[illumos-gate merge]

commit ad69a33458cf73ee14857d57799cf686946e0b88
    5491 libipadm`i_ipadm_init_ifs() calls free() on bogus memory address
commit 4076b1bf41cfd9f968a33ed54a7ae76d9e996fe8
    5445 Add more visibility via arcstats; specifically arc_state_t stats and differentiate between "data" and "metadata"

4 files changed, 241 insertions, 23 deletions

diff --git a/usr/src/cmd/mdb/common/modules/zfs/zfs.c b/usr/src/cmd/mdb/common/modules/zfs/zfs.c
index e940623d22..225cf3dee1 100644
--- a/usr/src/cmd/mdb/common/modules/zfs/zfs.c
+++ b/usr/src/cmd/mdb/common/modules/zfs/zfs.c
@@ -960,10 +960,16 @@ arc_print(uintptr_t addr, uint_t flags, int argc, const mdb_arg_t *argv)
 	static const char *bytestats[] = {
 		"p", "c", "c_min", "c_max", "size", "duplicate_buffers_size",
 		"arc_meta_used", "arc_meta_limit", "arc_meta_max",
-		"arc_meta_min", "hdr_size", "data_size", "other_size",
-		"evict_l2_cached", "evict_l2_eligible", "evict_l2_ineligible",
-		"l2_read_bytes", "l2_write_bytes", "l2_size", "l2_asize",
-		"l2_hdr_size",
+		"arc_meta_min", "hdr_size", "data_size", "metadata_size",
+		"other_size", "anon_size", "anon_evictable_data",
+		"anon_evictable_metadata", "mru_size", "mru_evictable_data",
+		"mru_evictable_metadata", "mru_ghost_size",
+		"mru_ghost_evictable_data", "mru_ghost_evictable_metadata",
+		"mfu_size", "mfu_evictable_data", "mfu_evictable_metadata",
+		"mfu_ghost_size", "mfu_ghost_evictable_data",
+		"mfu_ghost_evictable_metadata", "evict_l2_cached",
+		"evict_l2_eligible", "evict_l2_ineligible", "l2_read_bytes",
+		"l2_write_bytes", "l2_size", "l2_asize", "l2_hdr_size",
 		NULL
 	};
 
diff --git a/usr/src/lib/libipadm/common/libipadm.c b/usr/src/lib/libipadm/common/libipadm.c
index e897771556..068c8d6535 100644
--- a/usr/src/lib/libipadm/common/libipadm.c
+++ b/usr/src/lib/libipadm/common/libipadm.c
@@ -18,9 +18,11 @@
  *
  * CDDL HEADER END
  */
+
 /*
  * Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved.
  * Copyright 2014, Joyent, Inc. All rights reserved.
+ * Copyright 2014 Nexenta Systems, Inc.  All rights reserved.
  */
 
 #include <stdio.h>
@@ -815,14 +817,14 @@ i_ipadm_init_ifs(ipadm_handle_t iph, const char *ifs, nvlist_t **allifs)
 		status = ipadm_errno2status(err);
 		goto done;
 	}
-	nvlsize = rvalp->ir_nvlsize;
-	nvlbuf = (char *)rvalp + sizeof (ipmgmt_get_rval_t);
 
 	/*
-	 * nvlbuf contains a list of nvlists, each of which represents
-	 * configuration information for the given interface(s)
+	 * Daemon reply pointed to by rvalp contains ipmgmt_get_rval_t structure
+	 * followed by a list of packed nvlists, each of which represents
+	 * configuration information for the given interface(s).
 	 */
-	err = nvlist_unpack(nvlbuf, nvlsize, allifs, NV_ENCODE_NATIVE);
+	err = nvlist_unpack((char *)rvalp + sizeof (ipmgmt_get_rval_t),
+	    rvalp->ir_nvlsize, allifs, NV_ENCODE_NATIVE);
 	if (err != 0)
 		status = ipadm_errno2status(err);
 done:
diff --git a/usr/src/uts/common/fs/zfs/arc.c b/usr/src/uts/common/fs/zfs/arc.c
index 01843c4b43..55a99b7944 100644
--- a/usr/src/uts/common/fs/zfs/arc.c
+++ b/usr/src/uts/common/fs/zfs/arc.c
@@ -301,9 +301,137 @@ typedef struct arc_stats {
 	kstat_named_t arcstat_c_min;
 	kstat_named_t arcstat_c_max;
 	kstat_named_t arcstat_size;
+	/*
+	 * Number of bytes consumed by internal ARC structures necessary
+	 * for tracking purposes; these structures are not actually
+	 * backed by ARC buffers. This includes arc_buf_hdr_t structures
+	 * (allocated via arc_buf_hdr_t_full and arc_buf_hdr_t_l2only
+	 * caches), and arc_buf_t structures (allocated via arc_buf_t
+	 * cache).
+	 */
 	kstat_named_t arcstat_hdr_size;
+	/*
+	 * Number of bytes consumed by ARC buffers of type equal to
+	 * ARC_BUFC_DATA. This is generally consumed by buffers backing
+	 * on disk user data (e.g. plain file contents).
+	 */
 	kstat_named_t arcstat_data_size;
+	/*
+	 * Number of bytes consumed by ARC buffers of type equal to
+	 * ARC_BUFC_METADATA. This is generally consumed by buffers
+	 * backing on disk data that is used for internal ZFS
+	 * structures (e.g. ZAP, dnode, indirect blocks, etc).
+	 */
+	kstat_named_t arcstat_metadata_size;
+	/*
+	 * Number of bytes consumed by various buffers and structures
+	 * not actually backed with ARC buffers. This includes bonus
+	 * buffers (allocated directly via zio_buf_* functions),
+	 * dmu_buf_impl_t structures (allocated via dmu_buf_impl_t
+	 * cache), and dnode_t structures (allocated via dnode_t cache).
+	 */
 	kstat_named_t arcstat_other_size;
+	/*
+	 * Total number of bytes consumed by ARC buffers residing in the
+	 * arc_anon state. This includes *all* buffers in the arc_anon
+	 * state; e.g. data, metadata, evictable, and unevictable buffers
+	 * are all included in this value.
+	 */
+	kstat_named_t arcstat_anon_size;
+	/*
+	 * Number of bytes consumed by ARC buffers that meet the
+	 * following criteria: backing buffers of type ARC_BUFC_DATA,
+	 * residing in the arc_anon state, and are eligible for eviction
+	 * (e.g. have no outstanding holds on the buffer).
+	 */
+	kstat_named_t arcstat_anon_evictable_data;
+	/*
+	 * Number of bytes consumed by ARC buffers that meet the
+	 * following criteria: backing buffers of type ARC_BUFC_METADATA,
+	 * residing in the arc_anon state, and are eligible for eviction
+	 * (e.g. have no outstanding holds on the buffer).
+	 */
+	kstat_named_t arcstat_anon_evictable_metadata;
+	/*
+	 * Total number of bytes consumed by ARC buffers residing in the
+	 * arc_mru state. This includes *all* buffers in the arc_mru
+	 * state; e.g. data, metadata, evictable, and unevictable buffers
+	 * are all included in this value.
+	 */
+	kstat_named_t arcstat_mru_size;
+	/*
+	 * Number of bytes consumed by ARC buffers that meet the
+	 * following criteria: backing buffers of type ARC_BUFC_DATA,
+	 * residing in the arc_mru state, and are eligible for eviction
+	 * (e.g. have no outstanding holds on the buffer).
+	 */
+	kstat_named_t arcstat_mru_evictable_data;
+	/*
+	 * Number of bytes consumed by ARC buffers that meet the
+	 * following criteria: backing buffers of type ARC_BUFC_METADATA,
+	 * residing in the arc_mru state, and are eligible for eviction
+	 * (e.g. have no outstanding holds on the buffer).
+	 */
+	kstat_named_t arcstat_mru_evictable_metadata;
+	/*
+	 * Total number of bytes that *would have been* consumed by ARC
+	 * buffers in the arc_mru_ghost state. The key thing to note
+	 * here, is the fact that this size doesn't actually indicate
+	 * RAM consumption. The ghost lists only consist of headers and
+	 * don't actually have ARC buffers linked off of these headers.
+	 * Thus, *if* the headers had associated ARC buffers, these
+	 * buffers *would have* consumed this number of bytes.
+	 */
+	kstat_named_t arcstat_mru_ghost_size;
+	/*
+	 * Number of bytes that *would have been* consumed by ARC
+	 * buffers that are eligible for eviction, of type
+	 * ARC_BUFC_DATA, and linked off the arc_mru_ghost state.
+	 */
+	kstat_named_t arcstat_mru_ghost_evictable_data;
+	/*
+	 * Number of bytes that *would have been* consumed by ARC
+	 * buffers that are eligible for eviction, of type
+	 * ARC_BUFC_METADATA, and linked off the arc_mru_ghost state.
+	 */
+	kstat_named_t arcstat_mru_ghost_evictable_metadata;
+	/*
+	 * Total number of bytes consumed by ARC buffers residing in the
+	 * arc_mfu state. This includes *all* buffers in the arc_mfu
+	 * state; e.g. data, metadata, evictable, and unevictable buffers
+	 * are all included in this value.
+	 */
+	kstat_named_t arcstat_mfu_size;
+	/*
+	 * Number of bytes consumed by ARC buffers that are eligible for
+	 * eviction, of type ARC_BUFC_DATA, and reside in the arc_mfu
+	 * state.
+	 */
+	kstat_named_t arcstat_mfu_evictable_data;
+	/*
+	 * Number of bytes consumed by ARC buffers that are eligible for
+	 * eviction, of type ARC_BUFC_METADATA, and reside in the
+	 * arc_mfu state.
+	 */
+	kstat_named_t arcstat_mfu_evictable_metadata;
+	/*
+	 * Total number of bytes that *would have been* consumed by ARC
+	 * buffers in the arc_mfu_ghost state. See the comment above
+	 * arcstat_mru_ghost_size for more details.
+	 */
+	kstat_named_t arcstat_mfu_ghost_size;
+	/*
+	 * Number of bytes that *would have been* consumed by ARC
+	 * buffers that are eligible for eviction, of type
+	 * ARC_BUFC_DATA, and linked off the arc_mfu_ghost state.
+	 */
+	kstat_named_t arcstat_mfu_ghost_evictable_data;
+	/*
+	 * Number of bytes that *would have been* consumed by ARC
+	 * buffers that are eligible for eviction, of type
+	 * ARC_BUFC_METADATA, and linked off the arc_mru_ghost state.
+	 */
+	kstat_named_t arcstat_mfu_ghost_evictable_metadata;
 	kstat_named_t arcstat_l2_hits;
 	kstat_named_t arcstat_l2_misses;
 	kstat_named_t arcstat_l2_feeds;
@@ -372,7 +500,23 @@ static arc_stats_t arc_stats = {
 	{ "size",			KSTAT_DATA_UINT64 },
 	{ "hdr_size",			KSTAT_DATA_UINT64 },
 	{ "data_size",			KSTAT_DATA_UINT64 },
+	{ "metadata_size",		KSTAT_DATA_UINT64 },
 	{ "other_size",			KSTAT_DATA_UINT64 },
+	{ "anon_size",			KSTAT_DATA_UINT64 },
+	{ "anon_evictable_data",	KSTAT_DATA_UINT64 },
+	{ "anon_evictable_metadata",	KSTAT_DATA_UINT64 },
+	{ "mru_size",			KSTAT_DATA_UINT64 },
+	{ "mru_evictable_data",		KSTAT_DATA_UINT64 },
+	{ "mru_evictable_metadata",	KSTAT_DATA_UINT64 },
+	{ "mru_ghost_size",		KSTAT_DATA_UINT64 },
+	{ "mru_ghost_evictable_data",	KSTAT_DATA_UINT64 },
+	{ "mru_ghost_evictable_metadata", KSTAT_DATA_UINT64 },
+	{ "mfu_size",			KSTAT_DATA_UINT64 },
+	{ "mfu_evictable_data",		KSTAT_DATA_UINT64 },
+	{ "mfu_evictable_metadata",	KSTAT_DATA_UINT64 },
+	{ "mfu_ghost_size",		KSTAT_DATA_UINT64 },
+	{ "mfu_ghost_evictable_data",	KSTAT_DATA_UINT64 },
+	{ "mfu_ghost_evictable_metadata", KSTAT_DATA_UINT64 },
 	{ "l2_hits",			KSTAT_DATA_UINT64 },
 	{ "l2_misses",			KSTAT_DATA_UINT64 },
 	{ "l2_feeds",			KSTAT_DATA_UINT64 },
@@ -1503,6 +1647,9 @@ arc_space_consume(uint64_t space, arc_space_type_t type)
 	case ARC_SPACE_DATA:
 		ARCSTAT_INCR(arcstat_data_size, space);
 		break;
+	case ARC_SPACE_META:
+		ARCSTAT_INCR(arcstat_metadata_size, space);
+		break;
 	case ARC_SPACE_OTHER:
 		ARCSTAT_INCR(arcstat_other_size, space);
 		break;
@@ -1514,7 +1661,9 @@ arc_space_consume(uint64_t space, arc_space_type_t type)
 		break;
 	}
 
-	ARCSTAT_INCR(arcstat_meta_used, space);
+	if (type != ARC_SPACE_DATA)
+		ARCSTAT_INCR(arcstat_meta_used, space);
+
 	atomic_add_64(&arc_size, space);
 }
 
@@ -1527,6 +1676,9 @@ arc_space_return(uint64_t space, arc_space_type_t type)
 	case ARC_SPACE_DATA:
 		ARCSTAT_INCR(arcstat_data_size, -space);
 		break;
+	case ARC_SPACE_META:
+		ARCSTAT_INCR(arcstat_metadata_size, -space);
+		break;
 	case ARC_SPACE_OTHER:
 		ARCSTAT_INCR(arcstat_other_size, -space);
 		break;
@@ -1538,10 +1690,13 @@ arc_space_return(uint64_t space, arc_space_type_t type)
 		break;
 	}
 
-	ASSERT(arc_meta_used >= space);
-	if (arc_meta_max < arc_meta_used)
-		arc_meta_max = arc_meta_used;
-	ARCSTAT_INCR(arcstat_meta_used, -space);
+	if (type != ARC_SPACE_DATA) {
+		ASSERT(arc_meta_used >= space);
+		if (arc_meta_max < arc_meta_used)
+			arc_meta_max = arc_meta_used;
+		ARCSTAT_INCR(arcstat_meta_used, -space);
+	}
+
 	ASSERT(arc_size >= space);
 	atomic_add_64(&arc_size, -space);
 }
@@ -1747,12 +1902,11 @@ arc_buf_destroy(arc_buf_t *buf, boolean_t recycle, boolean_t remove)
 		if (!recycle) {
 			if (type == ARC_BUFC_METADATA) {
 				arc_buf_data_free(buf, zio_buf_free);
-				arc_space_return(size, ARC_SPACE_DATA);
+				arc_space_return(size, ARC_SPACE_META);
 			} else {
 				ASSERT(type == ARC_BUFC_DATA);
 				arc_buf_data_free(buf, zio_data_buf_free);
-				ARCSTAT_INCR(arcstat_data_size, -size);
-				atomic_add_64(&arc_size, -size);
+				arc_space_return(size, ARC_SPACE_DATA);
 			}
 		}
 		if (list_link_active(&buf->b_hdr->b_l1hdr.b_arc_node)) {
@@ -2745,6 +2899,20 @@ arc_reclaim_thread(void)
 		if (arc_eviction_list != NULL)
 			arc_do_user_evicts();
 
+		/*
+		 * This is necessary in order for the mdb ::arc dcmd to
+		 * show up to date information. Since the ::arc command
+		 * does not call the kstat's update function, without
+		 * this call, the command may show stale stats for the
+		 * anon, mru, mru_ghost, mfu, and mfu_ghost lists. Even
+		 * with this change, the data might be up to 1 second
+		 * out of date; but that should suffice. The arc_state_t
+		 * structures can be queried directly if more accurate
+		 * information is needed.
+		 */
+		if (arc_ksp != NULL)
+			arc_ksp->ks_update(arc_ksp, KSTAT_READ);
+
 		/* block until needed, or one second, whichever is shorter */
 		CALLB_CPR_SAFE_BEGIN(&cpr);
 		(void) cv_timedwait(&arc_reclaim_thr_cv,
@@ -2882,15 +3050,14 @@ arc_get_data_buf(arc_buf_t *buf)
 		if (type == ARC_BUFC_METADATA) {
 			buf->b_data = zio_buf_alloc_canfail(size);
 			if (buf->b_data != NULL) {
-				arc_space_consume(size, ARC_SPACE_DATA);
+				arc_space_consume(size, ARC_SPACE_META);
 				goto out;
 			}
 		} else {
 			ASSERT(type == ARC_BUFC_DATA);
 			buf->b_data = zio_data_buf_alloc_canfail(size);
 			if (buf->b_data != NULL) {
-				ARCSTAT_INCR(arcstat_data_size, size);
-				atomic_add_64(&arc_size, size);
+				arc_space_consume(size, ARC_SPACE_DATA);
 				goto out;
 			}
 		}
@@ -2925,12 +3092,11 @@ arc_get_data_buf(arc_buf_t *buf)
 	if ((buf->b_data = arc_evict(state, NULL, size, TRUE, type)) == NULL) {
 		if (type == ARC_BUFC_METADATA) {
 			buf->b_data = zio_buf_alloc(size);
-			arc_space_consume(size, ARC_SPACE_DATA);
+			arc_space_consume(size, ARC_SPACE_META);
 		} else {
 			ASSERT(type == ARC_BUFC_DATA);
 			buf->b_data = zio_data_buf_alloc(size);
-			ARCSTAT_INCR(arcstat_data_size, size);
-			atomic_add_64(&arc_size, size);
+			arc_space_consume(size, ARC_SPACE_DATA);
 		}
 		ARCSTAT_BUMP(arcstat_recycle_miss);
 	}
@@ -4138,6 +4304,48 @@ arc_tempreserve_space(uint64_t reserve, uint64_t txg)
 	return (0);
 }
 
+static void
+arc_kstat_update_state(arc_state_t *state, kstat_named_t *size,
+    kstat_named_t *evict_data, kstat_named_t *evict_metadata)
+{
+	size->value.ui64 = state->arcs_size;
+	evict_data->value.ui64 = state->arcs_lsize[ARC_BUFC_DATA];
+	evict_metadata->value.ui64 = state->arcs_lsize[ARC_BUFC_METADATA];
+}
+
+static int
+arc_kstat_update(kstat_t *ksp, int rw)
+{
+	arc_stats_t *as = ksp->ks_data;
+
+	if (rw == KSTAT_WRITE) {
+		return (EACCES);
+	} else {
+		arc_kstat_update_state(arc_anon,
+		    &as->arcstat_anon_size,
+		    &as->arcstat_anon_evictable_data,
+		    &as->arcstat_anon_evictable_metadata);
+		arc_kstat_update_state(arc_mru,
+		    &as->arcstat_mru_size,
+		    &as->arcstat_mru_evictable_data,
+		    &as->arcstat_mru_evictable_metadata);
+		arc_kstat_update_state(arc_mru_ghost,
+		    &as->arcstat_mru_ghost_size,
+		    &as->arcstat_mru_ghost_evictable_data,
+		    &as->arcstat_mru_ghost_evictable_metadata);
+		arc_kstat_update_state(arc_mfu,
+		    &as->arcstat_mfu_size,
+		    &as->arcstat_mfu_evictable_data,
+		    &as->arcstat_mfu_evictable_metadata);
+		arc_kstat_update_state(arc_mfu_ghost,
+		    &as->arcstat_mfu_ghost_size,
+		    &as->arcstat_mfu_ghost_evictable_data,
+		    &as->arcstat_mfu_ghost_evictable_metadata);
+	}
+
+	return (0);
+}
+
 void
 arc_init(void)
 {
@@ -4284,6 +4492,7 @@ arc_init(void)
 
 	if (arc_ksp != NULL) {
 		arc_ksp->ks_data = &arc_stats;
+		arc_ksp->ks_update = arc_kstat_update;
 		kstat_install(arc_ksp);
 	}
 
diff --git a/usr/src/uts/common/fs/zfs/sys/arc.h b/usr/src/uts/common/fs/zfs/sys/arc.h
index 4e9e8e202a..60112baaba 100644
--- a/usr/src/uts/common/fs/zfs/sys/arc.h
+++ b/usr/src/uts/common/fs/zfs/sys/arc.h
@@ -115,6 +115,7 @@ typedef enum arc_buf_contents {
  */
 typedef enum arc_space_type {
 	ARC_SPACE_DATA,
+	ARC_SPACE_META,
 	ARC_SPACE_HDRS,
 	ARC_SPACE_L2HDRS,
 	ARC_SPACE_OTHER,