1 files changed, 81 insertions, 102 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 86a38b979323..64fe82ec65ff 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -47,6 +47,9 @@
 #include <linux/pagevec.h>
 #include <linux/sched/mm.h>
 #include <trace/events/block.h>
+#include <linux/fscrypt.h>
+
+#include "internal.h"
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
@@ -120,14 +123,6 @@ void __wait_on_buffer(struct buffer_head * bh)
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 
-static void
-__clear_page_buffers(struct page *page)
-{
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	put_page(page);
-}
-
 static void buffer_io_error(struct buffer_head *bh, char *msg)
 {
 	if (!test_bit(BH_Quiet, &bh->b_state))
@@ -246,10 +241,6 @@ out:
 	return ret;
 }
 
-/*
- * I/O completion handler for block_read_full_page() - pages
- * which come unlocked at the end of I/O.
- */
 static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 {
 	unsigned long flags;
@@ -275,8 +266,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	 * decide that the page is now completely done.
 	 */
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	spin_lock_irqsave(&first->b_uptodate_lock, flags);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -289,8 +279,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 
 	/*
 	 * If none of the buffers had errors and they are all
@@ -302,11 +291,51 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
 
+struct decrypt_bh_ctx {
+	struct work_struct work;
+	struct buffer_head *bh;
+};
+
+static void decrypt_bh(struct work_struct *work)
+{
+	struct decrypt_bh_ctx *ctx =
+		container_of(work, struct decrypt_bh_ctx, work);
+	struct buffer_head *bh = ctx->bh;
+	int err;
+
+	err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size,
+					       bh_offset(bh));
+	end_buffer_async_read(bh, err == 0);
+	kfree(ctx);
+}
+
+/*
+ * I/O completion handler for block_read_full_page() - pages
+ * which come unlocked at the end of I/O.
+ */
+static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
+{
+	/* Decrypt if needed */
+	if (uptodate && IS_ENABLED(CONFIG_FS_ENCRYPTION) &&
+	    IS_ENCRYPTED(bh->b_page->mapping->host) &&
+	    S_ISREG(bh->b_page->mapping->host->i_mode)) {
+		struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
+
+		if (ctx) {
+			INIT_WORK(&ctx->work, decrypt_bh);
+			ctx->bh = bh;
+			fscrypt_enqueue_decrypt_work(&ctx->work);
+			return;
+		}
+		uptodate = 0;
+	}
+	end_buffer_async_read(bh, uptodate);
+}
+
 /*
  * Completion handler for block_write_full_page() - pages which are unlocked
  * during I/O, and which have PageWriteback cleared upon I/O completion.
@@ -331,8 +360,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 	}
 
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	spin_lock_irqsave(&first->b_uptodate_lock, flags);
 
 	clear_buffer_async_write(bh);
 	unlock_buffer(bh);
@@ -344,14 +372,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	}
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	end_page_writeback(page);
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
 EXPORT_SYMBOL(end_buffer_async_write);
@@ -379,7 +405,7 @@ EXPORT_SYMBOL(end_buffer_async_write);
  */
 static void mark_buffer_async_read(struct buffer_head *bh)
 {
-	bh->b_end_io = end_buffer_async_read;
+	bh->b_end_io = end_buffer_async_read_io;
 	set_buffer_async_read(bh);
 }
 
@@ -872,7 +898,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
 		bh = bh->b_this_page;
 	} while (bh);
 	tail->b_this_page = head;
-	attach_page_buffers(page, head);
+	attach_page_private(page, head);
 }
 
 static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
@@ -933,7 +959,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	struct page *page;
 	struct buffer_head *bh;
 	sector_t end_block;
-	int ret = 0;		/* Will call free_more_memory() */
+	int ret = 0;
 	gfp_t gfp_mask;
 
 	gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
@@ -1120,12 +1146,19 @@ EXPORT_SYMBOL(mark_buffer_dirty);
 
 void mark_buffer_write_io_error(struct buffer_head *bh)
 {
+	struct super_block *sb;
+
 	set_buffer_write_io_error(bh);
 	/* FIXME: do we need to set this in both places? */
 	if (bh->b_page && bh->b_page->mapping)
 		mapping_set_error(bh->b_page->mapping, -EIO);
 	if (bh->b_assoc_map)
 		mapping_set_error(bh->b_assoc_map, -EIO);
+	rcu_read_lock();
+	sb = READ_ONCE(bh->b_bdev->bd_super);
+	if (sb)
+		errseq_set(&sb->s_wb_err, -EIO);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(mark_buffer_write_io_error);
 
@@ -1337,6 +1370,17 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 }
 EXPORT_SYMBOL(__breadahead);
 
+void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
+		      gfp_t gfp)
+{
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
+	if (likely(bh)) {
+		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		brelse(bh);
+	}
+}
+EXPORT_SYMBOL(__breadahead_gfp);
+
 /**
  *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
@@ -1385,15 +1429,15 @@ static bool has_bh_in_lru(int cpu, void *dummy)
 	
 	for (i = 0; i < BH_LRU_SIZE; i++) {
 		if (b->bhs[i])
-			return 1;
+			return true;
 	}
 
-	return 0;
+	return false;
 }
 
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
@@ -1535,7 +1579,7 @@ void create_empty_buffers(struct page *page,
 			bh = bh->b_this_page;
 		} while (bh != head);
 	}
-	attach_page_buffers(page, head);
+	attach_page_private(page, head);
 	spin_unlock(&page->mapping->private_lock);
 }
 EXPORT_SYMBOL(create_empty_buffers);
@@ -2522,7 +2566,7 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
 			bh->b_this_page = head;
 		bh = bh->b_this_page;
 	} while (bh != head);
-	attach_page_buffers(page, head);
+	attach_page_private(page, head);
 	spin_unlock(&page->mapping->private_lock);
 }
 
@@ -2979,72 +3023,6 @@ static void end_bio_bh_io_sync(struct bio *bio)
 	bio_put(bio);
 }
 
-/*
- * This allows us to do IO even on the odd last sectors
- * of a device, even if the block size is some multiple
- * of the physical sector size.
- *
- * We'll just truncate the bio to the size of the device,
- * and clear the end of the buffer head manually.
- *
- * Truly out-of-range accesses will turn into actual IO
- * errors, this only handles the "we need to be able to
- * do IO at the final sector" case.
- */
-void guard_bio_eod(int op, struct bio *bio)
-{
-	sector_t maxsector;
-	struct bio_vec *bvec = bio_last_bvec_all(bio);
-	unsigned truncated_bytes;
-	struct hd_struct *part;
-
-	rcu_read_lock();
-	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
-	if (part)
-		maxsector = part_nr_sects_read(part);
-	else
-		maxsector = get_capacity(bio->bi_disk);
-	rcu_read_unlock();
-
-	if (!maxsector)
-		return;
-
-	/*
-	 * If the *whole* IO is past the end of the device,
-	 * let it through, and the IO layer will turn it into
-	 * an EIO.
-	 */
-	if (unlikely(bio->bi_iter.bi_sector >= maxsector))
-		return;
-
-	maxsector -= bio->bi_iter.bi_sector;
-	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
-		return;
-
-	/* Uhhuh. We've got a bio that straddles the device size! */
-	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
-
-	/*
-	 * The bio contains more than one segment which spans EOD, just return
-	 * and let IO layer turn it into an EIO
-	 */
-	if (truncated_bytes > bvec->bv_len)
-		return;
-
-	/* Truncate the bio.. */
-	bio->bi_iter.bi_size -= truncated_bytes;
-	bvec->bv_len -= truncated_bytes;
-
-	/* ..and clear the end of the buffer for reads */
-	if (op == REQ_OP_READ) {
-		struct bio_vec bv;
-
-		mp_bvec_last_segment(bvec, &bv);
-		zero_user(bv.bv_page, bv.bv_offset + bv.bv_len,
-				truncated_bytes);
-	}
-}
-
 static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 			 enum rw_hint write_hint, struct writeback_control *wbc)
 {
@@ -3078,15 +3056,15 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
 
-	/* Take care of bh's that straddle the end of the device */
-	guard_bio_eod(op, bio);
-
 	if (buffer_meta(bh))
 		op_flags |= REQ_META;
 	if (buffer_prio(bh))
 		op_flags |= REQ_PRIO;
 	bio_set_op_attrs(bio, op, op_flags);
 
+	/* Take care of bh's that straddle the end of the device */
+	guard_bio_eod(bio);
+
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
 		wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
@@ -3248,7 +3226,7 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
 		bh = next;
 	} while (bh != head);
 	*buffers_to_free = head;
-	__clear_page_buffers(page);
+	detach_page_private(page);
 	return 1;
 failed:
 	return 0;
@@ -3368,6 +3346,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
 	struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
 	if (ret) {
 		INIT_LIST_HEAD(&ret->b_assoc_buffers);
+		spin_lock_init(&ret->b_uptodate_lock);
 		preempt_disable();
 		__this_cpu_inc(bh_accounting.nr);
 		recalc_bh_state();