f2fs: read contiguous sit entry pages by merging for mount performance

Previously we read sit entries page one by one, this method lost the chance
of reading contiguous page together. So we read pages as contiguous as
possible for better mount performance.

change log:
 o merge judgements/use 'Continue' or 'Break' instead of 'Goto' as Gu Zheng
   suggested.
 o add mark_page_accessed() before release page to delay VM reclaiming.
 o remove '*order' for simplification of function as Jaegeuk Kim suggested.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
[Jaegeuk Kim: fix a bug on the block address calculation]
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a1acaa0..6dd1dc1 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -14,6 +14,7 @@
 #include <linux/blkdev.h>
 #include <linux/prefetch.h>
 #include <linux/vmalloc.h>
+#include <linux/swap.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -1706,41 +1707,89 @@
 	return restore_curseg_summaries(sbi);
 }
 
+static int ra_sit_pages(struct f2fs_sb_info *sbi, int start, int nrpages)
+{
+	struct address_space *mapping = sbi->meta_inode->i_mapping;
+	struct page *page;
+	block_t blk_addr, prev_blk_addr = 0;
+	int sit_blk_cnt = SIT_BLK_CNT(sbi);
+	int blkno = start;
+
+	for (; blkno < start + nrpages && blkno < sit_blk_cnt; blkno++) {
+
+		blk_addr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK);
+
+		if (blkno != start && prev_blk_addr + 1 != blk_addr)
+			break;
+		prev_blk_addr = blk_addr;
+repeat:
+		page = grab_cache_page(mapping, blk_addr);
+		if (!page) {
+			cond_resched();
+			goto repeat;
+		}
+		if (PageUptodate(page)) {
+			mark_page_accessed(page);
+			f2fs_put_page(page, 1);
+			continue;
+		}
+
+		submit_read_page(sbi, page, blk_addr, READ_SYNC);
+
+		mark_page_accessed(page);
+		f2fs_put_page(page, 0);
+	}
+
+	f2fs_submit_read_bio(sbi, READ_SYNC);
+	return blkno - start;
+}
+
 static void build_sit_entries(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
 	struct f2fs_summary_block *sum = curseg->sum_blk;
-	unsigned int start;
+	int sit_blk_cnt = SIT_BLK_CNT(sbi);
+	unsigned int i, start, end;
+	unsigned int readed, start_blk = 0;
+	int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
 
-	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
-		struct seg_entry *se = &sit_i->sentries[start];
-		struct f2fs_sit_block *sit_blk;
-		struct f2fs_sit_entry sit;
-		struct page *page;
-		int i;
+	do {
+		readed = ra_sit_pages(sbi, start_blk, nrpages);
 
-		mutex_lock(&curseg->curseg_mutex);
-		for (i = 0; i < sits_in_cursum(sum); i++) {
-			if (le32_to_cpu(segno_in_journal(sum, i)) == start) {
-				sit = sit_in_journal(sum, i);
-				mutex_unlock(&curseg->curseg_mutex);
-				goto got_it;
+		start = start_blk * sit_i->sents_per_block;
+		end = (start_blk + readed) * sit_i->sents_per_block;
+
+		for (; start < end && start < TOTAL_SEGS(sbi); start++) {
+			struct seg_entry *se = &sit_i->sentries[start];
+			struct f2fs_sit_block *sit_blk;
+			struct f2fs_sit_entry sit;
+			struct page *page;
+
+			mutex_lock(&curseg->curseg_mutex);
+			for (i = 0; i < sits_in_cursum(sum); i++) {
+				if (le32_to_cpu(segno_in_journal(sum, i)) == start) {
+					sit = sit_in_journal(sum, i);
+					mutex_unlock(&curseg->curseg_mutex);
+					goto got_it;
+				}
+			}
+			mutex_unlock(&curseg->curseg_mutex);
+
+			page = get_current_sit_page(sbi, start);
+			sit_blk = (struct f2fs_sit_block *)page_address(page);
+			sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
+			f2fs_put_page(page, 1);
+got_it:
+			check_block_count(sbi, start, &sit);
+			seg_info_from_raw_sit(se, &sit);
+			if (sbi->segs_per_sec > 1) {
+				struct sec_entry *e = get_sec_entry(sbi, start);
+				e->valid_blocks += se->valid_blocks;
 			}
 		}
-		mutex_unlock(&curseg->curseg_mutex);
-		page = get_current_sit_page(sbi, start);
-		sit_blk = (struct f2fs_sit_block *)page_address(page);
-		sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
-		f2fs_put_page(page, 1);
-got_it:
-		check_block_count(sbi, start, &sit);
-		seg_info_from_raw_sit(se, &sit);
-		if (sbi->segs_per_sec > 1) {
-			struct sec_entry *e = get_sec_entry(sbi, start);
-			e->valid_blocks += se->valid_blocks;
-		}
-	}
+		start_blk += readed;
+	} while (start_blk < sit_blk_cnt);
 }
 
 static void init_free_segmap(struct f2fs_sb_info *sbi)