@@ -314,6 +314,7 @@ enum rw_hint {
#define IOCB_SYNC (1 << 5)
#define IOCB_WRITE (1 << 6)
#define IOCB_NOWAIT (1 << 7)
+#define IOCB_UNCACHED (1 << 8)
struct kiocb {
struct file *ki_filp;
@@ -3418,6 +3419,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
if (flags & RWF_APPEND)
ki->ki_flags |= IOCB_APPEND;
+ if (flags & RWF_UNCACHED)
+ ki->ki_flags |= IOCB_UNCACHED;
return 0;
}
@@ -299,8 +299,11 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO O_APPEND */
#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+/* drop cache after reading or writing data */
+#define RWF_UNCACHED ((__force __kernel_rwf_t)0x00000040)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND)
+ RWF_APPEND | RWF_UNCACHED)
#endif /* _UAPI_LINUX_FS_H */
@@ -1990,6 +1990,13 @@ static void shrink_readahead_size_eio(struct file *filp,
ra->ra_pages /= 4;
}
+static void buffered_put_page(struct page *page, bool clear_mapping)
+{
+ if (clear_mapping)
+ page->mapping = NULL;
+ put_page(page);
+}
+
/**
* generic_file_buffered_read - generic file read routine
* @iocb: the iocb to read
@@ -2013,6 +2020,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct file_ra_state *ra = &filp->f_ra;
+ bool did_dio_begin = false;
loff_t *ppos = &iocb->ki_pos;
pgoff_t index;
pgoff_t last_index;
@@ -2032,6 +2040,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
offset = *ppos & ~PAGE_MASK;
for (;;) {
+ bool clear_mapping = false;
struct page *page;
pgoff_t end_index;
loff_t isize;
@@ -2048,6 +2057,13 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
if (!page) {
if (iocb->ki_flags & IOCB_NOWAIT)
goto would_block;
+ /* UNCACHED implies no read-ahead */
+ if (iocb->ki_flags & IOCB_UNCACHED) {
+ did_dio_begin = true;
+ /* block truncate for UNCACHED reads */
+ inode_dio_begin(inode);
+ goto no_cached_page;
+ }
page_cache_sync_readahead(mapping,
ra, filp,
index, last_index - index);
@@ -2106,7 +2122,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
isize = i_size_read(inode);
end_index = (isize - 1) >> PAGE_SHIFT;
if (unlikely(!isize || index > end_index)) {
- put_page(page);
+ buffered_put_page(page, clear_mapping);
goto out;
}
@@ -2115,7 +2131,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
if (index == end_index) {
nr = ((isize - 1) & ~PAGE_MASK) + 1;
if (nr <= offset) {
- put_page(page);
+ buffered_put_page(page, clear_mapping);
goto out;
}
}
@@ -2147,7 +2163,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
offset &= ~PAGE_MASK;
prev_offset = offset;
- put_page(page);
+ buffered_put_page(page, clear_mapping);
written += ret;
if (!iov_iter_count(iter))
goto out;
@@ -2189,7 +2205,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
- put_page(page);
+ buffered_put_page(page, clear_mapping);
error = 0;
goto find_page;
}
@@ -2206,7 +2222,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
* invalidate_mapping_pages got it
*/
unlock_page(page);
- put_page(page);
+ buffered_put_page(page, clear_mapping);
goto find_page;
}
unlock_page(page);
@@ -2221,7 +2237,7 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
- put_page(page);
+ buffered_put_page(page, clear_mapping);
goto out;
no_cached_page:
@@ -2234,7 +2250,15 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
error = -ENOMEM;
goto out;
}
- error = add_to_page_cache_lru(page, mapping, index,
+ if (iocb->ki_flags & IOCB_UNCACHED) {
+ __SetPageLocked(page);
+ page->mapping = mapping;
+ page->index = index;
+ clear_mapping = true;
+ goto readpage;
+ }
+
+ error = add_to_page_cache(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error) {
put_page(page);
@@ -2250,6 +2274,8 @@ static ssize_t generic_file_buffered_read(struct kiocb *iocb,
would_block:
error = -EAGAIN;
out:
+ if (did_dio_begin)
+ inode_dio_end(inode);
ra->prev_pos = prev_index;
ra->prev_pos <<= PAGE_SHIFT;
ra->prev_pos |= prev_offset;
If RWF_UNCACHED is set for io_uring (or preadv2(2)), we'll use private pages for the buffered reads. These pages will never be inserted into the page cache, and they are simply droped when we have done the copy at the end of IO. If pages in the read range are already in the page cache, then use those for just copying the data instead of starting IO on private pages. A previous solution used the page cache even for non-cached ranges, but the cost of doing so was too high. Removing nodes at the end is expensive, even with LRU bypass. On top of that, repeatedly instantiating new xarray nodes is very costly, as it needs to memset 576 bytes of data, and freeing said nodes involve an RCU call per node as well. All that adds up, making uncached somewhat slower than O_DIRECT. With the current solition, we're basically at O_DIRECT levels of performance for RWF_UNCACHED IO. Protect against truncate the same way O_DIRECT does, by calling inode_dio_begin() to elevate the inode->i_dio_count. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- include/linux/fs.h | 3 +++ include/uapi/linux/fs.h | 5 ++++- mm/filemap.c | 40 +++++++++++++++++++++++++++++++++------- 3 files changed, 40 insertions(+), 8 deletions(-)