From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/nfs/file.c | 157 +++++++++++++++++++++++++++++-----------------------
1 files changed, 88 insertions(+), 69 deletions(-)
diff --git a/kernel/fs/nfs/file.c b/kernel/fs/nfs/file.c
index 29553fd..7be1a7f 100644
--- a/kernel/fs/nfs/file.c
+++ b/kernel/fs/nfs/file.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/file.c
*
@@ -89,8 +90,8 @@
/**
* nfs_revalidate_size - Revalidate the file size
- * @inode - pointer to inode struct
- * @file - pointer to struct file
+ * @inode: pointer to inode struct
+ * @filp: pointer to struct file
*
* Revalidates the file length. This is basically a wrapper around
* nfs_revalidate_inode() that takes into account the fact that we may
@@ -139,6 +140,7 @@
nfs_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
+ errseq_t since;
dprintk("NFS: flush(%pD2)\n", file);
@@ -147,7 +149,9 @@
return 0;
/* Flush writes to the server and return any errors */
- return vfs_fsync(file, 0);
+ since = filemap_sample_wb_err(file->f_mapping);
+ nfs_wb_all(inode);
+ return filemap_check_wb_err(file->f_mapping, since);
}
ssize_t
@@ -157,7 +161,7 @@
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to);
+ return nfs_file_direct_read(iocb, to, false);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
@@ -199,64 +203,44 @@
* Flush any dirty pages for this process, and check for write errors.
* The return status from this call provides a reliable indication of
* whether any write errors occurred for this process.
- *
- * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
- * disk, but it retrieves and clears ctx->error after synching, despite
- * the two being set at the same time in nfs_context_set_write_error().
- * This is because the former is used to notify the _next_ call to
- * nfs_file_write() that a write error occurred, and hence cause it to
- * fall back to doing a synchronous write.
*/
static int
nfs_file_fsync_commit(struct file *file, int datasync)
{
- struct nfs_open_context *ctx = nfs_file_open_context(file);
struct inode *inode = file_inode(file);
- int do_resend, status;
- int ret = 0;
+ int ret, ret2;
dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync);
nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
- do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
- status = nfs_commit_inode(inode, FLUSH_SYNC);
- if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
- ret = xchg(&ctx->error, 0);
- if (ret)
- goto out;
- }
- if (status < 0) {
- ret = status;
- goto out;
- }
- do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
- if (do_resend)
- ret = -EAGAIN;
-out:
+ ret = nfs_commit_inode(inode, FLUSH_SYNC);
+ ret2 = file_check_and_advance_wb_err(file);
+ if (ret2 < 0)
+ return ret2;
return ret;
}
int
nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
- int ret;
+ struct nfs_open_context *ctx = nfs_file_open_context(file);
struct inode *inode = file_inode(file);
+ int ret;
trace_nfs_fsync_enter(inode);
- do {
- struct nfs_open_context *ctx = nfs_file_open_context(file);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) {
- int ret2 = xchg(&ctx->error, 0);
- if (ret2)
- ret = ret2;
- }
+ for (;;) {
+ ret = file_write_and_wait_range(file, start, end);
if (ret != 0)
break;
ret = nfs_file_fsync_commit(file, datasync);
- if (!ret)
- ret = pnfs_sync_inode(inode, !!datasync);
+ if (ret != 0)
+ break;
+ ret = pnfs_sync_inode(inode, !!datasync);
+ if (ret != 0)
+ break;
+ if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags))
+ break;
/*
* If nfs_file_fsync_commit detected a server reboot, then
* resend all dirty pages that might have been covered by
@@ -264,7 +248,7 @@
*/
start = 0;
end = LLONG_MAX;
- } while (ret == -EAGAIN);
+ }
trace_nfs_fsync_exit(inode, ret);
return ret;
@@ -275,6 +259,12 @@
* Decide whether a read/modify/write cycle may be more efficient
* then a modify/write/read cycle when writing to a page in the
* page cache.
+ *
+ * Some pNFS layout drivers can only read/write at a certain block
+ * granularity like all block devices and therefore we must perform
+ * read/modify/write whenever a page hasn't read yet and the data
+ * to be written there is not aligned to a block boundary and/or
+ * smaller than the block size.
*
* The modify/write/read cycle may occur if a page is read before
* being completely filled by the writer. In this situation, the
@@ -291,26 +281,32 @@
* and that the new data won't completely replace the old data in
* that range of the file.
*/
-static int nfs_want_read_modify_write(struct file *file, struct page *page,
- loff_t pos, unsigned len)
+static bool nfs_full_page_write(struct page *page, loff_t pos, unsigned int len)
{
unsigned int pglen = nfs_page_length(page);
unsigned int offset = pos & (PAGE_SIZE - 1);
unsigned int end = offset + len;
- if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
- if (!PageUptodate(page))
- return 1;
- return 0;
- }
+ return !pglen || (end >= pglen && !offset);
+}
- if ((file->f_mode & FMODE_READ) && /* open for read? */
- !PageUptodate(page) && /* Uptodate? */
- !PagePrivate(page) && /* i/o request already? */
- pglen && /* valid bytes of file? */
- (end < pglen || offset)) /* replace all valid bytes? */
- return 1;
- return 0;
+static bool nfs_want_read_modify_write(struct file *file, struct page *page,
+ loff_t pos, unsigned int len)
+{
+ /*
+ * Up-to-date pages, those with ongoing or full-page write
+ * don't need read/modify/write
+ */
+ if (PageUptodate(page) || PagePrivate(page) ||
+ nfs_full_page_write(page, pos, len))
+ return false;
+
+ if (pnfs_ld_read_whole_page(file->f_mapping->host))
+ return true;
+ /* Open for reading too? */
+ if (file->f_mode & FMODE_READ)
+ return true;
+ return false;
}
/*
@@ -394,11 +390,8 @@
return status;
NFS_I(mapping->host)->write_io += copied;
- if (nfs_ctx_key_to_expire(ctx, mapping->host)) {
- status = nfs_wb_all(mapping->host);
- if (status < 0)
- return status;
- }
+ if (nfs_ctx_key_to_expire(ctx, mapping->host))
+ nfs_wb_all(mapping->host);
return copied;
}
@@ -492,18 +485,39 @@
static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
- struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+ unsigned long blocks;
+ long long isize;
+ struct inode *inode = file_inode(file);
+ struct rpc_clnt *clnt = NFS_CLIENT(inode);
+ struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
+
+ spin_lock(&inode->i_lock);
+ blocks = inode->i_blocks;
+ isize = inode->i_size;
+ spin_unlock(&inode->i_lock);
+ if (blocks*512 < isize) {
+ pr_warn("swap activate: swapfile has holes\n");
+ return -EINVAL;
+ }
*span = sis->pages;
+
+
+ if (cl->rpc_ops->enable_swap)
+ cl->rpc_ops->enable_swap(inode);
return rpc_clnt_swap_activate(clnt);
}
static void nfs_swap_deactivate(struct file *file)
{
- struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+ struct inode *inode = file_inode(file);
+ struct rpc_clnt *clnt = NFS_CLIENT(inode);
+ struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
rpc_clnt_swap_deactivate(clnt);
+ if (cl->rpc_ops->disable_swap)
+ cl->rpc_ops->disable_swap(file_inode(file));
}
const struct address_space_operations nfs_file_aops = {
@@ -583,12 +597,13 @@
.page_mkwrite = nfs_vm_page_mkwrite,
};
-static int nfs_need_check_write(struct file *filp, struct inode *inode)
+static int nfs_need_check_write(struct file *filp, struct inode *inode,
+ int error)
{
struct nfs_open_context *ctx;
ctx = nfs_file_open_context(filp);
- if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
+ if (nfs_error_is_fatal_on_server(error) ||
nfs_ctx_key_to_expire(ctx, inode))
return 1;
return 0;
@@ -600,13 +615,15 @@
struct inode *inode = file_inode(file);
unsigned long written = 0;
ssize_t result;
+ errseq_t since;
+ int error;
result = nfs_key_timeout_notify(file, inode);
if (result)
return result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_write(iocb, from);
+ return nfs_file_direct_write(iocb, from, false);
dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, iov_iter_count(from), (long long) iocb->ki_pos);
@@ -624,6 +641,7 @@
if (iocb->ki_pos > i_size_read(inode))
nfs_revalidate_mapping(inode, file->f_mapping);
+ since = filemap_sample_wb_err(file->f_mapping);
nfs_start_io_write(inode);
result = generic_write_checks(iocb, from);
if (result > 0) {
@@ -642,8 +660,9 @@
goto out;
/* Return error values */
- if (nfs_need_check_write(file, inode)) {
- int err = vfs_fsync(file, 0);
+ error = filemap_check_wb_err(file->f_mapping, since);
+ if (nfs_need_check_write(file, inode, error)) {
+ int err = nfs_wb_all(inode);
if (err < 0)
result = err;
}
@@ -653,7 +672,7 @@
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
- return -EBUSY;
+ return -ETXTBSY;
}
EXPORT_SYMBOL_GPL(nfs_file_write);
@@ -697,7 +716,7 @@
* Flush all pending writes before doing anything
* with locks..
*/
- vfs_fsync(filp, 0);
+ nfs_wb_all(inode);
l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
if (!IS_ERR(l_ctx)) {
--
Gitblit v1.6.2