#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fcntl.h>
-#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
struct bdi_writeback;
struct bio;
struct export_operations;
+struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
struct page;
struct address_space;
struct writeback_control;
+struct readahead_control;
/*
* Write life time hint values.
*/
int (*readpages)(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
+ void (*readahead)(struct readahead_control *);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
+ errseq_t f_sb_err; /* for syncfs */
} __randomize_layout
__attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
bool (*lm_break)(struct file_lock *);
int (*lm_change)(struct file_lock *, int, struct list_head *);
void (*lm_setup)(struct file_lock *, void **);
+ bool (*lm_breaker_owns_lease)(struct file_lock *);
};
struct lock_manager {
#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020
#define SB_I_UNTRUSTED_MOUNTER 0x00000040
+#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */
+
/* Possible states of 'frozen' field */
enum {
SB_UNFROZEN = 0, /* FS is unfrozen */
/* Being remounted read-only */
int s_readonly_remount;
+ /* per-sb errseq_t for reporting writeback errors via syncfs */
+ errseq_t s_wb_err;
+
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
*
* Since page fault freeze protection behaves as a lock, users have to preserve
* ordering of freeze protection and other filesystem locks. It is advised to
- * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
+ * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
* handling code implies lock dependency:
*
- * mmap_sem
+ * mmap_lock
* -> sb_start_pagefault
*/
static inline void sb_start_pagefault(struct super_block *sb)
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
-extern int vfs_whiteout(struct inode *, struct dentry *);
+
+static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+}
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
int open_flag);
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
umode_t mode);
extern bool may_open_dev(const struct path *path);
-/*
- * VFS FS_IOC_FIEMAP helper definitions.
- */
-struct fiemap_extent_info {
- unsigned int fi_flags; /* Flags as passed from user */
- unsigned int fi_extents_mapped; /* Number of mapped extents */
- unsigned int fi_extents_max; /* Size of fiemap_extent array */
- struct fiemap_extent __user *fi_extents_start; /* Start of
- fiemap_extent array */
-};
-int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
- u64 phys, u64 len, u32 flags);
-int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
/*
* This is the "filldir" function type, used by readdir() to let
*
* I_CREATING New object's inode in the middle of setting up.
*
+ * I_DONTCACHE Evict inode as soon as it is not used anymore.
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
#define I_WB_SWITCH (1 << 13)
#define I_OVL_INUSE (1 << 14)
#define I_CREATING (1 << 15)
+#define I_DONTCACHE (1 << 16)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
#ifdef CONFIG_BLOCK
extern int register_blkdev(unsigned int, const char *);
extern void unregister_blkdev(unsigned int, const char *);
-extern void bdev_unhash_inode(dev_t dev);
extern struct block_device *bdget(dev_t);
extern struct block_device *bdgrab(struct block_device *bdev);
extern void bd_set_size(struct block_device *, loff_t size);
extern const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;
#ifdef CONFIG_BLOCK
-extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
extern int revalidate_disk(struct gendisk *);
extern int check_disk_change(struct block_device *);
extern int __invalidate_device(struct block_device *, bool);
-extern int invalidate_partition(struct gendisk *, int);
#endif
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end);
return errseq_sample(&mapping->wb_err);
}
+/**
+ * file_sample_sb_err - sample the current errseq_t to test for later errors
+ * @mapping: mapping to be sampled
+ *
+ * Grab the most current superblock-level errseq_t value for the given
+ * struct file.
+ */
+static inline errseq_t file_sample_sb_err(struct file *file)
+{
+ return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
+}
+
static inline int filemap_nr_thps(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
extern int generic_delete_inode(struct inode *inode);
static inline int generic_drop_inode(struct inode *inode)
{
- return !inode->i_nlink || inode_unhashed(inode);
+ return !inode->i_nlink || inode_unhashed(inode) ||
+ (inode->i_state & I_DONTCACHE);
}
+extern void d_mark_dontcache(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
int (*match)(struct inode *,
unsigned long, void *),
void *data);
+extern struct inode *find_inode_rcu(struct super_block *, unsigned long,
+ int (*)(struct inode *, void *), void *);
+extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t *count, unsigned int flags);
+extern ssize_t generic_file_buffered_read(struct kiocb *iocb,
+ struct iov_iter *to, ssize_t already_read);
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
DIO_SKIP_HOLES = 0x02,
};
-void dio_end_io(struct bio *bio);
-
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
get_block_t get_block,
extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
extern int vfs_readlink(struct dentry *, char __user *, int);
-extern int __generic_block_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo,
- loff_t start, loff_t len,
- get_block_t *get_block);
-extern int generic_block_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo, u64 start,
- u64 len, get_block_t *get_block);
-
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern int file_update_time(struct file *file);
-static inline bool io_is_direct(struct file *filp)
-{
- return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
-}
-
static inline bool vma_is_dax(const struct vm_area_struct *vma)
{
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
int res = 0;
if (file->f_flags & O_APPEND)
res |= IOCB_APPEND;
- if (io_is_direct(file))
+ if (file->f_flags & O_DIRECT)
res |= IOCB_DIRECT;
if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
res |= IOCB_DSYNC;
struct ctl_table;
int proc_nr_files(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int proc_nr_dentry(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int proc_nr_inodes(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int __init get_filesystem_list(char *buf);
#define __FMODE_EXEC ((__force int) FMODE_EXEC)
#include <net/tcp_states.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
- #include <trace/events/skb.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/xprt.h>
+ #include <trace/events/sunrpc.h>
+
#include "socklib.h"
#include "sunrpc.h"
}
#endif
- /*
- * Release an skbuff after use
+ /**
+ * svc_tcp_release_rqst - Release transport-related resources
+ * @rqstp: request structure with resources to be released
+ *
*/
- static void svc_release_skb(struct svc_rqst *rqstp)
+ static void svc_tcp_release_rqst(struct svc_rqst *rqstp)
{
struct sk_buff *skb = rqstp->rq_xprt_ctxt;
if (skb) {
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
- rqstp->rq_xprt_ctxt = NULL;
- dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
+ rqstp->rq_xprt_ctxt = NULL;
skb_free_datagram_locked(svsk->sk_sk, skb);
}
}
- static void svc_release_udp_skb(struct svc_rqst *rqstp)
+ /**
+ * svc_udp_release_rqst - Release transport-related resources
+ * @rqstp: request structure with resources to be released
+ *
+ */
+ static void svc_udp_release_rqst(struct svc_rqst *rqstp)
{
struct sk_buff *skb = rqstp->rq_xprt_ctxt;
if (skb) {
rqstp->rq_xprt_ctxt = NULL;
-
- dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
consume_skb(skb);
}
}
return len;
}
+ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+ static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek)
+ {
+ struct bvec_iter bi = {
+ .bi_size = size,
+ };
+ struct bio_vec bv;
+
+ bvec_iter_advance(bvec, &bi, seek & PAGE_MASK);
+ for_each_bvec(bv, bvec, bi, bi)
+ flush_dcache_page(bv.bv_page);
+ }
+ #else
+ static inline void svc_flush_bvec(const struct bio_vec *bvec, size_t size,
+ size_t seek)
+ {
+ }
+ #endif
+
/*
- * Generic recvfrom routine.
+ * Read from @rqstp's transport socket. The incoming message fills whole
+ * pages in @rqstp's rq_pages array until the last page of the message
+ * has been received into a partial page.
*/
- static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
- unsigned int nr, size_t buflen, unsigned int base)
+ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
+ size_t seek)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+ struct bio_vec *bvec = rqstp->rq_bvec;
struct msghdr msg = { NULL };
+ unsigned int i;
ssize_t len;
+ size_t t;
rqstp->rq_xprt_hlen = 0;
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
- if (base != 0) {
- iov_iter_advance(&msg.msg_iter, base);
- buflen -= base;
+
+ for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) {
+ bvec[i].bv_page = rqstp->rq_pages[i];
+ bvec[i].bv_len = PAGE_SIZE;
+ bvec[i].bv_offset = 0;
+ }
+ rqstp->rq_respages = &rqstp->rq_pages[i];
+ rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+ iov_iter_bvec(&msg.msg_iter, READ, bvec, i, buflen);
+ if (seek) {
+ iov_iter_advance(&msg.msg_iter, seek);
+ buflen -= seek;
}
len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
+ if (len > 0)
+ svc_flush_bvec(bvec, len, seek);
+
/* If we read a full record, then assume there may be more
* data to read (stream based sockets only!)
*/
if (len == buflen)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
- svsk, iov[0].iov_base, iov[0].iov_len, len);
return len;
}
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
if (svsk) {
- dprintk("svc: socket %p(inet %p), busy=%d\n",
- svsk, sk,
- test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
-
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_odata(sk);
+ trace_svcsock_data_ready(&svsk->sk_xprt, 0);
if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags))
svc_xprt_enqueue(&svsk->sk_xprt);
}
struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data);
if (svsk) {
- dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
- svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
-
/* Refer to svc_setup_socket() for details. */
rmb();
+ trace_svcsock_write_space(&svsk->sk_xprt, 0);
svsk->sk_owspace(sk);
svc_xprt_enqueue(&svsk->sk_xprt);
}
static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
{
- struct svc_sock *svsk;
- struct socket *sock;
- struct linger no_linger = {
- .l_onoff = 1,
- .l_linger = 0,
- };
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
- svsk = container_of(xprt, struct svc_sock, sk_xprt);
- sock = svsk->sk_sock;
- kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
- (char *)&no_linger, sizeof(no_linger));
+ sock_no_linger(svsk->sk_sock->sk);
}
/*
return 0;
}
- /*
- * Receive a datagram from a UDP socket.
+ /**
+ * svc_udp_recvfrom - Receive a datagram from a UDP socket.
+ * @rqstp: request structure into which to receive an RPC Call
+ *
+ * Called in a loop when XPT_DATA has been set.
+ *
+ * Returns:
+ * On success, the number of bytes in a received RPC Call, or
+ * %0 if a complete RPC Call message was not ready to return
*/
static int svc_udp_recvfrom(struct svc_rqst *rqstp)
{
svc_sock_setbufsize(svsk, serv->sv_nrthreads + 3);
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- skb = NULL;
err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
0, 0, MSG_PEEK | MSG_DONTWAIT);
- if (err >= 0)
- skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err);
-
- if (skb == NULL) {
- if (err != -EAGAIN) {
- /* possibly an icmp error */
- dprintk("svc: recvfrom returned error %d\n", -err);
- set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- }
- return 0;
- }
+ if (err < 0)
+ goto out_recv_err;
+ skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err);
+ if (!skb)
+ goto out_recv_err;
+
len = svc_addr_len(svc_addr(rqstp));
rqstp->rq_addrlen = len;
if (skb->tstamp == 0) {
sock_write_timestamp(svsk->sk_sk, skb->tstamp);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
- len = skb->len;
+ len = skb->len;
rqstp->rq_arg.len = len;
+ trace_svcsock_udp_recv(&svsk->sk_xprt, len);
rqstp->rq_prot = IPPROTO_UDP;
- if (!svc_udp_get_dest_address(rqstp, cmh)) {
- net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
- cmh->cmsg_level, cmh->cmsg_type);
- goto out_free;
- }
+ if (!svc_udp_get_dest_address(rqstp, cmh))
+ goto out_cmsg_err;
rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp));
if (skb_is_nonlinear(skb)) {
/* we have to copy */
local_bh_disable();
- if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
- local_bh_enable();
- /* checksum error */
- goto out_free;
- }
+ if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb))
+ goto out_bh_enable;
local_bh_enable();
consume_skb(skb);
} else {
serv->sv_stats->netudpcnt++;
return len;
+
+ out_recv_err:
+ if (err != -EAGAIN) {
+ /* possibly an icmp error */
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ }
+ trace_svcsock_udp_recv_err(&svsk->sk_xprt, err);
+ return 0;
+ out_cmsg_err:
+ net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
+ cmh->cmsg_level, cmh->cmsg_type);
+ goto out_free;
+ out_bh_enable:
+ local_bh_enable();
out_free:
kfree_skb(skb);
return 0;
* svc_udp_sendto - Send out a reply on a UDP socket
* @rqstp: completed svc_rqst
*
+ * xpt_mutex ensures @rqstp's whole message is written to the socket
+ * without interruption.
+ *
* Returns the number of bytes sent, or a negative errno.
*/
static int svc_udp_sendto(struct svc_rqst *rqstp)
unsigned int uninitialized_var(sent);
int err;
- svc_release_udp_skb(rqstp);
+ svc_udp_release_rqst(rqstp);
svc_set_cmsg_data(rqstp, cmh);
+ mutex_lock(&xprt->xpt_mutex);
+
+ if (svc_xprt_is_dead(xprt))
+ goto out_notconn;
+
err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
xdr_free_bvec(xdr);
if (err == -ECONNREFUSED) {
err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
xdr_free_bvec(xdr);
}
+ trace_svcsock_udp_send(xprt, err);
+
+ mutex_unlock(&xprt->xpt_mutex);
if (err < 0)
return err;
return sent;
+
+ out_notconn:
+ mutex_unlock(&xprt->xpt_mutex);
+ return -ENOTCONN;
}
static int svc_udp_has_wspace(struct svc_xprt *xprt)
.xpo_recvfrom = svc_udp_recvfrom,
.xpo_sendto = svc_udp_sendto,
.xpo_read_payload = svc_sock_read_payload,
- .xpo_release_rqst = svc_release_udp_skb,
+ .xpo_release_rqst = svc_udp_release_rqst,
.xpo_detach = svc_sock_detach,
.xpo_free = svc_sock_free,
.xpo_has_wspace = svc_udp_has_wspace,
static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
- int level, optname, one = 1;
-
svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class,
&svsk->sk_xprt, serv);
clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
/* make sure we get destination address info */
switch (svsk->sk_sk->sk_family) {
case AF_INET:
- level = SOL_IP;
- optname = IP_PKTINFO;
+ ip_sock_set_pktinfo(svsk->sk_sock->sk);
break;
case AF_INET6:
- level = SOL_IPV6;
- optname = IPV6_RECVPKTINFO;
+ ip6_sock_set_recvpktinfo(svsk->sk_sock->sk);
break;
default:
BUG();
}
- kernel_setsockopt(svsk->sk_sock, level, optname, (char *)&one,
- sizeof(one));
}
/*
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
- dprintk("svc: socket %p TCP (listen) state change %d\n",
- sk, sk->sk_state);
-
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
if (svsk) {
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
- } else
- printk("svc: socket %p: no user data\n", sk);
+ }
}
}
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
- dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
- sk, sk->sk_state, sk->sk_user_data);
-
- if (!svsk)
- printk("svc: socket %p: no user data\n", sk);
- else {
+ if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_ostate(sk);
+ trace_svcsock_tcp_state(&svsk->sk_xprt, svsk->sk_sock);
if (sk->sk_state != TCP_ESTABLISHED) {
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
struct socket *newsock;
struct svc_sock *newsvsk;
int err, slen;
- RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
- dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
if (!sock)
return NULL;
else if (err != -EAGAIN)
net_warn_ratelimited("%s: accept failed (err %d)!\n",
serv->sv_name, -err);
+ trace_svcsock_accept_err(xprt, serv->sv_name, err);
return NULL;
}
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
err = kernel_getpeername(newsock, sin);
if (err < 0) {
- net_warn_ratelimited("%s: peername failed (err %d)!\n",
- serv->sv_name, -err);
+ trace_svcsock_getpeername_err(xprt, serv->sv_name, err);
goto failed; /* aborted connection or whatever */
}
slen = err;
- /* Ideally, we would want to reject connections from unauthorized
- * hosts here, but when we get encryption, the IP of the host won't
- * tell us anything. For now just warn about unpriv connections.
- */
- if (!svc_port_is_privileged(sin)) {
- dprintk("%s: connect from unprivileged port: %s\n",
- serv->sv_name,
- __svc_print_addr(sin, buf, sizeof(buf)));
- }
- dprintk("%s: connect from %s\n", serv->sv_name,
- __svc_print_addr(sin, buf, sizeof(buf)));
-
/* Reset the inherited callbacks before calling svc_setup_socket */
newsock->sk->sk_state_change = svsk->sk_ostate;
newsock->sk->sk_data_ready = svsk->sk_odata;
svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
err = kernel_getsockname(newsock, sin);
slen = err;
- if (unlikely(err < 0)) {
- dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
+ if (unlikely(err < 0))
slen = offsetof(struct sockaddr, sa_data);
- }
svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
if (sock_is_loopback(newsock->sk))
return NULL;
}
- static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+ static size_t svc_tcp_restore_pages(struct svc_sock *svsk,
+ struct svc_rqst *rqstp)
{
- unsigned int i, len, npages;
+ size_t len = svsk->sk_datalen;
+ unsigned int i, npages;
- if (svsk->sk_datalen == 0)
+ if (!len)
return 0;
- len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (rqstp->rq_pages[i] != NULL)
}
/*
- * Receive fragment record header.
- * If we haven't gotten the record length yet, get the next four bytes.
+ * Receive fragment record header into sk_marker.
*/
- static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
+ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
+ struct svc_rqst *rqstp)
{
- struct svc_serv *serv = svsk->sk_xprt.xpt_server;
- unsigned int want;
- int len;
+ ssize_t want, len;
+ /* If we haven't gotten the record length yet,
+ * get the next four bytes.
+ */
if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
+ struct msghdr msg = { NULL };
struct kvec iov;
want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
- iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
+ iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen;
iov.iov_len = want;
- len = svc_recvfrom(rqstp, &iov, 1, want, 0);
+ iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, want);
+ len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
if (len < 0)
- goto error;
+ return len;
svsk->sk_tcplen += len;
-
if (len < want) {
- dprintk("svc: short recvfrom while reading record "
- "length (%d of %d)\n", len, want);
- return -EAGAIN;
+ /* call again to read the remaining bytes */
+ goto err_short;
}
-
- dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk));
+ trace_svcsock_marker(&svsk->sk_xprt, svsk->sk_marker);
if (svc_sock_reclen(svsk) + svsk->sk_datalen >
- serv->sv_max_mesg) {
- net_notice_ratelimited("RPC: fragment too large: %d\n",
- svc_sock_reclen(svsk));
- goto err_delete;
- }
+ svsk->sk_xprt.xpt_server->sv_max_mesg)
+ goto err_too_large;
}
-
return svc_sock_reclen(svsk);
- error:
- dprintk("RPC: TCP recv_record got %d\n", len);
- return len;
- err_delete:
+
+ err_too_large:
+ net_notice_ratelimited("svc: %s %s RPC fragment too large: %d\n",
+ __func__, svsk->sk_xprt.xpt_server->sv_name,
+ svc_sock_reclen(svsk));
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+ err_short:
return -EAGAIN;
}
return -EAGAIN;
}
- static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
- {
- int i = 0;
- int t = 0;
-
- while (t < len) {
- vec[i].iov_base = page_address(pages[i]);
- vec[i].iov_len = PAGE_SIZE;
- i++;
- t += PAGE_SIZE;
- }
- return i;
- }
-
static void svc_tcp_fragment_received(struct svc_sock *svsk)
{
/* If we have more data, signal svc_xprt_enqueue() to try again */
- dprintk("svc: TCP %s record (%d bytes)\n",
- svc_sock_final_rec(svsk) ? "final" : "nonfinal",
- svc_sock_reclen(svsk));
svsk->sk_tcplen = 0;
- svsk->sk_reclen = 0;
+ svsk->sk_marker = xdr_zero;
}
- /*
- * Receive data from a TCP socket.
+ /**
+ * svc_tcp_recvfrom - Receive data from a TCP socket
+ * @rqstp: request structure into which to receive an RPC Call
+ *
+ * Called in a loop when XPT_DATA has been set.
+ *
+ * Read the 4-byte stream record marker, then use the record length
+ * in that marker to set up exactly the resources needed to receive
+ * the next RPC message into @rqstp.
+ *
+ * Returns:
+ * On success, the number of bytes in a received RPC Call, or
+ * %0 if a complete RPC Call message was not ready to return
+ *
+ * The zero return case handles partial receives and callback Replies.
+ * The state of a partial receive is preserved in the svc_sock for
+ * the next call to svc_tcp_recvfrom.
*/
static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
- int len;
- struct kvec *vec;
- unsigned int want, base;
+ size_t want, base;
+ ssize_t len;
__be32 *p;
__be32 calldir;
- int pnum;
-
- dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
- svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
- test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
- test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
- len = svc_tcp_recv_record(svsk, rqstp);
+ clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ len = svc_tcp_read_marker(svsk, rqstp);
if (len < 0)
goto error;
base = svc_tcp_restore_pages(svsk, rqstp);
- want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
-
- vec = rqstp->rq_vec;
-
- pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
-
- rqstp->rq_respages = &rqstp->rq_pages[pnum];
- rqstp->rq_next_page = rqstp->rq_respages + 1;
-
- /* Now receive data */
- len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
+ want = len - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
+ len = svc_tcp_read_msg(rqstp, base + want, base);
if (len >= 0) {
+ trace_svcsock_tcp_recv(&svsk->sk_xprt, len);
svsk->sk_tcplen += len;
svsk->sk_datalen += len;
}
- if (len != want || !svc_sock_final_rec(svsk)) {
- svc_tcp_save_pages(svsk, rqstp);
- if (len < 0 && len != -EAGAIN)
- goto err_delete;
- if (len == want)
- svc_tcp_fragment_received(svsk);
- else
- dprintk("svc: incomplete TCP record (%d of %d)\n",
- (int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)),
- svc_sock_reclen(svsk));
- goto err_noclose;
- }
-
- if (svsk->sk_datalen < 8) {
- svsk->sk_datalen = 0;
- goto err_delete; /* client is nuts. */
- }
+ if (len != want || !svc_sock_final_rec(svsk))
+ goto err_incomplete;
+ if (svsk->sk_datalen < 8)
+ goto err_nuts;
rqstp->rq_arg.len = svsk->sk_datalen;
rqstp->rq_arg.page_base = 0;
return rqstp->rq_arg.len;
+ err_incomplete:
+ svc_tcp_save_pages(svsk, rqstp);
+ if (len < 0 && len != -EAGAIN)
+ goto err_delete;
+ if (len == want)
+ svc_tcp_fragment_received(svsk);
+ else
+ trace_svcsock_tcp_recv_short(&svsk->sk_xprt,
+ svc_sock_reclen(svsk),
+ svsk->sk_tcplen - sizeof(rpc_fraghdr));
+ goto err_noclose;
error:
if (len != -EAGAIN)
goto err_delete;
- dprintk("RPC: TCP recvfrom got EAGAIN\n");
+ trace_svcsock_tcp_recv_eagain(&svsk->sk_xprt, 0);
return 0;
+ err_nuts:
+ svsk->sk_datalen = 0;
err_delete:
- printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
- svsk->sk_xprt.xpt_server->sv_name, -len);
+ trace_svcsock_tcp_recv_err(&svsk->sk_xprt, len);
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
err_noclose:
return 0; /* record not complete */
* svc_tcp_sendto - Send out a reply on a TCP socket
* @rqstp: completed svc_rqst
*
+ * xpt_mutex ensures @rqstp's whole message is written to the socket
+ * without interruption.
+ *
* Returns the number of bytes sent, or a negative errno.
*/
static int svc_tcp_sendto(struct svc_rqst *rqstp)
unsigned int uninitialized_var(sent);
int err;
- svc_release_skb(rqstp);
+ svc_tcp_release_rqst(rqstp);
+ mutex_lock(&xprt->xpt_mutex);
+ if (svc_xprt_is_dead(xprt))
+ goto out_notconn;
err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
xdr_free_bvec(xdr);
+ trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
if (err < 0 || sent != (xdr->len + sizeof(marker)))
goto out_close;
+ mutex_unlock(&xprt->xpt_mutex);
return sent;
+ out_notconn:
+ mutex_unlock(&xprt->xpt_mutex);
+ return -ENOTCONN;
out_close:
pr_notice("rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
xprt->xpt_server->sv_name,
(err < 0) ? err : sent, xdr->len);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
+ mutex_unlock(&xprt->xpt_mutex);
return -EAGAIN;
}
.xpo_recvfrom = svc_tcp_recvfrom,
.xpo_sendto = svc_tcp_sendto,
.xpo_read_payload = svc_sock_read_payload,
- .xpo_release_rqst = svc_release_skb,
+ .xpo_release_rqst = svc_tcp_release_rqst,
.xpo_detach = svc_tcp_sock_detach,
.xpo_free = svc_sock_free,
.xpo_has_wspace = svc_tcp_has_wspace,
set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
if (sk->sk_state == TCP_LISTEN) {
- dprintk("setting up TCP socket for listening\n");
strcpy(svsk->sk_xprt.xpt_remotebuf, "listener");
set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
sk->sk_data_ready = svc_tcp_listen_data_ready;
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
} else {
- dprintk("setting up TCP socket for reading\n");
sk->sk_state_change = svc_tcp_state_change;
sk->sk_data_ready = svc_data_ready;
sk->sk_write_space = svc_write_space;
- svsk->sk_reclen = 0;
+ svsk->sk_marker = xdr_zero;
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
int pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
int err = 0;
- dprintk("svc: svc_setup_socket %p\n", sock);
svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
if (!svsk)
return ERR_PTR(-ENOMEM);
else
svc_tcp_init(svsk, serv);
- dprintk("svc: svc_setup_socket created %p (inet %p), "
- "listen %d close %d\n",
- svsk, svsk->sk_sk,
- test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags),
- test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
-
+ trace_svcsock_new_socket(sock);
return svsk;
}
struct sockaddr *newsin = (struct sockaddr *)&addr;
int newlen;
int family;
- RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-
- dprintk("svc: svc_create_socket(%s, %d, %s)\n",
- serv->sv_program->pg_name, protocol,
- __svc_print_addr(sin, buf, sizeof(buf)));
- int val;
if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) {
printk(KERN_WARNING "svc: only UDP and TCP "
* getting requests from IPv4 remotes. Those should
* be shunted to a PF_INET listener via rpcbind.
*/
- val = 1;
if (family == PF_INET6)
- kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
- (char *)&val, sizeof(val));
-
+ ip6_sock_set_v6only(sock->sk);
if (type == SOCK_STREAM)
sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */
error = kernel_bind(sock, sin, len);
svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
return (struct svc_xprt *)svsk;
bummer:
- dprintk("svc: svc_create_socket error = %d\n", -error);
sock_release(sock);
return ERR_PTR(error);
}
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct sock *sk = svsk->sk_sk;
- dprintk("svc: svc_sock_detach(%p)\n", svsk);
-
/* put back the old socket callbacks */
lock_sock(sk);
sk->sk_state_change = svsk->sk_ostate;
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
- dprintk("svc: svc_tcp_sock_detach(%p)\n", svsk);
-
svc_sock_detach(xprt);
if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
static void svc_sock_free(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
- dprintk("svc: svc_sock_free(%p)\n", svsk);
if (svsk->sk_sock->file)
sockfd_put(svsk->sk_sock);
projects / linux-2.6-microblaze.git / commitdiff