Received-SPF: pass (google.com: domain of linux-kernel+bounces-102182-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: "Pankaj Raghav (Samsung)" <kernel@pankajraghav.com>
To: willy@infradead.org,
	linux-xfs@vger.kernel.org,
	linux-fsdevel@vger.kernel.org
Cc: gost.dev@samsung.com,
	chandan.babu@oracle.com,
	hare@suse.de,
	mcgrof@kernel.org,
	djwong@kernel.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	david@fromorbit.com,
	akpm@linux-foundation.org,
	Pankaj Raghav <p.raghav@samsung.com>
Subject: [PATCH v3 11/11] xfs: enable block size larger than page size support
Date: Wed, 13 Mar 2024 18:02:53 +0100
Message-ID: <20240313170253.2324812-12-kernel@pankajraghav.com>
In-Reply-To: <20240313170253.2324812-1-kernel@pankajraghav.com>
References: <20240313170253.2324812-1-kernel@pankajraghav.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Pankaj Raghav <p.raghav@samsung.com>

Page cache now has the ability to have a minimum order when allocating
a folio which is a prerequisite to add support for block size > page
size.

Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 fs/xfs/libxfs/xfs_ialloc.c |  5 +++++
 fs/xfs/libxfs/xfs_shared.h |  3 +++
 fs/xfs/xfs_icache.c        |  6 ++++--
 fs/xfs/xfs_mount.c         |  1 -
 fs/xfs/xfs_super.c         | 10 ++--------
 5 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 2361a22035b0..c040bd6271fd 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2892,6 +2892,11 @@ xfs_ialloc_setup_geometry(
 		igeo->ialloc_align = mp->m_dalign;
 	else
 		igeo->ialloc_align = 0;
+
+	if (mp->m_sb.sb_blocksize > PAGE_SIZE)
+		igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT;
+	else
+		igeo->min_folio_order = 0;
 }
 
 /* Compute the location of the root directory inode that is laid out by mkfs. */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 4220d3584c1b..67ed406e7a81 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -188,6 +188,9 @@ struct xfs_ino_geometry {
 	/* precomputed value for di_flags2 */
 	uint64_t	new_diflags2;
 
+	/* minimum folio order of a page cache allocation */
+	unsigned int	min_folio_order;
+
 };
 
 #endif /* __XFS_SHARED_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index dba514a2c84d..a1857000e2cd 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -88,7 +88,8 @@ xfs_inode_alloc(
 	/* VFS doesn't initialise i_mode or i_state! */
 	VFS_I(ip)->i_mode = 0;
 	VFS_I(ip)->i_state = 0;
-	mapping_set_large_folios(VFS_I(ip)->i_mapping);
+	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -323,7 +324,8 @@ xfs_reinit_inode(
 	inode->i_rdev = dev;
 	inode->i_uid = uid;
 	inode->i_gid = gid;
-	mapping_set_large_folios(inode->i_mapping);
+	mapping_set_folio_min_order(inode->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 9cf800586da7..a77e927807e5 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -131,7 +131,6 @@ xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
 	uint64_t	nblocks)
 {
-	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 	uint64_t max_index;
 	uint64_t max_bytes;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 98401de832ee..4f5f4cb772d4 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1624,16 +1624,10 @@ xfs_fs_fill_super(
 		goto out_free_sb;
 	}
 
-	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
 	if (mp->m_sb.sb_blocksize > PAGE_SIZE) {
 		xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
-				mp->m_sb.sb_blocksize, PAGE_SIZE);
-		error = -ENOSYS;
-		goto out_free_sb;
+"EXPERIMENTAL: Filesystem with Large Block Size (%d bytes) enabled.",
+			mp->m_sb.sb_blocksize);
 	}
 
 	/* Ensure this filesystem fits in the page cache limits */
-- 
2.43.0