From 10ebd8556b7990499c896a550e3d416b444211e6 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 02:23:07 +0000
Subject: [PATCH] add led
---
kernel/fs/orangefs/file.c | 463 +++++++++++++++++++++++++--------------------------------
1 files changed, 207 insertions(+), 256 deletions(-)
diff --git a/kernel/fs/orangefs/file.c b/kernel/fs/orangefs/file.c
index a5a2fe7..af375e0 100644
--- a/kernel/fs/orangefs/file.c
+++ b/kernel/fs/orangefs/file.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/*
* (C) 2001 Clemson University and The University of Chicago
+ * Copyright 2018 Omnibond Systems, L.L.C.
*
* See COPYING in top-level directory.
*/
@@ -44,15 +45,19 @@
/*
* Post and wait for the I/O upcall to finish
*/
-static 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)
+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 = -1;
+ 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)
@@ -84,6 +89,42 @@
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);
+ }
+ /*
+ * Orangefs has no open, and orangefs checks file permissions
+ * on each file access. Posix requires that file permissions
+ * be checked on open and nowhere else. Orangefs-through-the-kernel
+ * needs to seem posix compliant.
+ *
+ * The VFS opens files, even if the filesystem provides no
+ * method. We can see if a file was successfully opened for
+ * read and or for write by looking at file->f_mode.
+ *
+ * When writes are flowing from the page cache, file is no
+ * longer available. We can trust the VFS to have checked
+ * file->f_mode before writing to the page cache.
+ *
+ * The mode of a file might change between when it is opened
+ * and IO commences, or it might be created with an arbitrary mode.
+ *
+ * We'll make sure we don't hit EACCES during the IO stage by
+ * using UID 0. Some of the time we have access without changing
+ * to UID 0 - how to check?
+ */
+ 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; /* not relevant? */
+ }
+ 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",
@@ -128,7 +169,6 @@
*/
if (ret == -EAGAIN && op_state_purged(new_op)) {
orangefs_bufmap_put(buffer_index);
- buffer_index = -1;
if (type == ORANGEFS_IO_WRITE)
iov_iter_revert(iter, total_size);
gossip_debug(GOSSIP_FILE_DEBUG,
@@ -168,7 +208,10 @@
* trigger the write.
*/
case OP_VFS_STATE_INPROGR:
- ret = total_size;
+ if (type == ORANGEFS_IO_READ)
+ ret = -EINTR;
+ else
+ ret = total_size;
break;
default:
gossip_err("%s: unexpected op state :%d:.\n",
@@ -204,8 +247,25 @@
* can futher be kernel-space or user-space addresses.
* or it can pointers to struct page's
*/
+
+ /*
+ * When reading, readahead_size will only be zero when
+ * we're doing O_DIRECT, otherwise we got here from
+ * orangefs_readpage.
+ *
+ * If we got here from orangefs_readpage we want to
+ * copy either a page or the whole file into the io
+ * vector, whichever is smaller.
+ */
+ if (readahead_size)
+ copy_amount =
+ min(new_op->downcall.resp.io.amt_complete,
+ (__s64)PAGE_SIZE);
+ else
+ copy_amount = new_op->downcall.resp.io.amt_complete;
+
ret = orangefs_bufmap_copy_to_iovec(iter, buffer_index,
- new_op->downcall.resp.io.amt_complete);
+ 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);
@@ -223,250 +283,112 @@
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);
- buffer_index = -1;
+ if ((readahead_size) && (type == ORANGEFS_IO_READ)) {
+ /* readpage */
+ *index_return = buffer_index;
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s: hold on to buffer_index :%d:\n",
+ __func__, buffer_index);
+ } else {
+ /* O_DIRECT */
+ 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;
}
-/*
- * Common entry point for read/write/readv/writev
- * This function will dispatch it to either the direct I/O
- * or buffered I/O path depending on the mount options and/or
- * augmented/extended metadata attached to the file.
- * Note: File extended attributes override any mount options.
- */
-static ssize_t do_readv_writev(enum ORANGEFS_io_type type, struct file *file,
- loff_t *offset, struct iov_iter *iter)
+int orangefs_revalidate_mapping(struct inode *inode)
{
- struct inode *inode = file->f_mapping->host;
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
- struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
- size_t count = iov_iter_count(iter);
- ssize_t total_count = 0;
- ssize_t ret = -EINVAL;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long *bitlock = &orangefs_inode->bitlock;
+ int ret;
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n",
- __func__,
- handle,
- (int)count);
-
- if (type == ORANGEFS_IO_WRITE) {
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): proceeding with offset : %llu, "
- "size %d\n",
- __func__,
- handle,
- llu(*offset),
- (int)count);
- }
-
- if (count == 0) {
- ret = 0;
- goto out;
- }
-
- while (iov_iter_count(iter)) {
- size_t each_count = iov_iter_count(iter);
- size_t amt_complete;
-
- /* how much to transfer in this loop iteration */
- if (each_count > orangefs_bufmap_size_query())
- each_count = orangefs_bufmap_size_query();
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): size of each_count(%d)\n",
- __func__,
- handle,
- (int)each_count);
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): BEFORE wait_for_io: offset is %d\n",
- __func__,
- handle,
- (int)*offset);
-
- ret = wait_for_direct_io(type, inode, offset, iter,
- each_count, 0);
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): return from wait_for_io:%d\n",
- __func__,
- handle,
- (int)ret);
-
- if (ret < 0)
- goto out;
-
- *offset += ret;
- total_count += ret;
- amt_complete = ret;
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): AFTER wait_for_io: offset is %d\n",
- __func__,
- handle,
- (int)*offset);
-
- /*
- * if we got a short I/O operations,
- * fall out and return what we got so far
- */
- if (amt_complete < each_count)
+ 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;
- } /*end while */
+ 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:
- if (total_count > 0)
- ret = total_count;
- if (ret > 0) {
- if (type == ORANGEFS_IO_READ) {
- file_accessed(file);
- } else {
- file_update_time(file);
- /*
- * Must invalidate to ensure write loop doesn't
- * prevent kernel from reading updated
- * attribute. Size probably changed because of
- * the write, and other clients could update
- * any other attribute.
- */
- orangefs_inode->getattr_time = jiffies - 1;
- }
- }
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): Value(%d) returned.\n",
- __func__,
- handle,
- (int)ret);
-
+ up_read(&file_inode(iocb->ki_filp)->i_rwsem);
return ret;
}
-/*
- * Read data from a specified offset in a file (referenced by inode).
- * Data may be placed either in a user or kernel buffer.
- */
-ssize_t orangefs_inode_read(struct inode *inode,
- struct iov_iter *iter,
- loff_t *offset,
- loff_t readahead_size)
+static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
+ struct iov_iter *iter)
{
- struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
- size_t count = iov_iter_count(iter);
- size_t bufmap_size;
- ssize_t ret = -EINVAL;
-
- orangefs_stats.reads++;
-
- bufmap_size = orangefs_bufmap_size_query();
- if (count > bufmap_size) {
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s: count is too large (%zd/%zd)!\n",
- __func__, count, bufmap_size);
- return -EINVAL;
- }
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU) %zd@%llu\n",
- __func__,
- &orangefs_inode->refn.khandle,
- count,
- llu(*offset));
-
- ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, offset, iter,
- count, readahead_size);
- if (ret > 0)
- *offset += ret;
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): Value(%zd) returned.\n",
- __func__,
- &orangefs_inode->refn.khandle,
- ret);
-
- return ret;
-}
-
-static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- loff_t pos = iocb->ki_pos;
- ssize_t rc = 0;
-
- BUG_ON(iocb->private);
-
- gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n");
-
- orangefs_stats.reads++;
-
- rc = do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter);
- iocb->ki_pos = pos;
-
- return rc;
-}
-
-static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- loff_t pos;
- ssize_t rc;
-
- BUG_ON(iocb->private);
-
- gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
-
- inode_lock(file->f_mapping->host);
-
- /* Make sure generic_write_checks sees an up to date inode size. */
- if (file->f_flags & O_APPEND) {
- rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
- STATX_SIZE);
- if (rc == -ESTALE)
- rc = -EIO;
- if (rc) {
- gossip_err("%s: orangefs_inode_getattr failed, "
- "rc:%zd:.\n", __func__, rc);
- goto out;
- }
- }
-
- rc = generic_write_checks(iocb, iter);
-
- if (rc <= 0) {
- gossip_err("%s: generic_write_checks failed, rc:%zd:.\n",
- __func__, rc);
- goto out;
- }
-
- /*
- * if we are appending, generic_write_checks would have updated
- * pos to the end of the file, so we will wait till now to set
- * pos...
- */
- pos = iocb->ki_pos;
-
- rc = do_readv_writev(ORANGEFS_IO_WRITE,
- file,
- &pos,
- iter);
- if (rc < 0) {
- gossip_err("%s: do_readv_writev failed, rc:%zd:.\n",
- __func__, rc);
- goto out;
- }
-
- iocb->ki_pos = pos;
+ int ret;
orangefs_stats.writes++;
-out:
+ 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;
+ }
- inode_unlock(file->f_mapping->host);
- return rc;
+ ret = generic_file_write_iter(iocb, iter);
+ return ret;
+}
+
+static int orangefs_getflags(struct inode *inode, unsigned long *uval)
+{
+ __u64 val = 0;
+ int ret;
+
+ ret = orangefs_inode_getxattr(inode,
+ "user.pvfs2.meta_hint",
+ &val, sizeof(val));
+ if (ret < 0 && ret != -ENODATA)
+ return ret;
+ else if (ret == -ENODATA)
+ val = 0;
+ *uval = val;
+ return 0;
}
/*
@@ -474,6 +396,7 @@
*/
static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
+ struct inode *inode = file_inode(file);
int ret = -ENOTTY;
__u64 val = 0;
unsigned long uval;
@@ -487,20 +410,16 @@
* and append flags
*/
if (cmd == FS_IOC_GETFLAGS) {
- val = 0;
- ret = orangefs_inode_getxattr(file_inode(file),
- "user.pvfs2.meta_hint",
- &val, sizeof(val));
- if (ret < 0 && ret != -ENODATA)
+ ret = orangefs_getflags(inode, &uval);
+ if (ret)
return ret;
- else if (ret == -ENODATA)
- val = 0;
- uval = val;
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n",
(unsigned long long)uval);
return put_user(uval, (int __user *)arg);
} else if (cmd == FS_IOC_SETFLAGS) {
+ unsigned long old_uval;
+
ret = 0;
if (get_user(uval, (int __user *)arg))
return -EFAULT;
@@ -516,11 +435,17 @@
gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n");
return -EINVAL;
}
+ ret = orangefs_getflags(inode, &old_uval);
+ if (ret)
+ return ret;
+ ret = vfs_ioc_setflags_prepare(inode, old_uval, uval);
+ if (ret)
+ return ret;
val = uval;
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
(unsigned long long)val);
- ret = orangefs_inode_setxattr(file_inode(file),
+ ret = orangefs_inode_setxattr(inode,
"user.pvfs2.meta_hint",
&val, sizeof(val), 0);
}
@@ -532,14 +457,13 @@
{
struct file *file = vmf->vma->vm_file;
int ret;
-
- ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
- STATX_SIZE);
+ 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);
+ gossip_err("%s: orangefs_inode_getattr failed, "
+ "ret:%d:.\n", __func__, ret);
return VM_FAULT_SIGBUS;
}
return filemap_fault(vmf);
@@ -548,7 +472,7 @@
static const struct vm_operations_struct orangefs_file_vm_ops = {
.fault = orangefs_fault,
.map_pages = filemap_map_pages,
- .page_mkwrite = filemap_page_mkwrite,
+ .page_mkwrite = orangefs_page_mkwrite,
};
/*
@@ -556,14 +480,17 @@
*/
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 %s\n",
(file ?
(char *)file->f_path.dentry->d_name.name :
(char *)"Unknown"));
-
- if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
- return -EINVAL;
/* set the sequential readahead hint */
vma->vm_flags |= VM_SEQ_READ;
@@ -604,8 +531,7 @@
gossip_debug(GOSSIP_INODE_DEBUG,
"flush_racache finished\n");
}
- truncate_inode_pages(file_inode(file)->i_mapping,
- 0);
+
}
return 0;
}
@@ -622,6 +548,11 @@
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)
@@ -644,7 +575,7 @@
* Change the file pointer position for an instance of an open file.
*
* \note If .llseek is overriden, we must acquire lock as described in
- * Documentation/filesystems/Locking.
+ * Documentation/filesystems/locking.rst.
*
* Future upgrade could support SEEK_DATA and SEEK_HOLE but would
* require much changes to the FS
@@ -660,8 +591,8 @@
* NOTE: We are only interested in file size here,
* so we set mask accordingly.
*/
- ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
- STATX_SIZE);
+ ret = orangefs_inode_getattr(file->f_mapping->host,
+ ORANGEFS_GETATTR_SIZE);
if (ret == -ESTALE)
ret = -EIO;
if (ret) {
@@ -704,6 +635,25 @@
return rc;
}
+static int orangefs_flush(struct file *file, fl_owner_t id)
+{
+ /*
+ * This is vfs_fsync_range(file, 0, LLONG_MAX, 0) without the
+ * service_operation in orangefs_fsync.
+ *
+ * Do not send fsync to OrangeFS server on a close. Do send fsync
+ * on an explicit fsync call. This duplicates historical OrangeFS
+ * behavior.
+ */
+ int r;
+
+ r = filemap_write_and_wait_range(file->f_mapping, 0, LLONG_MAX);
+ if (r > 0)
+ return 0;
+ else
+ return r;
+}
+
/** ORANGEFS implementation of VFS file operations */
const struct file_operations orangefs_file_operations = {
.llseek = orangefs_file_llseek,
@@ -713,6 +663,7 @@
.unlocked_ioctl = orangefs_ioctl,
.mmap = orangefs_file_mmap,
.open = generic_file_open,
+ .flush = orangefs_flush,
.release = orangefs_file_release,
.fsync = orangefs_fsync,
};
--
Gitblit v1.6.2