#include <linux/nfs_fs.h>
#include <linux/utsname.h>
#include <linux/smp_lock.h>
+ #include <linux/freezer.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
goto retry_cancel;
}
- dprintk("lockd: cancel status %d (task %d)\n",
+ dprintk("lockd: cancel status %u (task %u)\n",
req->a_res.status, task->tk_pid);
switch (req->a_res.status) {
#define NFSDBG_FACILITY NFSDBG_VFS
- static kmem_cache_t *nfs_direct_cachep;
+ static struct kmem_cache *nfs_direct_cachep;
/*
* This represents a set of asynchronous requests that we're waiting on
{
struct nfs_direct_req *dreq;
- dreq = kmem_cache_alloc(nfs_direct_cachep, SLAB_KERNEL);
+ dreq = kmem_cache_alloc(nfs_direct_cachep, GFP_KERNEL);
if (!dreq)
return NULL;
data->task.tk_cookie = (unsigned long) inode;
- lock_kernel();
rpc_execute(&data->task);
- unlock_kernel();
dfprintk(VFS, "NFS: %5u initiated direct read call (req %s/%Ld, %zu bytes @ offset %Lu)\n",
data->task.tk_pid,
dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
- lock_kernel();
rpc_execute(&data->task);
- unlock_kernel();
}
static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
data->task.tk_priority = RPC_PRIORITY_NORMAL;
data->task.tk_cookie = (unsigned long) inode;
- lock_kernel();
rpc_execute(&data->task);
- unlock_kernel();
dfprintk(VFS, "NFS: %5u initiated direct write call (req %s/%Ld, %zu bytes @ offset %Lu)\n",
data->task.tk_pid,
static void nfs_zap_acl_cache(struct inode *);
- static kmem_cache_t * nfs_inode_cachep;
+ static struct kmem_cache * nfs_inode_cachep;
static inline unsigned long
nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
int err;
/* Flush out writes to the server in order to update c/mtime */
- nfs_sync_inode_wait(inode, 0, 0, FLUSH_NOCOMMIT);
+ nfs_sync_mapping_range(inode->i_mapping, 0, 0, FLUSH_NOCOMMIT);
/*
* We may force a getattr if the user cares about atime.
struct inode *nfs_alloc_inode(struct super_block *sb)
{
struct nfs_inode *nfsi;
- nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, SLAB_KERNEL);
+ nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
if (!nfsi)
return NULL;
nfsi->flags = 0UL;
#endif
}
- static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
#include <linux/nfs_page.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
+#include <linux/writeback.h>
#define NFS_PARANOIA 1
- static kmem_cache_t *nfs_page_cachep;
+ static struct kmem_cache *nfs_page_cachep;
static inline struct nfs_page *
nfs_page_alloc(void)
{
struct nfs_page *p;
- p = kmem_cache_alloc(nfs_page_cachep, SLAB_KERNEL);
+ p = kmem_cache_alloc(nfs_page_cachep, GFP_KERNEL);
if (p) {
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->wb_list);
#define NFS_SCAN_MAXENTRIES 16
/**
- * nfs_scan_lock_dirty - Scan the radix tree for dirty requests
- * @nfsi: NFS inode
+ * nfs_scan_dirty - Scan the radix tree for dirty requests
+ * @mapping: pointer to address space
+ * @wbc: writeback_control structure
* @dst: Destination list
- * @idx_start: lower bound of page->index to scan
- * @npages: idx_start + npages sets the upper bound to scan.
*
* Moves elements from one of the inode request lists.
* If the number of requests is set to 0, the entire address_space
* The requests are *not* checked to ensure that they form a contiguous set.
* You must be holding the inode's req_lock when calling this function
*/
-int
-nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst,
- unsigned long idx_start, unsigned int npages)
+long nfs_scan_dirty(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct list_head *dst)
{
+ struct nfs_inode *nfsi = NFS_I(mapping->host);
struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
struct nfs_page *req;
- unsigned long idx_end;
+ pgoff_t idx_start, idx_end;
+ long res = 0;
int found, i;
- int res;
- res = 0;
- if (npages == 0)
- idx_end = ~0;
- else
- idx_end = idx_start + npages - 1;
+ if (nfsi->ndirty == 0)
+ return 0;
+ if (wbc->range_cyclic) {
+ idx_start = 0;
+ idx_end = ULONG_MAX;
+ } else if (wbc->range_end == 0) {
+ idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
+ idx_end = ULONG_MAX;
+ } else {
+ idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
+ idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ }
for (;;) {
+ unsigned int toscan = NFS_SCAN_MAXENTRIES;
+
found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree,
- (void **)&pgvec[0], idx_start, NFS_SCAN_MAXENTRIES,
+ (void **)&pgvec[0], idx_start, toscan,
NFS_PAGE_TAG_DIRTY);
+
+ /* Did we make progress? */
if (found <= 0)
break;
+
for (i = 0; i < found; i++) {
req = pgvec[i];
- if (req->wb_index > idx_end)
+ if (!wbc->range_cyclic && req->wb_index > idx_end)
goto out;
+ /* Try to lock request and mark it for writeback */
+ if (!nfs_set_page_writeback_locked(req))
+ goto next;
+ radix_tree_tag_clear(&nfsi->nfs_page_tree,
+ req->wb_index, NFS_PAGE_TAG_DIRTY);
+ nfsi->ndirty--;
+ nfs_list_remove_request(req);
+ nfs_list_add_request(req, dst);
+ res++;
+ if (res == LONG_MAX)
+ goto out;
+next:
idx_start = req->wb_index + 1;
-
- if (nfs_set_page_writeback_locked(req)) {
- radix_tree_tag_clear(&nfsi->nfs_page_tree,
- req->wb_index, NFS_PAGE_TAG_DIRTY);
- nfs_list_remove_request(req);
- nfs_list_add_request(req, dst);
- dec_zone_page_state(req->wb_page, NR_FILE_DIRTY);
- res++;
- }
}
}
out:
+ WARN_ON ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty));
return res;
}
#include <asm/system.h>
+#include "internal.h"
#include "iostat.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
static const struct rpc_call_ops nfs_read_partial_ops;
static const struct rpc_call_ops nfs_read_full_ops;
- static kmem_cache_t *nfs_rdata_cachep;
+ static struct kmem_cache *nfs_rdata_cachep;
static mempool_t *nfs_rdata_mempool;
#define MIN_POOL_READ (32)
struct nfs_read_data *nfs_readdata_alloc(size_t len)
{
unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, SLAB_NOFS);
+ struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
return p;
}
-static void nfs_readdata_free(struct nfs_read_data *p)
+static void nfs_readdata_rcu_free(struct rcu_head *head)
{
+ struct nfs_read_data *p = container_of(head, struct nfs_read_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_rdata_mempool);
}
-void nfs_readdata_release(void *data)
+static void nfs_readdata_free(struct nfs_read_data *rdata)
{
- nfs_readdata_free(data);
+ call_rcu_bh(&rdata->task.u.tk_rcu, nfs_readdata_rcu_free);
}
-static
-unsigned int nfs_page_length(struct inode *inode, struct page *page)
+void nfs_readdata_release(void *data)
{
- loff_t i_size = i_size_read(inode);
- unsigned long idx;
-
- if (i_size <= 0)
- return 0;
- idx = (i_size - 1) >> PAGE_CACHE_SHIFT;
- if (page->index > idx)
- return 0;
- if (page->index != idx)
- return PAGE_CACHE_SIZE;
- return 1 + ((i_size - 1) & (PAGE_CACHE_SIZE - 1));
+ nfs_readdata_free(data);
}
static
{
unsigned int rsize = NFS_SERVER(inode)->rsize;
unsigned int count = PAGE_CACHE_SIZE;
- int result;
+ int result = -ENOMEM;
struct nfs_read_data *rdata;
rdata = nfs_readdata_alloc(count);
if (!rdata)
- return -ENOMEM;
+ goto out_unlock;
memset(rdata, 0, sizeof(*rdata));
rdata->flags = (IS_SWAPFILE(inode)? NFS_RPC_SWAPFLAGS : 0);
result = 0;
io_error:
- unlock_page(page);
nfs_readdata_free(rdata);
+out_unlock:
+ unlock_page(page);
return result;
}
struct nfs_page *new;
unsigned int len;
- len = nfs_page_length(inode, page);
+ len = nfs_page_length(page);
if (len == 0)
return nfs_return_empty_page(page);
new = nfs_create_request(ctx, inode, page, 0, len);
sigset_t oldset;
rpc_clnt_sigmask(clnt, &oldset);
- lock_kernel();
rpc_execute(&data->task);
- unlock_kernel();
rpc_clnt_sigunmask(clnt, &oldset);
}
return error;
}
+/*
+ * This is the callback from RPC telling us whether a reply was
+ * received or some error occurred (timeout or socket shutdown).
+ */
+int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
+{
+ int status;
+
+ dprintk("%s: %4d, (status %d)\n", __FUNCTION__, task->tk_pid,
+ task->tk_status);
+
+ status = NFS_PROTO(data->inode)->read_done(task, data);
+ if (status != 0)
+ return status;
+
+ nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count);
+
+ if (task->tk_status == -ESTALE) {
+ set_bit(NFS_INO_STALE, &NFS_FLAGS(data->inode));
+ nfs_mark_for_revalidate(data->inode);
+ }
+ spin_lock(&data->inode->i_lock);
+ NFS_I(data->inode)->cache_validity |= NFS_INO_INVALID_ATIME;
+ spin_unlock(&data->inode->i_lock);
+ return 0;
+}
+
+static int nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data)
+{
+ struct nfs_readargs *argp = &data->args;
+ struct nfs_readres *resp = &data->res;
+
+ if (resp->eof || resp->count == argp->count)
+ return 0;
+
+ /* This is a short read! */
+ nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
+ /* Has the server at least made some progress? */
+ if (resp->count == 0)
+ return 0;
+
+ /* Yes, so retry the read at the end of the data */
+ argp->offset += resp->count;
+ argp->pgbase += resp->count;
+ argp->count -= resp->count;
+ rpc_restart_call(task);
+ return -EAGAIN;
+}
+
/*
* Handle a read reply that fills part of a page.
*/
struct nfs_page *req = data->req;
struct page *page = req->wb_page;
- if (likely(task->tk_status >= 0))
- nfs_readpage_truncate_uninitialised_page(data);
- else
- SetPageError(page);
if (nfs_readpage_result(task, data) != 0)
return;
+
+ if (likely(task->tk_status >= 0)) {
+ nfs_readpage_truncate_uninitialised_page(data);
+ if (nfs_readpage_retry(task, data) != 0)
+ return;
+ }
+ if (unlikely(task->tk_status < 0))
+ SetPageError(page);
if (atomic_dec_and_test(&req->wb_complete)) {
if (!PageError(page))
SetPageUptodate(page);
count += base;
for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++)
SetPageUptodate(*pages);
- if (count != 0)
+ if (count == 0)
+ return;
+ /* Was this a short read? */
+ if (data->res.eof || data->res.count == data->args.count)
SetPageUptodate(*pages);
}
-static void nfs_readpage_set_pages_error(struct nfs_read_data *data)
-{
- unsigned int count = data->args.count;
- unsigned int base = data->args.pgbase;
- struct page **pages;
-
- pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
- base &= ~PAGE_CACHE_MASK;
- count += base;
- for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++)
- SetPageError(*pages);
- if (count != 0)
- SetPageError(*pages);
-}
-
/*
* This is the callback from RPC telling us whether a reply was
* received or some error occurred (timeout or socket shutdown).
{
struct nfs_read_data *data = calldata;
+ if (nfs_readpage_result(task, data) != 0)
+ return;
/*
- * Note: nfs_readpage_result may change the values of
+ * Note: nfs_readpage_retry may change the values of
* data->args. In the multi-page case, we therefore need
- * to ensure that we call the next nfs_readpage_set_page_uptodate()
- * first in the multi-page case.
+ * to ensure that we call nfs_readpage_set_pages_uptodate()
+ * first.
*/
if (likely(task->tk_status >= 0)) {
nfs_readpage_truncate_uninitialised_page(data);
nfs_readpage_set_pages_uptodate(data);
- } else
- nfs_readpage_set_pages_error(data);
- if (nfs_readpage_result(task, data) != 0)
- return;
+ if (nfs_readpage_retry(task, data) != 0)
+ return;
+ }
while (!list_empty(&data->pages)) {
struct nfs_page *req = nfs_list_entry(data->pages.next);
.rpc_release = nfs_readdata_release,
};
-/*
- * This is the callback from RPC telling us whether a reply was
- * received or some error occurred (timeout or socket shutdown).
- */
-int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
-{
- struct nfs_readargs *argp = &data->args;
- struct nfs_readres *resp = &data->res;
- int status;
-
- dprintk("NFS: %4d nfs_readpage_result, (status %d)\n",
- task->tk_pid, task->tk_status);
-
- status = NFS_PROTO(data->inode)->read_done(task, data);
- if (status != 0)
- return status;
-
- nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, resp->count);
-
- if (task->tk_status < 0) {
- if (task->tk_status == -ESTALE) {
- set_bit(NFS_INO_STALE, &NFS_FLAGS(data->inode));
- nfs_mark_for_revalidate(data->inode);
- }
- } else if (resp->count < argp->count && !resp->eof) {
- /* This is a short read! */
- nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
- /* Has the server at least made some progress? */
- if (resp->count != 0) {
- /* Yes, so retry the read at the end of the data */
- argp->offset += resp->count;
- argp->pgbase += resp->count;
- argp->count -= resp->count;
- rpc_restart_call(task);
- return -EAGAIN;
- }
- task->tk_status = -EIO;
- }
- spin_lock(&data->inode->i_lock);
- NFS_I(data->inode)->cache_validity |= NFS_INO_INVALID_ATIME;
- spin_unlock(&data->inode->i_lock);
- return 0;
-}
-
/*
* Read a page over NFS.
* We read the page synchronously in the following case:
goto out_error;
if (file == NULL) {
+ error = -EBADF;
ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
if (ctx == NULL)
- return -EBADF;
+ goto out_error;
} else
ctx = get_nfs_open_context((struct nfs_open_context *)
file->private_data);
unsigned int len;
nfs_wb_page(inode, page);
- len = nfs_page_length(inode, page);
+ len = nfs_page_length(page);
if (len == 0)
return nfs_return_empty_page(page);
new = nfs_create_request(desc->ctx, inode, page, 0, len);
#include <linux/smp_lock.h>
#include "delegation.h"
+#include "internal.h"
#include "iostat.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
* Local function declarations
*/
static struct nfs_page * nfs_update_request(struct nfs_open_context*,
- struct inode *,
struct page *,
unsigned int, unsigned int);
+static void nfs_mark_request_dirty(struct nfs_page *req);
static int nfs_wait_on_write_congestion(struct address_space *, int);
static int nfs_wait_on_requests(struct inode *, unsigned long, unsigned int);
-static int nfs_flush_inode(struct inode *inode, unsigned long idx_start,
- unsigned int npages, int how);
+static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how);
static const struct rpc_call_ops nfs_write_partial_ops;
static const struct rpc_call_ops nfs_write_full_ops;
static const struct rpc_call_ops nfs_commit_ops;
- static kmem_cache_t *nfs_wdata_cachep;
+ static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
static mempool_t *nfs_commit_mempool;
struct nfs_write_data *nfs_commit_alloc(void)
{
- struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, SLAB_NOFS);
+ struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
return p;
}
-void nfs_commit_free(struct nfs_write_data *p)
+void nfs_commit_rcu_free(struct rcu_head *head)
{
+ struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_commit_mempool);
}
+void nfs_commit_free(struct nfs_write_data *wdata)
+{
+ call_rcu_bh(&wdata->task.u.tk_rcu, nfs_commit_rcu_free);
+}
+
struct nfs_write_data *nfs_writedata_alloc(size_t len)
{
unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, SLAB_NOFS);
+ struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
return p;
}
-static void nfs_writedata_free(struct nfs_write_data *p)
+static void nfs_writedata_rcu_free(struct rcu_head *head)
{
+ struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_wdata_mempool);
}
+static void nfs_writedata_free(struct nfs_write_data *wdata)
+{
+ call_rcu_bh(&wdata->task.u.tk_rcu, nfs_writedata_rcu_free);
+}
+
void nfs_writedata_release(void *wdata)
{
nfs_writedata_free(wdata);
}
+static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+{
+ struct nfs_page *req = NULL;
+
+ if (PagePrivate(page)) {
+ req = (struct nfs_page *)page_private(page);
+ if (req != NULL)
+ atomic_inc(&req->wb_count);
+ }
+ return req;
+}
+
+static struct nfs_page *nfs_page_find_request(struct page *page)
+{
+ struct nfs_page *req = NULL;
+ spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock;
+
+ spin_lock(req_lock);
+ req = nfs_page_find_request_locked(page);
+ spin_unlock(req_lock);
+ return req;
+}
+
/* Adjust the file length if we're writing beyond the end */
static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
{
*/
static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count)
{
- loff_t end_offs;
-
if (PageUptodate(page))
return;
if (base != 0)
return;
- if (count == PAGE_CACHE_SIZE) {
- SetPageUptodate(page);
- return;
- }
-
- end_offs = i_size_read(page->mapping->host) - 1;
- if (end_offs < 0)
+ if (count != nfs_page_length(page))
return;
- /* Is this the last page? */
- if (page->index != (unsigned long)(end_offs >> PAGE_CACHE_SHIFT))
- return;
- /* This is the last page: set PG_uptodate if we cover the entire
- * extent of the data, then zero the rest of the page.
- */
- if (count == (unsigned int)(end_offs & (PAGE_CACHE_SIZE - 1)) + 1) {
+ if (count != PAGE_CACHE_SIZE)
memclear_highpage_flush(page, count, PAGE_CACHE_SIZE - count);
- SetPageUptodate(page);
- }
+ SetPageUptodate(page);
}
-/*
- * Write a page synchronously.
- * Offset is the data offset within the page.
- */
-static int nfs_writepage_sync(struct nfs_open_context *ctx, struct inode *inode,
- struct page *page, unsigned int offset, unsigned int count,
- int how)
-{
- unsigned int wsize = NFS_SERVER(inode)->wsize;
- int result, written = 0;
- struct nfs_write_data *wdata;
-
- wdata = nfs_writedata_alloc(wsize);
- if (!wdata)
- return -ENOMEM;
-
- wdata->flags = how;
- wdata->cred = ctx->cred;
- wdata->inode = inode;
- wdata->args.fh = NFS_FH(inode);
- wdata->args.context = ctx;
- wdata->args.pages = &page;
- wdata->args.stable = NFS_FILE_SYNC;
- wdata->args.pgbase = offset;
- wdata->args.count = wsize;
- wdata->res.fattr = &wdata->fattr;
- wdata->res.verf = &wdata->verf;
-
- dprintk("NFS: nfs_writepage_sync(%s/%Ld %d@%Ld)\n",
- inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
- count, (long long)(page_offset(page) + offset));
-
- set_page_writeback(page);
- nfs_begin_data_update(inode);
- do {
- if (count < wsize)
- wdata->args.count = count;
- wdata->args.offset = page_offset(page) + wdata->args.pgbase;
-
- result = NFS_PROTO(inode)->write(wdata);
-
- if (result < 0) {
- /* Must mark the page invalid after I/O error */
- ClearPageUptodate(page);
- goto io_error;
- }
- if (result < wdata->args.count)
- printk(KERN_WARNING "NFS: short write, count=%u, result=%d\n",
- wdata->args.count, result);
-
- wdata->args.offset += result;
- wdata->args.pgbase += result;
- written += result;
- count -= result;
- nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, result);
- } while (count);
- /* Update file length */
- nfs_grow_file(page, offset, written);
- /* Set the PG_uptodate flag? */
- nfs_mark_uptodate(page, offset, written);
-
- if (PageError(page))
- ClearPageError(page);
-
-io_error:
- nfs_end_data_update(inode);
- end_page_writeback(page);
- nfs_writedata_free(wdata);
- return written ? written : result;
-}
-
-static int nfs_writepage_async(struct nfs_open_context *ctx,
- struct inode *inode, struct page *page,
+static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
unsigned int offset, unsigned int count)
{
struct nfs_page *req;
+ int ret;
- req = nfs_update_request(ctx, inode, page, offset, count);
- if (IS_ERR(req))
- return PTR_ERR(req);
+ for (;;) {
+ req = nfs_update_request(ctx, page, offset, count);
+ if (!IS_ERR(req))
+ break;
+ ret = PTR_ERR(req);
+ if (ret != -EBUSY)
+ return ret;
+ ret = nfs_wb_page(page->mapping->host, page);
+ if (ret != 0)
+ return ret;
+ }
/* Update file length */
nfs_grow_file(page, offset, count);
/* Set the PG_uptodate flag? */
return 0;
}
+/*
+ * Find an associated nfs write request, and prepare to flush it out
+ * Returns 1 if there was no write request, or if the request was
+ * already tagged by nfs_set_page_dirty.Returns 0 if the request
+ * was not tagged.
+ * May also return an error if the user signalled nfs_wait_on_request().
+ */
+static int nfs_page_mark_flush(struct page *page)
+{
+ struct nfs_page *req;
+ spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock;
+ int ret;
+
+ spin_lock(req_lock);
+ for(;;) {
+ req = nfs_page_find_request_locked(page);
+ if (req == NULL) {
+ spin_unlock(req_lock);
+ return 1;
+ }
+ if (nfs_lock_request_dontget(req))
+ break;
+ /* Note: If we hold the page lock, as is the case in nfs_writepage,
+ * then the call to nfs_lock_request_dontget() will always
+ * succeed provided that someone hasn't already marked the
+ * request as dirty (in which case we don't care).
+ */
+ spin_unlock(req_lock);
+ ret = nfs_wait_on_request(req);
+ nfs_release_request(req);
+ if (ret != 0)
+ return ret;
+ spin_lock(req_lock);
+ }
+ spin_unlock(req_lock);
+ if (test_and_set_bit(PG_FLUSHING, &req->wb_flags) == 0) {
+ nfs_mark_request_dirty(req);
+ set_page_writeback(page);
+ }
+ ret = test_bit(PG_NEED_FLUSH, &req->wb_flags);
+ nfs_unlock_request(req);
+ return ret;
+}
+
/*
* Write an mmapped page to the server.
*/
-int nfs_writepage(struct page *page, struct writeback_control *wbc)
+static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
{
struct nfs_open_context *ctx;
struct inode *inode = page->mapping->host;
- unsigned long end_index;
- unsigned offset = PAGE_CACHE_SIZE;
- loff_t i_size = i_size_read(inode);
- int inode_referenced = 0;
- int priority = wb_priority(wbc);
+ unsigned offset;
int err;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
- /*
- * Note: We need to ensure that we have a reference to the inode
- * if we are to do asynchronous writes. If not, waiting
- * in nfs_wait_on_request() may deadlock with clear_inode().
- *
- * If igrab() fails here, then it is in any case safe to
- * call nfs_wb_page(), since there will be no pending writes.
- */
- if (igrab(inode) != 0)
- inode_referenced = 1;
- end_index = i_size >> PAGE_CACHE_SHIFT;
-
- /* Ensure we've flushed out any previous writes */
- nfs_wb_page_priority(inode, page, priority);
-
- /* easy case */
- if (page->index < end_index)
- goto do_it;
- /* things got complicated... */
- offset = i_size & (PAGE_CACHE_SIZE-1);
-
- /* OK, are we completely out? */
- err = 0; /* potential race with truncate - ignore */
- if (page->index >= end_index+1 || !offset)
+ err = nfs_page_mark_flush(page);
+ if (err <= 0)
+ goto out;
+ err = 0;
+ offset = nfs_page_length(page);
+ if (!offset)
goto out;
-do_it:
+
ctx = nfs_find_open_context(inode, NULL, FMODE_WRITE);
if (ctx == NULL) {
err = -EBADF;
goto out;
}
- lock_kernel();
- if (!IS_SYNC(inode) && inode_referenced) {
- err = nfs_writepage_async(ctx, inode, page, 0, offset);
- if (!wbc->for_writepages)
- nfs_flush_inode(inode, 0, 0, wb_priority(wbc));
- } else {
- err = nfs_writepage_sync(ctx, inode, page, 0,
- offset, priority);
- if (err >= 0) {
- if (err != offset)
- redirty_page_for_writepage(wbc, page);
- err = 0;
- }
- }
- unlock_kernel();
+ err = nfs_writepage_setup(ctx, page, 0, offset);
put_nfs_open_context(ctx);
+ if (err != 0)
+ goto out;
+ err = nfs_page_mark_flush(page);
+ if (err > 0)
+ err = 0;
out:
+ if (!wbc->for_writepages)
+ nfs_flush_mapping(page->mapping, wbc, wb_priority(wbc));
+ return err;
+}
+
+int nfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+ int err;
+
+ err = nfs_writepage_locked(page, wbc);
unlock_page(page);
- if (inode_referenced)
- iput(inode);
return err;
}
return 0;
nfs_wait_on_write_congestion(mapping, 0);
}
- err = nfs_flush_inode(inode, 0, 0, wb_priority(wbc));
+ err = nfs_flush_mapping(mapping, wbc, wb_priority(wbc));
if (err < 0)
goto out;
nfs_add_stats(inode, NFSIOS_WRITEPAGES, err);
- wbc->nr_to_write -= err;
if (!wbc->nonblocking && wbc->sync_mode == WB_SYNC_ALL) {
err = nfs_wait_on_requests(inode, 0, 0);
if (err < 0)
goto out;
}
err = nfs_commit_inode(inode, wb_priority(wbc));
- if (err > 0) {
- wbc->nr_to_write -= err;
+ if (err > 0)
err = 0;
- }
out:
clear_bit(BDI_write_congested, &bdi->state);
wake_up_all(&nfs_write_congestion);
nfsi->change_attr++;
}
SetPagePrivate(req->wb_page);
+ set_page_private(req->wb_page, (unsigned long)req);
nfsi->npages++;
atomic_inc(&req->wb_count);
return 0;
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&nfsi->req_lock);
+ set_page_private(req->wb_page, 0);
ClearPagePrivate(req->wb_page);
radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
nfs_release_request(req);
}
-/*
- * Find a request
- */
-static inline struct nfs_page *
-_nfs_find_request(struct inode *inode, unsigned long index)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
- struct nfs_page *req;
-
- req = (struct nfs_page*)radix_tree_lookup(&nfsi->nfs_page_tree, index);
- if (req)
- atomic_inc(&req->wb_count);
- return req;
-}
-
-static struct nfs_page *
-nfs_find_request(struct inode *inode, unsigned long index)
-{
- struct nfs_page *req;
- struct nfs_inode *nfsi = NFS_I(inode);
-
- spin_lock(&nfsi->req_lock);
- req = _nfs_find_request(inode, index);
- spin_unlock(&nfsi->req_lock);
- return req;
-}
-
/*
* Add a request to the inode's dirty list.
*/
nfs_list_add_request(req, &nfsi->dirty);
nfsi->ndirty++;
spin_unlock(&nfsi->req_lock);
- inc_zone_page_state(req->wb_page, NR_FILE_DIRTY);
- mark_inode_dirty(inode);
+ __mark_inode_dirty(inode, I_DIRTY_PAGES);
+}
+
+static void
+nfs_redirty_request(struct nfs_page *req)
+{
+ clear_bit(PG_FLUSHING, &req->wb_flags);
+ __set_page_dirty_nobuffers(req->wb_page);
}
/*
static inline int
nfs_dirty_request(struct nfs_page *req)
{
- struct nfs_inode *nfsi = NFS_I(req->wb_context->dentry->d_inode);
- return !list_empty(&req->wb_list) && req->wb_list_head == &nfsi->dirty;
+ return test_bit(PG_FLUSHING, &req->wb_flags) == 0;
}
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
nfsi->ncommit++;
spin_unlock(&nfsi->req_lock);
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- mark_inode_dirty(inode);
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
#endif
}
}
-/*
- * nfs_scan_dirty - Scan an inode for dirty requests
- * @inode: NFS inode to scan
- * @dst: destination list
- * @idx_start: lower bound of page->index to scan.
- * @npages: idx_start + npages sets the upper bound to scan.
- *
- * Moves requests from the inode's dirty page list.
- * The requests are *not* checked to ensure that they form a contiguous set.
- */
-static int
-nfs_scan_dirty(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
- int res = 0;
-
- if (nfsi->ndirty != 0) {
- res = nfs_scan_lock_dirty(nfsi, dst, idx_start, npages);
- nfsi->ndirty -= res;
- if ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty))
- printk(KERN_ERR "NFS: desynchronized value of nfs_i.ndirty.\n");
- }
- return res;
-}
-
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
/*
* nfs_scan_commit - Scan an inode for commit requests
* Note: Should always be called with the Page Lock held!
*/
static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx,
- struct inode *inode, struct page *page,
- unsigned int offset, unsigned int bytes)
+ struct page *page, unsigned int offset, unsigned int bytes)
{
- struct nfs_server *server = NFS_SERVER(inode);
+ struct inode *inode = page->mapping->host;
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_page *req, *new = NULL;
unsigned long rqend, end;
end = offset + bytes;
- if (nfs_wait_on_write_congestion(page->mapping, server->flags & NFS_MOUNT_INTR))
+ if (nfs_wait_on_write_congestion(page->mapping, NFS_SERVER(inode)->flags & NFS_MOUNT_INTR))
return ERR_PTR(-ERESTARTSYS);
for (;;) {
/* Loop over all inode entries and see if we find
* A request for the page we wish to update
*/
spin_lock(&nfsi->req_lock);
- req = _nfs_find_request(inode, page->index);
+ req = nfs_page_find_request_locked(page);
if (req) {
if (!nfs_lock_request_dontget(req)) {
int error;
+
spin_unlock(&nfsi->req_lock);
error = nfs_wait_on_request(req);
nfs_release_request(req);
return ERR_PTR(error);
}
spin_unlock(&nfsi->req_lock);
- nfs_mark_request_dirty(new);
return new;
}
spin_unlock(&nfsi->req_lock);
int nfs_flush_incompatible(struct file *file, struct page *page)
{
struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
- struct inode *inode = page->mapping->host;
struct nfs_page *req;
- int status = 0;
+ int do_flush, status;
/*
* Look for a request corresponding to this page. If there
* is one, and it belongs to another file, we flush it out
* Also do the same if we find a request from an existing
* dropped page.
*/
- req = nfs_find_request(inode, page->index);
- if (req) {
- if (req->wb_page != page || ctx != req->wb_context)
- status = nfs_wb_page(inode, page);
+ do {
+ req = nfs_page_find_request(page);
+ if (req == NULL)
+ return 0;
+ do_flush = req->wb_page != page || req->wb_context != ctx
+ || !nfs_dirty_request(req);
nfs_release_request(req);
- }
- return (status < 0) ? status : 0;
+ if (!do_flush)
+ return 0;
+ status = nfs_wb_page(page->mapping->host, page);
+ } while (status == 0);
+ return status;
}
/*
{
struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
struct inode *inode = page->mapping->host;
- struct nfs_page *req;
int status = 0;
nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
file->f_dentry->d_name.name, count,
(long long)(page_offset(page) +offset));
- if (IS_SYNC(inode)) {
- status = nfs_writepage_sync(ctx, inode, page, offset, count, 0);
- if (status > 0) {
- if (offset == 0 && status == PAGE_CACHE_SIZE)
- SetPageUptodate(page);
- return 0;
- }
- return status;
- }
-
/* If we're not using byte range locks, and we know the page
* is entirely in cache, it may be more efficient to avoid
* fragmenting write requests.
*/
if (PageUptodate(page) && inode->i_flock == NULL && !(file->f_mode & O_SYNC)) {
- loff_t end_offs = i_size_read(inode) - 1;
- unsigned long end_index = end_offs >> PAGE_CACHE_SHIFT;
-
- count += offset;
+ count = max(count + offset, nfs_page_length(page));
offset = 0;
- if (unlikely(end_offs < 0)) {
- /* Do nothing */
- } else if (page->index == end_index) {
- unsigned int pglen;
- pglen = (unsigned int)(end_offs & (PAGE_CACHE_SIZE-1)) + 1;
- if (count < pglen)
- count = pglen;
- } else if (page->index < end_index)
- count = PAGE_CACHE_SIZE;
}
- /*
- * Try to find an NFS request corresponding to this page
- * and update it.
- * If the existing request cannot be updated, we must flush
- * it out now.
- */
- do {
- req = nfs_update_request(ctx, inode, page, offset, count);
- status = (IS_ERR(req)) ? PTR_ERR(req) : 0;
- if (status != -EBUSY)
- break;
- /* Request could not be updated. Flush it out and try again */
- status = nfs_wb_page(inode, page);
- } while (status >= 0);
- if (status < 0)
- goto done;
-
- status = 0;
+ status = nfs_writepage_setup(ctx, page, offset, count);
+ __set_page_dirty_nobuffers(page);
- /* Update file length */
- nfs_grow_file(page, offset, count);
- /* Set the PG_uptodate flag? */
- nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
- nfs_unlock_request(req);
-done:
dprintk("NFS: nfs_updatepage returns %d (isize %Ld)\n",
status, (long long)i_size_read(inode));
if (status < 0)
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
if (!PageError(req->wb_page)) {
if (NFS_NEED_RESCHED(req)) {
- nfs_mark_request_dirty(req);
+ nfs_redirty_request(req);
goto out;
} else if (NFS_NEED_COMMIT(req)) {
nfs_mark_request_commit(req);
sigset_t oldset;
rpc_clnt_sigmask(clnt, &oldset);
- lock_kernel();
rpc_execute(&data->task);
- unlock_kernel();
rpc_clnt_sigunmask(clnt, &oldset);
}
atomic_set(&req->wb_complete, requests);
ClearPageError(page);
- set_page_writeback(page);
offset = 0;
nbytes = req->wb_bytes;
do {
while (!list_empty(&list)) {
data = list_entry(list.next, struct nfs_write_data, pages);
list_del(&data->pages);
- nfs_writedata_free(data);
+ nfs_writedata_release(data);
}
- nfs_mark_request_dirty(req);
+ nfs_redirty_request(req);
nfs_clear_page_writeback(req);
return -ENOMEM;
}
nfs_list_remove_request(req);
nfs_list_add_request(req, &data->pages);
ClearPageError(req->wb_page);
- set_page_writeback(req->wb_page);
*pages++ = req->wb_page;
count += req->wb_bytes;
}
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- nfs_mark_request_dirty(req);
+ nfs_redirty_request(req);
nfs_clear_page_writeback(req);
}
return -ENOMEM;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- nfs_mark_request_dirty(req);
+ nfs_redirty_request(req);
nfs_clear_page_writeback(req);
}
return error;
}
/* We have a mismatch. Write the page again */
dprintk(" mismatch\n");
- nfs_mark_request_dirty(req);
+ nfs_redirty_request(req);
next:
nfs_clear_page_writeback(req);
}
}
#endif
-static int nfs_flush_inode(struct inode *inode, unsigned long idx_start,
- unsigned int npages, int how)
+static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how)
{
- struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_inode *nfsi = NFS_I(mapping->host);
LIST_HEAD(head);
- int res;
+ long res;
spin_lock(&nfsi->req_lock);
- res = nfs_scan_dirty(inode, &head, idx_start, npages);
+ res = nfs_scan_dirty(mapping, wbc, &head);
spin_unlock(&nfsi->req_lock);
if (res) {
- int error = nfs_flush_list(inode, &head, res, how);
+ int error = nfs_flush_list(mapping->host, &head, res, how);
if (error < 0)
return error;
}
}
#endif
-int nfs_sync_inode_wait(struct inode *inode, unsigned long idx_start,
- unsigned int npages, int how)
+long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how)
{
+ struct inode *inode = mapping->host;
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long idx_start, idx_end;
+ unsigned int npages = 0;
LIST_HEAD(head);
int nocommit = how & FLUSH_NOCOMMIT;
- int pages, ret;
-
+ long pages, ret;
+
+ /* FIXME */
+ if (wbc->range_cyclic)
+ idx_start = 0;
+ else {
+ idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
+ idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ if (idx_end > idx_start) {
+ unsigned long l_npages = 1 + idx_end - idx_start;
+ npages = l_npages;
+ if (sizeof(npages) != sizeof(l_npages) &&
+ (unsigned long)npages != l_npages)
+ npages = 0;
+ }
+ }
how &= ~FLUSH_NOCOMMIT;
spin_lock(&nfsi->req_lock);
do {
+ wbc->pages_skipped = 0;
ret = nfs_wait_on_requests_locked(inode, idx_start, npages);
if (ret != 0)
continue;
- pages = nfs_scan_dirty(inode, &head, idx_start, npages);
+ pages = nfs_scan_dirty(mapping, wbc, &head);
if (pages != 0) {
spin_unlock(&nfsi->req_lock);
- if (how & FLUSH_INVALIDATE)
+ if (how & FLUSH_INVALIDATE) {
nfs_cancel_dirty_list(&head);
- else
+ ret = pages;
+ } else
ret = nfs_flush_list(inode, &head, pages, how);
spin_lock(&nfsi->req_lock);
continue;
}
+ if (wbc->pages_skipped != 0)
+ continue;
if (nocommit)
break;
pages = nfs_scan_commit(inode, &head, idx_start, npages);
- if (pages == 0)
+ if (pages == 0) {
+ if (wbc->pages_skipped != 0)
+ continue;
break;
+ }
if (how & FLUSH_INVALIDATE) {
spin_unlock(&nfsi->req_lock);
nfs_cancel_commit_list(&head);
+ ret = pages;
spin_lock(&nfsi->req_lock);
continue;
}
return ret;
}
+/*
+ * flush the inode to disk.
+ */
+int nfs_wb_all(struct inode *inode)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct writeback_control wbc = {
+ .bdi = mapping->backing_dev_info,
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = LONG_MAX,
+ .for_writepages = 1,
+ .range_cyclic = 1,
+ };
+ int ret;
+
+ ret = generic_writepages(mapping, &wbc);
+ if (ret < 0)
+ goto out;
+ ret = nfs_sync_mapping_wait(mapping, &wbc, 0);
+ if (ret >= 0)
+ return 0;
+out:
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ return ret;
+}
+
+int nfs_sync_mapping_range(struct address_space *mapping, loff_t range_start, loff_t range_end, int how)
+{
+ struct writeback_control wbc = {
+ .bdi = mapping->backing_dev_info,
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = LONG_MAX,
+ .range_start = range_start,
+ .range_end = range_end,
+ .for_writepages = 1,
+ };
+ int ret;
+
+ if (!(how & FLUSH_NOWRITEPAGE)) {
+ ret = generic_writepages(mapping, &wbc);
+ if (ret < 0)
+ goto out;
+ }
+ ret = nfs_sync_mapping_wait(mapping, &wbc, how);
+ if (ret >= 0)
+ return 0;
+out:
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ return ret;
+}
+
+int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
+{
+ loff_t range_start = page_offset(page);
+ loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
+ struct writeback_control wbc = {
+ .bdi = page->mapping->backing_dev_info,
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = LONG_MAX,
+ .range_start = range_start,
+ .range_end = range_end,
+ };
+ int ret;
+
+ BUG_ON(!PageLocked(page));
+ if (!(how & FLUSH_NOWRITEPAGE) && clear_page_dirty_for_io(page)) {
+ ret = nfs_writepage_locked(page, &wbc);
+ if (ret < 0)
+ goto out;
+ }
+ ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
+ if (ret >= 0)
+ return 0;
+out:
+ __mark_inode_dirty(inode, I_DIRTY_PAGES);
+ return ret;
+}
+
+/*
+ * Write back all requests on one page - we do this before reading it.
+ */
+int nfs_wb_page(struct inode *inode, struct page* page)
+{
+ return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
+}
+
+int nfs_set_page_dirty(struct page *page)
+{
+ struct nfs_page *req;
+
+ req = nfs_page_find_request(page);
+ if (req != NULL) {
+ /* Mark any existing write requests for flushing */
+ set_bit(PG_NEED_FLUSH, &req->wb_flags);
+ nfs_release_request(req);
+ }
+ return __set_page_dirty_nobuffers(page);
+}
+
+
int __init nfs_init_writepagecache(void)
{
nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
#include <linux/timer.h>
#include <linux/sunrpc/types.h>
+#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
union {
struct work_struct tk_work; /* Async task work queue */
struct rpc_wait tk_wait; /* RPC wait */
+ struct rcu_head tk_rcu; /* for task deletion */
} u;
unsigned short tk_timeouts; /* maj timeouts */
} while (0)
#define RPC_IS_ACTIVATED(t) (test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate))
-#define rpc_set_active(t) (set_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate))
-#define rpc_clear_active(t) \
- do { \
- smp_mb__before_clear_bit(); \
- clear_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate); \
- smp_mb__after_clear_bit(); \
- } while(0)
/*
* Task priorities.
#ifndef RPC_DEBUG
# define RPC_WAITQ_INIT(var,qname) { \
- .lock = SPIN_LOCK_UNLOCKED, \
+ .lock = __SPIN_LOCK_UNLOCKED(var.lock), \
.tasks = { \
[0] = LIST_HEAD_INIT(var.tasks[0]), \
[1] = LIST_HEAD_INIT(var.tasks[1]), \
}
#else
# define RPC_WAITQ_INIT(var,qname) { \
- .lock = SPIN_LOCK_UNLOCKED, \
+ .lock = __SPIN_LOCK_UNLOCKED(var.lock), \
.tasks = { \
[0] = LIST_HEAD_INIT(var.tasks[0]), \
[1] = LIST_HEAD_INIT(var.tasks[1]), \
void rpc_init_task(struct rpc_task *task, struct rpc_clnt *clnt,
int flags, const struct rpc_call_ops *ops,
void *data);
+void rpc_put_task(struct rpc_task *);
void rpc_release_task(struct rpc_task *);
void rpc_exit_task(struct rpc_task *);
+void rpc_release_calldata(const struct rpc_call_ops *, void *);
void rpc_killall_tasks(struct rpc_clnt *);
int rpc_execute(struct rpc_task *);
void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *);
#define RPC_BUFFER_MAXSIZE (2048)
#define RPC_BUFFER_POOLSIZE (8)
#define RPC_TASK_POOLSIZE (8)
- static kmem_cache_t *rpc_task_slabp __read_mostly;
- static kmem_cache_t *rpc_buffer_slabp __read_mostly;
+ static struct kmem_cache *rpc_task_slabp __read_mostly;
+ static struct kmem_cache *rpc_buffer_slabp __read_mostly;
static mempool_t *rpc_task_mempool __read_mostly;
static mempool_t *rpc_buffer_mempool __read_mostly;
return 0;
}
+static void rpc_set_active(struct rpc_task *task)
+{
+ if (test_and_set_bit(RPC_TASK_ACTIVE, &task->tk_runstate) != 0)
+ return;
+ spin_lock(&rpc_sched_lock);
+#ifdef RPC_DEBUG
+ task->tk_magic = RPC_TASK_MAGIC_ID;
+ task->tk_pid = rpc_task_id++;
+#endif
+ /* Add to global list of all tasks */
+ list_add_tail(&task->tk_task, &all_tasks);
+ spin_unlock(&rpc_sched_lock);
+}
+
/*
* Mark an RPC call as having completed by clearing the 'active' bit
*/
-static inline void rpc_mark_complete_task(struct rpc_task *task)
+static void rpc_mark_complete_task(struct rpc_task *task)
{
- rpc_clear_active(task);
+ smp_mb__before_clear_bit();
+ clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
+ smp_mb__after_clear_bit();
wake_up_bit(&task->tk_runstate, RPC_TASK_ACTIVE);
}
*/
static void rpc_make_runnable(struct rpc_task *task)
{
- int do_ret;
-
BUG_ON(task->tk_timeout_fn);
- do_ret = rpc_test_and_set_running(task);
rpc_clear_queued(task);
- if (do_ret)
+ if (rpc_test_and_set_running(task))
return;
+ /* We might have raced */
+ if (RPC_IS_QUEUED(task)) {
+ rpc_clear_running(task);
+ return;
+ }
if (RPC_IS_ASYNC(task)) {
int status;
return;
}
- /* Mark the task as being activated if so needed */
- rpc_set_active(task);
-
__rpc_add_wait_queue(q, task);
BUG_ON(task->tk_callback != NULL);
void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
rpc_action action, rpc_action timer)
{
+ /* Mark the task as being activated if so needed */
+ rpc_set_active(task);
+
/*
* Protect the queue operations.
*/
*/
void rpc_wake_up_task(struct rpc_task *task)
{
+ rcu_read_lock_bh();
if (rpc_start_wakeup(task)) {
if (RPC_IS_QUEUED(task)) {
struct rpc_wait_queue *queue = task->u.tk_wait.rpc_waitq;
- spin_lock_bh(&queue->lock);
+ /* Note: we're already in a bh-safe context */
+ spin_lock(&queue->lock);
__rpc_do_wake_up_task(task);
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
}
rpc_finish_wakeup(task);
}
+ rcu_read_unlock_bh();
}
/*
struct rpc_task *task = NULL;
dprintk("RPC: wake_up_next(%p \"%s\")\n", queue, rpc_qname(queue));
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
if (RPC_IS_PRIORITY(queue))
task = __rpc_wake_up_next_priority(queue);
else {
task_for_first(task, &queue->tasks[0])
__rpc_wake_up_task(task);
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
return task;
}
struct rpc_task *task, *next;
struct list_head *head;
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
head = &queue->tasks[queue->maxpriority];
for (;;) {
list_for_each_entry_safe(task, next, head, u.tk_wait.list)
break;
head--;
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
}
/**
struct rpc_task *task, *next;
struct list_head *head;
- spin_lock_bh(&queue->lock);
+ rcu_read_lock_bh();
+ spin_lock(&queue->lock);
head = &queue->tasks[queue->maxpriority];
for (;;) {
list_for_each_entry_safe(task, next, head, u.tk_wait.list) {
break;
head--;
}
- spin_unlock_bh(&queue->lock);
+ spin_unlock(&queue->lock);
+ rcu_read_unlock_bh();
}
static void __rpc_atrun(struct rpc_task *task)
*/
static void rpc_prepare_task(struct rpc_task *task)
{
+ lock_kernel();
task->tk_ops->rpc_call_prepare(task, task->tk_calldata);
+ unlock_kernel();
}
/*
{
task->tk_action = NULL;
if (task->tk_ops->rpc_call_done != NULL) {
+ lock_kernel();
task->tk_ops->rpc_call_done(task, task->tk_calldata);
+ unlock_kernel();
if (task->tk_action != NULL) {
WARN_ON(RPC_ASSASSINATED(task));
/* Always release the RPC slot and buffer memory */
}
EXPORT_SYMBOL(rpc_exit_task);
+void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
+{
+ if (ops->rpc_release != NULL) {
+ lock_kernel();
+ ops->rpc_release(calldata);
+ unlock_kernel();
+ }
+}
+
/*
* This is the RPC `scheduler' (or rather, the finite state machine).
*/
*/
save_callback=task->tk_callback;
task->tk_callback=NULL;
- lock_kernel();
save_callback(task);
- unlock_kernel();
}
/*
if (!RPC_IS_QUEUED(task)) {
if (task->tk_action == NULL)
break;
- lock_kernel();
task->tk_action(task);
- unlock_kernel();
}
/*
}
dprintk("RPC: %4d, return %d, status %d\n", task->tk_pid, status, task->tk_status);
- /* Wake up anyone who is waiting for task completion */
- rpc_mark_complete_task(task);
/* Release all resources associated with the task */
rpc_release_task(task);
return status;
task->tk_flags |= RPC_TASK_NOINTR;
}
-#ifdef RPC_DEBUG
- task->tk_magic = RPC_TASK_MAGIC_ID;
- task->tk_pid = rpc_task_id++;
-#endif
- /* Add to global list of all tasks */
- spin_lock(&rpc_sched_lock);
- list_add_tail(&task->tk_task, &all_tasks);
- spin_unlock(&rpc_sched_lock);
-
BUG_ON(task->tk_ops == NULL);
/* starting timestamp */
return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
}
-static void rpc_free_task(struct rpc_task *task)
+static void rpc_free_task(struct rcu_head *rcu)
{
+ struct rpc_task *task = container_of(rcu, struct rpc_task, u.tk_rcu);
dprintk("RPC: %4d freeing task\n", task->tk_pid);
mempool_free(task, rpc_task_mempool);
}
goto out;
}
-void rpc_release_task(struct rpc_task *task)
+
+void rpc_put_task(struct rpc_task *task)
{
const struct rpc_call_ops *tk_ops = task->tk_ops;
void *calldata = task->tk_calldata;
+ if (!atomic_dec_and_test(&task->tk_count))
+ return;
+ /* Release resources */
+ if (task->tk_rqstp)
+ xprt_release(task);
+ if (task->tk_msg.rpc_cred)
+ rpcauth_unbindcred(task);
+ if (task->tk_client) {
+ rpc_release_client(task->tk_client);
+ task->tk_client = NULL;
+ }
+ if (task->tk_flags & RPC_TASK_DYNAMIC)
+ call_rcu_bh(&task->u.tk_rcu, rpc_free_task);
+ rpc_release_calldata(tk_ops, calldata);
+}
+EXPORT_SYMBOL(rpc_put_task);
+
+void rpc_release_task(struct rpc_task *task)
+{
#ifdef RPC_DEBUG
BUG_ON(task->tk_magic != RPC_TASK_MAGIC_ID);
#endif
- if (!atomic_dec_and_test(&task->tk_count))
- return;
dprintk("RPC: %4d release task\n", task->tk_pid);
/* Remove from global task list */
/* Synchronously delete any running timer */
rpc_delete_timer(task);
- /* Release resources */
- if (task->tk_rqstp)
- xprt_release(task);
- if (task->tk_msg.rpc_cred)
- rpcauth_unbindcred(task);
- if (task->tk_client) {
- rpc_release_client(task->tk_client);
- task->tk_client = NULL;
- }
-
#ifdef RPC_DEBUG
task->tk_magic = 0;
#endif
- if (task->tk_flags & RPC_TASK_DYNAMIC)
- rpc_free_task(task);
- if (tk_ops->rpc_release)
- tk_ops->rpc_release(calldata);
+ /* Wake up anyone who is waiting for task completion */
+ rpc_mark_complete_task(task);
+
+ rpc_put_task(task);
}
/**
struct rpc_task *task;
task = rpc_new_task(clnt, flags, ops, data);
if (task == NULL) {
- if (ops->rpc_release != NULL)
- ops->rpc_release(data);
+ rpc_release_calldata(ops, data);
return ERR_PTR(-ENOMEM);
}
atomic_inc(&task->tk_count);
unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;
+/*
+ * We can register our own files under /proc/sys/sunrpc by
+ * calling register_sysctl_table() again. The files in that
+ * directory become the union of all files registered there.
+ *
+ * We simply need to make sure that we don't collide with
+ * someone else's file names!
+ */
+
+#ifdef RPC_DEBUG
+
+static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
+static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;
+static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT;
+static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT;
+
+static struct ctl_table_header *sunrpc_table_header;
+
+/*
+ * FIXME: changing the UDP slot table size should also resize the UDP
+ * socket buffers for existing UDP transports
+ */
+static ctl_table xs_tunables_table[] = {
+ {
+ .ctl_name = CTL_SLOTTABLE_UDP,
+ .procname = "udp_slot_table_entries",
+ .data = &xprt_udp_slot_table_entries,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &min_slot_table_size,
+ .extra2 = &max_slot_table_size
+ },
+ {
+ .ctl_name = CTL_SLOTTABLE_TCP,
+ .procname = "tcp_slot_table_entries",
+ .data = &xprt_tcp_slot_table_entries,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &min_slot_table_size,
+ .extra2 = &max_slot_table_size
+ },
+ {
+ .ctl_name = CTL_MIN_RESVPORT,
+ .procname = "min_resvport",
+ .data = &xprt_min_resvport,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &xprt_min_resvport_limit,
+ .extra2 = &xprt_max_resvport_limit
+ },
+ {
+ .ctl_name = CTL_MAX_RESVPORT,
+ .procname = "max_resvport",
+ .data = &xprt_max_resvport,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &xprt_min_resvport_limit,
+ .extra2 = &xprt_max_resvport_limit
+ },
+ {
+ .ctl_name = 0,
+ },
+};
+
+static ctl_table sunrpc_table[] = {
+ {
+ .ctl_name = CTL_SUNRPC,
+ .procname = "sunrpc",
+ .mode = 0555,
+ .child = xs_tunables_table
+ },
+ {
+ .ctl_name = 0,
+ },
+};
+
+#endif
+
/*
* How many times to try sending a request on a socket before waiting
* for the socket buffer to clear.
}
#endif
+struct sock_xprt {
+ struct rpc_xprt xprt;
+
+ /*
+ * Network layer
+ */
+ struct socket * sock;
+ struct sock * inet;
+
+ /*
+ * State of TCP reply receive
+ */
+ __be32 tcp_fraghdr,
+ tcp_xid;
+
+ u32 tcp_offset,
+ tcp_reclen;
+
+ unsigned long tcp_copied,
+ tcp_flags;
+
+ /*
+ * Connection of transports
+ */
+ struct delayed_work connect_worker;
+ unsigned short port;
+
+ /*
+ * UDP socket buffer size parameters
+ */
+ size_t rcvsize,
+ sndsize;
+
+ /*
+ * Saved socket callback addresses
+ */
+ void (*old_data_ready)(struct sock *, int);
+ void (*old_state_change)(struct sock *);
+ void (*old_write_space)(struct sock *);
+};
+
+/*
+ * TCP receive state flags
+ */
+#define TCP_RCV_LAST_FRAG (1UL << 0)
+#define TCP_RCV_COPY_FRAGHDR (1UL << 1)
+#define TCP_RCV_COPY_XID (1UL << 2)
+#define TCP_RCV_COPY_DATA (1UL << 3)
+
static void xs_format_peer_addresses(struct rpc_xprt *xprt)
{
struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
#define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
-static inline int xs_send_head(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, unsigned int len)
+static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more)
{
- struct kvec iov = {
- .iov_base = xdr->head[0].iov_base + base,
- .iov_len = len - base,
- };
struct msghdr msg = {
.msg_name = addr,
.msg_namelen = addrlen,
- .msg_flags = XS_SENDMSG_FLAGS,
+ .msg_flags = XS_SENDMSG_FLAGS | (more ? MSG_MORE : 0),
+ };
+ struct kvec iov = {
+ .iov_base = vec->iov_base + base,
+ .iov_len = vec->iov_len - base,
};
- if (xdr->len > len)
- msg.msg_flags |= MSG_MORE;
-
- if (likely(iov.iov_len))
+ if (iov.iov_len != 0)
return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}
-static int xs_send_tail(struct socket *sock, struct xdr_buf *xdr, unsigned int base, unsigned int len)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
{
- struct kvec iov = {
- .iov_base = xdr->tail[0].iov_base + base,
- .iov_len = len - base,
- };
- struct msghdr msg = {
- .msg_flags = XS_SENDMSG_FLAGS,
- };
+ struct page **ppage;
+ unsigned int remainder;
+ int err, sent = 0;
+
+ remainder = xdr->page_len - base;
+ base += xdr->page_base;
+ ppage = xdr->pages + (base >> PAGE_SHIFT);
+ base &= ~PAGE_MASK;
+ for(;;) {
+ unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
+ int flags = XS_SENDMSG_FLAGS;
- return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
+ remainder -= len;
+ if (remainder != 0 || more)
+ flags |= MSG_MORE;
+ err = sock->ops->sendpage(sock, *ppage, base, len, flags);
+ if (remainder == 0 || err != len)
+ break;
+ sent += err;
+ ppage++;
+ base = 0;
+ }
+ if (sent == 0)
+ return err;
+ if (err > 0)
+ sent += err;
+ return sent;
}
/**
* @base: starting position in the buffer
*
*/
-static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
{
- struct page **ppage = xdr->pages;
- unsigned int len, pglen = xdr->page_len;
- int err, ret = 0;
+ unsigned int remainder = xdr->len - base;
+ int err, sent = 0;
if (unlikely(!sock))
return -ENOTCONN;
clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+ if (base != 0) {
+ addr = NULL;
+ addrlen = 0;
+ }
- len = xdr->head[0].iov_len;
- if (base < len || (addr != NULL && base == 0)) {
- err = xs_send_head(sock, addr, addrlen, xdr, base, len);
- if (ret == 0)
- ret = err;
- else if (err > 0)
- ret += err;
- if (err != (len - base))
+ if (base < xdr->head[0].iov_len || addr != NULL) {
+ unsigned int len = xdr->head[0].iov_len - base;
+ remainder -= len;
+ err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
+ if (remainder == 0 || err != len)
goto out;
+ sent += err;
base = 0;
} else
- base -= len;
-
- if (unlikely(pglen == 0))
- goto copy_tail;
- if (unlikely(base >= pglen)) {
- base -= pglen;
- goto copy_tail;
- }
- if (base || xdr->page_base) {
- pglen -= base;
- base += xdr->page_base;
- ppage += base >> PAGE_CACHE_SHIFT;
- base &= ~PAGE_CACHE_MASK;
- }
-
- do {
- int flags = XS_SENDMSG_FLAGS;
-
- len = PAGE_CACHE_SIZE;
- if (base)
- len -= base;
- if (pglen < len)
- len = pglen;
-
- if (pglen != len || xdr->tail[0].iov_len != 0)
- flags |= MSG_MORE;
+ base -= xdr->head[0].iov_len;
- err = kernel_sendpage(sock, *ppage, base, len, flags);
- if (ret == 0)
- ret = err;
- else if (err > 0)
- ret += err;
- if (err != len)
+ if (base < xdr->page_len) {
+ unsigned int len = xdr->page_len - base;
+ remainder -= len;
+ err = xs_send_pagedata(sock, xdr, base, remainder != 0);
+ if (remainder == 0 || err != len)
goto out;
+ sent += err;
base = 0;
- ppage++;
- } while ((pglen -= len) != 0);
-copy_tail:
- len = xdr->tail[0].iov_len;
- if (base < len) {
- err = xs_send_tail(sock, xdr, base, len);
- if (ret == 0)
- ret = err;
- else if (err > 0)
- ret += err;
- }
+ } else
+ base -= xdr->page_len;
+
+ if (base >= xdr->tail[0].iov_len)
+ return sent;
+ err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
out:
- return ret;
+ if (sent == 0)
+ return err;
+ if (err > 0)
+ sent += err;
+ return sent;
}
/**
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
dprintk("RPC: %4d xmit incomplete (%u left of %u)\n",
task->tk_pid, req->rq_slen - req->rq_bytes_sent,
req->rq_slen);
- if (test_bit(SOCK_ASYNC_NOSPACE, &xprt->sock->flags)) {
+ if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
/* Protect against races with write_space */
spin_lock_bh(&xprt->transport_lock);
/* Don't race with disconnect */
if (!xprt_connected(xprt))
task->tk_status = -ENOTCONN;
- else if (test_bit(SOCK_NOSPACE, &xprt->sock->flags))
+ else if (test_bit(SOCK_NOSPACE, &transport->sock->flags))
xprt_wait_for_buffer_space(task);
spin_unlock_bh(&xprt->transport_lock);
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status;
req->rq_svec->iov_len);
req->rq_xtime = jiffies;
- status = xs_sendpages(xprt->sock, (struct sockaddr *) &xprt->addr,
- xprt->addrlen, xdr, req->rq_bytes_sent);
+ status = xs_sendpages(transport->sock,
+ (struct sockaddr *) &xprt->addr,
+ xprt->addrlen, xdr,
+ req->rq_bytes_sent);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
{
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
int status, retry = 0;
* called sendmsg(). */
while (1) {
req->rq_xtime = jiffies;
- status = xs_sendpages(xprt->sock, NULL, 0, xdr,
- req->rq_bytes_sent);
+ status = xs_sendpages(transport->sock,
+ NULL, 0, xdr, req->rq_bytes_sent);
dprintk("RPC: xs_tcp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
*/
static void xs_close(struct rpc_xprt *xprt)
{
- struct socket *sock = xprt->sock;
- struct sock *sk = xprt->inet;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct socket *sock = transport->sock;
+ struct sock *sk = transport->inet;
if (!sk)
goto clear_close_wait;
dprintk("RPC: xs_close xprt %p\n", xprt);
write_lock_bh(&sk->sk_callback_lock);
- xprt->inet = NULL;
- xprt->sock = NULL;
+ transport->inet = NULL;
+ transport->sock = NULL;
sk->sk_user_data = NULL;
- sk->sk_data_ready = xprt->old_data_ready;
- sk->sk_state_change = xprt->old_state_change;
- sk->sk_write_space = xprt->old_write_space;
+ sk->sk_data_ready = transport->old_data_ready;
+ sk->sk_state_change = transport->old_state_change;
+ sk->sk_write_space = transport->old_write_space;
write_unlock_bh(&sk->sk_callback_lock);
sk->sk_no_check = 0;
*/
static void xs_destroy(struct rpc_xprt *xprt)
{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+
dprintk("RPC: xs_destroy xprt %p\n", xprt);
- cancel_delayed_work(&xprt->connect_worker);
+ cancel_delayed_work(&transport->connect_worker);
flush_scheduled_work();
xprt_disconnect(xprt);
xs_close(xprt);
xs_free_peer_addresses(xprt);
kfree(xprt->slot);
+ kfree(xprt);
}
static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
read_unlock(&sk->sk_callback_lock);
}
-static inline size_t xs_tcp_copy_data(skb_reader_t *desc, void *p, size_t len)
-{
- if (len > desc->count)
- len = desc->count;
- if (skb_copy_bits(desc->skb, desc->offset, p, len)) {
- dprintk("RPC: failed to copy %zu bytes from skb. %zu bytes remain\n",
- len, desc->count);
- return 0;
- }
- desc->offset += len;
- desc->count -= len;
- dprintk("RPC: copied %zu bytes from skb. %zu bytes remain\n",
- len, desc->count);
- return len;
-}
-
-static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, skb_reader_t *desc)
+static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
size_t len, used;
char *p;
- p = ((char *) &xprt->tcp_recm) + xprt->tcp_offset;
- len = sizeof(xprt->tcp_recm) - xprt->tcp_offset;
- used = xs_tcp_copy_data(desc, p, len);
- xprt->tcp_offset += used;
+ p = ((char *) &transport->tcp_fraghdr) + transport->tcp_offset;
+ len = sizeof(transport->tcp_fraghdr) - transport->tcp_offset;
+ used = xdr_skb_read_bits(desc, p, len);
+ transport->tcp_offset += used;
if (used != len)
return;
- xprt->tcp_reclen = ntohl(xprt->tcp_recm);
- if (xprt->tcp_reclen & RPC_LAST_STREAM_FRAGMENT)
- xprt->tcp_flags |= XPRT_LAST_FRAG;
+ transport->tcp_reclen = ntohl(transport->tcp_fraghdr);
+ if (transport->tcp_reclen & RPC_LAST_STREAM_FRAGMENT)
+ transport->tcp_flags |= TCP_RCV_LAST_FRAG;
else
- xprt->tcp_flags &= ~XPRT_LAST_FRAG;
- xprt->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK;
+ transport->tcp_flags &= ~TCP_RCV_LAST_FRAG;
+ transport->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK;
- xprt->tcp_flags &= ~XPRT_COPY_RECM;
- xprt->tcp_offset = 0;
+ transport->tcp_flags &= ~TCP_RCV_COPY_FRAGHDR;
+ transport->tcp_offset = 0;
/* Sanity check of the record length */
- if (unlikely(xprt->tcp_reclen < 4)) {
+ if (unlikely(transport->tcp_reclen < 4)) {
dprintk("RPC: invalid TCP record fragment length\n");
xprt_disconnect(xprt);
return;
}
dprintk("RPC: reading TCP record fragment of length %d\n",
- xprt->tcp_reclen);
+ transport->tcp_reclen);
}
-static void xs_tcp_check_recm(struct rpc_xprt *xprt)
+static void xs_tcp_check_fraghdr(struct sock_xprt *transport)
{
- dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u, tcp_flags = %lx\n",
- xprt, xprt->tcp_copied, xprt->tcp_offset, xprt->tcp_reclen, xprt->tcp_flags);
- if (xprt->tcp_offset == xprt->tcp_reclen) {
- xprt->tcp_flags |= XPRT_COPY_RECM;
- xprt->tcp_offset = 0;
- if (xprt->tcp_flags & XPRT_LAST_FRAG) {
- xprt->tcp_flags &= ~XPRT_COPY_DATA;
- xprt->tcp_flags |= XPRT_COPY_XID;
- xprt->tcp_copied = 0;
+ if (transport->tcp_offset == transport->tcp_reclen) {
+ transport->tcp_flags |= TCP_RCV_COPY_FRAGHDR;
+ transport->tcp_offset = 0;
+ if (transport->tcp_flags & TCP_RCV_LAST_FRAG) {
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
+ transport->tcp_flags |= TCP_RCV_COPY_XID;
+ transport->tcp_copied = 0;
}
}
}
-static inline void xs_tcp_read_xid(struct rpc_xprt *xprt, skb_reader_t *desc)
+static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
size_t len, used;
char *p;
- len = sizeof(xprt->tcp_xid) - xprt->tcp_offset;
+ len = sizeof(transport->tcp_xid) - transport->tcp_offset;
dprintk("RPC: reading XID (%Zu bytes)\n", len);
- p = ((char *) &xprt->tcp_xid) + xprt->tcp_offset;
- used = xs_tcp_copy_data(desc, p, len);
- xprt->tcp_offset += used;
+ p = ((char *) &transport->tcp_xid) + transport->tcp_offset;
+ used = xdr_skb_read_bits(desc, p, len);
+ transport->tcp_offset += used;
if (used != len)
return;
- xprt->tcp_flags &= ~XPRT_COPY_XID;
- xprt->tcp_flags |= XPRT_COPY_DATA;
- xprt->tcp_copied = 4;
+ transport->tcp_flags &= ~TCP_RCV_COPY_XID;
+ transport->tcp_flags |= TCP_RCV_COPY_DATA;
+ transport->tcp_copied = 4;
dprintk("RPC: reading reply for XID %08x\n",
- ntohl(xprt->tcp_xid));
- xs_tcp_check_recm(xprt);
+ ntohl(transport->tcp_xid));
+ xs_tcp_check_fraghdr(transport);
}
-static inline void xs_tcp_read_request(struct rpc_xprt *xprt, skb_reader_t *desc)
+static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct rpc_rqst *req;
struct xdr_buf *rcvbuf;
size_t len;
/* Find and lock the request corresponding to this xid */
spin_lock(&xprt->transport_lock);
- req = xprt_lookup_rqst(xprt, xprt->tcp_xid);
+ req = xprt_lookup_rqst(xprt, transport->tcp_xid);
if (!req) {
- xprt->tcp_flags &= ~XPRT_COPY_DATA;
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
dprintk("RPC: XID %08x request not found!\n",
- ntohl(xprt->tcp_xid));
+ ntohl(transport->tcp_xid));
spin_unlock(&xprt->transport_lock);
return;
}
rcvbuf = &req->rq_private_buf;
len = desc->count;
- if (len > xprt->tcp_reclen - xprt->tcp_offset) {
- skb_reader_t my_desc;
+ if (len > transport->tcp_reclen - transport->tcp_offset) {
+ struct xdr_skb_reader my_desc;
- len = xprt->tcp_reclen - xprt->tcp_offset;
+ len = transport->tcp_reclen - transport->tcp_offset;
memcpy(&my_desc, desc, sizeof(my_desc));
my_desc.count = len;
- r = xdr_partial_copy_from_skb(rcvbuf, xprt->tcp_copied,
- &my_desc, xs_tcp_copy_data);
+ r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
+ &my_desc, xdr_skb_read_bits);
desc->count -= r;
desc->offset += r;
} else
- r = xdr_partial_copy_from_skb(rcvbuf, xprt->tcp_copied,
- desc, xs_tcp_copy_data);
+ r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
+ desc, xdr_skb_read_bits);
if (r > 0) {
- xprt->tcp_copied += r;
- xprt->tcp_offset += r;
+ transport->tcp_copied += r;
+ transport->tcp_offset += r;
}
if (r != len) {
/* Error when copying to the receive buffer,
* usually because we weren't able to allocate
* additional buffer pages. All we can do now
- * is turn off XPRT_COPY_DATA, so the request
+ * is turn off TCP_RCV_COPY_DATA, so the request
* will not receive any additional updates,
* and time out.
* Any remaining data from this record will
* be discarded.
*/
- xprt->tcp_flags &= ~XPRT_COPY_DATA;
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
dprintk("RPC: XID %08x truncated request\n",
- ntohl(xprt->tcp_xid));
+ ntohl(transport->tcp_xid));
dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u\n",
- xprt, xprt->tcp_copied, xprt->tcp_offset, xprt->tcp_reclen);
+ xprt, transport->tcp_copied, transport->tcp_offset,
+ transport->tcp_reclen);
goto out;
}
dprintk("RPC: XID %08x read %Zd bytes\n",
- ntohl(xprt->tcp_xid), r);
+ ntohl(transport->tcp_xid), r);
dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u\n",
- xprt, xprt->tcp_copied, xprt->tcp_offset, xprt->tcp_reclen);
-
- if (xprt->tcp_copied == req->rq_private_buf.buflen)
- xprt->tcp_flags &= ~XPRT_COPY_DATA;
- else if (xprt->tcp_offset == xprt->tcp_reclen) {
- if (xprt->tcp_flags & XPRT_LAST_FRAG)
- xprt->tcp_flags &= ~XPRT_COPY_DATA;
+ xprt, transport->tcp_copied, transport->tcp_offset,
+ transport->tcp_reclen);
+
+ if (transport->tcp_copied == req->rq_private_buf.buflen)
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
+ else if (transport->tcp_offset == transport->tcp_reclen) {
+ if (transport->tcp_flags & TCP_RCV_LAST_FRAG)
+ transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
}
out:
- if (!(xprt->tcp_flags & XPRT_COPY_DATA))
- xprt_complete_rqst(req->rq_task, xprt->tcp_copied);
+ if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
+ xprt_complete_rqst(req->rq_task, transport->tcp_copied);
spin_unlock(&xprt->transport_lock);
- xs_tcp_check_recm(xprt);
+ xs_tcp_check_fraghdr(transport);
}
-static inline void xs_tcp_read_discard(struct rpc_xprt *xprt, skb_reader_t *desc)
+static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
size_t len;
- len = xprt->tcp_reclen - xprt->tcp_offset;
+ len = transport->tcp_reclen - transport->tcp_offset;
if (len > desc->count)
len = desc->count;
desc->count -= len;
desc->offset += len;
- xprt->tcp_offset += len;
+ transport->tcp_offset += len;
dprintk("RPC: discarded %Zu bytes\n", len);
- xs_tcp_check_recm(xprt);
+ xs_tcp_check_fraghdr(transport);
}
static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)
{
struct rpc_xprt *xprt = rd_desc->arg.data;
- skb_reader_t desc = {
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct xdr_skb_reader desc = {
.skb = skb,
.offset = offset,
.count = len,
- .csum = 0
};
dprintk("RPC: xs_tcp_data_recv started\n");
do {
/* Read in a new fragment marker if necessary */
/* Can we ever really expect to get completely empty fragments? */
- if (xprt->tcp_flags & XPRT_COPY_RECM) {
+ if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
xs_tcp_read_fraghdr(xprt, &desc);
continue;
}
/* Read in the xid if necessary */
- if (xprt->tcp_flags & XPRT_COPY_XID) {
- xs_tcp_read_xid(xprt, &desc);
+ if (transport->tcp_flags & TCP_RCV_COPY_XID) {
+ xs_tcp_read_xid(transport, &desc);
continue;
}
/* Read in the request data */
- if (xprt->tcp_flags & XPRT_COPY_DATA) {
+ if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
xs_tcp_read_request(xprt, &desc);
continue;
}
/* Skip over any trailing bytes on short reads */
- xs_tcp_read_discard(xprt, &desc);
+ xs_tcp_read_discard(transport, &desc);
} while (desc.count);
dprintk("RPC: xs_tcp_data_recv done\n");
return len - desc.count;
case TCP_ESTABLISHED:
spin_lock_bh(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
+ struct sock_xprt *transport = container_of(xprt,
+ struct sock_xprt, xprt);
+
/* Reset TCP record info */
- xprt->tcp_offset = 0;
- xprt->tcp_reclen = 0;
- xprt->tcp_copied = 0;
- xprt->tcp_flags = XPRT_COPY_RECM | XPRT_COPY_XID;
+ transport->tcp_offset = 0;
+ transport->tcp_reclen = 0;
+ transport->tcp_copied = 0;
+ transport->tcp_flags =
+ TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
+
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
xprt_wake_pending_tasks(xprt, 0);
}
static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
{
- struct sock *sk = xprt->inet;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
- if (xprt->rcvsize) {
+ if (transport->rcvsize) {
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
- sk->sk_rcvbuf = xprt->rcvsize * xprt->max_reqs * 2;
+ sk->sk_rcvbuf = transport->rcvsize * xprt->max_reqs * 2;
}
- if (xprt->sndsize) {
+ if (transport->sndsize) {
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- sk->sk_sndbuf = xprt->sndsize * xprt->max_reqs * 2;
+ sk->sk_sndbuf = transport->sndsize * xprt->max_reqs * 2;
sk->sk_write_space(sk);
}
}
*/
static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize)
{
- xprt->sndsize = 0;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+
+ transport->sndsize = 0;
if (sndsize)
- xprt->sndsize = sndsize + 1024;
- xprt->rcvsize = 0;
+ transport->sndsize = sndsize + 1024;
+ transport->rcvsize = 0;
if (rcvsize)
- xprt->rcvsize = rcvsize + 1024;
+ transport->rcvsize = rcvsize + 1024;
xs_udp_do_set_buffer_size(xprt);
}
return rand + xprt_min_resvport;
}
-/**
- * xs_print_peer_address - format an IPv4 address for printing
- * @xprt: generic transport
- * @format: flags field indicating which parts of the address to render
- */
-static char *xs_print_peer_address(struct rpc_xprt *xprt, enum rpc_display_format_t format)
-{
- if (xprt->address_strings[format] != NULL)
- return xprt->address_strings[format];
- else
- return "unprintable";
-}
-
/**
* xs_set_port - reset the port number in the remote endpoint address
* @xprt: generic transport
sap->sin_port = htons(port);
}
-static int xs_bindresvport(struct rpc_xprt *xprt, struct socket *sock)
+static int xs_bindresvport(struct sock_xprt *transport, struct socket *sock)
{
struct sockaddr_in myaddr = {
.sin_family = AF_INET,
};
int err;
- unsigned short port = xprt->port;
+ unsigned short port = transport->port;
do {
myaddr.sin_port = htons(port);
err = kernel_bind(sock, (struct sockaddr *) &myaddr,
sizeof(myaddr));
if (err == 0) {
- xprt->port = port;
+ transport->port = port;
dprintk("RPC: xs_bindresvport bound to port %u\n",
port);
return 0;
port = xprt_max_resvport;
else
port--;
- } while (err == -EADDRINUSE && port != xprt->port);
+ } while (err == -EADDRINUSE && port != transport->port);
dprintk("RPC: can't bind to reserved port (%d).\n", -err);
return err;
}
+ #ifdef CONFIG_DEBUG_LOCK_ALLOC
+ static struct lock_class_key xs_key[2];
+ static struct lock_class_key xs_slock_key[2];
+
+ static inline void xs_reclassify_socket(struct socket *sock)
+ {
+ struct sock *sk = sock->sk;
+ BUG_ON(sk->sk_lock.owner != NULL);
+ switch (sk->sk_family) {
+ case AF_INET:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET-NFS",
+ &xs_slock_key[0], "sk_lock-AF_INET-NFS", &xs_key[0]);
+ break;
+
+ case AF_INET6:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFS",
+ &xs_slock_key[1], "sk_lock-AF_INET6-NFS", &xs_key[1]);
+ break;
+
+ default:
+ BUG();
+ }
+ }
+ #else
+ static inline void xs_reclassify_socket(struct socket *sock)
+ {
+ }
+ #endif
+
/**
* xs_udp_connect_worker - set up a UDP socket
* @work: RPC transport to connect
*/
static void xs_udp_connect_worker(struct work_struct *work)
{
- struct rpc_xprt *xprt =
- container_of(work, struct rpc_xprt, connect_worker.work);
- struct socket *sock = xprt->sock;
+ struct sock_xprt *transport =
+ container_of(work, struct sock_xprt, connect_worker.work);
+ struct rpc_xprt *xprt = &transport->xprt;
+ struct socket *sock = transport->sock;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
goto out;
}
+ xs_reclassify_socket(sock);
- if (xprt->resvport && xs_bindresvport(xprt, sock) < 0) {
+ if (xprt->resvport && xs_bindresvport(transport, sock) < 0) {
sock_release(sock);
goto out;
}
dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+ xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
- if (!xprt->inet) {
+ if (!transport->inet) {
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
sk->sk_user_data = xprt;
- xprt->old_data_ready = sk->sk_data_ready;
- xprt->old_state_change = sk->sk_state_change;
- xprt->old_write_space = sk->sk_write_space;
+ transport->old_data_ready = sk->sk_data_ready;
+ transport->old_state_change = sk->sk_state_change;
+ transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_udp_data_ready;
sk->sk_write_space = xs_udp_write_space;
sk->sk_no_check = UDP_CSUM_NORCV;
xprt_set_connected(xprt);
/* Reset to new socket */
- xprt->sock = sock;
- xprt->inet = sk;
+ transport->sock = sock;
+ transport->inet = sk;
write_unlock_bh(&sk->sk_callback_lock);
}
static void xs_tcp_reuse_connection(struct rpc_xprt *xprt)
{
int result;
- struct socket *sock = xprt->sock;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct sockaddr any;
dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt);
*/
memset(&any, 0, sizeof(any));
any.sa_family = AF_UNSPEC;
- result = kernel_connect(sock, &any, sizeof(any), 0);
+ result = kernel_connect(transport->sock, &any, sizeof(any), 0);
if (result)
dprintk("RPC: AF_UNSPEC connect return code %d\n",
result);
*/
static void xs_tcp_connect_worker(struct work_struct *work)
{
- struct rpc_xprt *xprt =
- container_of(work, struct rpc_xprt, connect_worker.work);
- struct socket *sock = xprt->sock;
+ struct sock_xprt *transport =
+ container_of(work, struct sock_xprt, connect_worker.work);
+ struct rpc_xprt *xprt = &transport->xprt;
+ struct socket *sock = transport->sock;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
goto out;
- if (!xprt->sock) {
+ if (!sock) {
/* start from scratch */
if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
dprintk("RPC: can't create TCP transport socket (%d).\n", -err);
goto out;
}
+ xs_reclassify_socket(sock);
- if (xprt->resvport && xs_bindresvport(xprt, sock) < 0) {
+ if (xprt->resvport && xs_bindresvport(transport, sock) < 0) {
sock_release(sock);
goto out;
}
xs_tcp_reuse_connection(xprt);
dprintk("RPC: worker connecting xprt %p to address: %s\n",
- xprt, xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+ xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
- if (!xprt->inet) {
+ if (!transport->inet) {
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
sk->sk_user_data = xprt;
- xprt->old_data_ready = sk->sk_data_ready;
- xprt->old_state_change = sk->sk_state_change;
- xprt->old_write_space = sk->sk_write_space;
+ transport->old_data_ready = sk->sk_data_ready;
+ transport->old_state_change = sk->sk_state_change;
+ transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_tcp_data_ready;
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
xprt_clear_connected(xprt);
/* Reset to new socket */
- xprt->sock = sock;
- xprt->inet = sk;
+ transport->sock = sock;
+ transport->inet = sk;
write_unlock_bh(&sk->sk_callback_lock);
}
static void xs_connect(struct rpc_task *task)
{
struct rpc_xprt *xprt = task->tk_xprt;
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
if (xprt_test_and_set_connecting(xprt))
return;
- if (xprt->sock != NULL) {
+ if (transport->sock != NULL) {
dprintk("RPC: xs_connect delayed xprt %p for %lu seconds\n",
xprt, xprt->reestablish_timeout / HZ);
- schedule_delayed_work(&xprt->connect_worker,
+ schedule_delayed_work(&transport->connect_worker,
xprt->reestablish_timeout);
xprt->reestablish_timeout <<= 1;
if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO)
xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
} else {
dprintk("RPC: xs_connect scheduled xprt %p\n", xprt);
- schedule_delayed_work(&xprt->connect_worker, 0);
+ schedule_delayed_work(&transport->connect_worker, 0);
/* flush_scheduled_work can sleep... */
if (!RPC_IS_ASYNC(task))
*/
static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+
seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n",
- xprt->port,
+ transport->port,
xprt->stat.bind_count,
xprt->stat.sends,
xprt->stat.recvs,
*/
static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
long idle_time = 0;
if (xprt_connected(xprt))
idle_time = (long)(jiffies - xprt->last_used) / HZ;
seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n",
- xprt->port,
+ transport->port,
xprt->stat.bind_count,
xprt->stat.connect_count,
xprt->stat.connect_time,
static struct rpc_xprt_ops xs_udp_ops = {
.set_buffer_size = xs_udp_set_buffer_size,
- .print_addr = xs_print_peer_address,
.reserve_xprt = xprt_reserve_xprt_cong,
.release_xprt = xprt_release_xprt_cong,
.rpcbind = rpc_getport,
};
static struct rpc_xprt_ops xs_tcp_ops = {
- .print_addr = xs_print_peer_address,
.reserve_xprt = xprt_reserve_xprt,
.release_xprt = xs_tcp_release_xprt,
.rpcbind = rpc_getport,
.print_stats = xs_tcp_print_stats,
};
+static struct rpc_xprt *xs_setup_xprt(struct sockaddr *addr, size_t addrlen, unsigned int slot_table_size)
+{
+ struct rpc_xprt *xprt;
+ struct sock_xprt *new;
+
+ if (addrlen > sizeof(xprt->addr)) {
+ dprintk("RPC: xs_setup_xprt: address too large\n");
+ return ERR_PTR(-EBADF);
+ }
+
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (new == NULL) {
+ dprintk("RPC: xs_setup_xprt: couldn't allocate rpc_xprt\n");
+ return ERR_PTR(-ENOMEM);
+ }
+ xprt = &new->xprt;
+
+ xprt->max_reqs = slot_table_size;
+ xprt->slot = kcalloc(xprt->max_reqs, sizeof(struct rpc_rqst), GFP_KERNEL);
+ if (xprt->slot == NULL) {
+ kfree(xprt);
+ dprintk("RPC: xs_setup_xprt: couldn't allocate slot table\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ memcpy(&xprt->addr, addr, addrlen);
+ xprt->addrlen = addrlen;
+ new->port = xs_get_random_port();
+
+ return xprt;
+}
+
/**
* xs_setup_udp - Set up transport to use a UDP socket
- * @xprt: transport to set up
+ * @addr: address of remote server
+ * @addrlen: length of address in bytes
* @to: timeout parameters
*
*/
-int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to)
+struct rpc_xprt *xs_setup_udp(struct sockaddr *addr, size_t addrlen, struct rpc_timeout *to)
{
- size_t slot_table_size;
- struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
+ struct rpc_xprt *xprt;
+ struct sock_xprt *transport;
- xprt->max_reqs = xprt_udp_slot_table_entries;
- slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
- xprt->slot = kzalloc(slot_table_size, GFP_KERNEL);
- if (xprt->slot == NULL)
- return -ENOMEM;
+ xprt = xs_setup_xprt(addr, addrlen, xprt_udp_slot_table_entries);
+ if (IS_ERR(xprt))
+ return xprt;
+ transport = container_of(xprt, struct sock_xprt, xprt);
- if (ntohs(addr->sin_port) != 0)
+ if (ntohs(((struct sockaddr_in *)addr)->sin_port) != 0)
xprt_set_bound(xprt);
- xprt->port = xs_get_random_port();
xprt->prot = IPPROTO_UDP;
xprt->tsh_size = 0;
/* XXX: header size can vary due to auth type, IPv6, etc. */
xprt->max_payload = (1U << 16) - (MAX_HEADER << 3);
- INIT_DELAYED_WORK(&xprt->connect_worker, xs_udp_connect_worker);
+ INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker);
xprt->bind_timeout = XS_BIND_TO;
xprt->connect_timeout = XS_UDP_CONN_TO;
xprt->reestablish_timeout = XS_UDP_REEST_TO;
xs_format_peer_addresses(xprt);
dprintk("RPC: set up transport to address %s\n",
- xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+ xprt->address_strings[RPC_DISPLAY_ALL]);
- return 0;
+ return xprt;
}
/**
* xs_setup_tcp - Set up transport to use a TCP socket
- * @xprt: transport to set up
+ * @addr: address of remote server
+ * @addrlen: length of address in bytes
* @to: timeout parameters
*
*/
-int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to)
+struct rpc_xprt *xs_setup_tcp(struct sockaddr *addr, size_t addrlen, struct rpc_timeout *to)
{
- size_t slot_table_size;
- struct sockaddr_in *addr = (struct sockaddr_in *) &xprt->addr;
+ struct rpc_xprt *xprt;
+ struct sock_xprt *transport;
- xprt->max_reqs = xprt_tcp_slot_table_entries;
- slot_table_size = xprt->max_reqs * sizeof(xprt->slot[0]);
- xprt->slot = kzalloc(slot_table_size, GFP_KERNEL);
- if (xprt->slot == NULL)
- return -ENOMEM;
+ xprt = xs_setup_xprt(addr, addrlen, xprt_tcp_slot_table_entries);
+ if (IS_ERR(xprt))
+ return xprt;
+ transport = container_of(xprt, struct sock_xprt, xprt);
- if (ntohs(addr->sin_port) != 0)
+ if (ntohs(((struct sockaddr_in *)addr)->sin_port) != 0)
xprt_set_bound(xprt);
- xprt->port = xs_get_random_port();
xprt->prot = IPPROTO_TCP;
xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
- INIT_DELAYED_WORK(&xprt->connect_worker, xs_tcp_connect_worker);
+ INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker);
xprt->bind_timeout = XS_BIND_TO;
xprt->connect_timeout = XS_TCP_CONN_TO;
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
xs_format_peer_addresses(xprt);
dprintk("RPC: set up transport to address %s\n",
- xs_print_peer_address(xprt, RPC_DISPLAY_ALL));
+ xprt->address_strings[RPC_DISPLAY_ALL]);
+
+ return xprt;
+}
+
+/**
+ * init_socket_xprt - set up xprtsock's sysctls
+ *
+ */
+int init_socket_xprt(void)
+{
+#ifdef RPC_DEBUG
+ if (!sunrpc_table_header) {
+ sunrpc_table_header = register_sysctl_table(sunrpc_table, 1);
+#ifdef CONFIG_PROC_FS
+ if (sunrpc_table[0].de)
+ sunrpc_table[0].de->owner = THIS_MODULE;
+#endif
+ }
+#endif
return 0;
}
+
+/**
+ * cleanup_socket_xprt - remove xprtsock's sysctls
+ *
+ */
+void cleanup_socket_xprt(void)
+{
+#ifdef RPC_DEBUG
+ if (sunrpc_table_header) {
+ unregister_sysctl_table(sunrpc_table_header);
+ sunrpc_table_header = NULL;
+ }
+#endif
+}
git.openpandora.org / pandora-kernel.git / commitdiff