On Wed, 2024-08-14 at 20:26 -0700, Fangrui Song wrote:
> glibc added support for DT_GNU_HASH in 2006 and DT_HASH has been
> obsoleted for more than one decade in many Linux distributions.
>
> Many vDSOs support DT_GNU_HASH. This patch adds selftests support.
>
> Signed-off-by: Fangrui Song <maskray@xxxxxxxxxx>
> ---
Ping.
Some context: I'd change LoongArch vDSO to use the toolchain default
instead of forcing DT_HASH (note that LoongArch is launched decades
after all major distros switched to DT_GNU_HASH), but without the
selftest support we'll lose test coverage.
And now ARM64 has already lost test coverage after commit 48f6430505c0.
> tools/testing/selftests/vDSO/parse_vdso.c | 105 ++++++++++++++++-----
> -
> 1 file changed, 79 insertions(+), 26 deletions(-)
>
> diff --git a/tools/testing/selftests/vDSO/parse_vdso.c
> b/tools/testing/selftests/vDSO/parse_vdso.c
> index 4ae417372e9e..35cb545da13e 100644
> --- a/tools/testing/selftests/vDSO/parse_vdso.c
> +++ b/tools/testing/selftests/vDSO/parse_vdso.c
> @@ -47,6 +47,7 @@ static struct vdso_info
> /* Symbol table */
> ELF(Sym) *symtab;
> const char *symstrings;
> + ELF(Word) *gnu_hash;
> ELF(Word) *bucket, *chain;
> ELF(Word) nbucket, nchain;
>
> @@ -75,6 +76,16 @@ static unsigned long elf_hash(const char *name)
> return h;
> }
>
> +static uint32_t gnu_hash(const char *name)
> +{
> + const unsigned char *s = (void *)name;
> + uint32_t h = 5381;
> +
> + for (; *s; s++)
> + h += h * 32 + *s;
> + return h;
> +}
> +
> void vdso_init_from_sysinfo_ehdr(uintptr_t base)
> {
> size_t i;
> @@ -117,6 +128,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
> */
> ELF(Word) *hash = 0;
> vdso_info.symstrings = 0;
> + vdso_info.gnu_hash = 0;
> vdso_info.symtab = 0;
> vdso_info.versym = 0;
> vdso_info.verdef = 0;
> @@ -137,6 +149,11 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
> ((uintptr_t)dyn[i].d_un.d_ptr
> + vdso_info.load_offset);
> break;
> + case DT_GNU_HASH:
> + vdso_info.gnu_hash =
> + (ELF(Word)
> *)((uintptr_t)dyn[i].d_un.d_ptr +
> + vdso_info.load_offset);
> + break;
> case DT_VERSYM:
> vdso_info.versym = (ELF(Versym) *)
> ((uintptr_t)dyn[i].d_un.d_ptr
> @@ -149,17 +166,26 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
> break;
> }
> }
> - if (!vdso_info.symstrings || !vdso_info.symtab || !hash)
> + if (!vdso_info.symstrings || !vdso_info.symtab ||
> + (!hash && !vdso_info.gnu_hash))
> return; /* Failed */
>
> if (!vdso_info.verdef)
> vdso_info.versym = 0;
>
> /* Parse the hash table header. */
> - vdso_info.nbucket = hash[0];
> - vdso_info.nchain = hash[1];
> - vdso_info.bucket = &hash[2];
> - vdso_info.chain = &hash[vdso_info.nbucket + 2];
> + if (vdso_info.gnu_hash) {
> + vdso_info.nbucket = vdso_info.gnu_hash[0];
> + /* The bucket array is located after the header (4
> uint32) and the bloom
> + filter (size_t array of gnu_hash[2] elements). */
> + vdso_info.bucket = vdso_info.gnu_hash + 4 +
> + sizeof(size_t) / 4 *
> vdso_info.gnu_hash[2];
> + } else {
> + vdso_info.nbucket = hash[0];
> + vdso_info.nchain = hash[1];
> + vdso_info.bucket = &hash[2];
> + vdso_info.chain = &hash[vdso_info.nbucket + 2];
> + }
>
> /* That's all we need. */
> vdso_info.valid = true;
> @@ -203,6 +229,26 @@ static bool vdso_match_version(ELF(Versym) ver,
> && !strcmp(name, vdso_info.symstrings + aux-
> >vda_name);
> }
>
> +static bool check_sym(ELF(Sym) *sym, ELF(Word) i, const char *name,
> + const char *version, unsigned long ver_hash)
> +{
> + /* Check for a defined global or weak function w/ right name.
> */
> + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
> + return false;
> + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
> + ELF64_ST_BIND(sym->st_info) != STB_WEAK)
> + return false;
> + if (strcmp(name, vdso_info.symstrings + sym->st_name))
> + return false;
> +
> + /* Check symbol version. */
> + if (vdso_info.versym &&
> + !vdso_match_version(vdso_info.versym[i], version,
> ver_hash))
> + return false;
> +
> + return true;
> +}
> +
> void *vdso_sym(const char *version, const char *name)
> {
> unsigned long ver_hash;
> @@ -210,29 +256,36 @@ void *vdso_sym(const char *version, const char
> *name)
> return 0;
>
> ver_hash = elf_hash(version);
> - ELF(Word) chain = vdso_info.bucket[elf_hash(name) %
> vdso_info.nbucket];
> + ELF(Word) i;
>
> - for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
> - ELF(Sym) *sym = &vdso_info.symtab[chain];
> + if (vdso_info.gnu_hash) {
> + uint32_t h1 = gnu_hash(name), h2, *hashval;
>
> - /* Check for a defined global or weak function w/
> right name. */
> - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
> - continue;
> - if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
> - ELF64_ST_BIND(sym->st_info) != STB_WEAK)
> - continue;
> - if (sym->st_shndx == SHN_UNDEF)
> - continue;
> - if (strcmp(name, vdso_info.symstrings + sym-
> >st_name))
> - continue;
> -
> - /* Check symbol version. */
> - if (vdso_info.versym
> - && !vdso_match_version(vdso_info.versym[chain],
> - version, ver_hash))
> - continue;
> -
> - return (void *)(vdso_info.load_offset + sym-
> >st_value);
> + i = vdso_info.bucket[h1 % vdso_info.nbucket];
> + if (i == 0)
> + return 0;
> + h1 |= 1;
> + hashval = vdso_info.bucket + vdso_info.nbucket +
> + (i - vdso_info.gnu_hash[1]);
> + for (;; i++) {
> + ELF(Sym) *sym = &vdso_info.symtab[i];
> + h2 = *hashval++;
> + if (h1 == (h2 | 1) &&
> + check_sym(sym, i, name, version,
> ver_hash))
> + return (void *)(vdso_info.load_offset
> +
> + sym->st_value);
> + if (h2 & 1)
> + break;
> + }
> + } else {
> + i = vdso_info.bucket[elf_hash(name) %
> vdso_info.nbucket];
> + for (; i; i = vdso_info.chain[i]) {
> + ELF(Sym) *sym = &vdso_info.symtab[i];
> + if (sym->st_shndx != SHN_UNDEF &&
> + check_sym(sym, i, name, version,
> ver_hash))
> + return (void *)(vdso_info.load_offset
> +
> + sym->st_value);
> + }
> }
>
> return 0;
--
Xi Ruoyao <xry111@xxxxxxxxxxx>
School of Aerospace Science and Technology, Xidian University
