#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 <linux/sched/signal.h>
#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;
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;
+};
+
+/* device unit number for iv sector */
+#define PG_DUN(i,p) \
+ ((((i)->i_ino & 0xffffffff) << 32) | ((p)->index & 0xffffffff))
+
+static inline bool f2fs_may_encrypt_bio(struct inode *inode,
+ struct f2fs_io_info *fio)
{
- struct bio_vec *bvec;
+#ifdef CONFIG_CRYPTO_DISKCIPHER
+ if (fio && (fio->type != DATA || fio->encrypted_page))
+ return false;
+
+ return (f2fs_encrypted_file(inode) &&
+ fscrypt_disk_encrypted(inode));
+#else
+ return false;
+#endif
+}
+
+static inline bool f2fs_bio_disk_encrypted(unsigned int bi_opf)
+{
+ if (bi_opf & REQ_CRYPT)
+ return true;
+ else
+ return false;
+}
+
+static bool f2fs_mergeable_bio(struct bio *bio, u64 dun, void *ci, bool bio_encrypted)
+{
+#ifdef CONFIG_CRYPTO_DISKCIPHER
+ if (!bio)
+ return true;
+
+ /* if both of them are not encrypted, no further check is needed */
+ if (!f2fs_bio_disk_encrypted(bio->bi_opf) && !bio_encrypted)
+ return true;
+
+#ifdef CONFIG_CRYPTO_DISKCIPHER_DUN
+ if (bio->bi_aux_private == ci)
+ return bio_end_dun(bio) == dun;
+ else
+ return false;
+#else
+ return bio->bi_aux_private == ci;
+#endif
+#else
+ return true;
+#endif
+}
+
+static void __read_end_io(struct bio *bio)
+{
+ 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_status || 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_status;
+}
+
+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);
}
#endif
- if (f2fs_bio_encrypted(bio)) {
- if (bio->bi_status) {
- fscrypt_release_ctx(bio->bi_private);
- } else {
- fscrypt_decrypt_bio_pages(bio->bi_private, bio);
- return;
- }
- }
+ if(f2fs_bio_disk_encrypted(bio->bi_opf))
+ goto end_io;
- 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_status) {
- 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);
+
+end_io:
+ __read_end_io(bio);
}
static void f2fs_write_end_io(struct bio *bio)
*/
static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
struct writeback_control *wbc,
- int npages, bool is_read)
+ 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);
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);
if (!io->bio)
return;
- bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+ if (f2fs_bio_disk_encrypted(io->bio->bi_opf))
+ bio_set_op_attrs(io->bio, fio->op, fio->op_flags | REQ_CRYPT);
+ else
+ bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
if (is_read_io(fio->op))
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
struct bio *bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
+ struct inode *inode = fio->page->mapping->host;
+ 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, fio->io_wbc,
- 1, is_read_io(fio->op));
+ 1, is_read_io(fio->op), fio->type, fio->temp);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
+ fio->op_flags |= fio->encrypted_page ? REQ_NOENCRYPT : 0;
bio_set_op_attrs(bio, fio->op, fio->op_flags);
+ if (f2fs_may_encrypt_bio(inode, fio))
+ fscrypt_set_bio(inode, bio, PG_DUN(inode, fio->page));
+
__submit_bio(fio->sbi, bio, fio->type);
if (!is_read_io(fio->op))
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
int err = 0;
+ struct inode *inode;
+ bool bio_encrypted;
+ u64 dun;
f2fs_bug_on(sbi, is_read_io(fio->op));
}
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;
+ inode = fio->page->mapping->host;
+ dun = PG_DUN(inode, fio->page);
+ bio_encrypted = f2fs_may_encrypt_bio(inode, fio);
+ fio->op_flags |= fio->encrypted_page ? REQ_NOENCRYPT : 0;
/* set submitted = true as a return value */
fio->submitted = true;
(io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
!__same_bdev(sbi, fio->new_blkaddr, io->bio)))
__submit_merged_bio(io);
+
+ if (!f2fs_mergeable_bio(io->bio, dun, fscrypt_get_diskcipher(inode), bio_encrypted))
+ __submit_merged_bio(io);
+
alloc_new:
if (io->bio == NULL) {
if ((fio->type == DATA || fio->type == NODE) &&
goto out_fail;
}
io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc,
- BIO_MAX_PAGES, false);
+ BIO_MAX_PAGES, false,
+ fio->type, fio->temp);
+ if (bio_encrypted)
+ fscrypt_set_bio(inode, io->bio, dun);
+
io->fio = *fio;
}
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) && !fscrypt_disk_encrypted(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;
+ bio_set_op_attrs(bio, REQ_OP_READ,
+ (f2fs_encrypted_inode(inode) ?
+ REQ_NOENCRYPT :
+ 0));
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_block_writeback(sbi, blkaddr);
+ }
+
return bio;
}
bio_put(bio);
return -EFAULT;
}
+
+ if (f2fs_may_encrypt_bio(inode, NULL))
+ fscrypt_set_bio(inode, bio, PG_DUN(inode, page));
+
__submit_bio(F2FS_I_SB(inode), bio, DATA);
return 0;
}
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);
if (direct_io) {
map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint);
- flag = __force_buffered_io(inode, WRITE) ?
+ flag = f2fs_force_buffered_io(inode, WRITE) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO;
goto map_blocks;
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, int seg_type)
sector_t last_block_in_file;
sector_t block_nr;
struct f2fs_map_blocks map;
+ bool bio_encrypted;
+ u64 dun;
map.m_pblk = 0;
map.m_lblk = 0;
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
+
+ dun = PG_DUN(inode, page);
+ bio_encrypted = f2fs_may_encrypt_bio(inode, NULL);
+ if (!f2fs_mergeable_bio(bio, dun, fscrypt_get_diskcipher(inode), bio_encrypted)) {
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ bio = NULL;
+ }
+
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
}
+ if (f2fs_may_encrypt_bio(inode, NULL))
+ fscrypt_set_bio(inode, bio, dun);
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
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:
+ if (fscrypt_disk_encrypted(inode))
+ return 0;
+
fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
PAGE_SIZE, 0, fio->page->index, gfp_flags);
if (!IS_ERR(fio->encrypted_page))
goto out_writepage;
set_page_writeback(page);
+ ClearPageError(page);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
goto out_writepage;
set_page_writeback(page);
+ ClearPageError(page);
/* LFS mode write path */
write_data_page(&dn, fio);
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;
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))
{
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);
loff_t offset = iocb->ki_pos;
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;
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
current->pid, path,
current->comm);
}
+ 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]);
+ }
- down_read(&F2FS_I(inode)->dio_rwsem[rw]);
err = blockdev_direct_IO(iocb, inode, iter, 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);
f2fs_write_failed(mapping, offset + count);
}
}
-
+out:
if (trace_android_fs_dataread_start_enabled() &&
(rw == READ))
trace_android_fs_dataread_end(inode, offset, count);
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;
- unsigned long flags;
-
- if (unlikely(!mapping))
- return;
-
- spin_lock(&mapping->private_lock);
- lock_page_memcg(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);
- radix_tree_tag_set(&mapping->page_tree,
- page_index(page), PAGECACHE_TAG_DIRTY);
- spin_unlock_irqrestore(&mapping->tree_lock, flags);
- unlock_page_memcg(page);
-
- __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;
}
if (!PageDirty(page)) {
- f2fs_set_page_dirty_nobuffers(page);
+ __set_page_dirty_nobuffers(page);
update_dirty_page(inode, page);
return 1;
}
.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);
+}