ldso : gnu hash support.

ldso : gnu hash support.

[boris brezillon]

Hi,

This patch adds support for gnu hash section (this was requested in a
previous mail : hm, libc crashes loading libc).
I've done some tests and it seems to work (algorithm described here :
https://blogs.oracle.com/ali/entry/gnu_hash_elf_sections).

BTW, I really like this new libc (clean code, light and efficient
implementation).
I plan to use it in my future projects and I'd like to contribute to
it's development.
Let me know if you need some help.

Regards,

Boris Brezillon


---
 src/ldso/dynlink.c |  125 +++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 115 insertions(+), 10 deletions(-)

diff --git a/src/ldso/dynlink.c b/src/ldso/dynlink.c
index 31ef684..0c8d75a 100644
--- a/src/ldso/dynlink.c
+++ b/src/ldso/dynlink.c
@@ -52,6 +52,7 @@ struct dso {

  int refcnt;
  Sym *syms;
+ uint32_t hashalg;
  uint32_t *hashtab;
  char *strings;
  unsigned char *map;
@@ -66,6 +67,15 @@ struct dso {
  char buf[];
 };

+struct hash_algo {
+ uint32_t (*hash) (const char *);
+ Sym *(*lookup) (const char *s, uint32_t h, struct dso *dso);
+};
+
+#define SYSV_HASH_ALG_IDX   0
+#define GNU_HASH_ALG_IDX    1
+#define HASH_ALG_CNT        2
+
 #include "reloc.h"

 void __init_ssp(size_t *);
@@ -94,7 +104,7 @@ static void decode_vec(size_t *v, size_t *a, size_t cnt)
  }
 }

-static uint32_t hash(const char *s0)
+static uint32_t sysv_hash(const char *s0)
 {
  const unsigned char *s = (void *)s0;
  uint_fast32_t h = 0;
@@ -105,7 +115,16 @@ static uint32_t hash(const char *s0)
  return h & 0xfffffff;
 }

-static Sym *lookup(const char *s, uint32_t h, struct dso *dso)
+static uint32_t gnu_hash (const char *s0)
+{
+ const unsigned char *s = (void *)s0;
+ uint_fast32_t h = 5381;
+ for (unsigned char c = *s; c != '\0'; c = *++s)
+ h = h * 33 + c;
+ return h & 0xffffffff;
+}
+
+static Sym *sysv_lookup(const char *s, uint32_t h, struct dso *dso)
 {
  size_t i;
  Sym *syms = dso->syms;
@@ -118,20 +137,86 @@ static Sym *lookup(const char *s, uint32_t h,
struct dso *dso)
  return 0;
 }

+static Sym *gnu_lookup(const char *s, uint32_t h1, struct dso *dso)
+{
+ size_t i;
+ Sym *sym;
+ char *strings = dso->strings;
+ uint32_t *hashtab = dso->hashtab;
+ uint32_t nbuckets = hashtab[0];
+ size_t *maskwords = (size_t *)(hashtab + 4);
+ uint32_t *buckets = hashtab + 4 + (hashtab[2] * (sizeof(size_t) /
sizeof(uint32_t)));
+ uint32_t symndx = hashtab[1];
+ Sym *syms = dso->syms;
+ uint32_t shift2 = hashtab[3];
+ uint32_t h2 = h1 >> shift2;
+ uint32_t *hashvals = buckets + nbuckets;
+ uint32_t *hashval;
+ size_t c = sizeof(size_t) * 8;
+ size_t n = (h1 / c) & (hashtab[2] - 1);
+ size_t bitmask = (1 << (h1 % c)) | (1 << (h2 % c));
+
+ if ((maskwords[n] & bitmask) != bitmask)
+ return 0;
+
+ n = buckets[h1 % nbuckets];
+ if (!n)
+ return 0;
+
+ sym = syms + n;
+ hashval = hashvals + n - symndx;
+
+ for (h1 &= ~1; 1; sym++) {
+ h2 = *hashval++;
+ if ((h1 == (h2 & ~1)) && !strcmp(s, strings + sym->st_name))
+ return sym;
+
+ if (h2 & 1)
+ break;
+ }
+
+ return 0;
+}
+
+static struct hash_algo hashalgs[] = {
+ {
+ .hash = sysv_hash,
+ .lookup = sysv_lookup,
+ },
+ {
+ .hash = gnu_hash,
+ .lookup = gnu_lookup,
+ },
+};
+
+
 #define OK_TYPES (1<<STT_NOTYPE | 1<<STT_OBJECT | 1<<STT_FUNC | 1<<STT_COMMON)
 #define OK_BINDS (1<<STB_GLOBAL | 1<<STB_WEAK)

 static void *find_sym(struct dso *dso, const char *s, int need_def)
 {
- uint32_t h = hash(s);
  void *def = 0;
- if (h==0x6b366be && !strcmp(s, "dlopen")) rtld_used = 1;
- if (h==0x6b3afd && !strcmp(s, "dlsym")) rtld_used = 1;
- if (h==0x595a4cc && !strcmp(s, "__stack_chk_fail")) ssp_used = 1;
+ uint32_t computed[HASH_ALG_CNT / 32 + 1];
+ uint32_t hashes[HASH_ALG_CNT];
+ memset (computed, 0, sizeof (computed));
+ if (!strcmp(s, "dlopen")) rtld_used = 1;
+ if (!strcmp(s, "dlsym")) rtld_used = 1;
+ if (!strcmp(s, "__stack_chk_fail")) ssp_used = 1;
  for (; dso; dso=dso->next) {
  Sym *sym;
+ uint32_t h;
  if (!dso->global) continue;
- sym = lookup(s, h, dso);
+
+ if (!(computed[dso->hashalg / 32] & (1 << (dso->hashalg % 32)))) {
+ h = hashalgs[dso->hashalg].hash(s);
+ hashes[dso->hashalg] = h;
+ computed[dso->hashalg / 32] |= (1 << (dso->hashalg % 32));
+ }
+ else {
+ h = hashes[dso->hashalg];
+ }
+
+ sym = hashalgs[dso->hashalg].lookup(s, h, dso);
  if (sym && (!need_def || sym->st_shndx) && sym->st_value
  && (1<<(sym->st_info&0xf) & OK_TYPES)
  && (1<<(sym->st_info>>4) & OK_BINDS)) {
@@ -320,11 +405,17 @@ static int path_open(const char *name, const
char *search, char *buf, size_t buf

 static void decode_dyn(struct dso *p)
 {
+ size_t *v = p->dynv;
  size_t dyn[DYN_CNT] = {0};
  decode_vec(p->dynv, dyn, DYN_CNT);
  p->syms = (void *)(p->base + dyn[DT_SYMTAB]);
  p->hashtab = (void *)(p->base + dyn[DT_HASH]);
+ p->hashalg = SYSV_HASH_ALG_IDX;
  p->strings = (void *)(p->base + dyn[DT_STRTAB]);
+ for (; v[0]; v+=2) if (v[0] == DT_GNU_HASH) {
+ p->hashtab = (void *)(p->base + v[1]);
+ p->hashalg = GNU_HASH_ALG_IDX;
+ }
 }

 static struct dso *load_library(const char *name)
@@ -786,6 +877,9 @@ static void *do_dlsym(struct dso *p, const char
*s, void *ra)
  size_t i;
  uint32_t h;
  Sym *sym;
+ uint32_t computed[HASH_ALG_CNT / 32 + 1];
+ uint32_t hashes[HASH_ALG_CNT];
+
  if (p == RTLD_NEXT) {
  for (p=head; p && (unsigned char *)ra-p->map>p->map_len; p=p->next);
  if (!p) p=head;
@@ -798,12 +892,23 @@ static void *do_dlsym(struct dso *p, const char
*s, void *ra)
  if (!res) goto failed;
  return res;
  }
- h = hash(s);
- sym = lookup(s, h, p);
+ memset (computed, 0, sizeof (computed));
+ h = hashalgs[p->hashalg].hash(s);
+ computed[p->hashalg / 32] |= (1 << (p->hashalg % 32));
+ hashes[p->hashalg] = h;
+ sym = hashalgs[p->hashalg].lookup(s, h, p);
  if (sym && sym->st_value && (1<<(sym->st_info&0xf) & OK_TYPES))
  return p->base + sym->st_value;
  if (p->deps) for (i=0; p->deps[i]; i++) {
- sym = lookup(s, h, p);
+ if (!(computed[p->deps[i]->hashalg / 32] & (1 <<
(p->deps[i]->hashalg % 32)))) {
+ h = hashalgs[p->deps[i]->hashalg].hash(s);
+ hashes[p->deps[i]->hashalg] = h;
+ computed[p->deps[i]->hashalg / 32] |= (1 << (p->deps[i]->hashalg % 32));
+ }
+ else {
+ h = hashes[p->deps[i]->hashalg];
+ }
+ sym = hashalgs[p->deps[i]->hashalg].lookup(s, h, p->deps[i]);
  if (sym && sym->st_value && (1<<(sym->st_info&0xf) & OK_TYPES))
  return p->deps[i]->base + sym->st_value;
  }
-- 
1.7.9.5

Re: ldso : gnu hash support.

[boris brezillon]

[-- Attachment #1: Type: text/plain, Size: 270 bytes --]

Sure

2012/8/7 John Spencer <maillist-musl@barfooze.de>:
> On 08/07/2012 12:49 AM, boris brezillon wrote:
>>
>> Hi,
>>
>> This patch adds support for gnu hash section
>
>
> the indentation seems to be messed up.. can you resend with the patch as a
> file attachment ?
>

[-- Attachment #2: 0001-Add-gnu-hash-support.patch --]
[-- Type: application/octet-stream, Size: 6101 bytes --]

From 28edcc77f5096d17be29da1be1c3972c2356d269 Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <b.brezillon@overkiz.com>
Date: Mon, 6 Aug 2012 20:17:01 +0200
Subject: [PATCH] Add gnu hash support.

---
 src/ldso/dynlink.c |  125 +++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 115 insertions(+), 10 deletions(-)

diff --git a/src/ldso/dynlink.c b/src/ldso/dynlink.c
index 31ef684..0c8d75a 100644
--- a/src/ldso/dynlink.c
+++ b/src/ldso/dynlink.c
@@ -52,6 +52,7 @@ struct dso {
 
 	int refcnt;
 	Sym *syms;
+	uint32_t hashalg;
 	uint32_t *hashtab;
 	char *strings;
 	unsigned char *map;
@@ -66,6 +67,15 @@ struct dso {
 	char buf[];
 };
 
+struct hash_algo {
+	uint32_t (*hash) (const char *);
+	Sym *(*lookup) (const char *s, uint32_t h, struct dso *dso);
+};
+
+#define SYSV_HASH_ALG_IDX   0
+#define GNU_HASH_ALG_IDX    1
+#define HASH_ALG_CNT        2
+
 #include "reloc.h"
 
 void __init_ssp(size_t *);
@@ -94,7 +104,7 @@ static void decode_vec(size_t *v, size_t *a, size_t cnt)
 	}
 }
 
-static uint32_t hash(const char *s0)
+static uint32_t sysv_hash(const char *s0)
 {
 	const unsigned char *s = (void *)s0;
 	uint_fast32_t h = 0;
@@ -105,7 +115,16 @@ static uint32_t hash(const char *s0)
 	return h & 0xfffffff;
 }
 
-static Sym *lookup(const char *s, uint32_t h, struct dso *dso)
+static uint32_t gnu_hash (const char *s0)
+{
+	const unsigned char *s = (void *)s0;
+	uint_fast32_t h = 5381;
+	for (unsigned char c = *s; c != '\0'; c = *++s)
+		h = h * 33 + c;
+	return h & 0xffffffff;
+}
+
+static Sym *sysv_lookup(const char *s, uint32_t h, struct dso *dso)
 {
 	size_t i;
 	Sym *syms = dso->syms;
@@ -118,20 +137,86 @@ static Sym *lookup(const char *s, uint32_t h, struct dso *dso)
 	return 0;
 }
 
+static Sym *gnu_lookup(const char *s, uint32_t h1, struct dso *dso)
+{
+	size_t i;
+	Sym *sym;
+	char *strings = dso->strings;
+	uint32_t *hashtab = dso->hashtab;
+	uint32_t nbuckets = hashtab[0];
+	size_t *maskwords = (size_t *)(hashtab + 4);
+	uint32_t *buckets = hashtab + 4 + (hashtab[2] * (sizeof(size_t) / sizeof(uint32_t)));
+	uint32_t symndx = hashtab[1];
+	Sym *syms = dso->syms;
+	uint32_t shift2 = hashtab[3];
+	uint32_t h2 = h1 >> shift2;
+	uint32_t *hashvals = buckets + nbuckets;
+	uint32_t *hashval;
+	size_t c = sizeof(size_t) * 8;
+	size_t n = (h1 / c) & (hashtab[2] - 1);
+	size_t bitmask = (1 << (h1 % c)) | (1 << (h2 % c));
+
+	if ((maskwords[n] & bitmask) != bitmask)
+		return 0;
+
+	n = buckets[h1 % nbuckets];
+	if (!n)
+		return 0;
+
+	sym = syms + n;
+	hashval = hashvals + n - symndx;
+
+	for (h1 &= ~1; 1; sym++) {
+		h2 = *hashval++;
+		if ((h1 == (h2 & ~1)) && !strcmp(s, strings + sym->st_name))
+			return sym;
+
+		if (h2 & 1)
+			break;
+	}
+
+	return 0;
+}
+
+static struct hash_algo hashalgs[] = {
+	{
+		.hash = sysv_hash,
+		.lookup = sysv_lookup,
+	},
+	{
+		.hash = gnu_hash,
+		.lookup = gnu_lookup,
+	},
+};
+
+
 #define OK_TYPES (1<<STT_NOTYPE | 1<<STT_OBJECT | 1<<STT_FUNC | 1<<STT_COMMON)
 #define OK_BINDS (1<<STB_GLOBAL | 1<<STB_WEAK)
 
 static void *find_sym(struct dso *dso, const char *s, int need_def)
 {
-	uint32_t h = hash(s);
 	void *def = 0;
-	if (h==0x6b366be && !strcmp(s, "dlopen")) rtld_used = 1;
-	if (h==0x6b3afd && !strcmp(s, "dlsym")) rtld_used = 1;
-	if (h==0x595a4cc && !strcmp(s, "__stack_chk_fail")) ssp_used = 1;
+	uint32_t computed[HASH_ALG_CNT / 32 + 1];
+	uint32_t hashes[HASH_ALG_CNT];
+	memset (computed, 0, sizeof (computed));
+	if (!strcmp(s, "dlopen")) rtld_used = 1;
+	if (!strcmp(s, "dlsym")) rtld_used = 1;
+	if (!strcmp(s, "__stack_chk_fail")) ssp_used = 1;
 	for (; dso; dso=dso->next) {
 		Sym *sym;
+		uint32_t h;
 		if (!dso->global) continue;
-		sym = lookup(s, h, dso);
+
+		if (!(computed[dso->hashalg / 32] & (1 << (dso->hashalg % 32)))) {
+			h = hashalgs[dso->hashalg].hash(s);
+			hashes[dso->hashalg] = h;
+			computed[dso->hashalg / 32] |= (1 << (dso->hashalg % 32));
+		}
+		else {
+			h = hashes[dso->hashalg];
+		}
+
+		sym = hashalgs[dso->hashalg].lookup(s, h, dso);
 		if (sym && (!need_def || sym->st_shndx) && sym->st_value
 		 && (1<<(sym->st_info&0xf) & OK_TYPES)
 		 && (1<<(sym->st_info>>4) & OK_BINDS)) {
@@ -320,11 +405,17 @@ static int path_open(const char *name, const char *search, char *buf, size_t buf
 
 static void decode_dyn(struct dso *p)
 {
+	size_t *v = p->dynv;
 	size_t dyn[DYN_CNT] = {0};
 	decode_vec(p->dynv, dyn, DYN_CNT);
 	p->syms = (void *)(p->base + dyn[DT_SYMTAB]);
 	p->hashtab = (void *)(p->base + dyn[DT_HASH]);
+	p->hashalg = SYSV_HASH_ALG_IDX;
 	p->strings = (void *)(p->base + dyn[DT_STRTAB]);
+	for (; v[0]; v+=2) if (v[0] == DT_GNU_HASH) {
+		p->hashtab = (void *)(p->base + v[1]);
+		p->hashalg = GNU_HASH_ALG_IDX;
+	}
 }
 
 static struct dso *load_library(const char *name)
@@ -786,6 +877,9 @@ static void *do_dlsym(struct dso *p, const char *s, void *ra)
 	size_t i;
 	uint32_t h;
 	Sym *sym;
+	uint32_t computed[HASH_ALG_CNT / 32 + 1];
+	uint32_t hashes[HASH_ALG_CNT];
+
 	if (p == RTLD_NEXT) {
 		for (p=head; p && (unsigned char *)ra-p->map>p->map_len; p=p->next);
 		if (!p) p=head;
@@ -798,12 +892,23 @@ static void *do_dlsym(struct dso *p, const char *s, void *ra)
 		if (!res) goto failed;
 		return res;
 	}
-	h = hash(s);
-	sym = lookup(s, h, p);
+	memset (computed, 0, sizeof (computed));
+	h = hashalgs[p->hashalg].hash(s);
+	computed[p->hashalg / 32] |= (1 << (p->hashalg % 32));
+	hashes[p->hashalg] = h;
+	sym = hashalgs[p->hashalg].lookup(s, h, p);
 	if (sym && sym->st_value && (1<<(sym->st_info&0xf) & OK_TYPES))
 		return p->base + sym->st_value;
 	if (p->deps) for (i=0; p->deps[i]; i++) {
-		sym = lookup(s, h, p);
+		if (!(computed[p->deps[i]->hashalg / 32] & (1 << (p->deps[i]->hashalg % 32)))) {
+			h = hashalgs[p->deps[i]->hashalg].hash(s);
+			hashes[p->deps[i]->hashalg] = h;
+			computed[p->deps[i]->hashalg / 32] |= (1 << (p->deps[i]->hashalg % 32));
+		}
+		else {
+			h = hashes[p->deps[i]->hashalg];
+		}
+		sym = hashalgs[p->deps[i]->hashalg].lookup(s, h, p->deps[i]);
 		if (sym && sym->st_value && (1<<(sym->st_info&0xf) & OK_TYPES))
 			return p->deps[i]->base + sym->st_value;
 	}
-- 
1.7.9.5

Re: ldso : gnu hash support.

[John Spencer]

On 08/07/2012 12:49 AM, boris brezillon wrote:
> Hi,
>
> This patch adds support for gnu hash section

the indentation seems to be messed up.. can you resend with the patch as 
a file attachment ?