1 files changed, 452 insertions, 140 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index cdccc429325b..3d846b027fa1 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -19,8 +19,6 @@
 #include <linux/bio.h>
 #include <linux/prefetch.h>
 #include <linux/uio.h>
-#include <linux/mm.h>
-#include <linux/memcontrol.h>
 #include <linux/cleancache.h>
 
 #include "f2fs.h"
@@ -30,6 +28,11 @@
 #include <trace/events/f2fs.h>
 #include <trace/events/android_fs.h>
 
+#define NUM_PREALLOC_POST_READ_CTXS	128
+
+static struct kmem_cache *bio_post_read_ctx_cache;
+static mempool_t *bio_post_read_ctx_pool;
+
 static bool __is_cp_guaranteed(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
@@ -50,11 +53,77 @@ static bool __is_cp_guaranteed(struct page *page)
 	return false;
 }
 
-static void f2fs_read_end_io(struct bio *bio)
+/* postprocessing steps for read bios */
+enum bio_post_read_step {
+	STEP_INITIAL = 0,
+	STEP_DECRYPT,
+};
+
+struct bio_post_read_ctx {
+	struct bio *bio;
+	struct work_struct work;
+	unsigned int cur_step;
+	unsigned int enabled_steps;
+};
+
+static void __read_end_io(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct page *page;
+	struct bio_vec *bv;
 	int i;
 
+	bio_for_each_segment_all(bv, bio, i) {
+		page = bv->bv_page;
+
+		/* PG_error was set if any post_read step failed */
+		if (bio->bi_error || PageError(page)) {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	if (bio->bi_private)
+		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+	bio_put(bio);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
+
+static void decrypt_work(struct work_struct *work)
+{
+	struct bio_post_read_ctx *ctx =
+		container_of(work, struct bio_post_read_ctx, work);
+
+	fscrypt_decrypt_bio(ctx->bio);
+
+	bio_post_read_processing(ctx);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
+{
+	switch (++ctx->cur_step) {
+	case STEP_DECRYPT:
+		if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
+			INIT_WORK(&ctx->work, decrypt_work);
+			fscrypt_enqueue_decrypt_work(&ctx->work);
+			return;
+		}
+		ctx->cur_step++;
+		/* fall-through */
+	default:
+		__read_end_io(ctx->bio);
+	}
+}
+
+static bool f2fs_bio_post_read_required(struct bio *bio)
+{
+	return bio->bi_private && !bio->bi_error;
+}
+
+static void f2fs_read_end_io(struct bio *bio)
+{
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
 		f2fs_show_injection_info(FAULT_IO);
@@ -62,28 +131,15 @@ static void f2fs_read_end_io(struct bio *bio)
 	}
 #endif
 
-	if (f2fs_bio_encrypted(bio)) {
-		if (bio->bi_error) {
-			fscrypt_release_ctx(bio->bi_private);
-		} else {
-			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
-			return;
-		}
-	}
-
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
+	if (f2fs_bio_post_read_required(bio)) {
+		struct bio_post_read_ctx *ctx = bio->bi_private;
 
-		if (!bio->bi_error) {
-			if (!PageUptodate(page))
-				SetPageUptodate(page);
-		} else {
-			ClearPageUptodate(page);
-			SetPageError(page);
-		}
-		unlock_page(page);
+		ctx->cur_step = STEP_INITIAL;
+		bio_post_read_processing(ctx);
+		return;
 	}
-	bio_put(bio);
+
+	__read_end_io(bio);
 }
 
 static void f2fs_write_end_io(struct bio *bio)
@@ -111,8 +167,13 @@ static void f2fs_write_end_io(struct bio *bio)
 
 		if (unlikely(bio->bi_error)) {
 			set_bit(AS_EIO, &page->mapping->flags);
-			f2fs_stop_checkpoint(sbi, true);
+			if (type == F2FS_WB_CP_DATA)
+				f2fs_stop_checkpoint(sbi, true);
 		}
+
+		f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
+					page->index != nid_of_node(page));
+
 		dec_page_count(sbi, type);
 		clear_cold_data(page);
 		end_page_writeback(page);
@@ -168,15 +229,25 @@ static bool __same_bdev(struct f2fs_sb_info *sbi,
  * Low-level block read/write IO operations.
  */
 static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
-				int npages, bool is_read)
+				struct writeback_control *wbc,
+				int npages, bool is_read,
+				enum page_type type, enum temp_type temp)
 {
 	struct bio *bio;
 
 	bio = f2fs_bio_alloc(sbi, npages, true);
 
 	f2fs_target_device(sbi, blk_addr, bio);
-	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
-	bio->bi_private = is_read ? NULL : sbi;
+	if (is_read) {
+		bio->bi_end_io = f2fs_read_end_io;
+		bio->bi_private = NULL;
+	} else {
+		bio->bi_end_io = f2fs_write_end_io;
+		bio->bi_private = sbi;
+		bio->bi_write_hint = io_type_to_rw_hint(sbi, type, temp);
+	}
+	if (wbc)
+		wbc_init_bio(wbc, bio);
 
 	return bio;
 }
@@ -187,13 +258,12 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 	if (!is_read_io(bio_op(bio))) {
 		unsigned int start;
 
-		if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
-			current->plug && (type == DATA || type == NODE))
-			blk_finish_plug(current->plug);
-
 		if (type != DATA && type != NODE)
 			goto submit_io;
 
+		if (f2fs_sb_has_blkzoned(sbi->sb) && current->plug)
+			blk_finish_plug(current->plug);
+
 		start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
 		start %= F2FS_IO_SIZE(sbi);
 
@@ -368,11 +438,13 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	struct page *page = fio->encrypted_page ?
 			fio->encrypted_page : fio->page;
 
+	verify_block_addr(fio, fio->new_blkaddr);
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc,
+				1, is_read_io(fio->op), fio->type, fio->temp);
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		bio_put(bio);
@@ -412,8 +484,8 @@ next:
 	}
 
 	if (fio->old_blkaddr != NEW_ADDR)
-		verify_block_addr(sbi, fio->old_blkaddr);
-	verify_block_addr(sbi, fio->new_blkaddr);
+		verify_block_addr(fio, fio->old_blkaddr);
+	verify_block_addr(fio, fio->new_blkaddr);
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
@@ -434,8 +506,9 @@ alloc_new:
 			dec_page_count(sbi, WB_DATA_TYPE(bio_page));
 			goto out_fail;
 		}
-		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						BIO_MAX_PAGES, false);
+		io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc,
+						BIO_MAX_PAGES, false,
+						fio->type, fio->temp);
 		io->fio = *fio;
 	}
 
@@ -444,6 +517,9 @@ alloc_new:
 		goto alloc_new;
 	}
 
+	if (fio->io_wbc)
+		wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE);
+
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
@@ -460,29 +536,33 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 							 unsigned nr_pages)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct fscrypt_ctx *ctx = NULL;
 	struct bio *bio;
-
-	if (f2fs_encrypted_file(inode)) {
-		ctx = fscrypt_get_ctx(inode, GFP_NOFS);
-		if (IS_ERR(ctx))
-			return ERR_CAST(ctx);
-
-		/* wait the page to be moved by cleaning */
-		f2fs_wait_on_block_writeback(sbi, blkaddr);
-	}
+	struct bio_post_read_ctx *ctx;
+	unsigned int post_read_steps = 0;
 
 	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
-	if (!bio) {
-		if (ctx)
-			fscrypt_release_ctx(ctx);
+	if (!bio)
 		return ERR_PTR(-ENOMEM);
-	}
 	f2fs_target_device(sbi, blkaddr, bio);
 	bio->bi_end_io = f2fs_read_end_io;
-	bio->bi_private = ctx;
 	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
+	if (f2fs_encrypted_file(inode))
+		post_read_steps |= 1 << STEP_DECRYPT;
+	if (post_read_steps) {
+		ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+		if (!ctx) {
+			bio_put(bio);
+			return ERR_PTR(-ENOMEM);
+		}
+		ctx->bio = bio;
+		ctx->enabled_steps = post_read_steps;
+		bio->bi_private = ctx;
+
+		/* wait the page to be moved by cleaning */
+		f2fs_wait_on_block_writeback(sbi, blkaddr);
+	}
+
 	return bio;
 }
 
@@ -782,7 +862,7 @@ got_it:
 	return page;
 }
 
-static int __allocate_data_block(struct dnode_of_data *dn)
+static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -807,7 +887,7 @@ alloc:
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-					&sum, CURSEG_WARM_DATA, NULL, false);
+					&sum, seg_type, NULL, false);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -819,21 +899,16 @@ alloc:
 	return 0;
 }
 
-static inline bool __force_buffered_io(struct inode *inode, int rw)
-{
-	return (f2fs_encrypted_file(inode) ||
-			(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
-			F2FS_I_SB(inode)->s_ndevs);
-}
-
 int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct f2fs_map_blocks map;
+	int flag;
 	int err = 0;
+	bool direct_io = iocb->ki_flags & IOCB_DIRECT;
 
 	/* convert inline data for Direct I/O*/
-	if (iocb->ki_flags & IOCB_DIRECT) {
+	if (direct_io) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
 			return err;
@@ -850,19 +925,33 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 		map.m_len = 0;
 
 	map.m_next_pgofs = NULL;
+	map.m_next_extent = NULL;
+	map.m_seg_type = NO_CHECK_TYPE;
 
-	if (iocb->ki_flags & IOCB_DIRECT)
-		return f2fs_map_blocks(inode, &map, 1,
-			__force_buffered_io(inode, WRITE) ?
-				F2FS_GET_BLOCK_PRE_AIO :
-				F2FS_GET_BLOCK_PRE_DIO);
+	if (direct_io) {
+		map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint);
+		flag = f2fs_force_buffered_io(inode, WRITE) ?
+					F2FS_GET_BLOCK_PRE_AIO :
+					F2FS_GET_BLOCK_PRE_DIO;
+		goto map_blocks;
+	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
 			return err;
 	}
-	if (!f2fs_has_inline_data(inode))
-		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	if (f2fs_has_inline_data(inode))
+		return err;
+
+	flag = F2FS_GET_BLOCK_PRE_AIO;
+
+map_blocks:
+	err = f2fs_map_blocks(inode, &map, 1, flag);
+	if (map.m_len > 0 && err == -ENOSPC) {
+		if (!direct_io)
+			set_inode_flag(inode, FI_NO_PREALLOC);
+		err = 0;
+	}
 	return err;
 }
 
@@ -903,6 +992,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	blkcnt_t prealloc;
 	struct extent_info ei = {0,0,0};
 	block_t blkaddr;
+	unsigned int start_pgofs;
 
 	if (!maxblocks)
 		return 0;
@@ -918,6 +1008,8 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
 		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
 		map->m_flags = F2FS_MAP_MAPPED;
+		if (map->m_next_extent)
+			*map->m_next_extent = pgofs + map->m_len;
 		goto out;
 	}
 
@@ -936,10 +1028,14 @@ next_dnode:
 			if (map->m_next_pgofs)
 				*map->m_next_pgofs =
 					get_next_page_offset(&dn, pgofs);
+			if (map->m_next_extent)
+				*map->m_next_extent =
+					get_next_page_offset(&dn, pgofs);
 		}
 		goto unlock_out;
 	}
 
+	start_pgofs = pgofs;
 	prealloc = 0;
 	last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
@@ -959,7 +1055,8 @@ next_block:
 					last_ofs_in_node = dn.ofs_in_node;
 				}
 			} else {
-				err = __allocate_data_block(&dn);
+				err = __allocate_data_block(&dn,
+							map->m_seg_type);
 				if (!err)
 					set_inode_flag(inode, FI_APPEND_WRITE);
 			}
@@ -972,14 +1069,20 @@ next_block:
 				map->m_pblk = 0;
 				goto sync_out;
 			}
+			if (flag == F2FS_GET_BLOCK_PRECACHE)
+				goto sync_out;
 			if (flag == F2FS_GET_BLOCK_FIEMAP &&
 						blkaddr == NULL_ADDR) {
 				if (map->m_next_pgofs)
 					*map->m_next_pgofs = pgofs + 1;
+				goto sync_out;
 			}
-			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						blkaddr != NEW_ADDR)
+			if (flag != F2FS_GET_BLOCK_FIEMAP) {
+				/* for defragment case */
+				if (map->m_next_pgofs)
+					*map->m_next_pgofs = pgofs + 1;
 				goto sync_out;
+			}
 		}
 	}
 
@@ -1030,6 +1133,16 @@ skip:
 	else if (dn.ofs_in_node < end_offset)
 		goto next_block;
 
+	if (flag == F2FS_GET_BLOCK_PRECACHE) {
+		if (map->m_flags & F2FS_MAP_MAPPED) {
+			unsigned int ofs = start_pgofs - map->m_lblk;
+
+			f2fs_update_extent_cache_range(&dn,
+				start_pgofs, map->m_pblk + ofs,
+				map->m_len - ofs);
+		}
+	}
+
 	f2fs_put_dnode(&dn);
 
 	if (create) {
@@ -1039,6 +1152,17 @@ skip:
 	goto next_dnode;
 
 sync_out:
+	if (flag == F2FS_GET_BLOCK_PRECACHE) {
+		if (map->m_flags & F2FS_MAP_MAPPED) {
+			unsigned int ofs = start_pgofs - map->m_lblk;
+
+			f2fs_update_extent_cache_range(&dn,
+				start_pgofs, map->m_pblk + ofs,
+				map->m_len - ofs);
+		}
+		if (map->m_next_extent)
+			*map->m_next_extent = pgofs + 1;
+	}
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
@@ -1050,9 +1174,34 @@ out:
 	return err;
 }
 
+bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
+{
+	struct f2fs_map_blocks map;
+	block_t last_lblk;
+	int err;
+
+	if (pos + len > i_size_read(inode))
+		return false;
+
+	map.m_lblk = F2FS_BYTES_TO_BLK(pos);
+	map.m_next_pgofs = NULL;
+	map.m_next_extent = NULL;
+	map.m_seg_type = NO_CHECK_TYPE;
+	last_lblk = F2FS_BLK_ALIGN(pos + len);
+
+	while (map.m_lblk < last_lblk) {
+		map.m_len = last_lblk - map.m_lblk;
+		err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
+		if (err || map.m_len == 0)
+			return false;
+		map.m_lblk += map.m_len;
+	}
+	return true;
+}
+
 static int __get_data_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh, int create, int flag,
-			pgoff_t *next_pgofs)
+			pgoff_t *next_pgofs, int seg_type)
 {
 	struct f2fs_map_blocks map;
 	int err;
@@ -1060,6 +1209,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 	map.m_next_pgofs = next_pgofs;
+	map.m_next_extent = NULL;
+	map.m_seg_type = seg_type;
 
 	err = f2fs_map_blocks(inode, &map, create, flag);
 	if (!err) {
@@ -1075,14 +1226,17 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 			pgoff_t *next_pgofs)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-							flag, next_pgofs);
+							flag, next_pgofs,
+							NO_CHECK_TYPE);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_DEFAULT, NULL);
+						F2FS_GET_BLOCK_DEFAULT, NULL,
+						rw_hint_to_seg_type(
+							inode->i_write_hint));
 }
 
 static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -1093,7 +1247,8 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock,
 		return -EFBIG;
 
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_BMAP, NULL);
+						F2FS_GET_BLOCK_BMAP, NULL,
+						NO_CHECK_TYPE);
 }
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -1106,6 +1261,68 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
 	return (blk << inode->i_blkbits);
 }
 
+static int f2fs_xattr_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct page *page;
+	struct node_info ni;
+	__u64 phys = 0, len;
+	__u32 flags;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	int err = 0;
+
+	if (f2fs_has_inline_xattr(inode)) {
+		int offset;
+
+		page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
+						inode->i_ino, false);
+		if (!page)
+			return -ENOMEM;
+
+		get_node_info(sbi, inode->i_ino, &ni);
+
+		phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+		offset = offsetof(struct f2fs_inode, i_addr) +
+					sizeof(__le32) * (DEF_ADDRS_PER_INODE -
+					get_inline_xattr_addrs(inode));
+
+		phys += offset;
+		len = inline_xattr_size(inode);
+
+		f2fs_put_page(page, 1);
+
+		flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
+
+		if (!xnid)
+			flags |= FIEMAP_EXTENT_LAST;
+
+		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+		if (err || err == 1)
+			return err;
+	}
+
+	if (xnid) {
+		page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
+		if (!page)
+			return -ENOMEM;
+
+		get_node_info(sbi, xnid, &ni);
+
+		phys = (__u64)blk_to_logical(inode, ni.blk_addr);
+		len = inode->i_sb->s_blocksize;
+
+		f2fs_put_page(page, 1);
+
+		flags = FIEMAP_EXTENT_LAST;
+	}
+
+	if (phys)
+		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+
+	return (err < 0 ? err : 0);
+}
+
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
@@ -1116,18 +1333,29 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	u32 flags = 0;
 	int ret = 0;
 
-	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+	if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+		ret = f2fs_precache_extents(inode);
+		if (ret)
+			return ret;
+	}
+
+	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
 	if (ret)
 		return ret;
 
+	inode_lock(inode);
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+		ret = f2fs_xattr_fiemap(inode, fieinfo);
+		goto out;
+	}
+
 	if (f2fs_has_inline_data(inode)) {
 		ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
 		if (ret != -EAGAIN)
-			return ret;
+			goto out;
 	}
 
-	inode_lock(inode);
-
 	if (logical_to_blk(inode, len) == 0)
 		len = blk_to_logical(inode, 1);
 
@@ -1197,7 +1425,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			unsigned nr_pages)
 {
 	struct bio *bio = NULL;
-	unsigned page_idx;
 	sector_t last_block_in_bio = 0;
 	struct inode *inode = mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
@@ -1213,9 +1440,10 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	map.m_len = 0;
 	map.m_flags = 0;
 	map.m_next_pgofs = NULL;
+	map.m_next_extent = NULL;
+	map.m_seg_type = NO_CHECK_TYPE;
 
-	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
-
+	for (; nr_pages; nr_pages--) {
 		if (pages) {
 			page = list_last_entry(pages, struct page, lru);
 
@@ -1355,7 +1583,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio)
 	if (!f2fs_encrypted_file(inode))
 		return 0;
 
-	/* wait for GCed encrypted page writeback */
+	/* wait for GCed page writeback via META_MAPPING */
 	f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr);
 
 retry_encrypt:
@@ -1374,18 +1602,79 @@ retry_encrypt:
 	return PTR_ERR(fio->encrypted_page);
 }
 
+static inline bool check_inplace_update_policy(struct inode *inode,
+				struct f2fs_io_info *fio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	unsigned int policy = SM_I(sbi)->ipu_policy;
+
+	if (policy & (0x1 << F2FS_IPU_FORCE))
+		return true;
+	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
+		return true;
+	if (policy & (0x1 << F2FS_IPU_UTIL) &&
+			utilization(sbi) > SM_I(sbi)->min_ipu_util)
+		return true;
+	if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
+			utilization(sbi) > SM_I(sbi)->min_ipu_util)
+		return true;
+
+	/*
+	 * IPU for rewrite async pages
+	 */
+	if (policy & (0x1 << F2FS_IPU_ASYNC) &&
+			fio && fio->op == REQ_OP_WRITE &&
+			!(fio->op_flags & REQ_SYNC) &&
+			!f2fs_encrypted_inode(inode))
+		return true;
+
+	/* this is only set during fdatasync */
+	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
+			is_inode_flag_set(inode, FI_NEED_IPU))
+		return true;
+
+	return false;
+}
+
+bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+	if (f2fs_is_pinned_file(inode))
+		return true;
+
+	/* if this is cold file, we should overwrite to avoid fragmentation */
+	if (file_is_cold(inode))
+		return true;
+
+	return check_inplace_update_policy(inode, fio);
+}
+
+bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (test_opt(sbi, LFS))
+		return true;
+	if (S_ISDIR(inode->i_mode))
+		return true;
+	if (f2fs_is_atomic_file(inode))
+		return true;
+	if (fio) {
+		if (is_cold_data(fio->page))
+			return true;
+		if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+			return true;
+	}
+	return false;
+}
+
 static inline bool need_inplace_update(struct f2fs_io_info *fio)
 {
 	struct inode *inode = fio->page->mapping->host;
 
-	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
-		return false;
-	if (is_cold_data(fio->page))
-		return false;
-	if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+	if (should_update_outplace(inode, fio))
 		return false;
 
-	return need_inplace_update_policy(inode, fio);
+	return should_update_inplace(inode, fio);
 }
 
 static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
@@ -1444,6 +1733,7 @@ got_it:
 			goto out_writepage;
 
 		set_page_writeback(page);
+		ClearPageError(page);
 		f2fs_put_dnode(&dn);
 		if (fio->need_lock == LOCK_REQ)
 			f2fs_unlock_op(fio->sbi);
@@ -1466,6 +1756,7 @@ got_it:
 		goto out_writepage;
 
 	set_page_writeback(page);
+	ClearPageError(page);
 
 	/* LFS mode write path */
 	write_data_page(&dn, fio);
@@ -1506,10 +1797,17 @@ static int __write_data_page(struct page *page, bool *submitted,
 		.submitted = false,
 		.need_lock = LOCK_RETRY,
 		.io_type = io_type,
+		.io_wbc = wbc,
 	};
 
 	trace_f2fs_writepage(page, DATA);
 
+	/* we should bypass data pages to proceed the kworkder jobs */
+	if (unlikely(f2fs_cp_error(sbi))) {
+		mapping_set_error(page->mapping, -EIO);
+		goto out;
+	}
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 
@@ -1534,12 +1832,6 @@ write:
 			available_free_memory(sbi, BASE_CHECK))))
 		goto redirty_out;
 
-	/* we should bypass data pages to proceed the kworkder jobs */
-	if (unlikely(f2fs_cp_error(sbi))) {
-		mapping_set_error(page->mapping, -EIO);
-		goto out;
-	}
-
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
 		fio.need_lock = LOCK_DONE;
@@ -1569,10 +1861,14 @@ write:
 		}
 	}
 
-	down_write(&F2FS_I(inode)->i_sem);
-	if (F2FS_I(inode)->last_disk_size < psize)
-		F2FS_I(inode)->last_disk_size = psize;
-	up_write(&F2FS_I(inode)->i_sem);
+	if (err) {
+		file_set_keep_isize(inode);
+	} else {
+		down_write(&F2FS_I(inode)->i_sem);
+		if (F2FS_I(inode)->last_disk_size < psize)
+			F2FS_I(inode)->last_disk_size = psize;
+		up_write(&F2FS_I(inode)->i_sem);
+	}
 
 done:
 	if (err && err != -ENOENT)
@@ -1606,7 +1902,13 @@ out:
 
 redirty_out:
 	redirty_page_for_writepage(wbc, page);
-	if (!err)
+	/*
+	 * pageout() in MM traslates EAGAIN, so calls handle_write_error()
+	 * -> mapping_set_error() -> set_bit(AS_EIO, ...).
+	 * file_write_and_wait_range() will see EIO error, which is critical
+	 * to return value of fsync() followed by atomic_write failure to user.
+	 */
+	if (!err || wbc->for_reclaim)
 		return AOP_WRITEPAGE_ACTIVATE;
 	unlock_page(page);
 	return err;
@@ -1936,7 +2238,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *page = NULL;
 	pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
-	bool need_balance = false;
+	bool need_balance = false, drop_atomic = false;
 	block_t blkaddr = NULL_ADDR;
 	int err = 0;
 
@@ -1955,6 +2257,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	if (f2fs_is_atomic_file(inode) &&
 			!available_free_memory(sbi, INMEM_PAGES)) {
 		err = -ENOMEM;
+		drop_atomic = true;
 		goto fail;
 	}
 
@@ -2000,8 +2303,8 @@ repeat:
 
 	f2fs_wait_on_page_writeback(page, DATA, false);
 
-	/* wait for GCed encrypted page writeback */
-	if (f2fs_encrypted_file(inode))
+	/* wait for GCed page writeback via META_MAPPING */
+	if (f2fs_post_read_required(inode))
 		f2fs_wait_on_block_writeback(sbi, blkaddr);
 
 	if (len == PAGE_SIZE || PageUptodate(page))
@@ -2035,7 +2338,7 @@ repeat:
 fail:
 	f2fs_put_page(page, 1);
 	f2fs_write_failed(mapping, pos + len);
-	if (f2fs_is_atomic_file(inode))
+	if (drop_atomic)
 		drop_inmem_pages_all(sbi);
 	return err;
 }
@@ -2093,15 +2396,18 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	size_t count = iov_iter_count(iter);
 	int rw = iov_iter_rw(iter);
 	int err;
+	enum rw_hint hint = iocb->ki_hint;
+	int whint_mode = F2FS_OPTION(sbi).whint_mode;
 
 	err = check_direct_IO(inode, iter, offset);
 	if (err)
 		return err;
 
-	if (__force_buffered_io(inode, rw))
+	if (f2fs_force_buffered_io(inode, rw))
 		return 0;
 
 	if (trace_android_fs_dataread_start_enabled() &&
@@ -2128,11 +2434,24 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	}
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
-	down_read(&F2FS_I(inode)->dio_rwsem[rw]);
+	if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
+		iocb->ki_hint = WRITE_LIFE_NOT_SET;
+
+	if (!down_read_trylock(&F2FS_I(inode)->dio_rwsem[rw])) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			iocb->ki_hint = hint;
+			err = -EAGAIN;
+			goto out;
+		}
+		down_read(&F2FS_I(inode)->dio_rwsem[rw]);
+	}
+
 	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
 	up_read(&F2FS_I(inode)->dio_rwsem[rw]);
 
 	if (rw == WRITE) {
+		if (whint_mode == WHINT_MODE_OFF)
+			iocb->ki_hint = hint;
 		if (err > 0) {
 			f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
 									err);
@@ -2141,7 +2460,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			f2fs_write_failed(mapping, offset + count);
 		}
 	}
-
+out:
 	if (trace_android_fs_dataread_start_enabled() &&
 	    (iov_iter_rw(iter) == READ))
 		trace_android_fs_dataread_end(inode, offset, count);
@@ -2198,37 +2517,6 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	return 1;
 }
 
-/*
- * This was copied from __set_page_dirty_buffers which gives higher performance
- * in very high speed storages. (e.g., pmem)
- */
-void f2fs_set_page_dirty_nobuffers(struct page *page)
-{
-	struct address_space *mapping = page->mapping;
-	struct mem_cgroup *memcg;
-	unsigned long flags;
-
-	if (unlikely(!mapping))
-		return;
-
-	spin_lock(&mapping->private_lock);
-	memcg = mem_cgroup_begin_page_stat(page);
-	SetPageDirty(page);
-	spin_unlock(&mapping->private_lock);
-
-	spin_lock_irqsave(&mapping->tree_lock, flags);
-	WARN_ON_ONCE(!PageUptodate(page));
-	account_page_dirtied(page, mapping, memcg);
-	radix_tree_tag_set(&mapping->page_tree,
-			page_index(page), PAGECACHE_TAG_DIRTY);
-	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-
-	mem_cgroup_end_page_stat(memcg);
-
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return;
-}
-
 static int f2fs_set_data_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
@@ -2252,7 +2540,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	}
 
 	if (!PageDirty(page)) {
-		f2fs_set_page_dirty_nobuffers(page);
+		__set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
 		return 1;
 	}
@@ -2345,3 +2633,27 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.migratepage    = f2fs_migrate_page,
 #endif
 };
+
+int __init f2fs_init_post_read_processing(void)
+{
+	bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0);
+	if (!bio_post_read_ctx_cache)
+		goto fail;
+	bio_post_read_ctx_pool =
+		mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
+					 bio_post_read_ctx_cache);
+	if (!bio_post_read_ctx_pool)
+		goto fail_free_cache;
+	return 0;
+
+fail_free_cache:
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+fail:
+	return -ENOMEM;
+}
+
+void __exit f2fs_destroy_post_read_processing(void)
+{
+	mempool_destroy(bio_post_read_ctx_pool);
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+}