- up to 2.2.0-rc3

[packages/zfs.git] / kernel-6.5.patch

From 3b8e318b7737fa40daf6abbc06ba31cd6ae8d572 Mon Sep 17 00:00:00 2001
From: Coleman Kane <ckane@colemankane.org>
Date: Tue, 1 Aug 2023 11:32:38 -0400
Subject: [PATCH] Linux 6.5 compat: use disk_check_media_change when it exists

When disk_check_media_change() exists, then define
zfs_check_media_change() to simply call disk_check_media_change() on
the bd_disk member of its argument. Since disk_check_media_change()
is newer than when revalidate_disk was present in bops, we should
be able to safely do this via a macro, instead of recreating a new
implementation of the inline function that forces revalidation.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15101
---
 include/os/linux/kernel/linux/blkdev_compat.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/os/linux/kernel/linux/blkdev_compat.h b/include/os/linux/kernel/linux/blkdev_compat.h
index e0f20ba32008..1641dd92a918 100644
--- a/include/os/linux/kernel/linux/blkdev_compat.h
+++ b/include/os/linux/kernel/linux/blkdev_compat.h
@@ -347,6 +347,7 @@ zfs_check_media_change(struct block_device *bdev)
 #define	vdev_bdev_reread_part(bdev)	zfs_check_media_change(bdev)
 #elif defined(HAVE_DISK_CHECK_MEDIA_CHANGE)
 #define	vdev_bdev_reread_part(bdev)	disk_check_media_change(bdev->bd_disk)
+#define	zfs_check_media_change(bdev)	disk_check_media_change(bdev->bd_disk)
 #else
 /*
  * This is encountered if check_disk_change() and bdev_check_media_change()
From 43e8f6e37fddc31f23301cb70d466687bd205cd9 Mon Sep 17 00:00:00 2001
From: Coleman Kane <ckane@colemankane.org>
Date: Tue, 1 Aug 2023 11:37:20 -0400
Subject: [PATCH] Linux 6.5 compat: blkdev changes

Multiple changes to the blkdev API were introduced in Linux 6.5. This
includes passing (void* holder) to blkdev_put, adding a new
blk_holder_ops* arg to blkdev_get_by_path, adding a new blk_mode_t type
that replaces uses of fmode_t, and removing an argument from the release
handler on block_device_operations that we weren't using. The open
function definition has also changed to take gendisk* and blk_mode_t, so
update it accordingly, too.

Implement local wrappers for blkdev_get_by_path() and
vdev_blkdev_put() so that the in-line calls are cleaner, and place the
conditionally-compiled implementation details inside of both of these
local wrappers. Both calls are exclusively used within vdev_disk.c, at
this time.

Add blk_mode_is_open_write() to test FMODE_WRITE / BLK_OPEN_WRITE
The wrapper function is now used for testing using the appropriate
method for the kernel, whether the open mode is writable or not.

Emphasize fmode_t arg in zvol_release is not used

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15099
---
 config/kernel-blkdev.m4                       | 84 ++++++++++++++++++-
 config/kernel-block-device-operations.m4      | 35 +++++++-
 include/os/linux/kernel/linux/blkdev_compat.h |  6 ++
 module/os/linux/zfs/vdev_disk.c               | 65 ++++++++++++--
 module/os/linux/zfs/zfs_vnops_os.c            |  2 +-
 module/os/linux/zfs/zpl_ctldir.c              |  2 +-
 module/os/linux/zfs/zvol_os.c                 | 28 ++++++-
 7 files changed, 203 insertions(+), 19 deletions(-)

diff --git a/config/kernel-blkdev.m4 b/config/kernel-blkdev.m4
index 887acee670ba..e04a2bd2c3b6 100644
--- a/config/kernel-blkdev.m4
+++ b/config/kernel-blkdev.m4
@@ -16,12 +16,63 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change,
+dnl # blkdev_get_by_path() takes 4 args
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG], [
+	ZFS_LINUX_TEST_SRC([blkdev_get_by_path_4arg], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		struct block_device *bdev __attribute__ ((unused)) = NULL;
+		const char *path = "path";
+		fmode_t mode = 0;
+		void *holder = NULL;
+		struct blk_holder_ops h;
+
+		bdev = blkdev_get_by_path(path, mode, holder, &h);
+	])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_GET_BY_PATH], [
-	AC_MSG_CHECKING([whether blkdev_get_by_path() exists])
+	AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 3 args])
 	ZFS_LINUX_TEST_RESULT([blkdev_get_by_path], [
 		AC_MSG_RESULT(yes)
 	], [
-		ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 4 args])
+		ZFS_LINUX_TEST_RESULT([blkdev_get_by_path_4arg], [
+			AC_DEFINE(HAVE_BLKDEV_GET_BY_PATH_4ARG, 1,
+				[blkdev_get_by_path() exists and takes 4 args])
+			AC_MSG_RESULT(yes)
+		], [
+			ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
+		])
+	])
+])
+
+dnl #
+dnl # 6.5.x API change
+dnl # blk_mode_t was added as a type to supercede some places where fmode_t
+dnl # is used
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T], [
+	ZFS_LINUX_TEST_SRC([blk_mode_t], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		blk_mode_t m __attribute((unused)) = (blk_mode_t)0;
+	])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T], [
+	AC_MSG_CHECKING([whether blk_mode_t is defined])
+	ZFS_LINUX_TEST_RESULT([blk_mode_t], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_BLK_MODE_T, 1, [blk_mode_t is defined])
+	], [
+		AC_MSG_RESULT(no)
 	])
 ])
 
@@ -41,12 +92,35 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change.
+dnl # blkdev_put() takes (void* holder) as arg 2
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER], [
+	ZFS_LINUX_TEST_SRC([blkdev_put_holder], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		struct block_device *bdev = NULL;
+		void *holder = NULL;
+
+		blkdev_put(bdev, holder);
+	])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_PUT], [
 	AC_MSG_CHECKING([whether blkdev_put() exists])
 	ZFS_LINUX_TEST_RESULT([blkdev_put], [
 		AC_MSG_RESULT(yes)
 	], [
-		ZFS_LINUX_TEST_ERROR([blkdev_put()])
+		AC_MSG_CHECKING([whether blkdev_put() accepts void* as arg 2])
+		ZFS_LINUX_TEST_RESULT([blkdev_put_holder], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE(HAVE_BLKDEV_PUT_HOLDER, 1,
+				[blkdev_put() accepts void* as arg 2])
+		], [
+			ZFS_LINUX_TEST_ERROR([blkdev_put()])
+		])
 	])
 ])
 
@@ -495,7 +569,9 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT], [
 
 AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH
+	ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG
 	ZFS_AC_KERNEL_SRC_BLKDEV_PUT
+	ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER
 	ZFS_AC_KERNEL_SRC_BLKDEV_REREAD_PART
 	ZFS_AC_KERNEL_SRC_BLKDEV_INVALIDATE_BDEV
 	ZFS_AC_KERNEL_SRC_BLKDEV_LOOKUP_BDEV
@@ -510,6 +586,7 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	ZFS_AC_KERNEL_SRC_BLKDEV_PART_TO_DEV
 	ZFS_AC_KERNEL_SRC_BLKDEV_DISK_CHECK_MEDIA_CHANGE
 	ZFS_AC_KERNEL_SRC_BLKDEV_BLK_STS_RESV_CONFLICT
+	ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
@@ -530,4 +607,5 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
 	ZFS_AC_KERNEL_BLKDEV_PART_TO_DEV
 	ZFS_AC_KERNEL_BLKDEV_DISK_CHECK_MEDIA_CHANGE
 	ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT
+	ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T
 ])
diff --git a/config/kernel-block-device-operations.m4 b/config/kernel-block-device-operations.m4
index 84e39dc8a2f6..d13c1337b1fb 100644
--- a/config/kernel-block-device-operations.m4
+++ b/config/kernel-block-device-operations.m4
@@ -49,12 +49,42 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
 	], [], [])
 ])
 
+dnl #
+dnl # 5.9.x API change
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [
+	ZFS_LINUX_TEST_SRC([block_device_operations_release_void_1arg], [
+		#include <linux/blkdev.h>
+
+		void blk_release(struct gendisk *g) {
+			(void) g;
+			return;
+		}
+
+		static const struct block_device_operations
+		    bops __attribute__ ((unused)) = {
+			.open		= NULL,
+			.release	= blk_release,
+			.ioctl		= NULL,
+			.compat_ioctl	= NULL,
+		};
+	], [], [])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
-	AC_MSG_CHECKING([whether bops->release() is void])
+	AC_MSG_CHECKING([whether bops->release() is void and takes 2 args])
 	ZFS_LINUX_TEST_RESULT([block_device_operations_release_void], [
 		AC_MSG_RESULT(yes)
 	],[
-		ZFS_LINUX_TEST_ERROR([bops->release()])
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING([whether bops->release() is void and takes 1 arg])
+		ZFS_LINUX_TEST_RESULT([block_device_operations_release_void_1arg], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE([HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [1],
+				[Define if release() in block_device_operations takes 1 arg])
+		],[
+			ZFS_LINUX_TEST_ERROR([bops->release()])
+		])
 	])
 ])
 
@@ -92,6 +122,7 @@ AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK], [
 AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS], [
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_CHECK_EVENTS
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID
+	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK
 ])
 
diff --git a/include/os/linux/kernel/linux/blkdev_compat.h b/include/os/linux/kernel/linux/blkdev_compat.h
index 1641dd92a918..f111e648ccf7 100644
--- a/include/os/linux/kernel/linux/blkdev_compat.h
+++ b/include/os/linux/kernel/linux/blkdev_compat.h
@@ -398,6 +398,12 @@ vdev_lookup_bdev(const char *path, dev_t *dev)
 #endif
 }
 
+#if defined(HAVE_BLK_MODE_T)
+#define	blk_mode_is_open_write(flag)	((flag) & BLK_OPEN_WRITE)
+#else
+#define	blk_mode_is_open_write(flag)	((flag) & FMODE_WRITE)
+#endif
+
 /*
  * Kernels without bio_set_op_attrs use bi_rw for the bio flags.
  */
diff --git a/module/os/linux/zfs/vdev_disk.c b/module/os/linux/zfs/vdev_disk.c
index 925ee9d9fe9c..48ac55f07034 100644
--- a/module/os/linux/zfs/vdev_disk.c
+++ b/module/os/linux/zfs/vdev_disk.c
@@ -80,9 +80,22 @@ typedef struct dio_request {
 
 static unsigned int zfs_vdev_failfast_mask = 1;
 
+#ifdef HAVE_BLK_MODE_T
+static blk_mode_t
+#else
 static fmode_t
+#endif
 vdev_bdev_mode(spa_mode_t spa_mode)
 {
+#ifdef HAVE_BLK_MODE_T
+	blk_mode_t mode = 0;
+
+	if (spa_mode & SPA_MODE_READ)
+		mode |= BLK_OPEN_READ;
+
+	if (spa_mode & SPA_MODE_WRITE)
+		mode |= BLK_OPEN_WRITE;
+#else
 	fmode_t mode = 0;
 
 	if (spa_mode & SPA_MODE_READ)
@@ -90,6 +103,7 @@ vdev_bdev_mode(spa_mode_t spa_mode)
 
 	if (spa_mode & SPA_MODE_WRITE)
 		mode |= FMODE_WRITE;
+#endif
 
 	return (mode);
 }
@@ -197,12 +211,47 @@ vdev_disk_kobj_evt_post(vdev_t *v)
 	}
 }
 
+#if !defined(HAVE_BLKDEV_GET_BY_PATH_4ARG)
+/*
+ * Define a dummy struct blk_holder_ops for kernel versions
+ * prior to 6.5.
+ */
+struct blk_holder_ops {};
+#endif
+
+static struct block_device *
+vdev_blkdev_get_by_path(const char *path, spa_mode_t mode, void *holder,
+    const struct blk_holder_ops *hops)
+{
+#ifdef HAVE_BLKDEV_GET_BY_PATH_4ARG
+	return (blkdev_get_by_path(path,
+	    vdev_bdev_mode(mode) | BLK_OPEN_EXCL, holder, hops));
+#else
+	return (blkdev_get_by_path(path,
+	    vdev_bdev_mode(mode) | FMODE_EXCL, holder));
+#endif
+}
+
+static void
+vdev_blkdev_put(struct block_device *bdev, spa_mode_t mode, void *holder)
+{
+#ifdef HAVE_BLKDEV_PUT_HOLDER
+	return (blkdev_put(bdev, holder));
+#else
+	return (blkdev_put(bdev, vdev_bdev_mode(mode) | FMODE_EXCL));
+#endif
+}
+
 static int
 vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
     uint64_t *logical_ashift, uint64_t *physical_ashift)
 {
 	struct block_device *bdev;
+#ifdef HAVE_BLK_MODE_T
+	blk_mode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
+#else
 	fmode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
+#endif
 	hrtime_t timeout = MSEC2NSEC(zfs_vdev_open_timeout_ms);
 	vdev_disk_t *vd;
 
@@ -252,15 +301,15 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
 					reread_part = B_TRUE;
 			}
 
-			blkdev_put(bdev, mode | FMODE_EXCL);
+			vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
 		}
 
 		if (reread_part) {
-			bdev = blkdev_get_by_path(disk_name, mode | FMODE_EXCL,
-			    zfs_vdev_holder);
+			bdev = vdev_blkdev_get_by_path(disk_name, mode,
+			    zfs_vdev_holder, NULL);
 			if (!IS_ERR(bdev)) {
 				int error = vdev_bdev_reread_part(bdev);
-				blkdev_put(bdev, mode | FMODE_EXCL);
+				vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
 				if (error == 0) {
 					timeout = MSEC2NSEC(
 					    zfs_vdev_open_timeout_ms * 2);
@@ -305,8 +354,8 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
 	hrtime_t start = gethrtime();
 	bdev = ERR_PTR(-ENXIO);
 	while (IS_ERR(bdev) && ((gethrtime() - start) < timeout)) {
-		bdev = blkdev_get_by_path(v->vdev_path, mode | FMODE_EXCL,
-		    zfs_vdev_holder);
+		bdev = vdev_blkdev_get_by_path(v->vdev_path, mode,
+		    zfs_vdev_holder, NULL);
 		if (unlikely(PTR_ERR(bdev) == -ENOENT)) {
 			/*
 			 * There is no point of waiting since device is removed
@@ -382,8 +431,8 @@ vdev_disk_close(vdev_t *v)
 		return;
 
 	if (vd->vd_bdev != NULL) {
-		blkdev_put(vd->vd_bdev,
-		    vdev_bdev_mode(spa_mode(v->vdev_spa)) | FMODE_EXCL);
+		vdev_blkdev_put(vd->vd_bdev, spa_mode(v->vdev_spa),
+		    zfs_vdev_holder);
 	}
 
 	rw_destroy(&vd->vd_lock);
diff --git a/module/os/linux/zfs/zfs_vnops_os.c b/module/os/linux/zfs/zfs_vnops_os.c
index 234c4d5ef0e0..33baac9db06b 100644
--- a/module/os/linux/zfs/zfs_vnops_os.c
+++ b/module/os/linux/zfs/zfs_vnops_os.c
@@ -186,7 +186,7 @@ zfs_open(struct inode *ip, int mode, int flag, cred_t *cr)
 		return (error);
 
 	/* Honor ZFS_APPENDONLY file attribute */
-	if ((mode & FMODE_WRITE) && (zp->z_pflags & ZFS_APPENDONLY) &&
+	if (blk_mode_is_open_write(mode) && (zp->z_pflags & ZFS_APPENDONLY) &&
 	    ((flag & O_APPEND) == 0)) {
 		zfs_exit(zfsvfs, FTAG);
 		return (SET_ERROR(EPERM));
diff --git a/module/os/linux/zfs/zpl_ctldir.c b/module/os/linux/zfs/zpl_ctldir.c
index 68a7de78f471..7786444fea35 100644
--- a/module/os/linux/zfs/zpl_ctldir.c
+++ b/module/os/linux/zfs/zpl_ctldir.c
@@ -42,7 +42,7 @@
 static int
 zpl_common_open(struct inode *ip, struct file *filp)
 {
-	if (filp->f_mode & FMODE_WRITE)
+	if (blk_mode_is_open_write(filp->f_mode))
 		return (-EACCES);
 
 	return (generic_file_open(ip, filp));
diff --git a/module/os/linux/zfs/zvol_os.c b/module/os/linux/zfs/zvol_os.c
index 38bc8e2c4eeb..7a95b54bdf0d 100644
--- a/module/os/linux/zfs/zvol_os.c
+++ b/module/os/linux/zfs/zvol_os.c
@@ -671,7 +671,11 @@ zvol_request(struct request_queue *q, struct bio *bio)
 }
 
 static int
+#ifdef HAVE_BLK_MODE_T
+zvol_open(struct gendisk *disk, blk_mode_t flag)
+#else
 zvol_open(struct block_device *bdev, fmode_t flag)
+#endif
 {
 	zvol_state_t *zv;
 	int error = 0;
@@ -686,10 +690,14 @@ zvol_open(struct block_device *bdev, fmode_t flag)
 	/*
 	 * Obtain a copy of private_data under the zvol_state_lock to make
 	 * sure that either the result of zvol free code path setting
-	 * bdev->bd_disk->private_data to NULL is observed, or zvol_os_free()
+	 * disk->private_data to NULL is observed, or zvol_os_free()
 	 * is not called on this zv because of the positive zv_open_count.
 	 */
+#ifdef HAVE_BLK_MODE_T
+	zv = disk->private_data;
+#else
 	zv = bdev->bd_disk->private_data;
+#endif
 	if (zv == NULL) {
 		rw_exit(&zvol_state_lock);
 		return (SET_ERROR(-ENXIO));
@@ -769,14 +777,15 @@ zvol_open(struct block_device *bdev, fmode_t flag)
 			}
 		}
 
-		error = -zvol_first_open(zv, !(flag & FMODE_WRITE));
+		error = -zvol_first_open(zv, !(blk_mode_is_open_write(flag)));
 
 		if (drop_namespace)
 			mutex_exit(&spa_namespace_lock);
 	}
 
 	if (error == 0) {
-		if ((flag & FMODE_WRITE) && (zv->zv_flags & ZVOL_RDONLY)) {
+		if ((blk_mode_is_open_write(flag)) &&
+		    (zv->zv_flags & ZVOL_RDONLY)) {
 			if (zv->zv_open_count == 0)
 				zvol_last_close(zv);
 
@@ -791,14 +800,25 @@ zvol_open(struct block_device *bdev, fmode_t flag)
 		rw_exit(&zv->zv_suspend_lock);
 
 	if (error == 0)
+#ifdef HAVE_BLK_MODE_T
+		disk_check_media_change(disk);
+#else
 		zfs_check_media_change(bdev);
+#endif
 
 	return (error);
 }
 
 static void
-zvol_release(struct gendisk *disk, fmode_t mode)
+#ifdef HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
+zvol_release(struct gendisk *disk)
+#else
+zvol_release(struct gendisk *disk, fmode_t unused)
+#endif
 {
+#if !defined(HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG)
+	(void) unused;
+#endif
 	zvol_state_t *zv;
 	boolean_t drop_suspend = B_TRUE;
 
From e47e9bbe86f2e8fe5da0fc7c3a9014e1f8c132a9 Mon Sep 17 00:00:00 2001
From: Coleman Kane <ckane@colemankane.org>
Date: Wed, 2 Aug 2023 17:05:46 -0400
Subject: [PATCH] Linux 6.5 compat: register_sysctl_table removed

Additionally, the .child element of ctl_table has been removed in 6.5.
This change adds a new test for the pre-6.5 register_sysctl_table()
function, and uses the old code in that case. If it isn't found, then
the parentage entries in the tables are removed, and the register_sysctl
call is provided the paths of "kernel/spl", "kernel/spl/kmem", and
"kernel/spl/kstat" directly, to populate each subdirectory over three
calls, as is the new API.

Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15138
---
 config/kernel-register_sysctl_table.m4 | 27 ++++++++++++++++++++++++++
 config/kernel.m4                       |  2 ++
 module/os/linux/spl/spl-proc.c         | 26 ++++++++++++++++++++++---
 3 files changed, 52 insertions(+), 3 deletions(-)
 create mode 100644 config/kernel-register_sysctl_table.m4

diff --git a/config/kernel-register_sysctl_table.m4 b/config/kernel-register_sysctl_table.m4
new file mode 100644
index 000000000000..a5e934f56d29
--- /dev/null
+++ b/config/kernel-register_sysctl_table.m4
@@ -0,0 +1,27 @@
+dnl #
+dnl # Linux 6.5 removes register_sysctl_table
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE], [
+	ZFS_LINUX_TEST_SRC([has_register_sysctl_table], [
+		#include <linux/sysctl.h>
+
+		static struct ctl_table dummy_table[] = {
+			{}
+		};
+
+    ],[
+		struct ctl_table_header *h
+			__attribute((unused)) = register_sysctl_table(dummy_table);
+    ])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE], [
+	AC_MSG_CHECKING([whether register_sysctl_table exists])
+	ZFS_LINUX_TEST_RESULT([has_register_sysctl_table], [
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_REGISTER_SYSCTL_TABLE, 1,
+			[register_sysctl_table exists])
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
diff --git a/config/kernel.m4 b/config/kernel.m4
index 1487fa2e7793..28bd361d33ff 100644
--- a/config/kernel.m4
+++ b/config/kernel.m4
@@ -160,6 +160,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_SRC], [
 	ZFS_AC_KERNEL_SRC_FILEMAP
 	ZFS_AC_KERNEL_SRC_WRITEPAGE_T
 	ZFS_AC_KERNEL_SRC_RECLAIMED
+	ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_SRC_CPU_HAS_FEATURE
@@ -299,6 +300,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_RESULT], [
 	ZFS_AC_KERNEL_FILEMAP
 	ZFS_AC_KERNEL_WRITEPAGE_T
 	ZFS_AC_KERNEL_RECLAIMED
+	ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_CPU_HAS_FEATURE
diff --git a/module/os/linux/spl/spl-proc.c b/module/os/linux/spl/spl-proc.c
index 01f5619e1893..bcc356ae55b6 100644
--- a/module/os/linux/spl/spl-proc.c
+++ b/module/os/linux/spl/spl-proc.c
@@ -624,6 +624,7 @@ static struct ctl_table spl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dohostid,
 	},
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 	{
 		.procname	= "kmem",
 		.mode		= 0555,
@@ -634,9 +635,11 @@ static struct ctl_table spl_table[] = {
 		.mode		= 0555,
 		.child		= spl_kstat_table,
 	},
+#endif
 	{},
 };
 
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 static struct ctl_table spl_dir[] = {
 	{
 		.procname	= "spl",
@@ -648,21 +651,38 @@ static struct ctl_table spl_dir[] = {
 
 static struct ctl_table spl_root[] = {
 	{
-	.procname = "kernel",
-	.mode = 0555,
-	.child = spl_dir,
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= spl_dir,
 	},
 	{}
 };
+#endif
 
 int
 spl_proc_init(void)
 {
 	int rc = 0;
 
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 	spl_header = register_sysctl_table(spl_root);
 	if (spl_header == NULL)
 		return (-EUNATCH);
+#else
+	spl_header = register_sysctl("kernel/spl", spl_table);
+	if (spl_header == NULL)
+		return (-EUNATCH);
+
+	if (register_sysctl("kernel/spl/kmem", spl_kmem_table) == NULL) {
+		rc = -EUNATCH;
+		goto out;
+	}
+
+	if (register_sysctl("kernel/spl/kstat", spl_kstat_table) == NULL) {
+		rc = -EUNATCH;
+		goto out;
+	}
+#endif
 
 	proc_spl = proc_mkdir("spl", NULL);
 	if (proc_spl == NULL) {
From 36261c8238df462b214854ccea1df4f060cf0995 Mon Sep 17 00:00:00 2001
From: Coleman Kane <ckane@colemankane.org>
Date: Mon, 7 Aug 2023 18:47:46 -0400
Subject: [PATCH] Linux 6.5 compat: replace generic_file_splice_read with
 filemap_splice_read

The generic_file_splice_read function was removed in Linux 6.5 in favor
of filemap_splice_read. Add an autoconf test for filemap_splice_read and
use it if it is found as the handler for .splice_read in the
file_operations struct. Additionally, ITER_PIPE was removed in 6.5. This
change removes the ITER_* macros that OpenZFS doesn't use from being
tested in config/kernel-vfs-iov_iter.m4. The removal of ITER_PIPE was
causing the test to fail, which also affected the code responsible for
setting the .splice_read handler, above. That behavior caused run-time
panics on Linux 6.5.

Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15155
---
 config/kernel-filemap-splice-read.m4 | 25 +++++++++++++++++++++++++
 config/kernel-vfs-iov_iter.m4        |  3 +--
 config/kernel.m4                     |  2 ++
 module/os/linux/zfs/zpl_file.c       |  4 ++++
 4 files changed, 32 insertions(+), 2 deletions(-)
 create mode 100644 config/kernel-filemap-splice-read.m4

diff --git a/config/kernel-filemap-splice-read.m4 b/config/kernel-filemap-splice-read.m4
new file mode 100644
index 000000000000..5199b7373e4d
--- /dev/null
+++ b/config/kernel-filemap-splice-read.m4
@@ -0,0 +1,25 @@
+AC_DEFUN([ZFS_AC_KERNEL_SRC_FILEMAP_SPLICE_READ], [
+	dnl #
+	dnl # Kernel 6.5 - generic_file_splice_read was removed in favor
+	dnl # of filemap_splice_read for the .splice_read member of the
+	dnl # file_operations struct.
+	dnl #
+	ZFS_LINUX_TEST_SRC([has_filemap_splice_read], [
+		#include <linux/fs.h>
+
+		struct file_operations fops __attribute__((unused)) = {
+			.splice_read = filemap_splice_read,
+		};
+	],[])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_FILEMAP_SPLICE_READ], [
+	AC_MSG_CHECKING([whether filemap_splice_read() exists])
+	ZFS_LINUX_TEST_RESULT([has_filemap_splice_read], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_FILEMAP_SPLICE_READ, 1,
+		    [filemap_splice_read exists])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
diff --git a/config/kernel-vfs-iov_iter.m4 b/config/kernel-vfs-iov_iter.m4
index cc5a7ab0c237..ff560ff3eef0 100644
--- a/config/kernel-vfs-iov_iter.m4
+++ b/config/kernel-vfs-iov_iter.m4
@@ -6,8 +6,7 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_VFS_IOV_ITER], [
 		#include <linux/fs.h>
 		#include <linux/uio.h>
 	],[
-		int type __attribute__ ((unused)) =
-		    ITER_IOVEC | ITER_KVEC | ITER_BVEC | ITER_PIPE;
+		int type __attribute__ ((unused)) = ITER_KVEC;
 	])
 
 	ZFS_LINUX_TEST_SRC([iov_iter_advance], [
diff --git a/config/kernel.m4 b/config/kernel.m4
index 28bd361d33ff..309f1819be48 100644
--- a/config/kernel.m4
+++ b/config/kernel.m4
@@ -161,6 +161,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_SRC], [
 	ZFS_AC_KERNEL_SRC_WRITEPAGE_T
 	ZFS_AC_KERNEL_SRC_RECLAIMED
 	ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE
+	ZFS_AC_KERNEL_SRC_FILEMAP_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_SRC_CPU_HAS_FEATURE
@@ -301,6 +302,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_RESULT], [
 	ZFS_AC_KERNEL_WRITEPAGE_T
 	ZFS_AC_KERNEL_RECLAIMED
 	ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE
+	ZFS_AC_KERNEL_FILEMAP_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_CPU_HAS_FEATURE
diff --git a/module/os/linux/zfs/zpl_file.c b/module/os/linux/zfs/zpl_file.c
index f6af2ebd1163..24cc1064a8fc 100644
--- a/module/os/linux/zfs/zpl_file.c
+++ b/module/os/linux/zfs/zpl_file.c
@@ -1323,7 +1323,11 @@ const struct file_operations zpl_file_operations = {
 	.read_iter	= zpl_iter_read,
 	.write_iter	= zpl_iter_write,
 #ifdef HAVE_VFS_IOV_ITER
+#ifdef HAVE_FILEMAP_SPLICE_READ
+	.splice_read	= filemap_splice_read,
+#else
 	.splice_read	= generic_file_splice_read,
+#endif
 	.splice_write	= iter_file_splice_write,
 #endif
 #else
From 8ce2eba9e6a384feef93d77c397f37d17dc588ce Mon Sep 17 00:00:00 2001
From: Coleman Kane <ckane@colemankane.org>
Date: Tue, 8 Aug 2023 18:42:32 -0400
Subject: [PATCH] Linux 6.5 compat: Use copy_splice_read instead of
 filemap_splice_read

Using the filemap_splice_read function for the splice_read handler was
leading to occasional data corruption under certain circumstances. Favor
using copy_splice_read instead, which does not demonstrate the same
erroneous behavior under the tested failure cases.

Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15164
---
 config/kernel-filemap-splice-read.m4 | 18 +++++++++---------
 config/kernel.m4                     |  4 ++--
 module/os/linux/zfs/zpl_file.c       |  4 ++--
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/config/kernel-filemap-splice-read.m4 b/config/kernel-filemap-splice-read.m4
index 5199b7373e4d..4c83b31d738a 100644
--- a/config/kernel-filemap-splice-read.m4
+++ b/config/kernel-filemap-splice-read.m4
@@ -1,24 +1,24 @@
-AC_DEFUN([ZFS_AC_KERNEL_SRC_FILEMAP_SPLICE_READ], [
+AC_DEFUN([ZFS_AC_KERNEL_SRC_COPY_SPLICE_READ], [
 	dnl #
 	dnl # Kernel 6.5 - generic_file_splice_read was removed in favor
-	dnl # of filemap_splice_read for the .splice_read member of the
+	dnl # of copy_splice_read for the .splice_read member of the
 	dnl # file_operations struct.
 	dnl #
-	ZFS_LINUX_TEST_SRC([has_filemap_splice_read], [
+	ZFS_LINUX_TEST_SRC([has_copy_splice_read], [
 		#include <linux/fs.h>
 
 		struct file_operations fops __attribute__((unused)) = {
-			.splice_read = filemap_splice_read,
+			.splice_read = copy_splice_read,
 		};
 	],[])
 ])
 
-AC_DEFUN([ZFS_AC_KERNEL_FILEMAP_SPLICE_READ], [
-	AC_MSG_CHECKING([whether filemap_splice_read() exists])
-	ZFS_LINUX_TEST_RESULT([has_filemap_splice_read], [
+AC_DEFUN([ZFS_AC_KERNEL_COPY_SPLICE_READ], [
+	AC_MSG_CHECKING([whether copy_splice_read() exists])
+	ZFS_LINUX_TEST_RESULT([has_copy_splice_read], [
 		AC_MSG_RESULT(yes)
-		AC_DEFINE(HAVE_FILEMAP_SPLICE_READ, 1,
-		    [filemap_splice_read exists])
+		AC_DEFINE(HAVE_COPY_SPLICE_READ, 1,
+		    [copy_splice_read exists])
 	],[
 		AC_MSG_RESULT(no)
 	])
diff --git a/config/kernel.m4 b/config/kernel.m4
index 309f1819be48..df194ec72207 100644
--- a/config/kernel.m4
+++ b/config/kernel.m4
@@ -161,7 +161,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_SRC], [
 	ZFS_AC_KERNEL_SRC_WRITEPAGE_T
 	ZFS_AC_KERNEL_SRC_RECLAIMED
 	ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE
-	ZFS_AC_KERNEL_SRC_FILEMAP_SPLICE_READ
+	ZFS_AC_KERNEL_SRC_COPY_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_SRC_CPU_HAS_FEATURE
@@ -302,7 +302,7 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_RESULT], [
 	ZFS_AC_KERNEL_WRITEPAGE_T
 	ZFS_AC_KERNEL_RECLAIMED
 	ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE
-	ZFS_AC_KERNEL_FILEMAP_SPLICE_READ
+	ZFS_AC_KERNEL_COPY_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_CPU_HAS_FEATURE
diff --git a/module/os/linux/zfs/zpl_file.c b/module/os/linux/zfs/zpl_file.c
index 24cc1064a8fc..3caa0fc6c214 100644
--- a/module/os/linux/zfs/zpl_file.c
+++ b/module/os/linux/zfs/zpl_file.c
@@ -1323,8 +1323,8 @@ const struct file_operations zpl_file_operations = {
 	.read_iter	= zpl_iter_read,
 	.write_iter	= zpl_iter_write,
 #ifdef HAVE_VFS_IOV_ITER
-#ifdef HAVE_FILEMAP_SPLICE_READ
-	.splice_read	= filemap_splice_read,
+#ifdef HAVE_COPY_SPLICE_READ
+	.splice_read	= copy_splice_read,
 #else
 	.splice_read	= generic_file_splice_read,
 #endif
From bcb1159c095f57564914b59f5e7e82170261afb0 Mon Sep 17 00:00:00 2001
From: Andrea Righi <andrea.righi@canonical.com>
Date: Sat, 2 Sep 2023 02:21:40 +0200
Subject: [PATCH] Linux 6.5 compat: safe cleanup in spl_proc_fini()

If we fail to create a proc entry in spl_proc_init() we may end up
calling unregister_sysctl_table() twice: one in the failure path of
spl_proc_init() and another time during spl_proc_fini().

Avoid the double call to unregister_sysctl_table() and while at it
refactor the code a bit to reduce code duplication.

This was accidentally introduced when the spl code was
updated for Linux 6.5 compatibility.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ameer Hamza <ahamza@ixsystems.com>
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Closes #15234
Closes #15235
---
 module/os/linux/spl/spl-proc.c | 36 +++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/module/os/linux/spl/spl-proc.c b/module/os/linux/spl/spl-proc.c
index bcc356ae55b6..5cb5a6dadb05 100644
--- a/module/os/linux/spl/spl-proc.c
+++ b/module/os/linux/spl/spl-proc.c
@@ -659,6 +659,21 @@ static struct ctl_table spl_root[] = {
 };
 #endif
 
+static void spl_proc_cleanup(void)
+{
+	remove_proc_entry("kstat", proc_spl);
+	remove_proc_entry("slab", proc_spl_kmem);
+	remove_proc_entry("kmem", proc_spl);
+	remove_proc_entry("taskq-all", proc_spl);
+	remove_proc_entry("taskq", proc_spl);
+	remove_proc_entry("spl", NULL);
+
+	if (spl_header) {
+		unregister_sysctl_table(spl_header);
+		spl_header = NULL;
+	}
+}
+
 int
 spl_proc_init(void)
 {
@@ -723,15 +738,8 @@ spl_proc_init(void)
 		goto out;
 	}
 out:
-	if (rc) {
-		remove_proc_entry("kstat", proc_spl);
-		remove_proc_entry("slab", proc_spl_kmem);
-		remove_proc_entry("kmem", proc_spl);
-		remove_proc_entry("taskq-all", proc_spl);
-		remove_proc_entry("taskq", proc_spl);
-		remove_proc_entry("spl", NULL);
-		unregister_sysctl_table(spl_header);
-	}
+	if (rc)
+		spl_proc_cleanup();
 
 	return (rc);
 }
@@ -739,13 +747,5 @@ spl_proc_init(void)
 void
 spl_proc_fini(void)
 {
-	remove_proc_entry("kstat", proc_spl);
-	remove_proc_entry("slab", proc_spl_kmem);
-	remove_proc_entry("kmem", proc_spl);
-	remove_proc_entry("taskq-all", proc_spl);
-	remove_proc_entry("taskq", proc_spl);
-	remove_proc_entry("spl", NULL);
-
-	ASSERT(spl_header != NULL);
-	unregister_sysctl_table(spl_header);
+	spl_proc_cleanup();
 }