From 2244d07bfa2097cb00600da91c715a8aa547917e Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 17 Aug 2010 08:59:14 +0000 Subject: net: simplify flags for tx timestamping This patch removes the abstraction introduced by the union skb_shared_tx in the shared skb data. The access of the different union elements at several places led to some confusion about accessing the shared tx_flags e.g. in skb_orphan_try(). http://marc.info/?l=linux-netdev&m=128084897415886&w=2 Signed-off-by: Oliver Hartkopp Signed-off-by: David S. Miller --- net/socket.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2270b941bcc7..7848d12f5e4d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -535,14 +535,13 @@ void sock_release(struct socket *sock) } EXPORT_SYMBOL(sock_release); -int sock_tx_timestamp(struct msghdr *msg, struct sock *sk, - union skb_shared_tx *shtx) +int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags) { - shtx->flags = 0; + *tx_flags = 0; if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) - shtx->hardware = 1; + *tx_flags |= SKBTX_HW_TSTAMP; if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) - shtx->software = 1; + *tx_flags |= SKBTX_SW_TSTAMP; return 0; } EXPORT_SYMBOL(sock_tx_timestamp); -- cgit v1.2.3 From fb8621bb6c040a25ac2fc246653859f841a1f53d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 7 Sep 2010 03:55:00 +0000 Subject: net: remove address space warnings in net/socket.c Casts __kernel to __user pointer require __force markup, so add it. Also sock_get/setsockopt() takes @optval and/or @optlen arguments as user pointers but were taking kernel pointers, use new variables 'uoptval' and/or 'uoptlen' to fix it. These remove following warnings from sparse: net/socket.c:1922:46: warning: cast adds address space to expression () net/socket.c:3061:61: warning: incorrect type in argument 4 (different address spaces) net/socket.c:3061:61: expected char [noderef] *optval net/socket.c:3061:61: got char *optval net/socket.c:3061:69: warning: incorrect type in argument 5 (different address spaces) net/socket.c:3061:69: expected int [noderef] *optlen net/socket.c:3061:69: got int *optlen net/socket.c:3063:67: warning: incorrect type in argument 4 (different address spaces) net/socket.c:3063:67: expected char [noderef] *optval net/socket.c:3063:67: got char *optval net/socket.c:3064:45: warning: incorrect type in argument 5 (different address spaces) net/socket.c:3064:45: expected int [noderef] *optlen net/socket.c:3064:45: got int *optlen net/socket.c:3078:61: warning: incorrect type in argument 4 (different address spaces) net/socket.c:3078:61: expected char [noderef] *optval net/socket.c:3078:61: got char *optval net/socket.c:3080:67: warning: incorrect type in argument 4 (different address spaces) net/socket.c:3080:67: expected char [noderef] *optval net/socket.c:3080:67: got char *optval Signed-off-by: Namhyung Kim Signed-off-by: David S. Miller --- net/socket.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 7848d12f5e4d..717a5f1c8792 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1918,7 +1918,8 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) * Afterwards, it will be a kernel pointer. Thus the compiler-assisted * checking falls down on this. */ - if (copy_from_user(ctl_buf, (void __user *)msg_sys.msg_control, + if (copy_from_user(ctl_buf, + (void __user __force *)msg_sys.msg_control, ctl_len)) goto out_freectl; msg_sys.msg_control = ctl_buf; @@ -3053,14 +3054,19 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen) { mm_segment_t oldfs = get_fs(); + char __user *uoptval; + int __user *uoptlen; int err; + uoptval = (char __user __force *) optval; + uoptlen = (int __user __force *) optlen; + set_fs(KERNEL_DS); if (level == SOL_SOCKET) - err = sock_getsockopt(sock, level, optname, optval, optlen); + err = sock_getsockopt(sock, level, optname, uoptval, uoptlen); else - err = sock->ops->getsockopt(sock, level, optname, optval, - optlen); + err = sock->ops->getsockopt(sock, level, optname, uoptval, + uoptlen); set_fs(oldfs); return err; } @@ -3070,13 +3076,16 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); + char __user *uoptval; int err; + uoptval = (char __user __force *) optval; + set_fs(KERNEL_DS); if (level == SOL_SOCKET) - err = sock_setsockopt(sock, level, optname, optval, optlen); + err = sock_setsockopt(sock, level, optname, uoptval, optlen); else - err = sock->ops->setsockopt(sock, level, optname, optval, + err = sock->ops->setsockopt(sock, level, optname, uoptval, optlen); set_fs(oldfs); return err; -- cgit v1.2.3 From 721db93a55dad71bb89e7d11cc6be1f180ec3f2d Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 29 Sep 2010 16:06:32 +0400 Subject: net: Export __sock_create Signed-off-by: Pavel Emelyanov Acked-by: David S. Miller Signed-off-by: J. Bruce Fields --- net/socket.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2270b941bcc7..0c37b0037b97 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1144,7 +1144,7 @@ call_kill: } EXPORT_SYMBOL(sock_wake_async); -static int __sock_create(struct net *net, int family, int type, int protocol, +int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; @@ -1256,6 +1256,7 @@ out_release: rcu_read_unlock(); goto out_sock_release; } +EXPORT_SYMBOL(__sock_create); int sock_create(int family, int type, int protocol, struct socket **res) { -- cgit v1.2.3 From 6038f373a3dc1f1c26496e60b6c40b164716f07e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 15 Aug 2010 18:52:59 +0200 Subject: llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann Cc: Julia Lawall Cc: Christoph Hellwig --- net/socket.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2270b941bcc7..9eac5c394134 100644 --- a/net/socket.c +++ b/net/socket.c @@ -502,6 +502,7 @@ static int sock_no_open(struct inode *irrelevant, struct file *dontcare) const struct file_operations bad_sock_fops = { .owner = THIS_MODULE, .open = sock_no_open, + .llseek = noop_llseek, }; /** -- cgit v1.2.3 From 11165f1457181e4499e5eada442434a07827ffd8 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 18 Oct 2010 14:27:29 +0000 Subject: socket: localize functions A couple of functions in socket.c are only used there and should be localized. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/socket.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 717a5f1c8792..72da57d6ab7b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -209,8 +209,8 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr) * specified. Zero is returned for a success. */ -int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr, - int __user *ulen) +static int move_addr_to_user(struct sockaddr *kaddr, int klen, + void __user *uaddr, int __user *ulen) { int err; int len; @@ -661,7 +661,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); -inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) +static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, -- cgit v1.2.3 From 7de9c6ee3ecffd99e1628e81a5ea5468f7581a1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Oct 2010 11:11:40 -0400 Subject: new helper: ihold() Clones an existing reference to inode; caller must already hold one. Signed-off-by: Al Viro --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index abf3e2561521..d223725f99e5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -377,7 +377,7 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags) &socket_file_ops); if (unlikely(!file)) { /* drop dentry, keep inode */ - atomic_inc(&path.dentry->d_inode->i_count); + ihold(path.dentry->d_inode); path_put(&path); put_unused_fd(fd); return -ENFILE; -- cgit v1.2.3 From 85fe4025c616a7c0ed07bc2fc8c5371b07f3888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Oct 2010 11:19:54 -0400 Subject: fs: do not assign default i_ino in new_inode Instead of always assigning an increasing inode number in new_inode move the call to assign it into those callers that actually need it. For now callers that need it is estimated conservatively, that is the call is added to all filesystems that do not assign an i_ino by themselves. For a few more filesystems we can avoid assigning any inode number given that they aren't user visible, and for others it could be done lazily when an inode number is actually needed, but that's left for later patches. Signed-off-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- net/socket.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index d223725f99e5..5cac1c707755 100644 --- a/net/socket.c +++ b/net/socket.c @@ -480,6 +480,7 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); kmemcheck_annotate_bitfield(sock, type); + inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); -- cgit v1.2.3 From 51139adac92f7160ad3ca1cab2de1b4b8d19dc96 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Jul 2010 23:47:46 +0400 Subject: convert get_sb_pseudo() users Signed-off-by: Al Viro --- net/socket.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index ee3cd280c76e..5247ae10f374 100644 --- a/net/socket.c +++ b/net/socket.c @@ -305,19 +305,17 @@ static const struct super_operations sockfs_ops = { .statfs = simple_statfs, }; -static int sockfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *sockfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC, - mnt); + return mount_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC); } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", - .get_sb = sockfs_get_sb, + .mount = sockfs_mount, .kill_sb = kill_anon_super, }; -- cgit v1.2.3 From 253eacc070b114c2ec1f81b067d2fed7305467b0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 30 Oct 2010 16:43:10 -0700 Subject: net: Truncate recvfrom and sendto length to INT_MAX. Signed-off-by: Linus Torvalds Signed-off-by: David S. Miller --- net/socket.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index abf3e2561521..2808b4db46ee 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1652,6 +1652,8 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, struct iovec iov; int fput_needed; + if (len > INT_MAX) + len = INT_MAX; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1709,6 +1711,8 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, int err, err2; int fput_needed; + if (size > INT_MAX) + size = INT_MAX; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; -- cgit v1.2.3 From c1249c0aae4c93a753c70496ab2e9a51430a6f02 Mon Sep 17 00:00:00 2001 From: Martin Lucina Date: Fri, 10 Dec 2010 00:04:05 +0000 Subject: net: Document the kernel_recvmsg() function Signed-off-by: Martin Lucina Signed-off-by: David S. Miller --- net/socket.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 3ca2fd9e3720..088fb3fd45e0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -732,6 +732,21 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, return ret; } +/** + * kernel_recvmsg - Receive a message from a socket (kernel space) + * @sock: The socket to receive the message from + * @msg: Received message + * @vec: Input s/g array for message data + * @num: Size of input s/g array + * @size: Number of bytes to read + * @flags: Message flags (MSG_DONTWAIT, etc...) + * + * On return the msg structure contains the scatter/gather array passed in the + * vec argument. The array is modified so that it consists of the unfilled + * portion of the original array. + * + * The returned value is the total number of bytes received, or an error. + */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { -- cgit v1.2.3