Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

5 files changed, 975 insertions, 81 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index dc51616..a165552 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -460,16 +460,6 @@ config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 config LRU_CACHE
 	tristate
 
-config AVERAGE
-	bool "Averaging functions"
-	help
-	  This option is provided for the case where no in-kernel-tree
-	  modules require averaging functions, but a module built outside
-	  the kernel tree does. Such modules that use library averaging
-	  functions require Y here.
-
-	  If unsure, say N.
-
 config CLZ_TAB
 	bool
 
diff --git a/lib/Makefile b/lib/Makefile
index 2ee6ea2..f261006 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -138,8 +138,6 @@ obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
 
 obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
 
-obj-$(CONFIG_AVERAGE) += average.o
-
 obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
diff --git a/lib/average.c b/lib/average.c
deleted file mode 100644
index 114d1be..0000000
--- a/lib/average.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * lib/average.c
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
- */
-
-#include <linux/export.h>
-#include <linux/average.h>
-#include <linux/kernel.h>
-#include <linux/bug.h>
-#include <linux/log2.h>
-
-/**
- * DOC: Exponentially Weighted Moving Average (EWMA)
- *
- * These are generic functions for calculating Exponentially Weighted Moving
- * Averages (EWMA). We keep a structure with the EWMA parameters and a scaled
- * up internal representation of the average value to prevent rounding errors.
- * The factor for scaling up and the exponential weight (or decay rate) have to
- * be specified thru the init fuction. The structure should not be accessed
- * directly but only thru the helper functions.
- */
-
-/**
- * ewma_init() - Initialize EWMA parameters
- * @avg: Average structure
- * @factor: Factor to use for the scaled up internal value. The maximum value
- *	of averages can be ULONG_MAX/(factor*weight). For performance reasons
- *	factor has to be a power of 2.
- * @weight: Exponential weight, or decay rate. This defines how fast the
- *	influence of older values decreases. For performance reasons weight has
- *	to be a power of 2.
- *
- * Initialize the EWMA parameters for a given struct ewma @avg.
- */
-void ewma_init(struct ewma *avg, unsigned long factor, unsigned long weight)
-{
-	WARN_ON(!is_power_of_2(weight) || !is_power_of_2(factor));
-
-	avg->weight = ilog2(weight);
-	avg->factor = ilog2(factor);
-	avg->internal = 0;
-}
-EXPORT_SYMBOL(ewma_init);
-
-/**
- * ewma_add() - Exponentially weighted moving average (EWMA)
- * @avg: Average structure
- * @val: Current value
- *
- * Add a sample to the average.
- */
-struct ewma *ewma_add(struct ewma *avg, unsigned long val)
-{
-	unsigned long internal = ACCESS_ONCE(avg->internal);
-
-	ACCESS_ONCE(avg->internal) = internal ?
-		(((internal << avg->weight) - internal) +
-			(val << avg->factor)) >> avg->weight :
-		(val << avg->factor);
-	return avg;
-}
-EXPORT_SYMBOL(ewma_add);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 7f58c73..d137739 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -18,10 +18,12 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/filter.h>
+#include <linux/bpf.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/random.h>
+#include <linux/highmem.h>
 
 /* General test specific settings */
 #define MAX_SUBTESTS	3
@@ -55,6 +57,7 @@
 /* Flags that can be passed to test cases */
 #define FLAG_NO_DATA		BIT(0)
 #define FLAG_EXPECTED_FAIL	BIT(1)
+#define FLAG_SKB_FRAG		BIT(2)
 
 enum {
 	CLASSIC  = BIT(6),	/* Old BPF instructions only. */
@@ -80,6 +83,7 @@ struct bpf_test {
 		__u32 result;
 	} test[MAX_SUBTESTS];
 	int (*fill_helper)(struct bpf_test *self);
+	__u8 frag_data[MAX_DATA];
 };
 
 /* Large test cases need separate allocation and fill handler. */
@@ -355,6 +359,81 @@ static int bpf_fill_ja(struct bpf_test *self)
 	return __bpf_fill_ja(self, 12, 9);
 }
 
+static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct sock_filter *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	for (i = 0; i < len - 1; i += 2) {
+		insn[i] = __BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 0);
+		insn[i + 1] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+					 SKF_AD_OFF + SKF_AD_CPU);
+	}
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xbee);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+#define PUSH_CNT 68
+/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn;
+	int i = 0, j, k = 0;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[i++] = BPF_MOV64_REG(R6, R1);
+loop:
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(R1, R6);
+		insn[i++] = BPF_MOV64_IMM(R2, 1);
+		insn[i++] = BPF_MOV64_IMM(R3, 2);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 bpf_skb_vlan_push_proto.func - __bpf_call_base);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
+		i++;
+	}
+
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(R1, R6);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 bpf_skb_vlan_pop_proto.func - __bpf_call_base);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
+		i++;
+	}
+	if (++k < 5)
+		goto loop;
+
+	for (; i < len - 1; i++)
+		insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef);
+
+	insn[len - 1] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
 static struct bpf_test tests[] = {
 	{
 		"TAX",
@@ -3674,6 +3753,9 @@ static struct bpf_test tests[] = {
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
 			BPF_ENDIAN(BPF_FROM_BE, R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
@@ -3708,6 +3790,9 @@ static struct bpf_test tests[] = {
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
 			BPF_ENDIAN(BPF_FROM_LE, R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
@@ -4392,6 +4477,618 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xababcbac } },
 		.fill_helper = bpf_fill_maxinsns11,
 	},
+	{
+		"BPF_MAXINSNS: ld_abs+get_processor_id",
+		{ },
+		CLASSIC,
+		{ },
+		{ { 1, 0xbee } },
+		.fill_helper = bpf_fill_ld_abs_get_processor_id,
+	},
+	{
+		"BPF_MAXINSNS: ld_abs+vlan_push/pop",
+		{ },
+		INTERNAL,
+		{ 0x34 },
+		{ { 1, 0xbef } },
+		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+	},
+	/*
+	 * LD_IND / LD_ABS on fragmented SKBs
+	 */
+	{
+		"LD_IND byte frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x42} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND halfword frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x4344} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND word frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x8),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x21071983} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND halfword mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x0519} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_IND word mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x25051982} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_ABS byte frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x40),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x42} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS halfword frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x44),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x4344} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS word frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x48),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x21071983} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS halfword mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x0519} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_ABS word mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x25051982} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	/*
+	 * LD_IND / LD_ABS on non fragmented SKBs
+	 */
+	{
+		/*
+		 * this tests that the JIT/interpreter correctly resets X
+		 * before using it in an LD_IND instruction.
+		 */
+		"LD_IND byte default X",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x1] = 0x42 },
+		{ {0x40, 0x42 } },
+	},
+	{
+		"LD_IND byte positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 } },
+	},
+	{
+		"LD_IND byte negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x05 } },
+	},
+	{
+		"LD_IND halfword positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0xdd88 } },
+	},
+	{
+		"LD_IND halfword negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0xbb66 } },
+	},
+	{
+		"LD_IND halfword unaligned",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0x66cc } },
+	},
+	{
+		"LD_IND word positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xee99ffaa } },
+	},
+	{
+		"LD_IND word negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xaa55bb66 } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 2)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xbb66cc77 } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 1)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x55bb66cc } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 3)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x66cc77dd } },
+	},
+	{
+		"LD_ABS byte",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x20),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xcc } },
+	},
+	{
+		"LD_ABS halfword",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x22),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xdd88 } },
+	},
+	{
+		"LD_ABS halfword unaligned",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x25),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x99ff } },
+	},
+	{
+		"LD_ABS word",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x1c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xaa55bb66 } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 2)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x22),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xdd88ee99 } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 1)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x21),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x77dd88ee } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 3)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x23),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x88ee99ff } },
+	},
+	/*
+	 * verify that the interpreter or JIT correctly sets A and X
+	 * to 0.
+	 */
+	{
+		"ADD default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A + X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"ADD default A",
+		.u.insns = {
+			/*
+			 * A = A + 0x42
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"SUB default X",
+		.u.insns = {
+			/*
+			 * A = 0x66
+			 * A = A - X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x66),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x66 } },
+	},
+	{
+		"SUB default A",
+		.u.insns = {
+			/*
+			 * A = A - -0x66
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_K, -0x66),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x66 } },
+	},
+	{
+		"MUL default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A * X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_MUL | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"MUL default A",
+		.u.insns = {
+			/*
+			 * A = A * 0x66
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_MUL | BPF_K, 0x66),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"DIV default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A / X ; this halt the filter execution if X is 0
+			 * ret 0x42
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"DIV default A",
+		.u.insns = {
+			/*
+			 * A = A / 1
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"JMP EQ default A",
+		.u.insns = {
+			/*
+			 * cmp A, 0x0, 0, 1
+			 * ret 0x42
+			 * ret 0x66
+			 */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_K, 0x66),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"JMP EQ default X",
+		.u.insns = {
+			/*
+			 * A = 0x0
+			 * cmp A, X, 0, 1
+			 * ret 0x42
+			 * ret 0x66
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_X, 0x0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_K, 0x66),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
 };
 
 static struct net_device dev;
@@ -4427,6 +5124,9 @@ static struct sk_buff *populate_skb(char *buf, int size)
 
 static void *generate_test_data(struct bpf_test *test, int sub)
 {
+	struct sk_buff *skb;
+	struct page *page;
+
 	if (test->aux & FLAG_NO_DATA)
 		return NULL;
 
@@ -4434,7 +5134,38 @@ static void *generate_test_data(struct bpf_test *test, int sub)
 	 * subtests generate skbs of different sizes based on
 	 * the same data.
 	 */
-	return populate_skb(test->data, test->test[sub].data_size);
+	skb = populate_skb(test->data, test->test[sub].data_size);
+	if (!skb)
+		return NULL;
+
+	if (test->aux & FLAG_SKB_FRAG) {
+		/*
+		 * when the test requires a fragmented skb, add a
+		 * single fragment to the skb, filled with
+		 * test->frag_data.
+		 */
+		void *ptr;
+
+		page = alloc_page(GFP_KERNEL);
+
+		if (!page)
+			goto err_kfree_skb;
+
+		ptr = kmap(page);
+		if (!ptr)
+			goto err_free_page;
+		memcpy(ptr, test->frag_data, MAX_DATA);
+		kunmap(page);
+		skb_add_rx_frag(skb, 0, page, 0, MAX_DATA, MAX_DATA);
+	}
+
+	return skb;
+
+err_free_page:
+	__free_page(page);
+err_kfree_skb:
+	kfree_skb(skb);
+	return NULL;
 }
 
 static void release_test_data(const struct bpf_test *test, void *data)
@@ -4515,6 +5246,8 @@ static struct bpf_prog *generate_filter(int which, int *err)
 		}
 
 		fp->len = flen;
+		/* Type doesn't really matter here as long as it's not unspec. */
+		fp->type = BPF_PROG_TYPE_SOCKET_FILTER;
 		memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn));
 
 		bpf_prog_select_runtime(fp);
@@ -4545,14 +5278,14 @@ static int __run_one(const struct bpf_prog *fp, const void *data,
 	u64 start, finish;
 	int ret = 0, i;
 
-	start = ktime_to_us(ktime_get());
+	start = ktime_get_ns();
 
 	for (i = 0; i < runs; i++)
 		ret = BPF_PROG_RUN(fp, data);
 
-	finish = ktime_to_us(ktime_get());
+	finish = ktime_get_ns();
 
-	*duration = (finish - start) * 1000ULL;
+	*duration = finish - start;
 	do_div(*duration, runs);
 
 	return ret;
@@ -4572,6 +5305,11 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 			break;
 
 		data = generate_test_data(test, i);
+		if (!data && !(test->aux & FLAG_NO_DATA)) {
+			pr_cont("data generation failed ");
+			err_cnt++;
+			break;
+		}
 		ret = __run_one(fp, data, runs, &duration);
 		release_test_data(test, data);
 
@@ -4587,10 +5325,73 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 	return err_cnt;
 }
 
+static char test_name[64];
+module_param_string(test_name, test_name, sizeof(test_name), 0);
+
+static int test_id = -1;
+module_param(test_id, int, 0);
+
+static int test_range[2] = { 0, ARRAY_SIZE(tests) - 1 };
+module_param_array(test_range, int, NULL, 0);
+
+static __init int find_test_index(const char *test_name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!strcmp(tests[i].descr, test_name))
+			return i;
+	}
+	return -1;
+}
+
 static __init int prepare_bpf_tests(void)
 {
 	int i;
 
+	if (test_id >= 0) {
+		/*
+		 * if a test_id was specified, use test_range to
+		 * cover only that test.
+		 */
+		if (test_id >= ARRAY_SIZE(tests)) {
+			pr_err("test_bpf: invalid test_id specified.\n");
+			return -EINVAL;
+		}
+
+		test_range[0] = test_id;
+		test_range[1] = test_id;
+	} else if (*test_name) {
+		/*
+		 * if a test_name was specified, find it and setup
+		 * test_range to cover only that test.
+		 */
+		int idx = find_test_index(test_name);
+
+		if (idx < 0) {
+			pr_err("test_bpf: no test named '%s' found.\n",
+			       test_name);
+			return -EINVAL;
+		}
+		test_range[0] = idx;
+		test_range[1] = idx;
+	} else {
+		/*
+		 * check that the supplied test_range is valid.
+		 */
+		if (test_range[0] >= ARRAY_SIZE(tests) ||
+		    test_range[1] >= ARRAY_SIZE(tests) ||
+		    test_range[0] < 0 || test_range[1] < 0) {
+			pr_err("test_bpf: test_range is out of bound.\n");
+			return -EINVAL;
+		}
+
+		if (test_range[1] < test_range[0]) {
+			pr_err("test_bpf: test_range is ending before it starts.\n");
+			return -EINVAL;
+		}
+	}
+
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		if (tests[i].fill_helper &&
 		    tests[i].fill_helper(&tests[i]) < 0)
@@ -4610,6 +5411,11 @@ static __init void destroy_bpf_tests(void)
 	}
 }
 
+static bool exclude_test(int test_id)
+{
+	return test_id < test_range[0] || test_id > test_range[1];
+}
+
 static __init int test_bpf(void)
 {
 	int i, err_cnt = 0, pass_cnt = 0;
@@ -4619,6 +5425,9 @@ static __init int test_bpf(void)
 		struct bpf_prog *fp;
 		int err;
 
+		if (exclude_test(i))
+			continue;
+
 		pr_info("#%d %s ", i, tests[i].descr);
 
 		fp = generate_filter(i, &err);
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c90777e..8c1ad1c 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -16,10 +16,14 @@
 #include <linux/init.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/rhashtable.h>
+#include <linux/semaphore.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
 
 #define MAX_ENTRIES	1000000
 #define TEST_INSERT_FAIL INT_MAX
@@ -44,11 +48,21 @@ static int size = 8;
 module_param(size, int, 0);
 MODULE_PARM_DESC(size, "Initial size hint of table (default: 8)");
 
+static int tcount = 10;
+module_param(tcount, int, 0);
+MODULE_PARM_DESC(tcount, "Number of threads to spawn (default: 10)");
+
 struct test_obj {
 	int			value;
 	struct rhash_head	node;
 };
 
+struct thread_data {
+	int id;
+	struct task_struct *task;
+	struct test_obj *objs;
+};
+
 static struct test_obj array[MAX_ENTRIES];
 
 static struct rhashtable_params test_rht_params = {
@@ -59,6 +73,9 @@ static struct rhashtable_params test_rht_params = {
 	.nulls_base = (3U << RHT_BASE_SHIFT),
 };
 
+static struct semaphore prestart_sem;
+static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
+
 static int __init test_rht_lookup(struct rhashtable *ht)
 {
 	unsigned int i;
@@ -87,6 +104,8 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 				return -EINVAL;
 			}
 		}
+
+		cond_resched_rcu();
 	}
 
 	return 0;
@@ -160,6 +179,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 		} else if (err) {
 			return err;
 		}
+
+		cond_resched();
 	}
 
 	if (insert_fails)
@@ -183,6 +204,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 
 			rhashtable_remove_fast(ht, &obj->node, test_rht_params);
 		}
+
+		cond_resched();
 	}
 
 	end = ktime_get_ns();
@@ -193,10 +216,97 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 
 static struct rhashtable ht;
 
+static int thread_lookup_test(struct thread_data *tdata)
+{
+	int i, err = 0;
+
+	for (i = 0; i < entries; i++) {
+		struct test_obj *obj;
+		int key = (tdata->id << 16) | i;
+
+		obj = rhashtable_lookup_fast(&ht, &key, test_rht_params);
+		if (obj && (tdata->objs[i].value == TEST_INSERT_FAIL)) {
+			pr_err("  found unexpected object %d\n", key);
+			err++;
+		} else if (!obj && (tdata->objs[i].value != TEST_INSERT_FAIL)) {
+			pr_err("  object %d not found!\n", key);
+			err++;
+		} else if (obj && (obj->value != key)) {
+			pr_err("  wrong object returned (got %d, expected %d)\n",
+			       obj->value, key);
+			err++;
+		}
+	}
+	return err;
+}
+
+static int threadfunc(void *data)
+{
+	int i, step, err = 0, insert_fails = 0;
+	struct thread_data *tdata = data;
+
+	up(&prestart_sem);
+	if (down_interruptible(&startup_sem))
+		pr_err("  thread[%d]: down_interruptible failed\n", tdata->id);
+
+	for (i = 0; i < entries; i++) {
+		tdata->objs[i].value = (tdata->id << 16) | i;
+		err = rhashtable_insert_fast(&ht, &tdata->objs[i].node,
+		                             test_rht_params);
+		if (err == -ENOMEM || err == -EBUSY) {
+			tdata->objs[i].value = TEST_INSERT_FAIL;
+			insert_fails++;
+		} else if (err) {
+			pr_err("  thread[%d]: rhashtable_insert_fast failed\n",
+			       tdata->id);
+			goto out;
+		}
+	}
+	if (insert_fails)
+		pr_info("  thread[%d]: %d insert failures\n",
+		        tdata->id, insert_fails);
+
+	err = thread_lookup_test(tdata);
+	if (err) {
+		pr_err("  thread[%d]: rhashtable_lookup_test failed\n",
+		       tdata->id);
+		goto out;
+	}
+
+	for (step = 10; step > 0; step--) {
+		for (i = 0; i < entries; i += step) {
+			if (tdata->objs[i].value == TEST_INSERT_FAIL)
+				continue;
+			err = rhashtable_remove_fast(&ht, &tdata->objs[i].node,
+			                             test_rht_params);
+			if (err) {
+				pr_err("  thread[%d]: rhashtable_remove_fast failed\n",
+				       tdata->id);
+				goto out;
+			}
+			tdata->objs[i].value = TEST_INSERT_FAIL;
+		}
+		err = thread_lookup_test(tdata);
+		if (err) {
+			pr_err("  thread[%d]: rhashtable_lookup_test (2) failed\n",
+			       tdata->id);
+			goto out;
+		}
+	}
+out:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+	return err;
+}
+
 static int __init test_rht_init(void)
 {
-	int i, err;
+	int i, err, started_threads = 0, failed_threads = 0;
 	u64 total_time = 0;
+	struct thread_data *tdata;
+	struct test_obj *objs;
 
 	entries = min(entries, MAX_ENTRIES);
 
@@ -232,6 +342,57 @@ static int __init test_rht_init(void)
 	do_div(total_time, runs);
 	pr_info("Average test time: %llu\n", total_time);
 
+	if (!tcount)
+		return 0;
+
+	pr_info("Testing concurrent rhashtable access from %d threads\n",
+	        tcount);
+	sema_init(&prestart_sem, 1 - tcount);
+	tdata = vzalloc(tcount * sizeof(struct thread_data));
+	if (!tdata)
+		return -ENOMEM;
+	objs  = vzalloc(tcount * entries * sizeof(struct test_obj));
+	if (!objs) {
+		vfree(tdata);
+		return -ENOMEM;
+	}
+
+	err = rhashtable_init(&ht, &test_rht_params);
+	if (err < 0) {
+		pr_warn("Test failed: Unable to initialize hashtable: %d\n",
+			err);
+		vfree(tdata);
+		vfree(objs);
+		return -EINVAL;
+	}
+	for (i = 0; i < tcount; i++) {
+		tdata[i].id = i;
+		tdata[i].objs = objs + i * entries;
+		tdata[i].task = kthread_run(threadfunc, &tdata[i],
+		                            "rhashtable_thrad[%d]", i);
+		if (IS_ERR(tdata[i].task))
+			pr_err(" kthread_run failed for thread %d\n", i);
+		else
+			started_threads++;
+	}
+	if (down_interruptible(&prestart_sem))
+		pr_err("  down interruptible failed\n");
+	for (i = 0; i < tcount; i++)
+		up(&startup_sem);
+	for (i = 0; i < tcount; i++) {
+		if (IS_ERR(tdata[i].task))
+			continue;
+		if ((err = kthread_stop(tdata[i].task))) {
+			pr_warn("Test failed: thread %d returned: %d\n",
+			        i, err);
+			failed_threads++;
+		}
+	}
+	pr_info("Started %d threads, %d failed\n",
+	        started_threads, failed_threads);
+	rhashtable_destroy(&ht);
+	vfree(tdata);
+	vfree(objs);
 	return 0;
 }