lzo: update from N770FXXU8HVK5

Documentation/lzo.txt

@@ -73,15 +73,33 @@ Description
   They just have to "refill" this credit if they consume extra bytes. This is
   an implementation design choice independent on the algorithm or encoding.
 
+Versions
+
+0: Original version
+1: LZO-RLE
+
+Version 1 of LZO implements an extension to encode runs of zeros using run
+length encoding. This improves speed for data with many zeros, which is a
+common case for zram. This modifies the bitstream in a backwards compatible way
+(v1 can correctly decompress v0 compressed data, but v0 cannot read v1 data).
+
+For maximum compatibility, both versions are available under different names
+(lzo and lzo-rle). Differences in the encoding are noted in this document with
+e.g.: version 1 only.
+
 Byte sequences
 
   First byte encoding :
 
-      0..17   : follow regular instruction encoding, see below. It is worth
+      0..16   : follow regular instruction encoding, see below. It is worth
-                noting that codes 16 and 17 will represent a block copy from
+                noting that code 16 will represent a block copy from the
-                the dictionary which is empty, and that they will always be
+                dictionary which is empty, and that it will always be
                 invalid at this place.
 
+      17      : bitstream version. If the first byte is 17, the next byte
+                gives the bitstream version (version 1 only). If the first byte
+                is not 17, the bitstream version is 0.
+
       18..21  : copy 0..3 literals
                 state = (byte - 17) = 0..3  [ copy <state> literals ]
                 skip byte
@@ -134,6 +152,11 @@ Byte sequences
            state = S (copy S literals after this block)
            End of stream is reached if distance == 16384
 
+        In version 1 only, this instruction is also used to encode a run of
+        zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
+           In this case, it is followed by a fourth byte, X.
+           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4.
+
       0 0 1 L L L L L  (32..63)
            Copy of small block within 16kB distance (preferably less than 34B)
            length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
@@ -158,7 +181,9 @@ Byte sequences
 Authors
 
   This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
-  analysis of the decompression code available in Linux 3.16-rc5. The code is
+  analysis of the decompression code available in Linux 3.16-rc5, and updated
-  tricky, it is possible that this document contains mistakes or that a few
+  by Dave Rodgman <dave.rodgman@arm.com> on 2018/10/30 to introduce run-length
-  corner cases were overlooked. In any case, please report any doubt, fix, or
+  encoding. The code is tricky, it is possible that this document contains
-  proposed updates to the author(s) so that the document can be updated.
+  mistakes or that a few corner cases were overlooked. In any case, please
+  report any doubt, fix, or proposed updates to the author(s) so that the
+  document can be updated.

crypto/Makefile

@@ -116,7 +116,7 @@ obj-$(CONFIG_CRYPTO_CRC32C) += crc32c_generic.o
 obj-$(CONFIG_CRYPTO_CRC32) += crc32_generic.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
-obj-$(CONFIG_CRYPTO_LZO) += lzo.o
+obj-$(CONFIG_CRYPTO_LZO) += lzo.o lzo-rle.o
 obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
 obj-$(CONFIG_CRYPTO_LZ4HC) += lz4hc.o
 obj-$(CONFIG_CRYPTO_842) += 842.o

crypto/lzo-rle.c

@@ -0,0 +1,175 @@
+/*
+ * Cryptographic API.
+ *
+ * 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.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/lzo.h>
+#include <crypto/internal/scompress.h>
+
+struct lzorle_ctx {
+	void *lzorle_comp_mem;
+};
+
+static void *lzorle_alloc_ctx(struct crypto_scomp *tfm)
+{
+	void *ctx;
+
+	ctx = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	return ctx;
+}
+
+static int lzorle_init(struct crypto_tfm *tfm)
+{
+	struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->lzorle_comp_mem = lzorle_alloc_ctx(NULL);
+	if (IS_ERR(ctx->lzorle_comp_mem))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void lzorle_free_ctx(struct crypto_scomp *tfm, void *ctx)
+{
+	kvfree(ctx);
+}
+
+static void lzorle_exit(struct crypto_tfm *tfm)
+{
+	struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	lzorle_free_ctx(NULL, ctx->lzorle_comp_mem);
+}
+
+static int __lzorle_compress(const u8 *src, unsigned int slen,
+			  u8 *dst, unsigned int *dlen, void *ctx)
+{
+	size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
+	int err;
+
+	err = lzorle1x_1_compress(src, slen, dst, &tmp_len, ctx);
+
+	if (err != LZO_E_OK)
+		return -EINVAL;
+
+	*dlen = tmp_len;
+	return 0;
+}
+
+static int lzorle_compress(struct crypto_tfm *tfm, const u8 *src,
+			unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	return __lzorle_compress(src, slen, dst, dlen, ctx->lzorle_comp_mem);
+}
+
+static int lzorle_scompress(struct crypto_scomp *tfm, const u8 *src,
+			 unsigned int slen, u8 *dst, unsigned int *dlen,
+			 void *ctx)
+{
+	return __lzorle_compress(src, slen, dst, dlen, ctx);
+}
+
+static int __lzorle_decompress(const u8 *src, unsigned int slen,
+			    u8 *dst, unsigned int *dlen)
+{
+	int err;
+	size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
+
+	err = lzo1x_decompress_safe(src, slen, dst, &tmp_len);
+
+	if (err != LZO_E_OK)
+		return -EINVAL;
+
+	*dlen = tmp_len;
+	return 0;
+}
+
+static int lzorle_decompress(struct crypto_tfm *tfm, const u8 *src,
+			  unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+	return __lzorle_decompress(src, slen, dst, dlen);
+}
+
+static int lzorle_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+			   unsigned int slen, u8 *dst, unsigned int *dlen,
+			   void *ctx)
+{
+	return __lzorle_decompress(src, slen, dst, dlen);
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "lzo-rle",
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct lzorle_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= lzorle_init,
+	.cra_exit		= lzorle_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= lzorle_compress,
+	.coa_decompress		= lzorle_decompress } }
+};
+
+static struct scomp_alg scomp = {
+	.alloc_ctx		= lzorle_alloc_ctx,
+	.free_ctx		= lzorle_free_ctx,
+	.compress		= lzorle_scompress,
+	.decompress		= lzorle_sdecompress,
+	.base			= {
+		.cra_name	= "lzo-rle",
+		.cra_driver_name = "lzo-rle-scomp",
+		.cra_module	 = THIS_MODULE,
+	}
+};
+
+static int __init lzorle_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_alg(&alg);
+	if (ret)
+		return ret;
+
+	ret = crypto_register_scomp(&scomp);
+	if (ret) {
+		crypto_unregister_alg(&alg);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void __exit lzorle_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+	crypto_unregister_scomp(&scomp);
+}
+
+module_init(lzorle_mod_init);
+module_exit(lzorle_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO-RLE Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo-rle");

crypto/tcrypt.c

@@ -73,7 +73,8 @@ static char *check[] = {
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
 	"khazad", "wp512", "wp384", "wp256", "tnepres", "xeta",  "fcrypt",
 	"camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320",
-	"lzo", "cts", "zlib", "sha3-224", "sha3-256", "sha3-384", "sha3-512",
+	"lzo", "lzo-rle", "cts", "zlib", "sha3-224", "sha3-256", "sha3-384",
+	"sha3-512",
 	NULL
 };
 

drivers/block/zram/Kconfig

@@ -41,7 +41,7 @@ config ZRAM_MEMORY_TRACKING
 
 config ZRAM_DEFAULT_COMP_ALGORITHM
 	string "Default ZRAM algorithm"
-	default "lz4"
+	default "lzo-rle"
 
 config ZRAM_LRU_WRITEBACK
 	bool

drivers/block/zram/zcomp.c

@@ -20,6 +20,7 @@
 
 static const char * const backends[] = {
 	"lzo",
+	"lzo-rle",
 #if IS_ENABLED(CONFIG_CRYPTO_LZ4)
 	"lz4",
 #endif

include/linux/lzo.h

@@ -17,12 +17,16 @@
 #define LZO1X_1_MEM_COMPRESS	(8192 * sizeof(unsigned short))
 #define LZO1X_MEM_COMPRESS	LZO1X_1_MEM_COMPRESS
 
-#define lzo1x_worst_compress(x) ((x) + ((x) / 16) + 64 + 3)
+#define lzo1x_worst_compress(x) ((x) + ((x) / 16) + 64 + 3 + 2)
 
 /* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */
 int lzo1x_1_compress(const unsigned char *src, size_t src_len,
 		     unsigned char *dst, size_t *dst_len, void *wrkmem);
 
+/* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */
+int lzorle1x_1_compress(const unsigned char *src, size_t src_len,
+		     unsigned char *dst, size_t *dst_len, void *wrkmem);
+
 /* safe decompression with overrun testing */
 int lzo1x_decompress_safe(const unsigned char *src, size_t src_len,
 			  unsigned char *dst, size_t *dst_len);

lib/lzo/lzo1x_compress.c

@@ -20,7 +20,8 @@
 static noinline size_t
 lzo1x_1_do_compress(const unsigned char *in, size_t in_len,
 		    unsigned char *out, size_t *out_len,
-		    size_t ti, void *wrkmem)
+		    size_t ti, void *wrkmem, signed char *state_offset,
+		    const unsigned char bitstream_version)
 {
 	const unsigned char *ip;
 	unsigned char *op;
@@ -35,27 +36,85 @@ lzo1x_1_do_compress(const unsigned char *in, size_t in_len,
 	ip += ti < 4 ? 4 - ti : 0;
 
 	for (;;) {
-		const unsigned char *m_pos;
+		const unsigned char *m_pos = NULL;
 		size_t t, m_len, m_off;
 		u32 dv;
+		u32 run_length = 0;
 literal:
 		ip += 1 + ((ip - ii) >> 5);
 next:
 		if (unlikely(ip >= ip_end))
 			break;
 		dv = get_unaligned_le32(ip);
-		t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK;
+
-		m_pos = in + dict[t];
+		if (dv == 0 && bitstream_version) {
-		dict[t] = (lzo_dict_t) (ip - in);
+			const unsigned char *ir = ip + 4;
-		if (unlikely(dv != get_unaligned_le32(m_pos)))
+			const unsigned char *limit = ip_end
-			goto literal;
+				< (ip + MAX_ZERO_RUN_LENGTH + 1)
+				? ip_end : ip + MAX_ZERO_RUN_LENGTH + 1;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
+	defined(LZO_FAST_64BIT_MEMORY_ACCESS)
+			u64 dv64;
+
+			for (; (ir + 32) <= limit; ir += 32) {
+				dv64 = get_unaligned((u64 *)ir);
+				dv64 |= get_unaligned((u64 *)ir + 1);
+				dv64 |= get_unaligned((u64 *)ir + 2);
+				dv64 |= get_unaligned((u64 *)ir + 3);
+				if (dv64)
+					break;
+			}
+			for (; (ir + 8) <= limit; ir += 8) {
+				dv64 = get_unaligned((u64 *)ir);
+				if (dv64) {
+#  if defined(__LITTLE_ENDIAN)
+					ir += __builtin_ctzll(dv64) >> 3;
+#  elif defined(__BIG_ENDIAN)
+					ir += __builtin_clzll(dv64) >> 3;
+#  else
+#    error "missing endian definition"
+#  endif
+					break;
+				}
+			}
+#else
+			while ((ir < (const unsigned char *)
+					ALIGN((uintptr_t)ir, 4)) &&
+					(ir < limit) && (*ir == 0))
+				ir++;
+			for (; (ir + 4) <= limit; ir += 4) {
+				dv = *((u32 *)ir);
+				if (dv) {
+#  if defined(__LITTLE_ENDIAN)
+					ir += __builtin_ctz(dv) >> 3;
+#  elif defined(__BIG_ENDIAN)
+					ir += __builtin_clz(dv) >> 3;
+#  else
+#    error "missing endian definition"
+#  endif
+					break;
+				}
+			}
+#endif
+			while (likely(ir < limit) && unlikely(*ir == 0))
+				ir++;
+			run_length = ir - ip;
+			if (run_length > MAX_ZERO_RUN_LENGTH)
+				run_length = MAX_ZERO_RUN_LENGTH;
+		} else {
+			t = ((dv * 0x1824429d) >> (32 - D_BITS)) & D_MASK;
+			m_pos = in + dict[t];
+			dict[t] = (lzo_dict_t) (ip - in);
+			if (unlikely(dv != get_unaligned_le32(m_pos)))
+				goto literal;
+		}
 
 		ii -= ti;
 		ti = 0;
 		t = ip - ii;
 		if (t != 0) {
 			if (t <= 3) {
-				op[-2] |= t;
+				op[*state_offset] |= t;
 				COPY4(op, ii);
 				op += t;
 			} else if (t <= 16) {
@@ -88,6 +147,17 @@ next:
 			}
 		}
 
+		if (unlikely(run_length)) {
+			ip += run_length;
+			run_length -= MIN_ZERO_RUN_LENGTH;
+			put_unaligned_le32((run_length << 21) | 0xfffc18
+					   | (run_length & 0x7), op);
+			op += 4;
+			run_length = 0;
+			*state_offset = -3;
+			goto finished_writing_instruction;
+		}
+
 		m_len = 4;
 		{
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(LZO_USE_CTZ64)
@@ -170,7 +240,6 @@ m_len_done:
 
 		m_off = ip - m_pos;
 		ip += m_len;
-		ii = ip;
 		if (m_len <= M2_MAX_LEN && m_off <= M2_MAX_OFFSET) {
 			m_off -= 1;
 			*op++ = (((m_len - 1) << 5) | ((m_off & 7) << 2));
@@ -207,29 +276,45 @@ m_len_done:
 			*op++ = (m_off << 2);
 			*op++ = (m_off >> 6);
 		}
+		*state_offset = -2;
+finished_writing_instruction:
+		ii = ip;
 		goto next;
 	}
 	*out_len = op - out;
 	return in_end - (ii - ti);
 }
 
-int lzo1x_1_compress(const unsigned char *in, size_t in_len,
+int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 		     unsigned char *out, size_t *out_len,
-		     void *wrkmem)
+		     void *wrkmem, const unsigned char bitstream_version)
 {
 	const unsigned char *ip = in;
 	unsigned char *op = out;
 	size_t l = in_len;
 	size_t t = 0;
+	signed char state_offset = -2;
+	unsigned int m4_max_offset;
+
+	// LZO v0 will never write 17 as first byte,
+	// so this is used to version the bitstream
+	if (bitstream_version > 0) {
+		*op++ = 17;
+		*op++ = bitstream_version;
+		m4_max_offset = M4_MAX_OFFSET_V1;
+	} else {
+		m4_max_offset = M4_MAX_OFFSET_V0;
+	}
 
 	while (l > 20) {
-		size_t ll = l <= (M4_MAX_OFFSET + 1) ? l : (M4_MAX_OFFSET + 1);
+		size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1);
 		uintptr_t ll_end = (uintptr_t) ip + ll;
 		if ((ll_end + ((t + ll) >> 5)) <= ll_end)
 			break;
 		BUILD_BUG_ON(D_SIZE * sizeof(lzo_dict_t) > LZO1X_1_MEM_COMPRESS);
 		memset(wrkmem, 0, D_SIZE * sizeof(lzo_dict_t));
-		t = lzo1x_1_do_compress(ip, ll, op, out_len, t, wrkmem);
+		t = lzo1x_1_do_compress(ip, ll, op, out_len, t, wrkmem,
+					&state_offset, bitstream_version);
 		ip += ll;
 		op += *out_len;
 		l  -= ll;
@@ -242,7 +327,7 @@ int lzo1x_1_compress(const unsigned char *in, size_t in_len,
 		if (op == out && t <= 238) {
 			*op++ = (17 + t);
 		} else if (t <= 3) {
-			op[-2] |= t;
+			op[state_offset] |= t;
 		} else if (t <= 18) {
 			*op++ = (t - 3);
 		} else {
@@ -273,7 +358,24 @@ int lzo1x_1_compress(const unsigned char *in, size_t in_len,
 	*out_len = op - out;
 	return LZO_E_OK;
 }
+
+int lzo1x_1_compress(const unsigned char *in, size_t in_len,
+		     unsigned char *out, size_t *out_len,
+		     void *wrkmem)
+{
+	return lzogeneric1x_1_compress(in, in_len, out, out_len, wrkmem, 0);
+}
+
+int lzorle1x_1_compress(const unsigned char *in, size_t in_len,
+		     unsigned char *out, size_t *out_len,
+		     void *wrkmem)
+{
+	return lzogeneric1x_1_compress(in, in_len, out, out_len,
+				       wrkmem, LZO_VERSION);
+}
+
 EXPORT_SYMBOL_GPL(lzo1x_1_compress);
+EXPORT_SYMBOL_GPL(lzorle1x_1_compress);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZO1X-1 Compressor");

lib/lzo/lzo1x_decompress_safe.c

@@ -46,11 +46,23 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 	const unsigned char * const ip_end = in + in_len;
 	unsigned char * const op_end = out + *out_len;
 
+	unsigned char bitstream_version;
+
 	op = out;
 	ip = in;
 
 	if (unlikely(in_len < 3))
 		goto input_overrun;
+
+	if (likely(*ip == 17)) {
+		bitstream_version = ip[1];
+		ip += 2;
+		if (unlikely(in_len < 5))
+			goto input_overrun;
+	} else {
+		bitstream_version = 0;
+	}
+
 	if (*ip > 17) {
 		t = *ip++ - 17;
 		if (t < 4) {
@@ -154,32 +166,49 @@ copy_literal_run:
 			m_pos -= next >> 2;
 			next &= 3;
 		} else {
-			m_pos = op;
+			NEED_IP(2);
-			m_pos -= (t & 8) << 11;
-			t = (t & 7) + (3 - 1);
-			if (unlikely(t == 2)) {
-				size_t offset;
-				const unsigned char *ip_last = ip;
-
-				while (unlikely(*ip == 0)) {
-					ip++;
-					NEED_IP(1);
-				}
-				offset = ip - ip_last;
-				if (unlikely(offset > MAX_255_COUNT))
-					return LZO_E_ERROR;
-
-				offset = (offset << 8) - offset;
-				t += offset + 7 + *ip++;
-				NEED_IP(2);
-			}
 			next = get_unaligned_le16(ip);
-			ip += 2;
+			if (((next & 0xfffc) == 0xfffc) &&
-			m_pos -= next >> 2;
+			    ((t & 0xf8) == 0x18) &&
-			next &= 3;
+			    likely(bitstream_version)) {
-			if (m_pos == op)
+				NEED_IP(3);
-				goto eof_found;
+				t &= 7;
-			m_pos -= 0x4000;
+				t |= ip[2] << 3;
+				t += MIN_ZERO_RUN_LENGTH;
+				NEED_OP(t);
+				memset(op, 0, t);
+				op += t;
+				next &= 3;
+				ip += 3;
+				goto match_next;
+			} else {
+				m_pos = op;
+				m_pos -= (t & 8) << 11;
+				t = (t & 7) + (3 - 1);
+				if (unlikely(t == 2)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
+					while (unlikely(*ip == 0)) {
+						ip++;
+						NEED_IP(1);
+					}
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 7 + *ip++;
+					NEED_IP(2);
+					next = get_unaligned_le16(ip);
+				}
+				ip += 2;
+				m_pos -= next >> 2;
+				next &= 3;
+				if (m_pos == op)
+					goto eof_found;
+				m_pos -= 0x4000;
+			}
 		}
 		TEST_LB(m_pos);
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)

lib/lzo/lzodefs.h

@@ -12,9 +12,15 @@
  */
 
 
+/* Version
+ * 0: original lzo version
+ * 1: lzo with support for RLE
+ */
+#define LZO_VERSION 1
+
 #define COPY4(dst, src)	\
 		put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst))
-#if defined(__x86_64__)
+#if defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
 #define COPY8(dst, src)	\
 		put_unaligned(get_unaligned((const u64 *)(src)), (u64 *)(dst))
 #else
@@ -24,19 +30,21 @@
 
 #if defined(__BIG_ENDIAN) && defined(__LITTLE_ENDIAN)
 #error "conflicting endian definitions"
-#elif defined(__x86_64__)
+#elif defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
 #define LZO_USE_CTZ64	1
 #define LZO_USE_CTZ32	1
-#elif defined(__i386__) || defined(__powerpc__)
+#define LZO_FAST_64BIT_MEMORY_ACCESS
+#elif defined(CONFIG_X86) || defined(CONFIG_PPC)
 #define LZO_USE_CTZ32	1
-#elif defined(__arm__) && (__LINUX_ARM_ARCH__ >= 5)
+#elif defined(CONFIG_ARM) && (__LINUX_ARM_ARCH__ >= 5)
 #define LZO_USE_CTZ32	1
 #endif
 
 #define M1_MAX_OFFSET	0x0400
 #define M2_MAX_OFFSET	0x0800
 #define M3_MAX_OFFSET	0x4000
-#define M4_MAX_OFFSET	0xbfff
+#define M4_MAX_OFFSET_V0	0xbfff
+#define M4_MAX_OFFSET_V1	0xbffe
 
 #define M1_MIN_LEN	2
 #define M1_MAX_LEN	2
@@ -52,6 +60,9 @@
 #define M3_MARKER	32
 #define M4_MARKER	16
 
+#define MIN_ZERO_RUN_LENGTH	4
+#define MAX_ZERO_RUN_LENGTH	(2047 + MIN_ZERO_RUN_LENGTH)
+
 #define lzo_dict_t      unsigned short
 #define D_BITS		13
 #define D_SIZE		(1u << D_BITS)