From: "Ken Chen" It is really sad that we always call kmap and friends for every pipe buffer page on 64-bit arch that doesn't use HIGHMEM, or on configuration that doesn't turn on HIGHMEM. The effect of calling kmap* is visible in the execution profile when pipe code is being stressed. It is especially true on amd's x86-64 platform where kmap() has to traverse through numa node index calculation in order to convert struct page * to kernel virtual address. It is fairly pointless to perform that calculation repeatly on system with no highmem (i.e., 64-bit arch like x86-64). This patch caches kernel pipe buffer page's kernel vaddr to speed up pipe buffer mapping functions. There is another suboptimal block in pipe_read() where wake_up is called twice. I think it was an oversight since in pipe_write(), it looks like it is doing the right thing. Signed-off-by: Ken Chen Signed-off-by: Andrew Morton --- fs/pipe.c | 34 ++++++++++++++++++++++++++-------- 1 files changed, 26 insertions(+), 8 deletions(-) diff -puN fs/pipe.c~cache-pipe-buf-page-address-for-non-highmem-arch fs/pipe.c --- a/fs/pipe.c~cache-pipe-buf-page-address-for-non-highmem-arch +++ a/fs/pipe.c @@ -21,6 +21,21 @@ #include #include +#ifdef CONFIG_HIGHMEM +#define pipe_kmap kmap +#define pipe_kmap_atomic kmap_atomic +#define pipe_kunmap kunmap +#define pipe_kunmap_atomic kunmap_atomic +#else /* CONFIG_HIGHMEM */ +static inline void *pipe_kmap(struct page *page) +{ + return (void *) page->private; +} +#define pipe_kmap_atomic(page, type) pipe_kmap(page) +#define pipe_kunmap(page) do { } while (0) +#define pipe_kunmap_atomic(page, type) do { } while (0) +#endif + /* * We use a start+len construction, which provides full use of the * allocated memory. @@ -169,10 +184,10 @@ void *generic_pipe_buf_map(struct pipe_i { if (atomic) { buf->flags |= PIPE_BUF_FLAG_ATOMIC; - return kmap_atomic(buf->page, KM_USER0); + return pipe_kmap_atomic(buf->page, KM_USER0); } - return kmap(buf->page); + return pipe_kmap(buf->page); } void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, @@ -180,9 +195,9 @@ void generic_pipe_buf_unmap(struct pipe_ { if (buf->flags & PIPE_BUF_FLAG_ATOMIC) { buf->flags &= ~PIPE_BUF_FLAG_ATOMIC; - kunmap_atomic(map_data, KM_USER0); + pipe_kunmap_atomic(map_data, KM_USER0); } else - kunmap(buf->page); + pipe_kunmap(buf->page); } int generic_pipe_buf_steal(struct pipe_inode_info *pipe, @@ -316,6 +331,7 @@ redo: if (do_wakeup) { wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); + do_wakeup = 0; } pipe_wait(pipe); } @@ -423,6 +439,8 @@ redo1: ret = ret ? : -ENOMEM; break; } + page->private = (unsigned long) + page_address(page); pipe->tmp_page = page; } /* Always wake up, even if the copy fails. Otherwise @@ -438,16 +456,16 @@ redo1: iov_fault_in_pages_read(iov, chars); redo2: if (atomic) - src = kmap_atomic(page, KM_USER0); + src = pipe_kmap_atomic(page, KM_USER0); else - src = kmap(page); + src = pipe_kmap(page); error = pipe_iov_copy_from_user(src, iov, chars, atomic); if (atomic) - kunmap_atomic(src, KM_USER0); + pipe_kunmap_atomic(src, KM_USER0); else - kunmap(page); + pipe_kunmap(page); if (unlikely(error)) { if (atomic) { _