[PATCH 3/3] kallsyms: Match compressed tokens on the fly during binary search

[Jim Cromie]

kallsyms_lookup_names() runs a binary search across kallsyms_names[],
a packed array of ~130k encoded kernel symbols.  For each of the ~17
comparisons in the search, it currently decompresses the candidate
symbol into a temporary buffer on the stack before calling strcmp().

Comparing raw tokens directly in compressed space is impossible.  The
BPE token table assigns values by frequency, not alphabetical order
(e.g. token 0x05 might expand to "zebra" while 0x42 expands to "apple"),
so comparing raw token values scrambles lexicographical order.

However, full string expansion is equally wasteful: roughly 16 of the
17 binary search steps fail within the first two characters.

Introduce kallsyms_strcmp_symbol() to compare ASCII queries against
compressed tokens on the fly.  It walks kallsyms_token_index and
kallsyms_token_table incrementally, matching characters directly and
bailing out on the first character mismatch without expanding subsequent
tokens.

This optimization:

0. Avoids decompressing non-matching tokens, short-circuiting ~94% of
   binary search character expansions without adding any tables in
   .rodata.

1. Drops the 512-byte namebuf buffer from the kernel stack in
   kallsyms_lookup_names().

2. Leaves sequential address ordering and kallsyms_expand_symbol()
   streaming invariants intact for /proc/kallsyms and table walks.

Signed-off-by: Jim Cromie <jim.cromie@xxxxxxxxx>
---
 kernel/kallsyms.c | 97 ++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 61 insertions(+), 36 deletions(-)

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 21adc5b74ec5..3be2b4e74057 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -34,6 +34,21 @@
 
 #include "kallsyms_internal.h"
 
+/*
+ * Get the compressed symbol length and data pointer.
+ */
+static inline const u8 *get_symbol_data(unsigned int off, unsigned int *len)
+{
+	const u8 *p = &kallsyms_names[off];
+	unsigned int l = *p++;
+
+	if (unlikely(l & 0x80))
+		l = (l & 0x7F) | (*p++ << 7);
+	*len = l;
+
+	return p;
+}
+
 /*
  * Expand a compressed symbol data into the resulting uncompressed string,
  * if uncompressed string is too long (>= maxlen), it will be truncated,
@@ -42,28 +57,12 @@
 static unsigned int kallsyms_expand_symbol(unsigned int off,
 					   char *result, size_t maxlen)
 {
-	int len, skipped_first = 0;
+	int skipped_first = 0;
 	const char *tptr;
-	const u8 *data;
+	unsigned int len;
+	const u8 *data = get_symbol_data(off, &len);
 
-	/* Get the compressed symbol length from the first symbol byte. */
-	data = &kallsyms_names[off];
-	len = *data;
-	data++;
-	off++;
-
-	/* If MSB is 1, it is a "big" symbol, so needs an additional byte. */
-	if ((len & 0x80) != 0) {
-		len = (len & 0x7F) | (*data << 7);
-		data++;
-		off++;
-	}
-
-	/*
-	 * Update the offset to return the offset for the next symbol on
-	 * the compressed stream.
-	 */
-	off += len;
+	off = (data - kallsyms_names) + len;
 
 	/*
 	 * For every byte on the compressed symbol data, copy the table
@@ -91,7 +90,7 @@ static unsigned int kallsyms_expand_symbol(unsigned int off,
 	if (maxlen)
 		*result = '\0';
 
-	/* Return to offset to the next symbol. */
+	/* Return offset to the next symbol. */
 	return off;
 }
 
@@ -101,16 +100,46 @@ static unsigned int kallsyms_expand_symbol(unsigned int off,
  */
 static char kallsyms_get_symbol_type(unsigned int off)
 {
-	/*
-	 * Get just the first code, look it up in the token table,
-	 * and return the first char from this token. If MSB of length
-	 * is 1, it is a "big" symbol, so needs an additional byte.
-	 */
-	if (kallsyms_names[off] & 0x80)
-		off++;
-	return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
+	unsigned int len;
+	const u8 *data = get_symbol_data(off, &len);
+
+	return kallsyms_token_table[kallsyms_token_index[*data]];
 }
 
+/*
+ * Compare an uncompressed ASCII string against a compressed symbol table entry.
+ * Returns negative if name < sym, positive if name > sym, 0 if equal.
+ * Exits immediately on the first mismatched character without decompressing
+ * the rest of the symbol name.
+ */
+static int kallsyms_strcmp_symbol(unsigned int off, const char *name)
+{
+	int skipped_first = 0;
+	const char *tptr;
+	unsigned int len;
+	const u8 *data = get_symbol_data(off, &len);
+
+	while (len) {
+		tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
+		data++;
+		len--;
+
+		while (*tptr) {
+			if (skipped_first) {
+				int diff = (unsigned char)*name - (unsigned char)*tptr;
+
+				if (diff != 0)
+					return diff;
+				name++;
+			} else {
+				skipped_first = 1;
+			}
+			tptr++;
+		}
+	}
+
+	return (unsigned char)*name - '\0';
+}
 
 /*
  * Find the offset on the compressed table given an index in the
@@ -145,7 +174,6 @@ static int kallsyms_lookup_names(const char *name,
 	int ret;
 	int low, mid, high;
 	unsigned int seq, off;
-	char namebuf[KSYM_NAME_LEN];
 
 	low = 0;
 	high = kallsyms_num_syms - 1;
@@ -154,8 +182,7 @@ static int kallsyms_lookup_names(const char *name,
 		mid = low + (high - low) / 2;
 		seq = get_symbol_seq(mid);
 		off = get_symbol_offset(seq);
-		kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-		ret = strcmp(name, namebuf);
+		ret = kallsyms_strcmp_symbol(off, name);
 		if (ret > 0)
 			low = mid + 1;
 		else if (ret < 0)
@@ -171,8 +198,7 @@ static int kallsyms_lookup_names(const char *name,
 	while (low) {
 		seq = get_symbol_seq(low - 1);
 		off = get_symbol_offset(seq);
-		kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-		if (strcmp(name, namebuf))
+		if (kallsyms_strcmp_symbol(off, name) != 0)
 			break;
 		low--;
 	}
@@ -183,8 +209,7 @@ static int kallsyms_lookup_names(const char *name,
 		while (high < kallsyms_num_syms - 1) {
 			seq = get_symbol_seq(high + 1);
 			off = get_symbol_offset(seq);
-			kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-			if (strcmp(name, namebuf))
+			if (kallsyms_strcmp_symbol(off, name) != 0)
 				break;
 			high++;
 		}

-- 
2.55.0