smb: client: compress: LZ77 code improvements cleanup

- Check data compressibility with some heuristics (copied from
  btrfs):
  - should_compress() final decision is is_compressible(data)

- Cleanup compress/lz77.h leaving only lz77_compress() exposed:
  - Move parts to compress/lz77.c, while removing the rest of it
    because they were either unused, used only once, were
    implemented wrong (thanks to David Howells for the help)

- Updated the compression parameters (still compatible with
  Windows implementation) trading off ~20% compression ratio
  for ~40% performance:
  - min match len: 3 -> 4
  - max distance: 8KiB -> 1KiB
  - hash table type: u32 * -> u64 *

Known bugs:
This implementation currently works fine in general, but breaks with
some payloads used during testing.  Investigation ongoing, to be
fixed in a next commit.

Signed-off-by: Enzo Matsumiya <ematsumiya@suse.de>
Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>

2 files changed, 149 insertions, 396 deletions

diff --git a/fs/smb/client/compress/lz77.c b/fs/smb/client/compress/lz77.c
index 2b8d548f9492..553e253ada29 100644
--- a/fs/smb/client/compress/lz77.c
+++ b/fs/smb/client/compress/lz77.c
@@ -7,14 +7,75 @@
  * Implementation of the LZ77 "plain" compression algorithm, as per MS-XCA spec.
  */
 #include <linux/slab.h>
+#include <linux/sizes.h>
+#include <linux/count_zeros.h>
+#include <asm/unaligned.h>
+
 #include "lz77.h"
 
-static __always_inline u32 hash3(const u8 *ptr)
+/*
+ * Compression parameters.
+ */
+#define LZ77_MATCH_MIN_LEN	4
+#define LZ77_MATCH_MIN_DIST	1
+#define LZ77_MATCH_MAX_DIST	SZ_1K
+#define LZ77_HASH_LOG		15
+#define LZ77_HASH_SIZE		(1 << LZ77_HASH_LOG)
+#define LZ77_STEP_SIZE		sizeof(u64)
+
+static __always_inline u8 lz77_read8(const u8 *ptr)
+{
+	return get_unaligned(ptr);
+}
+
+static __always_inline u64 lz77_read64(const u64 *ptr)
+{
+	return get_unaligned(ptr);
+}
+
+static __always_inline void lz77_write8(u8 *ptr, u8 v)
+{
+	put_unaligned(v, ptr);
+}
+
+static __always_inline void lz77_write16(u16 *ptr, u16 v)
+{
+	put_unaligned_le16(v, ptr);
+}
+
+static __always_inline void lz77_write32(u32 *ptr, u32 v)
+{
+	put_unaligned_le32(v, ptr);
+}
+
+static __always_inline u32 lz77_match_len(const void *wnd, const void *cur, const void *end)
 {
-	return lz77_hash32(lz77_read32(ptr) & 0xffffff, LZ77_HASH_LOG);
+	const void *start = cur;
+	u64 diff;
+
+	/* Safe for a do/while because otherwise we wouldn't reach here from the main loop. */
+	do {
+		diff = lz77_read64(cur) ^ lz77_read64(wnd);
+		if (!diff) {
+			cur += LZ77_STEP_SIZE;
+			wnd += LZ77_STEP_SIZE;
+
+			continue;
+		}
+
+		/* This computes the number of common bytes in @diff. */
+		cur += count_trailing_zeros(diff) >> 3;
+
+		return (cur - start);
+	} while (likely(cur + LZ77_STEP_SIZE < end));
+
+	while (cur < end && lz77_read8(cur++) == lz77_read8(wnd++))
+		;
+
+	return (cur - start);
 }
 
-static u8 *write_match(u8 *dst, u8 **nib, u32 dist, u32 len)
+static __always_inline void *lz77_write_match(void *dst, void **nib, u32 dist, u32 len)
 {
 	len -= 3;
 	dist--;
@@ -22,6 +83,7 @@ static u8 *write_match(u8 *dst, u8 **nib, u32 dist, u32 len)
 
 	if (len < 7) {
 		lz77_write16(dst, dist + len);
+
 		return dst + 2;
 	}
 
@@ -31,11 +93,13 @@ static u8 *write_match(u8 *dst, u8 **nib, u32 dist, u32 len)
 	len -= 7;
 
 	if (!*nib) {
+		lz77_write8(dst, umin(len, 15));
 		*nib = dst;
-		lz77_write8(dst, min_t(unsigned int, len, 15));
 		dst++;
 	} else {
-		**nib |= min_t(unsigned int, len, 15) << 4;
+		u8 *b = *nib;
+
+		lz77_write8(b, *b | umin(len, 15) << 4);
 		*nib = NULL;
 	}
 
@@ -45,15 +109,16 @@ static u8 *write_match(u8 *dst, u8 **nib, u32 dist, u32 len)
 	len -= 15;
 	if (len < 255) {
 		lz77_write8(dst, len);
+
 		return dst + 1;
 	}
 
 	lz77_write8(dst, 0xff);
 	dst++;
-
 	len += 7 + 15;
 	if (len <= 0xffff) {
 		lz77_write16(dst, len);
+
 		return dst + 2;
 	}
 
@@ -64,148 +129,107 @@ static u8 *write_match(u8 *dst, u8 **nib, u32 dist, u32 len)
 	return dst + 4;
 }
 
-static u8 *write_literals(u8 *dst, const u8 *dst_end, const u8 *src, size_t count,
-			  struct lz77_flags *flags)
+noinline int lz77_compress(const void *src, u32 slen, void *dst, u32 *dlen)
 {
-	const u8 *end = src + count;
-
-	while (src < end) {
-		size_t c = lz77_min(count, 32 - flags->count);
-
-		if (dst + c >= dst_end)
-			return ERR_PTR(-EFAULT);
-
-		if (lz77_copy(dst, src, c))
-			return ERR_PTR(-EFAULT);
-
-		dst += c;
-		src += c;
-		count -= c;
-
-		flags->val <<= c;
-		flags->count += c;
-		if (flags->count == 32) {
-			lz77_write32(flags->pos, flags->val);
-			flags->count = 0;
-			flags->pos = dst;
-			dst += 4;
-		}
-	}
-
-	return dst;
-}
-
-static __always_inline bool is_valid_match(const u32 dist, const u32 len)
-{
-	return (dist >= LZ77_MATCH_MIN_DIST && dist < LZ77_MATCH_MAX_DIST) &&
-	       (len >= LZ77_MATCH_MIN_LEN && len < LZ77_MATCH_MAX_LEN);
-}
-
-static __always_inline const u8 *find_match(u32 *htable, const u8 *base, const u8 *cur,
-					    const u8 *end, u32 *best_len)
-{
-	const u8 *match;
-	u32 hash;
-	size_t offset;
-
-	hash = hash3(cur);
-	offset = cur - base;
-
-	if (htable[hash] >= offset)
-		return cur;
-
-	match = base + htable[hash];
-	*best_len = lz77_match(match, cur, end);
-	if (is_valid_match(cur - match, *best_len))
-		return match;
-
-	return cur;
-}
-
-int lz77_compress(const u8 *src, size_t src_len, u8 *dst, size_t *dst_len)
-{
-	const u8 *srcp, *src_end, *anchor;
-	struct lz77_flags flags = { 0 };
-	u8 *dstp, *dst_end, *nib;
-	u32 *htable;
-	int ret;
+	const void *srcp, *end;
+	void *dstp, *nib, *flag_pos;
+	u32 flag_count = 0;
+	long flag = 0;
+	u64 *htable;
 
 	srcp = src;
-	anchor = srcp;
-	src_end = src + src_len;
-
+	end = src + slen;
 	dstp = dst;
-	dst_end = dst + *dst_len;
-	flags.pos = dstp;
 	nib = NULL;
-
-	memset(dstp, 0, *dst_len);
+	flag_pos = dstp;
 	dstp += 4;
 
-	htable = kvcalloc(LZ77_HASH_SIZE, sizeof(u32), GFP_KERNEL);
+	htable = kvcalloc(LZ77_HASH_SIZE, sizeof(*htable), GFP_KERNEL);
 	if (!htable)
 		return -ENOMEM;
 
-	/* fill hashtable with invalid offsets */
-	memset(htable, 0xff, LZ77_HASH_SIZE * sizeof(u32));
+	/* Main loop. */
+	do {
+		u32 dist, len = 0;
+		const void *wnd;
+		u64 hash;
 
-	/* from here on, any error is because @dst_len reached >= @src_len */
-	ret = -EMSGSIZE;
+		hash = ((lz77_read64(srcp) << 24) * 889523592379ULL) >> (64 - LZ77_HASH_LOG);
+		wnd = src + htable[hash];
+		htable[hash] = srcp - src;
+		dist = srcp - wnd;
 
-	/* main loop */
-	while (srcp < src_end) {
-		u32 hash, dist, len;
-		const u8 *match;
+		if (dist && dist < LZ77_MATCH_MAX_DIST)
+			len = lz77_match_len(wnd, srcp, end);
 
-		while (srcp + 3 < src_end) {
-			len = LZ77_MATCH_MIN_LEN - 1;
-			match = find_match(htable, src, srcp, src_end, &len);
-			hash = hash3(srcp);
-			htable[hash] = srcp - src;
+		if (len < LZ77_MATCH_MIN_LEN) {
+			lz77_write8(dstp, lz77_read8(srcp));
+
+			dstp++;
+			srcp++;
 
-			if (likely(match < srcp)) {
-				dist = srcp - match;
-				break;
+			flag <<= 1;
+			flag_count++;
+			if (flag_count == 32) {
+				lz77_write32(flag_pos, flag);
+				flag_count = 0;
+				flag_pos = dstp;
+				dstp += 4;
 			}
 
-			srcp++;
+			continue;
 		}
 
-		dstp = write_literals(dstp, dst_end, anchor, srcp - anchor, &flags);
-		if (IS_ERR(dstp))
-			goto err_free;
-
-		if (srcp + 3 >= src_end)
-			goto leftovers;
+		/*
+		 * Bail out if @dstp reached >= 7/8 of @slen -- already compressed badly, not worth
+		 * going further.
+		 */
+		if (unlikely(dstp - dst >= slen - (slen >> 3))) {
+			*dlen = slen;
+			goto out;
+		}
 
-		dstp = write_match(dstp, &nib, dist, len);
+		dstp = lz77_write_match(dstp, &nib, dist, len);
 		srcp += len;
-		anchor = srcp;
-
-		flags.val = (flags.val << 1) | 1;
-		flags.count++;
-		if (flags.count == 32) {
-			lz77_write32(flags.pos, flags.val);
-			flags.count = 0;
-			flags.pos = dstp;
+
+		flag = (flag << 1) | 1;
+		flag_count++;
+		if (flag_count == 32) {
+			lz77_write32(flag_pos, flag);
+			flag_count = 0;
+			flag_pos = dstp;
+			dstp += 4;
+		}
+	} while (likely(srcp + LZ77_STEP_SIZE < end));
+
+	while (srcp < end) {
+		u32 c = umin(end - srcp, 32 - flag_count);
+
+		memcpy(dstp, srcp, c);
+
+		dstp += c;
+		srcp += c;
+
+		flag <<= c;
+		flag_count += c;
+		if (flag_count == 32) {
+			lz77_write32(flag_pos, flag);
+			flag_count = 0;
+			flag_pos = dstp;
 			dstp += 4;
 		}
-	}
-leftovers:
-	if (srcp < src_end) {
-		dstp = write_literals(dstp, dst_end, srcp, src_end - srcp, &flags);
-		if (IS_ERR(dstp))
-			goto err_free;
 	}
 
-	flags.val <<= (32 - flags.count);
-	flags.val |= (1 << (32 - flags.count)) - 1;
-	lz77_write32(flags.pos, flags.val);
+	flag <<= (32 - flag_count);
+	flag |= (1 << (32 - flag_count)) - 1;
+	lz77_write32(flag_pos, flag);
 
-	*dst_len = dstp - dst;
-	ret = 0;
-err_free:
+	*dlen = dstp - dst;
+out:
 	kvfree(htable);
 
-	return ret;
+	if (*dlen < slen)
+		return 0;
+
+	return -EMSGSIZE;
 }
diff --git a/fs/smb/client/compress/lz77.h b/fs/smb/client/compress/lz77.h
index 3d0d3eaa8ffb..cdcb191b48a2 100644
--- a/fs/smb/client/compress/lz77.h
+++ b/fs/smb/client/compress/lz77.h
@@ -4,283 +4,12 @@
  *
  * Authors: Enzo Matsumiya <ematsumiya@suse.de>
  *
- * Definitions and optmized helpers for LZ77 compression.
+ * Implementation of the LZ77 "plain" compression algorithm, as per MS-XCA spec.
  */
 #ifndef _SMB_COMPRESS_LZ77_H
 #define _SMB_COMPRESS_LZ77_H
 
-#include <linux/uaccess.h>
-#ifdef CONFIG_CIFS_COMPRESSION
-#include <asm/ptrace.h>
 #include <linux/kernel.h>
-#include <linux/string.h>
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#include <asm-generic/unaligned.h>
-#endif
 
-#define LZ77_HASH_LOG		13
-#define LZ77_HASH_SIZE		(1 << LZ77_HASH_LOG)
-#define LZ77_HASH_MASK		lz77_hash_mask(LZ77_HASH_LOG)
-
-/* We can increase this for better compression (but worse performance). */
-#define LZ77_MATCH_MIN_LEN	3
-/* From MS-XCA, but it's arbitrarily chosen. */
-#define LZ77_MATCH_MAX_LEN	S32_MAX
-/*
- * Check this to ensure we don't match the current position, which would
- * end up doing a verbatim copy of the input, and actually overflowing
- * the output buffer because of the encoded metadata.
- */
-#define LZ77_MATCH_MIN_DIST	1
-/* How far back in the buffer can we try to find a match (i.e. window size) */
-#define LZ77_MATCH_MAX_DIST	8192
-
-#define LZ77_STEPSIZE_16	sizeof(u16)
-#define LZ77_STEPSIZE_32	sizeof(u32)
-#define LZ77_STEPSIZE_64	sizeof(u64)
-
-struct lz77_flags {
-	u8 *pos;
-	size_t count;
-	long val;
-};
-
-static __always_inline u32 lz77_hash_mask(const unsigned int log2)
-{
-	return ((1 << log2) - 1);
-}
-
-static __always_inline u32 lz77_hash64(const u64 v, const unsigned int log2)
-{
-	const u64 prime5bytes = 889523592379ULL;
-
-	return (u32)(((v << 24) * prime5bytes) >> (64 - log2));
-}
-
-static __always_inline u32 lz77_hash32(const u32 v, const unsigned int log2)
-{
-	return ((v * 2654435769LL) >> (32 - log2)) & lz77_hash_mask(log2);
-}
-
-static __always_inline u32 lz77_log2(unsigned int x)
-{
-	return x ? ((u32)(31 - __builtin_clz(x))) : 0;
-}
-
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-static __always_inline u8 lz77_read8(const void *ptr)
-{
-	return *(u8 *)ptr;
-}
-
-static __always_inline u16 lz77_read16(const void *ptr)
-{
-	return *(u16 *)ptr;
-}
-
-static __always_inline u32 lz77_read32(const void *ptr)
-{
-	return *(u32 *)ptr;
-}
-
-static __always_inline u64 lz77_read64(const void *ptr)
-{
-	return *(u64 *)ptr;
-}
-
-static __always_inline void lz77_write8(void *ptr, const u8 v)
-{
-	*(u8 *)ptr = v;
-}
-
-static __always_inline void lz77_write16(void *ptr, const u16 v)
-{
-	*(u16 *)ptr = v;
-}
-
-static __always_inline void lz77_write32(void *ptr, const u32 v)
-{
-	*(u32 *)ptr = v;
-}
-
-static __always_inline void lz77_write64(void *ptr, const u64 v)
-{
-	*(u64 *)ptr = v;
-}
-
-static __always_inline void lz77_write_ptr16(void *ptr, const void *vp)
-{
-	*(u16 *)ptr = *(const u16 *)vp;
-}
-
-static __always_inline void lz77_write_ptr32(void *ptr, const void *vp)
-{
-	*(u32 *)ptr = *(const u32 *)vp;
-}
-
-static __always_inline void lz77_write_ptr64(void *ptr, const void *vp)
-{
-	*(u64 *)ptr = *(const u64 *)vp;
-}
-
-static __always_inline long lz77_copy(u8 *dst, const u8 *src, size_t count)
-{
-	return copy_from_kernel_nofault(dst, src, count);
-}
-#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
-static __always_inline u8 lz77_read8(const void *ptr)
-{
-	return get_unaligned((u8 *)ptr);
-}
-
-static __always_inline u16 lz77_read16(const void *ptr)
-{
-	return lz77_read8(ptr) | (lz77_read8(ptr + 1) << 8);
-}
-
-static __always_inline u32 lz77_read32(const void *ptr)
-{
-	return lz77_read16(ptr) | (lz77_read16(ptr + 2) << 16);
-}
-
-static __always_inline u64 lz77_read64(const void *ptr)
-{
-	return lz77_read32(ptr) | ((u64)lz77_read32(ptr + 4) << 32);
-}
-
-static __always_inline void lz77_write8(void *ptr, const u8 v)
-{
-	put_unaligned(v, (u8 *)ptr);
-}
-
-static __always_inline void lz77_write16(void *ptr, const u16 v)
-{
-	lz77_write8(ptr, v & 0xff);
-	lz77_write8(ptr + 1, (v >> 8) & 0xff);
-}
-
-static __always_inline void lz77_write32(void *ptr, const u32 v)
-{
-	lz77_write16(ptr, v & 0xffff);
-	lz77_write16(ptr + 2, (v >> 16) & 0xffff);
-}
-
-static __always_inline void lz77_write64(void *ptr, const u64 v)
-{
-	lz77_write32(ptr, v & 0xffffffff);
-	lz77_write32(ptr + 4, (v >> 32) & 0xffffffff);
-}
-
-static __always_inline void lz77_write_ptr16(void *ptr, const void *vp)
-{
-	const u16 v = lz77_read16(vp);
-
-	lz77_write16(ptr, v);
-}
-
-static __always_inline void lz77_write_ptr32(void *ptr, const void *vp)
-{
-	const u32 v = lz77_read32(vp);
-
-	lz77_write32(ptr, v);
-}
-
-static __always_inline void lz77_write_ptr64(void *ptr, const void *vp)
-{
-	const u64 v = lz77_read64(vp);
-
-	lz77_write64(ptr, v);
-}
-static __always_inline long lz77_copy(u8 *dst, const u8 *src, size_t count)
-{
-	memcpy(dst, src, count);
-	return 0;
-}
-#endif /* !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
-
-static __always_inline unsigned int __count_common_bytes(const unsigned long diff)
-{
-#ifdef __has_builtin
-#  if __has_builtin(__builtin_ctzll)
-	return (unsigned int)__builtin_ctzll(diff) >> 3;
-#  endif
-#else
-	/* count trailing zeroes */
-	unsigned long bits = 0, i, z = 0;
-
-	bits |= diff;
-	for (i = 0; i < 64; i++) {
-		if (bits[i])
-			break;
-		z++;
-	}
-
-	return (unsigned int)z >> 3;
-#endif
-}
-
-static __always_inline size_t lz77_match(const u8 *match, const u8 *cur, const u8 *end)
-{
-	const u8 *start = cur;
-
-	if (cur == match)
-		return 0;
-
-	if (likely(cur < end - (LZ77_STEPSIZE_64 - 1))) {
-		u64 const diff = lz77_read64(cur) ^ lz77_read64(match);
-
-		if (!diff) {
-			cur += LZ77_STEPSIZE_64;
-			match += LZ77_STEPSIZE_64;
-		} else {
-			return __count_common_bytes(diff);
-		}
-	}
-
-	while (likely(cur < end - (LZ77_STEPSIZE_64 - 1))) {
-		u64 const diff = lz77_read64(cur) ^ lz77_read64(match);
-
-		if (!diff) {
-			cur += LZ77_STEPSIZE_64;
-			match += LZ77_STEPSIZE_64;
-			continue;
-		}
-
-		cur += __count_common_bytes(diff);
-		return (size_t)(cur - start);
-	}
-
-	if (cur < end - 3 && !(lz77_read32(cur) ^ lz77_read32(match))) {
-		cur += LZ77_STEPSIZE_32;
-		match += LZ77_STEPSIZE_32;
-	}
-
-	if (cur < end - 1 && lz77_read16(cur) == lz77_read16(match)) {
-		cur += LZ77_STEPSIZE_16;
-		match += LZ77_STEPSIZE_16;
-	}
-
-	if (cur < end && *cur == *match)
-		cur++;
-
-	return (size_t)(cur - start);
-}
-
-static __always_inline unsigned long lz77_max(unsigned long a, unsigned long b)
-{
-	int m = (a < b) - 1;
-
-	return (a & m) | (b & ~m);
-}
-
-static __always_inline unsigned long lz77_min(unsigned long a, unsigned long b)
-{
-	int m = (a > b) - 1;
-
-	return (a & m) | (b & ~m);
-}
-
-int lz77_compress(const u8 *src, size_t src_len, u8 *dst, size_t *dst_len);
-/* when CONFIG_CIFS_COMPRESSION not set lz77_compress() is not called */
-#endif /* !CONFIG_CIFS_COMPRESSION */
+int lz77_compress(const void *src, u32 slen, void *dst, u32 *dlen);
 #endif /* _SMB_COMPRESS_LZ77_H */