ZFS: MFV 2.0-rc1-ga00c61

12 files changed, 73 insertions, 34 deletions

diff --git a/sys/contrib/openzfs/module/Makefile.bsd b/sys/contrib/openzfs/module/Makefile.bsd
index 53b97dafd9e9..4feb9e1eaf0c 100644
--- a/sys/contrib/openzfs/module/Makefile.bsd
+++ b/sys/contrib/openzfs/module/Makefile.bsd
@@ -356,4 +356,4 @@ CFLAGS.zil.c= -Wno-cast-qual
 CFLAGS.zio.c= -Wno-cast-qual
 CFLAGS.zrlock.c= -Wno-cast-qual
 CFLAGS.zfs_zstd.c= -Wno-cast-qual -Wno-pointer-arith
-CFLAGS.zstd.c= -fno-tree-vectorize
+CFLAGS.zstd.c= -fno-tree-vectorize -U__BMI__
diff --git a/sys/contrib/openzfs/module/lua/setjmp/setjmp_ppc.S b/sys/contrib/openzfs/module/lua/setjmp/setjmp_ppc.S
index f787ef349136..72aa5d5ab5b0 100644
--- a/sys/contrib/openzfs/module/lua/setjmp/setjmp_ppc.S
+++ b/sys/contrib/openzfs/module/lua/setjmp/setjmp_ppc.S
@@ -56,7 +56,7 @@
 #define	ENTRY(name) \
 	.align 2 ; \
 	.type name,@function; \
-	.globl name; \
+	.weak name; \
 name:
 
 #else /* PPC64_ELF_ABI_v1 */
@@ -65,8 +65,8 @@ name:
 #define	GLUE(a,b) XGLUE(a,b)
 #define	ENTRY(name) \
 	.align 2 ; \
-	.globl name; \
-	.globl GLUE(.,name); \
+	.weak name; \
+	.weak GLUE(.,name); \
 	.pushsection ".opd","aw"; \
 name: \
 	.quad GLUE(.,name); \
@@ -83,8 +83,8 @@ GLUE(.,name):
 #define	ENTRY(name) \
 	.text; \
 	.p2align 4; \
-	.globl  name; \
-	.type   name,@function; \
+	.weak name; \
+	.type name,@function; \
 name:
 
 #endif /* __powerpc64__ */
diff --git a/sys/contrib/openzfs/module/os/linux/zfs/zfs_ctldir.c b/sys/contrib/openzfs/module/os/linux/zfs/zfs_ctldir.c
index c2748ce450b4..26e785a0d422 100644
--- a/sys/contrib/openzfs/module/os/linux/zfs/zfs_ctldir.c
+++ b/sys/contrib/openzfs/module/os/linux/zfs/zfs_ctldir.c
@@ -31,6 +31,7 @@
  * Copyright 2015, OmniTI Computer Consulting, Inc. All rights reserved.
  * Copyright (c) 2018 George Melikov. All Rights Reserved.
  * Copyright (c) 2019 Datto, Inc. All rights reserved.
+ * Copyright (c) 2020 The MathWorks, Inc. All rights reserved.
  */
 
 /*
@@ -978,6 +979,22 @@ out:
 }
 
 /*
+ * Flush everything out of the kernel's export table and such.
+ * This is needed as once the snapshot is used over NFS, its
+ * entries in svc_export and svc_expkey caches hold reference
+ * to the snapshot mount point. There is no known way of flushing
+ * only the entries related to the snapshot.
+ */
+static void
+exportfs_flush(void)
+{
+	char *argv[] = { "/usr/sbin/exportfs", "-f", NULL };
+	char *envp[] = { NULL };
+
+	(void) call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+}
+
+/*
  * Attempt to unmount a snapshot by making a call to user space.
  * There is no assurance that this can or will succeed, is just a
  * best effort.  In the case where it does fail, perhaps because
@@ -999,6 +1016,8 @@ zfsctl_snapshot_unmount(char *snapname, int flags)
 	}
 	rw_exit(&zfs_snapshot_lock);
 
+	exportfs_flush();
+
 	if (flags & MNT_FORCE)
 		argv[4] = "-fn";
 	argv[5] = se->se_path;
diff --git a/sys/contrib/openzfs/module/zcommon/zfs_fletcher.c b/sys/contrib/openzfs/module/zcommon/zfs_fletcher.c
index 18998bceeada..3e0632a32864 100644
--- a/sys/contrib/openzfs/module/zcommon/zfs_fletcher.c
+++ b/sys/contrib/openzfs/module/zcommon/zfs_fletcher.c
@@ -187,7 +187,7 @@ static const fletcher_4_ops_t *fletcher_4_impls[] = {
 #if defined(__x86_64) && defined(HAVE_AVX512BW)
 	&fletcher_4_avx512bw_ops,
 #endif
-#if defined(__aarch64__)
+#if defined(__aarch64__) && !defined(__FreeBSD__)
 	&fletcher_4_aarch64_neon_ops,
 #endif
 };
diff --git a/sys/contrib/openzfs/module/zfs/arc.c b/sys/contrib/openzfs/module/zfs/arc.c
index bd1a993dca92..70565cc25011 100644
--- a/sys/contrib/openzfs/module/zfs/arc.c
+++ b/sys/contrib/openzfs/module/zfs/arc.c
@@ -823,6 +823,7 @@ unsigned long l2arc_feed_min_ms = L2ARC_FEED_MIN_MS;	/* min interval msecs */
 int l2arc_noprefetch = B_TRUE;			/* don't cache prefetch bufs */
 int l2arc_feed_again = B_TRUE;			/* turbo warmup */
 int l2arc_norw = B_FALSE;			/* no reads during writes */
+int l2arc_meta_percent = 33;			/* limit on headers size */
 
 /*
  * L2ARC Internals
@@ -4988,9 +4989,6 @@ arc_adapt(int bytes, arc_state_t *state)
 	int64_t mrug_size = zfs_refcount_count(&arc_mru_ghost->arcs_size);
 	int64_t mfug_size = zfs_refcount_count(&arc_mfu_ghost->arcs_size);
 
-	if (state == arc_l2c_only)
-		return;
-
 	ASSERT(bytes > 0);
 	/*
 	 * Adapt the target size of the MRU list:
@@ -9144,6 +9142,15 @@ l2arc_write_buffers(spa_t *spa, l2arc_dev_t *dev, uint64_t target_sz)
 	return (write_asize);
 }
 
+static boolean_t
+l2arc_hdr_limit_reached(void)
+{
+	int64_t s = aggsum_upper_bound(&astat_l2_hdr_size);
+
+	return (arc_reclaim_needed() || (s > arc_meta_limit * 3 / 4) ||
+	    (s > (arc_warm ? arc_c : arc_c_max) * l2arc_meta_percent / 100));
+}
+
 /*
  * This thread feeds the L2ARC at regular intervals.  This is the beating
  * heart of the L2ARC.
@@ -9211,7 +9218,7 @@ l2arc_feed_thread(void *unused)
 		/*
 		 * Avoid contributing to memory pressure.
 		 */
-		if (arc_reclaim_needed()) {
+		if (l2arc_hdr_limit_reached()) {
 			ARCSTAT_BUMP(arcstat_l2_abort_lowmem);
 			spa_config_exit(spa, SCL_L2ARC, dev);
 			continue;
@@ -9662,7 +9669,7 @@ l2arc_rebuild(l2arc_dev_t *dev)
 		 * online the L2ARC dev at a later time (or re-import the pool)
 		 * to reconstruct it (when there's less memory pressure).
 		 */
-		if (arc_reclaim_needed()) {
+		if (l2arc_hdr_limit_reached()) {
 			ARCSTAT_BUMP(arcstat_l2_rebuild_abort_lowmem);
 			cmn_err(CE_NOTE, "System running low on memory, "
 			    "aborting L2ARC rebuild.");
@@ -10002,6 +10009,13 @@ l2arc_log_blk_restore(l2arc_dev_t *dev, const l2arc_log_blk_phys_t *lb,
 	uint64_t	size = 0, asize = 0;
 	uint64_t	log_entries = dev->l2ad_log_entries;
 
+	/*
+	 * Usually arc_adapt() is called only for data, not headers, but
+	 * since we may allocate significant amount of memory here, let ARC
+	 * grow its arc_c.
+	 */
+	arc_adapt(log_entries * HDR_L2ONLY_SIZE, arc_l2c_only);
+
 	for (int i = log_entries - 1; i >= 0; i--) {
 		/*
 		 * Restore goes in the reverse temporal direction to preserve
@@ -10538,6 +10552,9 @@ ZFS_MODULE_PARAM(zfs_l2arc, l2arc_, feed_again, INT, ZMOD_RW,
 ZFS_MODULE_PARAM(zfs_l2arc, l2arc_, norw, INT, ZMOD_RW,
 	"No reads during writes");
 
+ZFS_MODULE_PARAM(zfs_l2arc, l2arc_, meta_percent, INT, ZMOD_RW,
+	"Percent of ARC size allowed for L2ARC-only headers");
+
 ZFS_MODULE_PARAM(zfs_l2arc, l2arc_, rebuild_enabled, INT, ZMOD_RW,
 	"Rebuild the L2ARC when importing a pool");
 
diff --git a/sys/contrib/openzfs/module/zfs/dmu.c b/sys/contrib/openzfs/module/zfs/dmu.c
index 06d6df618748..2c96645214f8 100644
--- a/sys/contrib/openzfs/module/zfs/dmu.c
+++ b/sys/contrib/openzfs/module/zfs/dmu.c
@@ -2458,6 +2458,7 @@ EXPORT_SYMBOL(dmu_object_set_blocksize);
 EXPORT_SYMBOL(dmu_object_set_maxblkid);
 EXPORT_SYMBOL(dmu_object_set_checksum);
 EXPORT_SYMBOL(dmu_object_set_compress);
+EXPORT_SYMBOL(dmu_offset_next);
 EXPORT_SYMBOL(dmu_write_policy);
 EXPORT_SYMBOL(dmu_sync);
 EXPORT_SYMBOL(dmu_request_arcbuf);
diff --git a/sys/contrib/openzfs/module/zfs/dnode_sync.c b/sys/contrib/openzfs/module/zfs/dnode_sync.c
index eafea3403c71..ae44cb69765c 100644
--- a/sys/contrib/openzfs/module/zfs/dnode_sync.c
+++ b/sys/contrib/openzfs/module/zfs/dnode_sync.c
@@ -23,6 +23,7 @@
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
  * Copyright (c) 2012, 2018 by Delphix. All rights reserved.
  * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
+ * Copyright 2020 Oxide Computer Company
  */
 
 #include <sys/zfs_context.h>
@@ -762,13 +763,22 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx)
 		dsfra.dsfra_dnode = dn;
 		dsfra.dsfra_tx = tx;
 		dsfra.dsfra_free_indirects = freeing_dnode;
+		mutex_enter(&dn->dn_mtx);
 		if (freeing_dnode) {
 			ASSERT(range_tree_contains(dn->dn_free_ranges[txgoff],
 			    0, dn->dn_maxblkid + 1));
 		}
-		mutex_enter(&dn->dn_mtx);
-		range_tree_vacate(dn->dn_free_ranges[txgoff],
+		/*
+		 * Because dnode_sync_free_range() must drop dn_mtx during its
+		 * processing, using it as a callback to range_tree_vacate() is
+		 * not safe.  No other operations (besides destroy) are allowed
+		 * once range_tree_vacate() has begun, and dropping dn_mtx
+		 * would leave a window open for another thread to observe that
+		 * invalid (and unsafe) state.
+		 */
+		range_tree_walk(dn->dn_free_ranges[txgoff],
 		    dnode_sync_free_range, &dsfra);
+		range_tree_vacate(dn->dn_free_ranges[txgoff], NULL, NULL);
 		range_tree_destroy(dn->dn_free_ranges[txgoff]);
 		dn->dn_free_ranges[txgoff] = NULL;
 		mutex_exit(&dn->dn_mtx);
diff --git a/sys/contrib/openzfs/module/zfs/dsl_dir.c b/sys/contrib/openzfs/module/zfs/dsl_dir.c
index 73b7943b8f99..29672e9a613e 100644
--- a/sys/contrib/openzfs/module/zfs/dsl_dir.c
+++ b/sys/contrib/openzfs/module/zfs/dsl_dir.c
@@ -121,13 +121,6 @@
  * and updated by dsl_fs_ss_count_adjust(). A new limit value is setup in
  * dsl_dir_activate_fs_ss_limit() and the counts are adjusted, if necessary, by
  * dsl_dir_init_fs_ss_count().
- *
- * There is a special case when we receive a filesystem that already exists. In
- * this case a temporary clone name of %X is created (see dmu_recv_begin). We
- * never update the filesystem counts for temporary clones.
- *
- * Likewise, we do not update the snapshot counts for temporary snapshots,
- * such as those created by zfs diff.
  */
 
 extern inline dsl_dir_phys_t *dsl_dir_phys(dsl_dir_t *dd);
@@ -593,11 +586,9 @@ dsl_dir_init_fs_ss_count(dsl_dir_t *dd, dmu_tx_t *tx)
 		    &chld_dd));
 
 		/*
-		 * Ignore hidden ($FREE, $MOS & $ORIGIN) objsets and
-		 * temporary datasets.
+		 * Ignore hidden ($FREE, $MOS & $ORIGIN) objsets.
 		 */
-		if (chld_dd->dd_myname[0] == '$' ||
-		    chld_dd->dd_myname[0] == '%') {
+		if (chld_dd->dd_myname[0] == '$') {
 			dsl_dir_rele(chld_dd, FTAG);
 			continue;
 		}
@@ -910,14 +901,12 @@ dsl_fs_ss_count_adjust(dsl_dir_t *dd, int64_t delta, const char *prop,
 	    strcmp(prop, DD_FIELD_SNAPSHOT_COUNT) == 0);
 
 	/*
-	 * When we receive an incremental stream into a filesystem that already
-	 * exists, a temporary clone is created.  We don't count this temporary
-	 * clone, whose name begins with a '%'. We also ignore hidden ($FREE,
-	 * $MOS & $ORIGIN) objsets.
+	 * We don't do accounting for hidden ($FREE, $MOS & $ORIGIN) objsets.
 	 */
-	if ((dd->dd_myname[0] == '%' || dd->dd_myname[0] == '$') &&
-	    strcmp(prop, DD_FIELD_FILESYSTEM_COUNT) == 0)
+	if (dd->dd_myname[0] == '$' && strcmp(prop,
+	    DD_FIELD_FILESYSTEM_COUNT) == 0) {
 		return;
+	}
 
 	/*
 	 * e.g. if renaming a dataset with no snapshots, count adjustment is 0
diff --git a/sys/contrib/openzfs/module/zfs/sa.c b/sys/contrib/openzfs/module/zfs/sa.c
index 977e729fe468..83a10e7b4548 100644
--- a/sys/contrib/openzfs/module/zfs/sa.c
+++ b/sys/contrib/openzfs/module/zfs/sa.c
@@ -39,7 +39,6 @@
 #include <sys/sa.h>
 #include <sys/sunddi.h>
 #include <sys/sa_impl.h>
-#include <sys/dnode.h>
 #include <sys/errno.h>
 #include <sys/zfs_context.h>
 
diff --git a/sys/contrib/openzfs/module/zfs/spa.c b/sys/contrib/openzfs/module/zfs/spa.c
index 1e3728d93cee..75ff398d17c7 100644
--- a/sys/contrib/openzfs/module/zfs/spa.c
+++ b/sys/contrib/openzfs/module/zfs/spa.c
@@ -3201,7 +3201,8 @@ spa_verify_host(spa_t *spa, nvlist_t *mos_config)
 			cmn_err(CE_WARN, "pool '%s' could not be "
 			    "loaded as it was last accessed by "
 			    "another system (host: %s hostid: 0x%llx). "
-			    "See: http://illumos.org/msg/ZFS-8000-EY",
+			    "See: https://openzfs.github.io/openzfs-docs/msg/"
+			    "ZFS-8000-EY",
 			    spa_name(spa), hostname, (u_longlong_t)hostid);
 			spa_load_failed(spa, "hostid verification failed: pool "
 			    "last accessed by host: %s (hostid: 0x%llx)",
diff --git a/sys/contrib/openzfs/module/zfs/vdev_raidz_math.c b/sys/contrib/openzfs/module/zfs/vdev_raidz_math.c
index aa92cb83d301..9595a7b95251 100644
--- a/sys/contrib/openzfs/module/zfs/vdev_raidz_math.c
+++ b/sys/contrib/openzfs/module/zfs/vdev_raidz_math.c
@@ -61,7 +61,7 @@ const raidz_impl_ops_t *raidz_all_maths[] = {
 #if defined(__x86_64) && defined(HAVE_AVX512BW)	/* only x86_64 for now */
 	&vdev_raidz_avx512bw_impl,
 #endif
-#if defined(__aarch64__)
+#if defined(__aarch64__) && !defined(__FreeBSD__)
 	&vdev_raidz_aarch64_neon_impl,
 	&vdev_raidz_aarch64_neonx2_impl,
 #endif
diff --git a/sys/contrib/openzfs/module/zstd/Makefile.in b/sys/contrib/openzfs/module/zstd/Makefile.in
index eea749ea8a5a..f67db710f097 100644
--- a/sys/contrib/openzfs/module/zstd/Makefile.in
+++ b/sys/contrib/openzfs/module/zstd/Makefile.in
@@ -20,6 +20,9 @@ ccflags-y += -O3
 # Set it for other compilers, too.
 $(obj)/lib/zstd.o: c_flags += -fno-tree-vectorize
 
+# SSE register return with SSE disabled if -march=znverX is passed
+$(obj)/lib/zstd.o: c_flags += -U__BMI__
+
 # Quiet warnings about frame size due to unused code in unmodified zstd lib
 $(obj)/lib/zstd.o: c_flags += -Wframe-larger-than=20480