#include "../llite/llite_internal.h"
-const struct cl_req_operations ccc_req_ops;
+static const struct cl_req_operations ccc_req_ops;
/*
* ccc_ prefix stands for "Common Client Code".
*
*/
-void *ccc_key_init(const struct lu_context *ctx,
- struct lu_context_key *key)
+void *ccc_key_init(const struct lu_context *ctx, struct lu_context_key *key)
{
struct ccc_thread_info *info;
- OBD_SLAB_ALLOC_PTR_GFP(info, ccc_thread_kmem, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(info, ccc_thread_kmem, GFP_NOFS);
if (info == NULL)
info = ERR_PTR(-ENOMEM);
return info;
{
struct ccc_session *session;
- OBD_SLAB_ALLOC_PTR_GFP(session, ccc_session_kmem, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(session, ccc_session_kmem, GFP_NOFS);
if (session == NULL)
session = ERR_PTR(-ENOMEM);
return session;
struct ccc_req *vrq;
int result;
- OBD_SLAB_ALLOC_PTR_GFP(vrq, ccc_req_kmem, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(vrq, ccc_req_kmem, GFP_NOFS);
if (vrq != NULL) {
cl_req_slice_add(req, &vrq->crq_cl, dev, &ccc_req_ops);
result = 0;
struct ccc_object *vob;
struct lu_object *obj;
- OBD_SLAB_ALLOC_PTR_GFP(vob, ccc_object_kmem, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(vob, ccc_object_kmem, GFP_NOFS);
if (vob != NULL) {
struct cl_object_header *hdr;
CLOBINVRNT(env, obj, ccc_object_invariant(obj));
- OBD_SLAB_ALLOC_PTR_GFP(clk, ccc_lock_kmem, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(clk, ccc_lock_kmem, GFP_NOFS);
if (clk != NULL) {
cl_lock_slice_add(lock, &clk->clk_cl, obj, lkops);
result = 0;
void ccc_io_update_iov(const struct lu_env *env,
struct ccc_io *cio, struct cl_io *io)
{
- int i;
size_t size = io->u.ci_rw.crw_count;
- cio->cui_iov_olen = 0;
- if (!cl_is_normalio(env, io) || cio->cui_tot_nrsegs == 0)
+ if (!cl_is_normalio(env, io) || cio->cui_iter == NULL)
return;
- for (i = 0; i < cio->cui_tot_nrsegs; i++) {
- struct iovec *iv = &cio->cui_iov[i];
-
- if (iv->iov_len < size)
- size -= iv->iov_len;
- else {
- if (iv->iov_len > size) {
- cio->cui_iov_olen = iv->iov_len;
- iv->iov_len = size;
- }
- break;
- }
- }
-
- cio->cui_nrsegs = i + 1;
- LASSERTF(cio->cui_tot_nrsegs >= cio->cui_nrsegs,
- "tot_nrsegs: %lu, nrsegs: %lu\n",
- cio->cui_tot_nrsegs, cio->cui_nrsegs);
+ iov_iter_truncate(cio->cui_iter, size);
}
int ccc_io_one_lock(const struct lu_env *env, struct cl_io *io,
if (!cl_is_normalio(env, io))
return;
- LASSERT(cio->cui_tot_nrsegs >= cio->cui_nrsegs);
- LASSERT(cio->cui_tot_count >= nob);
-
- cio->cui_iov += cio->cui_nrsegs;
- cio->cui_tot_nrsegs -= cio->cui_nrsegs;
- cio->cui_tot_count -= nob;
-
- /* update the iov */
- if (cio->cui_iov_olen > 0) {
- struct iovec *iv;
-
- cio->cui_iov--;
- cio->cui_tot_nrsegs++;
- iv = &cio->cui_iov[0];
- if (io->ci_continue) {
- iv->iov_base += iv->iov_len;
- LASSERT(cio->cui_iov_olen > iv->iov_len);
- iv->iov_len = cio->cui_iov_olen - iv->iov_len;
- } else {
- /* restore the iov_len, in case of restart io. */
- iv->iov_len = cio->cui_iov_olen;
- }
- cio->cui_iov_olen = 0;
- }
+ iov_iter_reexpand(cio->cui_iter, cio->cui_tot_count -= nob);
}
/**
JOBSTATS_JOBID_SIZE);
}
-const struct cl_req_operations ccc_req_ops = {
+static const struct cl_req_operations ccc_req_ops = {
.cro_attr_set = ccc_req_attr_set,
.cro_completion = ccc_req_completion
};
#include "cl_object.h"
-struct ll_file_data *ll_file_data_get(void)
+static int
+ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg);
+
+static int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
+ bool *lease_broken);
+
+static enum llioc_iter
+ll_iocontrol_call(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long arg, int *rcp);
+
+static struct ll_file_data *ll_file_data_get(void)
{
struct ll_file_data *fd;
- OBD_SLAB_ALLOC_PTR_GFP(fd, ll_file_data_slab, __GFP_IO);
+ OBD_SLAB_ALLOC_PTR_GFP(fd, ll_file_data_slab, GFP_NOFS);
if (fd == NULL)
return NULL;
fd->fd_write_failed = false;
return rc;
}
-int ll_md_close(struct obd_export *md_exp, struct inode *inode,
- struct file *file)
+static int ll_md_close(struct obd_export *md_exp, struct inode *inode,
+ struct file *file)
{
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
struct ll_inode_info *lli = ll_i2info(inode);
return md_set_open_replay_data(md_exp, och, it);
}
-int ll_local_open(struct file *file, struct lookup_intent *it,
- struct ll_file_data *fd, struct obd_client_handle *och)
+static int ll_local_open(struct file *file, struct lookup_intent *it,
+ struct ll_file_data *fd, struct obd_client_handle *och)
{
struct inode *inode = file->f_dentry->d_inode;
struct ll_inode_info *lli = ll_i2info(inode);
/**
* Acquire a lease and open the file.
*/
-struct obd_client_handle *ll_lease_open(struct inode *inode, struct file *file,
- fmode_t fmode, __u64 open_flags)
+static struct obd_client_handle *
+ll_lease_open(struct inode *inode, struct file *file, fmode_t fmode,
+ __u64 open_flags)
{
struct lookup_intent it = { .it_op = IT_OPEN };
struct ll_sb_info *sbi = ll_i2sbi(inode);
OBD_FREE_PTR(och);
return ERR_PTR(rc);
}
-EXPORT_SYMBOL(ll_lease_open);
/**
* Release lease and close the file.
* It will check if the lease has ever broken.
*/
-int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
- bool *lease_broken)
+static int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
+ bool *lease_broken)
{
struct ldlm_lock *lock;
bool cancelled = true;
NULL);
return rc;
}
-EXPORT_SYMBOL(ll_lease_close);
/* Fills the obdo with the attributes for the lsm */
static int ll_lsm_getattr(struct lov_stripe_md *lsm, struct obd_export *exp,
switch (vio->cui_io_subtype) {
case IO_NORMAL:
- cio->cui_iov = args->u.normal.via_iov;
- cio->cui_nrsegs = args->u.normal.via_nrsegs;
- cio->cui_tot_nrsegs = cio->cui_nrsegs;
+ cio->cui_iter = args->u.normal.via_iter;
cio->cui_iocb = args->u.normal.via_iocb;
if ((iot == CIT_WRITE) &&
!(cio->cui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
return result;
}
- static ssize_t ll_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t ll_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct lu_env *env;
struct vvp_io_args *args;
- size_t count = 0;
ssize_t result;
int refcheck;
- result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
- if (result)
- return result;
-
env = cl_env_get(&refcheck);
if (IS_ERR(env))
return PTR_ERR(env);
args = vvp_env_args(env, IO_NORMAL);
- args->u.normal.via_iov = (struct iovec *)iov;
- args->u.normal.via_nrsegs = nr_segs;
+ args->u.normal.via_iter = to;
args->u.normal.via_iocb = iocb;
result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_READ,
- &iocb->ki_pos, count);
- cl_env_put(env, &refcheck);
- return result;
- }
-
- static ssize_t ll_file_read(struct file *file, char *buf, size_t count,
- loff_t *ppos)
- {
- struct lu_env *env;
- struct iovec *local_iov;
- struct kiocb *kiocb;
- ssize_t result;
- int refcheck;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- return PTR_ERR(env);
-
- local_iov = &vvp_env_info(env)->vti_local_iov;
- kiocb = &vvp_env_info(env)->vti_kiocb;
- local_iov->iov_base = (void __user *)buf;
- local_iov->iov_len = count;
- init_sync_kiocb(kiocb, file);
- kiocb->ki_pos = *ppos;
- kiocb->ki_nbytes = count;
-
- result = ll_file_aio_read(kiocb, local_iov, 1, kiocb->ki_pos);
- *ppos = kiocb->ki_pos;
-
+ &iocb->ki_pos, iov_iter_count(to));
cl_env_put(env, &refcheck);
return result;
}
/*
* Write to a file (through the page cache).
*/
- static ssize_t ll_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct lu_env *env;
struct vvp_io_args *args;
- size_t count = 0;
ssize_t result;
int refcheck;
- result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
- if (result)
- return result;
-
env = cl_env_get(&refcheck);
if (IS_ERR(env))
return PTR_ERR(env);
args = vvp_env_args(env, IO_NORMAL);
- args->u.normal.via_iov = (struct iovec *)iov;
- args->u.normal.via_nrsegs = nr_segs;
+ args->u.normal.via_iter = from;
args->u.normal.via_iocb = iocb;
result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_WRITE,
- &iocb->ki_pos, count);
+ &iocb->ki_pos, iov_iter_count(from));
cl_env_put(env, &refcheck);
return result;
}
- static ssize_t ll_file_write(struct file *file, const char *buf, size_t count,
- loff_t *ppos)
- {
- struct lu_env *env;
- struct iovec *local_iov;
- struct kiocb *kiocb;
- ssize_t result;
- int refcheck;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- return PTR_ERR(env);
-
- local_iov = &vvp_env_info(env)->vti_local_iov;
- kiocb = &vvp_env_info(env)->vti_kiocb;
- local_iov->iov_base = (void __user *)buf;
- local_iov->iov_len = count;
- init_sync_kiocb(kiocb, file);
- kiocb->ki_pos = *ppos;
- kiocb->ki_nbytes = count;
-
- result = ll_file_aio_write(kiocb, local_iov, 1, kiocb->ki_pos);
- *ppos = kiocb->ki_pos;
-
- cl_env_put(env, &refcheck);
- return result;
- }
-
-
-
/*
* Send file content (through pagecache) somewhere with helper
*/
struct md_op_data *op_data;
int rc, lmmsize;
- rc = ll_get_max_mdsize(sbi, &lmmsize);
+ rc = ll_get_default_mdsize(sbi, &lmmsize);
if (rc)
return rc;
return rc;
}
-int ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg)
+static int
+ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg)
{
struct ll_inode_info *lli = ll_i2info(inode);
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
* Get size for inode for which FIEMAP mapping is requested.
* Make the FIEMAP get_info call and returns the result.
*/
-int ll_do_fiemap(struct inode *inode, struct ll_user_fiemap *fiemap,
- int num_bytes)
+static int ll_do_fiemap(struct inode *inode, struct ll_user_fiemap *fiemap,
+ size_t num_bytes)
{
struct obd_export *exp = ll_i2dtexp(inode);
struct lov_stripe_md *lsm = NULL;
struct ll_fiemap_info_key fm_key = { .name = KEY_FIEMAP, };
- int vallen = num_bytes;
+ __u32 vallen = num_bytes;
int rc;
/* Checks for fiemap flags */
if (get_user(extent_count,
&((struct ll_user_fiemap __user *)arg)->fm_extent_count))
return -EFAULT;
+
+ if (extent_count >=
+ (SIZE_MAX - sizeof(*fiemap_s)) / sizeof(struct ll_fiemap_extent))
+ return -EINVAL;
num_bytes = sizeof(*fiemap_s) + (extent_count *
sizeof(struct ll_fiemap_extent));
return rc;
}
-long ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long
+ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file->f_dentry->d_inode;
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
}
-loff_t ll_file_seek(struct file *file, loff_t offset, int origin)
+static loff_t ll_file_seek(struct file *file, loff_t offset, int origin)
{
struct inode *inode = file->f_dentry->d_inode;
loff_t retval, eof = 0;
return retval;
}
-int ll_flush(struct file *file, fl_owner_t id)
+static int ll_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file->f_dentry->d_inode;
struct ll_inode_info *lli = ll_i2info(inode);
/**
* Called to make sure a portion of file has been written out.
- * if @local_only is not true, it will send OST_SYNC RPCs to ost.
+ * if @mode is not CL_FSYNC_LOCAL, it will send OST_SYNC RPCs to OST.
*
* Return how many pages have been written.
*/
if (!err)
ptlrpc_req_finished(req);
- if (datasync && S_ISREG(inode->i_mode)) {
+ if (S_ISREG(inode->i_mode)) {
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
- err = cl_sync_file_range(inode, 0, OBD_OBJECT_EOF,
- CL_FSYNC_ALL, 0);
+ err = cl_sync_file_range(inode, start, end, CL_FSYNC_ALL, 0);
if (rc == 0 && err < 0)
rc = err;
if (rc < 0)
return rc;
}
-int ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
+static int
+ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock)
{
struct inode *inode = file->f_dentry->d_inode;
struct ll_sb_info *sbi = ll_i2sbi(inode);
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_FLOCK, 1);
- if (file_lock->fl_flags & FL_FLOCK) {
+ if (file_lock->fl_flags & FL_FLOCK)
LASSERT((cmd == F_SETLKW) || (cmd == F_SETLK));
- /* flocks are whole-file locks */
- flock.l_flock.end = OFFSET_MAX;
- /* For flocks owner is determined by the local file descriptor*/
- flock.l_flock.owner = (unsigned long)file_lock->fl_file;
- } else if (file_lock->fl_flags & FL_POSIX) {
- flock.l_flock.owner = (unsigned long)file_lock->fl_owner;
- flock.l_flock.start = file_lock->fl_start;
- flock.l_flock.end = file_lock->fl_end;
- } else {
+ else if (!(file_lock->fl_flags & FL_POSIX))
return -EINVAL;
- }
+
+ flock.l_flock.owner = (unsigned long)file_lock->fl_owner;
flock.l_flock.pid = file_lock->fl_pid;
+ flock.l_flock.start = file_lock->fl_start;
+ flock.l_flock.end = file_lock->fl_end;
/* Somewhat ugly workaround for svc lockd.
* lockd installs custom fl_lmops->lm_compare_owner that checks
return rc;
}
-int ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
+static int
+ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
{
return -ENOSYS;
}
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return 0;
} else if (rc != 0) {
- CERROR("%s: revalidate FID "DFID" error: rc = %d\n",
- ll_get_fsname(inode->i_sb, NULL, 0),
- PFID(ll_inode2fid(inode)), rc);
+ CDEBUG_LIMIT((rc == -EACCES || rc == -EIDRM) ? D_INFO : D_ERROR,
+ "%s: revalidate FID "DFID" error: rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0),
+ PFID(ll_inode2fid(inode)), rc);
}
return rc;
}
-int __ll_inode_revalidate_it(struct dentry *dentry, struct lookup_intent *it,
- __u64 ibits)
+static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
{
struct inode *inode = dentry->d_inode;
struct ptlrpc_request *req = NULL;
int ealen = 0;
if (S_ISREG(inode->i_mode)) {
- rc = ll_get_max_mdsize(sbi, &ealen);
+ rc = ll_get_default_mdsize(sbi, &ealen);
if (rc)
return rc;
valid |= OBD_MD_FLEASIZE | OBD_MD_FLMODEASIZE;
return rc;
}
-int ll_inode_revalidate_it(struct dentry *dentry, struct lookup_intent *it,
- __u64 ibits)
+static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
{
struct inode *inode = dentry->d_inode;
int rc;
- rc = __ll_inode_revalidate_it(dentry, it, ibits);
+ rc = __ll_inode_revalidate(dentry, ibits);
if (rc != 0)
return rc;
return rc;
}
-int ll_getattr_it(struct vfsmount *mnt, struct dentry *de,
- struct lookup_intent *it, struct kstat *stat)
+int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
{
struct inode *inode = de->d_inode;
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct ll_inode_info *lli = ll_i2info(inode);
int res = 0;
- res = ll_inode_revalidate_it(de, it, MDS_INODELOCK_UPDATE |
- MDS_INODELOCK_LOOKUP);
+ res = ll_inode_revalidate(de, MDS_INODELOCK_UPDATE |
+ MDS_INODELOCK_LOOKUP);
ll_stats_ops_tally(sbi, LPROC_LL_GETATTR, 1);
if (res)
return 0;
}
-int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
-{
- struct lookup_intent it = { .it_op = IT_GETATTR };
-
- return ll_getattr_it(mnt, de, &it, stat);
-}
-int ll_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- __u64 start, __u64 len)
+static int ll_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len)
{
int rc;
size_t num_bytes;
fiemap->fm_extent_count = fieinfo->fi_extents_max;
fiemap->fm_start = start;
fiemap->fm_length = len;
- memcpy(&fiemap->fm_extents[0], fieinfo->fi_extents_start,
- sizeof(struct ll_fiemap_extent));
+ if (extent_count > 0)
+ memcpy(&fiemap->fm_extents[0], fieinfo->fi_extents_start,
+ sizeof(struct ll_fiemap_extent));
rc = ll_do_fiemap(inode, fiemap, num_bytes);
fieinfo->fi_flags = fiemap->fm_flags;
fieinfo->fi_extents_mapped = fiemap->fm_mapped_extents;
- memcpy(fieinfo->fi_extents_start, &fiemap->fm_extents[0],
- fiemap->fm_mapped_extents * sizeof(struct ll_fiemap_extent));
+ if (extent_count > 0)
+ memcpy(fieinfo->fi_extents_start, &fiemap->fm_extents[0],
+ fiemap->fm_mapped_extents *
+ sizeof(struct ll_fiemap_extent));
OBD_FREE_LARGE(fiemap, num_bytes);
return rc;
}
-struct posix_acl * ll_get_acl(struct inode *inode, int type)
+struct posix_acl *ll_get_acl(struct inode *inode, int type)
{
struct ll_inode_info *lli = ll_i2info(inode);
struct posix_acl *acl = NULL;
* need to do it before permission check. */
if (inode == inode->i_sb->s_root->d_inode) {
- struct lookup_intent it = { .it_op = IT_LOOKUP };
-
- rc = __ll_inode_revalidate_it(inode->i_sb->s_root, &it,
- MDS_INODELOCK_LOOKUP);
+ rc = __ll_inode_revalidate(inode->i_sb->s_root,
+ MDS_INODELOCK_LOOKUP);
if (rc)
return rc;
}
/* -o localflock - only provides locally consistent flock locks */
struct file_operations ll_file_operations = {
- .read = ll_file_read,
- .aio_read = ll_file_aio_read,
- .write = ll_file_write,
- .aio_write = ll_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = ll_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = ll_file_write_iter,
.unlocked_ioctl = ll_file_ioctl,
.open = ll_file_open,
.release = ll_file_release,
};
struct file_operations ll_file_operations_flock = {
- .read = ll_file_read,
- .aio_read = ll_file_aio_read,
- .write = ll_file_write,
- .aio_write = ll_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = ll_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = ll_file_write_iter,
.unlocked_ioctl = ll_file_ioctl,
.open = ll_file_open,
.release = ll_file_release,
/* These are for -o noflock - to return ENOSYS on flock calls */
struct file_operations ll_file_operations_noflock = {
- .read = ll_file_read,
- .aio_read = ll_file_aio_read,
- .write = ll_file_write,
- .aio_write = ll_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = ll_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = ll_file_write_iter,
.unlocked_ioctl = ll_file_ioctl,
.open = ll_file_open,
.release = ll_file_release,
EXPORT_SYMBOL(ll_iocontrol_register);
EXPORT_SYMBOL(ll_iocontrol_unregister);
-enum llioc_iter ll_iocontrol_call(struct inode *inode, struct file *file,
- unsigned int cmd, unsigned long arg, int *rcp)
+static enum llioc_iter
+ll_iocontrol_call(struct inode *inode, struct file *file,
+ unsigned int cmd, unsigned long arg, int *rcp)
{
enum llioc_iter ret = LLIOC_CONT;
struct llioc_data *data;
* layout here. Please note that we can't use the LVB buffer in
* completion AST because it doesn't have a large enough buffer */
oc = ll_mdscapa_get(inode);
- rc = ll_get_max_mdsize(sbi, &lmmsize);
+ rc = ll_get_default_mdsize(sbi, &lmmsize);
if (rc == 0)
rc = md_getxattr(sbi->ll_md_exp, ll_inode2fid(inode), oc,
OBD_MD_FLXATTR, XATTR_NAME_LOV, NULL, 0,
return rc;
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (body == NULL || body->eadatasize > lmmsize)
+ if (body == NULL)
GOTO(out, rc = -EPROTO);
lmmsize = body->eadatasize;
if (lvb_ready) {
/* layout_gen must be valid if layout lock is not
* cancelled and stripe has already set */
- *gen = lli->lli_layout_gen;
+ *gen = ll_layout_version_get(lli);
rc = 0;
}
GOTO(out, rc);
};
int rc;
- *gen = lli->lli_layout_gen;
- if (!(sbi->ll_flags & LL_SBI_LAYOUT_LOCK))
+ *gen = ll_layout_version_get(lli);
+ if (!(sbi->ll_flags & LL_SBI_LAYOUT_LOCK) || *gen != LL_LAYOUT_GEN_NONE)
return 0;
/* sanity checks */
LASSERT(fid_is_sane(ll_inode2fid(inode)));
LASSERT(S_ISREG(inode->i_mode));
- /* mostly layout lock is caching on the local side, so try to match
- * it before grabbing layout lock mutex. */
- mode = ll_take_md_lock(inode, MDS_INODELOCK_LAYOUT, &lockh, 0,
- LCK_CR | LCK_CW | LCK_PR | LCK_PW);
- if (mode != 0) { /* hit cached lock */
- rc = ll_layout_lock_set(&lockh, mode, inode, gen, false);
- if (rc == 0)
- return 0;
-
- /* better hold lli_layout_mutex to try again otherwise
- * it will have starvation problem. */
- }
-
/* take layout lock mutex to enqueue layout lock exclusively. */
mutex_lock(&lli->lli_layout_mutex);
again:
- /* try again. Maybe somebody else has done this. */
+ /* mostly layout lock is caching on the local side, so try to match
+ * it before grabbing layout lock mutex. */
mode = ll_take_md_lock(inode, MDS_INODELOCK_LAYOUT, &lockh, 0,
LCK_CR | LCK_CW | LCK_PR | LCK_PW);
if (mode != 0) { /* hit cached lock */
#define LUSTRE_FPRIVATE(file) ((file)->private_data)
struct ll_dentry_data {
- int lld_cwd_count;
- int lld_mnt_count;
- struct obd_client_handle lld_cwd_och;
- struct obd_client_handle lld_mnt_och;
struct lookup_intent *lld_it;
unsigned int lld_sa_generation;
unsigned int lld_invalid:1;
#define ll_d2d(de) ((struct ll_dentry_data*)((de)->d_fsdata))
-extern struct file_operations ll_pgcache_seq_fops;
-
#define LLI_INODE_MAGIC 0x111d0de5
#define LLI_INODE_DEAD 0xdeadd00d
/* Sizeon-on-MDS attributes are changed. An attribute update needs to
* be sent to MDS. */
LLIF_SOM_DIRTY = (1 << 3),
- /* File is contented */
- LLIF_CONTENDED = (1 << 4),
- /* Truncate uses server lock for this file */
- LLIF_SRVLOCK = (1 << 5),
/* File data is modified. */
- LLIF_DATA_MODIFIED = (1 << 6),
+ LLIF_DATA_MODIFIED = (1 << 4),
/* File is being restored */
- LLIF_FILE_RESTORING = (1 << 7),
+ LLIF_FILE_RESTORING = (1 << 5),
/* Xattr cache is attached to the file */
- LLIF_XATTR_CACHE = (1 << 8),
+ LLIF_XATTR_CACHE = (1 << 6),
};
struct ll_inode_info {
* cleanup the dir readahead. */
void *d_opendir_key;
struct ll_statahead_info *d_sai;
- struct posix_acl *d_def_acl;
/* protect statahead stuff. */
spinlock_t d_sa_lock;
/* "opendir_pid" is the token when lookup/revalid
#define lli_readdir_mutex u.d.d_readdir_mutex
#define lli_opendir_key u.d.d_opendir_key
#define lli_sai u.d.d_sai
-#define lli_def_acl u.d.d_def_acl
#define lli_sa_lock u.d.d_sa_lock
#define lli_opendir_pid u.d.d_opendir_pid
/* for non-directory */
struct {
- struct semaphore f_size_sem;
- void *f_size_sem_owner;
+ struct mutex f_size_mutex;
char *f_symlink_name;
__u64 f_maxbytes;
/*
/* for writepage() only to communicate to fsync */
int f_async_rc;
- /* volatile file criteria is based on file name, this
- * flag is used to keep the test result, so the strcmp
- * is done only once
- */
- bool f_volatile;
/*
* whenever a process try to read/write the file, the
* jobid of the process will be saved here, and it'll
char f_jobid[JOBSTATS_JOBID_SIZE];
} f;
-#define lli_size_sem u.f.f_size_sem
-#define lli_size_sem_owner u.f.f_size_sem_owner
+#define lli_size_mutex u.f.f_size_mutex
#define lli_symlink_name u.f.f_symlink_name
#define lli_maxbytes u.f.f_maxbytes
#define lli_trunc_sem u.f.f_trunc_sem
#define lli_agl_index u.f.f_agl_index
#define lli_async_rc u.f.f_async_rc
#define lli_jobid u.f.f_jobid
-#define lli_volatile u.f.f_volatile
} u;
/* mutex to request for layout lock exclusively. */
struct mutex lli_layout_mutex;
- /* valid only inside LAYOUT ibits lock, protected by lli_layout_mutex */
+ /* Layout version, protected by lli_layout_lock */
__u32 lli_layout_gen;
+ spinlock_t lli_layout_lock;
struct rw_semaphore lli_xattrs_list_rwsem;
struct mutex lli_xattrs_enq_lock;
struct list_head lli_xattrs;/* ll_xattr_entry->xe_list */
};
+static inline __u32 ll_layout_version_get(struct ll_inode_info *lli)
+{
+ __u32 gen;
+
+ spin_lock(&lli->lli_layout_lock);
+ gen = lli->lli_layout_gen;
+ spin_unlock(&lli->lli_layout_lock);
+
+ return gen;
+}
+
+static inline void ll_layout_version_set(struct ll_inode_info *lli, __u32 gen)
+{
+ spin_lock(&lli->lli_layout_lock);
+ lli->lli_layout_gen = gen;
+ spin_unlock(&lli->lli_layout_lock);
+}
+
int ll_xattr_cache_destroy(struct inode *inode);
int ll_xattr_cache_get(struct inode *inode,
* Locking to guarantee consistency of non-atomic updates to long long i_size,
* consistency between file size and KMS.
*
- * Implemented by ->lli_size_sem and ->lsm_lock, nested in that order.
+ * Implemented by ->lli_size_mutex and ->lsm_lock, nested in that order.
*/
void ll_inode_size_lock(struct inode *inode);
"xattr", \
}
-/* default value for ll_sb_info->contention_time */
-#define SBI_DEFAULT_CONTENTION_SECONDS 60
-/* default value for lockless_truncate_enable */
-#define SBI_DEFAULT_LOCKLESS_TRUNCATE_ENABLE 1
#define RCE_HASHES 32
struct rmtacl_ctl_entry {
return &lli->lli_vfs_inode;
}
-struct it_cb_data {
- struct inode *icbd_parent;
- struct dentry **icbd_childp;
- obd_id hash;
-};
-
__u32 ll_i2suppgid(struct inode *i);
void ll_i2gids(__u32 *suppgids, struct inode *i1,struct inode *i2);
{
#if BITS_PER_LONG == 32
return 1;
+#elif defined(CONFIG_COMPAT)
+ return unlikely(is_compat_task() || (sbi->ll_flags & LL_SBI_32BIT_API));
#else
- return unlikely(
-#ifdef CONFIG_COMPAT
- is_compat_task() ||
-#endif
- (sbi->ll_flags & LL_SBI_32BIT_API)
- );
+ return unlikely(sbi->ll_flags & LL_SBI_32BIT_API);
#endif
}
-#define LLAP_MAGIC 98764321
-
-extern struct kmem_cache *ll_async_page_slab;
-extern size_t ll_async_page_slab_size;
-
void ll_ra_read_in(struct file *f, struct ll_ra_read *rar);
void ll_ra_read_ex(struct file *f, struct ll_ra_read *rar);
struct ll_ra_read *ll_ra_read_get(struct file *f);
/* llite/dir.c */
void ll_release_page(struct page *page, int remove);
-extern struct file_operations ll_dir_operations;
-extern struct inode_operations ll_dir_inode_operations;
+extern const struct file_operations ll_dir_operations;
+extern const struct inode_operations ll_dir_inode_operations;
struct page *ll_get_dir_page(struct inode *dir, __u64 hash,
struct ll_dir_chain *chain);
int ll_dir_read(struct inode *inode, struct dir_context *ctx);
int ll_get_mdt_idx(struct inode *inode);
/* llite/namei.c */
+extern const struct inode_operations ll_special_inode_operations;
+
int ll_objects_destroy(struct ptlrpc_request *request,
struct inode *dir);
struct inode *ll_iget(struct super_block *sb, ino_t hash,
int ll_commit_write(struct file *, struct page *, unsigned from, unsigned to);
int ll_writepage(struct page *page, struct writeback_control *wbc);
int ll_writepages(struct address_space *, struct writeback_control *wbc);
-void ll_removepage(struct page *page);
int ll_readpage(struct file *file, struct page *page);
void ll_readahead_init(struct inode *inode, struct ll_readahead_state *ras);
-int ll_file_punch(struct inode *, loff_t, int);
-ssize_t ll_file_lockless_io(struct file *, char *, size_t, loff_t *, int);
-void ll_clear_file_contended(struct inode*);
-int ll_sync_page_range(struct inode *, struct address_space *, loff_t, size_t);
int ll_readahead(const struct lu_env *env, struct cl_io *io,
struct ll_readahead_state *ras, struct address_space *mapping,
struct cl_page_list *queue, int flags);
+#ifndef MS_HAS_NEW_AOPS
+extern const struct address_space_operations ll_aops;
+#else
+extern const struct address_space_operations_ext ll_aops;
+#endif
+
/* llite/file.c */
extern struct file_operations ll_file_operations;
extern struct file_operations ll_file_operations_flock;
extern struct file_operations ll_file_operations_noflock;
extern struct inode_operations ll_file_inode_operations;
-extern int ll_inode_revalidate_it(struct dentry *, struct lookup_intent *,
- __u64);
extern int ll_have_md_lock(struct inode *inode, __u64 *bits,
ldlm_mode_t l_req_mode);
extern ldlm_mode_t ll_take_md_lock(struct inode *inode, __u64 bits,
struct lustre_handle *lockh, __u64 flags,
ldlm_mode_t mode);
-int __ll_inode_revalidate_it(struct dentry *, struct lookup_intent *,
- __u64 bits);
-int ll_revalidate_nd(struct dentry *dentry, unsigned int flags);
int ll_file_open(struct inode *inode, struct file *file);
int ll_file_release(struct inode *inode, struct file *file);
int ll_glimpse_ioctl(struct ll_sb_info *sbi,
struct lov_stripe_md *lsm, lstat_t *st);
void ll_ioepoch_open(struct ll_inode_info *lli, __u64 ioepoch);
-int ll_local_open(struct file *file,
- struct lookup_intent *it, struct ll_file_data *fd,
- struct obd_client_handle *och);
int ll_release_openhandle(struct dentry *, struct lookup_intent *);
-int ll_md_close(struct obd_export *md_exp, struct inode *inode,
- struct file *file);
int ll_md_real_close(struct inode *inode, fmode_t fmode);
void ll_ioepoch_close(struct inode *inode, struct md_op_data *op_data,
struct obd_client_handle **och, unsigned long flags);
int ll_som_update(struct inode *inode, struct md_op_data *op_data);
int ll_inode_getattr(struct inode *inode, struct obdo *obdo,
__u64 ioepoch, int sync);
-int ll_md_setattr(struct dentry *dentry, struct md_op_data *op_data,
- struct md_open_data **mod);
void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data,
struct lustre_handle *fh);
-int ll_getattr_it(struct vfsmount *mnt, struct dentry *de,
- struct lookup_intent *it, struct kstat *stat);
int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat);
-struct ll_file_data *ll_file_data_get(void);
-struct posix_acl * ll_get_acl(struct inode *inode, int type);
+struct posix_acl *ll_get_acl(struct inode *inode, int type);
int ll_inode_permission(struct inode *inode, int mask);
int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
int *lmm_size, struct ptlrpc_request **request);
int ll_fsync(struct file *file, loff_t start, loff_t end, int data);
-int ll_do_fiemap(struct inode *inode, struct ll_user_fiemap *fiemap,
- int num_bytes);
int ll_merge_lvb(const struct lu_env *env, struct inode *inode);
-int ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg);
-int ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg);
int ll_fid2path(struct inode *inode, void *arg);
int ll_data_version(struct inode *inode, __u64 *data_version, int extent_lock);
int ll_hsm_release(struct inode *inode);
-struct obd_client_handle *ll_lease_open(struct inode *inode, struct file *file,
- fmode_t mode, __u64 flags);
-int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
- bool *lease_broken);
-
/* llite/dcache.c */
int ll_d_init(struct dentry *de);
-extern struct dentry_operations ll_d_ops;
+extern const struct dentry_operations ll_d_ops;
void ll_intent_drop_lock(struct lookup_intent *);
void ll_intent_release(struct lookup_intent *);
void ll_invalidate_aliases(struct inode *);
-void ll_frob_intent(struct lookup_intent **itp, struct lookup_intent *deft);
void ll_lookup_finish_locks(struct lookup_intent *it, struct dentry *dentry);
-int ll_dcompare(const struct dentry *parent, const struct dentry *dentry,
- unsigned int len, const char *str, const struct qstr *d_name);
int ll_revalidate_it_finish(struct ptlrpc_request *request,
struct lookup_intent *it, struct dentry *de);
/* llite/llite_lib.c */
extern struct super_operations lustre_super_operations;
-char *ll_read_opt(const char *opt, char *data);
void ll_lli_init(struct ll_inode_info *lli);
int ll_fill_super(struct super_block *sb, struct vfsmount *mnt);
void ll_put_super(struct super_block *sb);
void ll_kill_super(struct super_block *sb);
struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock);
-struct inode *ll_inode_from_lock(struct ldlm_lock *lock);
void ll_clear_inode(struct inode *inode);
int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import);
int ll_setattr(struct dentry *de, struct iattr *attr);
int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
struct super_block *, struct lookup_intent *);
void lustre_dump_dentry(struct dentry *, int recur);
-void lustre_dump_inode(struct inode *);
int ll_obd_statfs(struct inode *inode, void *arg);
int ll_get_max_mdsize(struct ll_sb_info *sbi, int *max_mdsize);
+int ll_get_default_mdsize(struct ll_sb_info *sbi, int *default_mdsize);
+int ll_get_max_cookiesize(struct ll_sb_info *sbi, int *max_cookiesize);
+int ll_get_default_cookiesize(struct ll_sb_info *sbi, int *default_cookiesize);
int ll_process_config(struct lustre_cfg *lcfg);
struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
struct inode *i1, struct inode *i2,
struct inode *search_inode_for_lustre(struct super_block *sb,
const struct lu_fid *fid);
-/* llite/special.c */
-extern struct inode_operations ll_special_inode_operations;
-extern struct file_operations ll_special_chr_inode_fops;
-extern struct file_operations ll_special_chr_file_fops;
-extern struct file_operations ll_special_blk_inode_fops;
-extern struct file_operations ll_special_fifo_inode_fops;
-extern struct file_operations ll_special_fifo_file_fops;
-extern struct file_operations ll_special_sock_inode_fops;
-
/* llite/symlink.c */
extern struct inode_operations ll_fast_symlink_inode_operations;
* Set when cui_bead has been initialized.
*/
int cui_ra_window_set;
- /**
- * Partially truncated page, that vvp_io_trunc_start() keeps locked
- * across truncate.
- */
- struct cl_page *cui_partpage;
};
/**
union {
struct {
struct kiocb *via_iocb;
- struct iovec *via_iov;
- unsigned long via_nrsegs;
+ struct iov_iter *via_iter;
} normal;
struct {
struct pipe_inode_info *via_pipe;
struct cl_page *lcc_page;
struct lu_env *lcc_env;
int lcc_refcheck;
- int lcc_created;
};
struct vvp_thread_info {
- struct ost_lvb vti_lvb;
- struct cl_2queue vti_queue;
struct iovec vti_local_iov;
struct vvp_io_args vti_args;
struct ra_io_arg vti_ria;
return &vvp_env_session(env)->vs_ios;
}
+int vvp_global_init(void);
+void vvp_global_fini(void);
+
void ll_queue_done_writing(struct inode *inode, unsigned long flags);
void ll_close_thread_shutdown(struct ll_close_queue *lcq);
int ll_close_thread_start(struct ll_close_queue **lcq_ret);
/* llite/llite_mmap.c */
-typedef struct rb_root rb_root_t;
-typedef struct rb_node rb_node_t;
-
-struct ll_lock_tree_node;
-struct ll_lock_tree {
- rb_root_t lt_root;
- struct list_head lt_locked_list;
- struct ll_file_data *lt_fd;
-};
int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last);
int ll_file_mmap(struct file * file, struct vm_area_struct * vma);
-struct ll_lock_tree_node * ll_node_from_inode(struct inode *inode, __u64 start,
- __u64 end, ldlm_mode_t mode);
void policy_from_vma(ldlm_policy_data_t *policy,
struct vm_area_struct *vma, unsigned long addr, size_t count);
struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr,
return fid;
}
-static inline int ll_mds_max_easize(struct super_block *sb)
-{
- return sbi2mdc(ll_s2sbi(sb))->cl_max_mds_easize;
-}
-
static inline __u64 ll_file_maxbytes(struct inode *inode)
{
return ll_i2info(inode)->lli_maxbytes;
extern struct kmem_cache *ll_remote_perm_cachep;
extern struct kmem_cache *ll_rmtperm_hash_cachep;
-struct hlist_head *alloc_rmtperm_hash(void);
void free_rmtperm_hash(struct hlist_head *hash);
int ll_update_remote_perm(struct inode *inode, struct mdt_remote_perm *perm);
int lustre_check_remote_perm(struct inode *inode, int mask);
void ll_capa_timer_callback(unsigned long unused);
struct obd_capa *ll_add_capa(struct inode *inode, struct obd_capa *ocapa);
-int ll_update_capa(struct obd_capa *ocapa, struct lustre_capa *capa);
void ll_capa_open(struct inode *inode);
void ll_capa_close(struct inode *inode);
*/
int cl_sb_init(struct super_block *sb);
int cl_sb_fini(struct super_block *sb);
-enum cl_lock_mode vvp_mode_from_vma(struct vm_area_struct *vma);
void ll_io_init(struct cl_io *io, const struct file *file, int write);
void ras_update(struct ll_sb_info *sbi, struct inode *inode,
struct ll_readahead_state *ras, unsigned long index,
unsigned hit);
void ll_ra_count_put(struct ll_sb_info *sbi, unsigned long len);
-int ll_is_file_contended(struct file *file);
void ll_ra_stats_inc(struct address_space *mapping, enum ra_stat which);
/* llite/llite_rmtacl.c */
unsigned int sai_skip_hidden;/* skipped hidden dentry count */
unsigned int sai_ls_all:1, /* "ls -al", do stat-ahead for
* hidden entries */
- sai_in_readpage:1,/* statahead is in readdir()*/
sai_agl_valid:1;/* AGL is valid for the dir */
wait_queue_head_t sai_waitq; /* stat-ahead wait queue */
struct ptlrpc_thread sai_thread; /* stat-ahead thread */
struct file *file, unsigned int cmd, unsigned long arg,
void *magic, int *rcp);
-enum llioc_iter ll_iocontrol_call(struct inode *inode, struct file *file,
- unsigned int cmd, unsigned long arg, int *rcp);
-
/* export functions */
/* Register ioctl block dynamatically for a regular file.
*
static inline void cl_isize_write_nolock(struct inode *inode, loff_t kms)
{
- LASSERT(down_trylock(&ll_i2info(inode)->lli_size_sem) != 0);
+ LASSERT(mutex_is_locked(&ll_i2info(inode)->lli_size_mutex));
i_size_write(inode, kms);
}
cl_page_put(env, page);
}
- if (io && lcc->lcc_created) {
- cl_io_end(env, io);
- cl_io_unlock(env, io);
- cl_io_iter_fini(env, io);
- cl_io_fini(env, io);
- }
cl_env_put(env, &lcc->lcc_refcheck);
}
result = cl_io_rw_init(env, io, CIT_WRITE, pos, PAGE_CACHE_SIZE);
if (result == 0) {
cio->cui_fd = LUSTRE_FPRIVATE(file);
- cio->cui_iov = NULL;
- cio->cui_nrsegs = 0;
+ cio->cui_iter = NULL;
result = cl_io_iter_init(env, io);
if (result == 0) {
result = cl_io_lock(env, io);
}
} else
result = io->ci_result;
- lcc->lcc_created = 1;
}
lcc->lcc_io = io;
int i;
for (i = 0; i < npages; i++) {
- if (pages[i] == NULL)
- break;
if (do_dirty)
set_page_dirty_lock(pages[i]);
page_cache_release(pages[i]);
}
-
- OBD_FREE_LARGE(pages, npages * sizeof(*pages));
+ kvfree(pages);
}
ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io,
#define MAX_DIO_SIZE ((MAX_MALLOC / sizeof(struct brw_page) * PAGE_CACHE_SIZE) & \
~(DT_MAX_BRW_SIZE - 1))
static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t file_offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t file_offset)
{
struct lu_env *env;
struct cl_io *io;
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct ccc_object *obj = cl_inode2ccc(inode);
- long count = iov_length(iov, nr_segs);
- long tot_bytes = 0, result = 0;
+ ssize_t count = iov_iter_count(iter);
+ ssize_t tot_bytes = 0, result = 0;
struct ll_inode_info *lli = ll_i2info(inode);
- unsigned long seg = 0;
long size = MAX_DIO_SIZE;
int refcheck;
if ((file_offset & ~CFS_PAGE_MASK) || (count & ~CFS_PAGE_MASK))
return -EINVAL;
- CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p), size=%lu (max %lu), "
- "offset=%lld=%llx, pages %lu (max %lu)\n",
+ CDEBUG(D_VFSTRACE,
+ "VFS Op:inode=%lu/%u(%p), size=%zd (max %lu), offset=%lld=%llx, pages %zd (max %lu)\n",
inode->i_ino, inode->i_generation, inode, count, MAX_DIO_SIZE,
file_offset, file_offset, count >> PAGE_CACHE_SHIFT,
MAX_DIO_SIZE >> PAGE_CACHE_SHIFT);
/* Check that all user buffers are aligned as well */
- for (seg = 0; seg < nr_segs; seg++) {
- if (((unsigned long)iov[seg].iov_base & ~CFS_PAGE_MASK) ||
- (iov[seg].iov_len & ~CFS_PAGE_MASK))
- return -EINVAL;
- }
+ if (iov_iter_alignment(iter) & ~CFS_PAGE_MASK)
+ return -EINVAL;
env = cl_env_get(&refcheck);
LASSERT(!IS_ERR(env));
mutex_lock(&inode->i_mutex);
LASSERT(obj->cob_transient_pages == 0);
- for (seg = 0; seg < nr_segs; seg++) {
- long iov_left = iov[seg].iov_len;
- unsigned long user_addr = (unsigned long)iov[seg].iov_base;
+ while (iov_iter_count(iter)) {
+ struct page **pages;
+ size_t offs;
+ count = min_t(size_t, iov_iter_count(iter), size);
if (rw == READ) {
if (file_offset >= i_size_read(inode))
break;
- if (file_offset + iov_left > i_size_read(inode))
- iov_left = i_size_read(inode) - file_offset;
+ if (file_offset + count > i_size_read(inode))
+ count = i_size_read(inode) - file_offset;
}
- while (iov_left > 0) {
- struct page **pages;
- int page_count, max_pages = 0;
- long bytes;
-
- bytes = min(size, iov_left);
- page_count = ll_get_user_pages(rw, user_addr, bytes,
- &pages, &max_pages);
- if (likely(page_count > 0)) {
- if (unlikely(page_count < max_pages))
- bytes = page_count << PAGE_CACHE_SHIFT;
- result = ll_direct_IO_26_seg(env, io, rw, inode,
- file->f_mapping,
- bytes, file_offset,
- pages, page_count);
- ll_free_user_pages(pages, max_pages, rw==READ);
- } else if (page_count == 0) {
- GOTO(out, result = -EFAULT);
- } else {
- result = page_count;
- }
- if (unlikely(result <= 0)) {
- /* If we can't allocate a large enough buffer
- * for the request, shrink it to a smaller
- * PAGE_SIZE multiple and try again.
- * We should always be able to kmalloc for a
- * page worth of page pointers = 4MB on i386. */
- if (result == -ENOMEM &&
- size > (PAGE_CACHE_SIZE / sizeof(*pages)) *
- PAGE_CACHE_SIZE) {
- size = ((((size / 2) - 1) |
- ~CFS_PAGE_MASK) + 1) &
- CFS_PAGE_MASK;
- CDEBUG(D_VFSTRACE,"DIO size now %lu\n",
- size);
- continue;
- }
-
- GOTO(out, result);
+ result = iov_iter_get_pages_alloc(iter, &pages, count, &offs);
+ if (likely(result > 0)) {
+ int n = (result + offs + PAGE_SIZE - 1) / PAGE_SIZE;
+ result = ll_direct_IO_26_seg(env, io, rw, inode,
+ file->f_mapping,
+ result, file_offset,
+ pages, n);
+ ll_free_user_pages(pages, n, rw==READ);
+ }
+ if (unlikely(result <= 0)) {
+ /* If we can't allocate a large enough buffer
+ * for the request, shrink it to a smaller
+ * PAGE_SIZE multiple and try again.
+ * We should always be able to kmalloc for a
+ * page worth of page pointers = 4MB on i386. */
+ if (result == -ENOMEM &&
+ size > (PAGE_CACHE_SIZE / sizeof(*pages)) *
+ PAGE_CACHE_SIZE) {
+ size = ((((size / 2) - 1) |
+ ~CFS_PAGE_MASK) + 1) &
+ CFS_PAGE_MASK;
+ CDEBUG(D_VFSTRACE,"DIO size now %lu\n",
+ size);
+ continue;
}
- tot_bytes += result;
- file_offset += result;
- iov_left -= result;
- user_addr += result;
+ GOTO(out, result);
}
+ iov_iter_advance(iter, result);
+ tot_bytes += result;
+ file_offset += result;
}
out:
LASSERT(obj->cob_transient_pages == 0);
}
#ifdef CONFIG_MIGRATION
-int ll_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page
- , enum migrate_mode mode
+static int ll_migratepage(struct address_space *mapping,
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode
)
{
/* Always fail page migration until we have a proper implementation */
#endif
#ifndef MS_HAS_NEW_AOPS
-struct address_space_operations ll_aops = {
- .readpage = ll_readpage,
-// .readpages = ll_readpages,
+const struct address_space_operations ll_aops = {
+ .readpage = ll_readpage,
.direct_IO = ll_direct_IO_26,
.writepage = ll_writepage,
.writepages = ll_writepages,
#ifdef CONFIG_MIGRATION
.migratepage = ll_migratepage,
#endif
- .bmap = NULL
};
#else
-struct address_space_operations_ext ll_aops = {
+const struct address_space_operations_ext ll_aops = {
.orig_aops.readpage = ll_readpage,
// .orig_aops.readpages = ll_readpages,
.orig_aops.direct_IO = ll_direct_IO_26,
#ifdef CONFIG_MIGRATION
.orig_aops.migratepage = ll_migratepage,
#endif
- .orig_aops.bmap = NULL,
.write_begin = ll_write_begin,
.write_end = ll_write_end
};
case CIT_WRITE:
/* don't need lock here to check lli_layout_gen as we have held
* extent lock and GROUP lock has to hold to swap layout */
- if (lli->lli_layout_gen != cio->cui_layout_gen) {
+ if (ll_layout_version_get(lli) != cio->cui_layout_gen) {
io->ci_need_restart = 1;
/* this will return application a short read/write */
io->ci_continue = 0;
vvp_io_fini(env, ios);
}
-enum cl_lock_mode vvp_mode_from_vma(struct vm_area_struct *vma)
+static enum cl_lock_mode vvp_mode_from_vma(struct vm_area_struct *vma)
{
/*
* we only want to hold PW locks if the mmap() can generate
struct cl_lock_descr *descr = &cti->cti_descr;
ldlm_policy_data_t policy;
unsigned long addr;
- unsigned long seg;
ssize_t count;
int result;
+ struct iov_iter i;
+ struct iovec iov;
LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
if (!cl_is_normalio(env, io))
return 0;
- if (vio->cui_iov == NULL) /* nfs or loop back device write */
+ if (vio->cui_iter == NULL) /* nfs or loop back device write */
return 0;
/* No MM (e.g. NFS)? No vmas too. */
if (mm == NULL)
return 0;
- for (seg = 0; seg < vio->cui_nrsegs; seg++) {
- const struct iovec *iv = &vio->cui_iov[seg];
-
- addr = (unsigned long)iv->iov_base;
- count = iv->iov_len;
+ iov_for_each(iov, i, *(vio->cui_iter)) {
+ addr = (unsigned long)iov.iov_base;
+ count = iov.iov_len;
if (count == 0)
continue;
switch (vio->cui_io_subtype) {
case IO_NORMAL:
LASSERT(cio->cui_iocb->ki_pos == pos);
- result = generic_file_aio_read(cio->cui_iocb,
- cio->cui_iov, cio->cui_nrsegs,
- cio->cui_iocb->ki_pos);
+ result = generic_file_read_iter(cio->cui_iocb, cio->cui_iter);
break;
case IO_SPLICE:
result = generic_file_splice_read(file, &pos,
CDEBUG(D_VFSTRACE, "write: [%lli, %lli)\n", pos, pos + (long long)cnt);
- if (cio->cui_iov == NULL) /* from a temp io in ll_cl_init(). */
+ if (cio->cui_iter == NULL) /* from a temp io in ll_cl_init(). */
result = 0;
else
- result = generic_file_aio_write(cio->cui_iocb,
- cio->cui_iov, cio->cui_nrsegs,
- cio->cui_iocb->ki_pos);
+ result = generic_file_write_iter(cio->cui_iocb, cio->cui_iter);
+
if (result > 0) {
if (result < cnt)
io->ci_continue = 0;
* results." -- Single Unix Spec */
if (count == 0)
result = 1;
- else {
+ else
cio->cui_tot_count = count;
- cio->cui_tot_nrsegs = 0;
- }
+
/* for read/write, we store the jobid in the inode, and
* it'll be fetched by osc when building RPC.
*
.bInterfaceProtocol = USB_PR_BULK, /* Adjusted during fsg_bind() */
.iInterface = FSG_STRING_INTERFACE,
};
-EXPORT_SYMBOL(fsg_intf_desc);
+EXPORT_SYMBOL_GPL(fsg_intf_desc);
/*
* Three full-speed endpoint descriptors: bulk-in, bulk-out, and
.bmAttributes = USB_ENDPOINT_XFER_BULK,
/* wMaxPacketSize set by autoconfiguration */
};
-EXPORT_SYMBOL(fsg_fs_bulk_in_desc);
+EXPORT_SYMBOL_GPL(fsg_fs_bulk_in_desc);
struct usb_endpoint_descriptor fsg_fs_bulk_out_desc = {
.bLength = USB_DT_ENDPOINT_SIZE,
.bmAttributes = USB_ENDPOINT_XFER_BULK,
/* wMaxPacketSize set by autoconfiguration */
};
-EXPORT_SYMBOL(fsg_fs_bulk_out_desc);
+EXPORT_SYMBOL_GPL(fsg_fs_bulk_out_desc);
struct usb_descriptor_header *fsg_fs_function[] = {
(struct usb_descriptor_header *) &fsg_intf_desc,
(struct usb_descriptor_header *) &fsg_fs_bulk_out_desc,
NULL,
};
-EXPORT_SYMBOL(fsg_fs_function);
+EXPORT_SYMBOL_GPL(fsg_fs_function);
/*
.bmAttributes = USB_ENDPOINT_XFER_BULK,
.wMaxPacketSize = cpu_to_le16(512),
};
-EXPORT_SYMBOL(fsg_hs_bulk_in_desc);
+EXPORT_SYMBOL_GPL(fsg_hs_bulk_in_desc);
struct usb_endpoint_descriptor fsg_hs_bulk_out_desc = {
.bLength = USB_DT_ENDPOINT_SIZE,
.wMaxPacketSize = cpu_to_le16(512),
.bInterval = 1, /* NAK every 1 uframe */
};
-EXPORT_SYMBOL(fsg_hs_bulk_out_desc);
+EXPORT_SYMBOL_GPL(fsg_hs_bulk_out_desc);
struct usb_descriptor_header *fsg_hs_function[] = {
(struct usb_descriptor_header *) &fsg_hs_bulk_out_desc,
NULL,
};
-EXPORT_SYMBOL(fsg_hs_function);
+EXPORT_SYMBOL_GPL(fsg_hs_function);
struct usb_endpoint_descriptor fsg_ss_bulk_in_desc = {
.bLength = USB_DT_ENDPOINT_SIZE,
.bmAttributes = USB_ENDPOINT_XFER_BULK,
.wMaxPacketSize = cpu_to_le16(1024),
};
-EXPORT_SYMBOL(fsg_ss_bulk_in_desc);
+EXPORT_SYMBOL_GPL(fsg_ss_bulk_in_desc);
struct usb_ss_ep_comp_descriptor fsg_ss_bulk_in_comp_desc = {
.bLength = sizeof(fsg_ss_bulk_in_comp_desc),
/*.bMaxBurst = DYNAMIC, */
};
-EXPORT_SYMBOL(fsg_ss_bulk_in_comp_desc);
+EXPORT_SYMBOL_GPL(fsg_ss_bulk_in_comp_desc);
struct usb_endpoint_descriptor fsg_ss_bulk_out_desc = {
.bLength = USB_DT_ENDPOINT_SIZE,
.bmAttributes = USB_ENDPOINT_XFER_BULK,
.wMaxPacketSize = cpu_to_le16(1024),
};
-EXPORT_SYMBOL(fsg_ss_bulk_out_desc);
+EXPORT_SYMBOL_GPL(fsg_ss_bulk_out_desc);
struct usb_ss_ep_comp_descriptor fsg_ss_bulk_out_comp_desc = {
.bLength = sizeof(fsg_ss_bulk_in_comp_desc),
/*.bMaxBurst = DYNAMIC, */
};
-EXPORT_SYMBOL(fsg_ss_bulk_out_comp_desc);
+EXPORT_SYMBOL_GPL(fsg_ss_bulk_out_comp_desc);
struct usb_descriptor_header *fsg_ss_function[] = {
(struct usb_descriptor_header *) &fsg_intf_desc,
(struct usb_descriptor_header *) &fsg_ss_bulk_out_comp_desc,
NULL,
};
-EXPORT_SYMBOL(fsg_ss_function);
+EXPORT_SYMBOL_GPL(fsg_ss_function);
/*-------------------------------------------------------------------------*/
curlun->filp = NULL;
}
}
-EXPORT_SYMBOL(fsg_lun_close);
+EXPORT_SYMBOL_GPL(fsg_lun_close);
int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
{
* If we can't read the file, it's no good.
* If we can't write the file, use it read-only.
*/
- if (!(filp->f_op->read || filp->f_op->aio_read)) {
+ if (!(filp->f_mode & FMODE_CAN_READ)) {
LINFO(curlun, "file not readable: %s\n", filename);
goto out;
}
- if (!(filp->f_op->write || filp->f_op->aio_write))
+ if (!(filp->f_mode & FMODE_CAN_WRITE))
ro = 1;
size = i_size_read(inode->i_mapping->host);
fput(filp);
return rc;
}
-EXPORT_SYMBOL(fsg_lun_open);
+EXPORT_SYMBOL_GPL(fsg_lun_open);
/*-------------------------------------------------------------------------*/
return 0;
return vfs_fsync(filp, 1);
}
-EXPORT_SYMBOL(fsg_lun_fsync_sub);
+EXPORT_SYMBOL_GPL(fsg_lun_fsync_sub);
void store_cdrom_address(u8 *dest, int msf, u32 addr)
{
put_unaligned_be32(addr, dest);
}
}
-EXPORT_SYMBOL(store_cdrom_address);
+EXPORT_SYMBOL_GPL(store_cdrom_address);
/*-------------------------------------------------------------------------*/
? curlun->ro
: curlun->initially_ro);
}
-EXPORT_SYMBOL(fsg_show_ro);
+EXPORT_SYMBOL_GPL(fsg_show_ro);
ssize_t fsg_show_nofua(struct fsg_lun *curlun, char *buf)
{
return sprintf(buf, "%u\n", curlun->nofua);
}
-EXPORT_SYMBOL(fsg_show_nofua);
+EXPORT_SYMBOL_GPL(fsg_show_nofua);
ssize_t fsg_show_file(struct fsg_lun *curlun, struct rw_semaphore *filesem,
char *buf)
up_read(filesem);
return rc;
}
-EXPORT_SYMBOL(fsg_show_file);
+EXPORT_SYMBOL_GPL(fsg_show_file);
ssize_t fsg_show_cdrom(struct fsg_lun *curlun, char *buf)
{
return sprintf(buf, "%u\n", curlun->cdrom);
}
-EXPORT_SYMBOL(fsg_show_cdrom);
+EXPORT_SYMBOL_GPL(fsg_show_cdrom);
ssize_t fsg_show_removable(struct fsg_lun *curlun, char *buf)
{
return sprintf(buf, "%u\n", curlun->removable);
}
-EXPORT_SYMBOL(fsg_show_removable);
+EXPORT_SYMBOL_GPL(fsg_show_removable);
/*
* The caller must hold fsg->filesem for reading when calling this function.
return rc;
}
-EXPORT_SYMBOL(fsg_store_ro);
+EXPORT_SYMBOL_GPL(fsg_store_ro);
ssize_t fsg_store_nofua(struct fsg_lun *curlun, const char *buf, size_t count)
{
return count;
}
-EXPORT_SYMBOL(fsg_store_nofua);
+EXPORT_SYMBOL_GPL(fsg_store_nofua);
ssize_t fsg_store_file(struct fsg_lun *curlun, struct rw_semaphore *filesem,
const char *buf, size_t count)
up_write(filesem);
return (rc < 0 ? rc : count);
}
-EXPORT_SYMBOL(fsg_store_file);
+EXPORT_SYMBOL_GPL(fsg_store_file);
ssize_t fsg_store_cdrom(struct fsg_lun *curlun, struct rw_semaphore *filesem,
const char *buf, size_t count)
return ret;
}
-EXPORT_SYMBOL(fsg_store_cdrom);
+EXPORT_SYMBOL_GPL(fsg_store_cdrom);
ssize_t fsg_store_removable(struct fsg_lun *curlun, const char *buf,
size_t count)
return count;
}
-EXPORT_SYMBOL(fsg_store_removable);
+EXPORT_SYMBOL_GPL(fsg_store_removable);
MODULE_LICENSE("GPL");
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
/* Convert flock to posix lock */
- fl->fl_owner = (fl_owner_t)filp;
- fl->fl_start = 0;
- fl->fl_end = OFFSET_MAX;
fl->fl_flags |= FL_POSIX;
fl->fl_flags ^= FL_FLOCK;
/**
* v9fs_cached_file_read - read from a file
* @filp: file pointer to read
- * @udata: user data buffer to read data into
+ * @data: user data buffer to read data into
* @count: size of buffer
* @offset: offset at which to read data
*
{
if (filp->f_flags & O_DIRECT)
return v9fs_direct_read(filp, data, count, offset);
- return do_sync_read(filp, data, count, offset);
+ return new_sync_read(filp, data, count, offset);
}
/**
* v9fs_mmap_file_read - read from a file
* @filp: file pointer to read
- * @udata: user data buffer to read data into
+ * @data: user data buffer to read data into
* @count: size of buffer
* @offset: offset at which to read data
*
buff_write:
mutex_unlock(&inode->i_mutex);
- return do_sync_write(filp, data, count, offsetp);
+ return new_sync_write(filp, data, count, offsetp);
}
/**
if (filp->f_flags & O_DIRECT)
return v9fs_direct_write(filp, data, count, offset);
- return do_sync_write(filp, data, count, offset);
+ return new_sync_write(filp, data, count, offset);
}
.llseek = generic_file_llseek,
.read = v9fs_cached_file_read,
.write = v9fs_cached_file_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
.llseek = generic_file_llseek,
.read = v9fs_cached_file_read,
.write = v9fs_cached_file_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.open = v9fs_file_open,
.release = v9fs_dir_release,
.lock = v9fs_file_lock_dotl,
const struct file_operations affs_file_operations = {
.llseek = generic_file_llseek,
- .read = do_sync_read,
- .aio_read = generic_file_aio_read,
- .write = do_sync_write,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = generic_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = generic_file_write_iter,
.mmap = generic_file_mmap,
.open = affs_file_open,
.release = affs_file_release,
static int
affs_file_open(struct inode *inode, struct file *filp)
{
- pr_debug("AFFS: open(%lu,%d)\n",
+ pr_debug("open(%lu,%d)\n",
inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
atomic_inc(&AFFS_I(inode)->i_opencnt);
return 0;
static int
affs_file_release(struct inode *inode, struct file *filp)
{
- pr_debug("AFFS: release(%lu, %d)\n",
+ pr_debug("release(%lu, %d)\n",
inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
if (atomic_dec_and_test(&AFFS_I(inode)->i_opencnt)) {
struct buffer_head *ext_bh;
u32 ext;
- pr_debug("AFFS: get_block(%u, %lu)\n", (u32)inode->i_ino, (unsigned long)block);
+ pr_debug("%s(%u, %lu)\n",
+ __func__, (u32)inode->i_ino, (unsigned long)block);
BUG_ON(block > (sector_t)0x7fffffffUL);
}
static int
-affs_do_readpage_ofs(struct file *file, struct page *page, unsigned from, unsigned to)
+affs_do_readpage_ofs(struct page *page, unsigned to)
{
struct inode *inode = page->mapping->host;
struct super_block *sb = inode->i_sb;
struct buffer_head *bh;
char *data;
+ unsigned pos = 0;
u32 bidx, boff, bsize;
u32 tmp;
- pr_debug("AFFS: read_page(%u, %ld, %d, %d)\n", (u32)inode->i_ino, page->index, from, to);
- BUG_ON(from > to || to > PAGE_CACHE_SIZE);
+ pr_debug("%s(%u, %ld, 0, %d)\n", __func__, (u32)inode->i_ino,
+ page->index, to);
+ BUG_ON(to > PAGE_CACHE_SIZE);
kmap(page);
data = page_address(page);
bsize = AFFS_SB(sb)->s_data_blksize;
- tmp = (page->index << PAGE_CACHE_SHIFT) + from;
+ tmp = page->index << PAGE_CACHE_SHIFT;
bidx = tmp / bsize;
boff = tmp % bsize;
- while (from < to) {
+ while (pos < to) {
bh = affs_bread_ino(inode, bidx, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
- tmp = min(bsize - boff, to - from);
- BUG_ON(from + tmp > to || tmp > bsize);
- memcpy(data + from, AFFS_DATA(bh) + boff, tmp);
+ tmp = min(bsize - boff, to - pos);
+ BUG_ON(pos + tmp > to || tmp > bsize);
+ memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
affs_brelse(bh);
bidx++;
- from += tmp;
+ pos += tmp;
boff = 0;
}
flush_dcache_page(page);
u32 size, bsize;
u32 tmp;
- pr_debug("AFFS: extent_file(%u, %d)\n", (u32)inode->i_ino, newsize);
+ pr_debug("%s(%u, %d)\n", __func__, (u32)inode->i_ino, newsize);
bsize = AFFS_SB(sb)->s_data_blksize;
bh = NULL;
size = AFFS_I(inode)->mmu_private;
u32 to;
int err;
- pr_debug("AFFS: read_page(%u, %ld)\n", (u32)inode->i_ino, page->index);
+ pr_debug("%s(%u, %ld)\n", __func__, (u32)inode->i_ino, page->index);
to = PAGE_CACHE_SIZE;
if (((page->index + 1) << PAGE_CACHE_SHIFT) > inode->i_size) {
to = inode->i_size & ~PAGE_CACHE_MASK;
memset(page_address(page) + to, 0, PAGE_CACHE_SIZE - to);
}
- err = affs_do_readpage_ofs(file, page, 0, to);
+ err = affs_do_readpage_ofs(page, to);
if (!err)
SetPageUptodate(page);
unlock_page(page);
pgoff_t index;
int err = 0;
- pr_debug("AFFS: write_begin(%u, %llu, %llu)\n", (u32)inode->i_ino, (unsigned long long)pos, (unsigned long long)pos + len);
+ pr_debug("%s(%u, %llu, %llu)\n", __func__, (u32)inode->i_ino,
+ (unsigned long long)pos, (unsigned long long)pos + len);
if (pos > AFFS_I(inode)->mmu_private) {
/* XXX: this probably leaves a too-big i_size in case of
* failure. Should really be updating i_size at write_end time
return 0;
/* XXX: inefficient but safe in the face of short writes */
- err = affs_do_readpage_ofs(file, page, 0, PAGE_CACHE_SIZE);
+ err = affs_do_readpage_ofs(page, PAGE_CACHE_SIZE);
if (err) {
unlock_page(page);
page_cache_release(page);
* due to write_begin.
*/
- pr_debug("AFFS: write_begin(%u, %llu, %llu)\n", (u32)inode->i_ino, (unsigned long long)pos, (unsigned long long)pos + len);
+ pr_debug("%s(%u, %llu, %llu)\n",
+ __func__, (u32)inode->i_ino, (unsigned long long)pos,
+ (unsigned long long)pos + len);
bsize = AFFS_SB(sb)->s_data_blksize;
data = page_address(page);
{
struct super_block *sb = inode->i_sb;
- pr_debug("AFFS: free_prealloc(ino=%lu)\n", inode->i_ino);
+ pr_debug("free_prealloc(ino=%lu)\n", inode->i_ino);
while (AFFS_I(inode)->i_pa_cnt) {
AFFS_I(inode)->i_pa_cnt--;
struct buffer_head *ext_bh;
int i;
- pr_debug("AFFS: truncate(inode=%d, oldsize=%u, newsize=%u)\n",
+ pr_debug("truncate(inode=%d, oldsize=%u, newsize=%u)\n",
(u32)inode->i_ino, (u32)AFFS_I(inode)->mmu_private, (u32)inode->i_size);
last_blk = 0;
}
static ssize_t
- blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+ blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
- nr_segs, blkdev_get_block, NULL, NULL, 0);
+ return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
+ offset, blkdev_get_block,
+ NULL, NULL, 0);
}
int __sync_blockdev(struct block_device *bdev, int wait)
}
EXPORT_SYMBOL(blkdev_fsync);
+/**
+ * bdev_read_page() - Start reading a page from a block device
+ * @bdev: The device to read the page from
+ * @sector: The offset on the device to read the page to (need not be aligned)
+ * @page: The page to read
+ *
+ * On entry, the page should be locked. It will be unlocked when the page
+ * has been read. If the block driver implements rw_page synchronously,
+ * that will be true on exit from this function, but it need not be.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to read this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_read_page(struct block_device *bdev, sector_t sector,
+ struct page *page)
+{
+ const struct block_device_operations *ops = bdev->bd_disk->fops;
+ if (!ops->rw_page)
+ return -EOPNOTSUPP;
+ return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+}
+EXPORT_SYMBOL_GPL(bdev_read_page);
+
+/**
+ * bdev_write_page() - Start writing a page to a block device
+ * @bdev: The device to write the page to
+ * @sector: The offset on the device to write the page to (need not be aligned)
+ * @page: The page to write
+ * @wbc: The writeback_control for the write
+ *
+ * On entry, the page should be locked and not currently under writeback.
+ * On exit, if the write started successfully, the page will be unlocked and
+ * under writeback. If the write failed already (eg the driver failed to
+ * queue the page to the device), the page will still be locked. If the
+ * caller is a ->writepage implementation, it will need to unlock the page.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to write this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_write_page(struct block_device *bdev, sector_t sector,
+ struct page *page, struct writeback_control *wbc)
+{
+ int result;
+ int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
+ const struct block_device_operations *ops = bdev->bd_disk->fops;
+ if (!ops->rw_page)
+ return -EOPNOTSUPP;
+ set_page_writeback(page);
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
+ if (result)
+ end_page_writeback(page);
+ else
+ unlock_page(page);
+ return result;
+}
+EXPORT_SYMBOL_GPL(bdev_write_page);
+
/*
* pseudo-fs
*/
* Does not take i_mutex for the write and thus is not for general purpose
* use.
*/
- ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct blk_plug plug;
ssize_t ret;
- BUG_ON(iocb->ki_pos != pos);
-
blk_start_plug(&plug);
- ret = __generic_file_aio_write(iocb, iov, nr_segs);
+ ret = __generic_file_write_iter(iocb, from);
if (ret > 0) {
ssize_t err;
-
- err = generic_write_sync(file, pos, ret);
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0)
ret = err;
}
blk_finish_plug(&plug);
return ret;
}
- EXPORT_SYMBOL_GPL(blkdev_aio_write);
+ EXPORT_SYMBOL_GPL(blkdev_write_iter);
- static ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *bd_inode = file->f_mapping->host;
loff_t size = i_size_read(bd_inode);
+ loff_t pos = iocb->ki_pos;
if (pos >= size)
return 0;
size -= pos;
- if (size < iocb->ki_nbytes)
- nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size);
- return generic_file_aio_read(iocb, iov, nr_segs, pos);
+ iov_iter_truncate(to, size);
+ return generic_file_read_iter(iocb, to);
}
/*
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = blkdev_aio_read,
- .aio_write = blkdev_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = blkdev_read_iter,
+ .write_iter = blkdev_write_iter,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
.compat_ioctl = compat_blkdev_ioctl,
#endif
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
};
int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
#include "tree-log.h"
#include "locking.h"
#include "volumes.h"
+#include "qgroup.h"
static struct kmem_cache *btrfs_inode_defrag_cachep;
/*
write_bytes -= copied;
total_copied += copied;
- /* Return to btrfs_file_aio_write to fault page */
+ /* Return to btrfs_file_write_iter to fault page */
if (unlikely(copied == 0))
break;
for (i = 0; i < num_pages; i++) {
/* page checked is some magic around finding pages that
* have been modified without going through btrfs_set_page_dirty
- * clear it here
+ * clear it here. There should be no need to mark the pages
+ * accessed as prepare_pages should have marked them accessed
+ * in prepare_pages via find_or_create_page()
*/
ClearPageChecked(pages[i]);
unlock_page(pages[i]);
- mark_page_accessed(pages[i]);
page_cache_release(pages[i]);
}
}
int recow;
int ret;
int modify_tree = -1;
- int update_refs = (root->ref_cows || root == root->fs_info->tree_root);
+ int update_refs;
int found = 0;
int leafs_visited = 0;
if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
modify_tree = 0;
+ update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ root == root->fs_info->tree_root);
while (1) {
recow = 0;
ret = btrfs_lookup_file_extent(trans, root, path, ino,
extent_end = search_start;
}
+ /*
+ * Don't skip extent items representing 0 byte lengths. They
+ * used to be created (bug) if while punching holes we hit
+ * -ENOSPC condition. So if we find one here, just ensure we
+ * delete it, otherwise we would insert a new file extent item
+ * with the same key (offset) as that 0 bytes length file
+ * extent item in the call to setup_items_for_insert() later
+ * in this function.
+ */
+ if (extent_end == key.offset && extent_end >= search_start)
+ goto delete_extent_item;
+
if (extent_end <= search_start) {
path->slots[0]++;
goto next_slot;
disk_bytenr, num_bytes, 0,
root->root_key.objectid,
new_key.objectid,
- start - extent_offset, 0);
+ start - extent_offset, 1);
BUG_ON(ret); /* -ENOMEM */
}
key.offset = start;
* | ------ extent ------ |
*/
if (start <= key.offset && end >= extent_end) {
+delete_extent_item:
if (del_nr == 0) {
del_slot = path->slots[0];
del_nr = 1;
ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
root->root_key.objectid,
- ino, orig_offset, 0);
+ ino, orig_offset, 1);
BUG_ON(ret); /* -ENOMEM */
if (split == start) {
}
static ssize_t __btrfs_direct_write(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs, loff_t pos,
- size_t count, size_t ocount)
+ struct iov_iter *from,
+ loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct iov_iter i;
ssize_t written;
ssize_t written_buffered;
loff_t endbyte;
int err;
- written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
- count, ocount);
+ written = generic_file_direct_write(iocb, from, pos);
- if (written < 0 || written == count)
+ if (written < 0 || !iov_iter_count(from))
return written;
pos += written;
- count -= written;
- iov_iter_init(&i, iov, nr_segs, count, written);
- written_buffered = __btrfs_buffered_write(file, &i, pos);
+ written_buffered = __btrfs_buffered_write(file, from, pos);
if (written_buffered < 0) {
err = written_buffered;
goto out;
inode_inc_iversion(inode);
}
- static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
u64 end_pos;
ssize_t num_written = 0;
ssize_t err = 0;
- size_t count, ocount;
+ size_t count = iov_iter_count(from);
bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
+ loff_t pos = iocb->ki_pos;
mutex_lock(&inode->i_mutex);
- err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
- if (err) {
- mutex_unlock(&inode->i_mutex);
- goto out;
- }
- count = ocount;
-
current->backing_dev_info = inode->i_mapping->backing_dev_info;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err) {
goto out;
}
+ iov_iter_truncate(from, count);
+
err = file_remove_suid(file);
if (err) {
mutex_unlock(&inode->i_mutex);
atomic_inc(&BTRFS_I(inode)->sync_writers);
if (unlikely(file->f_flags & O_DIRECT)) {
- num_written = __btrfs_direct_write(iocb, iov, nr_segs,
- pos, count, ocount);
+ num_written = __btrfs_direct_write(iocb, from, pos);
} else {
- struct iov_iter i;
-
- iov_iter_init(&i, iov, nr_segs, count, num_written);
-
- num_written = __btrfs_buffered_write(file, &i, pos);
+ num_written = __btrfs_buffered_write(file, from, pos);
if (num_written > 0)
iocb->ki_pos = pos + num_written;
}
if (!full_sync) {
ret = btrfs_wait_ordered_range(inode, start,
end - start + 1);
- if (ret)
+ if (ret) {
+ btrfs_end_transaction(trans, root);
goto out;
+ }
}
ret = btrfs_commit_transaction(trans, root);
} else {
return 0;
}
+/*
+ * Find a hole extent on given inode and change start/len to the end of hole
+ * extent.(hole/vacuum extent whose em->start <= start &&
+ * em->start + em->len > start)
+ * When a hole extent is found, return 1 and modify start/len.
+ */
+static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
+{
+ struct extent_map *em;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
+ if (IS_ERR_OR_NULL(em)) {
+ if (!em)
+ ret = -ENOMEM;
+ else
+ ret = PTR_ERR(em);
+ return ret;
+ }
+
+ /* Hole or vacuum extent(only exists in no-hole mode) */
+ if (em->block_start == EXTENT_MAP_HOLE) {
+ ret = 1;
+ *len = em->start + em->len > *start + *len ?
+ 0 : *start + *len - em->start - em->len;
+ *start = em->start + em->len;
+ }
+ free_extent_map(em);
+ return ret;
+}
+
static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
struct btrfs_block_rsv *rsv;
struct btrfs_trans_handle *trans;
- u64 lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
- u64 lockend = round_down(offset + len,
- BTRFS_I(inode)->root->sectorsize) - 1;
- u64 cur_offset = lockstart;
+ u64 lockstart;
+ u64 lockend;
+ u64 tail_start;
+ u64 tail_len;
+ u64 orig_start = offset;
+ u64 cur_offset;
u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
u64 drop_end;
int ret = 0;
int err = 0;
int rsv_count;
- bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
- ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+ bool same_page;
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
- u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+ u64 ino_size;
ret = btrfs_wait_ordered_range(inode, offset, len);
if (ret)
return ret;
mutex_lock(&inode->i_mutex);
+ ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+ ret = find_first_non_hole(inode, &offset, &len);
+ if (ret < 0)
+ goto out_only_mutex;
+ if (ret && !len) {
+ /* Already in a large hole */
+ ret = 0;
+ goto out_only_mutex;
+ }
+
+ lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+ lockend = round_down(offset + len,
+ BTRFS_I(inode)->root->sectorsize) - 1;
+ same_page = ((offset >> PAGE_CACHE_SHIFT) ==
+ ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+
/*
* We needn't truncate any page which is beyond the end of the file
* because we are sure there is no data there.
if (same_page && len < PAGE_CACHE_SIZE) {
if (offset < ino_size)
ret = btrfs_truncate_page(inode, offset, len, 0);
- mutex_unlock(&inode->i_mutex);
- return ret;
+ goto out_only_mutex;
}
/* zero back part of the first page */
}
}
- /* zero the front end of the last page */
- if (offset + len < ino_size) {
- ret = btrfs_truncate_page(inode, offset + len, 0, 1);
- if (ret) {
- mutex_unlock(&inode->i_mutex);
- return ret;
+ /* Check the aligned pages after the first unaligned page,
+ * if offset != orig_start, which means the first unaligned page
+ * including serveral following pages are already in holes,
+ * the extra check can be skipped */
+ if (offset == orig_start) {
+ /* after truncate page, check hole again */
+ len = offset + len - lockstart;
+ offset = lockstart;
+ ret = find_first_non_hole(inode, &offset, &len);
+ if (ret < 0)
+ goto out_only_mutex;
+ if (ret && !len) {
+ ret = 0;
+ goto out_only_mutex;
+ }
+ lockstart = offset;
+ }
+
+ /* Check the tail unaligned part is in a hole */
+ tail_start = lockend + 1;
+ tail_len = offset + len - tail_start;
+ if (tail_len) {
+ ret = find_first_non_hole(inode, &tail_start, &tail_len);
+ if (unlikely(ret < 0))
+ goto out_only_mutex;
+ if (!ret) {
+ /* zero the front end of the last page */
+ if (tail_start + tail_len < ino_size) {
+ ret = btrfs_truncate_page(inode,
+ tail_start + tail_len, 0, 1);
+ if (ret)
+ goto out_only_mutex;
+ }
}
}
if ((!ordered ||
(ordered->file_offset + ordered->len <= lockstart ||
ordered->file_offset > lockend)) &&
- !test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, EXTENT_UPTODATE, 0,
- cached_state)) {
+ !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
if (ordered)
btrfs_put_ordered_extent(ordered);
break;
BUG_ON(ret);
trans->block_rsv = rsv;
+ cur_offset = lockstart;
+ len = lockend - cur_offset;
while (cur_offset < lockend) {
ret = __btrfs_drop_extents(trans, root, inode, path,
cur_offset, lockend + 1,
rsv, min_size);
BUG_ON(ret); /* shouldn't happen */
trans->block_rsv = rsv;
+
+ ret = find_first_non_hole(inode, &cur_offset, &len);
+ if (unlikely(ret < 0))
+ break;
+ if (ret && !len) {
+ ret = 0;
+ break;
+ }
}
if (ret) {
}
trans->block_rsv = &root->fs_info->trans_block_rsv;
- if (cur_offset < ino_size) {
+ /*
+ * Don't insert file hole extent item if it's for a range beyond eof
+ * (because it's useless) or if it represents a 0 bytes range (when
+ * cur_offset == drop_end).
+ */
+ if (cur_offset < ino_size && cur_offset < drop_end) {
ret = fill_holes(trans, inode, path, cur_offset, drop_end);
if (ret) {
err = ret;
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state, GFP_NOFS);
+out_only_mutex:
mutex_unlock(&inode->i_mutex);
if (ret && !err)
err = ret;
const struct file_operations btrfs_file_operations = {
.llseek = btrfs_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
.splice_read = generic_file_splice_read,
- .aio_write = btrfs_file_aio_write,
+ .write_iter = btrfs_file_write_iter,
.mmap = btrfs_file_mmap,
.open = generic_file_open,
.release = btrfs_release_file,
* the btree. The caller should have done a btrfs_drop_extents so that
* no overlapping inline items exist in the btree
*/
-static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
+static int insert_inline_extent(struct btrfs_trans_handle *trans,
struct btrfs_path *path, int extent_inserted,
struct btrfs_root *root, struct inode *inode,
u64 start, size_t size, size_t compressed_size,
trans = NULL;
goto out_unlock;
}
+
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
root->orphan_block_rsv = NULL;
spin_unlock(&root->orphan_lock);
- if (root->orphan_item_inserted &&
+ if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
btrfs_root_refs(&root->root_item) > 0) {
ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
root->root_key.objectid);
if (ret)
btrfs_abort_transaction(trans, root, ret);
else
- root->orphan_item_inserted = 0;
+ clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ &root->state);
}
if (block_rsv) {
btrfs_block_rsv_release(root, root->orphan_block_rsv,
(u64)-1);
- if (root->orphan_block_rsv || root->orphan_item_inserted) {
+ if (root->orphan_block_rsv ||
+ test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
trans = btrfs_join_transaction(root);
if (!IS_ERR(trans))
btrfs_end_transaction(trans, root);
ret = btrfs_load_inode_props(inode, path);
if (ret)
btrfs_err(root->fs_info,
- "error loading props for ino %llu (root %llu): %d\n",
+ "error loading props for ino %llu (root %llu): %d",
btrfs_ino(inode),
root->root_key.objectid, ret);
}
* not block aligned since we will be keeping the last block of the
* extent just the way it is.
*/
- if (root->ref_cows || root == root->fs_info->tree_root)
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ root == root->fs_info->tree_root)
btrfs_drop_extent_cache(inode, ALIGN(new_size,
root->sectorsize), (u64)-1, 0);
extent_num_bytes);
num_dec = (orig_num_bytes -
extent_num_bytes);
- if (root->ref_cows && extent_start != 0)
+ if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state) &&
+ extent_start != 0)
inode_sub_bytes(inode, num_dec);
btrfs_mark_buffer_dirty(leaf);
} else {
num_dec = btrfs_file_extent_num_bytes(leaf, fi);
if (extent_start != 0) {
found_extent = 1;
- if (root->ref_cows)
+ if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state))
inode_sub_bytes(inode, num_dec);
}
}
btrfs_file_extent_other_encoding(leaf, fi) == 0) {
u32 size = new_size - found_key.offset;
- if (root->ref_cows) {
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
inode_sub_bytes(inode, item_end + 1 -
new_size);
- }
/*
* update the ram bytes to properly reflect
size =
btrfs_file_extent_calc_inline_size(size);
btrfs_truncate_item(root, path, size, 1);
- } else if (root->ref_cows) {
+ } else if (test_bit(BTRFS_ROOT_REF_COWS,
+ &root->state)) {
inode_sub_bytes(inode, item_end + 1 -
found_key.offset);
}
} else {
break;
}
- if (found_extent && (root->ref_cows ||
- root == root->fs_info->tree_root)) {
+ if (found_extent &&
+ (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ root == root->fs_info->tree_root)) {
btrfs_set_path_blocking(path);
ret = btrfs_free_extent(trans, root, extent_start,
extent_num_bytes, 0,
static void btrfs_dentry_release(struct dentry *dentry)
{
- if (dentry->d_fsdata)
- kfree(dentry->d_fsdata);
+ kfree(dentry->d_fsdata);
}
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
struct btrfs_inode_ref *ref;
struct btrfs_key key[2];
u32 sizes[2];
+ int nitems = name ? 2 : 1;
unsigned long ptr;
int ret;
*/
inode->i_ino = objectid;
- if (dir) {
+ if (dir && name) {
trace_btrfs_inode_request(dir);
ret = btrfs_set_inode_index(dir, index);
iput(inode);
return ERR_PTR(ret);
}
+ } else if (dir) {
+ *index = 0;
}
/*
* index_cnt is ignored for everything but a dir,
btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
key[0].offset = 0;
- /*
- * Start new inodes with an inode_ref. This is slightly more
- * efficient for small numbers of hard links since they will
- * be packed into one item. Extended refs will kick in if we
- * add more hard links than can fit in the ref item.
- */
- key[1].objectid = objectid;
- btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
- key[1].offset = ref_objectid;
-
sizes[0] = sizeof(struct btrfs_inode_item);
- sizes[1] = name_len + sizeof(*ref);
+
+ if (name) {
+ /*
+ * Start new inodes with an inode_ref. This is slightly more
+ * efficient for small numbers of hard links since they will
+ * be packed into one item. Extended refs will kick in if we
+ * add more hard links than can fit in the ref item.
+ */
+ key[1].objectid = objectid;
+ btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
+ key[1].offset = ref_objectid;
+
+ sizes[1] = name_len + sizeof(*ref);
+ }
path->leave_spinning = 1;
- ret = btrfs_insert_empty_items(trans, root, path, key, sizes, 2);
+ ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
if (ret != 0)
goto fail;
sizeof(*inode_item));
fill_inode_item(trans, path->nodes[0], inode_item, inode);
- ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
- struct btrfs_inode_ref);
- btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
- btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
- ptr = (unsigned long)(ref + 1);
- write_extent_buffer(path->nodes[0], name, ptr, name_len);
+ if (name) {
+ ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
+ struct btrfs_inode_ref);
+ btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
+ btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
+ ptr = (unsigned long)(ref + 1);
+ write_extent_buffer(path->nodes[0], name, ptr, name_len);
+ }
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
return inode;
fail:
- if (dir)
+ if (dir && name)
BTRFS_I(dir)->index_cnt--;
btrfs_free_path(path);
iput(inode);
err = btrfs_update_inode(trans, root, inode);
if (err)
goto fail;
+ if (inode->i_nlink == 1) {
+ /*
+ * If new hard link count is 1, it's a file created
+ * with open(2) O_TMPFILE flag.
+ */
+ err = btrfs_orphan_del(trans, inode);
+ if (err)
+ goto fail;
+ }
d_instantiate(dentry, inode);
btrfs_log_new_name(trans, inode, NULL, parent);
}
max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
- if (ret) {
- char *kaddr = kmap_atomic(page);
- unsigned long copy_size = min_t(u64,
- PAGE_CACHE_SIZE - pg_offset,
- max_size - extent_offset);
- memset(kaddr + pg_offset, 0, copy_size);
- kunmap_atomic(kaddr);
- }
kfree(tmp);
- return 0;
+ return ret;
}
/*
{
int ret;
int err = 0;
- u64 bytenr;
u64 extent_start = 0;
u64 extent_end = 0;
u64 objectid = btrfs_ino(inode);
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_trans_handle *trans = NULL;
- int compress_type;
+ const bool new_inline = !page || create;
again:
read_lock(&em_tree->lock);
found_type = btrfs_file_extent_type(leaf, item);
extent_start = found_key.offset;
- compress_type = btrfs_file_extent_compression(leaf, item);
if (found_type == BTRFS_FILE_EXTENT_REG ||
found_type == BTRFS_FILE_EXTENT_PREALLOC) {
extent_end = extent_start +
goto not_found_em;
}
- em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, item);
+ btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em);
+
if (found_type == BTRFS_FILE_EXTENT_REG ||
found_type == BTRFS_FILE_EXTENT_PREALLOC) {
- em->start = extent_start;
- em->len = extent_end - extent_start;
- em->orig_start = extent_start -
- btrfs_file_extent_offset(leaf, item);
- em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf,
- item);
- bytenr = btrfs_file_extent_disk_bytenr(leaf, item);
- if (bytenr == 0) {
- em->block_start = EXTENT_MAP_HOLE;
- goto insert;
- }
- if (compress_type != BTRFS_COMPRESS_NONE) {
- set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
- em->compress_type = compress_type;
- em->block_start = bytenr;
- em->block_len = em->orig_block_len;
- } else {
- bytenr += btrfs_file_extent_offset(leaf, item);
- em->block_start = bytenr;
- em->block_len = em->len;
- if (found_type == BTRFS_FILE_EXTENT_PREALLOC)
- set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
- }
goto insert;
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
unsigned long ptr;
size_t extent_offset;
size_t copy_size;
- em->block_start = EXTENT_MAP_INLINE;
- if (!page || create) {
- em->start = extent_start;
- em->len = extent_end - extent_start;
+ if (new_inline)
goto out;
- }
size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_offset = page_offset(page) + pg_offset - extent_start;
em->len = ALIGN(copy_size, root->sectorsize);
em->orig_block_len = em->len;
em->orig_start = em->start;
- if (compress_type) {
- set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
- em->compress_type = compress_type;
- }
ptr = btrfs_file_extent_inline_start(item) + extent_offset;
if (create == 0 && !PageUptodate(page)) {
if (btrfs_file_extent_compression(leaf, item) !=
ret = uncompress_inline(path, inode, page,
pg_offset,
extent_offset, item);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret) {
+ err = ret;
+ goto out;
+ }
} else {
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
set_extent_uptodate(io_tree, em->start,
extent_map_end(em) - 1, NULL, GFP_NOFS);
goto insert;
- } else {
- WARN(1, KERN_ERR "btrfs unknown found_type %d\n", found_type);
}
not_found:
em->start = start;
return ret;
}
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
+{
+ struct radix_tree_root *root = &inode->i_mapping->page_tree;
+ int found = false;
+ void **pagep = NULL;
+ struct page *page = NULL;
+ int start_idx;
+ int end_idx;
+
+ start_idx = start >> PAGE_CACHE_SHIFT;
+
+ /*
+ * end is the last byte in the last page. end == start is legal
+ */
+ end_idx = end >> PAGE_CACHE_SHIFT;
+
+ rcu_read_lock();
+
+ /* Most of the code in this while loop is lifted from
+ * find_get_page. It's been modified to begin searching from a
+ * page and return just the first page found in that range. If the
+ * found idx is less than or equal to the end idx then we know that
+ * a page exists. If no pages are found or if those pages are
+ * outside of the range then we're fine (yay!) */
+ while (page == NULL &&
+ radix_tree_gang_lookup_slot(root, &pagep, NULL, start_idx, 1)) {
+ page = radix_tree_deref_slot(pagep);
+ if (unlikely(!page))
+ break;
+
+ if (radix_tree_exception(page)) {
+ if (radix_tree_deref_retry(page)) {
+ page = NULL;
+ continue;
+ }
+ /*
+ * Otherwise, shmem/tmpfs must be storing a swap entry
+ * here as an exceptional entry: so return it without
+ * attempting to raise page count.
+ */
+ page = NULL;
+ break; /* TODO: Is this relevant for this use case? */
+ }
+
+ if (!page_cache_get_speculative(page)) {
+ page = NULL;
+ continue;
+ }
+
+ /*
+ * Has the page moved?
+ * This is part of the lockless pagecache protocol. See
+ * include/linux/pagemap.h for details.
+ */
+ if (unlikely(page != *pagep)) {
+ page_cache_release(page);
+ page = NULL;
+ }
+ }
+
+ if (page) {
+ if (page->index <= end_idx)
+ found = true;
+ page_cache_release(page);
+ }
+
+ rcu_read_unlock();
+ return found;
+}
+
static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
struct extent_state **cached_state, int writing)
{
* invalidate needs to happen so that reads after a write do not
* get stale data.
*/
- if (!ordered && (!writing ||
- !test_range_bit(&BTRFS_I(inode)->io_tree,
- lockstart, lockend, EXTENT_UPTODATE, 0,
- *cached_state)))
+ if (!ordered &&
+ (!writing ||
+ !btrfs_page_exists_in_range(inode, lockstart, lockend)))
break;
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
* before atomic variable goto zero, we must make sure
* dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
}
/* if there are more bios still pending for this dio, just exit */
* before atomic variable goto zero, we must
* make sure dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
if (atomic_dec_and_test(&dip->pending_bios))
bio_io_error(dip->orig_bio);
}
static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ const struct iov_iter *iter, loff_t offset)
{
int seg;
int i;
- size_t size;
- unsigned long addr;
unsigned blocksize_mask = root->sectorsize - 1;
ssize_t retval = -EINVAL;
- loff_t end = offset;
if (offset & blocksize_mask)
goto out;
- /* Check the memory alignment. Blocks cannot straddle pages */
- for (seg = 0; seg < nr_segs; seg++) {
- addr = (unsigned long)iov[seg].iov_base;
- size = iov[seg].iov_len;
- end += size;
- if ((addr & blocksize_mask) || (size & blocksize_mask))
- goto out;
-
- /* If this is a write we don't need to check anymore */
- if (rw & WRITE)
- continue;
+ if (iov_iter_alignment(iter) & blocksize_mask)
+ goto out;
- /*
- * Check to make sure we don't have duplicate iov_base's in this
- * iovec, if so return EINVAL, otherwise we'll get csum errors
- * when reading back.
- */
- for (i = seg + 1; i < nr_segs; i++) {
- if (iov[seg].iov_base == iov[i].iov_base)
+ /* If this is a write we don't need to check anymore */
+ if (rw & WRITE)
+ return 0;
+ /*
+ * Check to make sure we don't have duplicate iov_base's in this
+ * iovec, if so return EINVAL, otherwise we'll get csum errors
+ * when reading back.
+ */
+ for (seg = 0; seg < iter->nr_segs; seg++) {
+ for (i = seg + 1; i < iter->nr_segs; i++) {
+ if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
goto out;
}
}
}
static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
bool relock = false;
ssize_t ret;
- if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
- offset, nr_segs))
+ if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
return 0;
atomic_inc(&inode->i_dio_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/*
* The generic stuff only does filemap_write_and_wait_range, which
* we need to flush the dirty pages again to make absolutely sure
* that any outstanding dirty pages are on disk.
*/
- count = iov_length(iov, nr_segs);
+ count = iov_iter_count(iter);
if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags))
filemap_fdatawrite_range(inode->i_mapping, offset, count);
ret = __blockdev_direct_IO(rw, iocb, inode,
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
+ iter, offset, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (rw & WRITE) {
if (ret < 0 && ret != -EIOCBQUEUED)
err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
if (err)
btrfs_err(new_root->fs_info,
- "error inheriting subvolume %llu properties: %d\n",
+ "error inheriting subvolume %llu properties: %d",
new_root->root_key.objectid, err);
err = btrfs_update_inode(trans, new_root, inode);
BTRFS_I(old_inode)->dir_index = 0ULL;
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
/* force full log commit if subvolume involved. */
- root->fs_info->last_trans_log_full_commit = trans->transid;
+ btrfs_set_log_full_commit(root->fs_info, trans);
} else {
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
return generic_permission(inode, mask);
}
+static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(dir)->root;
+ struct inode *inode = NULL;
+ u64 objectid;
+ u64 index;
+ int ret = 0;
+
+ /*
+ * 5 units required for adding orphan entry
+ */
+ trans = btrfs_start_transaction(root, 5);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ goto out;
+
+ inode = btrfs_new_inode(trans, root, dir, NULL, 0,
+ btrfs_ino(dir), objectid, mode, &index);
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ inode = NULL;
+ goto out;
+ }
+
+ ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+ if (ret)
+ goto out;
+
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
+ inode->i_mapping->a_ops = &btrfs_aops;
+ inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+ BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+
+ ret = btrfs_orphan_add(trans, inode);
+ if (ret)
+ goto out;
+
+ d_tmpfile(dentry, inode);
+ mark_inode_dirty(inode);
+
+out:
+ btrfs_end_transaction(trans, root);
+ if (ret)
+ iput(inode);
+ btrfs_balance_delayed_items(root);
+ btrfs_btree_balance_dirty(root);
+
+ return ret;
+}
+
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
+ .tmpfile = btrfs_tmpfile,
};
static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
- pr_warning("writepage_start %p on forced umount\n", inode);
+ pr_warn("writepage_start %p on forced umount\n", inode);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
* never get called.
*/
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t pos)
{
WARN_ON(1);
return -EINVAL;
struct workqueue_struct *cifsiod_wq;
-#ifdef CONFIG_CIFS_SMB2
-__u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
-#endif
-
/*
* Bumps refcount for cifs super block.
* Note that it should be only called if a referece to VFS super block is
* server, can not assume caching of file data or metadata.
*/
cifs_set_oplock_level(cifs_inode, 0);
- cifs_inode->delete_pending = false;
- cifs_inode->invalid_mapping = false;
- clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cifs_inode->flags);
- clear_bit(CIFS_INODE_PENDING_WRITERS, &cifs_inode->flags);
- clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cifs_inode->flags);
+ cifs_inode->flags = 0;
spin_lock_init(&cifs_inode->writers_lock);
cifs_inode->writers = 0;
cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */
struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
- seq_printf(s, ",addr=");
+ seq_puts(s, ",addr=");
switch (server->dstaddr.ss_family) {
case AF_INET:
seq_printf(s, "%%%u", sa6->sin6_scope_id);
break;
default:
- seq_printf(s, "(unknown)");
+ seq_puts(s, "(unknown)");
}
}
if (ses->sectype == Unspecified)
return;
- seq_printf(s, ",sec=");
+ seq_puts(s, ",sec=");
switch (ses->sectype) {
case LANMAN:
- seq_printf(s, "lanman");
+ seq_puts(s, "lanman");
break;
case NTLMv2:
- seq_printf(s, "ntlmv2");
+ seq_puts(s, "ntlmv2");
break;
case NTLM:
- seq_printf(s, "ntlm");
+ seq_puts(s, "ntlm");
break;
case Kerberos:
- seq_printf(s, "krb5");
+ seq_puts(s, "krb5");
break;
case RawNTLMSSP:
- seq_printf(s, "ntlmssp");
+ seq_puts(s, "ntlmssp");
break;
default:
/* shouldn't ever happen */
- seq_printf(s, "unknown");
+ seq_puts(s, "unknown");
break;
}
if (ses->sign)
- seq_printf(s, "i");
+ seq_puts(s, "i");
}
static void
cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
{
- seq_printf(s, ",cache=");
+ seq_puts(s, ",cache=");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
- seq_printf(s, "strict");
+ seq_puts(s, "strict");
else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
- seq_printf(s, "none");
+ seq_puts(s, "none");
else
- seq_printf(s, "loose");
+ seq_puts(s, "loose");
}
static void
cifs_show_cache_flavor(s, cifs_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)
- seq_printf(s, ",multiuser");
+ seq_puts(s, ",multiuser");
else if (tcon->ses->user_name)
seq_printf(s, ",username=%s", tcon->ses->user_name);
seq_printf(s, ",uid=%u",
from_kuid_munged(&init_user_ns, cifs_sb->mnt_uid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
- seq_printf(s, ",forceuid");
+ seq_puts(s, ",forceuid");
else
- seq_printf(s, ",noforceuid");
+ seq_puts(s, ",noforceuid");
seq_printf(s, ",gid=%u",
from_kgid_munged(&init_user_ns, cifs_sb->mnt_gid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
- seq_printf(s, ",forcegid");
+ seq_puts(s, ",forcegid");
else
- seq_printf(s, ",noforcegid");
+ seq_puts(s, ",noforcegid");
cifs_show_address(s, tcon->ses->server);
cifs_show_nls(s, cifs_sb->local_nls);
if (tcon->seal)
- seq_printf(s, ",seal");
+ seq_puts(s, ",seal");
if (tcon->nocase)
- seq_printf(s, ",nocase");
+ seq_puts(s, ",nocase");
if (tcon->retry)
- seq_printf(s, ",hard");
+ seq_puts(s, ",hard");
if (tcon->unix_ext)
- seq_printf(s, ",unix");
+ seq_puts(s, ",unix");
else
- seq_printf(s, ",nounix");
+ seq_puts(s, ",nounix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
- seq_printf(s, ",posixpaths");
+ seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
- seq_printf(s, ",setuids");
+ seq_puts(s, ",setuids");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
- seq_printf(s, ",serverino");
+ seq_puts(s, ",serverino");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
- seq_printf(s, ",rwpidforward");
+ seq_puts(s, ",rwpidforward");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
- seq_printf(s, ",forcemand");
+ seq_puts(s, ",forcemand");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
- seq_printf(s, ",nouser_xattr");
+ seq_puts(s, ",nouser_xattr");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
- seq_printf(s, ",mapchars");
+ seq_puts(s, ",mapchars");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
- seq_printf(s, ",sfu");
+ seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
- seq_printf(s, ",nobrl");
+ seq_puts(s, ",nobrl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
- seq_printf(s, ",cifsacl");
+ seq_puts(s, ",cifsacl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
- seq_printf(s, ",dynperm");
+ seq_puts(s, ",dynperm");
if (root->d_sb->s_flags & MS_POSIXACL)
- seq_printf(s, ",acl");
+ seq_puts(s, ",acl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
- seq_printf(s, ",mfsymlinks");
+ seq_puts(s, ",mfsymlinks");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
- seq_printf(s, ",fsc");
+ seq_puts(s, ",fsc");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
- seq_printf(s, ",nostrictsync");
+ seq_puts(s, ",nostrictsync");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
- seq_printf(s, ",noperm");
+ seq_puts(s, ",noperm");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
seq_printf(s, ",backupuid=%u",
from_kuid_munged(&init_user_ns,
goto out;
}
- static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
if (written)
return written;
- written = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ written = generic_file_write_iter(iocb, from);
if (CIFS_CACHE_WRITE(CIFS_I(inode)))
goto out;
rc = filemap_fdatawrite(inode->i_mapping);
if (rc)
- cifs_dbg(FYI, "cifs_file_aio_write: %d rc on %p inode\n",
+ cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n",
rc, inode);
out:
};
const struct file_operations cifs_file_ops = {
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = cifs_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = cifs_file_write_iter,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
};
const struct file_operations cifs_file_strict_ops = {
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = cifs_strict_readv,
- .aio_write = cifs_strict_writev,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = cifs_strict_readv,
+ .write_iter = cifs_strict_writev,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
const struct file_operations cifs_file_direct_ops = {
/* BB reevaluate whether they can be done with directio, no cache */
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = cifs_user_readv,
- .aio_write = cifs_user_writev,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = cifs_user_readv,
+ .write_iter = cifs_user_writev,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
};
const struct file_operations cifs_file_nobrl_ops = {
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = cifs_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = cifs_file_write_iter,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_fsync,
};
const struct file_operations cifs_file_strict_nobrl_ops = {
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = cifs_strict_readv,
- .aio_write = cifs_strict_writev,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = cifs_strict_readv,
+ .write_iter = cifs_strict_writev,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_strict_fsync,
const struct file_operations cifs_file_direct_nobrl_ops = {
/* BB reevaluate whether they can be done with directio, no cache */
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = cifs_user_readv,
- .aio_write = cifs_user_writev,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = cifs_user_readv,
+ .write_iter = cifs_user_writev,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_fsync,
spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_SMB2
- get_random_bytes(cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
-#endif
-
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
#ifndef _CIFSFS_H
#define _CIFSFS_H
+#include <linux/hash.h>
+
#define ROOT_I 2
/*
* ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
- * so that it will fit.
+ * so that it will fit. We use hash_64 to convert the value to 31 bits, and
+ * then add 1, to ensure that we don't end up with a 0 as the value.
*/
+#if BITS_PER_LONG == 64
static inline ino_t
cifs_uniqueid_to_ino_t(u64 fileid)
{
- ino_t ino = (ino_t) fileid;
- if (sizeof(ino_t) < sizeof(u64))
- ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8;
- return ino;
+ return (ino_t)fileid;
}
+#else
+static inline ino_t
+cifs_uniqueid_to_ino_t(u64 fileid)
+{
+ return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+}
+#endif
extern struct file_system_type cifs_fs_type;
extern const struct address_space_operations cifs_addr_ops;
extern int cifs_revalidate_file(struct file *filp);
extern int cifs_revalidate_dentry(struct dentry *);
extern int cifs_invalidate_mapping(struct inode *inode);
+extern int cifs_revalidate_mapping(struct inode *inode);
+extern int cifs_zap_mapping(struct inode *inode);
extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int cifs_setattr(struct dentry *, struct iattr *);
extern int cifs_open(struct inode *inode, struct file *file);
extern int cifs_close(struct inode *inode, struct file *file);
extern int cifs_closedir(struct inode *inode, struct file *file);
- extern ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
- extern ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
- extern ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
- extern ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
+ extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to);
+ extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
+ extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
+ extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
extern int cifs_lock(struct file *, int, struct file_lock *);
extern int cifs_fsync(struct file *, loff_t, loff_t, int);
extern int cifs_strict_fsync(struct file *, loff_t, loff_t, int);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.02"
+#define CIFS_VERSION "2.03"
#endif /* _CIFSFS_H */
spin_unlock(&cifs_file_list_lock);
if (fid->purge_cache)
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
file->private_data = cfile;
return cfile;
* again and get at least level II oplock.
*/
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
- CIFS_I(inode)->invalid_mapping = true;
+ set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
cifs_set_oplock_level(cifsi, 0);
}
spin_unlock(&cifs_file_list_lock);
*/
if (!CIFS_CACHE_WRITE(CIFS_I(inode)) &&
CIFS_CACHE_READ(CIFS_I(inode))) {
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n",
inode);
CIFS_I(inode)->oplock = 0;
file->f_path.dentry->d_name.name, datasync);
if (!CIFS_CACHE_READ(CIFS_I(inode))) {
- rc = cifs_invalidate_mapping(inode);
+ rc = cifs_zap_mapping(inode);
if (rc) {
cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
rc = 0; /* don't care about it in fsync */
}
static ssize_t
- cifs_iovec_write(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *poffset)
+ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
{
unsigned long nr_pages, i;
size_t bytes, copied, len, cur_len;
ssize_t total_written = 0;
loff_t offset;
- struct iov_iter it;
struct cifsFileInfo *open_file;
struct cifs_tcon *tcon;
struct cifs_sb_info *cifs_sb;
int rc;
pid_t pid;
- len = iov_length(iov, nr_segs);
- if (!len)
- return 0;
-
+ len = iov_iter_count(from);
rc = generic_write_checks(file, poffset, &len, 0);
if (rc)
return rc;
+ if (!len)
+ return 0;
+
+ iov_iter_truncate(from, len);
+
INIT_LIST_HEAD(&wdata_list);
cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
open_file = file->private_data;
else
pid = current->tgid;
- iov_iter_init(&it, iov, nr_segs, len, 0);
do {
size_t save_len;
save_len = cur_len;
for (i = 0; i < nr_pages; i++) {
- bytes = min_t(const size_t, cur_len, PAGE_SIZE);
- copied = iov_iter_copy_from_user(wdata->pages[i], &it,
- 0, bytes);
+ bytes = min_t(size_t, cur_len, PAGE_SIZE);
+ copied = copy_page_from_iter(wdata->pages[i], 0, bytes,
+ from);
cur_len -= copied;
- iov_iter_advance(&it, copied);
/*
* If we didn't copy as much as we expected, then that
* may mean we trod into an unmapped area. Stop copying
return total_written ? total_written : (ssize_t)rc;
}
- ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
{
ssize_t written;
struct inode *inode;
+ loff_t pos = iocb->ki_pos;
inode = file_inode(iocb->ki_filp);
* write request.
*/
- written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos);
+ written = cifs_iovec_write(iocb->ki_filp, from, &pos);
if (written > 0) {
- CIFS_I(inode)->invalid_mapping = true;
+ set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
iocb->ki_pos = pos;
}
}
static ssize_t
- cifs_writev(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
mutex_lock(&inode->i_mutex);
if (file->f_flags & O_APPEND)
lock_pos = i_size_read(inode);
- if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
+ if (!cifs_find_lock_conflict(cfile, lock_pos, iov_iter_count(from),
server->vals->exclusive_lock_type, NULL,
CIFS_WRITE_OP)) {
- rc = __generic_file_aio_write(iocb, iov, nr_segs);
+ rc = __generic_file_write_iter(iocb, from);
mutex_unlock(&inode->i_mutex);
if (rc > 0) {
}
ssize_t
- cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
&& ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
- written = generic_file_aio_write(
- iocb, iov, nr_segs, pos);
+ written = generic_file_write_iter(iocb, from);
goto out;
}
- written = cifs_writev(iocb, iov, nr_segs, pos);
+ written = cifs_writev(iocb, from);
goto out;
}
/*
* affected pages because it may cause a error with mandatory locks on
* these pages but not on the region from pos to ppos+len-1.
*/
- written = cifs_user_writev(iocb, iov, nr_segs, pos);
+ written = cifs_user_writev(iocb, from);
if (written > 0 && CIFS_CACHE_READ(cinode)) {
/*
* Windows 7 server can delay breaking level2 oplock if a write
* request comes - break it on the client to prevent reading
* an old data.
*/
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n",
inode);
cinode->oplock = 0;
return total_read > 0 ? total_read : result;
}
- ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
ssize_t rc;
size_t len, cur_len;
ssize_t total_read = 0;
- loff_t offset = pos;
+ loff_t offset = iocb->ki_pos;
unsigned int npages;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct cifsFileInfo *open_file;
struct cifs_readdata *rdata, *tmp;
struct list_head rdata_list;
- struct iov_iter to;
pid_t pid;
- if (!nr_segs)
- return 0;
-
- len = iov_length(iov, nr_segs);
+ len = iov_iter_count(to);
if (!len)
return 0;
- iov_iter_init(&to, iov, nr_segs, len, 0);
-
INIT_LIST_HEAD(&rdata_list);
cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
open_file = file->private_data;
if (!list_empty(&rdata_list))
rc = 0;
- len = iov_iter_count(&to);
+ len = iov_iter_count(to);
/* the loop below should proceed in the order of increasing offsets */
list_for_each_entry_safe(rdata, tmp, &rdata_list, list) {
again:
goto again;
}
} else {
- rc = cifs_readdata_to_iov(rdata, &to);
+ rc = cifs_readdata_to_iov(rdata, to);
}
}
kref_put(&rdata->refcount, cifs_uncached_readdata_release);
}
- total_read = len - iov_iter_count(&to);
+ total_read = len - iov_iter_count(to);
cifs_stats_bytes_read(tcon, total_read);
rc = 0;
if (total_read) {
- iocb->ki_pos = pos + total_read;
+ iocb->ki_pos += total_read;
return total_read;
}
return rc;
}
ssize_t
- cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
* pos+len-1.
*/
if (!CIFS_CACHE_READ(cinode))
- return cifs_user_readv(iocb, iov, nr_segs, pos);
+ return cifs_user_readv(iocb, to);
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
- return generic_file_aio_read(iocb, iov, nr_segs, pos);
+ return generic_file_read_iter(iocb, to);
/*
* We need to hold the sem to be sure nobody modifies lock list
* with a brlock that prevents reading.
*/
down_read(&cinode->lock_sem);
- if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs),
+ if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to),
tcon->ses->server->vals->shared_lock_type,
NULL, CIFS_READ_OP))
- rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
+ rc = generic_file_read_iter(iocb, to);
up_read(&cinode->lock_sem);
return rc;
}
xid = get_xid();
if (!CIFS_CACHE_READ(CIFS_I(inode))) {
- rc = cifs_invalidate_mapping(inode);
+ rc = cifs_zap_mapping(inode);
if (rc)
return rc;
}
if (!CIFS_CACHE_READ(cinode)) {
rc = filemap_fdatawait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
- cifs_invalidate_mapping(inode);
+ cifs_zap_mapping(inode);
}
cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
}
* Direct IO is not yet supported in the cached mode.
*/
static ssize_t
- cifs_direct_io(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+ cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t pos)
{
/*
* FIXME
return sum < 0 ? 0 : sum;
}
-int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
+int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
struct dentry *parent = dentry->d_parent;
if (IS_ROOT(dentry))
return NULL;
+ if (unlikely((int)dentry->d_lockref.count < 0))
+ return NULL;
if (likely(spin_trylock(&parent->d_lock)))
return parent;
- spin_unlock(&dentry->d_lock);
rcu_read_lock();
+ spin_unlock(&dentry->d_lock);
again:
parent = ACCESS_ONCE(dentry->d_parent);
spin_lock(&parent->d_lock);
WARN_ON_ONCE(IS_RDONLY(inode) &&
!(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
- if (ext3_journal_current_handle())
- goto no_write;
-
trace_ext3_journalled_writepage(page);
- handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto no_write;
- }
-
if (!page_has_buffers(page) || PageChecked(page)) {
+ if (ext3_journal_current_handle())
+ goto no_write;
+
+ handle = ext3_journal_start(inode,
+ ext3_writepage_trans_blocks(inode));
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto no_write;
+ }
/*
* It's mmapped pagecache. Add buffers and journal it. There
* doesn't seem much point in redirtying the page here.
atomic_set(&EXT3_I(inode)->i_datasync_tid,
handle->h_transaction->t_tid);
unlock_page(page);
+ err = ext3_journal_stop(handle);
+ if (!ret)
+ ret = err;
} else {
/*
- * It may be a page full of checkpoint-mode buffers. We don't
- * really know unless we go poke around in the buffer_heads.
- * But block_write_full_page will do the right thing.
+ * It is a page full of checkpoint-mode buffers. Go and write
+ * them. They should have been already mapped when they went
+ * to the journal so provide NULL get_block function to catch
+ * errors.
*/
- ret = block_write_full_page(page, ext3_get_block, wbc);
+ ret = block_write_full_page(page, NULL, wbc);
}
- err = ext3_journal_stop(handle);
- if (!ret)
- ret = err;
out:
return ret;
* VFS code falls back into buffered path in that case so we are safe.
*/
static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
handle_t *handle;
ssize_t ret;
int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
int retries = 0;
- trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext3_direct_IO_enter(inode, offset, count, rw);
if (rw == WRITE) {
loff_t final_size = offset + count;
}
retry:
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- ext3_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;
if (end > isize)
ext3_truncate_failed_direct_write(inode);
ret = err;
}
out:
- trace_ext3_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
return ret;
}
struct inode vfs_inode;
struct jbd2_inode *jinode;
+ spinlock_t i_raw_lock; /* protects updates to the raw inode */
+
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
- __le32 s_reserved[108]; /* Padding to the end of the block */
+ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
+ __le32 s_reserved[106]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_fsblk_t block);
-extern void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- ext4_group_t block_group,
- struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
struct buffer_head *bh);
extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
-extern void ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
-extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_block_truncate_page(handle_t *handle,
- struct address_space *mapping, loff_t from);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs);
+ struct iov_iter *iter, loff_t offset);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
/* super.c */
extern int ext4_calculate_overhead(struct super_block *sb);
-extern int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb);
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
-extern void ext4_unwritten_wait(struct inode *inode);
/* inline.c */
extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
- struct ext4_iloc *iloc,
- void *buffer, loff_t pos,
- unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc);
+ struct writeback_control *wbc,
+ bool keep_towrite);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
-extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
-extern int ext4_mmp_csum_verify(struct super_block *sb,
- struct mmp_struct *mmp);
/*
* Note that these flags will never ever appear in a buffer_head's state flag.
return 0;
}
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
* or one thread will zero the other's data, causing corruption.
*/
static int
- ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
{
struct super_block *sb = inode->i_sb;
int blockmask = sb->s_blocksize - 1;
- size_t count = iov_length(iov, nr_segs);
- loff_t final_size = pos + count;
if (pos >= i_size_read(inode))
return 0;
- if ((pos & blockmask) || (final_size & blockmask))
+ if ((pos | iov_iter_alignment(from)) & blockmask)
return 1;
return 0;
}
static ssize_t
- ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(iocb->ki_filp);
struct blk_plug plug;
int o_direct = file->f_flags & O_DIRECT;
int overwrite = 0;
- size_t length = iov_length(iov, nr_segs);
+ size_t length = iov_iter_count(from);
ssize_t ret;
-
- BUG_ON(iocb->ki_pos != pos);
+ loff_t pos = iocb->ki_pos;
/*
* Unaligned direct AIO must be serialized; see comment above
ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb) &&
(file->f_flags & O_APPEND ||
- ext4_unaligned_aio(inode, iov, nr_segs, pos))) {
+ ext4_unaligned_aio(inode, from, pos))) {
aio_mutex = ext4_aio_mutex(inode);
mutex_lock(aio_mutex);
ext4_unwritten_wait(inode);
goto errout;
}
- if (pos + length > sbi->s_bitmap_maxbytes) {
- nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
- sbi->s_bitmap_maxbytes - pos);
- }
+ if (pos + length > sbi->s_bitmap_maxbytes)
+ iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
}
if (o_direct) {
}
}
- ret = __generic_file_aio_write(iocb, iov, nr_segs);
+ ret = __generic_file_write_iter(iocb, from);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
const struct file_operations ext4_file_operations = {
.llseek = ext4_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = ext4_file_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = ext4_file_write_iter,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
.release = ext4_release_file,
.fsync = ext4_sync_file,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = ext4_fallocate,
};
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
+ if (ext4_has_inline_data(inode))
+ return 0;
+
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
* could be converted.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
* file system block.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
*/
- down_write((&EXT4_I(inode)->i_data_sem));
+ down_write(&EXT4_I(inode)->i_data_sem);
/*
* if the caller is from delayed allocation writeout path
*/
if (dirty)
clear_buffer_dirty(bh);
+ BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
ext4_es_lru_add(inode);
if (ext4_es_is_hole(&es)) {
retval = 0;
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
* Try to see if we can get the block without requesting a new
* file system block.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode)) {
/*
* We will soon create blocks for this page, and let
BUG_ON(!ext4_handle_valid(handle));
if (inline_data) {
+ BUFFER_TRACE(inode_bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode_bh);
err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
+ bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
unlock_page(page);
return 0;
}
+ keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
unlock_page(page);
return -ENOMEM;
}
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
else
len = PAGE_CACHE_SIZE;
clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
*
*/
static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
int overwrite = 0;
get_block_t *get_block_func = NULL;
int dio_flags = 0;
/* Use the old path for reads and writes beyond i_size. */
if (rw != WRITE || final_size > inode->i_size)
- return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+ return ext4_ind_direct_IO(rw, iocb, iter, offset);
BUG_ON(iocb->private == NULL);
dio_flags = DIO_LOCKING;
}
ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
+ inode->i_sb->s_bdev, iter,
+ offset,
get_block_func,
ext4_end_io_dio,
NULL,
}
static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ size_t count = iov_iter_count(iter);
ssize_t ret;
/*
if (ext4_has_inline_data(inode))
return 0;
- trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext4_direct_IO_enter(inode, offset, count, rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+ ret = ext4_ext_direct_IO(rw, iocb, iter, offset);
else
- ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
- trace_ext4_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ ret = ext4_ind_direct_IO(rw, iocb, iter, offset);
+ trace_ext4_direct_IO_exit(inode, offset, count, rw, ret);
return ret;
}
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
-int ext4_block_truncate_page(handle_t *handle,
+static int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_CACHE_SIZE-1);
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
+ struct super_block *sb = inode->i_sb;
int err = 0, rc, block;
- int need_datasync = 0;
+ int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
- /* For fields not not tracking in the in-memory inode,
+ spin_lock(&ei->i_raw_lock);
+
+ /* For fields not tracked in the in-memory inode,
* initialise them to zero for new inodes. */
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
- if (ext4_inode_blocks_set(handle, raw_inode, ei))
+ if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
+ spin_unlock(&ei->i_raw_lock);
goto out_brelse;
+ }
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
need_datasync = 1;
}
if (ei->i_disksize > 0x7fffffffULL) {
- struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
- cpu_to_le32(EXT4_GOOD_OLD_REV)) {
- /* If this is the first large file
- * created, add a flag to the superblock.
- */
- err = ext4_journal_get_write_access(handle,
- EXT4_SB(sb)->s_sbh);
- if (err)
- goto out_brelse;
- ext4_update_dynamic_rev(sb);
- EXT4_SET_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
- ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
- }
+ cpu_to_le32(EXT4_GOOD_OLD_REV))
+ set_large_file = 1;
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
ext4_inode_csum_set(inode, raw_inode, ei);
+ spin_unlock(&ei->i_raw_lock);
+
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
-
+ if (set_large_file) {
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_brelse;
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_super(handle, sb);
+ }
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
if (unlikely(dn.data_blkaddr == NEW_ADDR))
return ERR_PTR(-EINVAL);
- page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+ page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
int err;
repeat:
- page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+ page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
goto put_out;
}
- end_offset = IS_INODE(dn.node_page) ?
- ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
bh_result->b_size = (((size_t)1) << blkbits);
dn.ofs_in_node++;
pgofs++;
if (dn.data_blkaddr == NEW_ADDR)
goto put_out;
- end_offset = IS_INODE(dn.node_page) ?
- ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
}
if (maxblocks > (bh_result->b_size >> blkbits)) {
return err;
}
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len, get_data_block);
+}
+
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
int ret;
+ trace_f2fs_readpage(page, DATA);
+
/* If the file has inline data, try to read it directlly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
};
+ trace_f2fs_writepage(page, DATA);
+
if (page->index < end_index)
goto write;
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_CACHE_SIZE - 1);
- if ((page->index >= end_index + 1) || !offset) {
- inode_dec_dirty_dents(inode);
+ if ((page->index >= end_index + 1) || !offset)
goto out;
- }
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
- inode_dec_dirty_dents(inode);
err = do_write_data_page(page, &fio);
goto done;
}
clear_cold_data(page);
out:
+ inode_dec_dirty_dents(inode);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
return 0;
redirty_out:
- wbc->pages_skipped++;
- account_page_redirty(page);
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
int ret;
long diff;
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
+
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
- get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA))
+ get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+ available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
diff = nr_pages_to_write(sbi, DATA, wbc);
struct dnode_of_data dn;
int err = 0;
+ trace_f2fs_write_begin(inode, pos, len, flags);
+
f2fs_balance_fs(sbi);
repeat:
err = f2fs_convert_inline_data(inode, pos + len);
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
+
+ /* to avoid latency during memory pressure */
+ unlock_page(page);
+
*pagep = page;
if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
f2fs_unlock_op(sbi);
if (err) {
- f2fs_put_page(page, 1);
+ f2fs_put_page(page, 0);
return err;
}
inline_data:
+ lock_page(page);
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ f2fs_wait_on_page_writeback(page, DATA);
+
if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
return 0;
{
struct inode *inode = page->mapping->host;
+ trace_f2fs_write_end(inode, pos, len, copied);
+
SetPageUptodate(page);
set_page_dirty(page);
}
static int check_direct_IO(struct inode *inode, int rw,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
- int i;
if (rw == READ)
return 0;
if (offset & blocksize_mask)
return -EINVAL;
- for (i = 0; i < nr_segs; i++)
- if (iov[i].iov_len & blocksize_mask)
- return -EINVAL;
+ if (iov_iter_alignment(iter) & blocksize_mask)
+ return -EINVAL;
+
return 0;
}
static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
if (f2fs_has_inline_data(inode))
return 0;
- if (check_direct_IO(inode, rw, iov, offset, nr_segs))
+ if (check_direct_IO(inode, rw, iter, offset))
return 0;
- return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- get_data_block);
+ /* clear fsync mark to recover these blocks */
+ fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
+
+ return blockdev_direct_IO(rw, iocb, inode, iter, offset,
+ get_data_block);
}
static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
+ struct inode *inode = mapping->host;
+
+ if (f2fs_has_inline_data(inode))
+ return 0;
+
return generic_block_bmap(mapping, block, get_data_block);
}
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
+#include <linux/pagevec.h>
#include "f2fs.h"
#include "node.h"
return ret;
}
+static pgoff_t __get_first_dirty_index(struct address_space *mapping,
+ pgoff_t pgofs, int whence)
+{
+ struct pagevec pvec;
+ int nr_pages;
+
+ if (whence != SEEK_DATA)
+ return 0;
+
+ /* find first dirty page index */
+ pagevec_init(&pvec, 0);
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1);
+ pgofs = nr_pages ? pvec.pages[0]->index: LONG_MAX;
+ pagevec_release(&pvec);
+ return pgofs;
+}
+
+static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
+ int whence)
+{
+ switch (whence) {
+ case SEEK_DATA:
+ if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
+ (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+ return true;
+ break;
+ case SEEK_HOLE:
+ if (blkaddr == NULL_ADDR)
+ return true;
+ break;
+ }
+ return false;
+}
+
+static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t maxbytes = inode->i_sb->s_maxbytes;
+ struct dnode_of_data dn;
+ pgoff_t pgofs, end_offset, dirty;
+ loff_t data_ofs = offset;
+ loff_t isize;
+ int err = 0;
+
+ mutex_lock(&inode->i_mutex);
+
+ isize = i_size_read(inode);
+ if (offset >= isize)
+ goto fail;
+
+ /* handle inline data case */
+ if (f2fs_has_inline_data(inode)) {
+ if (whence == SEEK_HOLE)
+ data_ofs = isize;
+ goto found;
+ }
+
+ pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+
+ dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
+
+ for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+ if (err && err != -ENOENT) {
+ goto fail;
+ } else if (err == -ENOENT) {
+ /* direct node is not exist */
+ if (whence == SEEK_DATA) {
+ pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
+ F2FS_I(inode));
+ continue;
+ } else {
+ goto found;
+ }
+ }
+
+ end_offset = IS_INODE(dn.node_page) ?
+ ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+
+ /* find data/hole in dnode block */
+ for (; dn.ofs_in_node < end_offset;
+ dn.ofs_in_node++, pgofs++,
+ data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ block_t blkaddr;
+ blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+ f2fs_put_dnode(&dn);
+ goto found;
+ }
+ }
+ f2fs_put_dnode(&dn);
+ }
+
+ if (whence == SEEK_DATA)
+ goto fail;
+found:
+ if (whence == SEEK_HOLE && data_ofs > isize)
+ data_ofs = isize;
+ mutex_unlock(&inode->i_mutex);
+ return vfs_setpos(file, data_ofs, maxbytes);
+fail:
+ mutex_unlock(&inode->i_mutex);
+ return -ENXIO;
+}
+
+static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t maxbytes = inode->i_sb->s_maxbytes;
+
+ switch (whence) {
+ case SEEK_SET:
+ case SEEK_CUR:
+ case SEEK_END:
+ return generic_file_llseek_size(file, offset, whence,
+ maxbytes, i_size_read(inode));
+ case SEEK_DATA:
+ case SEEK_HOLE:
+ return f2fs_seek_block(file, offset, whence);
+ }
+
+ return -EINVAL;
+}
+
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
unsigned offset = from & (PAGE_CACHE_SIZE - 1);
struct page *page;
+ if (f2fs_has_inline_data(inode))
+ return truncate_inline_data(inode, from);
+
if (!offset)
return;
return err;
}
- if (IS_INODE(dn.node_page))
- count = ADDRS_PER_INODE(F2FS_I(inode));
- else
- count = ADDRS_PER_BLOCK;
+ count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count -= dn.ofs_in_node;
f2fs_bug_on(count < 0);
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
+ .fiemap = f2fs_fiemap,
};
static void fill_zero(struct inode *inode, pgoff_t index,
i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
+ f2fs_write_inode(inode, NULL);
}
return ret;
#endif
const struct file_operations f2fs_file_operations = {
- .llseek = generic_file_llseek,
+ .llseek = f2fs_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.open = generic_file_open,
.mmap = f2fs_file_mmap,
.fsync = f2fs_sync_file,
.compat_ioctl = f2fs_compat_ioctl,
#endif
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
};
#define CONFIG_FAT_DEFAULT_IOCHARSET ""
#endif
+#define KB_IN_SECTORS 2
+
+/*
+ * A deserialized copy of the on-disk structure laid out in struct
+ * fat_boot_sector.
+ */
+struct fat_bios_param_block {
+ u16 fat_sector_size;
+ u8 fat_sec_per_clus;
+ u16 fat_reserved;
+ u8 fat_fats;
+ u16 fat_dir_entries;
+ u16 fat_sectors;
+ u16 fat_fat_length;
+ u32 fat_total_sect;
+
+ u8 fat16_state;
+ u32 fat16_vol_id;
+
+ u32 fat32_length;
+ u32 fat32_root_cluster;
+ u16 fat32_info_sector;
+ u8 fat32_state;
+ u32 fat32_vol_id;
+};
+
static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE;
static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET;
+static struct fat_floppy_defaults {
+ unsigned nr_sectors;
+ unsigned sec_per_clus;
+ unsigned dir_entries;
+ unsigned media;
+ unsigned fat_length;
+} floppy_defaults[] = {
+{
+ .nr_sectors = 160 * KB_IN_SECTORS,
+ .sec_per_clus = 1,
+ .dir_entries = 64,
+ .media = 0xFE,
+ .fat_length = 1,
+},
+{
+ .nr_sectors = 180 * KB_IN_SECTORS,
+ .sec_per_clus = 1,
+ .dir_entries = 64,
+ .media = 0xFC,
+ .fat_length = 2,
+},
+{
+ .nr_sectors = 320 * KB_IN_SECTORS,
+ .sec_per_clus = 2,
+ .dir_entries = 112,
+ .media = 0xFF,
+ .fat_length = 1,
+},
+{
+ .nr_sectors = 360 * KB_IN_SECTORS,
+ .sec_per_clus = 2,
+ .dir_entries = 112,
+ .media = 0xFD,
+ .fat_length = 2,
+},
+};
static int fat_add_cluster(struct inode *inode)
{
}
static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
+ size_t count = iov_iter_count(iter);
ssize_t ret;
if (rw == WRITE) {
*
* Return 0, and fallback to normal buffered write.
*/
- loff_t size = offset + iov_length(iov, nr_segs);
+ loff_t size = offset + count;
if (MSDOS_I(inode)->mmu_private < size)
return 0;
}
* FAT need to use the DIO_LOCKING for avoiding the race
* condition of fat_get_block() and ->truncate().
*/
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- fat_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block);
if (ret < 0 && (rw & WRITE))
- fat_write_failed(mapping, offset + iov_length(iov, nr_segs));
+ fat_write_failed(mapping, offset + count);
return ret;
}
static int is_exec(unsigned char *extension)
{
- unsigned char *exe_extensions = "EXECOMBAT", *walk;
+ unsigned char exe_extensions[] = "EXECOMBAT", *walk;
for (walk = exe_extensions; *walk; walk += 3)
if (!strncmp(extension, walk, 3))
seq_puts(m, ",nfs=stale_rw");
if (opts->discard)
seq_puts(m, ",discard");
+ if (opts->dos1xfloppy)
+ seq_puts(m, ",dos1xfloppy");
return 0;
}
Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset,
- Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err,
+ Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy,
};
static const match_table_t fat_tokens = {
{Opt_nfs_stale_rw, "nfs"},
{Opt_nfs_stale_rw, "nfs=stale_rw"},
{Opt_nfs_nostale_ro, "nfs=nostale_ro"},
+ {Opt_dos1xfloppy, "dos1xfloppy"},
{Opt_obsolete, "conv=binary"},
{Opt_obsolete, "conv=text"},
{Opt_obsolete, "conv=auto"},
case Opt_nfs_nostale_ro:
opts->nfs = FAT_NFS_NOSTALE_RO;
break;
+ case Opt_dos1xfloppy:
+ opts->dos1xfloppy = 1;
+ break;
/* msdos specific */
case Opt_dots:
return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
}
+static bool fat_bpb_is_zero(struct fat_boot_sector *b)
+{
+ if (get_unaligned_le16(&b->sector_size))
+ return false;
+ if (b->sec_per_clus)
+ return false;
+ if (b->reserved)
+ return false;
+ if (b->fats)
+ return false;
+ if (get_unaligned_le16(&b->dir_entries))
+ return false;
+ if (get_unaligned_le16(&b->sectors))
+ return false;
+ if (b->media)
+ return false;
+ if (b->fat_length)
+ return false;
+ if (b->secs_track)
+ return false;
+ if (b->heads)
+ return false;
+ return true;
+}
+
+static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b,
+ int silent, struct fat_bios_param_block *bpb)
+{
+ int error = -EINVAL;
+
+ /* Read in BPB ... */
+ memset(bpb, 0, sizeof(*bpb));
+ bpb->fat_sector_size = get_unaligned_le16(&b->sector_size);
+ bpb->fat_sec_per_clus = b->sec_per_clus;
+ bpb->fat_reserved = le16_to_cpu(b->reserved);
+ bpb->fat_fats = b->fats;
+ bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries);
+ bpb->fat_sectors = get_unaligned_le16(&b->sectors);
+ bpb->fat_fat_length = le16_to_cpu(b->fat_length);
+ bpb->fat_total_sect = le32_to_cpu(b->total_sect);
+
+ bpb->fat16_state = b->fat16.state;
+ bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id);
+
+ bpb->fat32_length = le32_to_cpu(b->fat32.length);
+ bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster);
+ bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector);
+ bpb->fat32_state = b->fat32.state;
+ bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id);
+
+ /* Validate this looks like a FAT filesystem BPB */
+ if (!bpb->fat_reserved) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "bogus number of reserved sectors");
+ goto out;
+ }
+ if (!bpb->fat_fats) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus number of FAT structure");
+ goto out;
+ }
+
+ /*
+ * Earlier we checked here that b->secs_track and b->head are nonzero,
+ * but it turns out valid FAT filesystems can have zero there.
+ */
+
+ if (!fat_valid_media(b->media)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)",
+ (unsigned)b->media);
+ goto out;
+ }
+
+ if (!is_power_of_2(bpb->fat_sector_size)
+ || (bpb->fat_sector_size < 512)
+ || (bpb->fat_sector_size > 4096)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus logical sector size %u",
+ (unsigned)bpb->fat_sector_size);
+ goto out;
+ }
+
+ if (!is_power_of_2(bpb->fat_sec_per_clus)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u",
+ (unsigned)bpb->fat_sec_per_clus);
+ goto out;
+ }
+
+ error = 0;
+
+out:
+ return error;
+}
+
+static int fat_read_static_bpb(struct super_block *sb,
+ struct fat_boot_sector *b, int silent,
+ struct fat_bios_param_block *bpb)
+{
+ static const char *notdos1x = "This doesn't look like a DOS 1.x volume";
+
+ struct fat_floppy_defaults *fdefaults = NULL;
+ int error = -EINVAL;
+ sector_t bd_sects;
+ unsigned i;
+
+ bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE;
+
+ /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */
+ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "%s; no bootstrapping code", notdos1x);
+ goto out;
+ }
+
+ /*
+ * If any value in this region is non-zero, it isn't archaic
+ * DOS.
+ */
+ if (!fat_bpb_is_zero(b)) {
+ if (!silent)
+ fat_msg(sb, KERN_ERR,
+ "%s; DOS 2.x BPB is non-zero", notdos1x);
+ goto out;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) {
+ if (floppy_defaults[i].nr_sectors == bd_sects) {
+ fdefaults = &floppy_defaults[i];
+ break;
+ }
+ }
+
+ if (fdefaults == NULL) {
+ if (!silent)
+ fat_msg(sb, KERN_WARNING,
+ "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)",
+ (u64)bd_sects);
+ goto out;
+ }
+
+ if (!silent)
+ fat_msg(sb, KERN_INFO,
+ "This looks like a DOS 1.x volume; assuming default BPB values");
+
+ memset(bpb, 0, sizeof(*bpb));
+ bpb->fat_sector_size = SECTOR_SIZE;
+ bpb->fat_sec_per_clus = fdefaults->sec_per_clus;
+ bpb->fat_reserved = 1;
+ bpb->fat_fats = 2;
+ bpb->fat_dir_entries = fdefaults->dir_entries;
+ bpb->fat_sectors = fdefaults->nr_sectors;
+ bpb->fat_fat_length = fdefaults->fat_length;
+
+ error = 0;
+
+out:
+ return error;
+}
+
/*
* Read the super block of an MS-DOS FS.
*/
struct inode *root_inode = NULL, *fat_inode = NULL;
struct inode *fsinfo_inode = NULL;
struct buffer_head *bh;
- struct fat_boot_sector *b;
+ struct fat_bios_param_block bpb;
struct msdos_sb_info *sbi;
u16 logical_sector_size;
u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors;
int debug;
- unsigned int media;
long error;
char buf[50];
goto out_fail;
}
- b = (struct fat_boot_sector *) bh->b_data;
- if (!b->reserved) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus number of reserved sectors");
- brelse(bh);
- goto out_invalid;
- }
- if (!b->fats) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus number of FAT structure");
- brelse(bh);
- goto out_invalid;
- }
-
- /*
- * Earlier we checked here that b->secs_track and b->head are nonzero,
- * but it turns out valid FAT filesystems can have zero there.
- */
+ error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent,
+ &bpb);
+ if (error == -EINVAL && sbi->options.dos1xfloppy)
+ error = fat_read_static_bpb(sb,
+ (struct fat_boot_sector *)bh->b_data, silent, &bpb);
+ brelse(bh);
- media = b->media;
- if (!fat_valid_media(media)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)",
- media);
- brelse(bh);
+ if (error == -EINVAL)
goto out_invalid;
- }
- logical_sector_size = get_unaligned_le16(&b->sector_size);
- if (!is_power_of_2(logical_sector_size)
- || (logical_sector_size < 512)
- || (logical_sector_size > 4096)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus logical sector size %u",
- logical_sector_size);
- brelse(bh);
- goto out_invalid;
- }
- sbi->sec_per_clus = b->sec_per_clus;
- if (!is_power_of_2(sbi->sec_per_clus)) {
- if (!silent)
- fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u",
- sbi->sec_per_clus);
- brelse(bh);
- goto out_invalid;
- }
+ else if (error)
+ goto out_fail;
+ logical_sector_size = bpb.fat_sector_size;
+ sbi->sec_per_clus = bpb.fat_sec_per_clus;
+
+ error = -EIO;
if (logical_sector_size < sb->s_blocksize) {
fat_msg(sb, KERN_ERR, "logical sector size too small for device"
" (logical sector size = %u)", logical_sector_size);
- brelse(bh);
goto out_fail;
}
+
if (logical_sector_size > sb->s_blocksize) {
- brelse(bh);
+ struct buffer_head *bh_resize;
if (!sb_set_blocksize(sb, logical_sector_size)) {
fat_msg(sb, KERN_ERR, "unable to set blocksize %u",
logical_sector_size);
goto out_fail;
}
- bh = sb_bread(sb, 0);
- if (bh == NULL) {
+
+ /* Verify that the larger boot sector is fully readable */
+ bh_resize = sb_bread(sb, 0);
+ if (bh_resize == NULL) {
fat_msg(sb, KERN_ERR, "unable to read boot sector"
" (logical sector size = %lu)",
sb->s_blocksize);
goto out_fail;
}
- b = (struct fat_boot_sector *) bh->b_data;
+ brelse(bh_resize);
}
mutex_init(&sbi->s_lock);
sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus;
sbi->cluster_bits = ffs(sbi->cluster_size) - 1;
- sbi->fats = b->fats;
+ sbi->fats = bpb.fat_fats;
sbi->fat_bits = 0; /* Don't know yet */
- sbi->fat_start = le16_to_cpu(b->reserved);
- sbi->fat_length = le16_to_cpu(b->fat_length);
+ sbi->fat_start = bpb.fat_reserved;
+ sbi->fat_length = bpb.fat_fat_length;
sbi->root_cluster = 0;
sbi->free_clusters = -1; /* Don't know yet */
sbi->free_clus_valid = 0;
sbi->prev_free = FAT_START_ENT;
sb->s_maxbytes = 0xffffffff;
- if (!sbi->fat_length && b->fat32.length) {
+ if (!sbi->fat_length && bpb.fat32_length) {
struct fat_boot_fsinfo *fsinfo;
struct buffer_head *fsinfo_bh;
/* Must be FAT32 */
sbi->fat_bits = 32;
- sbi->fat_length = le32_to_cpu(b->fat32.length);
- sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster);
+ sbi->fat_length = bpb.fat32_length;
+ sbi->root_cluster = bpb.fat32_root_cluster;
/* MC - if info_sector is 0, don't multiply by 0 */
- sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector);
+ sbi->fsinfo_sector = bpb.fat32_info_sector;
if (sbi->fsinfo_sector == 0)
sbi->fsinfo_sector = 1;
if (fsinfo_bh == NULL) {
fat_msg(sb, KERN_ERR, "bread failed, FSINFO block"
" (sector = %lu)", sbi->fsinfo_sector);
- brelse(bh);
goto out_fail;
}
/* interpret volume ID as a little endian 32 bit integer */
if (sbi->fat_bits == 32)
- sbi->vol_id = (((u32)b->fat32.vol_id[0]) |
- ((u32)b->fat32.vol_id[1] << 8) |
- ((u32)b->fat32.vol_id[2] << 16) |
- ((u32)b->fat32.vol_id[3] << 24));
+ sbi->vol_id = bpb.fat32_vol_id;
else /* fat 16 or 12 */
- sbi->vol_id = (((u32)b->fat16.vol_id[0]) |
- ((u32)b->fat16.vol_id[1] << 8) |
- ((u32)b->fat16.vol_id[2] << 16) |
- ((u32)b->fat16.vol_id[3] << 24));
+ sbi->vol_id = bpb.fat16_vol_id;
sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length;
- sbi->dir_entries = get_unaligned_le16(&b->dir_entries);
+ sbi->dir_entries = bpb.fat_dir_entries;
if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
if (!silent)
fat_msg(sb, KERN_ERR, "bogus directory-entries per block"
" (%u)", sbi->dir_entries);
- brelse(bh);
goto out_invalid;
}
rootdir_sectors = sbi->dir_entries
* sizeof(struct msdos_dir_entry) / sb->s_blocksize;
sbi->data_start = sbi->dir_start + rootdir_sectors;
- total_sectors = get_unaligned_le16(&b->sectors);
+ total_sectors = bpb.fat_sectors;
if (total_sectors == 0)
- total_sectors = le32_to_cpu(b->total_sect);
+ total_sectors = bpb.fat_total_sect;
total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus;
/* some OSes set FAT_STATE_DIRTY and clean it on unmount. */
if (sbi->fat_bits == 32)
- sbi->dirty = b->fat32.state & FAT_STATE_DIRTY;
+ sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY;
else /* fat 16 or 12 */
- sbi->dirty = b->fat16.state & FAT_STATE_DIRTY;
+ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY;
/* check that FAT table does not overflow */
fat_clusters = calc_fat_clusters(sb);
if (!silent)
fat_msg(sb, KERN_ERR, "count of clusters too big (%u)",
total_clusters);
- brelse(bh);
goto out_invalid;
}
if (sbi->prev_free < FAT_START_ENT)
sbi->prev_free = FAT_START_ENT;
- brelse(bh);
-
/* set up enough so that it can read an inode */
fat_hash_init(sb);
dir_hash_init(sb);
* Handle nr_files sysctl
*/
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(ctl_table *table, int write,
+int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#else
-int proc_nr_files(ctl_table *table, int write,
+int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
file->f_path = *path;
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
+ if ((mode & FMODE_READ) &&
+ likely(fop->read || fop->aio_read || fop->read_iter))
+ mode |= FMODE_CAN_READ;
+ if ((mode & FMODE_WRITE) &&
+ likely(fop->write || fop->aio_write || fop->write_iter))
+ mode |= FMODE_CAN_WRITE;
file->f_mode = mode;
file->f_op = fop;
if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
return err;
}
- static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
* i_size is up to date).
*/
if (fc->auto_inval_data ||
- (pos + iov_length(iov, nr_segs) > i_size_read(inode))) {
+ (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) {
int err;
err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
if (err)
return err;
}
- return generic_file_aio_read(iocb, iov, nr_segs, pos);
+ return generic_file_read_iter(iocb, to);
}
static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff,
tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
flush_dcache_page(page);
- mark_page_accessed(page);
-
if (!tmp) {
unlock_page(page);
page_cache_release(page);
return res > 0 ? res : err;
}
- static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
- size_t count = 0;
- size_t ocount = 0;
+ size_t count = iov_iter_count(from);
ssize_t written = 0;
ssize_t written_buffered = 0;
struct inode *inode = mapping->host;
ssize_t err;
- struct iov_iter i;
loff_t endbyte = 0;
+ loff_t pos = iocb->ki_pos;
if (get_fuse_conn(inode)->writeback_cache) {
/* Update size (EOF optimization) and mode (SUID clearing) */
if (err)
return err;
- return generic_file_aio_write(iocb, iov, nr_segs, pos);
+ return generic_file_write_iter(iocb, from);
}
- WARN_ON(iocb->ki_pos != pos);
-
- ocount = 0;
- err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
- if (err)
- return err;
-
- count = ocount;
mutex_lock(&inode->i_mutex);
/* We can write back this queue in page reclaim */
if (count == 0)
goto out;
+ iov_iter_truncate(from, count);
err = file_remove_suid(file);
if (err)
goto out;
goto out;
if (file->f_flags & O_DIRECT) {
- written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
- count, ocount);
- if (written < 0 || written == count)
+ written = generic_file_direct_write(iocb, from, pos);
+ if (written < 0 || !iov_iter_count(from))
goto out;
pos += written;
- count -= written;
- iov_iter_init(&i, iov, nr_segs, count, written);
- written_buffered = fuse_perform_write(file, mapping, &i, pos);
+ written_buffered = fuse_perform_write(file, mapping, from, pos);
if (written_buffered < 0) {
err = written_buffered;
goto out;
written += written_buffered;
iocb->ki_pos = pos + written_buffered;
} else {
- iov_iter_init(&i, iov, nr_segs, count, 0);
- written = fuse_perform_write(file, mapping, &i, pos);
+ written = fuse_perform_write(file, mapping, from, pos);
if (written >= 0)
iocb->ki_pos = pos + written;
}
size_t nbytes = 0; /* # bytes already packed in req */
/* Special case for kernel I/O: can copy directly into the buffer */
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (ii->type & ITER_KVEC) {
unsigned long user_addr = fuse_get_user_addr(ii);
size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
unsigned npages;
- unsigned long user_addr = fuse_get_user_addr(ii);
- unsigned offset = user_addr & ~PAGE_MASK;
- size_t frag_size = fuse_get_frag_size(ii, *nbytesp - nbytes);
- int ret;
-
+ size_t start;
unsigned n = req->max_pages - req->num_pages;
- frag_size = min_t(size_t, frag_size, n << PAGE_SHIFT);
-
- npages = (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
- npages = clamp(npages, 1U, n);
-
- ret = get_user_pages_fast(user_addr, npages, !write,
- &req->pages[req->num_pages]);
+ ssize_t ret = iov_iter_get_pages(ii,
+ &req->pages[req->num_pages],
+ n * PAGE_SIZE, &start);
if (ret < 0)
return ret;
- npages = ret;
- frag_size = min_t(size_t, frag_size,
- (npages << PAGE_SHIFT) - offset);
- iov_iter_advance(ii, frag_size);
+ iov_iter_advance(ii, ret);
+ nbytes += ret;
+
+ ret += start;
+ npages = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
- req->page_descs[req->num_pages].offset = offset;
+ req->page_descs[req->num_pages].offset = start;
fuse_page_descs_length_init(req, req->num_pages, npages);
req->num_pages += npages;
req->page_descs[req->num_pages - 1].length -=
- (npages << PAGE_SHIFT) - offset - frag_size;
-
- nbytes += frag_size;
+ (PAGE_SIZE - ret) & (PAGE_SIZE - 1);
}
if (write)
static inline int fuse_iter_npages(const struct iov_iter *ii_p)
{
- struct iov_iter ii = *ii_p;
- int npages = 0;
-
- while (iov_iter_count(&ii) && npages < FUSE_MAX_PAGES_PER_REQ) {
- unsigned long user_addr = fuse_get_user_addr(&ii);
- unsigned offset = user_addr & ~PAGE_MASK;
- size_t frag_size = iov_iter_single_seg_count(&ii);
-
- npages += (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
- iov_iter_advance(&ii, frag_size);
- }
-
- return min(npages, FUSE_MAX_PAGES_PER_REQ);
+ return iov_iter_npages(ii_p, FUSE_MAX_PAGES_PER_REQ);
}
- ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
- unsigned long nr_segs, size_t count, loff_t *ppos,
- int flags)
+ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
+ loff_t *ppos, int flags)
{
int write = flags & FUSE_DIO_WRITE;
int cuse = flags & FUSE_DIO_CUSE;
struct fuse_conn *fc = ff->fc;
size_t nmax = write ? fc->max_write : fc->max_read;
loff_t pos = *ppos;
+ size_t count = iov_iter_count(iter);
pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT;
pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
ssize_t res = 0;
struct fuse_req *req;
- struct iov_iter ii;
-
- iov_iter_init(&ii, iov, nr_segs, count, 0);
if (io->async)
- req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii));
+ req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
else
- req = fuse_get_req(fc, fuse_iter_npages(&ii));
+ req = fuse_get_req(fc, fuse_iter_npages(iter));
if (IS_ERR(req))
return PTR_ERR(req);
size_t nres;
fl_owner_t owner = current->files;
size_t nbytes = min(count, nmax);
- int err = fuse_get_user_pages(req, &ii, &nbytes, write);
+ int err = fuse_get_user_pages(req, iter, &nbytes, write);
if (err) {
res = err;
break;
fuse_put_request(fc, req);
if (io->async)
req = fuse_get_req_for_background(fc,
- fuse_iter_npages(&ii));
+ fuse_iter_npages(iter));
else
- req = fuse_get_req(fc, fuse_iter_npages(&ii));
+ req = fuse_get_req(fc, fuse_iter_npages(iter));
if (IS_ERR(req))
break;
}
EXPORT_SYMBOL_GPL(fuse_direct_io);
static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
- const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos,
- size_t count)
+ struct iov_iter *iter,
+ loff_t *ppos)
{
ssize_t res;
struct file *file = io->file;
if (is_bad_inode(inode))
return -EIO;
- res = fuse_direct_io(io, iov, nr_segs, count, ppos, 0);
+ res = fuse_direct_io(io, iter, ppos, 0);
fuse_invalidate_attr(inode);
{
struct fuse_io_priv io = { .async = 0, .file = file };
struct iovec iov = { .iov_base = buf, .iov_len = count };
- return __fuse_direct_read(&io, &iov, 1, ppos, count);
+ struct iov_iter ii;
+ iov_iter_init(&ii, READ, &iov, 1, count);
+ return __fuse_direct_read(&io, &ii, ppos);
}
static ssize_t __fuse_direct_write(struct fuse_io_priv *io,
- const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+ struct iov_iter *iter,
+ loff_t *ppos)
{
struct file *file = io->file;
struct inode *inode = file_inode(file);
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
ssize_t res;
+
res = generic_write_checks(file, ppos, &count, 0);
- if (!res)
- res = fuse_direct_io(io, iov, nr_segs, count, ppos,
- FUSE_DIO_WRITE);
+ if (!res) {
+ iov_iter_truncate(iter, count);
+ res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE);
+ }
fuse_invalidate_attr(inode);
struct inode *inode = file_inode(file);
ssize_t res;
struct fuse_io_priv io = { .async = 0, .file = file };
+ struct iov_iter ii;
+ iov_iter_init(&ii, WRITE, &iov, 1, count);
if (is_bad_inode(inode))
return -EIO;
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
- res = __fuse_direct_write(&io, &iov, 1, ppos);
+ res = __fuse_direct_write(&io, &ii, ppos);
if (res > 0)
fuse_write_update_size(inode, *ppos);
mutex_unlock(&inode->i_mutex);
struct fuse_file *ff = file->private_data;
/* emulate flock with POSIX locks */
- fl->fl_owner = (fl_owner_t) file;
ff->flock = true;
err = fuse_setlk(file, fl, 1);
}
if (!bytes)
return 0;
- iov_iter_init(&ii, iov, nr_segs, bytes, 0);
+ iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes);
while (iov_iter_count(&ii)) {
struct page *page = pages[page_idx++];
}
static ssize_t
- fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
ssize_t ret = 0;
struct file *file = iocb->ki_filp;
loff_t pos = 0;
struct inode *inode;
loff_t i_size;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
struct fuse_io_priv *io;
pos = offset;
if (offset >= i_size)
return 0;
count = min_t(loff_t, count, fuse_round_up(i_size - offset));
+ iov_iter_truncate(iter, count);
}
io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
io->async = false;
if (rw == WRITE)
- ret = __fuse_direct_write(io, iov, nr_segs, &pos);
+ ret = __fuse_direct_write(io, iter, &pos);
else
- ret = __fuse_direct_read(io, iov, nr_segs, &pos, count);
+ ret = __fuse_direct_read(io, iter, &pos);
if (io->async) {
fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
static const struct file_operations fuse_file_operations = {
.llseek = fuse_file_llseek,
- .read = do_sync_read,
- .aio_read = fuse_file_aio_read,
- .write = do_sync_write,
- .aio_write = fuse_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = fuse_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = fuse_file_write_iter,
.mmap = fuse_file_mmap,
.open = fuse_open,
.flush = fuse_flush,
ret = gfs2_write_cache_jdata(mapping, wbc);
if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
- gfs2_log_flush(sdp, ip->i_gl);
+ gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
ret = gfs2_write_cache_jdata(mapping, wbc);
}
return ret;
p = kmap_atomic(page);
memcpy(buf + copied, p + offset, amt);
kunmap_atomic(p);
- mark_page_accessed(page);
page_cache_release(page);
copied += amt;
index++;
static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
*/
if (mapping->nrpages) {
loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
- loff_t len = iov_length(iov, nr_segs);
+ loff_t len = iov_iter_count(iter);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
truncate_inode_pages_range(mapping, lstart, end);
}
- rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs, gfs2_get_block_direct,
- NULL, NULL, 0);
+ rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+ iter, offset,
+ gfs2_get_block_direct, NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
GFS2_DIF_INHERIT_JDATA)
/**
- * gfs2_set_flags - set flags on an inode
- * @inode: The inode
- * @flags: The flags to set
+ * do_gfs2_set_flags - set flags on an inode
+ * @filp: file pointer
+ * @reqflags: The flags to set
* @mask: Indicates which flags are valid
*
*/
}
if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
if (flags & GFS2_DIF_JDATA)
- gfs2_log_flush(sdp, ip->i_gl);
+ gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
error = filemap_fdatawrite(inode->i_mapping);
if (error)
goto out;
/**
* gfs2_size_hint - Give a hint to the size of a write request
- * @file: The struct file
+ * @filep: The struct file
* @offset: The file offset of the write
* @size: The length of the write
*
/**
* gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
* @vma: The virtual memory area
- * @page: The page which is about to become writable
+ * @vmf: The virtual memory fault containing the page to become writable
*
* When the page becomes writable, we need to ensure that we have
* blocks allocated on disk to back that page.
}
/**
- * gfs2_file_aio_write - Perform a write to a file
+ * gfs2_file_write_iter - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
*
*/
- static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- size_t writesize = iov_length(iov, nr_segs);
struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
if (ret)
return ret;
- gfs2_size_hint(file, pos, writesize);
+ gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from));
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
gfs2_glock_dq_uninit(&gh);
}
- return generic_file_aio_write(iocb, iov, nr_segs, pos);
+ return generic_file_write_iter(iocb, from);
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
const struct file_operations gfs2_file_fops = {
.llseek = gfs2_llseek,
- .read = do_sync_read,
- .aio_read = generic_file_aio_read,
- .write = do_sync_write,
- .aio_write = gfs2_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = generic_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = gfs2_file_write_iter,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
.lock = gfs2_lock,
.flock = gfs2_flock,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.setlease = gfs2_setlease,
.fallocate = gfs2_fallocate,
};
const struct file_operations gfs2_file_fops_nolock = {
.llseek = gfs2_llseek,
- .read = do_sync_read,
- .aio_read = generic_file_aio_read,
- .write = do_sync_write,
- .aio_write = gfs2_file_aio_write,
+ .read = new_sync_read,
+ .read_iter = generic_file_read_iter,
+ .write = new_sync_write,
+ .write_iter = gfs2_file_write_iter,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
.release = gfs2_release,
.fsync = gfs2_fsync,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.setlease = generic_setlease,
.fallocate = gfs2_fallocate,
};
return atomic_dec_and_test(&dreq->io_count);
}
+/*
+ * nfs_direct_select_verf - select the right verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
+ * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ *
+ * returns the correct verifier to use given the role of the server
+ */
+static struct nfs_writeverf *
+nfs_direct_select_verf(struct nfs_direct_req *dreq,
+ struct nfs_client *ds_clp,
+ int ds_idx)
+{
+ struct nfs_writeverf *verfp = &dreq->verf;
+
+#ifdef CONFIG_NFS_V4_1
+ if (ds_clp) {
+ /* pNFS is in use, use the DS verf */
+ if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
+ verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+ else
+ WARN_ON_ONCE(1);
+ }
+#endif
+ return verfp;
+}
+
+
+/*
+ * nfs_direct_set_hdr_verf - set the write/commit verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verfs
+ *
+ * Set the server's (MDS or DS) "seen" verifier
+ */
+static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
+ struct nfs_pgio_header *hdr)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+ hdr->data->ds_idx);
+ WARN_ON_ONCE(verfp->committed >= 0);
+ memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+ WARN_ON_ONCE(verfp->committed < 0);
+}
+
+/*
+ * nfs_direct_cmp_hdr_verf - compare verifier for pgio header
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verf
+ *
+ * set the server's "seen" verf if not initialized.
+ * returns result of comparison between @hdr->verf and the "seen"
+ * verf of the server used by @hdr (DS or MDS)
+ */
+static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
+ struct nfs_pgio_header *hdr)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+ hdr->data->ds_idx);
+ if (verfp->committed < 0) {
+ nfs_direct_set_hdr_verf(dreq, hdr);
+ return 0;
+ }
+ return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+}
+
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
+/*
+ * nfs_direct_cmp_commit_data_verf - compare verifier for commit data
+ * @dreq - direct request possibly spanning multiple servers
+ * @data - commit data to validate against previously seen verf
+ *
+ * returns result of comparison between @data->verf and the verf of
+ * the server used by @data (DS or MDS)
+ */
+static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
+ struct nfs_commit_data *data)
+{
+ struct nfs_writeverf *verfp;
+
+ verfp = nfs_direct_select_verf(dreq, data->ds_clp,
+ data->ds_commit_index);
+ WARN_ON_ONCE(verfp->committed < 0);
+ return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
+}
+#endif
+
/**
* nfs_direct_IO - NFS address space operation for direct I/O
* @rw: direction (read or write)
* shunt off direct read and write requests before the VFS gets them,
* so this method is only ever called for swap.
*/
- ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
+ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
{
#ifndef CONFIG_NFS_SWAP
dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
- iocb->ki_filp, (long long) pos, nr_segs);
+ iocb->ki_filp, (long long) pos, iter->nr_segs);
return -EINVAL;
#else
VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
if (rw == READ || rw == KERNEL_READ)
- return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+ return nfs_file_direct_read(iocb, iter, pos,
rw == READ ? true : false);
- return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+ return nfs_file_direct_write(iocb, iter, pos,
rw == WRITE ? true : false);
#endif /* CONFIG_NFS_SWAP */
}
kref_get(&dreq->kref);
init_completion(&dreq->completion);
INIT_LIST_HEAD(&dreq->mds_cinfo.list);
+ dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */
INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
spin_lock_init(&dreq->lock);
* handled automatically by nfs_direct_read_result(). Otherwise, if
* no requests have been sent, just return an error.
*/
- static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
- const struct iovec *iov,
- loff_t pos, bool uio)
- {
- struct nfs_direct_req *dreq = desc->pg_dreq;
- struct nfs_open_context *ctx = dreq->ctx;
- struct inode *inode = ctx->dentry->d_inode;
- unsigned long user_addr = (unsigned long)iov->iov_base;
- size_t count = iov->iov_len;
- size_t rsize = NFS_SERVER(inode)->rsize;
- unsigned int pgbase;
- int result;
- ssize_t started = 0;
- struct page **pagevec = NULL;
- unsigned int npages;
-
- do {
- size_t bytes;
- int i;
- pgbase = user_addr & ~PAGE_MASK;
- bytes = min(max_t(size_t, rsize, PAGE_SIZE), count);
+ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
+ struct iov_iter *iter,
+ loff_t pos)
+ {
+ struct nfs_pageio_descriptor desc;
+ struct inode *inode = dreq->inode;
+ ssize_t result = -EINVAL;
+ size_t requested_bytes = 0;
+ size_t rsize = max_t(size_t, NFS_SERVER(inode)->rsize, PAGE_SIZE);
- result = -ENOMEM;
- npages = nfs_page_array_len(pgbase, bytes);
- if (!pagevec)
- pagevec = kmalloc(npages * sizeof(struct page *),
- GFP_KERNEL);
- if (!pagevec)
- break;
- if (uio) {
- down_read(¤t->mm->mmap_sem);
- result = get_user_pages(current, current->mm, user_addr,
- npages, 1, 0, pagevec, NULL);
- up_read(¤t->mm->mmap_sem);
- if (result < 0)
- break;
- } else {
- WARN_ON(npages != 1);
- result = get_kernel_page(user_addr, 1, pagevec);
- if (WARN_ON(result != 1))
- break;
- }
- NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
++ nfs_pageio_init_read(&desc, dreq->inode, false,
+ &nfs_direct_read_completion_ops);
+ get_dreq(dreq);
+ desc.pg_dreq = dreq;
+ atomic_inc(&inode->i_dio_count);
- if ((unsigned)result < npages) {
- bytes = result * PAGE_SIZE;
- if (bytes <= pgbase) {
- nfs_direct_release_pages(pagevec, result);
- break;
- }
- bytes -= pgbase;
- npages = result;
- }
+ while (iov_iter_count(iter)) {
+ struct page **pagevec;
+ size_t bytes;
+ size_t pgbase;
+ unsigned npages, i;
+ result = iov_iter_get_pages_alloc(iter, &pagevec,
+ rsize, &pgbase);
+ if (result < 0)
+ break;
+
+ bytes = result;
+ iov_iter_advance(iter, bytes);
+ npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
for (i = 0; i < npages; i++) {
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
/* XXX do we need to do the eof zeroing found in async_filler? */
- req = nfs_create_request(dreq->ctx, dreq->inode,
- pagevec[i],
+ req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
pgbase, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
}
req->wb_index = pos >> PAGE_SHIFT;
req->wb_offset = pos & ~PAGE_MASK;
- if (!nfs_pageio_add_request(desc, req)) {
- result = desc->pg_error;
+ if (!nfs_pageio_add_request(&desc, req)) {
+ result = desc.pg_error;
nfs_release_request(req);
break;
}
pgbase = 0;
bytes -= req_len;
- started += req_len;
- user_addr += req_len;
+ requested_bytes += req_len;
pos += req_len;
- count -= req_len;
dreq->bytes_left -= req_len;
}
- /* The nfs_page now hold references to these pages */
nfs_direct_release_pages(pagevec, npages);
- } while (count != 0 && result >= 0);
-
- kfree(pagevec);
-
- if (started)
- return started;
- return result < 0 ? (ssize_t) result : -EFAULT;
- }
-
- static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos, bool uio)
- {
- struct nfs_pageio_descriptor desc;
- struct inode *inode = dreq->inode;
- ssize_t result = -EINVAL;
- size_t requested_bytes = 0;
- unsigned long seg;
-
- nfs_pageio_init_read(&desc, dreq->inode, false,
- &nfs_direct_read_completion_ops);
- get_dreq(dreq);
- desc.pg_dreq = dreq;
- atomic_inc(&inode->i_dio_count);
-
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *vec = &iov[seg];
- result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
+ kvfree(pagevec);
if (result < 0)
break;
- requested_bytes += result;
- if ((size_t)result < vec->iov_len)
- break;
- pos += vec->iov_len;
}
nfs_pageio_complete(&desc);
/**
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
- * @iov: vector of user buffers into which to read data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers into which to read data
* @pos: byte offset in file where reading starts
*
* We use this function for direct reads instead of calling
* client must read the updated atime from the server back into its
* cache.
*/
- ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, bool uio)
+ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t pos, bool uio)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct nfs_direct_req *dreq;
struct nfs_lock_context *l_ctx;
ssize_t result = -EINVAL;
- size_t count;
-
- count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
goto out_unlock;
dreq->inode = inode;
- dreq->bytes_left = iov_length(iov, nr_segs);
+ dreq->bytes_left = count;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
if (!is_sync_kiocb(iocb))
dreq->iocb = iocb;
- NFS_I(inode)->read_io += iov_length(iov, nr_segs);
- result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+ NFS_I(inode)->read_io += count;
+ result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
mutex_unlock(&inode->i_mutex);
dreq->count = 0;
get_dreq(dreq);
- NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
+ nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
dprintk("NFS: %5u commit failed with error %d.\n",
data->task.tk_pid, status);
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
- } else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) {
+ } else if (nfs_direct_cmp_commit_data_verf(dreq, data)) {
dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
}
}
#endif
- /*
- * NB: Return the value of the first error return code. Subsequent
- * errors after the first one are ignored.
- */
- /*
- * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
- * operation. If nfs_writedata_alloc() or get_user_pages() fails,
- * bail and stop sending more writes. Write length accounting is
- * handled automatically by nfs_direct_write_result(). Otherwise, if
- * no requests have been sent, just return an error.
- */
- static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
- const struct iovec *iov,
- loff_t pos, bool uio)
- {
- struct nfs_direct_req *dreq = desc->pg_dreq;
- struct nfs_open_context *ctx = dreq->ctx;
- struct inode *inode = ctx->dentry->d_inode;
- unsigned long user_addr = (unsigned long)iov->iov_base;
- size_t count = iov->iov_len;
- size_t wsize = NFS_SERVER(inode)->wsize;
- unsigned int pgbase;
- int result;
- ssize_t started = 0;
- struct page **pagevec = NULL;
- unsigned int npages;
-
- do {
- size_t bytes;
- int i;
-
- pgbase = user_addr & ~PAGE_MASK;
- bytes = min(max_t(size_t, wsize, PAGE_SIZE), count);
-
- result = -ENOMEM;
- npages = nfs_page_array_len(pgbase, bytes);
- if (!pagevec)
- pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL);
- if (!pagevec)
- break;
-
- if (uio) {
- down_read(¤t->mm->mmap_sem);
- result = get_user_pages(current, current->mm, user_addr,
- npages, 0, 0, pagevec, NULL);
- up_read(¤t->mm->mmap_sem);
- if (result < 0)
- break;
- } else {
- WARN_ON(npages != 1);
- result = get_kernel_page(user_addr, 0, pagevec);
- if (WARN_ON(result != 1))
- break;
- }
-
- if ((unsigned)result < npages) {
- bytes = result * PAGE_SIZE;
- if (bytes <= pgbase) {
- nfs_direct_release_pages(pagevec, result);
- break;
- }
- bytes -= pgbase;
- npages = result;
- }
-
- for (i = 0; i < npages; i++) {
- struct nfs_page *req;
- unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
-
- req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
- pgbase, req_len);
- if (IS_ERR(req)) {
- result = PTR_ERR(req);
- break;
- }
- nfs_lock_request(req);
- req->wb_index = pos >> PAGE_SHIFT;
- req->wb_offset = pos & ~PAGE_MASK;
- if (!nfs_pageio_add_request(desc, req)) {
- result = desc->pg_error;
- nfs_unlock_and_release_request(req);
- break;
- }
- pgbase = 0;
- bytes -= req_len;
- started += req_len;
- user_addr += req_len;
- pos += req_len;
- count -= req_len;
- dreq->bytes_left -= req_len;
- }
- /* The nfs_page now hold references to these pages */
- nfs_direct_release_pages(pagevec, npages);
- } while (count != 0 && result >= 0);
-
- kfree(pagevec);
-
- if (started)
- return started;
- return result < 0 ? (ssize_t) result : -EFAULT;
- }
-
static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_direct_req *dreq = hdr->dreq;
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
bit = NFS_IOHDR_NEED_RESCHED;
else if (dreq->flags == 0) {
- memcpy(&dreq->verf, hdr->verf,
- sizeof(dreq->verf));
+ nfs_direct_set_hdr_verf(dreq, hdr);
bit = NFS_IOHDR_NEED_COMMIT;
dreq->flags = NFS_ODIRECT_DO_COMMIT;
} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
- if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) {
- dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+ if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) {
+ dreq->flags =
+ NFS_ODIRECT_RESCHED_WRITES;
bit = NFS_IOHDR_NEED_RESCHED;
} else
bit = NFS_IOHDR_NEED_COMMIT;
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
+ bool do_destroy = true;
+
req = nfs_list_entry(hdr->pages.next);
nfs_list_remove_request(req);
switch (bit) {
case NFS_IOHDR_NEED_COMMIT:
kref_get(&req->wb_kref);
nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+ do_destroy = false;
}
nfs_unlock_and_release_request(req);
}
.completion = nfs_direct_write_completion,
};
+
+ /*
+ * NB: Return the value of the first error return code. Subsequent
+ * errors after the first one are ignored.
+ */
+ /*
+ * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
+ * operation. If nfs_writedata_alloc() or get_user_pages() fails,
+ * bail and stop sending more writes. Write length accounting is
+ * handled automatically by nfs_direct_write_result(). Otherwise, if
+ * no requests have been sent, just return an error.
+ */
static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos, bool uio)
+ struct iov_iter *iter,
+ loff_t pos)
{
struct nfs_pageio_descriptor desc;
struct inode *inode = dreq->inode;
ssize_t result = 0;
size_t requested_bytes = 0;
- unsigned long seg;
+ size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
- NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
+ nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
get_dreq(dreq);
atomic_inc(&inode->i_dio_count);
- NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *vec = &iov[seg];
- result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
+ NFS_I(inode)->write_io += iov_iter_count(iter);
+ while (iov_iter_count(iter)) {
+ struct page **pagevec;
+ size_t bytes;
+ size_t pgbase;
+ unsigned npages, i;
+
+ result = iov_iter_get_pages_alloc(iter, &pagevec,
+ wsize, &pgbase);
if (result < 0)
break;
- requested_bytes += result;
- if ((size_t)result < vec->iov_len)
+
+ bytes = result;
+ iov_iter_advance(iter, bytes);
+ npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
+ for (i = 0; i < npages; i++) {
+ struct nfs_page *req;
+ unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
+
- req = nfs_create_request(dreq->ctx, inode,
- pagevec[i],
++ req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+ pgbase, req_len);
+ if (IS_ERR(req)) {
+ result = PTR_ERR(req);
+ break;
+ }
+ nfs_lock_request(req);
+ req->wb_index = pos >> PAGE_SHIFT;
+ req->wb_offset = pos & ~PAGE_MASK;
+ if (!nfs_pageio_add_request(&desc, req)) {
+ result = desc.pg_error;
+ nfs_unlock_and_release_request(req);
+ break;
+ }
+ pgbase = 0;
+ bytes -= req_len;
+ requested_bytes += req_len;
+ pos += req_len;
+ dreq->bytes_left -= req_len;
+ }
+ nfs_direct_release_pages(pagevec, npages);
+ kvfree(pagevec);
+ if (result < 0)
break;
- pos += vec->iov_len;
}
nfs_pageio_complete(&desc);
/**
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
- * @iov: vector of user buffers from which to write data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers from which to write data
* @pos: byte offset in file where writing starts
*
* We use this function for direct writes instead of calling
* 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 struct iovec *iov,
- unsigned long nr_segs, loff_t pos, bool uio)
+ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+ loff_t pos, bool uio)
{
ssize_t result = -EINVAL;
struct file *file = iocb->ki_filp;
struct nfs_direct_req *dreq;
struct nfs_lock_context *l_ctx;
loff_t end;
- size_t count;
-
- count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
if (!is_sync_kiocb(iocb))
dreq->iocb = iocb;
- result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+ result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
EXPORT_SYMBOL_GPL(nfs_file_flush);
ssize_t
- nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t result;
if (iocb->ki_filp->f_flags & O_DIRECT)
- return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
+ return nfs_file_direct_read(iocb, to, iocb->ki_pos, true);
- dprintk("NFS: read(%pD2, %lu@%lu)\n",
+ dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
- (unsigned long) iov_length(iov, nr_segs), (unsigned long) pos);
+ iov_iter_count(to), (unsigned long) iocb->ki_pos);
result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
if (!result) {
- result = generic_file_aio_read(iocb, iov, nr_segs, pos);
+ result = generic_file_read_iter(iocb, to);
if (result > 0)
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
}
return 0;
}
- ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
unsigned long written = 0;
ssize_t result;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(from);
+ loff_t pos = iocb->ki_pos;
result = nfs_key_timeout_notify(file, inode);
if (result)
return result;
if (file->f_flags & O_DIRECT)
- return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
+ return nfs_file_direct_write(iocb, from, pos, true);
- dprintk("NFS: write(%pD2, %lu@%Ld)\n",
- file, (unsigned long) count, (long long) pos);
+ dprintk("NFS: write(%pD2, %zu@%Ld)\n",
+ file, count, (long long) pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
if (!count)
goto out;
- result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ result = generic_file_write_iter(iocb, from);
if (result > 0)
written = result;
}
EXPORT_SYMBOL_GPL(nfs_file_write);
- ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
- struct file *filp, loff_t *ppos,
- size_t count, unsigned int flags)
- {
- struct inode *inode = file_inode(filp);
- unsigned long written = 0;
- ssize_t ret;
-
- dprintk("NFS splice_write(%pD2, %lu@%llu)\n",
- filp, (unsigned long) count, (unsigned long long) *ppos);
-
- /*
- * The combination of splice and an O_APPEND destination is disallowed.
- */
-
- ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
- if (ret > 0)
- written = ret;
-
- if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
- int err = vfs_fsync(filp, 0);
- if (err < 0)
- ret = err;
- }
- if (ret > 0)
- nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
- return ret;
- }
- EXPORT_SYMBOL_GPL(nfs_file_splice_write);
-
static int
do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
is_local = 1;
/* We're simulating flock() locks using posix locks on the server */
- fl->fl_owner = (fl_owner_t)filp;
- fl->fl_start = 0;
- fl->fl_end = OFFSET_MAX;
-
if (fl->fl_type == F_UNLCK)
return do_unlk(filp, cmd, fl, is_local);
return do_setlk(filp, cmd, fl, is_local);
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,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = nfs_file_read,
+ .write_iter = nfs_file_write,
.mmap = nfs_file_mmap,
.open = nfs_file_open,
.flush = nfs_file_flush,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
- .splice_write = nfs_file_splice_write,
+ .splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = nfs_setlease,
};
extern int __init nfs_init_directcache(void);
extern void nfs_destroy_directcache(void);
-extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount);
extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr,
void (*release)(struct nfs_pgio_header *hdr));
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
int nfs_iocounter_wait(struct nfs_io_counter *c);
+extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
+struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *);
+void nfs_rw_header_free(struct nfs_pgio_header *);
+void nfs_pgio_data_release(struct nfs_pgio_data *);
+int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
+int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *,
+ const struct rpc_call_ops *, int, int);
+
static inline void nfs_iocounter_init(struct nfs_io_counter *c)
{
c->flags = 0;
int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
loff_t nfs_file_llseek(struct file *, loff_t, int);
int nfs_file_flush(struct file *, fl_owner_t);
- ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
size_t, unsigned int);
int nfs_file_mmap(struct file *, struct vm_area_struct *);
- ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ ssize_t nfs_file_write(struct kiocb *, struct iov_iter *);
int nfs_file_release(struct inode *, struct file *);
int nfs_lock(struct file *, int, struct file_lock *);
int nfs_flock(struct file *, int, struct file_lock *);
- ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *,
- size_t, unsigned int);
int nfs_check_flags(int);
int nfs_setlease(struct file *, long, struct file_lock **);
struct nfs_pgio_completion_ops;
/* read.c */
-extern struct nfs_read_header *nfs_readhdr_alloc(void);
-extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
- struct inode *inode,
+ struct inode *inode, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops);
-extern int nfs_initiate_read(struct rpc_clnt *clnt,
- struct nfs_read_data *data,
- const struct rpc_call_ops *call_ops, int flags);
extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
-extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_readdata_release(struct nfs_read_data *rdata);
/* super.c */
void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
/* write.c */
extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
- struct inode *inode, int ioflags,
+ struct inode *inode, int ioflags, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops);
-extern struct nfs_write_header *nfs_writehdr_alloc(void);
-extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
-extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
- struct nfs_pgio_header *hdr);
extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_writedata_release(struct nfs_write_data *wdata);
extern void nfs_commit_free(struct nfs_commit_data *p);
-extern int nfs_initiate_write(struct rpc_clnt *clnt,
- struct nfs_write_data *data,
- const struct rpc_call_ops *call_ops,
- int how, int flags);
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct rpc_clnt *clnt,
struct nfs_commit_info *cinfo);
int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max);
+unsigned long nfs_reqs_to_commit(struct nfs_commit_info *);
int nfs_scan_commit(struct inode *inode, struct list_head *dst,
struct nfs_commit_info *cinfo);
void nfs_mark_request_commit(struct nfs_page *req,
extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
/* nfs4proc.c */
-extern void __nfs4_read_done_cb(struct nfs_read_data *);
+extern void __nfs4_read_done_cb(struct nfs_pgio_data *);
extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr);
break;
mutex_lock(&inode->i_mutex);
ret = nfs_file_fsync_commit(file, start, end, datasync);
- if (!ret && !datasync)
- /* application has asked for meta-data sync */
+ if (!ret)
ret = pnfs_layoutcommit_inode(inode, true);
mutex_unlock(&inode->i_mutex);
/*
const struct file_operations nfs4_file_operations = {
.llseek = nfs_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = nfs_file_read,
- .aio_write = nfs_file_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = nfs_file_read,
+ .write_iter = nfs_file_write,
.mmap = nfs_file_mmap,
.open = nfs4_file_open,
.flush = nfs_file_flush,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
- .splice_write = nfs_file_splice_write,
+ .splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = nfs_setlease,
};
}
do {
unlock_page(pages[--do_pages]);
- mark_page_accessed(pages[do_pages]);
page_cache_release(pages[do_pages]);
} while (do_pages);
if (unlikely(status))
size_t count; /* after file limit checks */
ssize_t written, err;
- count = 0;
- err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
- if (err)
- return err;
+ count = iov_length(iov, nr_segs);
pos = *ppos;
/* We can write back this queue in page reclaim. */
current->backing_dev_info = mapping->backing_dev_info;
const struct file_operations ntfs_file_ops = {
.llseek = generic_file_llseek, /* Seek inside file. */
- .read = do_sync_read, /* Read from file. */
- .aio_read = generic_file_aio_read, /* Async read from file. */
+ .read = new_sync_read, /* Read from file. */
+ .read_iter = generic_file_read_iter, /* Async read from file. */
#ifdef NTFS_RW
.write = do_sync_write, /* Write to file. */
.aio_write = ntfs_file_aio_write, /* Async write to file. */
/*
* fs-writeback will release the dirty pages without page lock
* whose offset are over inode size, the release happens at
- * block_write_full_page_endio().
+ * block_write_full_page().
*/
i_size_write(inode, abs_to);
inode->i_blocks = ocfs2_inode_sector_count(inode);
return ret;
}
- static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos)
+ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
{
int ret, direct_io, appending, rw_level, have_alloc_sem = 0;
int can_do_direct, has_refcount = 0;
ssize_t written = 0;
- size_t ocount; /* original count */
- size_t count; /* after file limit checks */
+ size_t count = iov_iter_count(from);
loff_t old_size, *ppos = &iocb->ki_pos;
u32 old_clusters;
struct file *file = iocb->ki_filp;
(unsigned long long)OCFS2_I(inode)->ip_blkno,
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name,
- (unsigned int)nr_segs);
+ (unsigned int)from->nr_segs); /* GRRRRR */
if (iocb->ki_nbytes == 0)
return 0;
/* communicate with ocfs2_dio_end_io */
ocfs2_iocb_set_rw_locked(iocb, rw_level);
- ret = generic_segment_checks(iov, &nr_segs, &ocount,
- VERIFY_READ);
- if (ret)
- goto out_dio;
-
- count = ocount;
ret = generic_write_checks(file, ppos, &count,
S_ISBLK(inode->i_mode));
if (ret)
goto out_dio;
+ iov_iter_truncate(from, count);
if (direct_io) {
- written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
- count, ocount);
+ written = generic_file_direct_write(iocb, from, *ppos);
if (written < 0) {
ret = written;
goto out_dio;
}
} else {
- struct iov_iter from;
- iov_iter_init(&from, iov, nr_segs, count, 0);
current->backing_dev_info = file->f_mapping->backing_dev_info;
- written = generic_perform_write(file, &from, *ppos);
+ written = generic_perform_write(file, from, *ppos);
if (likely(written >= 0))
iocb->ki_pos = *ppos + written;
current->backing_dev_info = NULL;
return ret;
}
- static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
- struct file *out,
- struct splice_desc *sd)
- {
- int ret;
-
- ret = ocfs2_prepare_inode_for_write(out, &sd->pos,
- sd->total_len, 0, NULL, NULL);
- if (ret < 0) {
- mlog_errno(ret);
- return ret;
- }
-
- return splice_from_pipe_feed(pipe, sd, pipe_to_file);
- }
-
- static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
- struct file *out,
- loff_t *ppos,
- size_t len,
- unsigned int flags)
- {
- int ret;
- struct address_space *mapping = out->f_mapping;
- struct inode *inode = mapping->host;
- struct splice_desc sd = {
- .total_len = len,
- .flags = flags,
- .pos = *ppos,
- .u.file = out,
- };
-
-
- trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry,
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- out->f_path.dentry->d_name.len,
- out->f_path.dentry->d_name.name, len);
-
- pipe_lock(pipe);
-
- splice_from_pipe_begin(&sd);
- do {
- ret = splice_from_pipe_next(pipe, &sd);
- if (ret <= 0)
- break;
-
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
- ret = ocfs2_rw_lock(inode, 1);
- if (ret < 0)
- mlog_errno(ret);
- else {
- ret = ocfs2_splice_to_file(pipe, out, &sd);
- ocfs2_rw_unlock(inode, 1);
- }
- mutex_unlock(&inode->i_mutex);
- } while (ret > 0);
- splice_from_pipe_end(pipe, &sd);
-
- pipe_unlock(pipe);
-
- if (sd.num_spliced)
- ret = sd.num_spliced;
-
- if (ret > 0) {
- int err;
-
- err = generic_write_sync(out, *ppos, ret);
- if (err)
- ret = err;
- else
- *ppos += ret;
-
- balance_dirty_pages_ratelimited(mapping);
- }
-
- return ret;
- }
-
static ssize_t ocfs2_file_splice_read(struct file *in,
loff_t *ppos,
struct pipe_inode_info *pipe,
in->f_path.dentry->d_name.name, len);
/*
- * See the comment in ocfs2_file_aio_read()
+ * See the comment in ocfs2_file_read_iter()
*/
ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
if (ret < 0) {
return ret;
}
- static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos)
+ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
+ struct iov_iter *to)
{
int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
struct file *filp = iocb->ki_filp;
trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
filp->f_path.dentry->d_name.len,
- filp->f_path.dentry->d_name.name, nr_segs);
+ filp->f_path.dentry->d_name.name,
+ to->nr_segs); /* GRRRRR */
if (!inode) {
}
ocfs2_inode_unlock(inode, lock_level);
- ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
+ ret = generic_file_read_iter(iocb, to);
trace_generic_file_aio_read_ret(ret);
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
- /* see ocfs2_file_aio_write */
+ /* see ocfs2_file_write_iter */
if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
rw_level = -1;
have_alloc_sem = 0;
*/
const struct file_operations ocfs2_fops = {
.llseek = ocfs2_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
.mmap = ocfs2_mmap,
.fsync = ocfs2_sync_file,
.release = ocfs2_file_release,
.open = ocfs2_file_open,
- .aio_read = ocfs2_file_aio_read,
- .aio_write = ocfs2_file_aio_write,
+ .read_iter = ocfs2_file_read_iter,
+ .write_iter = ocfs2_file_write_iter,
.unlocked_ioctl = ocfs2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ocfs2_compat_ioctl,
.lock = ocfs2_lock,
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
- .splice_write = ocfs2_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
*/
const struct file_operations ocfs2_fops_no_plocks = {
.llseek = ocfs2_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
.mmap = ocfs2_mmap,
.fsync = ocfs2_sync_file,
.release = ocfs2_file_release,
.open = ocfs2_file_open,
- .aio_read = ocfs2_file_aio_read,
- .aio_write = ocfs2_file_aio_write,
+ .read_iter = ocfs2_file_read_iter,
+ .write_iter = ocfs2_file_write_iter,
.unlocked_ioctl = ocfs2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ocfs2_compat_ioctl,
#endif
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
- .splice_write = ocfs2_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
#include <linux/quotaops.h>
/*
-** We pack the tails of files on file close, not at the time they are written.
-** This implies an unnecessary copy of the tail and an unnecessary indirect item
-** insertion/balancing, for files that are written in one write.
-** It avoids unnecessary tail packings (balances) for files that are written in
-** multiple writes and are small enough to have tails.
-**
-** file_release is called by the VFS layer when the file is closed. If
-** this is the last open file descriptor, and the file
-** small enough to have a tail, and the tail is currently in an
-** unformatted node, the tail is converted back into a direct item.
-**
-** We use reiserfs_truncate_file to pack the tail, since it already has
-** all the conditions coded.
-*/
+ * We pack the tails of files on file close, not at the time they are written.
+ * This implies an unnecessary copy of the tail and an unnecessary indirect item
+ * insertion/balancing, for files that are written in one write.
+ * It avoids unnecessary tail packings (balances) for files that are written in
+ * multiple writes and are small enough to have tails.
+ *
+ * file_release is called by the VFS layer when the file is closed. If
+ * this is the last open file descriptor, and the file
+ * small enough to have a tail, and the tail is currently in an
+ * unformatted node, the tail is converted back into a direct item.
+ *
+ * We use reiserfs_truncate_file to pack the tail, since it already has
+ * all the conditions coded.
+ */
static int reiserfs_file_release(struct inode *inode, struct file *filp)
{
if (atomic_add_unless(&REISERFS_I(inode)->openers, -1, 1))
return 0;
- mutex_lock(&(REISERFS_I(inode)->tailpack));
+ mutex_lock(&REISERFS_I(inode)->tailpack);
if (!atomic_dec_and_test(&REISERFS_I(inode)->openers)) {
- mutex_unlock(&(REISERFS_I(inode)->tailpack));
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
return 0;
}
if ((!(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) ||
!tail_has_to_be_packed(inode)) &&
REISERFS_I(inode)->i_prealloc_count <= 0) {
- mutex_unlock(&(REISERFS_I(inode)->tailpack));
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
return 0;
}
reiserfs_write_lock(inode->i_sb);
- /* freeing preallocation only involves relogging blocks that
+ /*
+ * freeing preallocation only involves relogging blocks that
* are already in the current transaction. preallocation gets
* freed at the end of each transaction, so it is impossible for
* us to log any additional blocks (including quota blocks)
*/
err = journal_begin(&th, inode->i_sb, 1);
if (err) {
- /* uh oh, we can't allow the inode to go away while there
+ /*
+ * uh oh, we can't allow the inode to go away while there
* is still preallocation blocks pending. Try to join the
* aborted transaction
*/
jbegin_failure = err;
- err = journal_join_abort(&th, inode->i_sb, 1);
+ err = journal_join_abort(&th, inode->i_sb);
if (err) {
- /* hmpf, our choices here aren't good. We can pin the inode
- * which will disallow unmount from every happening, we can
- * do nothing, which will corrupt random memory on unmount,
- * or we can forcibly remove the file from the preallocation
- * list, which will leak blocks on disk. Lets pin the inode
+ /*
+ * hmpf, our choices here aren't good. We can pin
+ * the inode which will disallow unmount from ever
+ * happening, we can do nothing, which will corrupt
+ * random memory on unmount, or we can forcibly
+ * remove the file from the preallocation list, which
+ * will leak blocks on disk. Lets pin the inode
* and let the admin know what is going on.
*/
igrab(inode);
#ifdef REISERFS_PREALLOCATE
reiserfs_discard_prealloc(&th, inode);
#endif
- err = journal_end(&th, inode->i_sb, 1);
+ err = journal_end(&th);
/* copy back the error code from journal_begin */
if (!err)
(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) &&
tail_has_to_be_packed(inode)) {
- /* if regular file is released by last holder and it has been
- appended (we append by unformatted node only) or its direct
- item(s) had to be converted, then it may have to be
- indirect2direct converted */
+ /*
+ * if regular file is released by last holder and it has been
+ * appended (we append by unformatted node only) or its direct
+ * item(s) had to be converted, then it may have to be
+ * indirect2direct converted
+ */
err = reiserfs_truncate_file(inode, 0);
}
- out:
+out:
reiserfs_write_unlock(inode->i_sb);
- mutex_unlock(&(REISERFS_I(inode)->tailpack));
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
return err;
}
static int reiserfs_file_open(struct inode *inode, struct file *file)
{
int err = dquot_file_open(inode, file);
+
+ /* somebody might be tailpacking on final close; wait for it */
if (!atomic_inc_not_zero(&REISERFS_I(inode)->openers)) {
- /* somebody might be tailpacking on final close; wait for it */
- mutex_lock(&(REISERFS_I(inode)->tailpack));
+ mutex_lock(&REISERFS_I(inode)->tailpack);
atomic_inc(&REISERFS_I(inode)->openers);
- mutex_unlock(&(REISERFS_I(inode)->tailpack));
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
}
return err;
}
void reiserfs_vfs_truncate_file(struct inode *inode)
{
- mutex_lock(&(REISERFS_I(inode)->tailpack));
+ mutex_lock(&REISERFS_I(inode)->tailpack);
reiserfs_truncate_file(inode, 1);
- mutex_unlock(&(REISERFS_I(inode)->tailpack));
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
}
/* Sync a reiserfs file. */
set_buffer_uptodate(bh);
if (logit) {
reiserfs_prepare_for_journal(s, bh, 1);
- journal_mark_dirty(&th, s, bh);
+ journal_mark_dirty(&th, bh);
} else if (!buffer_dirty(bh)) {
mark_buffer_dirty(bh);
- /* do data=ordered on any page past the end
+ /*
+ * do data=ordered on any page past the end
* of file and any buffer marked BH_New.
*/
if (reiserfs_data_ordered(inode->i_sb) &&
}
}
if (logit) {
- ret = journal_end(&th, s, bh_per_page + 1);
- drop_write_lock:
+ ret = journal_end(&th);
+drop_write_lock:
reiserfs_write_unlock(s);
}
/*
}
const struct file_operations reiserfs_file_operations = {
- .read = do_sync_read,
- .write = do_sync_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
.unlocked_ioctl = reiserfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = reiserfs_compat_ioctl,
.open = reiserfs_file_open,
.release = reiserfs_file_release,
.fsync = reiserfs_sync_file,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.llseek = generic_file_llseek,
};
void reiserfs_evict_inode(struct inode *inode)
{
- /* We need blocks for transaction + (user+group) quota update (possibly delete) */
+ /*
+ * We need blocks for transaction + (user+group) quota
+ * update (possibly delete)
+ */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 2 +
2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
if (inode->i_nlink)
goto no_delete;
- /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */
- if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */
+ /*
+ * The = 0 happens when we abort creating a new inode
+ * for some reason like lack of space..
+ * also handles bad_inode case
+ */
+ if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {
reiserfs_delete_xattrs(inode);
err = reiserfs_delete_object(&th, inode);
- /* Do quota update inside a transaction for journaled quotas. We must do that
- * after delete_object so that quota updates go into the same transaction as
- * stat data deletion */
+ /*
+ * Do quota update inside a transaction for journaled quotas.
+ * We must do that after delete_object so that quota updates
+ * go into the same transaction as stat data deletion
+ */
if (!err) {
int depth = reiserfs_write_unlock_nested(inode->i_sb);
dquot_free_inode(inode);
reiserfs_write_lock_nested(inode->i_sb, depth);
}
- if (journal_end(&th, inode->i_sb, jbegin_count))
+ if (journal_end(&th))
goto out;
- /* check return value from reiserfs_delete_object after
+ /*
+ * check return value from reiserfs_delete_object after
* ending the transaction
*/
if (err)
goto out;
- /* all items of file are deleted, so we can remove "save" link */
- remove_save_link(inode, 0 /* not truncate */ ); /* we can't do anything
- * about an error here */
+ /*
+ * all items of file are deleted, so we can remove
+ * "save" link
+ * we can't do anything about an error here
+ */
+ remove_save_link(inode, 0 /* not truncate */);
out:
reiserfs_write_unlock(inode->i_sb);
} else {
/* no object items are in the tree */
;
}
- clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */
+
+ /* note this must go after the journal_end to prevent deadlock */
+ clear_inode(inode);
+
dquot_drop(inode);
inode->i_blocks = 0;
return;
key->key_length = length;
}
-/* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set
- offset and type of key */
+/*
+ * take base of inode_key (it comes from inode always) (dirid, objectid)
+ * and version from an inode, set offset and type of key
+ */
void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
int type, int length)
{
length);
}
-//
-// when key is 0, do not set version and short key
-//
+/* when key is 0, do not set version and short key */
inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
int version,
loff_t offset, int type, int length,
set_le_ih_k_type(ih, type);
put_ih_item_len(ih, length);
/* set_ih_free_space (ih, 0); */
- // for directory items it is entry count, for directs and stat
- // datas - 0xffff, for indirects - 0
+ /*
+ * for directory items it is entry count, for directs and stat
+ * datas - 0xffff, for indirects - 0
+ */
put_ih_entry_count(ih, entry_count);
}
-//
-// FIXME: we might cache recently accessed indirect item
-
-// Ugh. Not too eager for that....
-// I cut the code until such time as I see a convincing argument (benchmark).
-// I don't want a bloated inode struct..., and I don't like code complexity....
-
-/* cutting the code is fine, since it really isn't in use yet and is easy
-** to add back in. But, Vladimir has a really good idea here. Think
-** about what happens for reading a file. For each page,
-** The VFS layer calls reiserfs_readpage, who searches the tree to find
-** an indirect item. This indirect item has X number of pointers, where
-** X is a big number if we've done the block allocation right. But,
-** we only use one or two of these pointers during each call to readpage,
-** needlessly researching again later on.
-**
-** The size of the cache could be dynamic based on the size of the file.
-**
-** I'd also like to see us cache the location the stat data item, since
-** we are needlessly researching for that frequently.
-**
-** --chris
-*/
+/*
+ * FIXME: we might cache recently accessed indirect item
+ * Ugh. Not too eager for that....
+ * I cut the code until such time as I see a convincing argument (benchmark).
+ * I don't want a bloated inode struct..., and I don't like code complexity....
+ */
-/* If this page has a file tail in it, and
-** it was read in by get_block_create_0, the page data is valid,
-** but tail is still sitting in a direct item, and we can't write to
-** it. So, look through this page, and check all the mapped buffers
-** to make sure they have valid block numbers. Any that don't need
-** to be unmapped, so that __block_write_begin will correctly call
-** reiserfs_get_block to convert the tail into an unformatted node
-*/
+/*
+ * cutting the code is fine, since it really isn't in use yet and is easy
+ * to add back in. But, Vladimir has a really good idea here. Think
+ * about what happens for reading a file. For each page,
+ * The VFS layer calls reiserfs_readpage, who searches the tree to find
+ * an indirect item. This indirect item has X number of pointers, where
+ * X is a big number if we've done the block allocation right. But,
+ * we only use one or two of these pointers during each call to readpage,
+ * needlessly researching again later on.
+ *
+ * The size of the cache could be dynamic based on the size of the file.
+ *
+ * I'd also like to see us cache the location the stat data item, since
+ * we are needlessly researching for that frequently.
+ *
+ * --chris
+ */
+
+/*
+ * If this page has a file tail in it, and
+ * it was read in by get_block_create_0, the page data is valid,
+ * but tail is still sitting in a direct item, and we can't write to
+ * it. So, look through this page, and check all the mapped buffers
+ * to make sure they have valid block numbers. Any that don't need
+ * to be unmapped, so that __block_write_begin will correctly call
+ * reiserfs_get_block to convert the tail into an unformatted node
+ */
static inline void fix_tail_page_for_writing(struct page *page)
{
struct buffer_head *head, *next, *bh;
}
}
-/* reiserfs_get_block does not need to allocate a block only if it has been
- done already or non-hole position has been found in the indirect item */
+/*
+ * reiserfs_get_block does not need to allocate a block only if it has been
+ * done already or non-hole position has been found in the indirect item
+ */
static inline int allocation_needed(int retval, b_blocknr_t allocated,
struct item_head *ih,
__le32 * item, int pos_in_item)
map_bh(bh, inode->i_sb, block);
}
-//
-// files which were created in the earlier version can not be longer,
-// than 2 gb
-//
+/*
+ * files which were created in the earlier version can not be longer,
+ * than 2 gb
+ */
static int file_capable(struct inode *inode, sector_t block)
{
- if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 || // it is new file.
- block < (1 << (31 - inode->i_sb->s_blocksize_bits))) // old file, but 'block' is inside of 2gb
+ /* it is new file. */
+ if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 ||
+ /* old file, but 'block' is inside of 2gb */
+ block < (1 << (31 - inode->i_sb->s_blocksize_bits)))
return 1;
return 0;
struct inode *inode, struct treepath *path)
{
struct super_block *s = th->t_super;
- int len = th->t_blocks_allocated;
int err;
BUG_ON(!th->t_trans_id);
return 0;
}
reiserfs_update_sd(th, inode);
- err = journal_end(th, s, len);
+ err = journal_end(th);
if (!err) {
err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6);
if (!err)
return err;
}
-// it is called by get_block when create == 0. Returns block number
-// for 'block'-th logical block of file. When it hits direct item it
-// returns 0 (being called from bmap) or read direct item into piece
-// of page (bh_result)
-
-// Please improve the english/clarity in the comment above, as it is
-// hard to understand.
-
+/*
+ * it is called by get_block when create == 0. Returns block number
+ * for 'block'-th logical block of file. When it hits direct item it
+ * returns 0 (being called from bmap) or read direct item into piece
+ * of page (bh_result)
+ * Please improve the english/clarity in the comment above, as it is
+ * hard to understand.
+ */
static int _get_block_create_0(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int args)
{
int done = 0;
unsigned long offset;
- // prepare the key to look for the 'block'-th block of file
+ /* prepare the key to look for the 'block'-th block of file */
make_cpu_key(&key, inode,
(loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
3);
kunmap(bh_result->b_page);
if (result == IO_ERROR)
return -EIO;
- // We do not return -ENOENT if there is a hole but page is uptodate, because it means
- // That there is some MMAPED data associated with it that is yet to be written to disk.
+ /*
+ * We do not return -ENOENT if there is a hole but page is
+ * uptodate, because it means that there is some MMAPED data
+ * associated with it that is yet to be written to disk.
+ */
if ((args & GET_BLOCK_NO_HOLE)
&& !PageUptodate(bh_result->b_page)) {
return -ENOENT;
}
return 0;
}
- //
+
bh = get_last_bh(&path);
- ih = get_ih(&path);
+ ih = tp_item_head(&path);
if (is_indirect_le_ih(ih)) {
- __le32 *ind_item = (__le32 *) B_I_PITEM(bh, ih);
+ __le32 *ind_item = (__le32 *) ih_item_body(bh, ih);
- /* FIXME: here we could cache indirect item or part of it in
- the inode to avoid search_by_key in case of subsequent
- access to file */
+ /*
+ * FIXME: here we could cache indirect item or part of it in
+ * the inode to avoid search_by_key in case of subsequent
+ * access to file
+ */
blocknr = get_block_num(ind_item, path.pos_in_item);
ret = 0;
if (blocknr) {
set_buffer_boundary(bh_result);
}
} else
- // We do not return -ENOENT if there is a hole but page is uptodate, because it means
- // That there is some MMAPED data associated with it that is yet to be written to disk.
+ /*
+ * We do not return -ENOENT if there is a hole but
+ * page is uptodate, because it means that there is
+ * some MMAPED data associated with it that is
+ * yet to be written to disk.
+ */
if ((args & GET_BLOCK_NO_HOLE)
&& !PageUptodate(bh_result->b_page)) {
ret = -ENOENT;
kunmap(bh_result->b_page);
return ret;
}
- // requested data are in direct item(s)
+ /* requested data are in direct item(s) */
if (!(args & GET_BLOCK_READ_DIRECT)) {
- // we are called by bmap. FIXME: we can not map block of file
- // when it is stored in direct item(s)
+ /*
+ * we are called by bmap. FIXME: we can not map block of file
+ * when it is stored in direct item(s)
+ */
pathrelse(&path);
if (p)
kunmap(bh_result->b_page);
return -ENOENT;
}
- /* if we've got a direct item, and the buffer or page was uptodate,
- ** we don't want to pull data off disk again. skip to the
- ** end, where we map the buffer and return
+ /*
+ * if we've got a direct item, and the buffer or page was uptodate,
+ * we don't want to pull data off disk again. skip to the
+ * end, where we map the buffer and return
*/
if (buffer_uptodate(bh_result)) {
goto finished;
} else
/*
- ** grab_tail_page can trigger calls to reiserfs_get_block on up to date
- ** pages without any buffers. If the page is up to date, we don't want
- ** read old data off disk. Set the up to date bit on the buffer instead
- ** and jump to the end
+ * grab_tail_page can trigger calls to reiserfs_get_block on
+ * up to date pages without any buffers. If the page is up
+ * to date, we don't want read old data off disk. Set the up
+ * to date bit on the buffer instead and jump to the end
*/
if (!bh_result->b_page || PageUptodate(bh_result->b_page)) {
set_buffer_uptodate(bh_result);
goto finished;
}
- // read file tail into part of page
+ /* read file tail into part of page */
offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
copy_item_head(&tmp_ih, ih);
- /* we only want to kmap if we are reading the tail into the page.
- ** this is not the common case, so we don't kmap until we are
- ** sure we need to. But, this means the item might move if
- ** kmap schedules
+ /*
+ * we only want to kmap if we are reading the tail into the page.
+ * this is not the common case, so we don't kmap until we are
+ * sure we need to. But, this means the item might move if
+ * kmap schedules
*/
if (!p)
p = (char *)kmap(bh_result->b_page);
if (!is_direct_le_ih(ih)) {
BUG();
}
- /* make sure we don't read more bytes than actually exist in
- ** the file. This can happen in odd cases where i_size isn't
- ** correct, and when direct item padding results in a few
- ** extra bytes at the end of the direct item
+ /*
+ * make sure we don't read more bytes than actually exist in
+ * the file. This can happen in odd cases where i_size isn't
+ * correct, and when direct item padding results in a few
+ * extra bytes at the end of the direct item
*/
if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size)
break;
} else {
chars = ih_item_len(ih) - path.pos_in_item;
}
- memcpy(p, B_I_PITEM(bh, ih) + path.pos_in_item, chars);
+ memcpy(p, ih_item_body(bh, ih) + path.pos_in_item, chars);
if (done)
break;
p += chars;
+ /*
+ * we done, if read direct item is not the last item of
+ * node FIXME: we could try to check right delimiting key
+ * to see whether direct item continues in the right
+ * neighbor or rely on i_size
+ */
if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1))
- // we done, if read direct item is not the last item of
- // node FIXME: we could try to check right delimiting key
- // to see whether direct item continues in the right
- // neighbor or rely on i_size
break;
- // update key to look for the next piece
+ /* update key to look for the next piece */
set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars);
result = search_for_position_by_key(inode->i_sb, &key, &path);
if (result != POSITION_FOUND)
- // i/o error most likely
+ /* i/o error most likely */
break;
bh = get_last_bh(&path);
- ih = get_ih(&path);
+ ih = tp_item_head(&path);
} while (1);
flush_dcache_page(bh_result->b_page);
kunmap(bh_result->b_page);
- finished:
+finished:
pathrelse(&path);
if (result == IO_ERROR)
return -EIO;
- /* this buffer has valid data, but isn't valid for io. mapping it to
+ /*
+ * this buffer has valid data, but isn't valid for io. mapping it to
* block #0 tells the rest of reiserfs it just has a tail in it
*/
map_bh(bh_result, inode->i_sb, 0);
return 0;
}
-// this is called to create file map. So, _get_block_create_0 will not
-// read direct item
+/*
+ * this is called to create file map. So, _get_block_create_0 will not
+ * read direct item
+ */
static int reiserfs_bmap(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int create)
{
return 0;
}
-/* special version of get_block that is only used by grab_tail_page right
-** now. It is sent to __block_write_begin, and when you try to get a
-** block past the end of the file (or a block from a hole) it returns
-** -ENOENT instead of a valid buffer. __block_write_begin expects to
-** be able to do i/o on the buffers returned, unless an error value
-** is also returned.
-**
-** So, this allows __block_write_begin to be used for reading a single block
-** in a page. Where it does not produce a valid page for holes, or past the
-** end of the file. This turns out to be exactly what we need for reading
-** tails for conversion.
-**
-** The point of the wrapper is forcing a certain value for create, even
-** though the VFS layer is calling this function with create==1. If you
-** don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
-** don't use this function.
+/*
+ * special version of get_block that is only used by grab_tail_page right
+ * now. It is sent to __block_write_begin, and when you try to get a
+ * block past the end of the file (or a block from a hole) it returns
+ * -ENOENT instead of a valid buffer. __block_write_begin expects to
+ * be able to do i/o on the buffers returned, unless an error value
+ * is also returned.
+ *
+ * So, this allows __block_write_begin to be used for reading a single block
+ * in a page. Where it does not produce a valid page for holes, or past the
+ * end of the file. This turns out to be exactly what we need for reading
+ * tails for conversion.
+ *
+ * The point of the wrapper is forcing a certain value for create, even
+ * though the VFS layer is calling this function with create==1. If you
+ * don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
+ * don't use this function.
*/
static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
struct buffer_head *bh_result,
return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE);
}
-/* This is special helper for reiserfs_get_block in case we are executing
- direct_IO request. */
+/*
+ * This is special helper for reiserfs_get_block in case we are executing
+ * direct_IO request.
+ */
static int reiserfs_get_blocks_direct_io(struct inode *inode,
sector_t iblock,
struct buffer_head *bh_result,
bh_result->b_page = NULL;
- /* We set the b_size before reiserfs_get_block call since it is
- referenced in convert_tail_for_hole() that may be called from
- reiserfs_get_block() */
+ /*
+ * We set the b_size before reiserfs_get_block call since it is
+ * referenced in convert_tail_for_hole() that may be called from
+ * reiserfs_get_block()
+ */
bh_result->b_size = (1 << inode->i_blkbits);
ret = reiserfs_get_block(inode, iblock, bh_result,
/* don't allow direct io onto tail pages */
if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
- /* make sure future calls to the direct io funcs for this offset
- ** in the file fail by unmapping the buffer
+ /*
+ * make sure future calls to the direct io funcs for this
+ * offset in the file fail by unmapping the buffer
*/
clear_buffer_mapped(bh_result);
ret = -EINVAL;
}
- /* Possible unpacked tail. Flush the data before pages have
- disappeared */
+
+ /*
+ * Possible unpacked tail. Flush the data before pages have
+ * disappeared
+ */
if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
int err;
if (err < 0)
ret = err;
}
- out:
+out:
return ret;
}
/*
-** helper function for when reiserfs_get_block is called for a hole
-** but the file tail is still in a direct item
-** bh_result is the buffer head for the hole
-** tail_offset is the offset of the start of the tail in the file
-**
-** This calls prepare_write, which will start a new transaction
-** you should not be in a transaction, or have any paths held when you
-** call this.
-*/
+ * helper function for when reiserfs_get_block is called for a hole
+ * but the file tail is still in a direct item
+ * bh_result is the buffer head for the hole
+ * tail_offset is the offset of the start of the tail in the file
+ *
+ * This calls prepare_write, which will start a new transaction
+ * you should not be in a transaction, or have any paths held when you
+ * call this.
+ */
static int convert_tail_for_hole(struct inode *inode,
struct buffer_head *bh_result,
loff_t tail_offset)
tail_end = (tail_start | (bh_result->b_size - 1)) + 1;
index = tail_offset >> PAGE_CACHE_SHIFT;
- /* hole_page can be zero in case of direct_io, we are sure
- that we cannot get here if we write with O_DIRECT into
- tail page */
+ /*
+ * hole_page can be zero in case of direct_io, we are sure
+ * that we cannot get here if we write with O_DIRECT into tail page
+ */
if (!hole_page || index != hole_page->index) {
tail_page = grab_cache_page(inode->i_mapping, index);
retval = -ENOMEM;
tail_page = hole_page;
}
- /* we don't have to make sure the conversion did not happen while
- ** we were locking the page because anyone that could convert
- ** must first take i_mutex.
- **
- ** We must fix the tail page for writing because it might have buffers
- ** that are mapped, but have a block number of 0. This indicates tail
- ** data that has been read directly into the page, and
- ** __block_write_begin won't trigger a get_block in this case.
+ /*
+ * we don't have to make sure the conversion did not happen while
+ * we were locking the page because anyone that could convert
+ * must first take i_mutex.
+ *
+ * We must fix the tail page for writing because it might have buffers
+ * that are mapped, but have a block number of 0. This indicates tail
+ * data that has been read directly into the page, and
+ * __block_write_begin won't trigger a get_block in this case.
*/
fix_tail_page_for_writing(tail_page);
retval = __reiserfs_write_begin(tail_page, tail_start,
retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end);
- unlock:
+unlock:
if (tail_page != hole_page) {
unlock_page(tail_page);
page_cache_release(tail_page);
}
- out:
+out:
return retval;
}
struct buffer_head *bh_result, int create)
{
int repeat, retval = 0;
- b_blocknr_t allocated_block_nr = 0; // b_blocknr_t is (unsigned) 32 bit int
+ /* b_blocknr_t is (unsigned) 32 bit int*/
+ b_blocknr_t allocated_block_nr = 0;
INITIALIZE_PATH(path);
int pos_in_item;
struct cpu_key key;
int done;
int fs_gen;
struct reiserfs_transaction_handle *th = NULL;
- /* space reserved in transaction batch:
- . 3 balancings in direct->indirect conversion
- . 1 block involved into reiserfs_update_sd()
- XXX in practically impossible worst case direct2indirect()
- can incur (much) more than 3 balancings.
- quota update for user, group */
+ /*
+ * space reserved in transaction batch:
+ * . 3 balancings in direct->indirect conversion
+ * . 1 block involved into reiserfs_update_sd()
+ * XXX in practically impossible worst case direct2indirect()
+ * can incur (much) more than 3 balancings.
+ * quota update for user, group
+ */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 + 1 +
2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
return -EFBIG;
}
- /* if !create, we aren't changing the FS, so we don't need to
- ** log anything, so we don't need to start a transaction
+ /*
+ * if !create, we aren't changing the FS, so we don't need to
+ * log anything, so we don't need to start a transaction
*/
if (!(create & GET_BLOCK_CREATE)) {
int ret;
reiserfs_write_unlock(inode->i_sb);
return ret;
}
+
/*
* if we're already in a transaction, make sure to close
* any new transactions we start in this func
reiserfs_transaction_running(inode->i_sb))
dangle = 0;
- /* If file is of such a size, that it might have a tail and tails are enabled
- ** we should mark it as possibly needing tail packing on close
+ /*
+ * If file is of such a size, that it might have a tail and
+ * tails are enabled we should mark it as possibly needing
+ * tail packing on close
*/
if ((have_large_tails(inode->i_sb)
&& inode->i_size < i_block_size(inode) * 4)
/* set the key of the first byte in the 'block'-th block of file */
make_cpu_key(&key, inode, new_offset, TYPE_ANY, 3 /*key length */ );
if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) {
- start_trans:
+start_trans:
th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count);
if (!th) {
retval = -ENOMEM;
}
reiserfs_update_inode_transaction(inode);
}
- research:
+research:
retval = search_for_position_by_key(inode->i_sb, &key, &path);
if (retval == IO_ERROR) {
}
bh = get_last_bh(&path);
- ih = get_ih(&path);
- item = get_item(&path);
+ ih = tp_item_head(&path);
+ item = tp_item_body(&path);
pos_in_item = path.pos_in_item;
fs_gen = get_generation(inode->i_sb);
_allocate_block(th, block, inode, &allocated_block_nr,
&path, create);
+ /*
+ * restart the transaction to give the journal a chance to free
+ * some blocks. releases the path, so we have to go back to
+ * research if we succeed on the second try
+ */
if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {
- /* restart the transaction to give the journal a chance to free
- ** some blocks. releases the path, so we have to go back to
- ** research if we succeed on the second try
- */
SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
retval = restart_transaction(th, inode, &path);
if (retval)
if (indirect_item_found(retval, ih)) {
b_blocknr_t unfm_ptr;
- /* 'block'-th block is in the file already (there is
- corresponding cell in some indirect item). But it may be
- zero unformatted node pointer (hole) */
+ /*
+ * 'block'-th block is in the file already (there is
+ * corresponding cell in some indirect item). But it may be
+ * zero unformatted node pointer (hole)
+ */
unfm_ptr = get_block_num(item, pos_in_item);
if (unfm_ptr == 0) {
/* use allocated block to plug the hole */
reiserfs_add_ordered_list(inode, bh_result);
put_block_num(item, pos_in_item, allocated_block_nr);
unfm_ptr = allocated_block_nr;
- journal_mark_dirty(th, inode->i_sb, bh);
+ journal_mark_dirty(th, bh);
reiserfs_update_sd(th, inode);
}
set_block_dev_mapped(bh_result, unfm_ptr, inode);
reiserfs_write_unlock(inode->i_sb);
- /* the item was found, so new blocks were not added to the file
- ** there is no need to make sure the inode is updated with this
- ** transaction
+ /*
+ * the item was found, so new blocks were not added to the file
+ * there is no need to make sure the inode is updated with this
+ * transaction
*/
return retval;
}
goto start_trans;
}
- /* desired position is not found or is in the direct item. We have
- to append file with holes up to 'block'-th block converting
- direct items to indirect one if necessary */
+ /*
+ * desired position is not found or is in the direct item. We have
+ * to append file with holes up to 'block'-th block converting
+ * direct items to indirect one if necessary
+ */
done = 0;
do {
if (is_statdata_le_ih(ih)) {
TYPE_INDIRECT, UNFM_P_SIZE,
0 /* free_space */ );
+ /*
+ * we are going to add 'block'-th block to the file.
+ * Use allocated block for that
+ */
if (cpu_key_k_offset(&key) == 1) {
- /* we are going to add 'block'-th block to the file. Use
- allocated block for that */
unp = cpu_to_le32(allocated_block_nr);
set_block_dev_mapped(bh_result,
allocated_block_nr, inode);
set_buffer_new(bh_result);
done = 1;
}
- tmp_key = key; // ;)
+ tmp_key = key; /* ;) */
set_cpu_key_k_offset(&tmp_key, 1);
PATH_LAST_POSITION(&path)++;
if (retval) {
reiserfs_free_block(th, inode,
allocated_block_nr, 1);
- goto failure; // retval == -ENOSPC, -EDQUOT or -EIO or -EEXIST
+ /*
+ * retval == -ENOSPC, -EDQUOT or -EIO
+ * or -EEXIST
+ */
+ goto failure;
}
- //mark_tail_converted (inode);
} else if (is_direct_le_ih(ih)) {
/* direct item has to be converted */
loff_t tail_offset;
tail_offset =
((le_ih_k_offset(ih) -
1) & ~(inode->i_sb->s_blocksize - 1)) + 1;
+
+ /*
+ * direct item we just found fits into block we have
+ * to map. Convert it into unformatted node: use
+ * bh_result for the conversion
+ */
if (tail_offset == cpu_key_k_offset(&key)) {
- /* direct item we just found fits into block we have
- to map. Convert it into unformatted node: use
- bh_result for the conversion */
set_block_dev_mapped(bh_result,
allocated_block_nr, inode);
unbh = bh_result;
done = 1;
} else {
- /* we have to padd file tail stored in direct item(s)
- up to block size and convert it to unformatted
- node. FIXME: this should also get into page cache */
+ /*
+ * we have to pad file tail stored in direct
+ * item(s) up to block size and convert it
+ * to unformatted node. FIXME: this should
+ * also get into page cache
+ */
pathrelse(&path);
/*
inode->i_ino,
retval);
if (allocated_block_nr) {
- /* the bitmap, the super, and the stat data == 3 */
+ /*
+ * the bitmap, the super,
+ * and the stat data == 3
+ */
if (!th)
th = reiserfs_persistent_transaction(inode->i_sb, 3);
if (th)
allocated_block_nr, 1);
goto failure;
}
- /* it is important the set_buffer_uptodate is done after
- ** the direct2indirect. The buffer might contain valid
- ** data newer than the data on disk (read by readpage, changed,
- ** and then sent here by writepage). direct2indirect needs
- ** to know if unbh was already up to date, so it can decide
- ** if the data in unbh needs to be replaced with data from
- ** the disk
+ /*
+ * it is important the set_buffer_uptodate is done
+ * after the direct2indirect. The buffer might
+ * contain valid data newer than the data on disk
+ * (read by readpage, changed, and then sent here by
+ * writepage). direct2indirect needs to know if unbh
+ * was already up to date, so it can decide if the
+ * data in unbh needs to be replaced with data from
+ * the disk
*/
set_buffer_uptodate(unbh);
- /* unbh->b_page == NULL in case of DIRECT_IO request, this means
- buffer will disappear shortly, so it should not be added to
+ /*
+ * unbh->b_page == NULL in case of DIRECT_IO request,
+ * this means buffer will disappear shortly, so it
+ * should not be added to
*/
if (unbh->b_page) {
- /* we've converted the tail, so we must
- ** flush unbh before the transaction commits
+ /*
+ * we've converted the tail, so we must
+ * flush unbh before the transaction commits
*/
reiserfs_add_tail_list(inode, unbh);
- /* mark it dirty now to prevent commit_write from adding
- ** this buffer to the inode's dirty buffer list
+ /*
+ * mark it dirty now to prevent commit_write
+ * from adding this buffer to the inode's
+ * dirty buffer list
*/
/*
- * AKPM: changed __mark_buffer_dirty to mark_buffer_dirty().
- * It's still atomic, but it sets the page dirty too,
- * which makes it eligible for writeback at any time by the
- * VM (which was also the case with __mark_buffer_dirty())
+ * AKPM: changed __mark_buffer_dirty to
+ * mark_buffer_dirty(). It's still atomic,
+ * but it sets the page dirty too, which makes
+ * it eligible for writeback at any time by the
+ * VM (which was also the case with
+ * __mark_buffer_dirty())
*/
mark_buffer_dirty(unbh);
}
} else {
- /* append indirect item with holes if needed, when appending
- pointer to 'block'-th block use block, which is already
- allocated */
+ /*
+ * append indirect item with holes if needed, when
+ * appending pointer to 'block'-th block use block,
+ * which is already allocated
+ */
struct cpu_key tmp_key;
- unp_t unf_single = 0; // We use this in case we need to allocate only
- // one block which is a fastpath
+ /*
+ * We use this in case we need to allocate
+ * only one block which is a fastpath
+ */
+ unp_t unf_single = 0;
unp_t *un;
__u64 max_to_insert =
MAX_ITEM_LEN(inode->i_sb->s_blocksize) /
RFALSE(pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
"vs-804: invalid position for append");
- /* indirect item has to be appended, set up key of that position */
+ /*
+ * indirect item has to be appended,
+ * set up key of that position
+ * (key type is unimportant)
+ */
make_cpu_key(&tmp_key, inode,
le_key_k_offset(version,
- &(ih->ih_key)) +
+ &ih->ih_key) +
op_bytes_number(ih,
inode->i_sb->s_blocksize),
- //pos_in_item * inode->i_sb->s_blocksize,
- TYPE_INDIRECT, 3); // key type is unimportant
+ TYPE_INDIRECT, 3);
RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
"green-805: invalid offset");
}
}
if (blocks_needed <= max_to_insert) {
- /* we are going to add target block to the file. Use allocated
- block for that */
+ /*
+ * we are going to add target block to
+ * the file. Use allocated block for that
+ */
un[blocks_needed - 1] =
cpu_to_le32(allocated_block_nr);
set_block_dev_mapped(bh_result,
done = 1;
} else {
/* paste hole to the indirect item */
- /* If kmalloc failed, max_to_insert becomes zero and it means we
- only have space for one block */
+ /*
+ * If kmalloc failed, max_to_insert becomes
+ * zero and it means we only have space for
+ * one block
+ */
blocks_needed =
max_to_insert ? max_to_insert : 1;
}
goto failure;
}
if (!done) {
- /* We need to mark new file size in case this function will be
- interrupted/aborted later on. And we may do this only for
- holes. */
+ /*
+ * We need to mark new file size in case
+ * this function will be interrupted/aborted
+ * later on. And we may do this only for
+ * holes.
+ */
inode->i_size +=
inode->i_sb->s_blocksize * blocks_needed;
}
if (done == 1)
break;
- /* this loop could log more blocks than we had originally asked
- ** for. So, we have to allow the transaction to end if it is
- ** too big or too full. Update the inode so things are
- ** consistent if we crash before the function returns
- **
- ** release the path so that anybody waiting on the path before
- ** ending their transaction will be able to continue.
+ /*
+ * this loop could log more blocks than we had originally
+ * asked for. So, we have to allow the transaction to end
+ * if it is too big or too full. Update the inode so things
+ * are consistent if we crash before the function returns
+ * release the path so that anybody waiting on the path before
+ * ending their transaction will be able to continue.
*/
if (journal_transaction_should_end(th, th->t_blocks_allocated)) {
retval = restart_transaction(th, inode, &path);
goto failure;
}
bh = get_last_bh(&path);
- ih = get_ih(&path);
- item = get_item(&path);
+ ih = tp_item_head(&path);
+ item = tp_item_body(&path);
pos_in_item = path.pos_in_item;
} while (1);
retval = 0;
- failure:
+failure:
if (th && (!dangle || (retval && !th->t_trans_id))) {
int err;
if (th->t_trans_id)
return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
}
-/* Compute real number of used bytes by file
- * Following three functions can go away when we'll have enough space in stat item
+/*
+ * Compute real number of used bytes by file
+ * Following three functions can go away when we'll have enough space in
+ * stat item
*/
static int real_space_diff(struct inode *inode, int sd_size)
{
if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode))
return sd_size;
- /* End of file is also in full block with indirect reference, so round
- ** up to the next block.
- **
- ** there is just no way to know if the tail is actually packed
- ** on the file, so we have to assume it isn't. When we pack the
- ** tail, we add 4 bytes to pretend there really is an unformatted
- ** node pointer
+ /*
+ * End of file is also in full block with indirect reference, so round
+ * up to the next block.
+ *
+ * there is just no way to know if the tail is actually packed
+ * on the file, so we have to assume it isn't. When we pack the
+ * tail, we add 4 bytes to pretend there really is an unformatted
+ * node pointer
*/
bytes =
((inode->i_size +
bytes += (loff_t) 511;
}
- /* files from before the quota patch might i_blocks such that
- ** bytes < real_space. Deal with that here to prevent it from
- ** going negative.
+ /*
+ * files from before the quota patch might i_blocks such that
+ * bytes < real_space. Deal with that here to prevent it from
+ * going negative.
*/
if (bytes < real_space)
return 0;
return (bytes - real_space) >> 9;
}
-//
-// BAD: new directories have stat data of new type and all other items
-// of old type. Version stored in the inode says about body items, so
-// in update_stat_data we can not rely on inode, but have to check
-// item version directly
-//
+/*
+ * BAD: new directories have stat data of new type and all other items
+ * of old type. Version stored in the inode says about body items, so
+ * in update_stat_data we can not rely on inode, but have to check
+ * item version directly
+ */
-// called by read_locked_inode
+/* called by read_locked_inode */
static void init_inode(struct inode *inode, struct treepath *path)
{
struct buffer_head *bh;
struct item_head *ih;
__u32 rdev;
- //int version = ITEM_VERSION_1;
bh = PATH_PLAST_BUFFER(path);
- ih = PATH_PITEM_HEAD(path);
+ ih = tp_item_head(path);
- copy_key(INODE_PKEY(inode), &(ih->ih_key));
+ copy_key(INODE_PKEY(inode), &ih->ih_key);
- INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list));
+ INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);
REISERFS_I(inode)->i_flags = 0;
REISERFS_I(inode)->i_prealloc_block = 0;
REISERFS_I(inode)->i_prealloc_count = 0;
if (stat_data_v1(ih)) {
struct stat_data_v1 *sd =
- (struct stat_data_v1 *)B_I_PITEM(bh, ih);
+ (struct stat_data_v1 *)ih_item_body(bh, ih);
unsigned long blocks;
set_inode_item_key_version(inode, KEY_FORMAT_3_5);
inode->i_generation = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
blocks = (inode->i_size + 511) >> 9;
blocks = _ROUND_UP(blocks, inode->i_sb->s_blocksize >> 9);
+
+ /*
+ * there was a bug in <=3.5.23 when i_blocks could take
+ * negative values. Starting from 3.5.17 this value could
+ * even be stored in stat data. For such files we set
+ * i_blocks based on file size. Just 2 notes: this can be
+ * wrong for sparse files. On-disk value will be only
+ * updated if file's inode will ever change
+ */
if (inode->i_blocks > blocks) {
- // there was a bug in <=3.5.23 when i_blocks could take negative
- // values. Starting from 3.5.17 this value could even be stored in
- // stat data. For such files we set i_blocks based on file
- // size. Just 2 notes: this can be wrong for sparce files. On-disk value will be
- // only updated if file's inode will ever change
inode->i_blocks = blocks;
}
rdev = sd_v1_rdev(sd);
REISERFS_I(inode)->i_first_direct_byte =
sd_v1_first_direct_byte(sd);
- /* an early bug in the quota code can give us an odd number for the
- ** block count. This is incorrect, fix it here.
+
+ /*
+ * an early bug in the quota code can give us an odd
+ * number for the block count. This is incorrect, fix it here.
*/
if (inode->i_blocks & 1) {
inode->i_blocks++;
inode_set_bytes(inode,
to_real_used_space(inode, inode->i_blocks,
SD_V1_SIZE));
- /* nopack is initially zero for v1 objects. For v2 objects,
- nopack is initialised from sd_attrs */
+ /*
+ * nopack is initially zero for v1 objects. For v2 objects,
+ * nopack is initialised from sd_attrs
+ */
REISERFS_I(inode)->i_flags &= ~i_nopack_mask;
} else {
- // new stat data found, but object may have old items
- // (directories and symlinks)
- struct stat_data *sd = (struct stat_data *)B_I_PITEM(bh, ih);
+ /*
+ * new stat data found, but object may have old items
+ * (directories and symlinks)
+ */
+ struct stat_data *sd = (struct stat_data *)ih_item_body(bh, ih);
inode->i_mode = sd_v2_mode(sd);
set_nlink(inode, sd_v2_nlink(sd));
inode_set_bytes(inode,
to_real_used_space(inode, inode->i_blocks,
SD_V2_SIZE));
- /* read persistent inode attributes from sd and initialise
- generic inode flags from them */
+ /*
+ * read persistent inode attributes from sd and initialise
+ * generic inode flags from them
+ */
REISERFS_I(inode)->i_attrs = sd_v2_attrs(sd);
sd_attrs_to_i_attrs(sd_v2_attrs(sd), inode);
}
}
}
-// update new stat data with inode fields
+/* update new stat data with inode fields */
static void inode2sd(void *sd, struct inode *inode, loff_t size)
{
struct stat_data *sd_v2 = (struct stat_data *)sd;
set_sd_v2_attrs(sd_v2, flags);
}
-// used to copy inode's fields to old stat data
+/* used to copy inode's fields to old stat data */
static void inode2sd_v1(void *sd, struct inode *inode, loff_t size)
{
struct stat_data_v1 *sd_v1 = (struct stat_data_v1 *)sd;
else
set_sd_v1_blocks(sd_v1, to_fake_used_blocks(inode, SD_V1_SIZE));
- // Sigh. i_first_direct_byte is back
+ /* Sigh. i_first_direct_byte is back */
set_sd_v1_first_direct_byte(sd_v1,
REISERFS_I(inode)->i_first_direct_byte);
}
-/* NOTE, you must prepare the buffer head before sending it here,
-** and then log it after the call
-*/
+/*
+ * NOTE, you must prepare the buffer head before sending it here,
+ * and then log it after the call
+ */
static void update_stat_data(struct treepath *path, struct inode *inode,
loff_t size)
{
struct item_head *ih;
bh = PATH_PLAST_BUFFER(path);
- ih = PATH_PITEM_HEAD(path);
+ ih = tp_item_head(path);
if (!is_statdata_le_ih(ih))
reiserfs_panic(inode->i_sb, "vs-13065", "key %k, found item %h",
INODE_PKEY(inode), ih);
+ /* path points to old stat data */
if (stat_data_v1(ih)) {
- // path points to old stat data
- inode2sd_v1(B_I_PITEM(bh, ih), inode, size);
+ inode2sd_v1(ih_item_body(bh, ih), inode, size);
} else {
- inode2sd(B_I_PITEM(bh, ih), inode, size);
+ inode2sd(ih_item_body(bh, ih), inode, size);
}
return;
BUG_ON(!th->t_trans_id);
- make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3); //key type is unimportant
+ /* key type is unimportant */
+ make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3);
for (;;) {
int pos;
return;
}
- /* sigh, prepare_for_journal might schedule. When it schedules the
- ** FS might change. We have to detect that, and loop back to the
- ** search if the stat data item has moved
+ /*
+ * sigh, prepare_for_journal might schedule. When it
+ * schedules the FS might change. We have to detect that,
+ * and loop back to the search if the stat data item has moved
*/
bh = get_last_bh(&path);
- ih = get_ih(&path);
+ ih = tp_item_head(&path);
copy_item_head(&tmp_ih, ih);
fs_gen = get_generation(inode->i_sb);
reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
+
+ /* Stat_data item has been moved after scheduling. */
if (fs_changed(fs_gen, inode->i_sb)
&& item_moved(&tmp_ih, &path)) {
reiserfs_restore_prepared_buffer(inode->i_sb, bh);
- continue; /* Stat_data item has been moved after scheduling. */
+ continue;
}
break;
}
update_stat_data(&path, inode, size);
- journal_mark_dirty(th, th->t_super, bh);
+ journal_mark_dirty(th, bh);
pathrelse(&path);
return;
}
-/* reiserfs_read_locked_inode is called to read the inode off disk, and it
-** does a make_bad_inode when things go wrong. But, we need to make sure
-** and clear the key in the private portion of the inode, otherwise a
-** corresponding iput might try to delete whatever object the inode last
-** represented.
-*/
+/*
+ * reiserfs_read_locked_inode is called to read the inode off disk, and it
+ * does a make_bad_inode when things go wrong. But, we need to make sure
+ * and clear the key in the private portion of the inode, otherwise a
+ * corresponding iput might try to delete whatever object the inode last
+ * represented.
+ */
static void reiserfs_make_bad_inode(struct inode *inode)
{
memset(INODE_PKEY(inode), 0, KEY_SIZE);
make_bad_inode(inode);
}
-//
-// initially this function was derived from minix or ext2's analog and
-// evolved as the prototype did
-//
-
+/*
+ * initially this function was derived from minix or ext2's analog and
+ * evolved as the prototype did
+ */
int reiserfs_init_locked_inode(struct inode *inode, void *p)
{
struct reiserfs_iget_args *args = (struct reiserfs_iget_args *)p;
return 0;
}
-/* looks for stat data in the tree, and fills up the fields of in-core
- inode stat data fields */
+/*
+ * looks for stat data in the tree, and fills up the fields of in-core
+ * inode stat data fields
+ */
void reiserfs_read_locked_inode(struct inode *inode,
struct reiserfs_iget_args *args)
{
dirino = args->dirid;
- /* set version 1, version 2 could be used too, because stat data
- key is the same in both versions */
+ /*
+ * set version 1, version 2 could be used too, because stat data
+ * key is the same in both versions
+ */
key.version = KEY_FORMAT_3_5;
key.on_disk_key.k_dir_id = dirino;
key.on_disk_key.k_objectid = inode->i_ino;
reiserfs_make_bad_inode(inode);
return;
}
+
+ /* a stale NFS handle can trigger this without it being an error */
if (retval != ITEM_FOUND) {
- /* a stale NFS handle can trigger this without it being an error */
pathrelse(&path_to_sd);
reiserfs_make_bad_inode(inode);
clear_nlink(inode);
init_inode(inode, &path_to_sd);
- /* It is possible that knfsd is trying to access inode of a file
- that is being removed from the disk by some other thread. As we
- update sd on unlink all that is required is to check for nlink
- here. This bug was first found by Sizif when debugging
- SquidNG/Butterfly, forgotten, and found again after Philippe
- Gramoulle <philippe.gramoulle@mmania.com> reproduced it.
-
- More logical fix would require changes in fs/inode.c:iput() to
- remove inode from hash-table _after_ fs cleaned disk stuff up and
- in iget() to return NULL if I_FREEING inode is found in
- hash-table. */
- /* Currently there is one place where it's ok to meet inode with
- nlink==0: processing of open-unlinked and half-truncated files
- during mount (fs/reiserfs/super.c:finish_unfinished()). */
+ /*
+ * It is possible that knfsd is trying to access inode of a file
+ * that is being removed from the disk by some other thread. As we
+ * update sd on unlink all that is required is to check for nlink
+ * here. This bug was first found by Sizif when debugging
+ * SquidNG/Butterfly, forgotten, and found again after Philippe
+ * Gramoulle <philippe.gramoulle@mmania.com> reproduced it.
+
+ * More logical fix would require changes in fs/inode.c:iput() to
+ * remove inode from hash-table _after_ fs cleaned disk stuff up and
+ * in iget() to return NULL if I_FREEING inode is found in
+ * hash-table.
+ */
+
+ /*
+ * Currently there is one place where it's ok to meet inode with
+ * nlink==0: processing of open-unlinked and half-truncated files
+ * during mount (fs/reiserfs/super.c:finish_unfinished()).
+ */
if ((inode->i_nlink == 0) &&
!REISERFS_SB(inode->i_sb)->s_is_unlinked_ok) {
reiserfs_warning(inode->i_sb, "vs-13075",
reiserfs_make_bad_inode(inode);
}
- reiserfs_check_path(&path_to_sd); /* init inode should be relsing */
+ /* init inode should be relsing */
+ reiserfs_check_path(&path_to_sd);
/*
* Stat data v1 doesn't support ACLs.
cache_no_acl(inode);
}
-/**
+/*
* reiserfs_find_actor() - "find actor" reiserfs supplies to iget5_locked().
*
* @inode: inode from hash table to check
struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
- /* fhtype happens to reflect the number of u32s encoded.
+ /*
+ * fhtype happens to reflect the number of u32s encoded.
* due to a bug in earlier code, fhtype might indicate there
* are more u32s then actually fitted.
* so if fhtype seems to be more than len, reduce fhtype.
return *lenp;
}
-/* looks for stat data, then copies fields to it, marks the buffer
- containing stat data as dirty */
-/* reiserfs inodes are never really dirty, since the dirty inode call
-** always logs them. This call allows the VFS inode marking routines
-** to properly mark inodes for datasync and such, but only actually
-** does something when called for a synchronous update.
-*/
+/*
+ * looks for stat data, then copies fields to it, marks the buffer
+ * containing stat data as dirty
+ */
+/*
+ * reiserfs inodes are never really dirty, since the dirty inode call
+ * always logs them. This call allows the VFS inode marking routines
+ * to properly mark inodes for datasync and such, but only actually
+ * does something when called for a synchronous update.
+ */
int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct reiserfs_transaction_handle th;
if (inode->i_sb->s_flags & MS_RDONLY)
return -EROFS;
- /* memory pressure can sometimes initiate write_inode calls with sync == 1,
- ** these cases are just when the system needs ram, not when the
- ** inode needs to reach disk for safety, and they can safely be
- ** ignored because the altered inode has already been logged.
+ /*
+ * memory pressure can sometimes initiate write_inode calls with
+ * sync == 1,
+ * these cases are just when the system needs ram, not when the
+ * inode needs to reach disk for safety, and they can safely be
+ * ignored because the altered inode has already been logged.
*/
if (wbc->sync_mode == WB_SYNC_ALL && !(current->flags & PF_MEMALLOC)) {
reiserfs_write_lock(inode->i_sb);
if (!journal_begin(&th, inode->i_sb, jbegin_count)) {
reiserfs_update_sd(&th, inode);
- journal_end_sync(&th, inode->i_sb, jbegin_count);
+ journal_end_sync(&th);
}
reiserfs_write_unlock(inode->i_sb);
}
return 0;
}
-/* stat data of new object is inserted already, this inserts the item
- containing "." and ".." entries */
+/*
+ * stat data of new object is inserted already, this inserts the item
+ * containing "." and ".." entries
+ */
static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
struct inode *inode,
struct item_head *ih, struct treepath *path,
le32_to_cpu(ih->ih_key.k_objectid), DOT_OFFSET,
TYPE_DIRENTRY, 3 /*key length */ );
- /* compose item head for new item. Directories consist of items of
- old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
- is done by reiserfs_new_inode */
+ /*
+ * compose item head for new item. Directories consist of items of
+ * old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
+ * is done by reiserfs_new_inode
+ */
if (old_format_only(sb)) {
make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
TYPE_DIRENTRY, EMPTY_DIR_SIZE_V1, 2);
return reiserfs_insert_item(th, path, &key, ih, inode, body);
}
-/* stat data of object has been inserted, this inserts the item
- containing the body of symlink */
-static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th, struct inode *inode, /* Inode of symlink */
+/*
+ * stat data of object has been inserted, this inserts the item
+ * containing the body of symlink
+ */
+static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th,
+ struct inode *inode,
struct item_head *ih,
struct treepath *path, const char *symname,
int item_len)
return reiserfs_insert_item(th, path, &key, ih, inode, symname);
}
-/* inserts the stat data into the tree, and then calls
- reiserfs_new_directory (to insert ".", ".." item if new object is
- directory) or reiserfs_new_symlink (to insert symlink body if new
- object is symlink) or nothing (if new object is regular file)
-
- NOTE! uid and gid must already be set in the inode. If we return
- non-zero due to an error, we have to drop the quota previously allocated
- for the fresh inode. This can only be done outside a transaction, so
- if we return non-zero, we also end the transaction. */
+/*
+ * inserts the stat data into the tree, and then calls
+ * reiserfs_new_directory (to insert ".", ".." item if new object is
+ * directory) or reiserfs_new_symlink (to insert symlink body if new
+ * object is symlink) or nothing (if new object is regular file)
+
+ * NOTE! uid and gid must already be set in the inode. If we return
+ * non-zero due to an error, we have to drop the quota previously allocated
+ * for the fresh inode. This can only be done outside a transaction, so
+ * if we return non-zero, we also end the transaction.
+ *
+ * @th: active transaction handle
+ * @dir: parent directory for new inode
+ * @mode: mode of new inode
+ * @symname: symlink contents if inode is symlink
+ * @isize: 0 for regular file, EMPTY_DIR_SIZE for dirs, strlen(symname) for
+ * symlinks
+ * @inode: inode to be filled
+ * @security: optional security context to associate with this inode
+ */
int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
struct inode *dir, umode_t mode, const char *symname,
/* 0 for regular, EMTRY_DIR_SIZE for dirs,
else
make_le_item_head(&ih, NULL, KEY_FORMAT_3_6, SD_OFFSET,
TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);
- memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE);
+ memcpy(INODE_PKEY(inode), &ih.ih_key, KEY_SIZE);
args.dirid = le32_to_cpu(ih.ih_key.k_dir_id);
depth = reiserfs_write_unlock_nested(inode->i_sb);
}
if (old_format_only(sb))
- /* not a perfect generation count, as object ids can be reused, but
- ** this is as good as reiserfs can do right now.
- ** note that the private part of inode isn't filled in yet, we have
- ** to use the directory.
+ /*
+ * not a perfect generation count, as object ids can be reused,
+ * but this is as good as reiserfs can do right now.
+ * note that the private part of inode isn't filled in yet,
+ * we have to use the directory.
*/
inode->i_generation = le32_to_cpu(INODE_PKEY(dir)->k_objectid);
else
REISERFS_I(inode)->i_first_direct_byte = S_ISLNK(mode) ? 1 :
U32_MAX /*NO_BYTES_IN_DIRECT_ITEM */ ;
- INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list));
+ INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);
REISERFS_I(inode)->i_flags = 0;
REISERFS_I(inode)->i_prealloc_block = 0;
REISERFS_I(inode)->i_prealloc_count = 0;
goto out_bad_inode;
}
if (old_format_only(sb)) {
+ /* i_uid or i_gid is too big to be stored in stat data v3.5 */
if (i_uid_read(inode) & ~0xffff || i_gid_read(inode) & ~0xffff) {
pathrelse(&path_to_key);
- /* i_uid or i_gid is too big to be stored in stat data v3.5 */
err = -EINVAL;
goto out_bad_inode;
}
} else {
inode2sd(&sd, inode, inode->i_size);
}
- // store in in-core inode the key of stat data and version all
- // object items will have (directory items will have old offset
- // format, other new objects will consist of new items)
+ /*
+ * store in in-core inode the key of stat data and version all
+ * object items will have (directory items will have old offset
+ * format, other new objects will consist of new items)
+ */
if (old_format_only(sb) || S_ISDIR(mode) || S_ISLNK(mode))
set_inode_item_key_version(inode, KEY_FORMAT_3_5);
else
if (retval) {
err = retval;
reiserfs_check_path(&path_to_key);
- journal_end(th, th->t_super, th->t_blocks_allocated);
+ journal_end(th);
goto out_inserted_sd;
}
if (retval) {
err = retval;
reiserfs_check_path(&path_to_key);
- journal_end(th, th->t_super, th->t_blocks_allocated);
+ journal_end(th);
goto out_inserted_sd;
}
} else if (inode->i_sb->s_flags & MS_POSIXACL) {
if (retval) {
err = retval;
reiserfs_check_path(&path_to_key);
- retval = journal_end(th, th->t_super,
- th->t_blocks_allocated);
+ retval = journal_end(th);
if (retval)
err = retval;
goto out_inserted_sd;
return 0;
-/* it looks like you can easily compress these two goto targets into
- * one. Keeping it like this doesn't actually hurt anything, and they
- * are place holders for what the quota code actually needs.
- */
- out_bad_inode:
+out_bad_inode:
/* Invalidate the object, nothing was inserted yet */
INODE_PKEY(inode)->k_objectid = 0;
dquot_free_inode(inode);
reiserfs_write_lock_nested(inode->i_sb, depth);
- out_end_trans:
- journal_end(th, th->t_super, th->t_blocks_allocated);
- /* Drop can be outside and it needs more credits so it's better to have it outside */
+out_end_trans:
+ journal_end(th);
+ /*
+ * Drop can be outside and it needs more credits so it's better
+ * to have it outside
+ */
depth = reiserfs_write_unlock_nested(inode->i_sb);
dquot_drop(inode);
reiserfs_write_lock_nested(inode->i_sb, depth);
inode->i_flags |= S_NOQUOTA;
make_bad_inode(inode);
- out_inserted_sd:
+out_inserted_sd:
clear_nlink(inode);
th->t_trans_id = 0; /* so the caller can't use this handle later */
unlock_new_inode(inode); /* OK to do even if we hadn't locked it */
}
/*
-** finds the tail page in the page cache,
-** reads the last block in.
-**
-** On success, page_result is set to a locked, pinned page, and bh_result
-** is set to an up to date buffer for the last block in the file. returns 0.
-**
-** tail conversion is not done, so bh_result might not be valid for writing
-** check buffer_mapped(bh_result) and bh_result->b_blocknr != 0 before
-** trying to write the block.
-**
-** on failure, nonzero is returned, page_result and bh_result are untouched.
-*/
+ * finds the tail page in the page cache,
+ * reads the last block in.
+ *
+ * On success, page_result is set to a locked, pinned page, and bh_result
+ * is set to an up to date buffer for the last block in the file. returns 0.
+ *
+ * tail conversion is not done, so bh_result might not be valid for writing
+ * check buffer_mapped(bh_result) and bh_result->b_blocknr != 0 before
+ * trying to write the block.
+ *
+ * on failure, nonzero is returned, page_result and bh_result are untouched.
+ */
static int grab_tail_page(struct inode *inode,
struct page **page_result,
struct buffer_head **bh_result)
{
- /* we want the page with the last byte in the file,
- ** not the page that will hold the next byte for appending
+ /*
+ * we want the page with the last byte in the file,
+ * not the page that will hold the next byte for appending
*/
unsigned long index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
unsigned long pos = 0;
struct page *page;
int error;
- /* we know that we are only called with inode->i_size > 0.
- ** we also know that a file tail can never be as big as a block
- ** If i_size % blocksize == 0, our file is currently block aligned
- ** and it won't need converting or zeroing after a truncate.
+ /*
+ * we know that we are only called with inode->i_size > 0.
+ * we also know that a file tail can never be as big as a block
+ * If i_size % blocksize == 0, our file is currently block aligned
+ * and it won't need converting or zeroing after a truncate.
*/
if ((offset & (blocksize - 1)) == 0) {
return -ENOENT;
} while (bh != head);
if (!buffer_uptodate(bh)) {
- /* note, this should never happen, prepare_write should
- ** be taking care of this for us. If the buffer isn't up to date,
- ** I've screwed up the code to find the buffer, or the code to
- ** call prepare_write
+ /*
+ * note, this should never happen, prepare_write should be
+ * taking care of this for us. If the buffer isn't up to
+ * date, I've screwed up the code to find the buffer, or the
+ * code to call prepare_write
*/
reiserfs_error(inode->i_sb, "clm-6000",
"error reading block %lu", bh->b_blocknr);
*bh_result = bh;
*page_result = page;
- out:
+out:
return error;
- unlock:
+unlock:
unlock_page(page);
page_cache_release(page);
return error;
}
/*
-** vfs version of truncate file. Must NOT be called with
-** a transaction already started.
-**
-** some code taken from block_truncate_page
-*/
+ * vfs version of truncate file. Must NOT be called with
+ * a transaction already started.
+ *
+ * some code taken from block_truncate_page
+ */
int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
{
struct reiserfs_transaction_handle th;
if (inode->i_size > 0) {
error = grab_tail_page(inode, &page, &bh);
if (error) {
- // -ENOENT means we truncated past the end of the file,
- // and get_block_create_0 could not find a block to read in,
- // which is ok.
+ /*
+ * -ENOENT means we truncated past the end of the
+ * file, and get_block_create_0 could not find a
+ * block to read in, which is ok.
+ */
if (error != -ENOENT)
reiserfs_error(inode->i_sb, "clm-6001",
"grab_tail_page failed %d",
}
}
- /* so, if page != NULL, we have a buffer head for the offset at
- ** the end of the file. if the bh is mapped, and bh->b_blocknr != 0,
- ** then we have an unformatted node. Otherwise, we have a direct item,
- ** and no zeroing is required on disk. We zero after the truncate,
- ** because the truncate might pack the item anyway
- ** (it will unmap bh if it packs).
+ /*
+ * so, if page != NULL, we have a buffer head for the offset at
+ * the end of the file. if the bh is mapped, and bh->b_blocknr != 0,
+ * then we have an unformatted node. Otherwise, we have a direct item,
+ * and no zeroing is required on disk. We zero after the truncate,
+ * because the truncate might pack the item anyway
+ * (it will unmap bh if it packs).
+ *
+ * it is enough to reserve space in transaction for 2 balancings:
+ * one for "save" link adding and another for the first
+ * cut_from_item. 1 is for update_sd
*/
- /* it is enough to reserve space in transaction for 2 balancings:
- one for "save" link adding and another for the first
- cut_from_item. 1 is for update_sd */
error = journal_begin(&th, inode->i_sb,
JOURNAL_PER_BALANCE_CNT * 2 + 1);
if (error)
goto out;
reiserfs_update_inode_transaction(inode);
if (update_timestamps)
- /* we are doing real truncate: if the system crashes before the last
- transaction of truncating gets committed - on reboot the file
- either appears truncated properly or not truncated at all */
+ /*
+ * we are doing real truncate: if the system crashes
+ * before the last transaction of truncating gets committed
+ * - on reboot the file either appears truncated properly
+ * or not truncated at all
+ */
add_save_link(&th, inode, 1);
err2 = reiserfs_do_truncate(&th, inode, page, update_timestamps);
- error =
- journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 2 + 1);
+ error = journal_end(&th);
if (error)
goto out;
reiserfs_write_unlock(inode->i_sb);
return 0;
- out:
+out:
if (page) {
unlock_page(page);
page_cache_release(page);
int copy_size;
int trans_running = 0;
- /* catch places below that try to log something without starting a trans */
+ /*
+ * catch places below that try to log something without
+ * starting a trans
+ */
th.t_trans_id = 0;
if (!buffer_uptodate(bh_result)) {
}
kmap(bh_result->b_page);
- start_over:
+start_over:
reiserfs_write_lock(inode->i_sb);
make_cpu_key(&key, inode, byte_offset, TYPE_ANY, 3);
- research:
+research:
retval = search_for_position_by_key(inode->i_sb, &key, &path);
if (retval != POSITION_FOUND) {
use_get_block = 1;
}
bh = get_last_bh(&path);
- ih = get_ih(&path);
- item = get_item(&path);
+ ih = tp_item_head(&path);
+ item = tp_item_body(&path);
pos_in_item = path.pos_in_item;
/* we've found an unformatted node */
goto research;
}
- memcpy(B_I_PITEM(bh, ih) + pos_in_item, p + bytes_copied,
+ memcpy(ih_item_body(bh, ih) + pos_in_item, p + bytes_copied,
copy_size);
- journal_mark_dirty(&th, inode->i_sb, bh);
+ journal_mark_dirty(&th, bh);
bytes_copied += copy_size;
set_block_dev_mapped(bh_result, 0, inode);
}
retval = 0;
- out:
+out:
pathrelse(&path);
if (trans_running) {
- int err = journal_end(&th, inode->i_sb, jbegin_count);
+ int err = journal_end(&th);
if (err)
retval = err;
trans_running = 0;
kunmap(bh_result->b_page);
if (!retval && buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
- /* we've copied data from the page into the direct item, so the
+ /*
+ * we've copied data from the page into the direct item, so the
* buffer in the page is now clean, mark it to reflect that.
*/
lock_buffer(bh_result);
return 0;
}
- /* The page dirty bit is cleared before writepage is called, which
+ /*
+ * The page dirty bit is cleared before writepage is called, which
* means we have to tell create_empty_buffers to make dirty buffers
* The page really should be up to date at this point, so tossing
* in the BH_Uptodate is just a sanity check.
}
head = page_buffers(page);
- /* last page in the file, zero out any contents past the
- ** last byte in the file
+ /*
+ * last page in the file, zero out any contents past the
+ * last byte in the file
*/
if (page->index >= end_index) {
unsigned last_offset;
(!buffer_mapped(bh) || (buffer_mapped(bh)
&& bh->b_blocknr ==
0))) {
- /* not mapped yet, or it points to a direct item, search
+ /*
+ * not mapped yet, or it points to a direct item, search
* the btree for the mapping info, and log any direct
* items found
*/
if (checked) {
reiserfs_prepare_for_journal(s, bh, 1);
- journal_mark_dirty(&th, s, bh);
+ journal_mark_dirty(&th, bh);
continue;
}
- /* from this point on, we know the buffer is mapped to a
+ /*
+ * from this point on, we know the buffer is mapped to a
* real block and not a direct item
*/
if (wbc->sync_mode != WB_SYNC_NONE) {
} while ((bh = bh->b_this_page) != head);
if (checked) {
- error = journal_end(&th, s, bh_per_page + 1);
+ error = journal_end(&th);
reiserfs_write_unlock(s);
if (error)
goto fail;
} while (bh != head);
error = 0;
- done:
+done:
if (nr == 0) {
/*
* if this page only had a direct item, it is very possible for
}
return error;
- fail:
- /* catches various errors, we need to make sure any valid dirty blocks
+fail:
+ /*
+ * catches various errors, we need to make sure any valid dirty blocks
* get to the media. The page is currently locked and not marked for
* writeback
*/
mark_buffer_async_write(bh);
} else {
/*
- * clear any dirty bits that might have come from getting
- * attached to a dirty page
+ * clear any dirty bits that might have come from
+ * getting attached to a dirty page
*/
clear_buffer_dirty(bh);
}
ret = __block_write_begin(page, pos, len, reiserfs_get_block);
if (ret && reiserfs_transaction_running(inode->i_sb)) {
struct reiserfs_transaction_handle *th = current->journal_info;
- /* this gets a little ugly. If reiserfs_get_block returned an
- * error and left a transacstion running, we've got to close it,
- * and we've got to free handle if it was a persistent transaction.
+ /*
+ * this gets a little ugly. If reiserfs_get_block returned an
+ * error and left a transacstion running, we've got to close
+ * it, and we've got to free handle if it was a persistent
+ * transaction.
*
* But, if we had nested into an existing transaction, we need
* to just drop the ref count on the handle.
*
* If old_ref == 0, the transaction is from reiserfs_get_block,
- * and it was a persistent trans. Otherwise, it was nested above.
+ * and it was a persistent trans. Otherwise, it was nested
+ * above.
*/
if (th->t_refcount > old_ref) {
if (old_ref)
ret = __block_write_begin(page, from, len, reiserfs_get_block);
if (ret && reiserfs_transaction_running(inode->i_sb)) {
struct reiserfs_transaction_handle *th = current->journal_info;
- /* this gets a little ugly. If reiserfs_get_block returned an
- * error and left a transacstion running, we've got to close it,
- * and we've got to free handle if it was a persistent transaction.
+ /*
+ * this gets a little ugly. If reiserfs_get_block returned an
+ * error and left a transacstion running, we've got to close
+ * it, and we've got to free handle if it was a persistent
+ * transaction.
*
* But, if we had nested into an existing transaction, we need
* to just drop the ref count on the handle.
*
* If old_ref == 0, the transaction is from reiserfs_get_block,
- * and it was a persistent trans. Otherwise, it was nested above.
+ * and it was a persistent trans. Otherwise, it was nested
+ * above.
*/
if (th->t_refcount > old_ref) {
if (old_ref)
reiserfs_commit_page(inode, page, start, start + copied);
- /* generic_commit_write does this for us, but does not update the
- ** transaction tracking stuff when the size changes. So, we have
- ** to do the i_size updates here.
+ /*
+ * generic_commit_write does this for us, but does not update the
+ * transaction tracking stuff when the size changes. So, we have
+ * to do the i_size updates here.
*/
if (pos + copied > inode->i_size) {
struct reiserfs_transaction_handle myth;
reiserfs_write_lock(inode->i_sb);
locked = true;
- /* If the file have grown beyond the border where it
- can have a tail, unmark it as needing a tail
- packing */
+ /*
+ * If the file have grown beyond the border where it
+ * can have a tail, unmark it as needing a tail
+ * packing
+ */
if ((have_large_tails(inode->i_sb)
&& inode->i_size > i_block_size(inode) * 4)
|| (have_small_tails(inode->i_sb)
inode->i_size = pos + copied;
/*
* this will just nest into our transaction. It's important
- * to use mark_inode_dirty so the inode gets pushed around on the
- * dirty lists, and so that O_SYNC works as expected
+ * to use mark_inode_dirty so the inode gets pushed around on
+ * the dirty lists, and so that O_SYNC works as expected
*/
mark_inode_dirty(inode);
reiserfs_update_sd(&myth, inode);
update_sd = 1;
- ret = journal_end(&myth, inode->i_sb, 1);
+ ret = journal_end(&myth);
if (ret)
goto journal_error;
}
goto out;
}
- out:
+out:
if (locked)
reiserfs_write_unlock(inode->i_sb);
unlock_page(page);
return ret == 0 ? copied : ret;
- journal_error:
+journal_error:
reiserfs_write_unlock(inode->i_sb);
locked = false;
if (th) {
}
reiserfs_commit_page(inode, page, from, to);
- /* generic_commit_write does this for us, but does not update the
- ** transaction tracking stuff when the size changes. So, we have
- ** to do the i_size updates here.
+ /*
+ * generic_commit_write does this for us, but does not update the
+ * transaction tracking stuff when the size changes. So, we have
+ * to do the i_size updates here.
*/
if (pos > inode->i_size) {
struct reiserfs_transaction_handle myth;
- /* If the file have grown beyond the border where it
- can have a tail, unmark it as needing a tail
- packing */
+ /*
+ * If the file have grown beyond the border where it
+ * can have a tail, unmark it as needing a tail
+ * packing
+ */
if ((have_large_tails(inode->i_sb)
&& inode->i_size > i_block_size(inode) * 4)
|| (have_small_tails(inode->i_sb)
inode->i_size = pos;
/*
* this will just nest into our transaction. It's important
- * to use mark_inode_dirty so the inode gets pushed around on the
- * dirty lists, and so that O_SYNC works as expected
+ * to use mark_inode_dirty so the inode gets pushed around
+ * on the dirty lists, and so that O_SYNC works as expected
*/
mark_inode_dirty(inode);
reiserfs_update_sd(&myth, inode);
update_sd = 1;
- ret = journal_end(&myth, inode->i_sb, 1);
+ ret = journal_end(&myth);
if (ret)
goto journal_error;
}
goto out;
}
- out:
+out:
return ret;
- journal_error:
+journal_error:
if (th) {
if (!update_sd)
reiserfs_update_sd(th, inode);
}
}
-/* decide if this buffer needs to stay around for data logging or ordered
-** write purposes
-*/
+/*
+ * decide if this buffer needs to stay around for data logging or ordered
+ * write purposes
+ */
static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
{
int ret = 1;
if (!buffer_mapped(bh)) {
goto free_jh;
}
- /* the page is locked, and the only places that log a data buffer
+ /*
+ * the page is locked, and the only places that log a data buffer
* also lock the page.
*/
if (reiserfs_file_data_log(inode)) {
struct reiserfs_journal_list *jl;
struct reiserfs_jh *jh = bh->b_private;
- /* why is this safe?
+ /*
+ * why is this safe?
* reiserfs_setattr updates i_size in the on disk
* stat data before allowing vmtruncate to be called.
*
&& jl != SB_JOURNAL(inode->i_sb)->j_current_jl)
ret = 0;
}
- free_jh:
+free_jh:
if (ret && bh->b_private) {
reiserfs_free_jh(bh);
}
ret = try_to_release_page(page, 0);
/* maybe should BUG_ON(!ret); - neilb */
}
- out:
+out:
return;
}
return ret;
}
-/* We thank Mingming Cao for helping us understand in great detail what
- to do in this section of the code. */
+/*
+ * We thank Mingming Cao for helping us understand in great detail what
+ * to do in this section of the code.
+ */
static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ size_t count = iov_iter_count(iter);
ssize_t ret;
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- reiserfs_get_blocks_direct_io);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+ reiserfs_get_blocks_direct_io);
/*
* In case of error extending write may have instantiated a few
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;
if ((end > isize) && inode_newsize_ok(inode, isize) == 0) {
truncate_setsize(inode, isize);
dquot_initialize(inode);
reiserfs_write_lock(inode->i_sb);
if (attr->ia_valid & ATTR_SIZE) {
- /* version 2 items will be caught by the s_maxbytes check
- ** done for us in vmtruncate
+ /*
+ * version 2 items will be caught by the s_maxbytes check
+ * done for us in vmtruncate
*/
if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5 &&
attr->ia_size > MAX_NON_LFS) {
err = journal_begin(&th, inode->i_sb, 4);
if (!err) {
reiserfs_discard_prealloc(&th, inode);
- err = journal_end(&th, inode->i_sb, 4);
+ err = journal_end(&th);
}
if (err)
error = err;
if (error)
return error;
- /* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */
+ /*
+ * (user+group)*(old+new) structure - we count quota
+ * info and , inode write (sb, inode)
+ */
reiserfs_write_lock(inode->i_sb);
error = journal_begin(&th, inode->i_sb, jbegin_count);
reiserfs_write_unlock(inode->i_sb);
error = dquot_transfer(inode, attr);
reiserfs_write_lock(inode->i_sb);
if (error) {
- journal_end(&th, inode->i_sb, jbegin_count);
+ journal_end(&th);
reiserfs_write_unlock(inode->i_sb);
goto out;
}
- /* Update corresponding info in inode so that everything is in
- * one transaction */
+ /*
+ * Update corresponding info in inode so that everything
+ * is in one transaction
+ */
if (attr->ia_valid & ATTR_UID)
inode->i_uid = attr->ia_uid;
if (attr->ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
mark_inode_dirty(inode);
- error = journal_end(&th, inode->i_sb, jbegin_count);
+ error = journal_end(&th);
reiserfs_write_unlock(inode->i_sb);
if (error)
goto out;
attr->ia_size != i_size_read(inode)) {
error = inode_newsize_ok(inode, attr->ia_size);
if (!error) {
+ /*
+ * Could race against reiserfs_file_release
+ * if called from NFS, so take tailpack mutex.
+ */
+ mutex_lock(&REISERFS_I(inode)->tailpack);
truncate_setsize(inode, attr->ia_size);
- reiserfs_vfs_truncate_file(inode);
+ reiserfs_truncate_file(inode, 1);
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
}
}
struct ubifs_info *c = inode->i_sb->s_fs_info;
#ifdef UBIFS_DEBUG
+ struct ubifs_inode *ui = ubifs_inode(inode);
spin_lock(&ui->ui_lock);
- ubifs_assert(page->index <= ui->synced_i_size << PAGE_CACHE_SIZE);
+ ubifs_assert(page->index <= ui->synced_i_size >> PAGE_CACHE_SHIFT);
spin_unlock(&ui->ui_lock);
#endif
/**
* update_ctime - update mtime and ctime of an inode.
- * @c: UBIFS file-system description object
* @inode: inode to update
*
* This function updates mtime and ctime of the inode if it is not equivalent to
* current time. Returns zero in case of success and a negative error code in
* case of failure.
*/
- static int update_mctime(struct ubifs_info *c, struct inode *inode)
+ static int update_mctime(struct inode *inode)
{
struct timespec now = ubifs_current_time(inode);
struct ubifs_inode *ui = ubifs_inode(inode);
+ struct ubifs_info *c = inode->i_sb->s_fs_info;
if (mctime_update_needed(inode, &now)) {
int err, release;
return 0;
}
- static ssize_t ubifs_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ static ssize_t ubifs_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- int err;
- struct inode *inode = iocb->ki_filp->f_mapping->host;
- struct ubifs_info *c = inode->i_sb->s_fs_info;
-
- err = update_mctime(c, inode);
+ int err = update_mctime(file_inode(iocb->ki_filp));
if (err)
return err;
- return generic_file_aio_write(iocb, iov, nr_segs, pos);
+ return generic_file_write_iter(iocb, from);
}
static int ubifs_set_page_dirty(struct page *page)
}
wait_for_stable_page(page);
- unlock_page(page);
- return 0;
+ return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
const struct file_operations ubifs_file_operations = {
.llseek = generic_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = ubifs_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = ubifs_write_iter,
.mmap = ubifs_file_mmap,
.fsync = ubifs_fsync,
.unlocked_ioctl = ubifs_ioctl,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
#ifdef CONFIG_COMPAT
.compat_ioctl = ubifs_compat_ioctl,
#endif
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
goto redirty;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
end_index = offset >> PAGE_CACHE_SHIFT;
last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
- if (page->index >= end_index) {
+
+ /*
+ * The page index is less than the end_index, adjust the end_offset
+ * to the highest offset that this page should represent.
+ * -----------------------------------------------------
+ * | file mapping | <EOF> |
+ * -----------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | |
+ * ^--------------------------------^----------|--------
+ * | desired writeback range | see else |
+ * ---------------------------------^------------------|
+ */
+ if (page->index < end_index)
+ end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+ else {
+ /*
+ * Check whether the page to write out is beyond or straddles
+ * i_size or not.
+ * -------------------------------------------------------
+ * | file mapping | <EOF> |
+ * -------------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | Beyond |
+ * ^--------------------------------^-----------|---------
+ * | | Straddles |
+ * ---------------------------------^-----------|--------|
+ */
unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
/*
* truncate operation that is in progress. We must redirty the
* page so that reclaim stops reclaiming it. Otherwise
* xfs_vm_releasepage() is called on it and gets confused.
+ *
+ * Note that the end_index is unsigned long, it would overflow
+ * if the given offset is greater than 16TB on 32-bit system
+ * and if we do check the page is fully outside i_size or not
+ * via "if (page->index >= end_index + 1)" as "end_index + 1"
+ * will be evaluated to 0. Hence this page will be redirtied
+ * and be written out repeatedly which would result in an
+ * infinite loop, the user program that perform this operation
+ * will hang. Instead, we can verify this situation by checking
+ * if the page to write is totally beyond the i_size or if it's
+ * offset is just equal to the EOF.
*/
- if (page->index >= end_index + 1 || offset_into_page == 0)
+ if (page->index > end_index ||
+ (page->index == end_index && offset_into_page == 0))
goto redirty;
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
- * that is not a multiple of the page size, the remaining
+ * that is not a multiple of the page size, the remaining
* memory is zeroed when mapped, and writes to that region are
* not written out to the file."
*/
zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+ /* Adjust the end_offset to the end of file */
+ end_offset = offset;
}
- end_offset = min_t(unsigned long long,
- (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
- offset);
len = 1 << inode->i_blkbits;
bh = head = page_buffers(page);
xfs_count_page_state(page, &delalloc, &unwritten);
- if (WARN_ON(delalloc))
+ if (WARN_ON_ONCE(delalloc))
return 0;
- if (WARN_ON(unwritten))
+ if (WARN_ON_ONCE(unwritten))
return 0;
return try_to_free_buffers(page);
xfs_vm_direct_IO(
int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct block_device *bdev = xfs_find_bdev_for_inode(inode);
ssize_t ret;
if (rw & WRITE) {
- size_t size = iov_length(iov, nr_segs);
+ size_t size = iov_iter_count(iter);
/*
* We cannot preallocate a size update transaction here as we
if (offset + size > XFS_I(inode)->i_d.di_size)
ioend->io_isdirect = 1;
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
xfs_end_io_direct_write, NULL,
DIO_ASYNC_EXTEND);
if (ret != -EIOCBQUEUED && iocb->private)
goto out_destroy_ioend;
} else {
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
NULL, NULL, 0);
}
}
STATIC ssize_t
- xfs_file_aio_read(
+ xfs_file_read_iter(
struct kiocb *iocb,
- const struct iovec *iovp,
- unsigned long nr_segs,
- loff_t pos)
+ struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- size_t size = 0;
+ size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
+ loff_t pos = iocb->ki_pos;
XFS_STATS_INC(xs_read_calls);
- BUG_ON(iocb->ki_pos != pos);
-
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
- ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
- if (ret < 0)
- return ret;
-
if (unlikely(ioflags & IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
trace_xfs_file_read(ip, size, pos, ioflags);
- ret = generic_file_aio_read(iocb, iovp, nr_segs, pos);
+ ret = generic_file_read_iter(iocb, to);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
}
/*
- * xfs_file_splice_write() does not use xfs_rw_ilock() because
- * generic_file_splice_write() takes the i_mutex itself. This, in theory,
- * couuld cause lock inversions between the aio_write path and the splice path
- * if someone is doing concurrent splice(2) based writes and write(2) based
- * writes to the same inode. The only real way to fix this is to re-implement
- * the generic code here with correct locking orders.
- */
- STATIC ssize_t
- xfs_file_splice_write(
- struct pipe_inode_info *pipe,
- struct file *outfilp,
- loff_t *ppos,
- size_t count,
- unsigned int flags)
- {
- struct inode *inode = outfilp->f_mapping->host;
- struct xfs_inode *ip = XFS_I(inode);
- int ioflags = 0;
- ssize_t ret;
-
- XFS_STATS_INC(xs_write_calls);
-
- if (outfilp->f_mode & FMODE_NOCMTIME)
- ioflags |= IO_INVIS;
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return -EIO;
-
- xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
- trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
-
- ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
- if (ret > 0)
- XFS_STATS_ADD(xs_write_bytes, ret);
-
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- return ret;
- }
-
- /*
* This routine is called to handle zeroing any space in the last block of the
* file that is beyond the EOF. We do this since the size is being increased
* without writing anything to that block and we don't want to read the
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
- const struct iovec *iovp,
- unsigned long nr_segs,
- loff_t pos,
- size_t ocount)
+ struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
- size_t count = ocount;
int unaligned_io = 0;
int iolock;
+ size_t count = iov_iter_count(from);
+ loff_t pos = iocb->ki_pos;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
+ iov_iter_truncate(from, count);
if (mapping->nrpages) {
ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
- ret = generic_file_direct_write(iocb, iovp,
- &nr_segs, pos, count, ocount);
+ ret = generic_file_direct_write(iocb, from, pos);
out:
xfs_rw_iunlock(ip, iolock);
STATIC ssize_t
xfs_file_buffered_aio_write(
struct kiocb *iocb,
- const struct iovec *iovp,
- unsigned long nr_segs,
- loff_t pos,
- size_t count)
+ struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
ssize_t ret;
int enospc = 0;
int iolock = XFS_IOLOCK_EXCL;
- struct iov_iter from;
+ loff_t pos = iocb->ki_pos;
+ size_t count = iov_iter_count(from);
xfs_rw_ilock(ip, iolock);
if (ret)
goto out;
- iov_iter_init(&from, iovp, nr_segs, count, 0);
+ iov_iter_truncate(from, count);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
write_retry:
trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
- ret = generic_perform_write(file, &from, pos);
+ ret = generic_perform_write(file, from, pos);
if (likely(ret >= 0))
iocb->ki_pos = pos + ret;
/*
}
STATIC ssize_t
- xfs_file_aio_write(
+ xfs_file_write_iter(
struct kiocb *iocb,
- const struct iovec *iovp,
- unsigned long nr_segs,
- loff_t pos)
+ struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t ret;
- size_t ocount = 0;
+ size_t ocount = iov_iter_count(from);
XFS_STATS_INC(xs_write_calls);
- BUG_ON(iocb->ki_pos != pos);
-
- ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
- if (ret)
- return ret;
-
if (ocount == 0)
return 0;
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- ret = -EIO;
- goto out;
- }
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ return -EIO;
if (unlikely(file->f_flags & O_DIRECT))
- ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
+ ret = xfs_file_dio_aio_write(iocb, from);
else
- ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
- ocount);
+ ret = xfs_file_buffered_aio_write(iocb, from);
if (ret > 0) {
ssize_t err;
if (err < 0)
ret = err;
}
-
- out:
return ret;
}
*/
mode = xfs_ilock_data_map_shared(ip);
if (ip->i_d.di_nextents > 0)
- xfs_dir3_data_readahead(NULL, ip, 0, -1);
+ xfs_dir3_data_readahead(ip, 0, -1);
xfs_iunlock(ip, mode);
return 0;
}
const struct file_operations xfs_file_operations = {
.llseek = xfs_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = xfs_file_aio_read,
- .aio_write = xfs_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = xfs_file_read_iter,
+ .write_iter = xfs_file_write_iter,
.splice_read = xfs_file_splice_read,
- .splice_write = xfs_file_splice_write,
+ .splice_write = iter_file_splice_write,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = xfs_file_compat_ioctl,
DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
DEFINE_BUF_ITEM_EVENT(xfs_trans_buf_ordered);
+DECLARE_EVENT_CLASS(xfs_filestream_class,
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno),
+ TP_ARGS(ip, agno),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_agnumber_t, agno)
+ __field(int, streams)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->agno = agno;
+ __entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+ ),
+ TP_printk("dev %d:%d ino 0x%llx agno %u streams %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->agno,
+ __entry->streams)
+)
+#define DEFINE_FILESTREAM_EVENT(name) \
+DEFINE_EVENT(xfs_filestream_class, name, \
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno), \
+ TP_ARGS(ip, agno))
+DEFINE_FILESTREAM_EVENT(xfs_filestream_free);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
+
+TRACE_EVENT(xfs_filestream_pick,
+ TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno,
+ xfs_extlen_t free, int nscan),
+ TP_ARGS(ip, agno, free, nscan),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_agnumber_t, agno)
+ __field(int, streams)
+ __field(xfs_extlen_t, free)
+ __field(int, nscan)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->agno = agno;
+ __entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+ __entry->free = free;
+ __entry->nscan = nscan;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx agno %u streams %d free %d nscan %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->agno,
+ __entry->streams,
+ __entry->free,
+ __entry->nscan)
+);
+
DECLARE_EVENT_CLASS(xfs_lock_class,
TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,
unsigned long caller_ip),
DEFINE_RW_EVENT(xfs_file_buffered_write);
DEFINE_RW_EVENT(xfs_file_direct_write);
DEFINE_RW_EVENT(xfs_file_splice_read);
- DEFINE_RW_EVENT(xfs_file_splice_write);
DECLARE_EVENT_CLASS(xfs_page_class,
TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
#ifndef __LINUX_BLK_TYPES_H
#define __LINUX_BLK_TYPES_H
- #ifdef CONFIG_BLOCK
-
#include <linux/types.h>
struct bio_set;
unsigned int bv_offset;
};
+ #ifdef CONFIG_BLOCK
+
struct bvec_iter {
sector_t bi_sector; /* device address in 512 byte
sectors */
__REQ_PM, /* runtime pm request */
__REQ_END, /* last of chain of requests */
__REQ_HASHED, /* on IO scheduler merge hash */
+ __REQ_MQ_INFLIGHT, /* track inflight for MQ */
__REQ_NR_BITS, /* stops here */
};
#define REQ_PM (1ULL << __REQ_PM)
#define REQ_END (1ULL << __REQ_END)
#define REQ_HASHED (1ULL << __REQ_HASHED)
+#define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT)
#endif /* __LINUX_BLK_TYPES_H */
#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000)
/* Write access to underlying fs */
#define FMODE_WRITER ((__force fmode_t)0x10000)
+ /* Has read method(s) */
+ #define FMODE_CAN_READ ((__force fmode_t)0x20000)
+ /* Has write method(s) */
+ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000)
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
- ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs);
+ ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
void **, unsigned long *);
/*
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1
+ struct iov_iter;
+
struct file_operations {
struct module *owner;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*write) (struct file *, 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);
+ ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+ ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
unsigned int (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
unsigned long size, pgoff_t pgoff);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
- 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);
- extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
- extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
- unsigned long *, loff_t, size_t, size_t);
+ extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
+ extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
+ extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
+ extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_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);
- extern int generic_segment_checks(const struct iovec *iov,
- unsigned long *nr_segs, size_t *count, int access_flags);
+ extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
+ extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
/* fs/block_dev.c */
- extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
+ extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync);
extern void block_sync_page(struct page *page);
struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t default_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
- extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
+ extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
struct file *out, loff_t *, size_t len, unsigned int flags);
void dio_end_io(struct bio *bio, int error);
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,
+ struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block, dio_iodone_t end_io,
dio_submit_t submit_io, int flags);
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
- struct inode *inode, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block)
+ struct inode *inode, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block)
{
- return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs, get_block, NULL, NULL,
+ return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+ offset, get_block, NULL, NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
}
#endif
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
+extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_check_addressable(unsigned, u64);
/*
* linux/fs/nfs/direct.c
*/
- extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
- unsigned long);
+ extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
- const struct iovec *iov, unsigned long nr_segs,
+ struct iov_iter *iter,
loff_t pos, bool uio);
extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
- const struct iovec *iov, unsigned long nr_segs,
+ struct iov_iter *iter,
loff_t pos, bool uio);
/*
extern int nfs_writepages(struct address_space *, struct writeback_control *);
extern int nfs_flush_incompatible(struct file *file, struct page *page);
extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
-extern void nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
/*
* Try to write back everything synchronously (but check the
extern int nfs_readpage(struct file *, struct page *);
extern int nfs_readpages(struct file *, struct address_space *,
struct list_head *, unsigned);
-extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
extern int nfs_readpage_async(struct nfs_open_context *, struct inode *,
struct page *);
{
VM_BUG_ON_PAGE(!PageLocked(page), page);
clear_bit_unlock(PG_locked, &page->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
*/
void end_page_writeback(struct page *page)
{
- if (TestClearPageReclaim(page))
+ /*
+ * TestClearPageReclaim could be used here but it is an atomic
+ * operation and overkill in this particular case. Failing to
+ * shuffle a page marked for immediate reclaim is too mild to
+ * justify taking an atomic operation penalty at the end of
+ * ever page writeback.
+ */
+ if (PageReclaim(page)) {
+ ClearPageReclaim(page);
rotate_reclaimable_page(page);
+ }
if (!test_clear_page_writeback(page))
BUG();
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);
+/*
+ * After completing I/O on a page, call this routine to update the page
+ * flags appropriately
+ */
+void page_endio(struct page *page, int rw, int err)
+{
+ if (rw == READ) {
+ if (!err) {
+ SetPageUptodate(page);
+ } else {
+ ClearPageUptodate(page);
+ SetPageError(page);
+ }
+ unlock_page(page);
+ } else { /* rw == WRITE */
+ if (err) {
+ SetPageError(page);
+ if (page->mapping)
+ mapping_set_error(page->mapping, err);
+ }
+ end_page_writeback(page);
+ }
+}
+EXPORT_SYMBOL_GPL(page_endio);
+
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
EXPORT_SYMBOL(find_get_entry);
/**
- * find_get_page - find and get a page reference
- * @mapping: the address_space to search
- * @offset: the page index
- *
- * Looks up the page cache slot at @mapping & @offset. If there is a
- * page cache page, it is returned with an increased refcount.
- *
- * Otherwise, %NULL is returned.
- */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
-{
- struct page *page = find_get_entry(mapping, offset);
-
- if (radix_tree_exceptional_entry(page))
- page = NULL;
- return page;
-}
-EXPORT_SYMBOL(find_get_page);
-
-/**
* find_lock_entry - locate, pin and lock a page cache entry
* @mapping: the address_space to search
* @offset: the page cache index
EXPORT_SYMBOL(find_lock_entry);
/**
- * find_lock_page - locate, pin and lock a pagecache page
+ * pagecache_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
+ * @fgp_flags: PCG flags
+ * @gfp_mask: gfp mask to use if a page is to be allocated
*
- * Looks up the page cache slot at @mapping & @offset. If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
- *
- * Otherwise, %NULL is returned.
- *
- * find_lock_page() may sleep.
- */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
-{
- struct page *page = find_lock_entry(mapping, offset);
-
- if (radix_tree_exceptional_entry(page))
- page = NULL;
- return page;
-}
-EXPORT_SYMBOL(find_lock_page);
-
-/**
- * find_or_create_page - locate or add a pagecache page
- * @mapping: the page's address_space
- * @index: the page's index into the mapping
- * @gfp_mask: page allocation mode
+ * Looks up the page cache slot at @mapping & @offset.
*
- * Looks up the page cache slot at @mapping & @offset. If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * PCG flags modify how the page is returned
*
- * If the page is not present, a new page is allocated using @gfp_mask
- * and added to the page cache and the VM's LRU list. The page is
- * returned locked and with an increased refcount.
+ * FGP_ACCESSED: the page will be marked accessed
+ * FGP_LOCK: Page is return locked
+ * FGP_CREAT: If page is not present then a new page is allocated using
+ * @gfp_mask and added to the page cache and the VM's LRU
+ * list. The page is returned locked and with an increased
+ * refcount. Otherwise, %NULL is returned.
*
- * On memory exhaustion, %NULL is returned.
+ * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
+ * if the GFP flags specified for FGP_CREAT are atomic.
*
- * find_or_create_page() may sleep, even if @gfp_flags specifies an
- * atomic allocation!
+ * If there is a page cache page, it is returned with an increased refcount.
*/
-struct page *find_or_create_page(struct address_space *mapping,
- pgoff_t index, gfp_t gfp_mask)
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
+ int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
{
struct page *page;
- int err;
+
repeat:
- page = find_lock_page(mapping, index);
- if (!page) {
- page = __page_cache_alloc(gfp_mask);
+ page = find_get_entry(mapping, offset);
+ if (radix_tree_exceptional_entry(page))
+ page = NULL;
+ if (!page)
+ goto no_page;
+
+ if (fgp_flags & FGP_LOCK) {
+ if (fgp_flags & FGP_NOWAIT) {
+ if (!trylock_page(page)) {
+ page_cache_release(page);
+ return NULL;
+ }
+ } else {
+ lock_page(page);
+ }
+
+ /* Has the page been truncated? */
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto repeat;
+ }
+ VM_BUG_ON_PAGE(page->index != offset, page);
+ }
+
+ if (page && (fgp_flags & FGP_ACCESSED))
+ mark_page_accessed(page);
+
+no_page:
+ if (!page && (fgp_flags & FGP_CREAT)) {
+ int err;
+ if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+ cache_gfp_mask |= __GFP_WRITE;
+ if (fgp_flags & FGP_NOFS) {
+ cache_gfp_mask &= ~__GFP_FS;
+ radix_gfp_mask &= ~__GFP_FS;
+ }
+
+ page = __page_cache_alloc(cache_gfp_mask);
if (!page)
return NULL;
- /*
- * We want a regular kernel memory (not highmem or DMA etc)
- * allocation for the radix tree nodes, but we need to honour
- * the context-specific requirements the caller has asked for.
- * GFP_RECLAIM_MASK collects those requirements.
- */
- err = add_to_page_cache_lru(page, mapping, index,
- (gfp_mask & GFP_RECLAIM_MASK));
+
+ if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+ fgp_flags |= FGP_LOCK;
+
+ /* Init accessed so avoit atomic mark_page_accessed later */
+ if (fgp_flags & FGP_ACCESSED)
+ init_page_accessed(page);
+
+ err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
if (unlikely(err)) {
page_cache_release(page);
page = NULL;
goto repeat;
}
}
+
return page;
}
-EXPORT_SYMBOL(find_or_create_page);
+EXPORT_SYMBOL(pagecache_get_page);
/**
* find_get_entries - gang pagecache lookup
}
EXPORT_SYMBOL(find_get_pages_tag);
-/**
- * grab_cache_page_nowait - returns locked page at given index in given cache
- * @mapping: target address_space
- * @index: the page index
- *
- * Same as grab_cache_page(), but do not wait if the page is unavailable.
- * This is intended for speculative data generators, where the data can
- * be regenerated if the page couldn't be grabbed. This routine should
- * be safe to call while holding the lock for another page.
- *
- * Clear __GFP_FS when allocating the page to avoid recursion into the fs
- * and deadlock against the caller's locked page.
- */
-struct page *
-grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
-{
- struct page *page = find_get_page(mapping, index);
-
- if (page) {
- if (trylock_page(page))
- return page;
- page_cache_release(page);
- return NULL;
- }
- page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
- if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
- page_cache_release(page);
- page = NULL;
- }
- return page;
-}
-EXPORT_SYMBOL(grab_cache_page_nowait);
-
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
* a _large_ part of the i/o request. Imagine the worst scenario:
return written ? written : error;
}
- /*
- * Performs necessary checks before doing a write
- * @iov: io vector request
- * @nr_segs: number of segments in the iovec
- * @count: number of bytes to write
- * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
- *
- * Adjust number of segments and amount of bytes to write (nr_segs should be
- * properly initialized first). Returns appropriate error code that caller
- * should return or zero in case that write should be allowed.
- */
- int generic_segment_checks(const struct iovec *iov,
- unsigned long *nr_segs, size_t *count, int access_flags)
- {
- unsigned long seg;
- size_t cnt = 0;
- for (seg = 0; seg < *nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- cnt += iv->iov_len;
- if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(access_flags, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- *nr_segs = seg;
- cnt -= iv->iov_len; /* This segment is no good */
- break;
- }
- *count = cnt;
- return 0;
- }
- EXPORT_SYMBOL(generic_segment_checks);
-
/**
- * generic_file_aio_read - generic filesystem read routine
+ * generic_file_read_iter - generic filesystem read routine
* @iocb: kernel I/O control block
- * @iov: io vector request
- * @nr_segs: number of segments in the iovec
- * @pos: current file position
+ * @iter: destination for the data read
*
- * This is the "read()" routine for all filesystems
+ * This is the "read_iter()" routine for all filesystems
* 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 pos)
+ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- struct file *filp = iocb->ki_filp;
- ssize_t retval;
- size_t count;
+ struct file *file = iocb->ki_filp;
+ ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
- struct iov_iter i;
-
- count = 0;
- retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
- if (retval)
- return retval;
- iov_iter_init(&i, iov, nr_segs, count, 0);
+ loff_t pos = *ppos;
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
- if (filp->f_flags & O_DIRECT) {
+ if (file->f_flags & O_DIRECT) {
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ size_t count = iov_iter_count(iter);
loff_t size;
- struct address_space *mapping;
- struct inode *inode;
- mapping = filp->f_mapping;
- inode = mapping->host;
if (!count)
goto out; /* skip atime */
size = i_size_read(inode);
retval = filemap_write_and_wait_range(mapping, pos,
- pos + iov_length(iov, nr_segs) - 1);
+ pos + count - 1);
if (!retval) {
- retval = mapping->a_ops->direct_IO(READ, iocb,
- iov, pos, nr_segs);
+ struct iov_iter data = *iter;
+ retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos);
}
+
if (retval > 0) {
*ppos = pos + retval;
- count -= retval;
- /*
- * If we did a short DIO read we need to skip the
- * section of the iov that we've already read data into.
- */
- iov_iter_advance(&i, retval);
+ iov_iter_advance(iter, retval);
}
/*
* and return. Otherwise fallthrough to buffered io for
* the rest of the read.
*/
- if (retval < 0 || !count || *ppos >= size) {
- file_accessed(filp);
+ if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) {
+ file_accessed(file);
goto out;
}
}
- retval = do_generic_file_read(filp, ppos, &i, retval);
+ retval = do_generic_file_read(file, ppos, iter, retval);
out:
return retval;
}
- EXPORT_SYMBOL(generic_file_aio_read);
+ EXPORT_SYMBOL(generic_file_read_iter);
#ifdef CONFIG_MMU
/**
{
const struct address_space_operations *aops = mapping->a_ops;
- mark_page_accessed(page);
return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
}
EXPORT_SYMBOL(pagecache_write_end);
ssize_t
- generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long *nr_segs, loff_t pos,
- size_t count, size_t ocount)
+ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
ssize_t written;
size_t write_len;
pgoff_t end;
+ struct iov_iter data;
- if (count != ocount)
- *nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
-
- write_len = iov_length(iov, *nr_segs);
+ write_len = iov_iter_count(from);
end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
}
}
- written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
+ data = *from;
+ written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos);
/*
* Finally, try again to invalidate clean pages which might have been
if (written > 0) {
pos += written;
+ iov_iter_advance(from, written);
if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags)
{
- int status;
- gfp_t gfp_mask;
struct page *page;
- gfp_t gfp_notmask = 0;
+ int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;
- gfp_mask = mapping_gfp_mask(mapping);
- if (mapping_cap_account_dirty(mapping))
- gfp_mask |= __GFP_WRITE;
if (flags & AOP_FLAG_NOFS)
- gfp_notmask = __GFP_FS;
-repeat:
- page = find_lock_page(mapping, index);
+ fgp_flags |= FGP_NOFS;
+
+ page = pagecache_get_page(mapping, index, fgp_flags,
+ mapping_gfp_mask(mapping),
+ GFP_KERNEL);
if (page)
- goto found;
+ wait_for_stable_page(page);
- page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
- if (!page)
- return NULL;
- status = add_to_page_cache_lru(page, mapping, index,
- GFP_KERNEL & ~gfp_notmask);
- if (unlikely(status)) {
- page_cache_release(page);
- if (status == -EEXIST)
- goto repeat;
- return NULL;
- }
-found:
- wait_for_stable_page(page);
return page;
}
EXPORT_SYMBOL(grab_cache_page_write_begin);
status = a_ops->write_begin(file, mapping, pos, bytes, flags,
&page, &fsdata);
- if (unlikely(status))
+ if (unlikely(status < 0))
break;
if (mapping_writably_mapped(mapping))
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
flush_dcache_page(page);
- mark_page_accessed(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
if (unlikely(status < 0))
EXPORT_SYMBOL(generic_perform_write);
/**
- * __generic_file_aio_write - write data to a file
+ * __generic_file_write_iter - write data to a file
* @iocb: IO state structure (file, offset, etc.)
- * @iov: vector with data to write
- * @nr_segs: number of segments in the vector
+ * @from: iov_iter with data to write
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
* A caller has to handle it. This is mainly due to the fact that we want to
* avoid syncing under i_mutex.
*/
- ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs)
+ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
- size_t ocount; /* original count */
- size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
loff_t pos = iocb->ki_pos;
ssize_t written = 0;
ssize_t err;
ssize_t status;
- struct iov_iter from;
-
- ocount = 0;
- err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
- if (err)
- return err;
-
- count = ocount;
+ size_t count = iov_iter_count(from);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if (count == 0)
goto out;
+ iov_iter_truncate(from, count);
+
err = file_remove_suid(file);
if (err)
goto out;
if (err)
goto out;
- iov_iter_init(&from, iov, nr_segs, count, 0);
-
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
- written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
- count, ocount);
+ written = generic_file_direct_write(iocb, from, pos);
if (written < 0 || written == count)
goto out;
- iov_iter_advance(&from, written);
/*
* direct-io write to a hole: fall through to buffered I/O
pos += written;
count -= written;
- status = generic_perform_write(file, &from, pos);
+ status = generic_perform_write(file, from, pos);
/*
* If generic_perform_write() returned a synchronous error
* then we want to return the number of bytes which were
*/
}
} else {
- written = generic_perform_write(file, &from, pos);
+ written = generic_perform_write(file, from, pos);
if (likely(written >= 0))
iocb->ki_pos = pos + written;
}
current->backing_dev_info = NULL;
return written ? written : err;
}
- EXPORT_SYMBOL(__generic_file_aio_write);
+ EXPORT_SYMBOL(__generic_file_write_iter);
/**
- * generic_file_aio_write - write data to a file
+ * generic_file_write_iter - write data to a file
* @iocb: IO state structure
- * @iov: vector with data to write
- * @nr_segs: number of segments in the vector
- * @pos: position in file where to write
+ * @from: iov_iter with data to write
*
- * This is a wrapper around __generic_file_aio_write() to be used by most
+ * This is a wrapper around __generic_file_write_iter() to be used by most
* filesystems. It takes care of syncing the file in case of O_SYNC file
* and acquires i_mutex as needed.
*/
- ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
- BUG_ON(iocb->ki_pos != pos);
-
mutex_lock(&inode->i_mutex);
- ret = __generic_file_aio_write(iocb, iov, nr_segs);
+ ret = __generic_file_write_iter(iocb, from);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
}
return ret;
}
- EXPORT_SYMBOL(generic_file_aio_write);
+ EXPORT_SYMBOL(generic_file_write_iter);
/**
* try_to_release_page() - release old fs-specific metadata on a page
return ret;
}
+static sector_t swap_page_sector(struct page *page)
+{
+ return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9);
+}
+
int __swap_writepage(struct page *page, struct writeback_control *wbc,
void (*end_write_func)(struct bio *, int))
{
struct bio *bio;
- int ret = 0, rw = WRITE;
+ int ret, rw = WRITE;
struct swap_info_struct *sis = page_swap_info(page);
if (sis->flags & SWP_FILE) {
struct kiocb kiocb;
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
- struct iovec iov = {
- .iov_base = kmap(page),
- .iov_len = PAGE_SIZE,
+ struct bio_vec bv = {
+ .bv_page = page,
+ .bv_len = PAGE_SIZE,
+ .bv_offset = 0
+ };
+ struct iov_iter from = {
+ .type = ITER_BVEC | WRITE,
+ .count = PAGE_SIZE,
+ .iov_offset = 0,
+ .nr_segs = 1,
+ .bvec = &bv
};
init_sync_kiocb(&kiocb, swap_file);
set_page_writeback(page);
unlock_page(page);
- ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
- &kiocb, &iov,
- kiocb.ki_pos, 1);
- kunmap(page);
+ ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
+ &kiocb, &from,
+ kiocb.ki_pos);
if (ret == PAGE_SIZE) {
count_vm_event(PSWPOUT);
ret = 0;
return ret;
}
+ ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
+ if (!ret) {
+ count_vm_event(PSWPOUT);
+ return 0;
+ }
+
+ ret = 0;
bio = get_swap_bio(GFP_NOIO, page, end_write_func);
if (bio == NULL) {
set_page_dirty(page);
return ret;
}
+ ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+ if (!ret) {
+ count_vm_event(PSWPIN);
+ return 0;
+ }
+
+ ret = 0;
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
goto decused;
}
- SetPageSwapBacked(page);
+ __SetPageSwapBacked(page);
__set_page_locked(page);
error = mem_cgroup_charge_file(page, current->mm,
gfp & GFP_RECLAIM_MASK);
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
+ int ret;
struct inode *inode = mapping->host;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
- return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+ ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+ if (ret == 0 && *pagep)
+ init_page_accessed(*pagep);
+ return ret;
}
static int
return copied;
}
- static ssize_t shmem_file_aio_read(struct kiocb *iocb,
- const struct iovec *iov, unsigned long nr_segs, loff_t pos)
+ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
unsigned long offset;
enum sgp_type sgp = SGP_READ;
int error = 0;
- ssize_t retval;
- size_t count;
+ ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
- struct iov_iter iter;
-
- retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
- if (retval)
- return retval;
- iov_iter_init(&iter, iov, nr_segs, count, 0);
/*
* Might this read be for a stacking filesystem? Then when reading
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*/
- ret = copy_page_to_iter(page, offset, nr, &iter);
+ ret = copy_page_to_iter(page, offset, nr, to);
retval += ret;
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
page_cache_release(page);
- if (!iov_iter_count(&iter))
+ if (!iov_iter_count(to))
break;
if (ret < nr) {
error = -EFAULT;
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
.llseek = shmem_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = shmem_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = shmem_file_read_iter,
+ .write_iter = generic_file_write_iter,
.fsync = noop_fsync,
.splice_read = shmem_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
};
* Multiqueue VM started 5.8.00, Rik van Riel.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/sysctl.h>
#include <linux/oom.h>
#include <linux/prefetch.h>
+#include <linux/printk.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
/* Scan (total_size >> priority) pages at once */
int priority;
+ /* anon vs. file LRUs scanning "ratio" */
+ int swappiness;
+
/*
* The memory cgroup that hit its limit and as a result is the
* primary target of this reclaim invocation.
else
new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
- trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+ trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan);
return freed;
}
* stalls if we need to run get_block(). We could test
* PagePrivate for that.
*
- * If this process is currently in __generic_file_aio_write() against
+ * If this process is currently in __generic_file_write_iter() against
* this page's queue, we can perform writeback even if that
* will block.
*
if (page_has_private(page)) {
if (try_to_free_buffers(page)) {
ClearPageDirty(page);
- printk("%s: orphaned page\n", __func__);
+ pr_info("%s: orphaned page\n", __func__);
return PAGE_CLEAN;
}
}
VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
- free_hot_cold_page_list(&free_pages, 1);
+ free_hot_cold_page_list(&free_pages, true);
list_splice(&ret_pages, page_list);
count_vm_events(PGACTIVATE, pgactivate);
}
/*
+ * If a kernel thread (such as nfsd for loop-back mounts) services
+ * a backing device by writing to the page cache it sets PF_LESS_THROTTLE.
+ * In that case we should only throttle if the backing device it is
+ * writing to is congested. In other cases it is safe to throttle.
+ */
+static int current_may_throttle(void)
+{
+ return !(current->flags & PF_LESS_THROTTLE) ||
+ current->backing_dev_info == NULL ||
+ bdi_write_congested(current->backing_dev_info);
+}
+
+/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
*/
spin_unlock_irq(&zone->lru_lock);
- free_hot_cold_page_list(&page_list, 1);
+ free_hot_cold_page_list(&page_list, true);
/*
* If reclaim is isolating dirty pages under writeback, it implies
* If dirty pages are scanned that are not queued for IO, it
* implies that flushers are not keeping up. In this case, flag
* the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
- * pages from reclaim context. It will forcibly stall in the
- * next check.
+ * pages from reclaim context.
*/
if (nr_unqueued_dirty == nr_taken)
zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
/*
- * In addition, if kswapd scans pages marked marked for
- * immediate reclaim and under writeback (nr_immediate), it
- * implies that pages are cycling through the LRU faster than
+ * If kswapd scans pages marked marked for immediate
+ * reclaim and under writeback (nr_immediate), it implies
+ * that pages are cycling through the LRU faster than
* they are written so also forcibly stall.
*/
- if (nr_unqueued_dirty == nr_taken || nr_immediate)
+ if (nr_immediate && current_may_throttle())
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
* is congested. Allow kswapd to continue until it starts encountering
* unqueued dirty pages or cycling through the LRU too quickly.
*/
- if (!sc->hibernation_mode && !current_is_kswapd())
+ if (!sc->hibernation_mode && !current_is_kswapd() &&
+ current_may_throttle())
wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&zone->lru_lock);
- free_hot_cold_page_list(&l_hold, 1);
+ free_hot_cold_page_list(&l_hold, true);
}
#ifdef CONFIG_SWAP
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
-static int vmscan_swappiness(struct scan_control *sc)
-{
- if (global_reclaim(sc))
- return vm_swappiness;
- return mem_cgroup_swappiness(sc->target_mem_cgroup);
-}
-
enum scan_balance {
SCAN_EQUAL,
SCAN_FRACT,
bool force_scan = false;
unsigned long ap, fp;
enum lru_list lru;
+ bool some_scanned;
+ int pass;
/*
* If the zone or memcg is small, nr[l] can be 0. This
* using the memory controller's swap limit feature would be
* too expensive.
*/
- if (!global_reclaim(sc) && !vmscan_swappiness(sc)) {
+ if (!global_reclaim(sc) && !sc->swappiness) {
scan_balance = SCAN_FILE;
goto out;
}
* system is close to OOM, scan both anon and file equally
* (unless the swappiness setting disagrees with swapping).
*/
- if (!sc->priority && vmscan_swappiness(sc)) {
+ if (!sc->priority && sc->swappiness) {
scan_balance = SCAN_EQUAL;
goto out;
}
* With swappiness at 100, anonymous and file have the same priority.
* This scanning priority is essentially the inverse of IO cost.
*/
- anon_prio = vmscan_swappiness(sc);
+ anon_prio = sc->swappiness;
file_prio = 200 - anon_prio;
/*
fraction[1] = fp;
denominator = ap + fp + 1;
out:
- for_each_evictable_lru(lru) {
- int file = is_file_lru(lru);
- unsigned long size;
- unsigned long scan;
+ some_scanned = false;
+ /* Only use force_scan on second pass. */
+ for (pass = 0; !some_scanned && pass < 2; pass++) {
+ for_each_evictable_lru(lru) {
+ int file = is_file_lru(lru);
+ unsigned long size;
+ unsigned long scan;
- size = get_lru_size(lruvec, lru);
- scan = size >> sc->priority;
+ size = get_lru_size(lruvec, lru);
+ scan = size >> sc->priority;
- if (!scan && force_scan)
- scan = min(size, SWAP_CLUSTER_MAX);
+ if (!scan && pass && force_scan)
+ scan = min(size, SWAP_CLUSTER_MAX);
- switch (scan_balance) {
- case SCAN_EQUAL:
- /* Scan lists relative to size */
- break;
- case SCAN_FRACT:
+ switch (scan_balance) {
+ case SCAN_EQUAL:
+ /* Scan lists relative to size */
+ break;
+ case SCAN_FRACT:
+ /*
+ * Scan types proportional to swappiness and
+ * their relative recent reclaim efficiency.
+ */
+ scan = div64_u64(scan * fraction[file],
+ denominator);
+ break;
+ case SCAN_FILE:
+ case SCAN_ANON:
+ /* Scan one type exclusively */
+ if ((scan_balance == SCAN_FILE) != file)
+ scan = 0;
+ break;
+ default:
+ /* Look ma, no brain */
+ BUG();
+ }
+ nr[lru] = scan;
/*
- * Scan types proportional to swappiness and
- * their relative recent reclaim efficiency.
+ * Skip the second pass and don't force_scan,
+ * if we found something to scan.
*/
- scan = div64_u64(scan * fraction[file], denominator);
- break;
- case SCAN_FILE:
- case SCAN_ANON:
- /* Scan one type exclusively */
- if ((scan_balance == SCAN_FILE) != file)
- scan = 0;
- break;
- default:
- /* Look ma, no brain */
- BUG();
+ some_scanned |= !!scan;
}
- nr[lru] = scan;
}
}
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct blk_plug plug;
- bool scan_adjusted = false;
+ bool scan_adjusted;
get_scan_count(lruvec, sc, nr);
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
+ /*
+ * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
+ * event that can occur when there is little memory pressure e.g.
+ * multiple streaming readers/writers. Hence, we do not abort scanning
+ * when the requested number of pages are reclaimed when scanning at
+ * DEF_PRIORITY on the assumption that the fact we are direct
+ * reclaiming implies that kswapd is not keeping up and it is best to
+ * do a batch of work at once. For memcg reclaim one check is made to
+ * abort proportional reclaim if either the file or anon lru has already
+ * dropped to zero at the first pass.
+ */
+ scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
+ sc->priority == DEF_PRIORITY);
+
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
continue;
/*
- * For global direct reclaim, reclaim only the number of pages
- * requested. Less care is taken to scan proportionally as it
- * is more important to minimise direct reclaim stall latency
- * than it is to properly age the LRU lists.
- */
- if (global_reclaim(sc) && !current_is_kswapd())
- break;
-
- /*
* For kswapd and memcg, reclaim at least the number of pages
- * requested. Ensure that the anon and file LRUs shrink
+ * requested. Ensure that the anon and file LRUs are scanned
* proportionally what was requested by get_scan_count(). We
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
+ /*
+ * It's just vindictive to attack the larger once the smaller
+ * has gone to zero. And given the way we stop scanning the
+ * smaller below, this makes sure that we only make one nudge
+ * towards proportionality once we've got nr_to_reclaim.
+ */
+ if (!nr_file || !nr_anon)
+ break;
+
if (nr_file > nr_anon) {
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
targets[LRU_ACTIVE_ANON] + 1;
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+ sc->swappiness = mem_cgroup_swappiness(memcg);
shrink_lruvec(lruvec, sc);
/*
* there is a buffer of free pages available to give compaction
* a reasonable chance of completing and allocating the page
*/
- balance_gap = min(low_wmark_pages(zone),
- (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
- KSWAPD_ZONE_BALANCE_GAP_RATIO);
+ balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
+ zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
+ if (!populated_zone(zone))
+ continue;
+
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
+ /* If there are no reserves (unexpected config) then do not throttle */
+ if (!pfmemalloc_reserve)
+ return true;
+
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
+ struct zoneref *z;
struct zone *zone;
- int high_zoneidx = gfp_zone(gfp_mask);
- pg_data_t *pgdat;
+ pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
if (fatal_signal_pending(current))
goto out;
- /* Check if the pfmemalloc reserves are ok */
- first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
- pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ /*
+ * Check if the pfmemalloc reserves are ok by finding the first node
+ * with a usable ZONE_NORMAL or lower zone. The expectation is that
+ * GFP_KERNEL will be required for allocating network buffers when
+ * swapping over the network so ZONE_HIGHMEM is unusable.
+ *
+ * Throttling is based on the first usable node and throttled processes
+ * wait on a queue until kswapd makes progress and wakes them. There
+ * is an affinity then between processes waking up and where reclaim
+ * progress has been made assuming the process wakes on the same node.
+ * More importantly, processes running on remote nodes will not compete
+ * for remote pfmemalloc reserves and processes on different nodes
+ * should make reasonable progress.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_mask, nodemask) {
+ if (zone_idx(zone) > ZONE_NORMAL)
+ continue;
+
+ /* Throttle based on the first usable node */
+ pgdat = zone->zone_pgdat;
+ if (pfmemalloc_watermark_ok(pgdat))
+ goto out;
+ break;
+ }
+
+ /* If no zone was usable by the allocation flags then do not throttle */
+ if (!pgdat)
goto out;
/* Account for the throttling */
.may_swap = !noswap,
.order = 0,
.priority = 0,
+ .swappiness = mem_cgroup_swappiness(memcg),
.target_mem_cgroup = memcg,
};
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
* high wmark plus a "gap" where the gap is either the low
* watermark or 1% of the zone, whichever is smaller.
*/
- balance_gap = min(low_wmark_pages(zone),
- (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
- KSWAPD_ZONE_BALANCE_GAP_RATIO);
+ balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
+ zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
/*
* If there is no low memory pressure or the zone is balanced then no
}
}
+ tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+
return 0;
}
/*
* Called by memory hotplug when all memory in a node is offlined. Caller must
- * hold lock_memory_hotplug().
+ * hold mem_hotplug_begin/end().
*/
void kswapd_stop(int nid)
{