#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/pagemap.h>
static int flush_racache(struct inode *inode)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_kernel_op_s *new_op;
int ret;
gossip_debug(GOSSIP_UTILS_DEBUG,
"%s: %pU: Handle is %pU | fs_id %d\n", __func__,
get_khandle_from_ino(inode), &orangefs_inode->refn.khandle,
orangefs_inode->refn.fs_id);
new_op = op_alloc(ORANGEFS_VFS_OP_RA_FLUSH);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.ra_cache_flush.refn = orangefs_inode->refn;
ret = service_operation(new_op, "orangefs_flush_racache",
get_interruptible_flag(inode));
gossip_debug(GOSSIP_UTILS_DEBUG, "%s: got return value of %d\n",
__func__, ret);
op_release(new_op);
return ret;
}
ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
loff_t *offset, struct iov_iter *iter, size_t total_size,
loff_t readahead_size, struct orangefs_write_range *wr,
int *index_return, struct file *file)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
struct orangefs_kernel_op_s *new_op = NULL;
int buffer_index;
ssize_t ret;
size_t copy_amount;
int open_for_read;
int open_for_write;
new_op = op_alloc(ORANGEFS_VFS_OP_FILE_IO);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.io.readahead_size = readahead_size;
new_op->upcall.req.io.io_type = type;
new_op->upcall.req.io.refn = orangefs_inode->refn;
populate_shared_memory:
buffer_index = orangefs_bufmap_get();
if (buffer_index < 0) {
ret = buffer_index;
gossip_debug(GOSSIP_FILE_DEBUG,
"%s: orangefs_bufmap_get failure (%zd)\n",
__func__, ret);
goto out;
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): GET op %p -> buffer_index %d\n",
__func__,
handle,
new_op,
buffer_index);
new_op->uses_shared_memory = 1;
new_op->upcall.req.io.buf_index = buffer_index;
new_op->upcall.req.io.count = total_size;
new_op->upcall.req.io.offset = *offset;
if (type == ORANGEFS_IO_WRITE && wr) {
new_op->upcall.uid = from_kuid(&init_user_ns, wr->uid);
new_op->upcall.gid = from_kgid(&init_user_ns, wr->gid);
}
if (file) {
open_for_write = file->f_mode & FMODE_WRITE;
open_for_read = file->f_mode & FMODE_READ;
} else {
open_for_write = 1;
open_for_read = 0;
}
if ((type == ORANGEFS_IO_WRITE) && open_for_write)
new_op->upcall.uid = 0;
if ((type == ORANGEFS_IO_READ) && open_for_read)
new_op->upcall.uid = 0;
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): offset: %llu total_size: %zd\n",
__func__,
handle,
llu(*offset),
total_size);
if (type == ORANGEFS_IO_WRITE && total_size) {
ret = orangefs_bufmap_copy_from_iovec(iter, buffer_index,
total_size);
if (ret < 0) {
gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
__func__, (long)ret);
goto out;
}
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): Calling post_io_request with tag (%llu)\n",
__func__,
handle,
llu(new_op->tag));
ret = service_operation(new_op,
type == ORANGEFS_IO_WRITE ?
"file_write" :
"file_read",
get_interruptible_flag(inode));
if (ret == -EAGAIN && op_state_purged(new_op)) {
orangefs_bufmap_put(buffer_index);
if (type == ORANGEFS_IO_WRITE)
iov_iter_revert(iter, total_size);
gossip_debug(GOSSIP_FILE_DEBUG,
"%s:going to repopulate_shared_memory.\n",
__func__);
goto populate_shared_memory;
}
if (ret < 0) {
if (ret == -EINTR) {
switch (new_op->op_state - OP_VFS_STATE_GIVEN_UP) {
case OP_VFS_STATE_WAITING:
if (*offset == 0)
ret = -EINTR;
else
ret = 0;
break;
case OP_VFS_STATE_INPROGR:
if (type == ORANGEFS_IO_READ)
ret = -EINTR;
else
ret = total_size;
break;
default:
gossip_err("%s: unexpected op state :%d:.\n",
__func__,
new_op->op_state);
ret = 0;
break;
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s: got EINTR, state:%d: %p\n",
__func__,
new_op->op_state,
new_op);
} else {
gossip_err("%s: error in %s handle %pU, returning %zd\n",
__func__,
type == ORANGEFS_IO_READ ?
"read from" : "write to",
handle, ret);
}
if (orangefs_cancel_op_in_progress(new_op))
return ret;
goto out;
}
if (type == ORANGEFS_IO_READ && new_op->downcall.resp.io.amt_complete) {
copy_amount = new_op->downcall.resp.io.amt_complete;
ret = orangefs_bufmap_copy_to_iovec(iter, buffer_index,
copy_amount);
if (ret < 0) {
gossip_err("%s: Failed to copy-out buffers. Please make sure that the pvfs2-client is running (%ld)\n",
__func__, (long)ret);
goto out;
}
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): Amount %s, returned by the sys-io call:%d\n",
__func__,
handle,
type == ORANGEFS_IO_READ ? "read" : "written",
(int)new_op->downcall.resp.io.amt_complete);
ret = new_op->downcall.resp.io.amt_complete;
out:
if (buffer_index >= 0) {
orangefs_bufmap_put(buffer_index);
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): PUT buffer_index %d\n",
__func__, handle, buffer_index);
}
op_release(new_op);
return ret;
}
int orangefs_revalidate_mapping(struct inode *inode)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct address_space *mapping = inode->i_mapping;
unsigned long *bitlock = &orangefs_inode->bitlock;
int ret;
while (1) {
ret = wait_on_bit(bitlock, 1, TASK_KILLABLE);
if (ret)
return ret;
spin_lock(&inode->i_lock);
if (test_bit(1, bitlock)) {
spin_unlock(&inode->i_lock);
continue;
}
if (!time_before(jiffies, orangefs_inode->mapping_time))
break;
spin_unlock(&inode->i_lock);
return 0;
}
set_bit(1, bitlock);
smp_wmb();
spin_unlock(&inode->i_lock);
unmap_mapping_range(mapping, 0, 0, 0);
ret = filemap_write_and_wait(mapping);
if (!ret)
ret = invalidate_inode_pages2(mapping);
orangefs_inode->mapping_time = jiffies +
orangefs_cache_timeout_msecs*HZ/1000;
clear_bit(1, bitlock);
smp_mb__after_atomic();
wake_up_bit(bitlock, 1);
return ret;
}
static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
struct iov_iter *iter)
{
int ret;
orangefs_stats.reads++;
down_read(&file_inode(iocb->ki_filp)->i_rwsem);
ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
if (ret)
goto out;
ret = generic_file_read_iter(iocb, iter);
out:
up_read(&file_inode(iocb->ki_filp)->i_rwsem);
return ret;
}
static ssize_t orangefs_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
{
struct inode *inode = file_inode(in);
ssize_t ret;
orangefs_stats.reads++;
down_read(&inode->i_rwsem);
ret = orangefs_revalidate_mapping(inode);
if (ret)
goto out;
ret = filemap_splice_read(in, ppos, pipe, len, flags);
out:
up_read(&inode->i_rwsem);
return ret;
}
static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
struct iov_iter *iter)
{
int ret;
orangefs_stats.writes++;
if (iocb->ki_pos > i_size_read(file_inode(iocb->ki_filp))) {
ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
if (ret)
return ret;
}
ret = generic_file_write_iter(iocb, iter);
return ret;
}
static vm_fault_t orangefs_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
int ret;
ret = orangefs_inode_getattr(file->f_mapping->host,
ORANGEFS_GETATTR_SIZE);
if (ret == -ESTALE)
ret = -EIO;
if (ret) {
gossip_err("%s: orangefs_inode_getattr failed, "
"ret:%d:.\n", __func__, ret);
return VM_FAULT_SIGBUS;
}
return filemap_fault(vmf);
}
static const struct vm_operations_struct orangefs_file_vm_ops = {
.fault = orangefs_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = orangefs_page_mkwrite,
};
static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
int ret;
ret = orangefs_revalidate_mapping(file_inode(file));
if (ret)
return ret;
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_file_mmap: called on %pD\n", file);
vm_flags_mod(vma, VM_SEQ_READ, VM_RAND_READ);
file_accessed(file);
vma->vm_ops = &orangefs_file_vm_ops;
return 0;
}
#define mapping_nrpages(idata) ((idata)->nrpages)
static int orangefs_file_release(struct inode *inode, struct file *file)
{
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_file_release: called on %pD\n",
file);
if (mapping_nrpages(file->f_mapping)) {
if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
gossip_debug(GOSSIP_INODE_DEBUG,
"calling flush_racache on %pU\n",
get_khandle_from_ino(inode));
flush_racache(inode);
gossip_debug(GOSSIP_INODE_DEBUG,
"flush_racache finished\n");
}
}
return 0;
}
static int orangefs_fsync(struct file *file,
loff_t start,
loff_t end,
int datasync)
{
int ret;
struct orangefs_inode_s *orangefs_inode =
ORANGEFS_I(file_inode(file));
struct orangefs_kernel_op_s *new_op = NULL;
ret = filemap_write_and_wait_range(file_inode(file)->i_mapping,
start, end);
if (ret < 0)
return ret;
new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.fsync.refn = orangefs_inode->refn;
ret = service_operation(new_op,
"orangefs_fsync",
get_interruptible_flag(file_inode(file)));
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_fsync got return value of %d\n",
ret);
op_release(new_op);
return ret;
}
static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin)
{
int ret = -EINVAL;
struct inode *inode = file_inode(file);
if (origin == SEEK_END) {
ret = orangefs_inode_getattr(file->f_mapping->host,
ORANGEFS_GETATTR_SIZE);
if (ret == -ESTALE)
ret = -EIO;
if (ret) {
gossip_debug(GOSSIP_FILE_DEBUG,
"%s:%s:%d calling make bad inode\n",
__FILE__,
__func__,
__LINE__);
return ret;
}
}
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_file_llseek: offset is %ld | origin is %d"
" | inode size is %lu\n",
(long)offset,
origin,
(unsigned long)i_size_read(inode));
return generic_file_llseek(file, offset, origin);
}
static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
int rc = -EINVAL;
if (ORANGEFS_SB(file_inode(filp)->i_sb)->flags & ORANGEFS_OPT_LOCAL_LOCK) {
if (cmd == F_GETLK) {
rc = 0;
posix_test_lock(filp, fl);
} else {
rc = posix_lock_file(filp, fl, NULL);
}
}
return rc;
}
static int orangefs_flush(struct file *file, fl_owner_t id)
{
int r;
r = filemap_write_and_wait_range(file->f_mapping, 0, LLONG_MAX);
if (r > 0)
return 0;
else
return r;
}
const struct file_operations orangefs_file_operations = {
.llseek = orangefs_file_llseek,
.read_iter = orangefs_file_read_iter,
.write_iter = orangefs_file_write_iter,
.lock = orangefs_lock,
.mmap = orangefs_file_mmap,
.open = generic_file_open,
.splice_read = orangefs_file_splice_read,
.splice_write = iter_file_splice_write,
.flush = orangefs_flush,
.release = orangefs_file_release,
.fsync = orangefs_fsync,
}