diff options
author | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 06:06:28 (GMT) |
---|---|---|
committer | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 06:06:28 (GMT) |
commit | f43dc23d5ea91fca257be02138a255f02d98e806 (patch) | |
tree | b29722f6e965316e90ac97abf79923ced250dc21 /fs/pipe.c | |
parent | f8e53553f452dcbf67cb89c8cba63a1cd6eb4cc0 (diff) | |
parent | 4162cf64973df51fc885825bc9ca4d055891c49f (diff) | |
download | linux-fsl-qoriq-f43dc23d5ea91fca257be02138a255f02d98e806.tar.xz |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework
Conflicts:
arch/sh/kernel/cpu/sh2/setup-sh7619.c
arch/sh/kernel/cpu/sh2a/setup-mxg.c
arch/sh/kernel/cpu/sh2a/setup-sh7201.c
arch/sh/kernel/cpu/sh2a/setup-sh7203.c
arch/sh/kernel/cpu/sh2a/setup-sh7206.c
arch/sh/kernel/cpu/sh3/setup-sh7705.c
arch/sh/kernel/cpu/sh3/setup-sh770x.c
arch/sh/kernel/cpu/sh3/setup-sh7710.c
arch/sh/kernel/cpu/sh3/setup-sh7720.c
arch/sh/kernel/cpu/sh4/setup-sh4-202.c
arch/sh/kernel/cpu/sh4/setup-sh7750.c
arch/sh/kernel/cpu/sh4/setup-sh7760.c
arch/sh/kernel/cpu/sh4a/setup-sh7343.c
arch/sh/kernel/cpu/sh4a/setup-sh7366.c
arch/sh/kernel/cpu/sh4a/setup-sh7722.c
arch/sh/kernel/cpu/sh4a/setup-sh7723.c
arch/sh/kernel/cpu/sh4a/setup-sh7724.c
arch/sh/kernel/cpu/sh4a/setup-sh7763.c
arch/sh/kernel/cpu/sh4a/setup-sh7770.c
arch/sh/kernel/cpu/sh4a/setup-sh7780.c
arch/sh/kernel/cpu/sh4a/setup-sh7785.c
arch/sh/kernel/cpu/sh4a/setup-sh7786.c
arch/sh/kernel/cpu/sh4a/setup-shx3.c
arch/sh/kernel/cpu/sh5/setup-sh5.c
drivers/serial/sh-sci.c
drivers/serial/sh-sci.h
include/linux/serial_sci.h
Diffstat (limited to 'fs/pipe.c')
-rw-r--r-- | fs/pipe.c | 291 |
1 files changed, 225 insertions, 66 deletions
@@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/log2.h> #include <linux/mount.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> @@ -18,11 +19,23 @@ #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> +#include <linux/fcntl.h> #include <asm/uaccess.h> #include <asm/ioctls.h> /* + * The max size that a non-root user is allowed to grow the pipe. Can + * be set by root in /proc/sys/fs/pipe-max-size + */ +unsigned int pipe_max_size = 1048576; + +/* + * Minimum pipe size, as required by POSIX + */ +unsigned int pipe_min_size = PAGE_SIZE; + +/* * We use a start+len construction, which provides full use of the * allocated memory. * -- Florian Coosmann (FGC) @@ -68,8 +81,8 @@ void pipe_double_lock(struct pipe_inode_info *pipe1, pipe_lock_nested(pipe1, I_MUTEX_PARENT); pipe_lock_nested(pipe2, I_MUTEX_CHILD); } else { - pipe_lock_nested(pipe2, I_MUTEX_CHILD); - pipe_lock_nested(pipe1, I_MUTEX_PARENT); + pipe_lock_nested(pipe2, I_MUTEX_PARENT); + pipe_lock_nested(pipe1, I_MUTEX_CHILD); } } @@ -222,6 +235,7 @@ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, return kmap(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_map); /** * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer @@ -241,6 +255,7 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, } else kunmap(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_unmap); /** * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer @@ -271,6 +286,7 @@ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, return 1; } +EXPORT_SYMBOL(generic_pipe_buf_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer @@ -286,6 +302,7 @@ void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { page_cache_get(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_confirm - verify contents of the pipe buffer @@ -301,6 +318,7 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info, { return 0; } +EXPORT_SYMBOL(generic_pipe_buf_confirm); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer @@ -315,6 +333,7 @@ void generic_pipe_buf_release(struct pipe_inode_info *pipe, { page_cache_release(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .can_merge = 1, @@ -363,7 +382,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, error = ops->confirm(pipe, buf); if (error) { if (!ret) - error = ret; + ret = error; break; } @@ -390,7 +409,7 @@ redo: if (!buf->len) { buf->ops = NULL; ops->release(pipe, buf); - curbuf = (curbuf + 1) & (PIPE_BUFFERS-1); + curbuf = (curbuf + 1) & (pipe->buffers - 1); pipe->curbuf = curbuf; pipe->nrbufs = --bufs; do_wakeup = 1; @@ -472,7 +491,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */ if (pipe->nrbufs && chars != 0) { int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) & - (PIPE_BUFFERS-1); + (pipe->buffers - 1); struct pipe_buffer *buf = pipe->bufs + lastbuf; const struct pipe_buf_operations *ops = buf->ops; int offset = buf->offset + buf->len; @@ -518,8 +537,8 @@ redo1: break; } bufs = pipe->nrbufs; - if (bufs < PIPE_BUFFERS) { - int newbuf = (pipe->curbuf + bufs) & (PIPE_BUFFERS-1); + if (bufs < pipe->buffers) { + int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1); struct pipe_buffer *buf = pipe->bufs + newbuf; struct page *page = pipe->tmp_page; char *src; @@ -580,7 +599,7 @@ redo2: if (!total_len) break; } - if (bufs < PIPE_BUFFERS) + if (bufs < pipe->buffers) continue; if (filp->f_flags & O_NONBLOCK) { if (!ret) @@ -640,7 +659,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) nrbufs = pipe->nrbufs; while (--nrbufs >= 0) { count += pipe->bufs[buf].len; - buf = (buf+1) & (PIPE_BUFFERS-1); + buf = (buf+1) & (pipe->buffers - 1); } mutex_unlock(&inode->i_mutex); @@ -671,7 +690,7 @@ pipe_poll(struct file *filp, poll_table *wait) } if (filp->f_mode & FMODE_WRITE) { - mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0; + mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0; /* * Most Unices do not set POLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). @@ -777,36 +796,55 @@ pipe_rdwr_release(struct inode *inode, struct file *filp) static int pipe_read_open(struct inode *inode, struct file *filp) { - /* We could have perhaps used atomic_t, but this and friends - below are the only places. So it doesn't seem worthwhile. */ + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - inode->i_pipe->readers++; + + if (inode->i_pipe) { + ret = 0; + inode->i_pipe->readers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } static int pipe_write_open(struct inode *inode, struct file *filp) { + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - inode->i_pipe->writers++; + + if (inode->i_pipe) { + ret = 0; + inode->i_pipe->writers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } static int pipe_rdwr_open(struct inode *inode, struct file *filp) { + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - if (filp->f_mode & FMODE_READ) - inode->i_pipe->readers++; - if (filp->f_mode & FMODE_WRITE) - inode->i_pipe->writers++; + + if (inode->i_pipe) { + ret = 0; + if (filp->f_mode & FMODE_READ) + inode->i_pipe->readers++; + if (filp->f_mode & FMODE_WRITE) + inode->i_pipe->writers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } /* @@ -858,25 +896,32 @@ struct pipe_inode_info * alloc_pipe_info(struct inode *inode) pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL); if (pipe) { - init_waitqueue_head(&pipe->wait); - pipe->r_counter = pipe->w_counter = 1; - pipe->inode = inode; + pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL); + if (pipe->bufs) { + init_waitqueue_head(&pipe->wait); + pipe->r_counter = pipe->w_counter = 1; + pipe->inode = inode; + pipe->buffers = PIPE_DEF_BUFFERS; + return pipe; + } + kfree(pipe); } - return pipe; + return NULL; } void __free_pipe_info(struct pipe_inode_info *pipe) { int i; - for (i = 0; i < PIPE_BUFFERS; i++) { + for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) buf->ops->release(pipe, buf); } if (pipe->tmp_page) __free_page(pipe->tmp_page); + kfree(pipe->bufs); kfree(pipe); } @@ -887,17 +932,6 @@ void free_pipe_info(struct inode *inode) } static struct vfsmount *pipe_mnt __read_mostly; -static int pipefs_delete_dentry(struct dentry *dentry) -{ - /* - * At creation time, we pretended this dentry was hashed - * (by clearing DCACHE_UNHASHED bit in d_flags) - * At delete time, we restore the truth : not hashed. - * (so that dput() can proceed correctly) - */ - dentry->d_flags |= DCACHE_UNHASHED; - return 0; -} /* * pipefs_dname() is called from d_path(). @@ -909,7 +943,6 @@ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) } static const struct dentry_operations pipefs_dentry_operations = { - .d_delete = pipefs_delete_dentry, .d_dname = pipefs_dname, }; @@ -921,6 +954,8 @@ static struct inode * get_pipe_inode(void) if (!inode) goto fail_inode; + inode->i_ino = get_next_ino(); + pipe = alloc_pipe_info(inode); if (!pipe) goto fail_iput; @@ -955,7 +990,7 @@ struct file *create_write_pipe(int flags) int err; struct inode *inode; struct file *f; - struct dentry *dentry; + struct path path; struct qstr name = { .name = "" }; err = -ENFILE; @@ -964,21 +999,16 @@ struct file *create_write_pipe(int flags) goto err; err = -ENOMEM; - dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name); - if (!dentry) + path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name); + if (!path.dentry) goto err_inode; + path.mnt = mntget(pipe_mnt); - dentry->d_op = &pipefs_dentry_operations; - /* - * We dont want to publish this dentry into global dentry hash table. - * We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED - * This permits a working /proc/$pid/fd/XXX on pipes - */ - dentry->d_flags &= ~DCACHE_UNHASHED; - d_instantiate(dentry, inode); + d_set_d_op(path.dentry, &pipefs_dentry_operations); + d_instantiate(path.dentry, inode); err = -ENFILE; - f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipefifo_fops); + f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops); if (!f) goto err_dentry; f->f_mapping = inode->i_mapping; @@ -990,7 +1020,7 @@ struct file *create_write_pipe(int flags) err_dentry: free_pipe_info(inode); - dput(dentry); + path_put(&path); return ERR_PTR(err); err_inode: @@ -1009,20 +1039,14 @@ void free_write_pipe(struct file *f) struct file *create_read_pipe(struct file *wrf, int flags) { - struct file *f = get_empty_filp(); + /* Grab pipe from the writer */ + struct file *f = alloc_file(&wrf->f_path, FMODE_READ, + &read_pipefifo_fops); if (!f) return ERR_PTR(-ENFILE); - /* Grab pipe from the writer */ - f->f_path = wrf->f_path; path_get(&wrf->f_path); - f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping; - - f->f_pos = 0; f->f_flags = O_RDONLY | (flags & O_NONBLOCK); - f->f_op = &read_pipefifo_fops; - f->f_mode = FMODE_READ; - f->f_version = 0; return f; } @@ -1098,21 +1122,156 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes) } /* + * Allocate a new array of pipe buffers and copy the info over. Returns the + * pipe size if successful, or return -ERROR on error. + */ +static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) +{ + struct pipe_buffer *bufs; + + /* + * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't + * expect a lot of shrink+grow operations, just free and allocate + * again like we would do for growing. If the pipe currently + * contains more buffers than arg, then return busy. + */ + if (nr_pages < pipe->nrbufs) + return -EBUSY; + + bufs = kcalloc(nr_pages, sizeof(struct pipe_buffer), GFP_KERNEL); + if (unlikely(!bufs)) + return -ENOMEM; + + /* + * The pipe array wraps around, so just start the new one at zero + * and adjust the indexes. + */ + if (pipe->nrbufs) { + unsigned int tail; + unsigned int head; + + tail = pipe->curbuf + pipe->nrbufs; + if (tail < pipe->buffers) + tail = 0; + else + tail &= (pipe->buffers - 1); + + head = pipe->nrbufs - tail; + if (head) + memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer)); + if (tail) + memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); + } + + pipe->curbuf = 0; + kfree(pipe->bufs); + pipe->bufs = bufs; + pipe->buffers = nr_pages; + return nr_pages * PAGE_SIZE; +} + +/* + * Currently we rely on the pipe array holding a power-of-2 number + * of pages. + */ +static inline unsigned int round_pipe_size(unsigned int size) +{ + unsigned long nr_pages; + + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; +} + +/* + * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax + * will return an error. + */ +int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buf, lenp, ppos); + if (ret < 0 || !write) + return ret; + + pipe_max_size = round_pipe_size(pipe_max_size); + return ret; +} + +/* + * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same + * location, so checking ->i_pipe is not enough to verify that this is a + * pipe. + */ +struct pipe_inode_info *get_pipe_info(struct file *file) +{ + struct inode *i = file->f_path.dentry->d_inode; + + return S_ISFIFO(i->i_mode) ? i->i_pipe : NULL; +} + +long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pipe_inode_info *pipe; + long ret; + + pipe = get_pipe_info(file); + if (!pipe) + return -EBADF; + + mutex_lock(&pipe->inode->i_mutex); + + switch (cmd) { + case F_SETPIPE_SZ: { + unsigned int size, nr_pages; + + size = round_pipe_size(arg); + nr_pages = size >> PAGE_SHIFT; + + ret = -EINVAL; + if (!nr_pages) + goto out; + + if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) { + ret = -EPERM; + goto out; + } + ret = pipe_set_size(pipe, nr_pages); + break; + } + case F_GETPIPE_SZ: + ret = pipe->buffers * PAGE_SIZE; + break; + default: + ret = -EINVAL; + break; + } + +out: + mutex_unlock(&pipe->inode->i_mutex); + return ret; +} + +static const struct super_operations pipefs_ops = { + .destroy_inode = free_inode_nonrcu, +}; + +/* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ -static int pipefs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *pipefs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC, mnt); + return mount_pseudo(fs_type, "pipe:", &pipefs_ops, PIPEFS_MAGIC); } static struct file_system_type pipe_fs_type = { .name = "pipefs", - .get_sb = pipefs_get_sb, + .mount = pipefs_mount, .kill_sb = kill_anon_super, }; @@ -1133,7 +1292,7 @@ static int __init init_pipe_fs(void) static void __exit exit_pipe_fs(void) { unregister_filesystem(&pipe_fs_type); - mntput(pipe_mnt); + mntput_long(pipe_mnt); } fs_initcall(init_pipe_fs); |