9dd268..e893e2be9ed4 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -53,8 +53,6 @@ const struct file_operations ext2_file_operations = { .open = generic_file_open, .release = ext2_release_file, .fsync = ext2_sync_file, - .readv = generic_file_readv, - .writev = generic_file_writev, .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 5c762457bc89..e96c388047e0 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -112,8 +112,6 @@ const struct file_operations ext3_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = ext3_file_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, diff --git a/fs/fat/file.c b/fs/fat/file.c index d50fc47169c1..f4b8f8b3fbdd 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -127,8 +127,6 @@ const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4fc557c40cc0..66571eafbb1e 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -680,14 +680,15 @@ static int fuse_read_interrupt(struct fuse_conn *fc, struct fuse_req *req, * request_end(). Otherwise add it to the processing list, and set * the 'sent' flag. */ -static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; struct fuse_req *req; struct fuse_in *in; struct fuse_copy_state cs; unsigned reqsize; + struct file *file = iocb->ki_filp; struct fuse_conn *fc = fuse_get_conn(file); if (!fc) return -EPERM; @@ -761,15 +762,6 @@ static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_read(struct file *file, char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = buf; - return fuse_dev_readv(file, &iov, 1, off); -} - /* Look up request on processing list by unique ID */ static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique) { @@ -814,15 +806,15 @@ static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out, * it from the list and copy the rest of the buffer to the request. * The request is finished by calling request_end() */ -static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *off) +static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { int err; unsigned nbytes = iov_length(iov, nr_segs); struct fuse_req *req; struct fuse_out_header oh; struct fuse_copy_state cs; - struct fuse_conn *fc = fuse_get_conn(file); + struct fuse_conn *fc = fuse_get_conn(iocb->ki_filp); if (!fc) return -EPERM; @@ -898,15 +890,6 @@ static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov, return err; } -static ssize_t fuse_dev_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *off) -{ - struct iovec iov; - iov.iov_len = nbytes; - iov.iov_base = (char __user *) buf; - return fuse_dev_writev(file, &iov, 1, off); -} - static unsigned fuse_dev_poll(struct file *file, poll_table *wait) { unsigned mask = POLLOUT | POLLWRNORM; @@ -1041,10 +1024,10 @@ static int fuse_dev_fasync(int fd, struct file *file, int on) const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = fuse_dev_read, - .readv = fuse_dev_readv, - .write = fuse_dev_write, - .writev = fuse_dev_writev, + .read = do_sync_read, + .aio_read = fuse_dev_read, + .write = do_sync_write, + .aio_write = fuse_dev_write, .poll = fuse_dev_poll, .release = fuse_dev_release, .fasync = fuse_dev_fasync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 322e876c35ed..4908c38a5885 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -389,8 +389,6 @@ static const struct file_operations hostfs_file_fops = { .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .readv = generic_file_readv, - .writev = generic_file_writev, .write = generic_file_write, .mmap = generic_file_mmap, .open = hostfs_file_open, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 1c9745be5ada..f535f2911c12 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -108,8 +108,6 @@ const struct file_operations jfs_file_operations = { .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .readv = generic_file_readv, - .writev = generic_file_writev, .sendfile = generic_file_sendfile, .fsync = jfs_fsync, .release = jfs_release, diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 0c46f5c86b71..2f9b5a0953ff 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2298,11 +2298,9 @@ const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ .read = generic_file_read, /* Read from file. */ .aio_read = generic_file_aio_read, /* Async read from file. */ - .readv = generic_file_readv, /* Read from file. */ #ifdef NTFS_RW .write = ntfs_file_write, /* Write to file. */ .aio_write = ntfs_file_aio_write, /* Async write to file. */ - .writev = ntfs_file_writev, /* Write to file. */ /*.release = ,*/ /* Last file is closed. See fs/ext2/file.c:: ext2_release_file() for diff --git a/fs/pipe.c b/fs/pipe.c index f3b6f71e9d0b..2e60e1c8815e 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -218,9 +218,10 @@ static struct pipe_buf_operations anon_pipe_buf_ops = { }; static ssize_t -pipe_readv(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_read(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t pos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; int do_wakeup; @@ -330,17 +331,10 @@ redo: } static ssize_t -pipe_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = buf, .iov_len = count }; - - return pipe_readv(filp, &iov, 1, ppos); -} - -static ssize_t -pipe_writev(struct file *filp, const struct iovec *_iov, - unsigned long nr_segs, loff_t *ppos) +pipe_write(struct kiocb *iocb, const struct iovec *_iov, + unsigned long nr_segs, loff_t ppos) { + struct file *filp = iocb->ki_filp; struct inode *inode = filp->f_dentry->d_inode; struct pipe_inode_info *pipe; ssize_t ret; @@ -509,15 +503,6 @@ out: return ret; } -static ssize_t -pipe_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return pipe_writev(filp, &iov, 1, ppos); -} - static ssize_t bad_pipe_r(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { @@ -736,8 +721,8 @@ pipe_rdwr_open(struct inode *inode, struct file *filp) */ const struct file_operations read_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -749,8 +734,8 @@ const struct file_operations read_fifo_fops = { const struct file_operations write_fifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -760,10 +745,10 @@ const struct file_operations write_fifo_fops = { const struct file_operations rdwr_fifo_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, @@ -773,8 +758,8 @@ const struct file_operations rdwr_fifo_fops = { static struct file_operations read_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, + .read = do_sync_read, + .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, .ioctl = pipe_ioctl, @@ -786,8 +771,8 @@ static struct file_operations read_pipe_fops = { static struct file_operations write_pipe_fops = { .llseek = no_llseek, .read = bad_pipe_r, - .write = pipe_write, - .writev = pipe_writev, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, @@ -797,10 +782,10 @@ static struct file_operations write_pipe_fops = { static struct file_operations rdwr_pipe_fops = { .llseek = no_llseek, - .read = pipe_read, - .readv = pipe_readv, - .write = pipe_write, - .writev = pipe_writev, + .read = do_sync_read, + .aio_read = pipe_read, + .write = do_sync_write, + .aio_write = pipe_write, .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, diff --git a/fs/read_write.c b/fs/read_write.c index 679dd535380f..32d54cca9bd9 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,6 +15,7 @@ #include #include #include +#include "read_write.h" #include #include @@ -450,6 +451,62 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_UNUSED_SYMBOL(iov_shorten); /* June 2006 */ +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) +{ + struct kiocb kiocb; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_left = len; + kiocb.ki_nbytes = len; + + for (;;) { + ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); + if (ret != -EIOCBRETRY) + break; + wait_on_retry_sync_kiocb(&kiocb); + } + + if (ret == -EIOCBQUEUED) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + +/* Do it by hand, with file-ops */ +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn) +{ + struct iovec *vector = iov; + ssize_t ret = 0; + + while (nr_segs > 0) { + void __user *base; + size_t len; + ssize_t nr; + + base = vector->iov_base; + len = vector->iov_len; + vector++; + nr_segs--; + + nr = fn(filp, base, len, ppos); + + if (nr < 0) { + if (!ret) + ret = nr; + break; + } + ret += nr; + if (nr != len) + break; + } + + return ret; +} + /* A write operation does a read from user space and vice versa */ #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) @@ -457,12 +514,9 @@ static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, unsigned long nr_segs, loff_t *pos) { - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov=iovstack, *vector; + struct iovec *iov = iovstack; ssize_t ret; int seg; io_fn_t fn; @@ -532,39 +586,18 @@ static ssize_t do_readv_writev(int type, struct file *file, fnv = NULL; if (type == READ) { fn = file->f_op->read; - fnv = file->f_op->readv; + fnv = file->f_op->aio_read; } else { fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; + fnv = file->f_op->aio_write; } - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); + if (fnv) + ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, + pos, fnv); + else + ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn); - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } out: if (iov != iovstack) kfree(iov); @@ -585,7 +618,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_READ)) return -EBADF; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) return -EINVAL; return do_readv_writev(READ, file, vec, vlen, pos); @@ -598,7 +631,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) return -EINVAL; return do_readv_writev(WRITE, file, vec, vlen, pos); diff --git a/fs/read_write.h b/fs/read_write.h new file mode 100644 index 000000000000..d07b954c6e0c --- /dev/null +++ b/fs/read_write.h @@ -0,0 +1,14 @@ +/* + * This file is only for sharing some helpers from read_write.c with compat.c. + * Don't use anywhere else. + */ + + +typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); + +ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn); +ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, + unsigned long nr_segs, loff_t *ppos, io_fn_t fn); diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 4737971c6a39..d93d8dd1958d 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -123,96 +123,6 @@ xfs_file_aio_write_invis( return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos); } -STATIC inline ssize_t -__xfs_file_readv( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - rval = bhv_vop_read(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_readv( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_readv_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_readv(file, iov, IO_INVIS, nr_segs, ppos); -} - -STATIC inline ssize_t -__xfs_file_writev( - struct file *file, - const struct iovec *iov, - int ioflags, - unsigned long nr_segs, - loff_t *ppos) -{ - struct inode *inode = file->f_mapping->host; - bhv_vnode_t *vp = vn_from_inode(inode); - struct kiocb kiocb; - ssize_t rval; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - if (unlikely(file->f_flags & O_DIRECT)) - ioflags |= IO_ISDIRECT; - - rval = bhv_vop_write(vp, &kiocb, iov, nr_segs, - &kiocb.ki_pos, ioflags, NULL); - - *ppos = kiocb.ki_pos; - return rval; -} - -STATIC ssize_t -xfs_file_writev( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_writev(file, iov, 0, nr_segs, ppos); -} - -STATIC ssize_t -xfs_file_writev_invis( - struct file *file, - const struct iovec *iov, - unsigned long nr_segs, - loff_t *ppos) -{ - return __xfs_file_writev(file, iov, IO_INVIS, nr_segs, ppos); -} - STATIC ssize_t xfs_file_sendfile( struct file *filp, @@ -540,8 +450,6 @@ const struct file_operations xfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv, - .writev = xfs_file_writev, .aio_read = xfs_file_aio_read, .aio_write = xfs_file_aio_write, .sendfile = xfs_file_sendfile, @@ -565,8 +473,6 @@ const struct file_operations xfs_invis_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, - .readv = xfs_file_readv_invis, - .writev = xfs_file_writev_invis, .aio_read = xfs_file_aio_read_invis, .aio_write = xfs_file_aio_write_invis, .sendfile = xfs_file_sendfile_invis, diff --git a/include/linux/fs.h b/include/linux/fs.h index 257bae16f545..afb6e6f89a01 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1113,8 +1113,6 @@ struct file_operations { int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -1734,10 +1732,6 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t remote_llseek(struct file *file, loff_t offset, int origin); diff --git a/mm/filemap.c b/mm/filemap.c index f6c1d22b504f..48497094ae83 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2421,42 +2421,6 @@ ssize_t generic_file_write(struct file *file, const char __user *buf, } EXPORT_SYMBOL(generic_file_write); -ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_readv); - -ssize_t generic_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_writev); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. diff --git a/net/socket.c b/net/socket.c index df92e4252749..01918f7a301a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -110,10 +110,6 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_readv(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); -static ssize_t sock_writev(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); @@ -136,8 +132,6 @@ static struct file_operations socket_file_ops = { .open = sock_no_open, /* special open code to disallow open via /proc */ .release = sock_close, .fasync = sock_fasync, - .readv = sock_readv, - .writev = sock_writev, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, }; @@ -700,23 +694,6 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); } -static ssize_t sock_readv(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb iocb; - struct sock_iocb siocb; - struct msghdr msg; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_read(&msg, &iocb, file, iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -759,23 +736,6 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, return __sock_sendmsg(iocb, sock, msg, size); } -static ssize_t sock_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct msghdr msg; - struct kiocb iocb; - struct sock_iocb siocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - iocb.private = &siocb; - - ret = do_sock_write(&msg, &iocb, file, iov, nr_segs); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 891d7140553c..37b4b10850ae 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2852,8 +2852,8 @@ static ssize_t snd_pcm_write(struct file *file, const char __user *buf, return result; } -static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; @@ -2864,22 +2864,22 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, return -ENXIO); runtime = substream->runtime; if (runtime->status->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; - if (count > 1024 || count != runtime->channels) + if (nr_segs > 1024 || nr_segs != runtime->channels) return -EINVAL; - if (!frame_aligned(runtime, _vector->iov_len)) + if (!frame_aligned(runtime, iov->iov_len)) return -EINVAL; - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_readv(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -2887,8 +2887,8 @@ static ssize_t snd_pcm_readv(struct file *file, const struct iovec *_vector, return result; } -static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, - unsigned long count, loff_t * offset) +static ssize_t snd_pcm_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; @@ -2898,7 +2898,7 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, void __user **bufs; snd_pcm_uframes_t frames; - pcm_file = file->private_data; + pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; snd_assert(substream != NULL, result = -ENXIO; goto end); runtime = substream->runtime; @@ -2906,17 +2906,17 @@ static ssize_t snd_pcm_writev(struct file *file, const struct iovec *_vector, result = -EBADFD; goto end; } - if (count > 128 || count != runtime->channels || - !frame_aligned(runtime, _vector->iov_len)) { + if (nr_segs > 128 || nr_segs != runtime->channels || + !frame_aligned(runtime, iov->iov_len)) { result = -EINVAL; goto end; } - frames = bytes_to_samples(runtime, _vector->iov_len); - bufs = kmalloc(sizeof(void *) * count, GFP_KERNEL); + frames = bytes_to_samples(runtime, iov->iov_len); + bufs = kmalloc(sizeof(void *) * nr_segs, GFP_KERNEL); if (bufs == NULL) return -ENOMEM; - for (i = 0; i < count; ++i) - bufs[i] = _vector[i].iov_base; + for (i = 0; i < nr_segs; ++i) + bufs[i] = iov[i].iov_base; result = snd_pcm_lib_writev(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); @@ -3426,7 +3426,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .write = snd_pcm_write, - .writev = snd_pcm_writev, + .aio_write = snd_pcm_aio_write, .open = snd_pcm_playback_open, .release = snd_pcm_release, .poll = snd_pcm_playback_poll, @@ -3438,7 +3438,7 @@ struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .read = snd_pcm_read, - .readv = snd_pcm_readv, + .aio_read = snd_pcm_aio_read, .open = snd_pcm_capture_open, .release = snd_pcm_release, .poll = snd_pcm_capture_poll, -- cgit v1.3-8-gc7d7 From 543ade1fc901db4c3dbe9fb27241fb977f1f3eea Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:48 -0700 Subject: [PATCH] Streamline generic_file_* interfaces and filemap cleanups This patch cleans up generic_file_*_read/write() interfaces. Christoph Hellwig gave me the idea for this clean ups. In a nutshell, all filesystems should set .aio_read/.aio_write methods and use do_sync_read/ do_sync_write() as their .read/.write methods. This allows us to cleanup all variants of generic_file_* routines. Final available interfaces: generic_file_aio_read() - read handler generic_file_aio_write() - write handler generic_file_aio_write_nolock() - no lock write handler __generic_file_aio_write_nolock() - internal worker routine Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/raw.c | 15 ++------ fs/adfs/file.c | 6 ++-- fs/affs/file.c | 6 ++-- fs/bfs/file.c | 6 ++-- fs/block_dev.c | 12 ++----- fs/ext2/file.c | 4 +-- fs/fuse/file.c | 6 ++-- fs/hfs/inode.c | 6 ++-- fs/hfsplus/inode.c | 6 ++-- fs/hostfs/hostfs_kern.c | 4 +-- fs/hpfs/file.c | 6 ++-- fs/jffs/inode-v23.c | 6 ++-- fs/jffs2/file.c | 6 ++-- fs/jfs/file.c | 4 +-- fs/minix/file.c | 6 ++-- fs/ntfs/file.c | 2 +- fs/qnx4/file.c | 6 ++-- fs/ramfs/file-mmu.c | 6 ++-- fs/ramfs/file-nommu.c | 6 ++-- fs/read_write.c | 3 +- fs/smbfs/file.c | 24 ++++++++----- fs/sysv/file.c | 6 ++-- fs/udf/file.c | 16 +++++---- fs/ufs/file.c | 6 ++-- fs/xfs/linux-2.6/xfs_lrw.c | 4 ++- include/linux/fs.h | 5 --- mm/filemap.c | 87 +++------------------------------------------- 27 files changed, 105 insertions(+), 165 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 490db531e2d8..89b718e326e5 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -238,21 +238,10 @@ out: return err; } -static ssize_t raw_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { - .iov_base = (char __user *)buf, - .iov_len = count - }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - static const struct file_operations raw_fops = { - .read = generic_file_read, + .read = do_sync_read, .aio_read = generic_file_aio_read, - .write = raw_file_write, + .write = do_sync_write, .aio_write = generic_file_aio_write_nolock, .open = raw_open, .release= raw_release, diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 1014b9f2117b..6101ea679cb1 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -27,10 +27,12 @@ const struct file_operations adfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .fsync = file_fsync, - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .sendfile = generic_file_sendfile, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 3de8590e4f6a..05b5e22de759 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -27,8 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp); const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = affs_file_open, .release = affs_file_release, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 3d5aca28a0a0..a9164a87f8de 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -19,8 +19,10 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, }; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0f143094ef1d..bc8f27cc4483 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1154,14 +1154,6 @@ static int blkdev_close(struct inode * inode, struct file * filp) return blkdev_put(bdev); } -static ssize_t blkdev_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - - return generic_file_write_nolock(file, &local_iov, 1, ppos); -} - static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); @@ -1181,8 +1173,8 @@ const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, - .read = generic_file_read, - .write = blkdev_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write_nolock, .mmap = generic_file_mmap, diff --git a/fs/ext2/file.c b/fs/ext2/file.c index e893e2be9ed4..2dba473c524a 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -41,8 +41,8 @@ static int ext2_release_file (struct inode * inode, struct file * filp) */ const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .ioctl = ext2_ioctl, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5c4fcd1dbf59..183626868eea 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -753,8 +753,10 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl) static const struct file_operations fuse_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = fuse_file_mmap, .open = fuse_open, .flush = fuse_flush, diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d05641c35fc9..02f5573e0349 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -601,8 +601,10 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 0eb1a6092668..9e3675249633 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -282,8 +282,10 @@ static struct inode_operations hfsplus_file_inode_operations = { static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, .fsync = file_fsync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 4908c38a5885..b6bd33ca3731 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -385,11 +385,11 @@ int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync) static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .write = generic_file_write, + .write = do_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, .release = NULL, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index d9eb19b7b8ae..8b94d24855f0 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -113,7 +113,7 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, { ssize_t retval; - retval = generic_file_write(file, buf, count, ppos); + retval = do_sync_write(file, buf, count, ppos); if (retval > 0) hpfs_i(file->f_dentry->d_inode)->i_dirty = 1; return retval; @@ -122,8 +122,10 @@ static ssize_t hpfs_file_write(struct file *file, const char __user *buf, const struct file_operations hpfs_file_ops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .write = hpfs_file_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index f5cf9c93e243..068ef0de8de2 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -1632,8 +1632,10 @@ static const struct file_operations jffs_file_operations = { .open = generic_file_open, .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs_fsync, diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 3ed6e3e120b6..242875f77cb3 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -42,8 +42,10 @@ const struct file_operations jffs2_file_operations = { .llseek = generic_file_llseek, .open = generic_file_open, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .ioctl = jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index f535f2911c12..976e90dc2d1b 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -103,8 +103,8 @@ struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = generic_file_write, - .read = generic_file_read, + .write = do_sync_write, + .read = do_sync_read, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, diff --git a/fs/minix/file.c b/fs/minix/file.c index 420b32882a10..40eac2e60d25 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -17,8 +17,10 @@ int minix_sync_file(struct file *, struct dentry *, int); const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = minix_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 2f9b5a0953ff..ae2fe0016d2c 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2296,7 +2296,7 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ - .read = generic_file_read, /* Read from file. */ + .read = do_sync_read, /* Read from file. */ .aio_read = generic_file_aio_read, /* Async read from file. */ #ifdef NTFS_RW .write = ntfs_file_write, /* Write to file. */ diff --git a/fs/qnx4/file.c b/fs/qnx4/file.c index 62af4b1348bd..467e5ac7280e 100644 --- a/fs/qnx4/file.c +++ b/fs/qnx4/file.c @@ -22,11 +22,13 @@ const struct file_operations qnx4_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, .sendfile = generic_file_sendfile, #ifdef CONFIG_QNX4FS_RW - .write = generic_file_write, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = qnx4_sync_file, #endif }; diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 86f14cacf641..0947fb57dcf3 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -33,8 +33,10 @@ const struct address_space_operations ramfs_aops = { }; const struct file_operations ramfs_file_operations = { - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 677139b48e00..bfe5dbf1002e 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -36,8 +36,10 @@ const struct address_space_operations ramfs_aops = { const struct file_operations ramfs_file_operations = { .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .fsync = simple_sync_file, .sendfile = generic_file_sendfile, .llseek = generic_file_llseek, diff --git a/fs/read_write.c b/fs/read_write.c index 32d54cca9bd9..4ed839bcb91c 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -22,7 +22,8 @@ const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .mmap = generic_file_readonly_mmap, .sendfile = generic_file_sendfile, }; diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index dae67048baba..50784d13c87b 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -214,13 +214,15 @@ smb_updatepage(struct file *file, struct page *page, unsigned long offset, } static ssize_t -smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) +smb_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t status; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); status = smb_revalidate_inode(dentry); if (status) { @@ -233,7 +235,7 @@ smb_file_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) (long)dentry->d_inode->i_size, dentry->d_inode->i_flags, dentry->d_inode->i_atime); - status = generic_file_read(file, buf, count, ppos); + status = generic_file_aio_read(iocb, iov, nr_segs, pos); out: return status; } @@ -317,14 +319,16 @@ const struct address_space_operations smb_file_aops = { * Write to a file (through the page cache). */ static ssize_t -smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +smb_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file * file = iocb->ki_filp; struct dentry * dentry = file->f_dentry; ssize_t result; VERBOSE("file %s/%s, count=%lu@%lu\n", DENTRY_PATH(dentry), - (unsigned long) count, (unsigned long) *ppos); + (unsigned long) iocb->ki_left, (unsigned long) pos); result = smb_revalidate_inode(dentry); if (result) { @@ -337,8 +341,8 @@ smb_file_write(struct file *file, const char __user *buf, size_t count, loff_t * if (result) goto out; - if (count > 0) { - result = generic_file_write(file, buf, count, ppos); + if (iocb->ki_left > 0) { + result = generic_file_aio_write(iocb, iov, nr_segs, pos); VERBOSE("pos=%ld, size=%ld, mtime=%ld, atime=%ld\n", (long) file->f_pos, (long) dentry->d_inode->i_size, dentry->d_inode->i_mtime, dentry->d_inode->i_atime); @@ -402,8 +406,10 @@ smb_file_permission(struct inode *inode, int mask, struct nameidata *nd) const struct file_operations smb_file_operations = { .llseek = remote_llseek, - .read = smb_file_read, - .write = smb_file_write, + .read = do_sync_read, + .aio_read = smb_file_aio_read, + .write = do_sync_write, + .aio_write = smb_file_aio_write, .ioctl = smb_ioctl, .mmap = smb_file_mmap, .open = smb_file_open, diff --git a/fs/sysv/file.c b/fs/sysv/file.c index a59e303135fa..47a4b728f15b 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -21,8 +21,10 @@ */ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = sysv_sync_file, .sendfile = generic_file_sendfile, diff --git a/fs/udf/file.c b/fs/udf/file.c index a59e5f33daf6..7aedd552cba1 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -103,19 +103,21 @@ const struct address_space_operations udf_adinicb_aops = { .commit_write = udf_adinicb_commit_write, }; -static ssize_t udf_file_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t ppos) { ssize_t retval; + struct file *file = iocb->ki_filp; struct inode *inode = file->f_dentry->d_inode; int err, pos; + size_t count = iocb->ki_left; if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB) { if (file->f_flags & O_APPEND) pos = inode->i_size; else - pos = *ppos; + pos = ppos; if (inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + pos + count)) @@ -136,7 +138,7 @@ static ssize_t udf_file_write(struct file * file, const char __user * buf, } } - retval = generic_file_write(file, buf, count, ppos); + retval = generic_file_aio_write(iocb, iov, nr_segs, ppos); if (retval > 0) mark_inode_dirty(inode); @@ -249,11 +251,13 @@ static int udf_release_file(struct inode * inode, struct file * filp) } const struct file_operations udf_file_operations = { - .read = generic_file_read, + .read = do_sync_read, + .aio_read = generic_file_aio_read, .ioctl = udf_ioctl, .open = generic_file_open, .mmap = generic_file_mmap, - .write = udf_file_write, + .write = do_sync_write, + .aio_write = udf_file_aio_write, .release = udf_release_file, .fsync = udf_fsync_file, .sendfile = generic_file_sendfile, diff --git a/fs/ufs/file.c b/fs/ufs/file.c index a9c6e5f04fae..1e096323bad4 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -53,8 +53,10 @@ static int ufs_sync_file(struct file *file, struct dentry *dentry, int datasync) const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, - .read = generic_file_read, - .write = generic_file_write, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = generic_file_open, .fsync = ufs_sync_file, diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 55992b40353c..fa842f1c9fa2 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -279,7 +279,9 @@ xfs_read( xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore, (void *)iovp, segs, *offset, ioflags); - ret = __generic_file_aio_read(iocb, iovp, segs, offset); + + iocb->ki_pos = *offset; + ret = generic_file_aio_read(iocb, iovp, segs, *offset); if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO)) ret = wait_on_sync_kiocb(iocb); if (ret > 0) diff --git a/include/linux/fs.h b/include/linux/fs.h index afb6e6f89a01..011129f8803e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1699,11 +1699,8 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, unsigned long, loff_t); @@ -1713,8 +1710,6 @@ extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, loff_t *, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, diff --git a/mm/filemap.c b/mm/filemap.c index 48497094ae83..ec469235985d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1149,13 +1149,14 @@ success: * that can use the page cache directly. */ ssize_t -__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg; size_t count; + loff_t *ppos = &iocb->ki_pos; count = 0; for (seg = 0; seg < nr_segs; seg++) { @@ -1179,7 +1180,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { - loff_t pos = *ppos, size; + loff_t size; struct address_space *mapping; struct inode *inode; @@ -1223,32 +1224,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } -EXPORT_SYMBOL(__generic_file_aio_read); - -ssize_t -generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, iov, nr_segs, &iocb->ki_pos); -} EXPORT_SYMBOL(generic_file_aio_read); -ssize_t -generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_read); - int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) { ssize_t written; @@ -2339,38 +2316,6 @@ ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, } EXPORT_SYMBOL(generic_file_aio_write_nolock); -static ssize_t -__generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} - -ssize_t -generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, *ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(generic_file_write_nolock); - ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -2397,30 +2342,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } EXPORT_SYMBOL(generic_file_aio_write); -ssize_t generic_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_write); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. -- cgit v1.3-8-gc7d7 From eed4e51fb60c3863c134a5e9f6006b29805ead97 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:49 -0700 Subject: [PATCH] Add vector AIO support This work is initially done by Zach Brown to add support for vectored aio. These are the core changes for AIO to support IOCB_CMD_PREADV/IOCB_CMD_PWRITEV. [akpm@osdl.org: huge build fix] Signed-off-by: Zach Brown Signed-off-by: Christoph Hellwig Signed-off-by: Badari Pulavarty Acked-by: Benjamin LaHaise Acked-by: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/aio.c | 171 +++++++++++++++++++++++++++++++++--------------- fs/read_write.c | 129 +++++++++++++++++++++--------------- include/linux/aio.h | 4 ++ include/linux/aio_abi.h | 2 + include/linux/fs.h | 5 ++ 5 files changed, 203 insertions(+), 108 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/aio.c b/fs/aio.c index 27ff56540c73..2e0d1505ee36 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -415,6 +415,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx) req->ki_retry = NULL; req->ki_dtor = NULL; req->private = NULL; + req->ki_iovec = NULL; INIT_LIST_HEAD(&req->ki_run_list); /* Check if the completion queue has enough free space to @@ -460,6 +461,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) if (req->ki_dtor) req->ki_dtor(req); + if (req->ki_iovec != &req->ki_inline_vec) + kfree(req->ki_iovec); kmem_cache_free(kiocb_cachep, req); ctx->reqs_active--; @@ -1301,69 +1304,63 @@ asmlinkage long sys_io_destroy(aio_context_t ctx) return -EINVAL; } -/* - * aio_p{read,write} are the default ki_retry methods for - * IO_CMD_P{READ,WRITE}. They maintains kiocb retry state around potentially - * multiple calls to f_op->aio_read(). They loop around partial progress - * instead of returning -EIOCBRETRY because they don't have the means to call - * kick_iocb(). - */ -static ssize_t aio_pread(struct kiocb *iocb) +static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret = 0; - - do { - iocb->ki_inline_vec.iov_base = iocb->ki_buf; - iocb->ki_inline_vec.iov_len = iocb->ki_left; - - ret = file->f_op->aio_read(iocb, &iocb->ki_inline_vec, - 1, iocb->ki_pos); - /* - * Can't just depend on iocb->ki_left to determine - * whether we are done. This may have been a short read. - */ - if (ret > 0) { - iocb->ki_buf += ret; - iocb->ki_left -= ret; + struct iovec *iov = &iocb->ki_iovec[iocb->ki_cur_seg]; + + BUG_ON(ret <= 0); + + while (iocb->ki_cur_seg < iocb->ki_nr_segs && ret > 0) { + ssize_t this = min((ssize_t)iov->iov_len, ret); + iov->iov_base += this; + iov->iov_len -= this; + iocb->ki_left -= this; + ret -= this; + if (iov->iov_len == 0) { + iocb->ki_cur_seg++; + iov++; } + } - /* - * For pipes and sockets we return once we have some data; for - * regular files we retry till we complete the entire read or - * find that we can't read any more data (e.g short reads). - */ - } while (ret > 0 && iocb->ki_left > 0 && - !S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)); - - /* This means we must have transferred all that we could */ - /* No need to retry anymore */ - if ((ret == 0) || (iocb->ki_left == 0)) - ret = iocb->ki_nbytes - iocb->ki_left; - - return ret; + /* the caller should not have done more io than what fit in + * the remaining iovecs */ + BUG_ON(ret > 0 && iocb->ki_left == 0); } -/* see aio_pread() */ -static ssize_t aio_pwrite(struct kiocb *iocb) +static ssize_t aio_rw_vect_retry(struct kiocb *iocb) { struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t (*rw_op)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); ssize_t ret = 0; + unsigned short opcode; + + if ((iocb->ki_opcode == IOCB_CMD_PREADV) || + (iocb->ki_opcode == IOCB_CMD_PREAD)) { + rw_op = file->f_op->aio_read; + opcode = IOCB_CMD_PREADV; + } else { + rw_op = file->f_op->aio_write; + opcode = IOCB_CMD_PWRITEV; + } do { - iocb->ki_inline_vec.iov_base = iocb->ki_buf; - iocb->ki_inline_vec.iov_len = iocb->ki_left; - - ret = file->f_op->aio_write(iocb, &iocb->ki_inline_vec, - 1, iocb->ki_pos); - if (ret > 0) { - iocb->ki_buf += ret; - iocb->ki_left -= ret; - } - } while (ret > 0 && iocb->ki_left > 0); + ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg], + iocb->ki_nr_segs - iocb->ki_cur_seg, + iocb->ki_pos); + if (ret > 0) + aio_advance_iovec(iocb, ret); + + /* retry all partial writes. retry partial reads as long as its a + * regular file. */ + } while (ret > 0 && iocb->ki_left > 0 && + (opcode == IOCB_CMD_PWRITEV || + (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)))); + /* This means we must have transferred all that we could */ + /* No need to retry anymore */ if ((ret == 0) || (iocb->ki_left == 0)) ret = iocb->ki_nbytes - iocb->ki_left; @@ -1390,6 +1387,38 @@ static ssize_t aio_fsync(struct kiocb *iocb) return ret; } +static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb) +{ + ssize_t ret; + + ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, + kiocb->ki_nbytes, 1, + &kiocb->ki_inline_vec, &kiocb->ki_iovec); + if (ret < 0) + goto out; + + kiocb->ki_nr_segs = kiocb->ki_nbytes; + kiocb->ki_cur_seg = 0; + /* ki_nbytes/left now reflect bytes instead of segs */ + kiocb->ki_nbytes = ret; + kiocb->ki_left = ret; + + ret = 0; +out: + return ret; +} + +static ssize_t aio_setup_single_vector(struct kiocb *kiocb) +{ + kiocb->ki_iovec = &kiocb->ki_inline_vec; + kiocb->ki_iovec->iov_base = kiocb->ki_buf; + kiocb->ki_iovec->iov_len = kiocb->ki_left; + kiocb->ki_nr_segs = 1; + kiocb->ki_cur_seg = 0; + kiocb->ki_nbytes = kiocb->ki_left; + return 0; +} + /* * aio_setup_iocb: * Performs the initial checks and aio retry method @@ -1412,9 +1441,12 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb) ret = security_file_permission(file, MAY_READ); if (unlikely(ret)) break; + ret = aio_setup_single_vector(kiocb); + if (ret) + break; ret = -EINVAL; if (file->f_op->aio_read) - kiocb->ki_retry = aio_pread; + kiocb->ki_retry = aio_rw_vect_retry; break; case IOCB_CMD_PWRITE: ret = -EBADF; @@ -1427,9 +1459,40 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb) ret = security_file_permission(file, MAY_WRITE); if (unlikely(ret)) break; + ret = aio_setup_single_vector(kiocb); + if (ret) + break; + ret = -EINVAL; + if (file->f_op->aio_write) + kiocb->ki_retry = aio_rw_vect_retry; + break; + case IOCB_CMD_PREADV: + ret = -EBADF; + if (unlikely(!(file->f_mode & FMODE_READ))) + break; + ret = security_file_permission(file, MAY_READ); + if (unlikely(ret)) + break; + ret = aio_setup_vectored_rw(READ, kiocb); + if (ret) + break; + ret = -EINVAL; + if (file->f_op->aio_read) + kiocb->ki_retry = aio_rw_vect_retry; + break; + case IOCB_CMD_PWRITEV: + ret = -EBADF; + if (unlikely(!(file->f_mode & FMODE_WRITE))) + break; + ret = security_file_permission(file, MAY_WRITE); + if (unlikely(ret)) + break; + ret = aio_setup_vectored_rw(WRITE, kiocb); + if (ret) + break; ret = -EINVAL; if (file->f_op->aio_write) - kiocb->ki_retry = aio_pwrite; + kiocb->ki_retry = aio_rw_vect_retry; break; case IOCB_CMD_FDSYNC: ret = -EINVAL; diff --git a/fs/read_write.c b/fs/read_write.c index 4ed839bcb91c..f792000a28e6 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -511,6 +511,74 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, /* A write operation does a read from user space and vice versa */ #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer) + { + unsigned long seg; + ssize_t ret; + struct iovec *iov = fast_pointer; + + /* + * SuS says "The readv() function *may* fail if the iovcnt argument + * was less than or equal to 0, or greater than {IOV_MAX}. Linux has + * traditionally returned zero for zero segments, so... + */ + if (nr_segs == 0) { + ret = 0; + goto out; + } + + /* + * First get the "struct iovec" from user memory and + * verify all the pointers + */ + if (nr_segs > UIO_MAXIOV) { + ret = -EINVAL; + goto out; + } + if (nr_segs > fast_segs) { + iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); + if (iov == NULL) { + ret = -ENOMEM; + goto out; + } + } + if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) { + ret = -EFAULT; + goto out; + } + + /* + * According to the Single Unix Specification we should return EINVAL + * if an element length is < 0 when cast to ssize_t or if the + * total length would overflow the ssize_t return value of the + * system call. + */ + ret = 0; + for (seg = 0; seg < nr_segs; seg++) { + void __user *buf = iov[seg].iov_base; + ssize_t len = (ssize_t)iov[seg].iov_len; + + /* see if we we're about to use an invalid len or if + * it's about to overflow ssize_t */ + if (len < 0 || (ret + len < ret)) { + ret = -EINVAL; + goto out; + } + if (unlikely(!access_ok(vrfy_dir(type), buf, len))) { + ret = -EFAULT; + goto out; + } + + ret += len; + } +out: + *ret_pointer = iov; + return ret; +} + static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, unsigned long nr_segs, loff_t *pos) @@ -519,64 +587,20 @@ static ssize_t do_readv_writev(int type, struct file *file, struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; ssize_t ret; - int seg; io_fn_t fn; iov_fn_t fnv; - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - ret = 0; - if (nr_segs == 0) - goto out; - - /* - * First get the "struct iovec" from user memory and - * verify all the pointers - */ - ret = -EINVAL; - if (nr_segs > UIO_MAXIOV) - goto out; - if (!file->f_op) - goto out; - if (nr_segs > UIO_FASTIOV) { - ret = -ENOMEM; - iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); - if (!iov) - goto out; - } - ret = -EFAULT; - if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) + if (!file->f_op) { + ret = -EINVAL; goto out; + } - /* - * Single unix specification: - * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. The total length is fitting an ssize_t - * - * Be careful here because iov_len is a size_t not an ssize_t - */ - tot_len = 0; - ret = -EINVAL; - for (seg = 0; seg < nr_segs; seg++) { - void __user *buf = iov[seg].iov_base; - ssize_t len = (ssize_t)iov[seg].iov_len; - - if (len < 0) /* size_t not fitting an ssize_t .. */ - goto out; - if (unlikely(!access_ok(vrfy_dir(type), buf, len))) - goto Efault; - tot_len += len; - if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */ - goto out; - } - if (tot_len == 0) { - ret = 0; + ret = rw_copy_check_uvector(type, uvector, nr_segs, + ARRAY_SIZE(iovstack), iovstack, &iov); + if (ret <= 0) goto out; - } + tot_len = ret; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; @@ -609,9 +633,6 @@ out: fsnotify_modify(file->f_dentry); } return ret; -Efault: - ret = -EFAULT; - goto out; } ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, diff --git a/include/linux/aio.h b/include/linux/aio.h index 58349e58b749..5722568fc71e 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -7,6 +7,7 @@ #include #include +#include #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 @@ -114,6 +115,9 @@ struct kiocb { long ki_kicked; /* just for testing */ long ki_queued; /* just for testing */ struct iovec ki_inline_vec; /* inline vector */ + struct iovec *ki_iovec; + unsigned long ki_nr_segs; + unsigned long ki_cur_seg; struct list_head ki_list; /* the aio core uses this * for cancellation */ diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h index 30fdcc89d142..3466b1d0ffd2 100644 --- a/include/linux/aio_abi.h +++ b/include/linux/aio_abi.h @@ -41,6 +41,8 @@ enum { * IOCB_CMD_POLL = 5, */ IOCB_CMD_NOOP = 6, + IOCB_CMD_PREADV = 7, + IOCB_CMD_PWRITEV = 8, }; /* read() from /dev/aio returns these structures. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 011129f8803e..4bb70871873f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1150,6 +1150,11 @@ struct inode_operations { struct seq_file; +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, -- cgit v1.3-8-gc7d7 From 9a53c3a783c2fa9b969628e65695c11c3e51e673 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:03 -0700 Subject: [PATCH] r/o bind mounts: unlink: monitor i_nlink When a filesystem decrements i_nlink to zero, it means that a write must be performed in order to drop the inode from the filesystem. We're shortly going to have keep filesystems from being remounted r/o between the time that this i_nlink decrement and that write occurs. So, add a little helper function to do the decrements. We'll tie into it in a bit to note when i_nlink hits zero. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/usb/core/inode.c | 7 ++++--- fs/autofs/root.c | 2 +- fs/autofs4/root.c | 2 +- fs/bfs/dir.c | 9 +++------ fs/cifs/inode.c | 10 +++++----- fs/coda/dir.c | 4 ++-- fs/ext2/namei.c | 2 +- fs/ext3/namei.c | 14 +++++++------- fs/hfs/dir.c | 2 +- fs/hfsplus/dir.c | 2 +- fs/hpfs/namei.c | 6 +++--- fs/jffs/inode-v23.c | 3 +-- fs/jffs2/dir.c | 6 +++--- fs/jfs/namei.c | 14 ++++++-------- fs/libfs.c | 10 +++++----- fs/minix/namei.c | 2 +- fs/msdos/namei.c | 9 ++++----- fs/nfs/dir.c | 6 +++--- fs/ocfs2/namei.c | 4 ++-- fs/qnx4/namei.c | 6 ++---- fs/reiserfs/namei.c | 6 +++--- fs/sysv/namei.c | 2 +- fs/udf/namei.c | 18 ++++++------------ fs/ufs/namei.c | 2 +- fs/vfat/namei.c | 9 ++++----- include/linux/fs.h | 7 ++++++- ipc/mqueue.c | 2 +- mm/shmem.c | 10 +++++----- 28 files changed, 83 insertions(+), 93 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index df3d152f0493..88002e45a6b4 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -332,7 +332,7 @@ static int usbfs_unlink (struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; mutex_lock(&inode->i_mutex); - dentry->d_inode->i_nlink--; + drop_nlink(dentry->d_inode); dput(dentry); mutex_unlock(&inode->i_mutex); d_delete(dentry); @@ -347,10 +347,11 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry) mutex_lock(&inode->i_mutex); dentry_unhash(dentry); if (usbfs_empty(dentry)) { - dentry->d_inode->i_nlink -= 2; + drop_nlink(dentry->d_inode); + drop_nlink(dentry->d_inode); dput(dentry); inode->i_flags |= S_DEAD; - dir->i_nlink--; + drop_nlink(dir); error = 0; } mutex_unlock(&inode->i_mutex); diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 9cac08d6a873..54ad70731927 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -414,7 +414,7 @@ static int autofs_root_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_time = (unsigned long)(struct autofs_dir_ent *)NULL; autofs_hash_delete(ent); - dir->i_nlink--; + drop_nlink(dir); d_drop(dentry); unlock_kernel(); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 563ef9d7da9f..348bec0982b0 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -676,7 +676,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_nlink = 0; if (dir->i_nlink) - dir->i_nlink--; + drop_nlink(dir); return 0; } diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index dcf04cb13283..ce05d1643dd1 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -117,8 +117,7 @@ static int bfs_create(struct inode * dir, struct dentry * dentry, int mode, err = bfs_add_entry(dir, dentry->d_name.name, dentry->d_name.len, inode->i_ino); if (err) { - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); iput(inode); unlock_kernel(); return err; @@ -196,9 +195,8 @@ static int bfs_unlink(struct inode * dir, struct dentry * dentry) mark_buffer_dirty(bh); dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); error = 0; out_brelse: @@ -249,9 +247,8 @@ static int bfs_rename(struct inode * old_dir, struct dentry * old_dentry, old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(old_dir); if (new_inode) { - new_inode->i_nlink--; new_inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } mark_buffer_dirty(old_bh); error = 0; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 05f874c7441b..74441a17e186 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -590,7 +590,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) if (!rc) { if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } else if (rc == -ENOENT) { d_drop(direntry); } else if (rc == -ETXTBSY) { @@ -609,7 +609,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); CIFSSMBClose(xid, pTcon, netfid); if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } } else if (rc == -EACCES) { /* try only if r/o attribute set in local lookup data? */ @@ -663,7 +663,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); if (!rc) { if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } else if (rc == -ETXTBSY) { int oplock = FALSE; __u16 netfid; @@ -684,7 +684,7 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry) CIFS_MOUNT_MAP_SPECIAL_CHR); CIFSSMBClose(xid, pTcon, netfid); if (direntry->d_inode) - direntry->d_inode->i_nlink--; + drop_nlink(direntry->d_inode); } /* BB if rc = -ETXTBUSY goto the rename logic BB */ } @@ -816,7 +816,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (!rc) { - inode->i_nlink--; + drop_nlink(inode); i_size_write(direntry->d_inode,0); direntry->d_inode->i_nlink = 0; } diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 8651ea6a23b7..0a2fd8bb7579 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -367,7 +367,7 @@ int coda_unlink(struct inode *dir, struct dentry *de) } coda_dir_changed(dir, 0); - de->d_inode->i_nlink--; + drop_nlink(de->d_inode); unlock_kernel(); return 0; @@ -394,7 +394,7 @@ int coda_rmdir(struct inode *dir, struct dentry *de) } coda_dir_changed(dir, -1); - de->d_inode->i_nlink--; + drop_nlink(de->d_inode); d_delete(de); unlock_kernel(); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 4ca824985321..e1af5b4cf80c 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -326,7 +326,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, ext2_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 235e77b52ea5..14c55adfae83 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1621,7 +1621,7 @@ static inline void ext3_inc_count(handle_t *handle, struct inode *inode) static inline void ext3_dec_count(handle_t *handle, struct inode *inode) { - inode->i_nlink--; + drop_nlink(inode); } static int ext3_add_nondir(handle_t *handle, @@ -1743,7 +1743,7 @@ retry: inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize; dir_block = ext3_bread (handle, inode, 0, 1, &err); if (!dir_block) { - inode->i_nlink--; /* is this nlink == 0? */ + drop_nlink(inode); /* is this nlink == 0? */ ext3_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -2053,7 +2053,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry) ext3_orphan_add(handle, inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; ext3_mark_inode_dirty(handle, inode); - dir->i_nlink--; + drop_nlink(dir); ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); @@ -2104,7 +2104,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry) dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); - inode->i_nlink--; + drop_nlink(inode); if (!inode->i_nlink) ext3_orphan_add(handle, inode); inode->i_ctime = dir->i_ctime; @@ -2326,7 +2326,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, } if (new_inode) { - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = CURRENT_TIME_SEC; } old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; @@ -2337,9 +2337,9 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext3_journal_dirty_metadata"); ext3_journal_dirty_metadata(handle, dir_bh); - old_dir->i_nlink--; + drop_nlink(old_dir); if (new_inode) { - new_inode->i_nlink--; + drop_nlink(new_inode); } else { new_dir->i_nlink++; ext3_update_dx_flag(new_dir); diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 7cd8cc03aea7..cfef6ad529a7 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -246,7 +246,7 @@ static int hfs_unlink(struct inode *dir, struct dentry *dentry) if (res) return res; - inode->i_nlink--; + drop_nlink(inode); hfs_delete_inode(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 1f9ece0de326..9ceb0dfaa1cc 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -338,7 +338,7 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry) return res; if (inode->i_nlink > 0) - inode->i_nlink--; + drop_nlink(inode); hfsplus_delete_inode(inode); if (inode->i_ino != cnid && !inode->i_nlink) { if (!atomic_read(&HFSPLUS_I(inode).opencnt)) { diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 59e7dc182a0c..4078b0becc5e 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -434,7 +434,7 @@ again: unlock_kernel(); return -ENOSPC; default: - inode->i_nlink--; + drop_nlink(inode); err = 0; } goto out; @@ -494,7 +494,7 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) err = -ENOSPC; break; default: - dir->i_nlink--; + drop_nlink(dir); inode->i_nlink = 0; err = 0; } @@ -636,7 +636,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { new_dir->i_nlink++; - old_dir->i_nlink--; + drop_nlink(old_dir); } if ((fnode = hpfs_map_fnode(i->i_sb, i->i_ino, &bh))) { fnode->up = new_dir->i_ino; diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index 068ef0de8de2..3f7899ea4cba 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -1052,9 +1052,8 @@ jffs_remove(struct inode *dir, struct dentry *dentry, int type) dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); d_delete(dentry); /* This also frees the inode */ diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index edd8371fc6a5..a5e9f2205b33 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -615,7 +615,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) } ret = jffs2_unlink(dir_i, dentry); if (!ret) - dir_i->i_nlink--; + drop_nlink(dir_i); return ret; } @@ -823,7 +823,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, if (victim_f) { /* There was a victim. Kill it off nicely */ - new_dentry->d_inode->i_nlink--; + drop_nlink(new_dentry->d_inode); /* Don't oops if the victim was a dirent pointing to an inode which didn't exist. */ if (victim_f->inocache) { @@ -862,7 +862,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, } if (S_ISDIR(old_dentry->d_inode->i_mode)) - old_dir_i->i_nlink--; + drop_nlink(old_dir_i); new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 295268ad231b..088b85976ac0 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -393,9 +393,8 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) /* update parent directory's link count corresponding * to ".." entry of the target directory deleted */ - dip->i_nlink--; dip->i_ctime = dip->i_mtime = CURRENT_TIME; - mark_inode_dirty(dip); + inode_dec_link_count(dip); /* * OS/2 could have created EA and/or ACL @@ -515,8 +514,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) mark_inode_dirty(dip); /* update target's inode */ - ip->i_nlink--; - mark_inode_dirty(ip); + inode_dec_link_count(ip); /* * commit zero link count object @@ -835,7 +833,7 @@ static int jfs_link(struct dentry *old_dentry, rc = txCommit(tid, 2, &iplist[0], 0); if (rc) { - ip->i_nlink--; + ip->i_nlink--; /* never instantiated */ iput(ip); } else d_instantiate(dentry, ip); @@ -1155,9 +1153,9 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_ip->i_ino, JFS_RENAME); if (rc) goto out4; - new_ip->i_nlink--; + drop_nlink(new_ip); if (S_ISDIR(new_ip->i_mode)) { - new_ip->i_nlink--; + drop_nlink(new_ip); if (new_ip->i_nlink) { mutex_unlock(&JFS_IP(new_ip)->commit_mutex); if (old_dir != new_dir) @@ -1223,7 +1221,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out4; } if (S_ISDIR(old_ip->i_mode)) { - old_dir->i_nlink--; + drop_nlink(old_dir); if (old_dir != new_dir) { /* * Change inode number of parent for moved directory diff --git a/fs/libfs.c b/fs/libfs.c index 3793aaa14577..9204feba75ac 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -275,7 +275,7 @@ int simple_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = dentry->d_inode; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); return 0; } @@ -285,9 +285,9 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dentry->d_inode->i_nlink--; + drop_nlink(dentry->d_inode); simple_unlink(dir, dentry); - dir->i_nlink--; + drop_nlink(dir); return 0; } @@ -303,9 +303,9 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dentry->d_inode) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; + drop_nlink(old_dir); new_dir->i_nlink++; } diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 5b6a4540a05b..299bb66e3bde 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -249,7 +249,7 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, minix_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c index d220165d4918..635613f2f65a 100644 --- a/fs/msdos/namei.c +++ b/fs/msdos/namei.c @@ -343,7 +343,7 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - dir->i_nlink--; + drop_nlink(dir); inode->i_nlink = 0; inode->i_ctime = CURRENT_TIME_SEC; @@ -549,7 +549,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, if (err) goto error_dotdot; } - old_dir->i_nlink--; + drop_nlink(old_dir); if (!new_inode) new_dir->i_nlink++; } @@ -566,10 +566,9 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, mark_inode_dirty(old_dir); if (new_inode) { + drop_nlink(new_inode); if (is_dir) - new_inode->i_nlink -= 2; - else - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = ts; } out: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7432f1a43f3d..26eecb86f9b0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -843,7 +843,7 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) nfs_inode_return_delegation(inode); if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { lock_kernel(); - inode->i_nlink--; + drop_nlink(inode); nfs_complete_unlink(dentry); unlock_kernel(); } @@ -1401,7 +1401,7 @@ static int nfs_safe_remove(struct dentry *dentry) error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); /* The VFS may want to delete this inode */ if (error == 0) - inode->i_nlink--; + drop_nlink(inode); nfs_mark_for_revalidate(inode); nfs_end_data_update(inode); } else @@ -1639,7 +1639,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } } else - new_inode->i_nlink--; + drop_nlink(new_inode); go_ahead: /* diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 849c3b4bb94a..40f83f53053a 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -739,7 +739,7 @@ static int ocfs2_link(struct dentry *old_dentry, err = ocfs2_journal_dirty(handle, fe_bh); if (err < 0) { le16_add_cpu(&fe->i_links_count, -1); - inode->i_nlink--; + drop_nlink(inode); mlog_errno(err); goto bail; } @@ -749,7 +749,7 @@ static int ocfs2_link(struct dentry *old_dentry, parent_fe_bh, de_bh); if (err) { le16_add_cpu(&fe->i_links_count, -1); - inode->i_nlink--; + drop_nlink(inode); mlog_errno(err); goto bail; } diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c index c3d83f67154a..ad5afa4ea8f3 100644 --- a/fs/qnx4/namei.c +++ b/fs/qnx4/namei.c @@ -189,8 +189,7 @@ int qnx4_rmdir(struct inode *dir, struct dentry *dentry) inode->i_nlink = 0; mark_inode_dirty(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; - dir->i_nlink--; - mark_inode_dirty(dir); + inode_dec_link_count(dir); retval = 0; end_rmdir: @@ -234,9 +233,8 @@ int qnx4_unlink(struct inode *dir, struct dentry *dentry) mark_buffer_dirty(bh); dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(dir); - inode->i_nlink--; inode->i_ctime = dir->i_ctime; - mark_inode_dirty(inode); + inode_dec_link_count(inode); retval = 0; end_unlink: diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index c61710e49c62..c76d427e027b 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -20,7 +20,7 @@ #include #define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { i->i_nlink++; if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } -#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) i->i_nlink--; +#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i); // directory item contains array of entry headers. This performs // binary search through that array @@ -994,7 +994,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) inode->i_nlink = 1; } - inode->i_nlink--; + drop_nlink(inode); /* * we schedule before doing the add_save_link call, save the link @@ -1475,7 +1475,7 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (S_ISDIR(new_dentry_inode->i_mode)) { new_dentry_inode->i_nlink = 0; } else { - new_dentry_inode->i_nlink--; + drop_nlink(new_dentry_inode); } new_dentry_inode->i_ctime = ctime; savelink = new_dentry_inode->i_nlink; diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index b8a73f716fbe..f7c08db8e34c 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -250,7 +250,7 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, sysv_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/udf/namei.c b/fs/udf/namei.c index ab9a7629d23e..d14d25534aa8 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -878,8 +878,7 @@ static int udf_rmdir(struct inode * dir, struct dentry * dentry) inode->i_nlink); inode->i_nlink = 0; inode->i_size = 0; - mark_inode_dirty(inode); - dir->i_nlink --; + inode_dec_link_count(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); mark_inode_dirty(dir); @@ -923,8 +922,7 @@ static int udf_unlink(struct inode * dir, struct dentry * dentry) goto end_unlink; dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); mark_inode_dirty(dir); - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); inode->i_ctime = dir->i_ctime; retval = 0; @@ -1101,8 +1099,7 @@ out: return err; out_no_entry: - inode->i_nlink--; - mark_inode_dirty(inode); + inode_dec_link_count(inode); iput(inode); goto out; } @@ -1261,9 +1258,8 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry, if (new_inode) { - new_inode->i_nlink--; new_inode->i_ctime = current_fs_time(new_inode->i_sb); - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } old_dir->i_ctime = old_dir->i_mtime = current_fs_time(old_dir->i_sb); mark_inode_dirty(old_dir); @@ -1279,12 +1275,10 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry, } else mark_buffer_dirty_inode(dir_bh, old_inode); - old_dir->i_nlink --; - mark_inode_dirty(old_dir); + inode_dec_link_count(old_dir); if (new_inode) { - new_inode->i_nlink --; - mark_inode_dirty(new_inode); + inode_dec_link_count(new_inode); } else { diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index d344b411e261..e84c0ecf0730 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -308,7 +308,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, ufs_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) - new_inode->i_nlink--; + drop_nlink(new_inode); inode_dec_link_count(new_inode); } else { if (dir_de) { diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c index 9a8f48bae956..090d74ffa061 100644 --- a/fs/vfat/namei.c +++ b/fs/vfat/namei.c @@ -782,7 +782,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - dir->i_nlink--; + drop_nlink(dir); inode->i_nlink = 0; inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; @@ -930,7 +930,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto error_dotdot; } - old_dir->i_nlink--; + drop_nlink(old_dir); if (!new_inode) new_dir->i_nlink++; } @@ -947,10 +947,9 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, mark_inode_dirty(old_dir); if (new_inode) { + drop_nlink(new_inode); if (is_dir) - new_inode->i_nlink -= 2; - else - new_inode->i_nlink--; + drop_nlink(new_inode); new_inode->i_ctime = ts; } out: diff --git a/include/linux/fs.h b/include/linux/fs.h index 4bb70871873f..26d3c61116c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1225,9 +1225,14 @@ static inline void inode_inc_link_count(struct inode *inode) mark_inode_dirty(inode); } -static inline void inode_dec_link_count(struct inode *inode) +static inline void drop_nlink(struct inode *inode) { inode->i_nlink--; +} + +static inline void inode_dec_link_count(struct inode *inode) +{ + drop_nlink(inode); mark_inode_dirty(inode); } diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 840f8a6fb85f..10aa8eeeb112 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -307,7 +307,7 @@ static int mqueue_unlink(struct inode *dir, struct dentry *dentry) dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME; dir->i_size -= DIRENT_SIZE; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); return 0; } diff --git a/mm/shmem.c b/mm/shmem.c index b96de69f236b..908dd947b1ea 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1772,7 +1772,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } @@ -1782,8 +1782,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dentry->d_inode->i_nlink--; - dir->i_nlink--; + drop_nlink(dentry->d_inode); + drop_nlink(dir); return shmem_unlink(dir, dentry); } @@ -1804,9 +1804,9 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; + drop_nlink(old_dir); new_dir->i_nlink++; } -- cgit v1.3-8-gc7d7 From d8c76e6f45c111c32a4b3e50a2adc9210737b0d8 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:04 -0700 Subject: [PATCH] r/o bind mount prepwork: inc_nlink() helper This is mostly included for parity with dec_nlink(), where we will have some more hooks. This one should stay pretty darn straightforward for now. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/hw/ipath/ipath_fs.c | 4 ++-- drivers/usb/core/inode.c | 4 ++-- fs/9p/vfs_inode.c | 2 +- fs/autofs/root.c | 2 +- fs/autofs4/root.c | 2 +- fs/bfs/dir.c | 2 +- fs/cifs/inode.c | 2 +- fs/coda/dir.c | 2 +- fs/configfs/dir.c | 4 ++-- fs/configfs/mount.c | 2 +- fs/debugfs/inode.c | 4 ++-- fs/ext3/namei.c | 6 +++--- fs/fuse/control.c | 2 +- fs/hfsplus/dir.c | 2 +- fs/hpfs/namei.c | 4 ++-- fs/hugetlbfs/inode.c | 4 ++-- fs/jffs2/dir.c | 6 +++--- fs/jffs2/fs.c | 6 +++--- fs/jfs/namei.c | 6 +++--- fs/libfs.c | 4 ++-- fs/msdos/namei.c | 4 ++-- fs/ocfs2/dlm/dlmfs.c | 6 +++--- fs/ocfs2/namei.c | 8 ++++---- fs/ramfs/inode.c | 4 ++-- fs/reiserfs/namei.c | 6 +++--- fs/sysfs/dir.c | 4 ++-- fs/sysfs/mount.c | 2 +- fs/udf/inode.c | 2 +- fs/udf/namei.c | 6 +++--- fs/vfat/namei.c | 4 ++-- include/linux/fs.h | 7 ++++++- ipc/mqueue.c | 2 +- kernel/cpuset.c | 8 ++++---- mm/shmem.c | 8 ++++---- net/sunrpc/rpc_pipe.c | 6 +++--- security/inode.c | 4 ++-- security/selinux/selinuxfs.c | 4 ++-- 37 files changed, 80 insertions(+), 75 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index a507d0b5be6c..d9ff283f725e 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -66,8 +66,8 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, inode->i_private = data; if ((mode & S_IFMT) == S_IFDIR) { inode->i_op = &simple_dir_inode_operations; - inode->i_nlink++; - dir->i_nlink++; + inc_nlink(inode); + inc_nlink(dir); } inode->i_fop = fops; diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 88002e45a6b4..7c77c2d8d300 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -263,7 +263,7 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -295,7 +295,7 @@ static int usbfs_mkdir (struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = usbfs_mknod (dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7a7ec2d1d2f4..5241c600ce28 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -233,7 +233,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode) inode->i_op = &v9fs_symlink_inode_operations; break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); if(v9ses->extended) inode->i_op = &v9fs_dir_inode_operations_ext; else diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 54ad70731927..368a1c33a3c8 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -466,7 +466,7 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode) ent->dentry = dentry; autofs_hash_insert(dh,ent); - dir->i_nlink++; + inc_nlink(dir); d_instantiate(dentry, iget(dir->i_sb,ino)); unlock_kernel(); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 348bec0982b0..e21bb4668201 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -713,7 +713,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (p_ino && dentry->d_parent != dentry) atomic_inc(&p_ino->count); ino->inode = inode; - dir->i_nlink++; + inc_nlink(dir); dir->i_mtime = CURRENT_TIME; return 0; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index ce05d1643dd1..a650f1d0b85e 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -163,7 +163,7 @@ static int bfs_link(struct dentry * old, struct inode * dir, struct dentry * new unlock_kernel(); return err; } - inode->i_nlink++; + inc_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); atomic_inc(&inode->i_count); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 74441a17e186..76b7fb34101a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -735,7 +735,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) cFYI(1, ("cifs_mkdir returned 0x%x", rc)); d_drop(direntry); } else { - inode->i_nlink++; + inc_nlink(inode); if (pTcon->ses->capabilities & CAP_UNIX) rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb,xid); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 0a2fd8bb7579..0102b28a15fb 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -304,7 +304,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, coda_dir_changed(dir_inode, 0); atomic_inc(&inode->i_count); d_instantiate(de, inode); - inode->i_nlink++; + inc_nlink(inode); out: unlock_kernel(); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 816e8ef64560..8a3b6a1a6ad1 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -139,7 +139,7 @@ static int init_dir(struct inode * inode) inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); return 0; } @@ -169,7 +169,7 @@ static int create_dir(struct config_item * k, struct dentry * p, if (!error) { error = configfs_create(d, mode, init_dir); if (!error) { - p->d_inode->i_nlink++; + inc_nlink(p->d_inode); (d)->d_op = &configfs_dentry_ops; } else { struct configfs_dirent *sd = d->d_fsdata; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 3e5fe843e1df..68bd5c93ca52 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -84,7 +84,7 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) inode->i_op = &configfs_dir_inode_operations; inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { pr_debug("configfs: could not get root inode\n"); return -ENOMEM; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 269e649e6dc6..ecf3da9edf21 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -54,7 +54,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -87,7 +87,7 @@ static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = debugfs_mknod(dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 14c55adfae83..b45c88bd5f73 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1616,7 +1616,7 @@ static int ext3_delete_entry (handle_t *handle, */ static inline void ext3_inc_count(handle_t *handle, struct inode *inode) { - inode->i_nlink++; + inc_nlink(inode); } static inline void ext3_dec_count(handle_t *handle, struct inode *inode) @@ -1775,7 +1775,7 @@ retry: iput (inode); goto out_stop; } - dir->i_nlink++; + inc_nlink(dir); ext3_update_dx_flag(dir); ext3_mark_inode_dirty(handle, dir); d_instantiate(dentry, inode); @@ -2341,7 +2341,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, if (new_inode) { drop_nlink(new_inode); } else { - new_dir->i_nlink++; + inc_nlink(new_dir); ext3_update_dx_flag(new_dir); ext3_mark_inode_dirty(handle, new_dir); } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 79ec1f23d4d2..16b39c053d47 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -116,7 +116,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) return 0; parent = fuse_control_sb->s_root; - parent->d_inode->i_nlink++; + inc_nlink(parent->d_inode); sprintf(name, "%llu", (unsigned long long) fc->id); parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2, &simple_dir_inode_operations, diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 9ceb0dfaa1cc..99b4ed1b87d2 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -298,7 +298,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, if (res) return res; - inode->i_nlink++; + inc_nlink(inode); hfsplus_instantiate(dst_dentry, inode, cnid); atomic_inc(&inode->i_count); inode->i_ctime = CURRENT_TIME_SEC; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 4078b0becc5e..25dd6f81eca7 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -89,7 +89,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) brelse(bh); hpfs_mark_4buffers_dirty(&qbh0); hpfs_brelse4(&qbh0); - dir->i_nlink++; + inc_nlink(dir); insert_inode_hash(result); if (result->i_uid != current->fsuid || @@ -635,7 +635,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, end: hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { - new_dir->i_nlink++; + inc_nlink(new_dir); drop_nlink(old_dir); } if ((fnode = hpfs_map_fnode(i->i_sb, i->i_ino, &bh))) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f5b8f329aca6..5e03b2f67b93 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -377,7 +377,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; @@ -418,7 +418,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) { int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0); if (!retval) - dir->i_nlink++; + inc_nlink(dir); return retval; } diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index a5e9f2205b33..9def6adf4a5d 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -588,7 +588,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode) } dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime)); - dir_i->i_nlink++; + inc_nlink(dir_i); jffs2_free_raw_dirent(rd); @@ -836,7 +836,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, /* If it was a directory we moved, and there was no victim, increase i_nlink on its new parent */ if (S_ISDIR(old_dentry->d_inode->i_mode) && !victim_f) - new_dir_i->i_nlink++; + inc_nlink(new_dir_i); /* Unlink the original */ ret = jffs2_do_unlink(c, JFFS2_INODE_INFO(old_dir_i), @@ -848,7 +848,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, /* Oh shit. We really ought to make a single node which can do both atomically */ struct jffs2_inode_info *f = JFFS2_INODE_INFO(old_dentry->d_inode); down(&f->sem); - old_dentry->d_inode->i_nlink++; + inc_nlink(old_dentry->d_inode); if (f->inocache) f->inocache->nlink++; up(&f->sem); diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 72d9909d95ff..7bc1a4201c0c 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -277,13 +277,13 @@ void jffs2_read_inode (struct inode *inode) for (fd=f->dents; fd; fd = fd->next) { if (fd->type == DT_DIR && fd->ino) - inode->i_nlink++; + inc_nlink(inode); } /* and '..' */ - inode->i_nlink++; + inc_nlink(inode); /* Root dir gets i_nlink 3 for some reason */ if (inode->i_ino == 1) - inode->i_nlink++; + inc_nlink(inode); inode->i_op = &jffs2_dir_inode_operations; inode->i_fop = &jffs2_dir_operations; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 088b85976ac0..8cef88170aa4 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -292,7 +292,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) mark_inode_dirty(ip); /* update parent directory inode */ - dip->i_nlink++; /* for '..' from child directory */ + inc_nlink(dip); /* for '..' from child directory */ dip->i_ctime = dip->i_mtime = CURRENT_TIME; mark_inode_dirty(dip); @@ -822,7 +822,7 @@ static int jfs_link(struct dentry *old_dentry, goto free_dname; /* update object inode */ - ip->i_nlink++; /* for new link */ + inc_nlink(ip); /* for new link */ ip->i_ctime = CURRENT_TIME; dir->i_ctime = dir->i_mtime = CURRENT_TIME; mark_inode_dirty(dir); @@ -1206,7 +1206,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out4; } if (S_ISDIR(old_ip->i_mode)) - new_dir->i_nlink++; + inc_nlink(new_dir); } /* * Remove old directory entry diff --git a/fs/libfs.c b/fs/libfs.c index 9204feba75ac..bd08e0e64a8c 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -243,7 +243,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den struct inode *inode = old_dentry->d_inode; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); atomic_inc(&inode->i_count); dget(dentry); d_instantiate(dentry, inode); @@ -306,7 +306,7 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry, drop_nlink(old_dir); } else if (they_are_dirs) { drop_nlink(old_dir); - new_dir->i_nlink++; + inc_nlink(new_dir); } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c index 635613f2f65a..fa868c755907 100644 --- a/fs/msdos/namei.c +++ b/fs/msdos/namei.c @@ -389,7 +389,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode) err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo); if (err) goto out_free; - dir->i_nlink++; + inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); @@ -551,7 +551,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, } drop_nlink(old_dir); if (!new_inode) - new_dir->i_nlink++; + inc_nlink(new_dir); } err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 0368c6402182..16b8d1ba7066 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -338,7 +338,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); inode->i_fop = &simple_dir_operations; inode->i_op = &dlmfs_root_inode_operations; @@ -395,7 +395,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, /* directory inodes start off with i_nlink == * 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } @@ -449,7 +449,7 @@ static int dlmfs_mkdir(struct inode * dir, } ip->ip_dlm = dlm; - dir->i_nlink++; + inc_nlink(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 40f83f53053a..8c370a39e0c1 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -429,7 +429,7 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } - dir->i_nlink++; + inc_nlink(dir); } status = ocfs2_add_entry(handle, dentry, inode, @@ -730,7 +730,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto bail; } - inode->i_nlink++; + inc_nlink(inode); inode->i_ctime = CURRENT_TIME; fe->i_links_count = cpu_to_le16(inode->i_nlink); fe->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); @@ -952,7 +952,7 @@ static int ocfs2_unlink(struct inode *dir, parent_node_bh); if (status < 0) { mlog_errno(status); - dir->i_nlink++; + inc_nlink(dir); } } @@ -1382,7 +1382,7 @@ static int ocfs2_rename(struct inode *old_dir, if (new_inode) { new_inode->i_nlink--; } else { - new_dir->i_nlink++; + inc_nlink(new_dir); mark_inode_dirty(new_dir); } } diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index bc0e51662424..2faf4cdf61b0 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -75,7 +75,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; @@ -113,7 +113,7 @@ static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, int mode) { int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0); if (!retval) - dir->i_nlink++; + inc_nlink(dir); return retval; } diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index c76d427e027b..cf92e89515f2 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -19,7 +19,7 @@ #include #include -#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { i->i_nlink++; if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } +#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } #define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i); // directory item contains array of entry headers. This performs @@ -1006,7 +1006,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) reiserfs_cut_from_item(&th, &path, &(de.de_entry_key), dir, NULL, 0); if (retval < 0) { - inode->i_nlink++; + inc_nlink(inode); goto end_unlink; } inode->i_ctime = CURRENT_TIME_SEC; @@ -1143,7 +1143,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, } /* inc before scheduling so reiserfs_unlink knows we are here */ - inode->i_nlink++; + inc_nlink(inode); retval = journal_begin(&th, dir->i_sb, jbegin_count); if (retval) { diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 5f3d725d1125..3aa3434621ca 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -103,7 +103,7 @@ static int init_dir(struct inode * inode) inode->i_fop = &sysfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); return 0; } @@ -137,7 +137,7 @@ static int create_dir(struct kobject * k, struct dentry * p, if (!error) { error = sysfs_create(*d, mode, init_dir); if (!error) { - p->d_inode->i_nlink++; + inc_nlink(p->d_inode); (*d)->d_op = &sysfs_dentry_ops; d_rehash(*d); } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 40190c489271..20551a1b8a56 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -49,7 +49,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) inode->i_op = &sysfs_dir_inode_operations; inode->i_fop = &sysfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { pr_debug("sysfs: could not get root inode\n"); return -ENOMEM; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index b223b32db991..ae21a0e59e95 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1165,7 +1165,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh) inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; inode->i_mode |= S_IFDIR; - inode->i_nlink ++; + inc_nlink(inode); break; } case ICBTAG_FILE_TYPE_REALTIME: diff --git a/fs/udf/namei.c b/fs/udf/namei.c index d14d25534aa8..e40c95e65117 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -762,7 +762,7 @@ static int udf_mkdir(struct inode * dir, struct dentry * dentry, int mode) cpu_to_le32(UDF_I_UNIQUE(inode) & 0x00000000FFFFFFFFUL); cfi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); - dir->i_nlink++; + inc_nlink(dir); mark_inode_dirty(dir); d_instantiate(dentry, inode); if (fibh.sbh != fibh.ebh) @@ -1147,7 +1147,7 @@ static int udf_link(struct dentry * old_dentry, struct inode * dir, if (fibh.sbh != fibh.ebh) udf_release_data(fibh.ebh); udf_release_data(fibh.sbh); - inode->i_nlink ++; + inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); atomic_inc(&inode->i_count); @@ -1282,7 +1282,7 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry, } else { - new_dir->i_nlink ++; + inc_nlink(new_dir); mark_inode_dirty(new_dir); } } diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c index 090d74ffa061..5846ba2d5d9f 100644 --- a/fs/vfat/namei.c +++ b/fs/vfat/namei.c @@ -837,7 +837,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (err) goto out_free; dir->i_version++; - dir->i_nlink++; + inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); @@ -932,7 +932,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, } drop_nlink(old_dir); if (!new_inode) - new_dir->i_nlink++; + inc_nlink(new_dir); } err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 26d3c61116c0..6a5267da565f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1219,9 +1219,14 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } -static inline void inode_inc_link_count(struct inode *inode) +static inline void inc_nlink(struct inode *inode) { inode->i_nlink++; +} + +static inline void inode_inc_link_count(struct inode *inode) +{ + inc_nlink(inode); mark_inode_dirty(inode); } diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 10aa8eeeb112..d75d0ba83360 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -168,7 +168,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, /* all is ok */ info->user = get_uid(u); } else if (S_ISDIR(mode)) { - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * DIRENT_SIZE; inode->i_op = &mqueue_dir_inode_operations; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 8c3c400cce91..9d850ae13b1b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -377,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data, inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directories start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else { return -ENOMEM; } @@ -1565,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode) inode->i_fop = &simple_dir_operations; /* start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); } else if (S_ISREG(mode)) { inode->i_size = 0; inode->i_fop = &cpuset_file_operations; @@ -1598,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode) error = cpuset_create_file(dentry, S_IFDIR | mode); if (!error) { dentry->d_fsdata = cs; - parent->d_inode->i_nlink++; + inc_nlink(parent->d_inode); cs->dentry = dentry; } dput(dentry); @@ -2033,7 +2033,7 @@ int __init cpuset_init(void) } root = cpuset_mount->mnt_sb->s_root; root->d_fsdata = &top_cpuset; - root->d_inode->i_nlink++; + inc_nlink(root->d_inode); top_cpuset.dentry = root; root->d_inode->i_op = &cpuset_dir_inode_operations; number_of_cpusets = 1; diff --git a/mm/shmem.c b/mm/shmem.c index 908dd947b1ea..bb8ca7ef7094 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1379,7 +1379,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) &sbinfo->policy_nodes); break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; @@ -1715,7 +1715,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode) if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; - dir->i_nlink++; + inc_nlink(dir); return 0; } @@ -1750,7 +1750,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); atomic_inc(&inode->i_count); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); @@ -1807,7 +1807,7 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct drop_nlink(old_dir); } else if (they_are_dirs) { drop_nlink(old_dir); - new_dir->i_nlink++; + inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 700c6e061a04..9a0b41a97f90 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -494,7 +494,7 @@ rpc_get_inode(struct super_block *sb, int mode) case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; - inode->i_nlink++; + inc_nlink(inode); default: break; } @@ -571,7 +571,7 @@ rpc_populate(struct dentry *parent, if (private) rpc_inode_setowner(inode, private); if (S_ISDIR(mode)) - dir->i_nlink++; + inc_nlink(dir); d_add(dentry, inode); } mutex_unlock(&dir->i_mutex); @@ -593,7 +593,7 @@ __rpc_mkdir(struct inode *dir, struct dentry *dentry) goto out_err; inode->i_ino = iunique(dir->i_sb, 100); d_instantiate(dentry, inode); - dir->i_nlink++; + inc_nlink(dir); inode_dir_notify(dir, DN_CREATE); return 0; out_err: diff --git a/security/inode.c b/security/inode.c index 49ee51529396..9b16e14f3a80 100644 --- a/security/inode.c +++ b/security/inode.c @@ -78,7 +78,7 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); break; } } @@ -111,7 +111,7 @@ static int mkdir(struct inode *dir, struct dentry *dentry, int mode) mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; res = mknod(dir, dentry, mode, 0); if (!res) - dir->i_nlink++; + inc_nlink(dir); return res; } diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index bab7b386cb8d..cd244419c980 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1253,10 +1253,10 @@ static int sel_make_dir(struct inode *dir, struct dentry *dentry) inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inode->i_nlink++; + inc_nlink(inode); d_add(dentry, inode); /* bump link count on parent directory, too */ - dir->i_nlink++; + inc_nlink(dir); out: return ret; } -- cgit v1.3-8-gc7d7 From ce71ec36840368b877fb63bd14c8e67ab62d08b1 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:06 -0700 Subject: [PATCH] r/o bind mounts: monitor zeroing of i_nlink Some filesystems, instead of simply decrementing i_nlink, simply zero it during an unlink operation. We need to catch these in addition to the decrement operations. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/root.c | 4 ++-- fs/cifs/inode.c | 2 +- fs/ext3/namei.c | 2 +- fs/fuse/dir.c | 4 ++-- fs/hfs/dir.c | 2 +- fs/hfsplus/dir.c | 4 ++-- fs/hpfs/namei.c | 4 ++-- fs/jfs/namei.c | 2 +- fs/msdos/namei.c | 4 ++-- fs/nfs/dir.c | 2 +- fs/qnx4/namei.c | 2 +- fs/reiserfs/namei.c | 4 ++-- fs/udf/namei.c | 2 +- fs/vfat/namei.c | 4 ++-- include/linux/fs.h | 5 +++++ 15 files changed, 26 insertions(+), 21 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index e21bb4668201..c1493524da4d 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -638,7 +638,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) dput(ino->dentry); dentry->d_inode->i_size = 0; - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); dir->i_mtime = CURRENT_TIME; @@ -673,7 +673,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) } dput(ino->dentry); dentry->d_inode->i_size = 0; - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); if (dir->i_nlink) drop_nlink(dir); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 76b7fb34101a..6b90ef98e4cf 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -818,7 +818,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) if (!rc) { drop_nlink(inode); i_size_write(direntry->d_inode,0); - direntry->d_inode->i_nlink = 0; + clear_nlink(direntry->d_inode); } cifsInode = CIFS_I(direntry->d_inode); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index b45c88bd5f73..906731a20f1a 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -2045,7 +2045,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry) "empty directory has nlink!=2 (%d)", inode->i_nlink); inode->i_version++; - inode->i_nlink = 0; + clear_nlink(inode); /* There's no need to set i_disksize: the fact that i_nlink is * zero will ensure that the right thing happens during any * recovery. */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index f85b2a282f13..8605155db171 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -508,7 +508,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) /* Set nlink to zero so the inode can be cleared, if the inode does have more links this will be discovered at the next lookup/getattr */ - inode->i_nlink = 0; + clear_nlink(inode); fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); @@ -534,7 +534,7 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) err = req->out.h.error; fuse_put_request(fc, req); if (!err) { - entry->d_inode->i_nlink = 0; + clear_nlink(entry->d_inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); } else if (err == -EINTR) diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index cfef6ad529a7..37d681b4f216 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -273,7 +273,7 @@ static int hfs_rmdir(struct inode *dir, struct dentry *dentry) res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name); if (res) return res; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; hfs_delete_inode(inode); mark_inode_dirty(inode); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 99b4ed1b87d2..7e309751645f 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -348,7 +348,7 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry) } else inode->i_flags |= S_DEAD; } else - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); @@ -387,7 +387,7 @@ static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry) res = hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); if (res) return res; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; hfsplus_delete_inode(inode); mark_inode_dirty(inode); diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 25dd6f81eca7..2507e7393f3c 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -495,7 +495,7 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) break; default: drop_nlink(dir); - inode->i_nlink = 0; + clear_nlink(inode); err = 0; } goto out; @@ -590,7 +590,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, int r; if ((r = hpfs_remove_dirent(old_dir, dno, dep, &qbh, 1)) != 2) { if ((nde = map_dirent(new_dir, hpfs_i(new_dir)->i_dno, (char *)new_name, new_len, NULL, &qbh1))) { - new_inode->i_nlink = 0; + clear_nlink(new_inode); copy_de(nde, &de); memcpy(nde->name, new_name, new_len); hpfs_mark_4buffers_dirty(&qbh1); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 8cef88170aa4..b8d16a6aa88f 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -414,7 +414,7 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) JFS_IP(ip)->acl.flag = 0; /* mark the target directory as deleted */ - ip->i_nlink = 0; + clear_nlink(ip); mark_inode_dirty(ip); rc = txCommit(tid, 2, &iplist[0], 0); diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c index fa868c755907..b0f01b3b0536 100644 --- a/fs/msdos/namei.c +++ b/fs/msdos/namei.c @@ -345,7 +345,7 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry) goto out; drop_nlink(dir); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -430,7 +430,7 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; fat_detach(inode); out: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 26eecb86f9b0..481f8892a919 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1286,7 +1286,7 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry) error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); /* Ensure the VFS deletes this inode */ if (error == 0 && dentry->d_inode != NULL) - dentry->d_inode->i_nlink = 0; + clear_nlink(dentry->d_inode); nfs_end_data_update(dir); unlock_kernel(); diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c index ad5afa4ea8f3..733cdf01d645 100644 --- a/fs/qnx4/namei.c +++ b/fs/qnx4/namei.c @@ -186,7 +186,7 @@ int qnx4_rmdir(struct inode *dir, struct dentry *dentry) memset(de->di_fname, 0, sizeof de->di_fname); de->di_mode = 0; mark_buffer_dirty(bh); - inode->i_nlink = 0; + clear_nlink(inode); mark_inode_dirty(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; inode_dec_link_count(dir); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index cf92e89515f2..16e9cff8f15d 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -913,7 +913,7 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry) reiserfs_warning(inode->i_sb, "%s: empty directory has nlink " "!= 2 (%d)", __FUNCTION__, inode->i_nlink); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; reiserfs_update_sd(&th, inode); @@ -1473,7 +1473,7 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dentry_inode) { // adjust link number of the victim if (S_ISDIR(new_dentry_inode->i_mode)) { - new_dentry_inode->i_nlink = 0; + clear_nlink(new_dentry_inode); } else { drop_nlink(new_dentry_inode); } diff --git a/fs/udf/namei.c b/fs/udf/namei.c index e40c95e65117..73163325e5ec 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -876,7 +876,7 @@ static int udf_rmdir(struct inode * dir, struct dentry * dentry) udf_warning(inode->i_sb, "udf_rmdir", "empty directory has nlink != 2 (%d)", inode->i_nlink); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_size = 0; inode_dec_link_count(inode); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb); diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c index 5846ba2d5d9f..edb711ff7b05 100644 --- a/fs/vfat/namei.c +++ b/fs/vfat/namei.c @@ -784,7 +784,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry) goto out; drop_nlink(dir); - inode->i_nlink = 0; + clear_nlink(inode); inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; fat_detach(inode); out: @@ -808,7 +808,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - inode->i_nlink = 0; + clear_nlink(inode); inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; fat_detach(inode); out: diff --git a/include/linux/fs.h b/include/linux/fs.h index 6a5267da565f..3493d2828f7d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1235,6 +1235,11 @@ static inline void drop_nlink(struct inode *inode) inode->i_nlink--; } +static inline void clear_nlink(struct inode *inode) +{ + inode->i_nlink = 0; +} + static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); -- cgit v1.3-8-gc7d7 From d6cbd281d189977b38eac7eb2a4678de19b6b483 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 30 Sep 2006 23:29:26 -0700 Subject: [PATCH] Some cleanup in the pipe code Split the big and hard to read do_pipe function into smaller pieces. This creates new create_write_pipe/free_write_pipe/create_read_pipe functions. These functions are made global so that they can be used by other parts of the kernel. The resulting code is more generic and easier to read and has cleaner error handling and less gotos. [akpm@osdl.org: cleanup] Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 155 ++++++++++++++++++++++++++++++++--------------------- include/linux/fs.h | 3 ++ 2 files changed, 96 insertions(+), 62 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/pipe.c b/fs/pipe.c index 2e60e1c8815e..b1626f269a34 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -874,87 +874,118 @@ fail_inode: return NULL; } -int do_pipe(int *fd) +struct file *create_write_pipe(void) { - struct qstr this; - char name[32]; + int err; + struct inode *inode; + struct file *f; struct dentry *dentry; - struct inode * inode; - struct file *f1, *f2; - int error; - int i, j; - - error = -ENFILE; - f1 = get_empty_filp(); - if (!f1) - goto no_files; - - f2 = get_empty_filp(); - if (!f2) - goto close_f1; + char name[32]; + struct qstr this; + f = get_empty_filp(); + if (!f) + return ERR_PTR(-ENFILE); + err = -ENFILE; inode = get_pipe_inode(); if (!inode) - goto close_f12; + goto err_file; - error = get_unused_fd(); - if (error < 0) - goto close_f12_inode; - i = error; - - error = get_unused_fd(); - if (error < 0) - goto close_f12_inode_i; - j = error; - - error = -ENOMEM; sprintf(name, "[%lu]", inode->i_ino); this.name = name; this.len = strlen(name); this.hash = inode->i_ino; /* will go */ + err = -ENOMEM; dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &this); if (!dentry) - goto close_f12_inode_i_j; + goto err_inode; dentry->d_op = &pipefs_dentry_operations; d_add(dentry, inode); - f1->f_vfsmnt = f2->f_vfsmnt = mntget(mntget(pipe_mnt)); - f1->f_dentry = f2->f_dentry = dget(dentry); - f1->f_mapping = f2->f_mapping = inode->i_mapping; - - /* read file */ - f1->f_pos = f2->f_pos = 0; - f1->f_flags = O_RDONLY; - f1->f_op = &read_pipe_fops; - f1->f_mode = FMODE_READ; - f1->f_version = 0; - - /* write file */ - f2->f_flags = O_WRONLY; - f2->f_op = &write_pipe_fops; - f2->f_mode = FMODE_WRITE; - f2->f_version = 0; - - fd_install(i, f1); - fd_install(j, f2); - fd[0] = i; - fd[1] = j; + f->f_vfsmnt = mntget(pipe_mnt); + f->f_dentry = dentry; + f->f_mapping = inode->i_mapping; - return 0; + f->f_flags = O_WRONLY; + f->f_op = &write_pipe_fops; + f->f_mode = FMODE_WRITE; + f->f_version = 0; -close_f12_inode_i_j: - put_unused_fd(j); -close_f12_inode_i: - put_unused_fd(i); -close_f12_inode: + return f; + + err_inode: free_pipe_info(inode); iput(inode); -close_f12: - put_filp(f2); -close_f1: - put_filp(f1); -no_files: - return error; + err_file: + put_filp(f); + return ERR_PTR(err); +} + +void free_write_pipe(struct file *f) +{ + mntput(f->f_vfsmnt); + dput(f->f_dentry); + put_filp(f); +} + +struct file *create_read_pipe(struct file *wrf) +{ + struct file *f = get_empty_filp(); + if (!f) + return ERR_PTR(-ENFILE); + + /* Grab pipe from the writer */ + f->f_vfsmnt = mntget(wrf->f_vfsmnt); + f->f_dentry = dget(wrf->f_dentry); + f->f_mapping = wrf->f_dentry->d_inode->i_mapping; + + f->f_pos = 0; + f->f_flags = O_RDONLY; + f->f_op = &read_pipe_fops; + f->f_mode = FMODE_READ; + f->f_version = 0; + + return f; +} + +int do_pipe(int *fd) +{ + struct file *fw, *fr; + int error; + int fdw, fdr; + + fw = create_write_pipe(); + if (IS_ERR(fw)) + return PTR_ERR(fw); + fr = create_read_pipe(fw); + error = PTR_ERR(fr); + if (IS_ERR(fr)) + goto err_write_pipe; + + error = get_unused_fd(); + if (error < 0) + goto err_read_pipe; + fdr = error; + + error = get_unused_fd(); + if (error < 0) + goto err_fdr; + fdw = error; + + fd_install(fdr, fr); + fd_install(fdw, fw); + fd[0] = fdr; + fd[1] = fdw; + + return 0; + + err_fdr: + put_unused_fd(fdr); + err_read_pipe: + put_filp(fr); + err_write_pipe: + free_write_pipe(fw); + return error; } /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 3493d2828f7d..2e29a2edaeec 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1641,6 +1641,9 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern struct file *create_read_pipe(struct file *f); +extern struct file *create_write_pipe(void); +extern void free_write_pipe(struct file *); extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); -- cgit v1.3-8-gc7d7