io_uring: track io length in async_list based on bytes

commit 9310a7ba6de8cce6209e3e8a3cdf733f824cdd9b upstream.

We are using PAGE_SIZE as the unit to determine if the total len in
async_list has exceeded max_pages, it's not fair for smaller io sizes.
For example, if we are doing 1k-size io streams, we will never exceed
max_pages since len >>= PAGE_SHIFT always gets zero. So use original
bytes to make it more accurate.
Signed-off-by: NZhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NJoseph Qi <joseph.qi@linux.alibaba.com>
Reviewed-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>

fs/io_uring.c

@@ -202,7 +202,7 @@ struct async_list {
 
 	struct file		*file;
 	off_t			io_end;
-	size_t			io_pages;
+	size_t			io_len;
 };
 
 struct io_ring_ctx {
@@ -1157,28 +1157,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
 	off_t io_end = kiocb->ki_pos + len;
 
 	if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) {
-		unsigned long max_pages;
+		unsigned long max_bytes;
 
 		/* Use 8x RA size as a decent limiter for both reads/writes */
-		max_pages = filp->f_ra.ra_pages;
-		if (!max_pages)
-			max_pages = VM_MAX_READAHEAD >> (PAGE_SHIFT - 10);
-		max_pages *= 8;
-
-		/* If max pages are exceeded, reset the state */
-		len >>= PAGE_SHIFT;
-		if (async_list->io_pages + len <= max_pages) {
+		max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3);
+		if (!max_bytes)
+			max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3);
+
+		/* If max len are exceeded, reset the state */
+		if (async_list->io_len + len <= max_bytes) {
 			req->flags |= REQ_F_SEQ_PREV;
-			async_list->io_pages += len;
+			async_list->io_len += len;
 		} else {
 			io_end = 0;
-			async_list->io_pages = 0;
+			async_list->io_len = 0;
 		}
 	}
 
 	/* New file? Reset state. */
 	if (async_list->file != filp) {
-		async_list->io_pages = 0;
+		async_list->io_len = 0;
 		async_list->file = filp;
 	}
 	async_list->io_end = io_end;

include/linux/mm.h

@@ -26,6 +26,7 @@
 #include <linux/page_ref.h>
 #include <linux/memremap.h>
 #include <linux/overflow.h>
+#include <linux/sizes.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -2489,6 +2490,7 @@ void task_dirty_inc(struct task_struct *tsk);
 /* readahead.c */
 #define VM_MAX_READAHEAD	128	/* kbytes */
 #define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */
+#define VM_READAHEAD_PAGES	(SZ_128K / PAGE_SIZE)
 
 int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read);