Linux-libre 4.2-gnu

39 files changed, 4415 insertions, 237 deletions

diff --git a/lib/842/842.h b/lib/842/842.h
new file mode 100644
index 000000000..7c200030a
--- /dev/null
+++ b/lib/842/842.h
@@ -0,0 +1,127 @@
+
+#ifndef __842_H__
+#define __842_H__
+
+/* The 842 compressed format is made up of multiple blocks, each of
+ * which have the format:
+ *
+ * <template>[arg1][arg2][arg3][arg4]
+ *
+ * where there are between 0 and 4 template args, depending on the specific
+ * template operation.  For normal operations, each arg is either a specific
+ * number of data bytes to add to the output buffer, or an index pointing
+ * to a previously-written number of data bytes to copy to the output buffer.
+ *
+ * The template code is a 5-bit value.  This code indicates what to do with
+ * the following data.  Template codes from 0 to 0x19 should use the template
+ * table, the static "decomp_ops" table used in decompress.  For each template
+ * (table row), there are between 1 and 4 actions; each action corresponds to
+ * an arg following the template code bits.  Each action is either a "data"
+ * type action, or a "index" type action, and each action results in 2, 4, or 8
+ * bytes being written to the output buffer.  Each template (i.e. all actions
+ * in the table row) will add up to 8 bytes being written to the output buffer.
+ * Any row with less than 4 actions is padded with noop actions, indicated by
+ * N0 (for which there is no corresponding arg in the compressed data buffer).
+ *
+ * "Data" actions, indicated in the table by D2, D4, and D8, mean that the
+ * corresponding arg is 2, 4, or 8 bytes, respectively, in the compressed data
+ * buffer should be copied directly to the output buffer.
+ *
+ * "Index" actions, indicated in the table by I2, I4, and I8, mean the
+ * corresponding arg is an index parameter that points to, respectively, a 2,
+ * 4, or 8 byte value already in the output buffer, that should be copied to
+ * the end of the output buffer.  Essentially, the index points to a position
+ * in a ring buffer that contains the last N bytes of output buffer data.
+ * The number of bits for each index's arg are: 8 bits for I2, 9 bits for I4,
+ * and 8 bits for I8.  Since each index points to a 2, 4, or 8 byte section,
+ * this means that I2 can reference 512 bytes ((2^8 bits = 256) * 2 bytes), I4
+ * can reference 2048 bytes ((2^9 = 512) * 4 bytes), and I8 can reference 2048
+ * bytes ((2^8 = 256) * 8 bytes).  Think of it as a kind-of ring buffer for
+ * each of I2, I4, and I8 that are updated for each byte written to the output
+ * buffer.  In this implementation, the output buffer is directly used for each
+ * index; there is no additional memory required.  Note that the index is into
+ * a ring buffer, not a sliding window; for example, if there have been 260
+ * bytes written to the output buffer, an I2 index of 0 would index to byte 256
+ * in the output buffer, while an I2 index of 16 would index to byte 16 in the
+ * output buffer.
+ *
+ * There are also 3 special template codes; 0x1b for "repeat", 0x1c for
+ * "zeros", and 0x1e for "end".  The "repeat" operation is followed by a 6 bit
+ * arg N indicating how many times to repeat.  The last 8 bytes written to the
+ * output buffer are written again to the output buffer, N + 1 times.  The
+ * "zeros" operation, which has no arg bits, writes 8 zeros to the output
+ * buffer.  The "end" operation, which also has no arg bits, signals the end
+ * of the compressed data.  There may be some number of padding (don't care,
+ * but usually 0) bits after the "end" operation bits, to fill the buffer
+ * length to a specific byte multiple (usually a multiple of 8, 16, or 32
+ * bytes).
+ *
+ * This software implementation also uses one of the undefined template values,
+ * 0x1d as a special "short data" template code, to represent less than 8 bytes
+ * of uncompressed data.  It is followed by a 3 bit arg N indicating how many
+ * data bytes will follow, and then N bytes of data, which should be copied to
+ * the output buffer.  This allows the software 842 compressor to accept input
+ * buffers that are not an exact multiple of 8 bytes long.  However, those
+ * compressed buffers containing this sw-only template will be rejected by
+ * the 842 hardware decompressor, and must be decompressed with this software
+ * library.  The 842 software compression module includes a parameter to
+ * disable using this sw-only "short data" template, and instead simply
+ * reject any input buffer that is not a multiple of 8 bytes long.
+ *
+ * After all actions for each operation code are processed, another template
+ * code is in the next 5 bits.  The decompression ends once the "end" template
+ * code is detected.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <asm/unaligned.h>
+
+#include <linux/sw842.h>
+
+/* special templates */
+#define OP_REPEAT	(0x1B)
+#define OP_ZEROS	(0x1C)
+#define OP_END		(0x1E)
+
+/* sw only template - this is not in the hw design; it's used only by this
+ * software compressor and decompressor, to allow input buffers that aren't
+ * a multiple of 8.
+ */
+#define OP_SHORT_DATA	(0x1D)
+
+/* additional bits of each op param */
+#define OP_BITS		(5)
+#define REPEAT_BITS	(6)
+#define SHORT_DATA_BITS	(3)
+#define I2_BITS		(8)
+#define I4_BITS		(9)
+#define I8_BITS		(8)
+
+#define REPEAT_BITS_MAX		(0x3f)
+#define SHORT_DATA_BITS_MAX	(0x7)
+
+/* Arbitrary values used to indicate action */
+#define OP_ACTION	(0x70)
+#define OP_ACTION_INDEX	(0x10)
+#define OP_ACTION_DATA	(0x20)
+#define OP_ACTION_NOOP	(0x40)
+#define OP_AMOUNT	(0x0f)
+#define OP_AMOUNT_0	(0x00)
+#define OP_AMOUNT_2	(0x02)
+#define OP_AMOUNT_4	(0x04)
+#define OP_AMOUNT_8	(0x08)
+
+#define D2		(OP_ACTION_DATA  | OP_AMOUNT_2)
+#define D4		(OP_ACTION_DATA  | OP_AMOUNT_4)
+#define D8		(OP_ACTION_DATA  | OP_AMOUNT_8)
+#define I2		(OP_ACTION_INDEX | OP_AMOUNT_2)
+#define I4		(OP_ACTION_INDEX | OP_AMOUNT_4)
+#define I8		(OP_ACTION_INDEX | OP_AMOUNT_8)
+#define N0		(OP_ACTION_NOOP  | OP_AMOUNT_0)
+
+/* the max of the regular templates - not including the special templates */
+#define OPS_MAX		(0x1a)
+
+#endif
diff --git a/lib/842/842_compress.c b/lib/842/842_compress.c
new file mode 100644
index 000000000..7ce68948e
--- /dev/null
+++ b/lib/842/842_compress.c
@@ -0,0 +1,626 @@
+/*
+ * 842 Software Compression
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * See 842.h for details of the 842 compressed format.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define MODULE_NAME "842_compress"
+
+#include <linux/hashtable.h>
+
+#include "842.h"
+#include "842_debugfs.h"
+
+#define SW842_HASHTABLE8_BITS	(10)
+#define SW842_HASHTABLE4_BITS	(11)
+#define SW842_HASHTABLE2_BITS	(10)
+
+/* By default, we allow compressing input buffers of any length, but we must
+ * use the non-standard "short data" template so the decompressor can correctly
+ * reproduce the uncompressed data buffer at the right length.  However the
+ * hardware 842 compressor will not recognize the "short data" template, and
+ * will fail to decompress any compressed buffer containing it (I have no idea
+ * why anyone would want to use software to compress and hardware to decompress
+ * but that's beside the point).  This parameter forces the compression
+ * function to simply reject any input buffer that isn't a multiple of 8 bytes
+ * long, instead of using the "short data" template, so that all compressed
+ * buffers produced by this function will be decompressable by the 842 hardware
+ * decompressor.  Unless you have a specific need for that, leave this disabled
+ * so that any length buffer can be compressed.
+ */
+static bool sw842_strict;
+module_param_named(strict, sw842_strict, bool, 0644);
+
+static u8 comp_ops[OPS_MAX][5] = { /* params size in bits */
+	{ I8, N0, N0, N0, 0x19 }, /* 8 */
+	{ I4, I4, N0, N0, 0x18 }, /* 18 */
+	{ I4, I2, I2, N0, 0x17 }, /* 25 */
+	{ I2, I2, I4, N0, 0x13 }, /* 25 */
+	{ I2, I2, I2, I2, 0x12 }, /* 32 */
+	{ I4, I2, D2, N0, 0x16 }, /* 33 */
+	{ I4, D2, I2, N0, 0x15 }, /* 33 */
+	{ I2, D2, I4, N0, 0x0e }, /* 33 */
+	{ D2, I2, I4, N0, 0x09 }, /* 33 */
+	{ I2, I2, I2, D2, 0x11 }, /* 40 */
+	{ I2, I2, D2, I2, 0x10 }, /* 40 */
+	{ I2, D2, I2, I2, 0x0d }, /* 40 */
+	{ D2, I2, I2, I2, 0x08 }, /* 40 */
+	{ I4, D4, N0, N0, 0x14 }, /* 41 */
+	{ D4, I4, N0, N0, 0x04 }, /* 41 */
+	{ I2, I2, D4, N0, 0x0f }, /* 48 */
+	{ I2, D2, I2, D2, 0x0c }, /* 48 */
+	{ I2, D4, I2, N0, 0x0b }, /* 48 */
+	{ D2, I2, I2, D2, 0x07 }, /* 48 */
+	{ D2, I2, D2, I2, 0x06 }, /* 48 */
+	{ D4, I2, I2, N0, 0x03 }, /* 48 */
+	{ I2, D2, D4, N0, 0x0a }, /* 56 */
+	{ D2, I2, D4, N0, 0x05 }, /* 56 */
+	{ D4, I2, D2, N0, 0x02 }, /* 56 */
+	{ D4, D2, I2, N0, 0x01 }, /* 56 */
+	{ D8, N0, N0, N0, 0x00 }, /* 64 */
+};
+
+struct sw842_hlist_node8 {
+	struct hlist_node node;
+	u64 data;
+	u8 index;
+};
+
+struct sw842_hlist_node4 {
+	struct hlist_node node;
+	u32 data;
+	u16 index;
+};
+
+struct sw842_hlist_node2 {
+	struct hlist_node node;
+	u16 data;
+	u8 index;
+};
+
+#define INDEX_NOT_FOUND		(-1)
+#define INDEX_NOT_CHECKED	(-2)
+
+struct sw842_param {
+	u8 *in;
+	u8 *instart;
+	u64 ilen;
+	u8 *out;
+	u64 olen;
+	u8 bit;
+	u64 data8[1];
+	u32 data4[2];
+	u16 data2[4];
+	int index8[1];
+	int index4[2];
+	int index2[4];
+	DECLARE_HASHTABLE(htable8, SW842_HASHTABLE8_BITS);
+	DECLARE_HASHTABLE(htable4, SW842_HASHTABLE4_BITS);
+	DECLARE_HASHTABLE(htable2, SW842_HASHTABLE2_BITS);
+	struct sw842_hlist_node8 node8[1 << I8_BITS];
+	struct sw842_hlist_node4 node4[1 << I4_BITS];
+	struct sw842_hlist_node2 node2[1 << I2_BITS];
+};
+
+#define get_input_data(p, o, b)						\
+	be##b##_to_cpu(get_unaligned((__be##b *)((p)->in + (o))))
+
+#define init_hashtable_nodes(p, b)	do {			\
+	int _i;							\
+	hash_init((p)->htable##b);				\
+	for (_i = 0; _i < ARRAY_SIZE((p)->node##b); _i++) {	\
+		(p)->node##b[_i].index = _i;			\
+		(p)->node##b[_i].data = 0;			\
+		INIT_HLIST_NODE(&(p)->node##b[_i].node);	\
+	}							\
+} while (0)
+
+#define find_index(p, b, n)	({					\
+	struct sw842_hlist_node##b *_n;					\
+	p->index##b[n] = INDEX_NOT_FOUND;				\
+	hash_for_each_possible(p->htable##b, _n, node, p->data##b[n]) {	\
+		if (p->data##b[n] == _n->data) {			\
+			p->index##b[n] = _n->index;			\
+			break;						\
+		}							\
+	}								\
+	p->index##b[n] >= 0;						\
+})
+
+#define check_index(p, b, n)			\
+	((p)->index##b[n] == INDEX_NOT_CHECKED	\
+	 ? find_index(p, b, n)			\
+	 : (p)->index##b[n] >= 0)
+
+#define replace_hash(p, b, i, d)	do {				\
+	struct sw842_hlist_node##b *_n = &(p)->node##b[(i)+(d)];	\
+	hash_del(&_n->node);						\
+	_n->data = (p)->data##b[d];					\
+	pr_debug("add hash index%x %x pos %x data %lx\n", b,		\
+		 (unsigned int)_n->index,				\
+		 (unsigned int)((p)->in - (p)->instart),		\
+		 (unsigned long)_n->data);				\
+	hash_add((p)->htable##b, &_n->node, _n->data);			\
+} while (0)
+
+static u8 bmask[8] = { 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc, 0xfe };
+
+static int add_bits(struct sw842_param *p, u64 d, u8 n);
+
+static int __split_add_bits(struct sw842_param *p, u64 d, u8 n, u8 s)
+{
+	int ret;
+
+	if (n <= s)
+		return -EINVAL;
+
+	ret = add_bits(p, d >> s, n - s);
+	if (ret)
+		return ret;
+	return add_bits(p, d & GENMASK_ULL(s - 1, 0), s);
+}
+
+static int add_bits(struct sw842_param *p, u64 d, u8 n)
+{
+	int b = p->bit, bits = b + n, s = round_up(bits, 8) - bits;
+	u64 o;
+	u8 *out = p->out;
+
+	pr_debug("add %u bits %lx\n", (unsigned char)n, (unsigned long)d);
+
+	if (n > 64)
+		return -EINVAL;
+
+	/* split this up if writing to > 8 bytes (i.e. n == 64 && p->bit > 0),
+	 * or if we're at the end of the output buffer and would write past end
+	 */
+	if (bits > 64)
+		return __split_add_bits(p, d, n, 32);
+	else if (p->olen < 8 && bits > 32 && bits <= 56)
+		return __split_add_bits(p, d, n, 16);
+	else if (p->olen < 4 && bits > 16 && bits <= 24)
+		return __split_add_bits(p, d, n, 8);
+
+	if (DIV_ROUND_UP(bits, 8) > p->olen)
+		return -ENOSPC;
+
+	o = *out & bmask[b];
+	d <<= s;
+
+	if (bits <= 8)
+		*out = o | d;
+	else if (bits <= 16)
+		put_unaligned(cpu_to_be16(o << 8 | d), (__be16 *)out);
+	else if (bits <= 24)
+		put_unaligned(cpu_to_be32(o << 24 | d << 8), (__be32 *)out);
+	else if (bits <= 32)
+		put_unaligned(cpu_to_be32(o << 24 | d), (__be32 *)out);
+	else if (bits <= 40)
+		put_unaligned(cpu_to_be64(o << 56 | d << 24), (__be64 *)out);
+	else if (bits <= 48)
+		put_unaligned(cpu_to_be64(o << 56 | d << 16), (__be64 *)out);
+	else if (bits <= 56)
+		put_unaligned(cpu_to_be64(o << 56 | d << 8), (__be64 *)out);
+	else
+		put_unaligned(cpu_to_be64(o << 56 | d), (__be64 *)out);
+
+	p->bit += n;
+
+	if (p->bit > 7) {
+		p->out += p->bit / 8;
+		p->olen -= p->bit / 8;
+		p->bit %= 8;
+	}
+
+	return 0;
+}
+
+static int add_template(struct sw842_param *p, u8 c)
+{
+	int ret, i, b = 0;
+	u8 *t = comp_ops[c];
+	bool inv = false;
+
+	if (c >= OPS_MAX)
+		return -EINVAL;
+
+	pr_debug("template %x\n", t[4]);
+
+	ret = add_bits(p, t[4], OP_BITS);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 4; i++) {
+		pr_debug("op %x\n", t[i]);
+
+		switch (t[i] & OP_AMOUNT) {
+		case OP_AMOUNT_8:
+			if (b)
+				inv = true;
+			else if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index8[0], I8_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data8[0], 64);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_4:
+			if (b == 2 && t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, get_input_data(p, 2, 32), 32);
+			else if (b != 0 && b != 4)
+				inv = true;
+			else if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index4[b >> 2], I4_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data4[b >> 2], 32);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_2:
+			if (b != 0 && b != 2 && b != 4 && b != 6)
+				inv = true;
+			if (t[i] & OP_ACTION_INDEX)
+				ret = add_bits(p, p->index2[b >> 1], I2_BITS);
+			else if (t[i] & OP_ACTION_DATA)
+				ret = add_bits(p, p->data2[b >> 1], 16);
+			else
+				inv = true;
+			break;
+		case OP_AMOUNT_0:
+			inv = (b != 8) || !(t[i] & OP_ACTION_NOOP);
+			break;
+		default:
+			inv = true;
+			break;
+		}
+
+		if (ret)
+			return ret;
+
+		if (inv) {
+			pr_err("Invalid templ %x op %d : %x %x %x %x\n",
+			       c, i, t[0], t[1], t[2], t[3]);
+			return -EINVAL;
+		}
+
+		b += t[i] & OP_AMOUNT;
+	}
+
+	if (b != 8) {
+		pr_err("Invalid template %x len %x : %x %x %x %x\n",
+		       c, b, t[0], t[1], t[2], t[3]);
+		return -EINVAL;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_count[t[4]]);
+
+	return 0;
+}
+
+static int add_repeat_template(struct sw842_param *p, u8 r)
+{
+	int ret;
+
+	/* repeat param is 0-based */
+	if (!r || --r > REPEAT_BITS_MAX)
+		return -EINVAL;
+
+	ret = add_bits(p, OP_REPEAT, OP_BITS);
+	if (ret)
+		return ret;
+
+	ret = add_bits(p, r, REPEAT_BITS);
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_repeat_count);
+
+	return 0;
+}
+
+static int add_short_data_template(struct sw842_param *p, u8 b)
+{
+	int ret, i;
+
+	if (!b || b > SHORT_DATA_BITS_MAX)
+		return -EINVAL;
+
+	ret = add_bits(p, OP_SHORT_DATA, OP_BITS);
+	if (ret)
+		return ret;
+
+	ret = add_bits(p, b, SHORT_DATA_BITS);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < b; i++) {
+		ret = add_bits(p, p->in[i], 8);
+		if (ret)
+			return ret;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_short_data_count);
+
+	return 0;
+}
+
+static int add_zeros_template(struct sw842_param *p)
+{
+	int ret = add_bits(p, OP_ZEROS, OP_BITS);
+
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_zeros_count);
+
+	return 0;
+}
+
+static int add_end_template(struct sw842_param *p)
+{
+	int ret = add_bits(p, OP_END, OP_BITS);
+
+	if (ret)
+		return ret;
+
+	if (sw842_template_counts)
+		atomic_inc(&template_end_count);
+
+	return 0;
+}
+
+static bool check_template(struct sw842_param *p, u8 c)
+{
+	u8 *t = comp_ops[c];
+	int i, match, b = 0;
+
+	if (c >= OPS_MAX)
+		return false;
+
+	for (i = 0; i < 4; i++) {
+		if (t[i] & OP_ACTION_INDEX) {
+			if (t[i] & OP_AMOUNT_2)
+				match = check_index(p, 2, b >> 1);
+			else if (t[i] & OP_AMOUNT_4)
+				match = check_index(p, 4, b >> 2);
+			else if (t[i] & OP_AMOUNT_8)
+				match = check_index(p, 8, 0);
+			else
+				return false;
+			if (!match)
+				return false;
+		}
+
+		b += t[i] & OP_AMOUNT;
+	}
+
+	return true;
+}
+
+static void get_next_data(struct sw842_param *p)
+{
+	p->data8[0] = get_input_data(p, 0, 64);
+	p->data4[0] = get_input_data(p, 0, 32);
+	p->data4[1] = get_input_data(p, 4, 32);
+	p->data2[0] = get_input_data(p, 0, 16);
+	p->data2[1] = get_input_data(p, 2, 16);
+	p->data2[2] = get_input_data(p, 4, 16);
+	p->data2[3] = get_input_data(p, 6, 16);
+}
+
+/* update the hashtable entries.
+ * only call this after finding/adding the current template
+ * the dataN fields for the current 8 byte block must be already updated
+ */
+static void update_hashtables(struct sw842_param *p)
+{
+	u64 pos = p->in - p->instart;
+	u64 n8 = (pos >> 3) % (1 << I8_BITS);
+	u64 n4 = (pos >> 2) % (1 << I4_BITS);
+	u64 n2 = (pos >> 1) % (1 << I2_BITS);
+
+	replace_hash(p, 8, n8, 0);
+	replace_hash(p, 4, n4, 0);
+	replace_hash(p, 4, n4, 1);
+	replace_hash(p, 2, n2, 0);
+	replace_hash(p, 2, n2, 1);
+	replace_hash(p, 2, n2, 2);
+	replace_hash(p, 2, n2, 3);
+}
+
+/* find the next template to use, and add it
+ * the p->dataN fields must already be set for the current 8 byte block
+ */
+static int process_next(struct sw842_param *p)
+{
+	int ret, i;
+
+	p->index8[0] = INDEX_NOT_CHECKED;
+	p->index4[0] = INDEX_NOT_CHECKED;
+	p->index4[1] = INDEX_NOT_CHECKED;
+	p->index2[0] = INDEX_NOT_CHECKED;
+	p->index2[1] = INDEX_NOT_CHECKED;
+	p->index2[2] = INDEX_NOT_CHECKED;
+	p->index2[3] = INDEX_NOT_CHECKED;
+
+	/* check up to OPS_MAX - 1; last op is our fallback */
+	for (i = 0; i < OPS_MAX - 1; i++) {
+		if (check_template(p, i))
+			break;
+	}
+
+	ret = add_template(p, i);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * sw842_compress
+ *
+ * Compress the uncompressed buffer of length @ilen at @in to the output buffer
+ * @out, using no more than @olen bytes, using the 842 compression format.
+ *
+ * Returns: 0 on success, error on failure.  The @olen parameter
+ * will contain the number of output bytes written on success, or
+ * 0 on error.
+ */
+int sw842_compress(const u8 *in, unsigned int ilen,
+		   u8 *out, unsigned int *olen, void *wmem)
+{
+	struct sw842_param *p = (struct sw842_param *)wmem;
+	int ret;
+	u64 last, next, pad, total;
+	u8 repeat_count = 0;
+
+	BUILD_BUG_ON(sizeof(*p) > SW842_MEM_COMPRESS);
+
+	init_hashtable_nodes(p, 8);
+	init_hashtable_nodes(p, 4);
+	init_hashtable_nodes(p, 2);
+
+	p->in = (u8 *)in;
+	p->instart = p->in;
+	p->ilen = ilen;
+	p->out = out;
+	p->olen = *olen;
+	p->bit = 0;
+
+	total = p->olen;
+
+	*olen = 0;
+
+	/* if using strict mode, we can only compress a multiple of 8 */
+	if (sw842_strict && (ilen % 8)) {
+		pr_err("Using strict mode, can't compress len %d\n", ilen);
+		return -EINVAL;
+	}
+
+	/* let's compress at least 8 bytes, mkay? */
+	if (unlikely(ilen < 8))
+		goto skip_comp;
+
+	/* make initial 'last' different so we don't match the first time */
+	last = ~get_unaligned((u64 *)p->in);
+
+	while (p->ilen > 7) {
+		next = get_unaligned((u64 *)p->in);
+
+		/* must get the next data, as we need to update the hashtable
+		 * entries with the new data every time
+		 */
+		get_next_data(p);
+
+		/* we don't care about endianness in last or next;
+		 * we're just comparing 8 bytes to another 8 bytes,
+		 * they're both the same endianness
+		 */
+		if (next == last) {
+			/* repeat count bits are 0-based, so we stop at +1 */
+			if (++repeat_count <= REPEAT_BITS_MAX)
+				goto repeat;
+		}
+		if (repeat_count) {
+			ret = add_repeat_template(p, repeat_count);
+			repeat_count = 0;
+			if (next == last) /* reached max repeat bits */
+				goto repeat;
+		}
+
+		if (next == 0)
+			ret = add_zeros_template(p);
+		else
+			ret = process_next(p);
+
+		if (ret)
+			return ret;
+
+repeat:
+		last = next;
+		update_hashtables(p);
+		p->in += 8;
+		p->ilen -= 8;
+	}
+
+	if (repeat_count) {
+		ret = add_repeat_template(p, repeat_count);
+		if (ret)
+			return ret;
+	}
+
+skip_comp:
+	if (p->ilen > 0) {
+		ret = add_short_data_template(p, p->ilen);
+		if (ret)
+			return ret;
+
+		p->in += p->ilen;
+		p->ilen = 0;
+	}
+
+	ret = add_end_template(p);
+	if (ret)
+		return ret;
+
+	if (p->bit) {
+		p->out++;
+		p->olen--;
+		p->bit = 0;
+	}
+
+	/* pad compressed length to multiple of 8 */
+	pad = (8 - ((total - p->olen) % 8)) % 8;
+	if (pad) {
+		if (pad > p->olen) /* we were so close! */
+			return -ENOSPC;
+		memset(p->out, 0, pad);
+		p->out += pad;
+		p->olen -= pad;
+	}
+
+	if (unlikely((total - p->olen) > UINT_MAX))
+		return -ENOSPC;
+
+	*olen = total - p->olen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sw842_compress);
+
+static int __init sw842_init(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_create();
+
+	return 0;
+}
+module_init(sw842_init);
+
+static void __exit sw842_exit(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_remove();
+}
+module_exit(sw842_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Software 842 Compressor");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/lib/842/842_debugfs.h b/lib/842/842_debugfs.h
new file mode 100644
index 000000000..e7f3bffaf
--- /dev/null
+++ b/lib/842/842_debugfs.h
@@ -0,0 +1,52 @@
+
+#ifndef __842_DEBUGFS_H__
+#define __842_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+
+static bool sw842_template_counts;
+module_param_named(template_counts, sw842_template_counts, bool, 0444);
+
+static atomic_t template_count[OPS_MAX], template_repeat_count,
+	template_zeros_count, template_short_data_count, template_end_count;
+
+static struct dentry *sw842_debugfs_root;
+
+static int __init sw842_debugfs_create(void)
+{
+	umode_t m = S_IRUGO | S_IWUSR;
+	int i;
+
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	sw842_debugfs_root = debugfs_create_dir(MODULE_NAME, NULL);
+	if (IS_ERR(sw842_debugfs_root))
+		return PTR_ERR(sw842_debugfs_root);
+
+	for (i = 0; i < ARRAY_SIZE(template_count); i++) {
+		char name[32];
+
+		snprintf(name, 32, "template_%02x", i);
+		debugfs_create_atomic_t(name, m, sw842_debugfs_root,
+					&template_count[i]);
+	}
+	debugfs_create_atomic_t("template_repeat", m, sw842_debugfs_root,
+				&template_repeat_count);
+	debugfs_create_atomic_t("template_zeros", m, sw842_debugfs_root,
+				&template_zeros_count);
+	debugfs_create_atomic_t("template_short_data", m, sw842_debugfs_root,
+				&template_short_data_count);
+	debugfs_create_atomic_t("template_end", m, sw842_debugfs_root,
+				&template_end_count);
+
+	return 0;
+}
+
+static void __exit sw842_debugfs_remove(void)
+{
+	if (sw842_debugfs_root && !IS_ERR(sw842_debugfs_root))
+		debugfs_remove_recursive(sw842_debugfs_root);
+}
+
+#endif
diff --git a/lib/842/842_decompress.c b/lib/842/842_decompress.c
new file mode 100644
index 000000000..5446ff0c9
--- /dev/null
+++ b/lib/842/842_decompress.c
@@ -0,0 +1,405 @@
+/*
+ * 842 Software Decompression
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * See 842.h for details of the 842 compressed format.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define MODULE_NAME "842_decompress"
+
+#include "842.h"
+#include "842_debugfs.h"
+
+/* rolling fifo sizes */
+#define I2_FIFO_SIZE	(2 * (1 << I2_BITS))
+#define I4_FIFO_SIZE	(4 * (1 << I4_BITS))
+#define I8_FIFO_SIZE	(8 * (1 << I8_BITS))
+
+static u8 decomp_ops[OPS_MAX][4] = {
+	{ D8, N0, N0, N0 },
+	{ D4, D2, I2, N0 },
+	{ D4, I2, D2, N0 },
+	{ D4, I2, I2, N0 },
+	{ D4, I4, N0, N0 },
+	{ D2, I2, D4, N0 },
+	{ D2, I2, D2, I2 },
+	{ D2, I2, I2, D2 },
+	{ D2, I2, I2, I2 },
+	{ D2, I2, I4, N0 },
+	{ I2, D2, D4, N0 },
+	{ I2, D4, I2, N0 },
+	{ I2, D2, I2, D2 },
+	{ I2, D2, I2, I2 },
+	{ I2, D2, I4, N0 },
+	{ I2, I2, D4, N0 },
+	{ I2, I2, D2, I2 },
+	{ I2, I2, I2, D2 },
+	{ I2, I2, I2, I2 },
+	{ I2, I2, I4, N0 },
+	{ I4, D4, N0, N0 },
+	{ I4, D2, I2, N0 },
+	{ I4, I2, D2, N0 },
+	{ I4, I2, I2, N0 },
+	{ I4, I4, N0, N0 },
+	{ I8, N0, N0, N0 }
+};
+
+struct sw842_param {
+	u8 *in;
+	u8 bit;
+	u64 ilen;
+	u8 *out;
+	u8 *ostart;
+	u64 olen;
+};
+
+#define beN_to_cpu(d, s)					\
+	((s) == 2 ? be16_to_cpu(get_unaligned((__be16 *)d)) :	\
+	 (s) == 4 ? be32_to_cpu(get_unaligned((__be32 *)d)) :	\
+	 (s) == 8 ? be64_to_cpu(get_unaligned((__be64 *)d)) :	\
+	 WARN(1, "pr_debug param err invalid size %x\n", s))
+
+static int next_bits(struct sw842_param *p, u64 *d, u8 n);
+
+static int __split_next_bits(struct sw842_param *p, u64 *d, u8 n, u8 s)
+{
+	u64 tmp = 0;
+	int ret;
+
+	if (n <= s) {
+		pr_debug("split_next_bits invalid n %u s %u\n", n, s);
+		return -EINVAL;
+	}
+
+	ret = next_bits(p, &tmp, n - s);
+	if (ret)
+		return ret;
+	ret = next_bits(p, d, s);
+	if (ret)
+		return ret;
+	*d |= tmp << s;
+	return 0;
+}
+
+static int next_bits(struct sw842_param *p, u64 *d, u8 n)
+{
+	u8 *in = p->in, b = p->bit, bits = b + n;
+
+	if (n > 64) {
+		pr_debug("next_bits invalid n %u\n", n);
+		return -EINVAL;
+	}
+
+	/* split this up if reading > 8 bytes, or if we're at the end of
+	 * the input buffer and would read past the end
+	 */
+	if (bits > 64)
+		return __split_next_bits(p, d, n, 32);
+	else if (p->ilen < 8 && bits > 32 && bits <= 56)
+		return __split_next_bits(p, d, n, 16);
+	else if (p->ilen < 4 && bits > 16 && bits <= 24)
+		return __split_next_bits(p, d, n, 8);
+
+	if (DIV_ROUND_UP(bits, 8) > p->ilen)
+		return -EOVERFLOW;
+
+	if (bits <= 8)
+		*d = *in >> (8 - bits);
+	else if (bits <= 16)
+		*d = be16_to_cpu(get_unaligned((__be16 *)in)) >> (16 - bits);
+	else if (bits <= 32)
+		*d = be32_to_cpu(get_unaligned((__be32 *)in)) >> (32 - bits);
+	else
+		*d = be64_to_cpu(get_unaligned((__be64 *)in)) >> (64 - bits);
+
+	*d &= GENMASK_ULL(n - 1, 0);
+
+	p->bit += n;
+
+	if (p->bit > 7) {
+		p->in += p->bit / 8;
+		p->ilen -= p->bit / 8;
+		p->bit %= 8;
+	}
+
+	return 0;
+}
+
+static int do_data(struct sw842_param *p, u8 n)
+{
+	u64 v;
+	int ret;
+
+	if (n > p->olen)
+		return -ENOSPC;
+
+	ret = next_bits(p, &v, n * 8);
+	if (ret)
+		return ret;
+
+	switch (n) {
+	case 2:
+		put_unaligned(cpu_to_be16((u16)v), (__be16 *)p->out);
+		break;
+	case 4:
+		put_unaligned(cpu_to_be32((u32)v), (__be32 *)p->out);
+		break;
+	case 8:
+		put_unaligned(cpu_to_be64((u64)v), (__be64 *)p->out);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	p->out += n;
+	p->olen -= n;
+
+	return 0;
+}
+
+static int __do_index(struct sw842_param *p, u8 size, u8 bits, u64 fsize)
+{
+	u64 index, offset, total = round_down(p->out - p->ostart, 8);
+	int ret;
+
+	ret = next_bits(p, &index, bits);
+	if (ret)
+		return ret;
+
+	offset = index * size;
+
+	/* a ring buffer of fsize is used; correct the offset */
+	if (total > fsize) {
+		/* this is where the current fifo is */
+		u64 section = round_down(total, fsize);
+		/* the current pos in the fifo */
+		u64 pos = total - section;
+
+		/* if the offset is past/at the pos, we need to
+		 * go back to the last fifo section
+		 */
+		if (offset >= pos)
+			section -= fsize;
+
+		offset += section;
+	}
+
+	if (offset + size > total) {
+		pr_debug("index%x %lx points past end %lx\n", size,
+			 (unsigned long)offset, (unsigned long)total);
+		return -EINVAL;
+	}
+
+	pr_debug("index%x to %lx off %lx adjoff %lx tot %lx data %lx\n",
+		 size, (unsigned long)index, (unsigned long)(index * size),
+		 (unsigned long)offset, (unsigned long)total,
+		 (unsigned long)beN_to_cpu(&p->ostart[offset], size));
+
+	memcpy(p->out, &p->ostart[offset], size);
+	p->out += size;
+	p->olen -= size;
+
+	return 0;
+}
+
+static int do_index(struct sw842_param *p, u8 n)
+{
+	switch (n) {
+	case 2:
+		return __do_index(p, 2, I2_BITS, I2_FIFO_SIZE);
+	case 4:
+		return __do_index(p, 4, I4_BITS, I4_FIFO_SIZE);
+	case 8:
+		return __do_index(p, 8, I8_BITS, I8_FIFO_SIZE);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int do_op(struct sw842_param *p, u8 o)
+{
+	int i, ret = 0;
+
+	if (o >= OPS_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < 4; i++) {
+		u8 op = decomp_ops[o][i];
+
+		pr_debug("op is %x\n", op);
+
+		switch (op & OP_ACTION) {
+		case OP_ACTION_DATA:
+			ret = do_data(p, op & OP_AMOUNT);
+			break;
+		case OP_ACTION_INDEX:
+			ret = do_index(p, op & OP_AMOUNT);
+			break;
+		case OP_ACTION_NOOP:
+			break;
+		default:
+			pr_err("Interal error, invalid op %x\n", op);
+			return -EINVAL;
+		}
+
+		if (ret)
+			return ret;
+	}
+
+	if (sw842_template_counts)
+		atomic_inc(&template_count[o]);
+
+	return 0;
+}
+
+/**
+ * sw842_decompress
+ *
+ * Decompress the 842-compressed buffer of length @ilen at @in
+ * to the output buffer @out, using no more than @olen bytes.
+ *
+ * The compressed buffer must be only a single 842-compressed buffer,
+ * with the standard format described in the comments in 842.h
+ * Processing will stop when the 842 "END" template is detected,
+ * not the end of the buffer.
+ *
+ * Returns: 0 on success, error on failure.  The @olen parameter
+ * will contain the number of output bytes written on success, or
+ * 0 on error.
+ */
+int sw842_decompress(const u8 *in, unsigned int ilen,
+		     u8 *out, unsigned int *olen)
+{
+	struct sw842_param p;
+	int ret;
+	u64 op, rep, tmp, bytes, total;
+
+	p.in = (u8 *)in;
+	p.bit = 0;
+	p.ilen = ilen;
+	p.out = out;
+	p.ostart = out;
+	p.olen = *olen;
+
+	total = p.olen;
+
+	*olen = 0;
+
+	do {
+		ret = next_bits(&p, &op, OP_BITS);
+		if (ret)
+			return ret;
+
+		pr_debug("template is %lx\n", (unsigned long)op);
+
+		switch (op) {
+		case OP_REPEAT:
+			ret = next_bits(&p, &rep, REPEAT_BITS);
+			if (ret)
+				return ret;
+
+			if (p.out == out) /* no previous bytes */
+				return -EINVAL;
+
+			/* copy rep + 1 */
+			rep++;
+
+			if (rep * 8 > p.olen)
+				return -ENOSPC;
+
+			while (rep-- > 0) {
+				memcpy(p.out, p.out - 8, 8);
+				p.out += 8;
+				p.olen -= 8;
+			}
+
+			if (sw842_template_counts)
+				atomic_inc(&template_repeat_count);
+
+			break;
+		case OP_ZEROS:
+			if (8 > p.olen)
+				return -ENOSPC;
+
+			memset(p.out, 0, 8);
+			p.out += 8;
+			p.olen -= 8;
+
+			if (sw842_template_counts)
+				atomic_inc(&template_zeros_count);
+
+			break;
+		case OP_SHORT_DATA:
+			ret = next_bits(&p, &bytes, SHORT_DATA_BITS);
+			if (ret)
+				return ret;
+
+			if (!bytes || bytes > SHORT_DATA_BITS_MAX)
+				return -EINVAL;
+
+			while (bytes-- > 0) {
+				ret = next_bits(&p, &tmp, 8);
+				if (ret)
+					return ret;
+				*p.out = (u8)tmp;
+				p.out++;
+				p.olen--;
+			}
+
+			if (sw842_template_counts)
+				atomic_inc(&template_short_data_count);
+
+			break;
+		case OP_END:
+			if (sw842_template_counts)
+				atomic_inc(&template_end_count);
+
+			break;
+		default: /* use template */
+			ret = do_op(&p, op);
+			if (ret)
+				return ret;
+			break;
+		}
+	} while (op != OP_END);
+
+	if (unlikely((total - p.olen) > UINT_MAX))
+		return -ENOSPC;
+
+	*olen = total - p.olen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sw842_decompress);
+
+static int __init sw842_init(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_create();
+
+	return 0;
+}
+module_init(sw842_init);
+
+static void __exit sw842_exit(void)
+{
+	if (sw842_template_counts)
+		sw842_debugfs_remove();
+}
+module_exit(sw842_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Software 842 Decompressor");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/lib/842/Makefile b/lib/842/Makefile
new file mode 100644
index 000000000..5d24c0baf
--- /dev/null
+++ b/lib/842/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_842_COMPRESS) += 842_compress.o
+obj-$(CONFIG_842_DECOMPRESS) += 842_decompress.o
diff --git a/lib/Kconfig b/lib/Kconfig
index 601965a94..3a2ef67db 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -212,6 +212,12 @@ config RANDOM32_SELFTEST
 #
 # compression support is select'ed if needed
 #
+config 842_COMPRESS
+	tristate
+
+config 842_DECOMPRESS
+	tristate
+
 config ZLIB_INFLATE
 	tristate
 
@@ -522,4 +528,7 @@ source "lib/fonts/Kconfig"
 config ARCH_HAS_SG_CHAIN
 	def_bool n
 
+config ARCH_HAS_PMEM_API
+	bool
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 3bddcda18..e2894b23e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -841,9 +841,14 @@ config SCHED_DEBUG
 	  that can help debug the scheduler. The runtime overhead of this
 	  option is minimal.
 
+config SCHED_INFO
+	bool
+	default n
+
 config SCHEDSTATS
 	bool "Collect scheduler statistics"
 	depends on DEBUG_KERNEL && PROC_FS
+	select SCHED_INFO
 	help
 	  If you say Y here, additional code will be inserted into the
 	  scheduler and related routines to collect statistics about
@@ -1230,9 +1235,10 @@ config TORTURE_TEST
 
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
-	depends on DEBUG_KERNEL && !SCHED_BFS
+	depends on DEBUG_KERNEL
 	select TORTURE_TEST
 	select SRCU
+	select TASKS_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -1261,12 +1267,38 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_TORTURE_TEST_SLOW_PREINIT
+	bool "Slow down RCU grace-period pre-initialization to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period pre-initialization (the
+	  propagation of CPU-hotplug changes up the rcu_node combining
+	  tree) for a few jiffies between initializing each pair of
+	  consecutive rcu_node structures.  This helps to expose races
+	  involving grace-period pre-initialization, in other words, it
+	  makes your kernel less stable.  It can also greatly increase
+	  grace-period latency, especially on systems with large numbers
+	  of CPUs.  This is useful when torture-testing RCU, but in
+	  almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+	int "How much to slow down RCU grace-period pre-initialization"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_PREINIT
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure pre-initialization step.
+
 config RCU_TORTURE_TEST_SLOW_INIT
 	bool "Slow down RCU grace-period initialization to expose races"
 	depends on RCU_TORTURE_TEST
 	help
-	  This option makes grace-period initialization block for a
-	  few jiffies between initializing each pair of consecutive
+	  This option delays grace-period initialization for a few
+	  jiffies between initializing each pair of consecutive
 	  rcu_node structures.	This helps to expose races involving
 	  grace-period initialization, in other words, it makes your
 	  kernel less stable.  It can also greatly increase grace-period
@@ -1286,6 +1318,30 @@ config RCU_TORTURE_TEST_SLOW_INIT_DELAY
 	  This option specifies the number of jiffies to wait between
 	  each rcu_node structure initialization.
 
+config RCU_TORTURE_TEST_SLOW_CLEANUP
+	bool "Slow down RCU grace-period cleanup to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period cleanup for a few jiffies
+	  between cleaning up each pair of consecutive rcu_node
+	  structures.  This helps to expose races involving grace-period
+	  cleanup, in other words, it makes your kernel less stable.
+	  It can also greatly increase grace-period latency, especially
+	  on systems with large numbers of CPUs.  This is useful when
+	  torture-testing RCU, but in almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+	int "How much to slow down RCU grace-period cleanup"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_CLEANUP
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure cleanup operation.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON
@@ -1322,6 +1378,17 @@ config RCU_TRACE
 	  Say Y here if you want to enable RCU tracing
 	  Say N if you are unsure.
 
+config RCU_EQS_DEBUG
+	bool "Use this when adding any sort of NO_HZ support to your arch"
+	depends on DEBUG_KERNEL
+	help
+	  This option provides consistency checks in RCU's handling of
+	  NO_HZ.  These checks have proven quite helpful in detecting
+	  bugs in arch-specific NO_HZ code.
+
+	  Say N here if you need ultimate kernel/user switch latencies
+	  Say Y if you are unsure
+
 endmenu # "RCU Debugging"
 
 config DEBUG_BLOCK_EXT_DEVT
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 777eda7d1..39f24d672 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -18,10 +18,6 @@ config KASAN
 	  For better error detection enable CONFIG_STACKTRACE,
 	  and add slub_debug=U to boot cmdline.
 
-config KASAN_SHADOW_OFFSET
-	hex
-	default 0xdffffc0000000000 if X86_64
-
 choice
 	prompt "Instrumentation type"
 	depends on KASAN
diff --git a/lib/Makefile b/lib/Makefile
index 3d30b6650..89cb00bec 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,9 @@ CFLAGS_kobject.o += -DDEBUG
 CFLAGS_kobject_uevent.o += -DDEBUG
 endif
 
+obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
+CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
+
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
@@ -78,6 +81,8 @@ obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
+obj-$(CONFIG_842_COMPRESS) += 842/
+obj-$(CONFIG_842_DECOMPRESS) += 842/
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 40162f87e..a578a0189 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -462,19 +462,20 @@ EXPORT_SYMBOL(bitmap_parse_user);
  * Output format is a comma-separated list of decimal numbers and
  * ranges if list is specified or hex digits grouped into comma-separated
  * sets of 8 digits/set. Returns the number of characters written to buf.
+ *
+ * It is assumed that @buf is a pointer into a PAGE_SIZE area and that
+ * sufficient storage remains at @buf to accommodate the
+ * bitmap_print_to_pagebuf() output.
  */
 int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
 			    int nmaskbits)
 {
-	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf - 2;
+	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
 	int n = 0;
 
-	if (len > 1) {
-		n = list ? scnprintf(buf, len, "%*pbl", nmaskbits, maskp) :
-			   scnprintf(buf, len, "%*pb", nmaskbits, maskp);
-		buf[n++] = '\n';
-		buf[n] = '\0';
-	}
+	if (len > 1)
+		n = list ? scnprintf(buf, len, "%*pbl\n", nmaskbits, maskp) :
+			   scnprintf(buf, len, "%*pb\n", nmaskbits, maskp);
 	return n;
 }
 EXPORT_SYMBOL(bitmap_print_to_pagebuf);
diff --git a/lib/bug.c b/lib/bug.c
index 0c3bd9552..cff145f03 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -66,7 +66,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr)
 	struct module *mod;
 	const struct bug_entry *bug = NULL;
 
-	rcu_read_lock();
+	rcu_read_lock_sched();
 	list_for_each_entry_rcu(mod, &module_bug_list, bug_list) {
 		unsigned i;
 
@@ -77,7 +77,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr)
 	}
 	bug = NULL;
 out:
-	rcu_read_unlock();
+	rcu_read_unlock_sched();
 
 	return bug;
 }
@@ -88,6 +88,8 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
 	char *secstrings;
 	unsigned int i;
 
+	lockdep_assert_held(&module_mutex);
+
 	mod->bug_table = NULL;
 	mod->num_bugs = 0;
 
@@ -113,6 +115,7 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
 
 void module_bug_cleanup(struct module *mod)
 {
+	lockdep_assert_held(&module_mutex);
 	list_del_rcu(&mod->bug_list);
 }
 
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4f134d890..f610b2a10 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -191,7 +191,7 @@ int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
 	/* Update distances based on topology */
 	for_each_cpu(cpu, update_mask) {
 		if (cpu_rmap_copy_neigh(rmap, cpu,
-					topology_thread_cpumask(cpu), 1))
+					topology_sibling_cpumask(cpu), 1))
 			continue;
 		if (cpu_rmap_copy_neigh(rmap, cpu,
 					topology_core_cpumask(cpu), 2))
diff --git a/lib/crc-itu-t.c b/lib/crc-itu-t.c
index a63472b82..b3219d0ab 100644
--- a/lib/crc-itu-t.c
+++ b/lib/crc-itu-t.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 #include <linux/crc-itu-t.h>
 
-/** CRC table for the CRC ITU-T V.41 0x0x1021 (x^16 + x^12 + x^15 + 1) */
+/** CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^15 + 1) */
 const u16 crc_itu_t_table[256] = {
 	0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
 	0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index dfe6ec17c..1ad33e555 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -19,7 +19,7 @@
 static struct crypto_shash *crct10dif_tfm;
 static struct static_key crct10dif_fallback __read_mostly;
 
-__u16 crc_t10dif(const unsigned char *buffer, size_t len)
+__u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 {
 	struct {
 		struct shash_desc shash;
@@ -28,17 +28,23 @@ __u16 crc_t10dif(const unsigned char *buffer, size_t len)
 	int err;
 
 	if (static_key_false(&crct10dif_fallback))
-		return crc_t10dif_generic(0, buffer, len);
+		return crc_t10dif_generic(crc, buffer, len);
 
 	desc.shash.tfm = crct10dif_tfm;
 	desc.shash.flags = 0;
-	*(__u16 *)desc.ctx = 0;
+	*(__u16 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, buffer, len);
 	BUG_ON(err);
 
 	return *(__u16 *)desc.ctx;
 }
+EXPORT_SYMBOL(crc_t10dif_update);
+
+__u16 crc_t10dif(const unsigned char *buffer, size_t len)
+{
+	return crc_t10dif_update(0, buffer, len);
+}
 EXPORT_SYMBOL(crc_t10dif);
 
 static int __init crc_t10dif_mod_init(void)
diff --git a/lib/debug_info.c b/lib/debug_info.c
new file mode 100644
index 000000000..2edbe2751
--- /dev/null
+++ b/lib/debug_info.c
@@ -0,0 +1,27 @@
+/*
+ * This file exists solely to ensure debug information for some core
+ * data structures is included in the final image even for
+ * CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However,
+ * adding appropriate #includes is fine.
+ */
+#include <stdarg.h>
+
+#include <linux/cred.h>
+#include <linux/crypto.h>
+#include <linux/dcache.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/fscache-cache.h>
+#include <linux/io.h>
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
diff --git a/lib/decompress.c b/lib/decompress.c
index 528ff932d..62696dff5 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -59,8 +59,11 @@ decompress_fn __init decompress_method(const unsigned char *inbuf, long len,
 {
 	const struct compress_format *cf;
 
-	if (len < 2)
+	if (len < 2) {
+		if (name)
+			*name = NULL;
 		return NULL;	/* Need at least this much... */
+	}
 
 	pr_debug("Compressed data magic: %#.2x %#.2x\n", inbuf[0], inbuf[1]);
 
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index d8f3d3150..e491e02ef 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -887,7 +887,7 @@ static int ddebug_dyndbg_param_cb(char *param, char *val,
 
 /* handle both dyndbg and $module.dyndbg params at boot */
 static int ddebug_dyndbg_boot_param_cb(char *param, char *val,
-				const char *unused)
+				const char *unused, void *arg)
 {
 	vpr_info("%s=\"%s\"\n", param, val);
 	return ddebug_dyndbg_param_cb(param, val, NULL, 0);
@@ -1028,7 +1028,7 @@ static int __init dynamic_debug_init(void)
 	 */
 	cmdline = kstrdup(saved_command_line, GFP_KERNEL);
 	parse_args("dyndbg params", cmdline, NULL,
-		   0, 0, 0, &ddebug_dyndbg_boot_param_cb);
+		   0, 0, 0, NULL, &ddebug_dyndbg_boot_param_cb);
 	kfree(cmdline);
 	return 0;
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index d214866ee..daf0afb6d 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -602,12 +602,12 @@ struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order,
 EXPORT_SYMBOL(devm_gen_pool_create);
 
 /**
- * dev_get_gen_pool - Obtain the gen_pool (if any) for a device
+ * gen_pool_get - Obtain the gen_pool (if any) for a device
  * @dev: device to retrieve the gen_pool from
  *
  * Returns the gen_pool for the device if one is present, or NULL.
  */
-struct gen_pool *dev_get_gen_pool(struct device *dev)
+struct gen_pool *gen_pool_get(struct device *dev)
 {
 	struct gen_pool **p = devres_find(dev, devm_gen_pool_release, NULL,
 					NULL);
@@ -616,11 +616,11 @@ struct gen_pool *dev_get_gen_pool(struct device *dev)
 		return NULL;
 	return *p;
 }
-EXPORT_SYMBOL_GPL(dev_get_gen_pool);
+EXPORT_SYMBOL_GPL(gen_pool_get);
 
 #ifdef CONFIG_OF
 /**
- * of_get_named_gen_pool - find a pool by phandle property
+ * of_gen_pool_get - find a pool by phandle property
  * @np: device node
  * @propname: property name containing phandle(s)
  * @index: index into the phandle array
@@ -629,7 +629,7 @@ EXPORT_SYMBOL_GPL(dev_get_gen_pool);
  * address of the device tree node pointed at by the phandle property,
  * or NULL if not found.
  */
-struct gen_pool *of_get_named_gen_pool(struct device_node *np,
+struct gen_pool *of_gen_pool_get(struct device_node *np,
 	const char *propname, int index)
 {
 	struct platform_device *pdev;
@@ -642,7 +642,7 @@ struct gen_pool *of_get_named_gen_pool(struct device_node *np,
 	of_node_put(np_pool);
 	if (!pdev)
 		return NULL;
-	return dev_get_gen_pool(&pdev->dev);
+	return gen_pool_get(&pdev->dev);
 }
-EXPORT_SYMBOL_GPL(of_get_named_gen_pool);
+EXPORT_SYMBOL_GPL(of_gen_pool_get);
 #endif /* CONFIG_OF */
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 7ea096998..8d74c20d8 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -11,6 +11,7 @@
 #include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <asm/unaligned.h>
 
 const char hex_asc[] = "0123456789abcdef";
 EXPORT_SYMBOL(hex_asc);
@@ -139,7 +140,7 @@ int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize,
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%16.16llx", j ? " " : "",
-				       (unsigned long long)*(ptr8 + j));
+				       get_unaligned(ptr8 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
@@ -150,7 +151,7 @@ int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize,
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%8.8x", j ? " " : "",
-				       *(ptr4 + j));
+				       get_unaligned(ptr4 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
@@ -161,7 +162,7 @@ int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize,
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%4.4x", j ? " " : "",
-				       *(ptr2 + j));
+				       get_unaligned(ptr2 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index df30632f0..ff19f66d3 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -119,7 +119,7 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	unsigned long align_mask = 0;
 
 	if (align_order > 0)
-		align_mask = 0xffffffffffffffffl >> (64 - align_order);
+		align_mask = ~0ul >> (BITS_PER_LONG - align_order);
 
 	/* Sanity check */
 	if (unlikely(npages == 0)) {
diff --git a/lib/kobject.c b/lib/kobject.c
index 3b841b97f..3e3a5c3cb 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -257,23 +257,20 @@ static int kobject_add_internal(struct kobject *kobj)
 int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
 				  va_list vargs)
 {
-	const char *old_name = kobj->name;
 	char *s;
 
 	if (kobj->name && !fmt)
 		return 0;
 
-	kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs);
-	if (!kobj->name) {
-		kobj->name = old_name;
+	s = kvasprintf(GFP_KERNEL, fmt, vargs);
+	if (!s)
 		return -ENOMEM;
-	}
 
 	/* ewww... some of these buggers have '/' in the name ... */
-	while ((s = strchr(kobj->name, '/')))
-		s[0] = '!';
+	strreplace(s, '/', '!');
+	kfree(kobj->name);
+	kobj->name = s;
 
-	kfree(old_name);
 	return 0;
 }
 
@@ -340,8 +337,9 @@ error:
 }
 EXPORT_SYMBOL(kobject_init);
 
-static int kobject_add_varg(struct kobject *kobj, struct kobject *parent,
-			    const char *fmt, va_list vargs)
+static __printf(3, 0) int kobject_add_varg(struct kobject *kobj,
+					   struct kobject *parent,
+					   const char *fmt, va_list vargs)
 {
 	int retval;
 
@@ -548,6 +546,7 @@ out:
 	kfree(devpath);
 	return error;
 }
+EXPORT_SYMBOL_GPL(kobject_move);
 
 /**
  * kobject_del - unlink kobject from hierarchy.
diff --git a/lib/list_sort.c b/lib/list_sort.c
index b29015102..3fe401067 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -289,5 +289,5 @@ exit:
 	kfree(elts);
 	return err;
 }
-module_init(list_sort_test);
+late_initcall(list_sort_test);
 #endif /* CONFIG_TEST_LIST_SORT */
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 26cc6029b..6d940c72b 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -140,8 +140,12 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			/* Error: request to write beyond destination buffer */
 			if (cpy > oend)
 				goto _output_error;
+#if LZ4_ARCH64
+			if ((ref + COPYLENGTH) > oend)
+#else
 			if ((ref + COPYLENGTH) > oend ||
 					(op + COPYLENGTH) > oend)
+#endif
 				goto _output_error;
 			LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
 			while (op < cpy)
@@ -266,7 +270,13 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 		if (cpy > oend - COPYLENGTH) {
 			if (cpy > oend)
 				goto _output_error; /* write outside of buf */
-
+#if LZ4_ARCH64
+			if ((ref + COPYLENGTH) > oend)
+#else
+			if ((ref + COPYLENGTH) > oend ||
+					(op + COPYLENGTH) > oend)
+#endif
+				goto _output_error;
 			LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
 			while (op < cpy)
 				*op++ = *ref++;
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 4cc644273..bc0a1da8a 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -128,28 +128,36 @@ leave:
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
-/****************
- * Return an allocated buffer with the MPI (msb first).
- * NBYTES receives the length of this buffer. Caller must free the
- * return string (This function does return a 0 byte buffer with NBYTES
- * set to zero if the value of A is zero. If sign is not NULL, it will
- * be set to the sign of the A.
+/**
+ * mpi_read_buffer() - read MPI to a bufer provided by user (msb first)
+ *
+ * @a:		a multi precision integer
+ * @buf:	bufer to which the output will be written to. Needs to be at
+ *		leaset mpi_get_size(a) long.
+ * @buf_len:	size of the buf.
+ * @nbytes:	receives the actual length of the data written.
+ * @sign:	if not NULL, it will be set to the sign of a.
+ *
+ * Return:	0 on success or error code in case of error
  */
-void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
+int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
+		    int *sign)
 {
-	uint8_t *p, *buffer;
+	uint8_t *p;
 	mpi_limb_t alimb;
+	unsigned int n = mpi_get_size(a);
 	int i;
-	unsigned int n;
+
+	if (buf_len < n || !buf)
+		return -EINVAL;
 
 	if (sign)
 		*sign = a->sign;
-	*nbytes = n = a->nlimbs * BYTES_PER_MPI_LIMB;
-	if (!n)
-		n++;		/* avoid zero length allocation */
-	p = buffer = kmalloc(n, GFP_KERNEL);
-	if (!p)
-		return NULL;
+
+	if (nbytes)
+		*nbytes = n;
+
+	p = buf;
 
 	for (i = a->nlimbs - 1; i >= 0; i--) {
 		alimb = a->d[i];
@@ -171,15 +179,56 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 #error please implement for this limb size.
 #endif
 	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_read_buffer);
+
+/*
+ * mpi_get_buffer() - Returns an allocated buffer with the MPI (msb first).
+ * Caller must free the return string.
+ * This function does return a 0 byte buffer with nbytes set to zero if the
+ * value of A is zero.
+ *
+ * @a:		a multi precision integer.
+ * @nbytes:	receives the length of this buffer.
+ * @sign:	if not NULL, it will be set to the sign of the a.
+ *
+ * Return:	Pointer to MPI buffer or NULL on error
+ */
+void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
+{
+	uint8_t *buf, *p;
+	unsigned int n;
+	int ret;
+
+	if (!nbytes)
+		return NULL;
+
+	n = mpi_get_size(a);
+
+	if (!n)
+		n++;
+
+	buf = kmalloc(n, GFP_KERNEL);
+
+	if (!buf)
+		return NULL;
+
+	ret = mpi_read_buffer(a, buf, n, nbytes, sign);
+
+	if (ret) {
+		kfree(buf);
+		return NULL;
+	}
 
 	/* this is sub-optimal but we need to do the shift operation
 	 * because the caller has to free the returned buffer */
-	for (p = buffer; !*p && *nbytes; p++, --*nbytes)
+	for (p = buf; !*p && *nbytes; p++, --*nbytes)
 		;
-	if (p != buffer)
-		memmove(buffer, p, *nbytes);
+	if (p != buf)
+		memmove(buf, p, *nbytes);
 
-	return buffer;
+	return buf;
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
 
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index bf076d281..314f4dfa6 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -69,7 +69,7 @@ void mpi_free_limb_space(mpi_ptr_t a)
 	if (!a)
 		return;
 
-	kfree(a);
+	kzfree(a);
 }
 
 void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs)
@@ -95,7 +95,7 @@ int mpi_resize(MPI a, unsigned nlimbs)
 		if (!p)
 			return -ENOMEM;
 		memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));
-		kfree(a->d);
+		kzfree(a->d);
 		a->d = p;
 	} else {
 		a->d = kzalloc(nlimbs * sizeof(mpi_limb_t), GFP_KERNEL);
@@ -112,7 +112,7 @@ void mpi_free(MPI a)
 		return;
 
 	if (a->flags & 4)
-		kfree(a->d);
+		kzfree(a->d);
 	else
 		mpi_free_limb_space(a->d);
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3d2aa27b8..f9ebe1c82 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -33,7 +33,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
-#include <linux/preempt_mask.h>		/* in_interrupt() */
+#include <linux/preempt.h>		/* in_interrupt() */
 
 
 /*
@@ -65,7 +65,8 @@ static struct kmem_cache *radix_tree_node_cachep;
  */
 struct radix_tree_preload {
 	int nr;
-	struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE];
+	/* nodes->private_data points to next preallocated node */
+	struct radix_tree_node *nodes;
 };
 static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
@@ -197,8 +198,9 @@ radix_tree_node_alloc(struct radix_tree_root *root)
 		 */
 		rtp = this_cpu_ptr(&radix_tree_preloads);
 		if (rtp->nr) {
-			ret = rtp->nodes[rtp->nr - 1];
-			rtp->nodes[rtp->nr - 1] = NULL;
+			ret = rtp->nodes;
+			rtp->nodes = ret->private_data;
+			ret->private_data = NULL;
 			rtp->nr--;
 		}
 		/*
@@ -257,17 +259,20 @@ static int __radix_tree_preload(gfp_t gfp_mask)
 
 	preempt_disable();
 	rtp = this_cpu_ptr(&radix_tree_preloads);
-	while (rtp->nr < ARRAY_SIZE(rtp->nodes)) {
+	while (rtp->nr < RADIX_TREE_PRELOAD_SIZE) {
 		preempt_enable();
 		node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 		if (node == NULL)
 			goto out;
 		preempt_disable();
 		rtp = this_cpu_ptr(&radix_tree_preloads);
-		if (rtp->nr < ARRAY_SIZE(rtp->nodes))
-			rtp->nodes[rtp->nr++] = node;
-		else
+		if (rtp->nr < RADIX_TREE_PRELOAD_SIZE) {
+			node->private_data = rtp->nodes;
+			rtp->nodes = node;
+			rtp->nr++;
+		} else {
 			kmem_cache_free(radix_tree_node_cachep, node);
+		}
 	}
 	ret = 0;
 out:
@@ -1463,15 +1468,16 @@ static int radix_tree_callback(struct notifier_block *nfb,
 {
        int cpu = (long)hcpu;
        struct radix_tree_preload *rtp;
+       struct radix_tree_node *node;
 
        /* Free per-cpu pool of perloaded nodes */
        if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
                rtp = &per_cpu(radix_tree_preloads, cpu);
                while (rtp->nr) {
-                       kmem_cache_free(radix_tree_node_cachep,
-                                       rtp->nodes[rtp->nr-1]);
-                       rtp->nodes[rtp->nr-1] = NULL;
-                       rtp->nr--;
+			node = rtp->nodes;
+			rtp->nodes = node->private_data;
+			kmem_cache_free(radix_tree_node_cachep, node);
+			rtp->nr--;
                }
        }
        return NOTIFY_OK;
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index c7dab0645..3b10a48fa 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -15,7 +15,7 @@ quiet_cmd_unroll = UNROLL  $@
                    < $< > $@ || ( rm -f $@ && exit 1 )
 
 ifeq ($(CONFIG_ALTIVEC),y)
-altivec_flags := -maltivec -mabi=altivec
+altivec_flags := -maltivec $(call cc-option,-mabi=altivec)
 endif
 
 # The GCC option -ffreestanding is required in order to compile code containing
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index b7595484a..8fe9d9662 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -23,7 +23,7 @@
 
 #ifdef __KERNEL__ /* Real code */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #else /* Dummy code for user space testing */
 
diff --git a/lib/rbtree.c b/lib/rbtree.c
index c16c81a3d..1356454e3 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -44,6 +44,30 @@
  *  parentheses and have some accompanying text comment.
  */
 
+/*
+ * Notes on lockless lookups:
+ *
+ * All stores to the tree structure (rb_left and rb_right) must be done using
+ * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the
+ * tree structure as seen in program order.
+ *
+ * These two requirements will allow lockless iteration of the tree -- not
+ * correct iteration mind you, tree rotations are not atomic so a lookup might
+ * miss entire subtrees.
+ *
+ * But they do guarantee that any such traversal will only see valid elements
+ * and that it will indeed complete -- does not get stuck in a loop.
+ *
+ * It also guarantees that if the lookup returns an element it is the 'correct'
+ * one. But not returning an element does _NOT_ mean it's not present.
+ *
+ * NOTE:
+ *
+ * Stores to __rb_parent_color are not important for simple lookups so those
+ * are left undone as of now. Nor did I check for loops involving parent
+ * pointers.
+ */
+
 static inline void rb_set_black(struct rb_node *rb)
 {
 	rb->__rb_parent_color |= RB_BLACK;
@@ -129,8 +153,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 				 * This still leaves us in violation of 4), the
 				 * continuation into Case 3 will fix that.
 				 */
-				parent->rb_right = tmp = node->rb_left;
-				node->rb_left = parent;
+				tmp = node->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp);
+				WRITE_ONCE(node->rb_left, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -149,8 +174,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			 *     /                 \
 			 *    n                   U
 			 */
-			gparent->rb_left = tmp;  /* == parent->rb_right */
-			parent->rb_right = gparent;
+			WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */
+			WRITE_ONCE(parent->rb_right, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -171,8 +196,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			tmp = parent->rb_left;
 			if (node == tmp) {
 				/* Case 2 - right rotate at parent */
-				parent->rb_left = tmp = node->rb_right;
-				node->rb_right = parent;
+				tmp = node->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp);
+				WRITE_ONCE(node->rb_right, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -183,8 +209,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			}
 
 			/* Case 3 - left rotate at gparent */
-			gparent->rb_right = tmp;  /* == parent->rb_left */
-			parent->rb_left = gparent;
+			WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */
+			WRITE_ONCE(parent->rb_left, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -224,8 +250,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				 *      / \         / \
 				 *     Sl  Sr      N   Sl
 				 */
-				parent->rb_right = tmp1 = sibling->rb_left;
-				sibling->rb_left = parent;
+				tmp1 = sibling->rb_left;
+				WRITE_ONCE(parent->rb_right, tmp1);
+				WRITE_ONCE(sibling->rb_left, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -275,9 +302,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				 *                       \
 				 *                        Sr
 				 */
-				sibling->rb_left = tmp1 = tmp2->rb_right;
-				tmp2->rb_right = sibling;
-				parent->rb_right = tmp2;
+				tmp1 = tmp2->rb_right;
+				WRITE_ONCE(sibling->rb_left, tmp1);
+				WRITE_ONCE(tmp2->rb_right, sibling);
+				WRITE_ONCE(parent->rb_right, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -297,8 +325,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 			 *        / \         / \
 			 *      (sl) sr      N  (sl)
 			 */
-			parent->rb_right = tmp2 = sibling->rb_left;
-			sibling->rb_left = parent;
+			tmp2 = sibling->rb_left;
+			WRITE_ONCE(parent->rb_right, tmp2);
+			WRITE_ONCE(sibling->rb_left, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
@@ -310,8 +339,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 			sibling = parent->rb_left;
 			if (rb_is_red(sibling)) {
 				/* Case 1 - right rotate at parent */
-				parent->rb_left = tmp1 = sibling->rb_right;
-				sibling->rb_right = parent;
+				tmp1 = sibling->rb_right;
+				WRITE_ONCE(parent->rb_left, tmp1);
+				WRITE_ONCE(sibling->rb_right, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -336,9 +366,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 					break;
 				}
 				/* Case 3 - right rotate at sibling */
-				sibling->rb_right = tmp1 = tmp2->rb_left;
-				tmp2->rb_left = sibling;
-				parent->rb_left = tmp2;
+				tmp1 = tmp2->rb_left;
+				WRITE_ONCE(sibling->rb_right, tmp1);
+				WRITE_ONCE(tmp2->rb_left, sibling);
+				WRITE_ONCE(parent->rb_left, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -347,8 +378,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				sibling = tmp2;
 			}
 			/* Case 4 - left rotate at parent + color flips */
-			parent->rb_left = tmp2 = sibling->rb_right;
-			sibling->rb_right = parent;
+			tmp2 = sibling->rb_right;
+			WRITE_ONCE(parent->rb_left, tmp2);
+			WRITE_ONCE(sibling->rb_right, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 8609378e6..cc0c69710 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -585,7 +585,6 @@ void *rhashtable_walk_next(struct rhashtable_iter *iter)
 	struct bucket_table *tbl = iter->walker->tbl;
 	struct rhashtable *ht = iter->ht;
 	struct rhash_head *p = iter->p;
-	void *obj = NULL;
 
 	if (p) {
 		p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot);
@@ -605,13 +604,14 @@ next:
 		if (!rht_is_a_nulls(p)) {
 			iter->skip++;
 			iter->p = p;
-			obj = rht_obj(ht, p);
-			goto out;
+			return rht_obj(ht, p);
 		}
 
 		iter->skip = 0;
 	}
 
+	iter->p = NULL;
+
 	/* Ensure we see any new tables. */
 	smp_rmb();
 
@@ -622,11 +622,7 @@ next:
 		return ERR_PTR(-EAGAIN);
 	}
 
-	iter->p = NULL;
-
-out:
-
-	return obj;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_next);
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index c9f2e8c6c..d105a9f56 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -56,6 +56,38 @@ int sg_nents(struct scatterlist *sg)
 }
 EXPORT_SYMBOL(sg_nents);
 
+/**
+ * sg_nents_for_len - return total count of entries in scatterlist
+ *                    needed to satisfy the supplied length
+ * @sg:		The scatterlist
+ * @len:	The total required length
+ *
+ * Description:
+ * Determines the number of entries in sg that are required to meet
+ * the supplied length, taking into acount chaining as well
+ *
+ * Returns:
+ *   the number of sg entries needed, negative error on failure
+ *
+ **/
+int sg_nents_for_len(struct scatterlist *sg, u64 len)
+{
+	int nents;
+	u64 total;
+
+	if (!len)
+		return 0;
+
+	for (nents = 0, total = 0; sg; sg = sg_next(sg)) {
+		nents++;
+		total += sg->length;
+		if (total >= len)
+			return nents;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(sg_nents_for_len);
 
 /**
  * sg_last - return the last scatterlist entry in a list
@@ -618,9 +650,8 @@ EXPORT_SYMBOL(sg_miter_stop);
  * Returns the number of copied bytes.
  *
  **/
-static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
-			     void *buf, size_t buflen, off_t skip,
-			     bool to_buffer)
+size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
+		      size_t buflen, off_t skip, bool to_buffer)
 {
 	unsigned int offset = 0;
 	struct sg_mapping_iter miter;
@@ -657,6 +688,7 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
 	local_irq_restore(flags);
 	return offset;
 }
+EXPORT_SYMBOL(sg_copy_buffer);
 
 /**
  * sg_copy_from_buffer - Copy from a linear buffer to an SG list
@@ -669,9 +701,9 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
  *
  **/
 size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			   void *buf, size_t buflen)
+			   const void *buf, size_t buflen)
 {
-	return sg_copy_buffer(sgl, nents, buf, buflen, 0, false);
+	return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false);
 }
 EXPORT_SYMBOL(sg_copy_from_buffer);
 
@@ -697,16 +729,16 @@ EXPORT_SYMBOL(sg_copy_to_buffer);
  * @sgl:		 The SG list
  * @nents:		 Number of SG entries
  * @buf:		 Where to copy from
- * @skip:		 Number of bytes to skip before copying
  * @buflen:		 The number of bytes to copy
+ * @skip:		 Number of bytes to skip before copying
  *
  * Returns the number of copied bytes.
  *
  **/
 size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
-			    void *buf, size_t buflen, off_t skip)
+			    const void *buf, size_t buflen, off_t skip)
 {
-	return sg_copy_buffer(sgl, nents, buf, buflen, skip, false);
+	return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false);
 }
 EXPORT_SYMBOL(sg_pcopy_from_buffer);
 
@@ -715,8 +747,8 @@ EXPORT_SYMBOL(sg_pcopy_from_buffer);
  * @sgl:		 The SG list
  * @nents:		 Number of SG entries
  * @buf:		 Where to copy to
- * @skip:		 Number of bytes to skip before copying
  * @buflen:		 The number of bytes to copy
+ * @skip:		 Number of bytes to skip before copying
  *
  * Returns the number of copied bytes.
  *
diff --git a/lib/sort.c b/lib/sort.c
index 43c9fe73a..fc20df42a 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -8,6 +8,12 @@
 #include <linux/export.h>
 #include <linux/sort.h>
 
+static int alignment_ok(const void *base, int align)
+{
+	return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+		((unsigned long)base & (align - 1)) == 0;
+}
+
 static void u32_swap(void *a, void *b, int size)
 {
 	u32 t = *(u32 *)a;
@@ -15,6 +21,13 @@ static void u32_swap(void *a, void *b, int size)
 	*(u32 *)b = t;
 }
 
+static void u64_swap(void *a, void *b, int size)
+{
+	u64 t = *(u64 *)a;
+	*(u64 *)a = *(u64 *)b;
+	*(u64 *)b = t;
+}
+
 static void generic_swap(void *a, void *b, int size)
 {
 	char t;
@@ -50,8 +63,14 @@ void sort(void *base, size_t num, size_t size,
 	/* pre-scale counters for performance */
 	int i = (num/2 - 1) * size, n = num * size, c, r;
 
-	if (!swap_func)
-		swap_func = (size == 4 ? u32_swap : generic_swap);
+	if (!swap_func) {
+		if (size == 4 && alignment_ok(base, 4))
+			swap_func = u32_swap;
+		else if (size == 8 && alignment_ok(base, 8))
+			swap_func = u64_swap;
+		else
+			swap_func = generic_swap;
+	}
 
 	/* heapify */
 	for ( ; i >= 0; i -= size) {
diff --git a/lib/string.c b/lib/string.c
index bb3d4b699..13d1e84dd 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -849,3 +849,20 @@ void *memchr_inv(const void *start, int c, size_t bytes)
 	return check_bytes8(start, value, bytes % 8);
 }
 EXPORT_SYMBOL(memchr_inv);
+
+/**
+ * strreplace - Replace all occurrences of character in string.
+ * @s: The string to operate on.
+ * @old: The character being replaced.
+ * @new: The character @old is replaced with.
+ *
+ * Returns pointer to the nul byte at the end of @s.
+ */
+char *strreplace(char *s, char old, char new)
+{
+	for (; *s; ++s)
+		if (*s == old)
+			*s = new;
+	return s;
+}
+EXPORT_SYMBOL(strreplace);
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index fe9a32591..3a5f2b366 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -85,7 +85,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
  * @str: The string to measure.
  * @count: Maximum count (including NUL character)
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
@@ -121,7 +122,8 @@ EXPORT_SYMBOL(strnlen_user);
  * strlen_user: - Get the size of a user string INCLUDING final NUL.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 3c365ab6c..76f29ecba 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -29,10 +29,10 @@
 #include <linux/ctype.h>
 #include <linux/highmem.h>
 #include <linux/gfp.h>
+#include <linux/scatterlist.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/scatterlist.h>
 
 #include <linux/init.h>
 #include <linux/bootmem.h>
@@ -656,7 +656,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 */
 		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (paddr == SWIOTLB_MAP_ERROR)
-			return NULL;
+			goto err_warn;
 
 		ret = phys_to_virt(paddr);
 		dev_addr = phys_to_dma(hwdev, paddr);
@@ -670,7 +670,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 			swiotlb_tbl_unmap_single(hwdev, paddr,
 						 size, DMA_TO_DEVICE);
-			return NULL;
+			goto err_warn;
 		}
 	}
 
@@ -678,6 +678,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	memset(ret, 0, size);
 
 	return ret;
+
+err_warn:
+	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+		dev_name(hwdev), size);
+	dump_stack();
+
+	return NULL;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
diff --git a/lib/test-hexdump.c b/lib/test-hexdump.c
index c227cc43e..5241df36e 100644
--- a/lib/test-hexdump.c
+++ b/lib/test-hexdump.c
@@ -25,19 +25,19 @@ static const char * const test_data_1_le[] __initconst = {
 	"4c", "d1", "19", "99", "43", "b1", "af", "0c",
 };
 
-static const char *test_data_2_le[] __initdata = {
+static const char * const test_data_2_le[] __initconst = {
 	"32be", "7bdb", "180a", "b293",
 	"ba70", "24c4", "837d", "9b34",
 	"9ca6", "ad31", "0f9c", "e9ac",
 	"d14c", "9919", "b143", "0caf",
 };
 
-static const char *test_data_4_le[] __initdata = {
+static const char * const test_data_4_le[] __initconst = {
 	"7bdb32be", "b293180a", "24c4ba70", "9b34837d",
 	"ad319ca6", "e9ac0f9c", "9919d14c", "0cafb143",
 };
 
-static const char *test_data_8_le[] __initdata = {
+static const char * const test_data_8_le[] __initconst = {
 	"b293180a7bdb32be", "9b34837d24c4ba70",
 	"e9ac0f9cad319ca6", "0cafb1439919d14c",
 };
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 80d78c51f..7f58c735d 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -21,6 +21,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
+#include <linux/random.h>
 
 /* General test specific settings */
 #define MAX_SUBTESTS	3
@@ -67,6 +68,10 @@ struct bpf_test {
 	union {
 		struct sock_filter insns[MAX_INSNS];
 		struct bpf_insn insns_int[MAX_INSNS];
+		struct {
+			void *insns;
+			unsigned int len;
+		} ptr;
 	} u;
 	__u8 aux;
 	__u8 data[MAX_DATA];
@@ -74,8 +79,282 @@ struct bpf_test {
 		int data_size;
 		__u32 result;
 	} test[MAX_SUBTESTS];
+	int (*fill_helper)(struct bpf_test *self);
 };
 
+/* Large test cases need separate allocation and fill handler. */
+
+static int bpf_fill_maxinsns1(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct sock_filter *insn;
+	__u32 k = ~0;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	for (i = 0; i < len; i++, k--)
+		insn[i] = __BPF_STMT(BPF_RET | BPF_K, k);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns2(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; i++)
+		insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns3(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct sock_filter *insn;
+	struct rnd_state rnd;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	prandom_seed_state(&rnd, 3141592653589793238ULL);
+
+	for (i = 0; i < len - 1; i++) {
+		__u32 k = prandom_u32_state(&rnd);
+
+		insn[i] = __BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, k);
+	}
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns4(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS + 1;
+	struct sock_filter *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	for (i = 0; i < len; i++)
+		insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns5(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;
+
+	insn[0] = __BPF_JUMP(BPF_JMP | BPF_JA, len - 2, 0, 0);
+
+	for (i = 1; i < len - 1; i++)
+		insn[i] = __BPF_STMT(BPF_RET | BPF_K, 0xfefefefe);
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xabababab);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns6(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++)
+		insn[i] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF +
+				     SKF_AD_VLAN_TAG_PRESENT);
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns7(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 - 4; i++)
+		insn[i] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF +
+				     SKF_AD_CPU);
+
+	insn[len - 4] = __BPF_STMT(BPF_MISC | BPF_TAX, 0);
+	insn[len - 3] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF +
+				   SKF_AD_CPU);
+	insn[len - 2] = __BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0);
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns8(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct sock_filter *insn;
+	int i, jmp_off = len - 3;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[0] = __BPF_STMT(BPF_LD | BPF_IMM, 0xffffffff);
+
+	for (i = 1; i < len - 1; i++)
+		insn[i] = __BPF_JUMP(BPF_JMP | BPF_JGT, 0xffffffff, jmp_off--, 0);
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_A, 0);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns9(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[0] = BPF_JMP_IMM(BPF_JA, 0, 0, len - 2);
+	insn[1] = BPF_ALU32_IMM(BPF_MOV, R0, 0xcbababab);
+	insn[2] = BPF_EXIT_INSN();
+
+	for (i = 3; i < len - 2; i++)
+		insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xfefefefe);
+
+	insn[len - 2] = BPF_EXIT_INSN();
+	insn[len - 1] = BPF_JMP_IMM(BPF_JA, 0, 0, -(len - 1));
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns10(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS, hlen = len - 2;
+	struct bpf_insn *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	for (i = 0; i < hlen / 2; i++)
+		insn[i] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen - 2 - 2 * i);
+	for (i = hlen - 1; i > hlen / 2; i--)
+		insn[i] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen - 1 - 2 * i);
+
+	insn[hlen / 2] = BPF_JMP_IMM(BPF_JA, 0, 0, hlen / 2 - 1);
+	insn[hlen]     = BPF_ALU32_IMM(BPF_MOV, R0, 0xabababac);
+	insn[hlen + 1] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int __bpf_fill_ja(struct bpf_test *self, unsigned int len,
+			 unsigned int plen)
+{
+	struct sock_filter *insn;
+	unsigned int rlen;
+	int i, j;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	rlen = (len % plen) - 1;
+
+	for (i = 0; i + plen < len; i += plen)
+		for (j = 0; j < plen; j++)
+			insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA,
+						 plen - 1 - j, 0, 0);
+	for (j = 0; j < rlen; j++)
+		insn[i + j] = __BPF_JUMP(BPF_JMP | BPF_JA, rlen - 1 - j,
+					 0, 0);
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xababcbac);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+static int bpf_fill_maxinsns11(struct bpf_test *self)
+{
+	/* Hits 70 passes on x86_64, so cannot get JITed there. */
+	return __bpf_fill_ja(self, BPF_MAXINSNS, 68);
+}
+
+static int bpf_fill_ja(struct bpf_test *self)
+{
+	/* Hits exactly 11 passes on x86_64 JIT. */
+	return __bpf_fill_ja(self, 12, 9);
+}
+
 static struct bpf_test tests[] = {
 	{
 		"TAX",
@@ -1755,7 +2034,8 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 			BPF_JMP_IMM(BPF_JEQ, R3, 0x1234, 1),
 			BPF_EXIT_INSN(),
-			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R0, 0x1ffffffffLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32), /* R0 = 1 */
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
@@ -1805,6 +2085,2313 @@ static struct bpf_test tests[] = {
 		  0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6},
 		{ { 38, 256 } }
 	},
+	/* BPF_ALU | BPF_MOV | BPF_X */
+	{
+		"ALU_MOV_X: dst = 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_MOV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_MOV_X: dst = 4294967295",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U),
+			BPF_ALU32_REG(BPF_MOV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	{
+		"ALU64_MOV_X: dst = 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_MOV_X: dst = 4294967295",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	/* BPF_ALU | BPF_MOV | BPF_K */
+	{
+		"ALU_MOV_K: dst = 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_MOV_K: dst = 4294967295",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 4294967295U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	{
+		"ALU_MOV_K: 0x0000ffffffff0000 = 0x00000000ffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x00000000ffffffffLL),
+			BPF_ALU32_IMM(BPF_MOV, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_MOV_K: dst = 2",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_MOV_K: dst = 2147483647",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2147483647 } },
+	},
+	{
+		"ALU64_OR_K: dst = 0x0",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x0),
+			BPF_ALU64_IMM(BPF_MOV, R2, 0x0),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_MOV_K: dst = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_MOV, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_ADD | BPF_X */
+	{
+		"ALU_ADD_X: 1 + 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_ADD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_ADD_X: 1 + 4294967294 = 4294967295",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U),
+			BPF_ALU32_REG(BPF_ADD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	{
+		"ALU64_ADD_X: 1 + 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_ADD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_ADD_X: 1 + 4294967294 = 4294967295",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U),
+			BPF_ALU64_REG(BPF_ADD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	/* BPF_ALU | BPF_ADD | BPF_K */
+	{
+		"ALU_ADD_K: 1 + 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_ADD, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_ADD_K: 3 + 0 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_ADD, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_ADD_K: 1 + 4294967294 = 4294967295",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_ADD, R0, 4294967294U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4294967295U } },
+	},
+	{
+		"ALU_ADD_K: 0 + (-1) = 0x00000000ffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0),
+			BPF_LD_IMM64(R3, 0x00000000ffffffff),
+			BPF_ALU32_IMM(BPF_ADD, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_ADD_K: 1 + 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_ADD, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_ADD_K: 3 + 0 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_ADD, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_ADD_K: 1 + 2147483646 = 2147483647",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_ADD, R0, 2147483646),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2147483647 } },
+	},
+	{
+		"ALU64_ADD_K: 2147483646 + -2147483647 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483646),
+			BPF_ALU64_IMM(BPF_ADD, R0, -2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	{
+		"ALU64_ADD_K: 1 + 0 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x1),
+			BPF_LD_IMM64(R3, 0x1),
+			BPF_ALU64_IMM(BPF_ADD, R2, 0x0),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_ADD_K: 0 + (-1) = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_ADD, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_SUB | BPF_X */
+	{
+		"ALU_SUB_X: 3 - 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU32_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_SUB_X: 4294967295 - 4294967294 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U),
+			BPF_ALU32_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_SUB_X: 3 - 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_SUB_X: 4294967295 - 4294967294 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967294U),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_ALU | BPF_SUB | BPF_K */
+	{
+		"ALU_SUB_K: 3 - 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_SUB, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_SUB_K: 3 - 0 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_SUB, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_SUB_K: 4294967295 - 4294967294 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_SUB, R0, 4294967294U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_SUB_K: 3 - 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_SUB, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_SUB_K: 3 - 0 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_SUB, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_SUB_K: 4294967294 - 4294967295 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967294U),
+			BPF_ALU64_IMM(BPF_SUB, R0, 4294967295U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	{
+		"ALU64_ADD_K: 2147483646 - 2147483647 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483646),
+			BPF_ALU64_IMM(BPF_SUB, R0, 2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	/* BPF_ALU | BPF_MUL | BPF_X */
+	{
+		"ALU_MUL_X: 2 * 3 = 6",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 3),
+			BPF_ALU32_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 6 } },
+	},
+	{
+		"ALU_MUL_X: 2 * 0x7FFFFFF8 = 0xFFFFFFF0",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0x7FFFFFF8),
+			BPF_ALU32_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xFFFFFFF0 } },
+	},
+	{
+		"ALU_MUL_X: -1 * -1 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -1),
+			BPF_ALU32_IMM(BPF_MOV, R1, -1),
+			BPF_ALU32_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_MUL_X: 2 * 3 = 6",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 3),
+			BPF_ALU64_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 6 } },
+	},
+	{
+		"ALU64_MUL_X: 1 * 2147483647 = 2147483647",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2147483647),
+			BPF_ALU64_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2147483647 } },
+	},
+	/* BPF_ALU | BPF_MUL | BPF_K */
+	{
+		"ALU_MUL_K: 2 * 3 = 6",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MUL, R0, 3),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 6 } },
+	},
+	{
+		"ALU_MUL_K: 3 * 1 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MUL, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_MUL_K: 2 * 0x7FFFFFF8 = 0xFFFFFFF0",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MUL, R0, 0x7FFFFFF8),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xFFFFFFF0 } },
+	},
+	{
+		"ALU_MUL_K: 1 * (-1) = 0x00000000ffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x1),
+			BPF_LD_IMM64(R3, 0x00000000ffffffff),
+			BPF_ALU32_IMM(BPF_MUL, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_MUL_K: 2 * 3 = 6",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU64_IMM(BPF_MUL, R0, 3),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 6 } },
+	},
+	{
+		"ALU64_MUL_K: 3 * 1 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_MUL, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_MUL_K: 1 * 2147483647 = 2147483647",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_MUL, R0, 2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2147483647 } },
+	},
+	{
+		"ALU64_MUL_K: 1 * -2147483647 = -2147483647",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_MUL, R0, -2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -2147483647 } },
+	},
+	{
+		"ALU64_MUL_K: 1 * (-1) = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x1),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_MUL, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_DIV | BPF_X */
+	{
+		"ALU_DIV_X: 6 / 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 6),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_DIV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_DIV_X: 4294967295 / 4294967295 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967295U),
+			BPF_ALU32_REG(BPF_DIV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_DIV_X: 6 / 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 6),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_DIV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_DIV_X: 2147483647 / 2147483647 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483647),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2147483647),
+			BPF_ALU64_REG(BPF_DIV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_DIV_X: 0xffffffffffffffff / (-1) = 0x0000000000000001",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffffffLL),
+			BPF_LD_IMM64(R4, 0xffffffffffffffffLL),
+			BPF_LD_IMM64(R3, 0x0000000000000001LL),
+			BPF_ALU64_REG(BPF_DIV, R2, R4),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_DIV | BPF_K */
+	{
+		"ALU_DIV_K: 6 / 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 6),
+			BPF_ALU32_IMM(BPF_DIV, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_DIV_K: 3 / 1 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_DIV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_DIV_K: 4294967295 / 4294967295 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_DIV, R0, 4294967295U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU_DIV_K: 0xffffffffffffffff / (-1) = 0x1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffffffLL),
+			BPF_LD_IMM64(R3, 0x1UL),
+			BPF_ALU32_IMM(BPF_DIV, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_DIV_K: 6 / 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 6),
+			BPF_ALU64_IMM(BPF_DIV, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_DIV_K: 3 / 1 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_DIV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_DIV_K: 2147483647 / 2147483647 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483647),
+			BPF_ALU64_IMM(BPF_DIV, R0, 2147483647),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_DIV_K: 0xffffffffffffffff / (-1) = 0x0000000000000001",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffffffLL),
+			BPF_LD_IMM64(R3, 0x0000000000000001LL),
+			BPF_ALU64_IMM(BPF_DIV, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_MOD | BPF_X */
+	{
+		"ALU_MOD_X: 3 % 2 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_MOD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU_MOD_X: 4294967295 % 4294967293 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4294967293U),
+			BPF_ALU32_REG(BPF_MOD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_MOD_X: 3 % 2 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_MOD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_MOD_X: 2147483647 % 2147483645 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483647),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2147483645),
+			BPF_ALU64_REG(BPF_MOD, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	/* BPF_ALU | BPF_MOD | BPF_K */
+	{
+		"ALU_MOD_K: 3 % 2 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOD, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU_MOD_K: 3 % 1 = 0",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOD, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+	},
+	{
+		"ALU_MOD_K: 4294967295 % 4294967293 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 4294967295U),
+			BPF_ALU32_IMM(BPF_MOD, R0, 4294967293U),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_MOD_K: 3 % 2 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_MOD, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_MOD_K: 3 % 1 = 0",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_MOD, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+	},
+	{
+		"ALU64_MOD_K: 2147483647 % 2147483645 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2147483647),
+			BPF_ALU64_IMM(BPF_MOD, R0, 2147483645),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	/* BPF_ALU | BPF_AND | BPF_X */
+	{
+		"ALU_AND_X: 3 & 2 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_AND, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_AND_X: 0xffffffff & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xffffffff),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU32_REG(BPF_AND, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_AND_X: 3 & 2 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_AND, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_AND_X: 0xffffffff & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xffffffff),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU64_REG(BPF_AND, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	/* BPF_ALU | BPF_AND | BPF_K */
+	{
+		"ALU_AND_K: 3 & 2 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU32_IMM(BPF_AND, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_AND_K: 0xffffffff & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xffffffff),
+			BPF_ALU32_IMM(BPF_AND, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_AND_K: 3 & 2 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_AND, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_AND_K: 0xffffffff & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xffffffff),
+			BPF_ALU64_IMM(BPF_AND, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_AND_K: 0x0000ffffffff0000 & 0x0 = 0x0000ffff00000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x0000000000000000LL),
+			BPF_ALU64_IMM(BPF_AND, R2, 0x0),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_AND_K: 0x0000ffffffff0000 & -1 = 0x0000ffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x0000ffffffff0000LL),
+			BPF_ALU64_IMM(BPF_AND, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_AND_K: 0xffffffffffffffff & -1 = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffffffLL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_AND, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_OR | BPF_X */
+	{
+		"ALU_OR_X: 1 | 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG(BPF_OR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_OR_X: 0x0 | 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU32_REG(BPF_OR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_OR_X: 1 | 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG(BPF_OR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_OR_X: 0 | 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU64_REG(BPF_OR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	/* BPF_ALU | BPF_OR | BPF_K */
+	{
+		"ALU_OR_K: 1 | 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_OR, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_OR_K: 0 & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_ALU32_IMM(BPF_OR, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_OR_K: 1 | 2 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_OR, R0, 2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_OR_K: 0 & 0xffffffff = 0xffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_ALU64_IMM(BPF_OR, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ALU64_OR_K: 0x0000ffffffff0000 | 0x0 = 0x0000ffff00000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x0000ffffffff0000LL),
+			BPF_ALU64_IMM(BPF_OR, R2, 0x0),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_OR_K: 0x0000ffffffff0000 | -1 = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_OR, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_OR_K: 0x000000000000000 | -1 = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000000000000000LL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_OR, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_XOR | BPF_X */
+	{
+		"ALU_XOR_X: 5 ^ 6 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 5),
+			BPF_ALU32_IMM(BPF_MOV, R1, 6),
+			BPF_ALU32_REG(BPF_XOR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_XOR_X: 0x1 ^ 0xffffffff = 0xfffffffe",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU32_REG(BPF_XOR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } },
+	},
+	{
+		"ALU64_XOR_X: 5 ^ 6 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 5),
+			BPF_ALU32_IMM(BPF_MOV, R1, 6),
+			BPF_ALU64_REG(BPF_XOR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_XOR_X: 1 ^ 0xffffffff = 0xfffffffe",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_ALU64_REG(BPF_XOR, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } },
+	},
+	/* BPF_ALU | BPF_XOR | BPF_K */
+	{
+		"ALU_XOR_K: 5 ^ 6 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 5),
+			BPF_ALU32_IMM(BPF_XOR, R0, 6),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU_XOR_K: 1 ^ 0xffffffff = 0xfffffffe",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_XOR, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } },
+	},
+	{
+		"ALU64_XOR_K: 5 ^ 6 = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 5),
+			BPF_ALU64_IMM(BPF_XOR, R0, 6),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_XOR_K: 1 & 0xffffffff = 0xfffffffe",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_XOR, R0, 0xffffffff),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } },
+	},
+	{
+		"ALU64_XOR_K: 0x0000ffffffff0000 ^ 0x0 = 0x0000ffffffff0000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0x0000ffffffff0000LL),
+			BPF_ALU64_IMM(BPF_XOR, R2, 0x0),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_XOR_K: 0x0000ffffffff0000 ^ -1 = 0xffff00000000ffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
+			BPF_LD_IMM64(R3, 0xffff00000000ffffLL),
+			BPF_ALU64_IMM(BPF_XOR, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_XOR_K: 0x000000000000000 ^ -1 = 0xffffffffffffffff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x0000000000000000LL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ALU64_IMM(BPF_XOR, R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* BPF_ALU | BPF_LSH | BPF_X */
+	{
+		"ALU_LSH_X: 1 << 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU32_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_LSH_X: 1 << 31 = 0x80000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 31),
+			BPF_ALU32_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x80000000 } },
+	},
+	{
+		"ALU64_LSH_X: 1 << 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_LSH_X: 1 << 31 = 0x80000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R1, 31),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x80000000 } },
+	},
+	/* BPF_ALU | BPF_LSH | BPF_K */
+	{
+		"ALU_LSH_K: 1 << 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_LSH, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU_LSH_K: 1 << 31 = 0x80000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU32_IMM(BPF_LSH, R0, 31),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x80000000 } },
+	},
+	{
+		"ALU64_LSH_K: 1 << 1 = 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_LSH, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2 } },
+	},
+	{
+		"ALU64_LSH_K: 1 << 31 = 0x80000000",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 1),
+			BPF_ALU64_IMM(BPF_LSH, R0, 31),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x80000000 } },
+	},
+	/* BPF_ALU | BPF_RSH | BPF_X */
+	{
+		"ALU_RSH_X: 2 >> 1 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU32_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU_RSH_X: 0x80000000 >> 31 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x80000000),
+			BPF_ALU32_IMM(BPF_MOV, R1, 31),
+			BPF_ALU32_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_RSH_X: 2 >> 1 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_RSH_X: 0x80000000 >> 31 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x80000000),
+			BPF_ALU32_IMM(BPF_MOV, R1, 31),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_ALU | BPF_RSH | BPF_K */
+	{
+		"ALU_RSH_K: 2 >> 1 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU32_IMM(BPF_RSH, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU_RSH_K: 0x80000000 >> 31 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x80000000),
+			BPF_ALU32_IMM(BPF_RSH, R0, 31),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_RSH_K: 2 >> 1 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 2),
+			BPF_ALU64_IMM(BPF_RSH, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"ALU64_RSH_K: 0x80000000 >> 31 = 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x80000000),
+			BPF_ALU64_IMM(BPF_RSH, R0, 31),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_ALU | BPF_ARSH | BPF_X */
+	{
+		"ALU_ARSH_X: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xff00ff0000000000LL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 40),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffff00ff } },
+	},
+	/* BPF_ALU | BPF_ARSH | BPF_K */
+	{
+		"ALU_ARSH_K: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xff00ff0000000000LL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffff00ff } },
+	},
+	/* BPF_ALU | BPF_NEG */
+	{
+		"ALU_NEG: -(3) = -3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 3),
+			BPF_ALU32_IMM(BPF_NEG, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	{
+		"ALU_NEG: -(-3) = 3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -3),
+			BPF_ALU32_IMM(BPF_NEG, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	{
+		"ALU64_NEG: -(3) = -3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 3),
+			BPF_ALU64_IMM(BPF_NEG, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	{
+		"ALU64_NEG: -(-3) = 3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -3),
+			BPF_ALU64_IMM(BPF_NEG, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 3 } },
+	},
+	/* BPF_ALU | BPF_END | BPF_FROM_BE */
+	{
+		"ALU_END_FROM_BE 16: 0x0123456789abcdef -> 0xcdef",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_BE, R0, 16),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0,  cpu_to_be16(0xcdef) } },
+	},
+	{
+		"ALU_END_FROM_BE 32: 0x0123456789abcdef -> 0x89abcdef",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_BE, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, cpu_to_be32(0x89abcdef) } },
+	},
+	{
+		"ALU_END_FROM_BE 64: 0x0123456789abcdef -> 0x89abcdef",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_BE, R0, 64),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, (u32) cpu_to_be64(0x0123456789abcdefLL) } },
+	},
+	/* BPF_ALU | BPF_END | BPF_FROM_LE */
+	{
+		"ALU_END_FROM_LE 16: 0x0123456789abcdef -> 0xefcd",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_LE, R0, 16),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, cpu_to_le16(0xcdef) } },
+	},
+	{
+		"ALU_END_FROM_LE 32: 0x0123456789abcdef -> 0xefcdab89",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_LE, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, cpu_to_le32(0x89abcdef) } },
+	},
+	{
+		"ALU_END_FROM_LE 64: 0x0123456789abcdef -> 0x67452301",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ENDIAN(BPF_FROM_LE, R0, 64),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, (u32) cpu_to_le64(0x0123456789abcdefLL) } },
+	},
+	/* BPF_ST(X) | BPF_MEM | BPF_B/H/W/DW */
+	{
+		"ST_MEM_B: Store/Load byte: max negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_B, R10, -40, 0xff),
+			BPF_LDX_MEM(BPF_B, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xff } },
+	},
+	{
+		"ST_MEM_B: Store/Load byte: max positive",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_H, R10, -40, 0x7f),
+			BPF_LDX_MEM(BPF_H, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x7f } },
+	},
+	{
+		"STX_MEM_B: Store/Load byte: max negative",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0xffLL),
+			BPF_STX_MEM(BPF_B, R10, R1, -40),
+			BPF_LDX_MEM(BPF_B, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xff } },
+	},
+	{
+		"ST_MEM_H: Store/Load half word: max negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_H, R10, -40, 0xffff),
+			BPF_LDX_MEM(BPF_H, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffff } },
+	},
+	{
+		"ST_MEM_H: Store/Load half word: max positive",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_H, R10, -40, 0x7fff),
+			BPF_LDX_MEM(BPF_H, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x7fff } },
+	},
+	{
+		"STX_MEM_H: Store/Load half word: max negative",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0xffffLL),
+			BPF_STX_MEM(BPF_H, R10, R1, -40),
+			BPF_LDX_MEM(BPF_H, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffff } },
+	},
+	{
+		"ST_MEM_W: Store/Load word: max negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_W, R10, -40, 0xffffffff),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ST_MEM_W: Store/Load word: max positive",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x7fffffff),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x7fffffff } },
+	},
+	{
+		"STX_MEM_W: Store/Load word: max negative",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0xffffffffLL),
+			BPF_STX_MEM(BPF_W, R10, R1, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ST_MEM_DW: Store/Load double word: max negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0xffffffff),
+			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	{
+		"ST_MEM_DW: Store/Load double word: max negative 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffff00000000ffffLL),
+			BPF_LD_IMM64(R3, 0xffffffffffffffffLL),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0xffffffff),
+			BPF_LDX_MEM(BPF_DW, R2, R10, -40),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ST_MEM_DW: Store/Load double word: max positive",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0x7fffffff),
+			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x7fffffff } },
+	},
+	{
+		"STX_MEM_DW: Store/Load double word: max negative",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+			BPF_STX_MEM(BPF_W, R10, R1, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } },
+	},
+	/* BPF_STX | BPF_XADD | BPF_W/DW */
+	{
+		"STX_XADD_W: Test: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_W, R10, R0, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x22 } },
+	},
+	{
+		"STX_XADD_DW: Test: 0x12 + 0x10 = 0x22",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
+			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
+			BPF_STX_XADD(BPF_DW, R10, R0, -40),
+			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x22 } },
+	},
+	/* BPF_JMP | BPF_EXIT */
+	{
+		"JMP_EXIT",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x4711),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x4712),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x4711 } },
+	},
+	/* BPF_JMP | BPF_JA */
+	{
+		"JMP_JA: Unconditional jump: if (true) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSGT | BPF_K */
+	{
+		"JMP_JSGT_K: Signed jump: if (-1 > -2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+			BPF_JMP_IMM(BPF_JSGT, R1, -2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSGT_K: Signed jump: if (-1 > -1) return 0",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+			BPF_JMP_IMM(BPF_JSGT, R1, -1, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSGE | BPF_K */
+	{
+		"JMP_JSGE_K: Signed jump: if (-1 >= -2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+			BPF_JMP_IMM(BPF_JSGE, R1, -2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSGE_K: Signed jump: if (-1 >= -1) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+			BPF_JMP_IMM(BPF_JSGE, R1, -1, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JGT | BPF_K */
+	{
+		"JMP_JGT_K: if (3 > 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JGT, R1, 2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JGE | BPF_K */
+	{
+		"JMP_JGE_K: if (3 >= 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JGE, R1, 2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JGT | BPF_K jump backwards */
+	{
+		"JMP_JGT_K: if (3 > 2) return 1 (jump backwards)",
+		.u.insns_int = {
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2), /* goto start */
+			BPF_ALU32_IMM(BPF_MOV, R0, 1), /* out: */
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0), /* start: */
+			BPF_LD_IMM64(R1, 3), /* note: this takes 2 insns */
+			BPF_JMP_IMM(BPF_JGT, R1, 2, -6), /* goto out */
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JGE_K: if (3 >= 3) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JGE, R1, 3, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JNE | BPF_K */
+	{
+		"JMP_JNE_K: if (3 != 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JNE, R1, 2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JEQ | BPF_K */
+	{
+		"JMP_JEQ_K: if (3 == 3) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JEQ, R1, 3, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSET | BPF_K */
+	{
+		"JMP_JSET_K: if (0x3 & 0x2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JNE, R1, 2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSET_K: if (0x3 & 0xffffffff) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_JMP_IMM(BPF_JNE, R1, 0xffffffff, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSGT | BPF_X */
+	{
+		"JMP_JSGT_X: Signed jump: if (-1 > -2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, -1),
+			BPF_LD_IMM64(R2, -2),
+			BPF_JMP_REG(BPF_JSGT, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSGT_X: Signed jump: if (-1 > -1) return 0",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, -1),
+			BPF_LD_IMM64(R2, -1),
+			BPF_JMP_REG(BPF_JSGT, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSGE | BPF_X */
+	{
+		"JMP_JSGE_X: Signed jump: if (-1 >= -2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, -1),
+			BPF_LD_IMM64(R2, -2),
+			BPF_JMP_REG(BPF_JSGE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSGE_X: Signed jump: if (-1 >= -1) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, -1),
+			BPF_LD_IMM64(R2, -1),
+			BPF_JMP_REG(BPF_JSGE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JGT | BPF_X */
+	{
+		"JMP_JGT_X: if (3 > 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGT, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JGE | BPF_X */
+	{
+		"JMP_JGE_X: if (3 >= 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JGE_X: if (3 >= 3) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 3),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JNE | BPF_X */
+	{
+		"JMP_JNE_X: if (3 != 2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JNE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JEQ | BPF_X */
+	{
+		"JMP_JEQ_X: if (3 == 3) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 3),
+			BPF_JMP_REG(BPF_JEQ, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	/* BPF_JMP | BPF_JSET | BPF_X */
+	{
+		"JMP_JSET_X: if (0x3 & 0x2) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JNE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JSET_X: if (0x3 & 0xffffffff) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 0xffffffff),
+			BPF_JMP_REG(BPF_JNE, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
+	{
+		"JMP_JA: Jump, gap, jump, ...",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xababcbac } },
+		.fill_helper = bpf_fill_ja,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Maximum possible literals",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xffffffff } },
+		.fill_helper = bpf_fill_maxinsns1,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Single literal",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xfefefefe } },
+		.fill_helper = bpf_fill_maxinsns2,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Run/add until end",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0x947bf368 } },
+		.fill_helper = bpf_fill_maxinsns3,
+	},
+	{
+		"BPF_MAXINSNS: Too many instructions",
+		{ },
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ },
+		.fill_helper = bpf_fill_maxinsns4,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Very long jump",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xabababab } },
+		.fill_helper = bpf_fill_maxinsns5,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Ctx heavy transformations",
+		{ },
+		CLASSIC,
+		{ },
+		{
+			{  1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
+			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
+		},
+		.fill_helper = bpf_fill_maxinsns6,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Call heavy transformations",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 1, 0 }, { 10, 0 } },
+		.fill_helper = bpf_fill_maxinsns7,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Jump heavy test",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xffffffff } },
+		.fill_helper = bpf_fill_maxinsns8,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Very long jump backwards",
+		{ },
+		INTERNAL | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xcbababab } },
+		.fill_helper = bpf_fill_maxinsns9,
+	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Edge hopping nuthouse",
+		{ },
+		INTERNAL | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xabababac } },
+		.fill_helper = bpf_fill_maxinsns10,
+	},
+	{
+		"BPF_MAXINSNS: Jump, gap, jump, ...",
+		{ },
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xababcbac } },
+		.fill_helper = bpf_fill_maxinsns11,
+	},
 };
 
 static struct net_device dev;
@@ -1858,10 +4445,15 @@ static void release_test_data(const struct bpf_test *test, void *data)
 	kfree_skb(data);
 }
 
-static int probe_filter_length(struct sock_filter *fp)
+static int filter_length(int which)
 {
-	int len = 0;
+	struct sock_filter *fp;
+	int len;
 
+	if (tests[which].fill_helper)
+		return tests[which].u.ptr.len;
+
+	fp = tests[which].u.insns;
 	for (len = MAX_INSNS - 1; len > 0; --len)
 		if (fp[len].code != 0 || fp[len].k != 0)
 			break;
@@ -1869,16 +4461,25 @@ static int probe_filter_length(struct sock_filter *fp)
 	return len + 1;
 }
 
+static void *filter_pointer(int which)
+{
+	if (tests[which].fill_helper)
+		return tests[which].u.ptr.insns;
+	else
+		return tests[which].u.insns;
+}
+
 static struct bpf_prog *generate_filter(int which, int *err)
 {
-	struct bpf_prog *fp;
-	struct sock_fprog_kern fprog;
-	unsigned int flen = probe_filter_length(tests[which].u.insns);
 	__u8 test_type = tests[which].aux & TEST_TYPE_MASK;
+	unsigned int flen = filter_length(which);
+	void *fptr = filter_pointer(which);
+	struct sock_fprog_kern fprog;
+	struct bpf_prog *fp;
 
 	switch (test_type) {
 	case CLASSIC:
-		fprog.filter = tests[which].u.insns;
+		fprog.filter = fptr;
 		fprog.len = flen;
 
 		*err = bpf_prog_create(&fp, &fprog);
@@ -1914,8 +4515,7 @@ static struct bpf_prog *generate_filter(int which, int *err)
 		}
 
 		fp->len = flen;
-		memcpy(fp->insnsi, tests[which].u.insns_int,
-		       fp->len * sizeof(struct bpf_insn));
+		memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn));
 
 		bpf_prog_select_runtime(fp);
 		break;
@@ -1987,9 +4587,33 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 	return err_cnt;
 }
 
+static __init int prepare_bpf_tests(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (tests[i].fill_helper &&
+		    tests[i].fill_helper(&tests[i]) < 0)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static __init void destroy_bpf_tests(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (tests[i].fill_helper)
+			kfree(tests[i].u.ptr.insns);
+	}
+}
+
 static __init int test_bpf(void)
 {
 	int i, err_cnt = 0, pass_cnt = 0;
+	int jit_cnt = 0, run_cnt = 0;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_prog *fp;
@@ -2006,6 +4630,13 @@ static __init int test_bpf(void)
 
 			return err;
 		}
+
+		pr_cont("jited:%u ", fp->jited);
+
+		run_cnt++;
+		if (fp->jited)
+			jit_cnt++;
+
 		err = run_one(fp, &tests[i]);
 		release_filter(fp, i);
 
@@ -2018,13 +4649,24 @@ static __init int test_bpf(void)
 		}
 	}
 
-	pr_info("Summary: %d PASSED, %d FAILED\n", pass_cnt, err_cnt);
+	pr_info("Summary: %d PASSED, %d FAILED, [%d/%d JIT'ed]\n",
+		pass_cnt, err_cnt, jit_cnt, run_cnt);
+
 	return err_cnt ? -EINVAL : 0;
 }
 
 static int __init test_bpf_init(void)
 {
-	return test_bpf();
+	int ret;
+
+	ret = prepare_bpf_tests();
+	if (ret < 0)
+		return ret;
+
+	ret = test_bpf();
+
+	destroy_bpf_tests();
+	return ret;
 }
 
 static void __exit test_bpf_exit(void)
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index b2957540d..c90777eae 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -1,14 +1,9 @@
 /*
  * Resizable, Scalable, Concurrent Hash Table
  *
- * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch>
+ * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch>
  * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
  *
- * Based on the following paper:
- * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf
- *
- * Code partially derived from nft_hash
- *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
@@ -26,20 +21,37 @@
 #include <linux/rhashtable.h>
 #include <linux/slab.h>
 
+#define MAX_ENTRIES	1000000
+#define TEST_INSERT_FAIL INT_MAX
+
+static int entries = 50000;
+module_param(entries, int, 0);
+MODULE_PARM_DESC(entries, "Number of entries to add (default: 50000)");
+
+static int runs = 4;
+module_param(runs, int, 0);
+MODULE_PARM_DESC(runs, "Number of test runs per variant (default: 4)");
+
+static int max_size = 65536;
+module_param(max_size, int, 0);
+MODULE_PARM_DESC(runs, "Maximum table size (default: 65536)");
 
-#define TEST_HT_SIZE	8
-#define TEST_ENTRIES	2048
-#define TEST_PTR	((void *) 0xdeadbeef)
-#define TEST_NEXPANDS	4
+static bool shrinking = false;
+module_param(shrinking, bool, 0);
+MODULE_PARM_DESC(shrinking, "Enable automatic shrinking (default: off)");
+
+static int size = 8;
+module_param(size, int, 0);
+MODULE_PARM_DESC(size, "Initial size hint of table (default: 8)");
 
 struct test_obj {
-	void			*ptr;
 	int			value;
 	struct rhash_head	node;
 };
 
-static const struct rhashtable_params test_rht_params = {
-	.nelem_hint = TEST_HT_SIZE,
+static struct test_obj array[MAX_ENTRIES];
+
+static struct rhashtable_params test_rht_params = {
 	.head_offset = offsetof(struct test_obj, node),
 	.key_offset = offsetof(struct test_obj, value),
 	.key_len = sizeof(int),
@@ -51,11 +63,14 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 {
 	unsigned int i;
 
-	for (i = 0; i < TEST_ENTRIES * 2; i++) {
+	for (i = 0; i < entries * 2; i++) {
 		struct test_obj *obj;
 		bool expected = !(i % 2);
 		u32 key = i;
 
+		if (array[i / 2].value == TEST_INSERT_FAIL)
+			expected = false;
+
 		obj = rhashtable_lookup_fast(ht, &key, test_rht_params);
 
 		if (expected && !obj) {
@@ -66,9 +81,9 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 				key);
 			return -EEXIST;
 		} else if (expected && obj) {
-			if (obj->ptr != TEST_PTR || obj->value != i) {
-				pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n",
-					obj->ptr, TEST_PTR, obj->value, i);
+			if (obj->value != i) {
+				pr_warn("Test failed: Lookup value mismatch %u!=%u\n",
+					obj->value, i);
 				return -EINVAL;
 			}
 		}
@@ -77,129 +92,147 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 	return 0;
 }
 
-static void test_bucket_stats(struct rhashtable *ht, bool quiet)
+static void test_bucket_stats(struct rhashtable *ht)
 {
-	unsigned int cnt, rcu_cnt, i, total = 0;
+	unsigned int err, total = 0, chain_len = 0;
+	struct rhashtable_iter hti;
 	struct rhash_head *pos;
-	struct test_obj *obj;
-	struct bucket_table *tbl;
 
-	tbl = rht_dereference_rcu(ht->tbl, ht);
-	for (i = 0; i < tbl->size; i++) {
-		rcu_cnt = cnt = 0;
+	err = rhashtable_walk_init(ht, &hti);
+	if (err) {
+		pr_warn("Test failed: allocation error");
+		return;
+	}
 
-		if (!quiet)
-			pr_info(" [%#4x/%u]", i, tbl->size);
+	err = rhashtable_walk_start(&hti);
+	if (err && err != -EAGAIN) {
+		pr_warn("Test failed: iterator failed: %d\n", err);
+		return;
+	}
 
-		rht_for_each_entry_rcu(obj, pos, tbl, i, node) {
-			cnt++;
-			total++;
-			if (!quiet)
-				pr_cont(" [%p],", obj);
+	while ((pos = rhashtable_walk_next(&hti))) {
+		if (PTR_ERR(pos) == -EAGAIN) {
+			pr_info("Info: encountered resize\n");
+			chain_len++;
+			continue;
+		} else if (IS_ERR(pos)) {
+			pr_warn("Test failed: rhashtable_walk_next() error: %ld\n",
+				PTR_ERR(pos));
+			break;
 		}
 
-		rht_for_each_entry_rcu(obj, pos, tbl, i, node)
-			rcu_cnt++;
-
-		if (rcu_cnt != cnt)
-			pr_warn("Test failed: Chain count mismach %d != %d",
-				cnt, rcu_cnt);
-
-		if (!quiet)
-			pr_cont("\n  [%#x] first element: %p, chain length: %u\n",
-				i, tbl->buckets[i], cnt);
+		total++;
 	}
 
-	pr_info("  Traversal complete: counted=%u, nelems=%u, entries=%d\n",
-		total, atomic_read(&ht->nelems), TEST_ENTRIES);
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
+
+	pr_info("  Traversal complete: counted=%u, nelems=%u, entries=%d, table-jumps=%u\n",
+		total, atomic_read(&ht->nelems), entries, chain_len);
 
-	if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES)
+	if (total != atomic_read(&ht->nelems) || total != entries)
 		pr_warn("Test failed: Total count mismatch ^^^");
 }
 
-static int __init test_rhashtable(struct rhashtable *ht)
+static s64 __init test_rhashtable(struct rhashtable *ht)
 {
-	struct bucket_table *tbl;
 	struct test_obj *obj;
-	struct rhash_head *pos, *next;
 	int err;
-	unsigned int i;
+	unsigned int i, insert_fails = 0;
+	s64 start, end;
 
 	/*
 	 * Insertion Test:
-	 * Insert TEST_ENTRIES into table with all keys even numbers
+	 * Insert entries into table with all keys even numbers
 	 */
-	pr_info("  Adding %d keys\n", TEST_ENTRIES);
-	for (i = 0; i < TEST_ENTRIES; i++) {
-		struct test_obj *obj;
-
-		obj = kzalloc(sizeof(*obj), GFP_KERNEL);
-		if (!obj) {
-			err = -ENOMEM;
-			goto error;
-		}
+	pr_info("  Adding %d keys\n", entries);
+	start = ktime_get_ns();
+	for (i = 0; i < entries; i++) {
+		struct test_obj *obj = &array[i];
 
-		obj->ptr = TEST_PTR;
 		obj->value = i * 2;
 
 		err = rhashtable_insert_fast(ht, &obj->node, test_rht_params);
-		if (err) {
-			kfree(obj);
-			goto error;
+		if (err == -ENOMEM || err == -EBUSY) {
+			/* Mark failed inserts but continue */
+			obj->value = TEST_INSERT_FAIL;
+			insert_fails++;
+		} else if (err) {
+			return err;
 		}
 	}
 
+	if (insert_fails)
+		pr_info("  %u insertions failed due to memory pressure\n",
+			insert_fails);
+
+	test_bucket_stats(ht);
 	rcu_read_lock();
-	test_bucket_stats(ht, true);
 	test_rht_lookup(ht);
 	rcu_read_unlock();
 
-	rcu_read_lock();
-	test_bucket_stats(ht, true);
-	rcu_read_unlock();
+	test_bucket_stats(ht);
 
-	pr_info("  Deleting %d keys\n", TEST_ENTRIES);
-	for (i = 0; i < TEST_ENTRIES; i++) {
+	pr_info("  Deleting %d keys\n", entries);
+	for (i = 0; i < entries; i++) {
 		u32 key = i * 2;
 
-		obj = rhashtable_lookup_fast(ht, &key, test_rht_params);
-		BUG_ON(!obj);
+		if (array[i].value != TEST_INSERT_FAIL) {
+			obj = rhashtable_lookup_fast(ht, &key, test_rht_params);
+			BUG_ON(!obj);
 
-		rhashtable_remove_fast(ht, &obj->node, test_rht_params);
-		kfree(obj);
+			rhashtable_remove_fast(ht, &obj->node, test_rht_params);
+		}
 	}
 
-	return 0;
-
-error:
-	tbl = rht_dereference_rcu(ht->tbl, ht);
-	for (i = 0; i < tbl->size; i++)
-		rht_for_each_entry_safe(obj, pos, next, tbl, i, node)
-			kfree(obj);
+	end = ktime_get_ns();
+	pr_info("  Duration of test: %lld ns\n", end - start);
 
-	return err;
+	return end - start;
 }
 
 static struct rhashtable ht;
 
 static int __init test_rht_init(void)
 {
-	int err;
+	int i, err;
+	u64 total_time = 0;
 
-	pr_info("Running resizable hashtable tests...\n");
+	entries = min(entries, MAX_ENTRIES);
 
-	err = rhashtable_init(&ht, &test_rht_params);
-	if (err < 0) {
-		pr_warn("Test failed: Unable to initialize hashtable: %d\n",
-			err);
-		return err;
-	}
+	test_rht_params.automatic_shrinking = shrinking;
+	test_rht_params.max_size = max_size;
+	test_rht_params.nelem_hint = size;
 
-	err = test_rhashtable(&ht);
+	pr_info("Running rhashtable test nelem=%d, max_size=%d, shrinking=%d\n",
+		size, max_size, shrinking);
 
-	rhashtable_destroy(&ht);
+	for (i = 0; i < runs; i++) {
+		s64 time;
 
-	return err;
+		pr_info("Test %02d:\n", i);
+		memset(&array, 0, sizeof(array));
+		err = rhashtable_init(&ht, &test_rht_params);
+		if (err < 0) {
+			pr_warn("Test failed: Unable to initialize hashtable: %d\n",
+				err);
+			continue;
+		}
+
+		time = test_rhashtable(&ht);
+		rhashtable_destroy(&ht);
+		if (time < 0) {
+			pr_warn("Test failed: return code %lld\n", time);
+			return -EINVAL;
+		}
+
+		total_time += time;
+	}
+
+	do_div(total_time, runs);
+	pr_info("Average test time: %llu\n", total_time);
+
+	return 0;
 }
 
 static void __exit test_rht_exit(void)
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index a382e4a32..782ae8ca2 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -36,7 +36,7 @@
  * Adds the timer node to the timerqueue, sorted by the
  * node's expires value.
  */
-void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	struct rb_node **p = &head->head.rb_node;
 	struct rb_node *parent = NULL;
@@ -56,8 +56,11 @@ void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 	rb_link_node(&node->node, parent, p);
 	rb_insert_color(&node->node, &head->head);
 
-	if (!head->next || node->expires.tv64 < head->next->expires.tv64)
+	if (!head->next || node->expires.tv64 < head->next->expires.tv64) {
 		head->next = node;
+		return true;
+	}
+	return false;
 }
 EXPORT_SYMBOL_GPL(timerqueue_add);
 
@@ -69,7 +72,7 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  *
  * Removes the timer node from the timerqueue.
  */
-void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {
 	WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
 
@@ -82,6 +85,7 @@ void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 	}
 	rb_erase(&node->node, &head->head);
 	RB_CLEAR_NODE(&node->node);
+	return head->next != NULL;
 }
 EXPORT_SYMBOL_GPL(timerqueue_del);