Merge pull request openzfs#1083 from ahrens/merge2

merge with 'zdb: include cloned blocks in block statistics'

cmd/zdb/zdb.c

@@ -81,6 +81,7 @@
 #include <sys/dsl_crypt.h>
 #include <sys/dsl_scan.h>
 #include <sys/btree.h>
+#include <sys/brt.h>
 #include <zfs_comutil.h>
 #include <sys/zstd/zstd.h>
 #include <libnvpair.h>
@@ -5380,12 +5381,20 @@ static const char *zdb_ot_extname[] = {
 #define	ZB_TOTAL	DN_MAX_LEVELS
 #define	SPA_MAX_FOR_16M	(SPA_MAXBLOCKSHIFT+1)
 
+typedef struct zdb_brt_entry {
+	dva_t		zbre_dva;
+	uint64_t	zbre_refcount;
+	avl_node_t	zbre_node;
+} zdb_brt_entry_t;
+
 typedef struct zdb_cb {
 	zdb_blkstats_t	zcb_type[ZB_TOTAL + 1][ZDB_OT_TOTAL + 1];
 	uint64_t	zcb_removing_size;
 	uint64_t	zcb_checkpoint_size;
 	uint64_t	zcb_dedup_asize;
 	uint64_t	zcb_dedup_blocks;
+	uint64_t	zcb_clone_asize;
+	uint64_t	zcb_clone_blocks;
 	uint64_t	zcb_psize_count[SPA_MAX_FOR_16M];
 	uint64_t	zcb_lsize_count[SPA_MAX_FOR_16M];
 	uint64_t	zcb_asize_count[SPA_MAX_FOR_16M];
@@ -5406,6 +5415,8 @@ typedef struct zdb_cb {
 	int		zcb_haderrors;
 	spa_t		*zcb_spa;
 	uint32_t	**zcb_vd_obsolete_counts;
+	avl_tree_t	zcb_brt;
+	boolean_t	zcb_brt_is_active;
 } zdb_cb_t;
 
 /* test if two DVA offsets from same vdev are within the same metaslab */
@@ -5700,6 +5711,45 @@ zdb_count_block(zdb_cb_t *zcb, zilog_t *zilog, const blkptr_t *bp,
 	zcb->zcb_asize_len[bin] += BP_GET_ASIZE(bp);
 	zcb->zcb_asize_total += BP_GET_ASIZE(bp);
 
+	if (zcb->zcb_brt_is_active && brt_maybe_exists(zcb->zcb_spa, bp)) {
+		/*
+		 * Cloned blocks are special. We need to count them, so we can
+		 * later uncount them when reporting leaked space, and we must
+		 * only claim them them once.
+		 *
+		 * To do this, we keep our own in-memory BRT. For each block
+		 * we haven't seen before, we look it up in the real BRT and
+		 * if its there, we note it and its refcount then proceed as
+		 * normal. If we see the block again, we count it as a clone
+		 * and then give it no further consideration.
+		 */
+		zdb_brt_entry_t zbre_search, *zbre;
+		avl_index_t where;
+
+		zbre_search.zbre_dva = bp->blk_dva[0];
+		zbre = avl_find(&zcb->zcb_brt, &zbre_search, &where);
+		if (zbre != NULL) {
+			zcb->zcb_clone_asize += BP_GET_ASIZE(bp);
+			zcb->zcb_clone_blocks++;
+
+			zbre->zbre_refcount--;
+			if (zbre->zbre_refcount == 0) {
+				avl_remove(&zcb->zcb_brt, zbre);
+				umem_free(zbre, sizeof (zdb_brt_entry_t));
+			}
+			return;
+		}
+
+		uint64_t crefcnt = brt_entry_get_refcount(zcb->zcb_spa, bp);
+		if (crefcnt > 0) {
+			zbre = umem_zalloc(sizeof (zdb_brt_entry_t),
+			    UMEM_NOFAIL);
+			zbre->zbre_dva = bp->blk_dva[0];
+			zbre->zbre_refcount = crefcnt;
+			avl_insert(&zcb->zcb_brt, zbre, where);
+		}
+	}
+
 	if (dump_opt['L'])
 		return;
 
@@ -6703,6 +6753,20 @@ deleted_livelists_dump_mos(spa_t *spa)
 	iterate_deleted_livelists(spa, dump_livelist_cb, NULL);
 }
 
+static int
+zdb_brt_entry_compare(const void *zcn1, const void *zcn2)
+{
+	const dva_t *dva1 = &((const zdb_brt_entry_t *)zcn1)->zbre_dva;
+	const dva_t *dva2 = &((const zdb_brt_entry_t *)zcn2)->zbre_dva;
+	int cmp;
+
+	cmp = TREE_CMP(DVA_GET_VDEV(dva1), DVA_GET_VDEV(dva2));
+	if (cmp == 0)
+		cmp = TREE_CMP(DVA_GET_OFFSET(dva1), DVA_GET_OFFSET(dva2));
+
+	return (cmp);
+}
+
 static int
 dump_block_stats(spa_t *spa)
 {
@@ -6717,6 +6781,13 @@ dump_block_stats(spa_t *spa)
 
 	zcb = umem_zalloc(sizeof (zdb_cb_t), UMEM_NOFAIL);
 
+	if (spa_feature_is_active(spa, SPA_FEATURE_BLOCK_CLONING)) {
+		avl_create(&zcb->zcb_brt, zdb_brt_entry_compare,
+		    sizeof (zdb_brt_entry_t),
+		    offsetof(zdb_brt_entry_t, zbre_node));
+		zcb->zcb_brt_is_active = B_TRUE;
+	}
+
 	/*
 	 * For an objectstore based zpool, there are no space maps and zdb leak
 	 * detection will not work.
@@ -6839,7 +6910,8 @@ dump_block_stats(spa_t *spa)
 	    metaslab_class_get_alloc(spa_special_class(spa)) +
 	    metaslab_class_get_alloc(spa_dedup_class(spa)) +
 	    get_unflushed_alloc_space(spa);
-	total_found = tzb->zb_asize - zcb->zcb_dedup_asize +
+	total_found =
+	    tzb->zb_asize - zcb->zcb_dedup_asize - zcb->zcb_clone_asize +
 	    zcb->zcb_removing_size + zcb->zcb_checkpoint_size;
 
 	if (total_found == total_alloc && !dump_opt['L']) {
@@ -6880,6 +6952,9 @@ dump_block_stats(spa_t *spa)
 	    "bp deduped:", (u_longlong_t)zcb->zcb_dedup_asize,
 	    (u_longlong_t)zcb->zcb_dedup_blocks,
 	    (double)zcb->zcb_dedup_asize / tzb->zb_asize + 1.0);
+	(void) printf("\t%-16s %14llu    count: %6llu\n",
+	    "bp cloned:", (u_longlong_t)zcb->zcb_clone_asize,
+	    (u_longlong_t)zcb->zcb_clone_blocks);
 	(void) printf("\t%-16s %14llu     used: %5.2f%%\n", "Normal class:",
 	    (u_longlong_t)norm_alloc, 100.0 * norm_alloc / norm_space);
 

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
 ])

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
 ])
 

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_SYSCTL_REGISTER_TABLE, 1,
+			[sysctl_register_table exists])
+	],[
+		AC_MSG_RESULT([no])
+	])
+])

config/kernel-vfs-iov_iter.m4

@@ -93,6 +93,14 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_VFS_IOV_ITER], [
 		struct iov_iter iter = { 0 };
 		__attribute__((unused)) enum iter_type i = iov_iter_type(&iter);
 	])
+
+	ZFS_LINUX_TEST_SRC([iter_iov], [
+		#include <linux/fs.h>
+		#include <linux/uio.h>
+	],[
+		struct iov_iter iter = { 0 };
+		__attribute__((unused)) const struct iovec *iov = iter_iov(&iter);
+	])
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_VFS_IOV_ITER], [
@@ -201,4 +209,19 @@ AC_DEFUN([ZFS_AC_KERNEL_VFS_IOV_ITER], [
 		AC_DEFINE(HAVE_VFS_IOV_ITER, 1,
 		    [All required iov_iter interfaces are available])
 	])
+
+	dnl #
+	dnl # Kernel 6.5 introduces the iter_iov() function that returns the
+	dnl # __iov member of an iov_iter*. The iov member was renamed to this
+	dnl # __iov member, and is intended to be accessed via the helper
+	dnl # function now.
+	dnl #
+	AC_MSG_CHECKING([whether iter_iov() is available])
+	ZFS_LINUX_TEST_RESULT([iter_iov], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_ITER_IOV, 1,
+		    [iter_iov() is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
 ])

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