Merge branch 'splice' of git://brick.kernel.dk/data/git/linux-2.6-block

* 'splice' of git://brick.kernel.dk/data/git/linux-2.6-block:
  [PATCH] splice: add ->splice_write support for /dev/null
  [PATCH] splice: rearrange moving to/from pipe helpers
  [PATCH] Add support for the sys_vmsplice syscall
  [PATCH] splice: fix offset problems
  [PATCH] splice: fix min() warning

11 files changed, 328 insertions, 77 deletions

diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index e307988112..bcb80ca5cf 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1610,5 +1610,6 @@ sys_call_table:
         data8 sys_get_robust_list
         data8 sys_sync_file_range               // 1300
         data8 sys_tee
+        data8 sys_vmsplice
 
         .org sys_call_table + 8*NR_syscalls     // guard against failures to increase NR_syscalls
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 8d15226905..0b98eea73c 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -324,6 +324,7 @@ COMPAT_SYS(ppoll)
 SYSCALL(unshare)
 SYSCALL(splice)
 SYSCALL(tee)
+SYSCALL(vmsplice)
 
 /*
  * please add new calls to arch/powerpc/platforms/cell/spu_callbacks.c
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
index deb3afb944..b283380a2a 100644
--- a/arch/powerpc/platforms/cell/spu_callbacks.c
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -318,6 +318,7 @@ void *spu_syscall_table[] = {
         [__NR_unshare]                  sys_unshare,
         [__NR_splice]                   sys_splice,
         [__NR_tee]                      sys_tee,
+        [__NR_vmsplice]                 sys_vmsplice,
 };
 
 long spu_sys_callback(struct spu_syscall_block *s)
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 66719f9d29..1fa9fa157c 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -27,6 +27,7 @@
 #include <linux/crash_dump.h>
 #include <linux/backing-dev.h>
 #include <linux/bootmem.h>
+#include <linux/pipe_fs_i.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -578,6 +579,18 @@ static ssize_t write_null(struct file * file, const char __user * buf,
         return count;
 }
 
+static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf,
+                        struct splice_desc *sd)
+{
+        return sd->len;
+}
+
+static ssize_t splice_write_null(struct pipe_inode_info *pipe,struct file *out,
+                                 loff_t *ppos, size_t len, unsigned int flags)
+{
+        return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
+}
+
 #ifdef CONFIG_MMU
 /*
  * For fun, we are using the MMU for this.
@@ -785,6 +798,7 @@ static struct file_operations null_fops = {
         .llseek         = null_lseek,
         .read           = read_null,
         .write          = write_null,
+        .splice_write   = splice_write_null,
 };
 
 #if defined(CONFIG_ISA) || !defined(__mc68000__)
diff --git a/fs/splice.c b/fs/splice.c
index 0559e7577a..447ebc0a37 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -27,15 +27,22 @@
 #include <linux/buffer_head.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/uio.h>
+
+struct partial_page {
+        unsigned int offset;
+        unsigned int len;
+};
 
 /*
- * Passed to the actors
+ * Passed to splice_to_pipe
  */
-struct splice_desc {
-        unsigned int len, total_len;    /* current and remaining length */
+struct splice_pipe_desc {
+        struct page **pages;            /* page map */
+        struct partial_page *partial;   /* pages[] may not be contig */
+        int nr_pages;                   /* number of pages in map */
         unsigned int flags;             /* splice flags */
-        struct file *file;              /* file to read/write */
-        loff_t pos;                     /* file position */
+        struct pipe_buf_operations *ops;/* ops associated with output pipe */
 };
 
 /*
@@ -128,6 +135,19 @@ static void page_cache_pipe_buf_unmap(struct pipe_inode_info *info,
         kunmap(buf->page);
 }
 
+static void *user_page_pipe_buf_map(struct file *file,
+                                    struct pipe_inode_info *pipe,
+                                    struct pipe_buffer *buf)
+{
+        return kmap(buf->page);
+}
+
+static void user_page_pipe_buf_unmap(struct pipe_inode_info *pipe,
+                                     struct pipe_buffer *buf)
+{
+        kunmap(buf->page);
+}
+
 static void page_cache_pipe_buf_get(struct pipe_inode_info *info,
                                     struct pipe_buffer *buf)
 {
@@ -143,19 +163,33 @@ static struct pipe_buf_operations page_cache_pipe_buf_ops = {
         .get = page_cache_pipe_buf_get,
 };
 
+static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
+                                    struct pipe_buffer *buf)
+{
+        return 1;
+}
+
+static struct pipe_buf_operations user_page_pipe_buf_ops = {
+        .can_merge = 0,
+        .map = user_page_pipe_buf_map,
+        .unmap = user_page_pipe_buf_unmap,
+        .release = page_cache_pipe_buf_release,
+        .steal = user_page_pipe_buf_steal,
+        .get = page_cache_pipe_buf_get,
+};
+
 /*
  * Pipe output worker. This sets up our pipe format with the page cache
  * pipe buffer operations. Otherwise very similar to the regular pipe_writev().
  */
-static ssize_t move_to_pipe(struct pipe_inode_info *pipe, struct page **pages,
-                            int nr_pages, unsigned long len,
-                            unsigned int offset, unsigned int flags)
+static ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
+                              struct splice_pipe_desc *spd)
 {
-        int ret, do_wakeup, i;
+        int ret, do_wakeup, page_nr;
 
         ret = 0;
         do_wakeup = 0;
-        i = 0;
+        page_nr = 0;
 
         if (pipe->inode)
                 mutex_lock(&pipe->inode->i_mutex);
@@ -171,27 +205,19 @@ static ssize_t move_to_pipe(struct pipe_inode_info *pipe, struct page **pages,
                 if (pipe->nrbufs < PIPE_BUFFERS) {
                         int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
                         struct pipe_buffer *buf = pipe->bufs + newbuf;
-                        struct page *page = pages[i++];
-                        unsigned long this_len;
 
-                        this_len = PAGE_CACHE_SIZE - offset;
-                        if (this_len > len)
-                                this_len = len;
-
-                        buf->page = page;
-                        buf->offset = offset;
-                        buf->len = this_len;
-                        buf->ops = &page_cache_pipe_buf_ops;
+                        buf->page = spd->pages[page_nr];
+                        buf->offset = spd->partial[page_nr].offset;
+                        buf->len = spd->partial[page_nr].len;
+                        buf->ops = spd->ops;
                         pipe->nrbufs++;
+                        page_nr++;
+                        ret += buf->len;
+
                         if (pipe->inode)
                                 do_wakeup = 1;