summaryrefslogtreecommitdiff
path: root/fs/fuse
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-12-01 01:12:13 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-12-01 01:12:13 +0300
commit6a965666b7e7475c2f8c8e724703db58b8a8a445 (patch)
tree0fcd268af15fb52cd32343572f5eaee7bf52e0d8 /fs/fuse
parent32ef9553635ab1236c33951a8bd9b5af1c3b1646 (diff)
parent3c0edea9b29f9be6c093f236f762202b30ac9431 (diff)
downloadlinux-6a965666b7e7475c2f8c8e724703db58b8a8a445.tar.xz
Merge tag 'notifications-pipe-prep-20191115' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
Pull pipe rework from David Howells: "This is my set of preparatory patches for building a general notification queue on top of pipes. It makes a number of significant changes: - It removes the nr_exclusive argument from __wake_up_sync_key() as this is always 1. This prepares for the next step: - Adds wake_up_interruptible_sync_poll_locked() so that poll can be woken up from a function that's holding the poll waitqueue spinlock. - Change the pipe buffer ring to be managed in terms of unbounded head and tail indices rather than bounded index and length. This means that reading the pipe only needs to modify one index, not two. - A selection of helper functions are provided to query the state of the pipe buffer, plus a couple to apply updates to the pipe indices. - The pipe ring is allowed to have kernel-reserved slots. This allows many notification messages to be spliced in by the kernel without allowing userspace to pin too many pages if it writes to the same pipe. - Advance the head and tail indices inside the pipe waitqueue lock and use wake_up_interruptible_sync_poll_locked() to poke poll without having to take the lock twice. - Rearrange pipe_write() to preallocate the buffer it is going to write into and then drop the spinlock. This allows kernel notifications to then be added the ring whilst it is filling the buffer it allocated. The read side is stalled because the pipe mutex is still held. - Don't wake up readers on a pipe if there was already data in it when we added more. - Don't wake up writers on a pipe if the ring wasn't full before we removed a buffer" * tag 'notifications-pipe-prep-20191115' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: pipe: Remove sync on wake_ups pipe: Increase the writer-wakeup threshold to reduce context-switch count pipe: Check for ring full inside of the spinlock in pipe_write() pipe: Remove redundant wakeup from pipe_write() pipe: Rearrange sequence in pipe_write() to preallocate slot pipe: Conditionalise wakeup in pipe_read() pipe: Advance tail pointer inside of wait spinlock in pipe_read() pipe: Allow pipes to have kernel-reserved slots pipe: Use head and tail pointers for the ring, not cursor and length Add wake_up_interruptible_sync_poll_locked() Remove the nr_exclusive argument from __wake_up_sync_key() pipe: Reduce #inclusion of pipe_fs_i.h
Diffstat (limited to 'fs/fuse')
-rw-r--r--fs/fuse/dev.c31
1 files changed, 18 insertions, 13 deletions
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed1abc9e33cf..a31f9072c123 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -705,7 +705,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
cs->pipebufs++;
cs->nr_segs--;
} else {
- if (cs->nr_segs == cs->pipe->buffers)
+ if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
page = alloc_page(GFP_HIGHUSER);
@@ -881,7 +881,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
struct pipe_buffer *buf;
int err;
- if (cs->nr_segs == cs->pipe->buffers)
+ if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
err = unlock_request(cs->req);
@@ -1343,7 +1343,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
if (!fud)
return -EPERM;
- bufs = kvmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
+ bufs = kvmalloc_array(pipe->max_usage, sizeof(struct pipe_buffer),
GFP_KERNEL);
if (!bufs)
return -ENOMEM;
@@ -1355,7 +1355,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
if (ret < 0)
goto out;
- if (pipe->nrbufs + cs.nr_segs > pipe->buffers) {
+ if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
ret = -EIO;
goto out;
}
@@ -1937,6 +1937,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
+ unsigned int head, tail, mask, count;
unsigned nbuf;
unsigned idx;
struct pipe_buffer *bufs;
@@ -1951,8 +1952,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
pipe_lock(pipe);
- bufs = kvmalloc_array(pipe->nrbufs, sizeof(struct pipe_buffer),
- GFP_KERNEL);
+ head = pipe->head;
+ tail = pipe->tail;
+ mask = pipe->ring_size - 1;
+ count = head - tail;
+
+ bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
if (!bufs) {
pipe_unlock(pipe);
return -ENOMEM;
@@ -1960,8 +1965,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
nbuf = 0;
rem = 0;
- for (idx = 0; idx < pipe->nrbufs && rem < len; idx++)
- rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;
+ for (idx = tail; idx < head && rem < len; idx++)
+ rem += pipe->bufs[idx & mask].len;
ret = -EINVAL;
if (rem < len)
@@ -1972,16 +1977,16 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct pipe_buffer *ibuf;
struct pipe_buffer *obuf;
- BUG_ON(nbuf >= pipe->buffers);
- BUG_ON(!pipe->nrbufs);
- ibuf = &pipe->bufs[pipe->curbuf];
+ BUG_ON(nbuf >= pipe->ring_size);
+ BUG_ON(tail == head);
+ ibuf = &pipe->bufs[tail & mask];
obuf = &bufs[nbuf];
if (rem >= ibuf->len) {
*obuf = *ibuf;
ibuf->ops = NULL;
- pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
- pipe->nrbufs--;
+ tail++;
+ pipe->tail = tail;
} else {
if (!pipe_buf_get(pipe, ibuf))
goto out_free;