From: Qian Yingjin <qian@ddn.com>
Date: Mon, 20 Feb 2023 03:11:54 +0000 (-0500)
Subject: LU-16579 llite: fix the wrong beyond read end calculation
X-Git-Tag: 2.15.55~83
X-Git-Url: https://git.whamcloud.com/?a=commitdiff_plain;h=ae356dc325877bd130ad94acc5f3610898de8a8a;p=fs%2Flustre-release.git

LU-16579 llite: fix the wrong beyond read end calculation

During the test, we found a dead loop in the read path which
retruns AOP_TRUNCATED_PAGE(0x8001) endless.
The reason is that the calculation of the ending beyond offset is
wrong: (iter->count + iocb->ki_pos).
The ending beyond offset was supposed to be not changed during
the read I/O loop for each page in buffered I/O mode.
However, @iter->count is decreased with read bytes when finished
the read of each page: @iter->count -= read_bytes.

In this patch, we store the ending beyond page index in
@lcc->lcc_end_index before call @generic_file_read_iter into a
loop for each read page and solve this bug.

Fixes: 2f8f38effa ("LU-16412 llite: check read page past requested")
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I5bb7ab82e5e2de8b9bd911798fb8ae65fc7c91af
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/50065
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Patrick Farrell <pfarrell@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
---

diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h
index 89edc09..bf632d4 100644
--- a/lustre/llite/llite_internal.h
+++ b/lustre/llite/llite_internal.h
@@ -1395,8 +1395,7 @@ struct ll_cl_context {
 	struct cl_io		*lcc_io;
 	struct cl_page		*lcc_page;
 	enum lcc_type		 lcc_type;
-	struct kiocb		*lcc_iocb;
-	struct iov_iter		*lcc_iter;
+	pgoff_t			 lcc_end_index;
 };
 
 struct ll_thread_info {
diff --git a/lustre/llite/rw.c b/lustre/llite/rw.c
index 49f1688..bad0150 100644
--- a/lustre/llite/rw.c
+++ b/lustre/llite/rw.c
@@ -1858,13 +1858,11 @@ int ll_readpage(struct file *file, struct page *vmpage)
 	struct inode *inode = file_inode(file);
 	struct cl_object *clob = ll_i2info(inode)->lli_clob;
 	struct ll_sb_info *sbi = ll_i2sbi(inode);
-	const struct lu_env  *env = NULL;
+	const struct lu_env *env = NULL;
 	struct cl_read_ahead ra = { 0 };
 	struct ll_cl_context *lcc;
-	struct cl_io   *io = NULL;
-	struct iov_iter *iter;
+	struct cl_io *io = NULL;
 	struct cl_page *page;
-	struct kiocb *iocb;
 	int result;
 	ENTRY;
 
@@ -1970,11 +1968,8 @@ int ll_readpage(struct file *file, struct page *vmpage)
 	}
 
 	if (lcc && lcc->lcc_type != LCC_MMAP) {
-		iocb = lcc->lcc_iocb;
-		iter = lcc->lcc_iter;
-
-		CDEBUG(D_VFSTRACE, "pgno:%ld, cnt:%ld, pos:%lld\n",
-		       vmpage->index, iter->count, iocb->ki_pos);
+		CDEBUG(D_VFSTRACE, "pgno:%ld, beyond read end_index:%ld\n",
+		       vmpage->index, lcc->lcc_end_index);
 
 		/*
 		 * This handles a kernel bug introduced in kernel 5.12:
@@ -2000,7 +1995,7 @@ int ll_readpage(struct file *file, struct page *vmpage)
 		 * This should never occur except in kernels with the bug
 		 * mentioned above.
 		 */
-		if (cl_offset(clob, vmpage->index) >= iter->count + iocb->ki_pos) {
+		if (vmpage->index >= lcc->lcc_end_index) {
 			result = cl_io_read_ahead(env, io, vmpage->index, &ra);
 			if (result < 0 || vmpage->index > ra.cra_end_idx) {
 				cl_read_ahead_release(env, &ra);
diff --git a/lustre/llite/vvp_io.c b/lustre/llite/vvp_io.c
index e19db59..7fa452e 100644
--- a/lustre/llite/vvp_io.c
+++ b/lustre/llite/vvp_io.c
@@ -889,10 +889,8 @@ static int vvp_io_read_start(const struct lu_env *env,
 	iter = *vio->vui_iter;
 
 	lcc = ll_cl_find(inode);
-	lcc->lcc_iter = &iter;
-	lcc->lcc_iocb = vio->vui_iocb;
-	CDEBUG(D_VFSTRACE, "cnt:%ld,iocb pos:%lld\n", lcc->lcc_iter->count,
-	       lcc->lcc_iocb->ki_pos);
+	lcc->lcc_end_index = DIV_ROUND_UP(pos + iter.count, PAGE_SIZE);
+	CDEBUG(D_VFSTRACE, "count:%ld iocb pos:%lld\n", iter.count, pos);
 
 	result = generic_file_read_iter(vio->vui_iocb, &iter);