@@ -46,6 +46,8 @@ ENTRY (__longjmp)
cfi_offset(d14, JB_D14<<3)
cfi_offset(d15, JB_D15<<3)
+ DELOUSE (0)
+
ldp x19, x20, [x0, #JB_X19<<3]
ldp x21, x22, [x0, #JB_X21<<3]
ldp x23, x24, [x0, #JB_X23<<3]
@@ -53,7 +55,7 @@ ENTRY (__longjmp)
ldp x27, x28, [x0, #JB_X27<<3]
#ifdef PTR_DEMANGLE
ldp x29, x4, [x0, #JB_X29<<3]
- PTR_DEMANGLE (x30, x4, x3, x2)
+ PTR_DEMANGLE (30, 4, 3, 2)
#else
ldp x29, x30, [x0, #JB_X29<<3]
#endif
@@ -98,7 +100,7 @@ ENTRY (__longjmp)
cfi_same_value(d15)
#ifdef PTR_DEMANGLE
ldr x4, [x0, #JB_SP<<3]
- PTR_DEMANGLE (x5, x4, x3, x2)
+ PTR_DEMANGLE (5, 4, 3, 2)
#else
ldr x5, [x0, #JB_SP<<3]
#endif
@@ -39,6 +39,7 @@
they can be called as functions. The symbols _init and _fini are
magic and cause the linker to emit DT_INIT and DT_FINI. */
+#include <sysdep.h>
#include <libc-symbols.h>
#ifndef PREINIT_FUNCTION
@@ -60,7 +61,7 @@
.type call_weak_fn, %function
call_weak_fn:
adrp x0, :got:PREINIT_FUNCTION
- ldr x0, [x0, #:got_lo12:PREINIT_FUNCTION]
+ ldr PTR_REG (0), [x0, #:got_lo12:PREINIT_FUNCTION]
cbz x0, 1f
b PREINIT_FUNCTION
1:
@@ -23,6 +23,7 @@
#include <stdio.h>
#include <unistd.h>
#include <ldsodefs.h>
+#include <sysdep.h>
#define ELF_MACHINE_IRELA 1
@@ -40,7 +41,7 @@ elf_irela (const ElfW(Rela) *reloc)
ElfW(Addr) *const reloc_addr = (void *) reloc->r_offset;
const unsigned long int r_type = ELFW(R_TYPE) (reloc->r_info);
- if (__glibc_likely (r_type == R_AARCH64_IRELATIVE))
+ if (__glibc_likely (r_type == AARCH64_R (IRELATIVE)))
{
ElfW(Addr) value = elf_ifunc_invoke (reloc->r_addend);
*reloc_addr = value;
@@ -21,6 +21,7 @@
#define ELF_MACHINE_NAME "aarch64"
+#include <sysdep.h>
#include <tls.h>
#include <dl-tlsdesc.h>
#include <dl-irel.h>
@@ -53,19 +54,33 @@ elf_machine_load_address (void)
by constructing a non GOT reference to the symbol, the dynamic
address of the symbol we compute using adrp/add to compute the
symbol's address relative to the PC.
- This depends on 32bit relocations being resolved at link time
- and that the static address fits in the 32bits. */
+ This depends on 32/16bit relocations being resolved at link time
+ and that the static address fits in the 32/16 bits. */
ElfW(Addr) static_addr;
ElfW(Addr) dynamic_addr;
asm (" \n"
" adrp %1, _dl_start; \n"
+#ifdef __LP64__
" add %1, %1, #:lo12:_dl_start \n"
+#else
+" add %w1, %w1, #:lo12:_dl_start \n"
+#endif
" ldr %w0, 1f \n"
" b 2f \n"
"1: \n"
+#ifdef __LP64__
" .word _dl_start \n"
+#else
+# ifdef __AARCH64EB__
+" .short 0 \n"
+# endif
+" .short _dl_start \n"
+# ifndef __AARCH64EB__
+" .short 0 \n"
+# endif
+#endif
"2: \n"
: "=r" (static_addr), "=r" (dynamic_addr));
return dynamic_addr - static_addr;
@@ -125,80 +140,86 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
/* Initial entry point for the dynamic linker. The C function
_dl_start is the real entry point, its return value is the user
program's entry point */
+#ifdef __LP64__
+# define RTLD_START RTLD_START_1 ("x", "3", "sp")
+#else
+# define RTLD_START RTLD_START_1 ("w", "2", "wsp")
+#endif
-#define RTLD_START asm ("\
-.text \n\
-.globl _start \n\
-.type _start, %function \n\
-.globl _dl_start_user \n\
-.type _dl_start_user, %function \n\
-_start: \n\
- mov x0, sp \n\
- bl _dl_start \n\
- // returns user entry point in x0 \n\
- mov x21, x0 \n\
-_dl_start_user: \n\
- // get the original arg count \n\
- ldr x1, [sp] \n\
- // get the argv address \n\
- add x2, sp, #8 \n\
- // get _dl_skip_args to see if we were \n\
- // invoked as an executable \n\
- adrp x4, _dl_skip_args \n\
- ldr w4, [x4, #:lo12:_dl_skip_args] \n\
- // do we need to adjust argc/argv \n\
- cmp w4, 0 \n\
- beq .L_done_stack_adjust \n\
- // subtract _dl_skip_args from original arg count \n\
- sub x1, x1, x4 \n\
- // store adjusted argc back to stack \n\
- str x1, [sp] \n\
- // find the first unskipped argument \n\
- mov x3, x2 \n\
- add x4, x2, x4, lsl #3 \n\
- // shuffle argv down \n\
-1: ldr x5, [x4], #8 \n\
- str x5, [x3], #8 \n\
- cmp x5, #0 \n\
- bne 1b \n\
- // shuffle envp down \n\
-1: ldr x5, [x4], #8 \n\
- str x5, [x3], #8 \n\
- cmp x5, #0 \n\
- bne 1b \n\
- // shuffle auxv down \n\
-1: ldp x0, x5, [x4, #16]! \n\
- stp x0, x5, [x3], #16 \n\
- cmp x0, #0 \n\
- bne 1b \n\
- // Update _dl_argv \n\
- adrp x3, _dl_argv \n\
- str x2, [x3, #:lo12:_dl_argv] \n\
-.L_done_stack_adjust: \n\
- // compute envp \n\
- add x3, x2, x1, lsl #3 \n\
- add x3, x3, #8 \n\
- adrp x16, _rtld_local \n\
- add x16, x16, #:lo12:_rtld_local \n\
- ldr x0, [x16] \n\
- bl _dl_init \n\
- // load the finalizer function \n\
- adrp x0, _dl_fini \n\
- add x0, x0, #:lo12:_dl_fini \n\
- // jump to the user_s entry point \n\
- br x21 \n\
+
+#define RTLD_START_1(PTR, PTR_SIZE_LOG, PTR_SP) asm ("\
+.text \n\
+.globl _start \n\
+.type _start, %function \n\
+.globl _dl_start_user \n\
+.type _dl_start_user, %function \n\
+_start: \n\
+ mov " PTR "0, " PTR_SP " \n\
+ bl _dl_start \n\
+ // returns user entry point in x0 \n\
+ mov x21, x0 \n\
+_dl_start_user: \n\
+ // get the original arg count \n\
+ ldr " PTR "1, [sp] \n\
+ // get the argv address \n\
+ add " PTR "2, " PTR_SP ", #(1<<" PTR_SIZE_LOG ") \n\
+ // get _dl_skip_args to see if we were \n\
+ // invoked as an executable \n\
+ adrp x4, _dl_skip_args \n\
+ ldr w4, [x4, #:lo12:_dl_skip_args] \n\
+ // do we need to adjust argc/argv \n\
+ cmp w4, 0 \n\
+ beq .L_done_stack_adjust \n\
+ // subtract _dl_skip_args from original arg count \n\
+ sub " PTR "1, " PTR "1, " PTR "4 \n\
+ // store adjusted argc back to stack \n\
+ str " PTR "1, [sp] \n\
+ // find the first unskipped argument \n\
+ mov " PTR "3, " PTR "2 \n\
+ add " PTR "4, " PTR "2, " PTR "4, lsl #" PTR_SIZE_LOG " \n\
+ // shuffle argv down \n\
+1: ldr " PTR "5, [x4], #(1<<" PTR_SIZE_LOG ") \n\
+ str " PTR "5, [x3], #(1<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "5, #0 \n\
+ bne 1b \n\
+ // shuffle envp down \n\
+1: ldr " PTR "5, [x4], #(1<<" PTR_SIZE_LOG ") \n\
+ str " PTR "5, [x3], #(1<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "5, #0 \n\
+ bne 1b \n\
+ // shuffle auxv down \n\
+1: ldp " PTR "0, " PTR "5, [x4, #(2<<" PTR_SIZE_LOG ")]! \n\
+ stp " PTR "0, " PTR "5, [x3], #(2<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "0, #0 \n\
+ bne 1b \n\
+ // Update _dl_argv \n\
+ adrp x3, _dl_argv \n\
+ str " PTR "2, [x3, #:lo12:_dl_argv] \n\
+.L_done_stack_adjust: \n\
+ // compute envp \n\
+ add " PTR "3, " PTR "2, " PTR "1, lsl #" PTR_SIZE_LOG " \n\
+ add " PTR "3, " PTR "3, #(1<<" PTR_SIZE_LOG ") \n\
+ adrp x16, _rtld_local \n\
+ add " PTR "16, " PTR "16, #:lo12:_rtld_local \n\
+ ldr " PTR "0, [x16] \n\
+ bl _dl_init \n\
+ // load the finalizer function \n\
+ adrp x0, _dl_fini \n\
+ add " PTR "0, " PTR "0, #:lo12:_dl_fini \n\
+ // jump to the user_s entry point \n\
+ br x21 \n\
");
#define elf_machine_type_class(type) \
- ((((type) == R_AARCH64_JUMP_SLOT || \
- (type) == R_AARCH64_TLS_DTPMOD || \
- (type) == R_AARCH64_TLS_DTPREL || \
- (type) == R_AARCH64_TLS_TPREL || \
- (type) == R_AARCH64_TLSDESC) * ELF_RTYPE_CLASS_PLT) \
- | (((type) == R_AARCH64_COPY) * ELF_RTYPE_CLASS_COPY) \
- | (((type) == R_AARCH64_GLOB_DAT) * ELF_RTYPE_CLASS_EXTERN_PROTECTED_DATA))
+ ((((type) == AARCH64_R (JUMP_SLOT) \
+ || (type) == AARCH64_R (TLS_DTPMOD) \
+ || (type) == AARCH64_R (TLS_DTPREL) \
+ || (type) == AARCH64_R (TLS_TPREL) \
+ || (type) == AARCH64_R (TLSDESC)) * ELF_RTYPE_CLASS_PLT) \
+ | (((type) == AARCH64_R (COPY)) * ELF_RTYPE_CLASS_COPY) \
+ | (((type) == AARCH64_R (GLOB_DAT)) * ELF_RTYPE_CLASS_EXTERN_PROTECTED_DATA))
-#define ELF_MACHINE_JMP_SLOT R_AARCH64_JUMP_SLOT
+#define ELF_MACHINE_JMP_SLOT AARCH64_R (JUMP_SLOT)
/* AArch64 uses RELA not REL */
#define ELF_MACHINE_NO_REL 1
@@ -237,9 +258,9 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
void *const reloc_addr_arg, int skip_ifunc)
{
ElfW(Addr) *const reloc_addr = reloc_addr_arg;
- const unsigned int r_type = ELF64_R_TYPE (reloc->r_info);
+ const unsigned int r_type = ELFW (R_TYPE) (reloc->r_info);
- if (__builtin_expect (r_type == R_AARCH64_RELATIVE, 0))
+ if (__builtin_expect (r_type == AARCH64_R (RELATIVE), 0))
*reloc_addr = map->l_addr + reloc->r_addend;
else if (__builtin_expect (r_type == R_AARCH64_NONE, 0))
return;
@@ -257,7 +278,7 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
switch (r_type)
{
- case R_AARCH64_COPY:
+ case AARCH64_R (COPY):
if (sym == NULL)
break;
@@ -275,15 +296,17 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
MIN (sym->st_size, refsym->st_size));
break;
- case R_AARCH64_RELATIVE:
- case R_AARCH64_GLOB_DAT:
- case R_AARCH64_JUMP_SLOT:
- case R_AARCH64_ABS32:
- case R_AARCH64_ABS64:
+ case AARCH64_R (RELATIVE):
+ case AARCH64_R (GLOB_DAT):
+ case AARCH64_R (JUMP_SLOT):
+ case AARCH64_R (ABS32):
+#ifdef __LP64__
+ case AARCH64_R (ABS64):
+#endif
*reloc_addr = value + reloc->r_addend;
break;
- case R_AARCH64_TLSDESC:
+ case AARCH64_R (TLSDESC):
{
struct tlsdesc volatile *td =
(struct tlsdesc volatile *)reloc_addr;
@@ -318,7 +341,7 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
break;
}
- case R_AARCH64_TLS_DTPMOD:
+ case AARCH64_R (TLS_DTPMOD):
#ifdef RTLD_BOOTSTRAP
*reloc_addr = 1;
#else
@@ -329,12 +352,12 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
#endif
break;
- case R_AARCH64_TLS_DTPREL:
+ case AARCH64_R (TLS_DTPREL):
if (sym)
*reloc_addr = sym->st_value + reloc->r_addend;
break;
- case R_AARCH64_TLS_TPREL:
+ case AARCH64_R (TLS_TPREL):
if (sym)
{
CHECK_STATIC_TLS (map, sym_map);
@@ -343,7 +366,7 @@ elf_machine_rela (struct link_map *map, const ElfW(Rela) *reloc,
}
break;
- case R_AARCH64_IRELATIVE:
+ case AARCH64_R (IRELATIVE):
value = map->l_addr + reloc->r_addend;
value = elf_ifunc_invoke (value);
*reloc_addr = value;
@@ -374,16 +397,16 @@ elf_machine_lazy_rel (struct link_map *map,
int skip_ifunc)
{
ElfW(Addr) *const reloc_addr = (void *) (l_addr + reloc->r_offset);
- const unsigned int r_type = ELF64_R_TYPE (reloc->r_info);
+ const unsigned int r_type = ELFW (R_TYPE) (reloc->r_info);
/* Check for unexpected PLT reloc type. */
- if (__builtin_expect (r_type == R_AARCH64_JUMP_SLOT, 1))
+ if (__builtin_expect (r_type == AARCH64_R (JUMP_SLOT), 1))
{
if (__builtin_expect (map->l_mach.plt, 0) == 0)
*reloc_addr += l_addr;
else
*reloc_addr = map->l_mach.plt;
}
- else if (__builtin_expect (r_type == R_AARCH64_TLSDESC, 1))
+ else if (__builtin_expect (r_type == AARCH64_R (TLSDESC), 1))
{
struct tlsdesc volatile *td =
(struct tlsdesc volatile *)reloc_addr;
@@ -392,7 +415,7 @@ elf_machine_lazy_rel (struct link_map *map,
td->entry = (void*)(D_PTR (map, l_info[ADDRIDX (DT_TLSDESC_PLT)])
+ map->l_addr);
}
- else if (__glibc_unlikely (r_type == R_AARCH64_IRELATIVE))
+ else if (__glibc_unlikely (r_type == AARCH64_R (IRELATIVE)))
{
ElfW(Addr) value = map->l_addr + reloc->r_addend;
if (__glibc_likely (!skip_ifunc))
@@ -74,7 +74,8 @@
cfi_startproc
.align 2
_dl_tlsdesc_return:
- ldr x0, [x0, #8]
+ DELOUSE (0)
+ ldr PTR_REG (0), [x0, #PTR_SIZE]
RET
cfi_endproc
.size _dl_tlsdesc_return, .-_dl_tlsdesc_return
@@ -95,9 +96,10 @@ _dl_tlsdesc_return_lazy:
so it reads the same value (this function is the final value of
td->entry) and thus it synchronizes with the release store to
td->entry in _dl_tlsdesc_resolve_rela_fixup ensuring that the load
- from [x0,#8] here happens after the initialization of td->arg. */
- ldar xzr, [x0]
- ldr x0, [x0, #8]
+ from [x0,#PTR_SIZE] here happens after the initialization of td->arg. */
+ DELOUSE (0)
+ ldar PTR_REG (zr), [x0]
+ ldr PTR_REG (0), [x0, #PTR_SIZE]
RET
cfi_endproc
.size _dl_tlsdesc_return_lazy, .-_dl_tlsdesc_return_lazy
@@ -125,10 +127,11 @@ _dl_tlsdesc_undefweak:
td->entry) and thus it synchronizes with the release store to
td->entry in _dl_tlsdesc_resolve_rela_fixup ensuring that the load
from [x0,#8] here happens after the initialization of td->arg. */
- ldar xzr, [x0]
- ldr x0, [x0, #8]
+ DELOUSE (0)
+ ldar PTR_REG (zr), [x0]
+ ldr PTR_REG (0), [x0, #PTR_SIZE]
mrs x1, tpidr_el0
- sub x0, x0, x1
+ sub PTR_REG (0), PTR_REG (0), PTR_REG (1)
ldr x1, [sp], #16
cfi_adjust_cfa_offset (-16)
RET
@@ -174,6 +177,7 @@ _dl_tlsdesc_dynamic:
stp x29, x30, [sp,#-(32+16*NSAVEXREGPAIRS)]!
cfi_adjust_cfa_offset (32+16*NSAVEXREGPAIRS)
mov x29, sp
+ DELOUSE (0)
/* Save just enough registers to support fast path, if we fall
into slow path we will save additional registers. */
@@ -187,22 +191,22 @@ _dl_tlsdesc_dynamic:
so it reads the same value (this function is the final value of
td->entry) and thus it synchronizes with the release store to
td->entry in _dl_tlsdesc_resolve_rela_fixup ensuring that the load
- from [x0,#8] here happens after the initialization of td->arg. */
- ldar xzr, [x0]
- ldr x1, [x0,#8]
- ldr x0, [x4]
- ldr x3, [x1,#16]
- ldr x2, [x0]
- cmp x3, x2
+ from [x0,#PTR_SIZE] here happens after the initialization of td->arg. */
+ ldar PTR_REG (zr), [x0]
+ ldr PTR_REG (1), [x0,#PTR_SIZE]
+ ldr PTR_REG (0), [x4]
+ ldr PTR_REG (3), [x1,#(PTR_SIZE * 2)]
+ ldr PTR_REG (2), [x0]
+ cmp PTR_REG (3), PTR_REG (2)
b.hi 2f
- ldr x2, [x1]
- add x0, x0, x2, lsl #4
- ldr x0, [x0]
+ ldr PTR_REG (2), [x1]
+ add PTR_REG (0), PTR_REG (0), PTR_REG (2), lsl #(PTR_LOG_SIZE + 1)
+ ldr PTR_REG (0), [x0]
cmn x0, #0x1
b.eq 2f
- ldr x1, [x1,#8]
- add x0, x0, x1
- sub x0, x0, x4
+ ldr PTR_REG (1), [x1,#(PTR_SIZE * 2)]
+ add PTR_REG (0), PTR_REG (0), PTR_REG (1)
+ sub PTR_REG (0), PTR_REG (0), PTR_REG (4)
1:
ldp x1, x2, [sp, #32+16*0]
ldp x3, x4, [sp, #32+16*1]
@@ -233,7 +237,7 @@ _dl_tlsdesc_dynamic:
bl __tls_get_addr
mrs x1, tpidr_el0
- sub x0, x0, x1
+ sub PTR_REG (0), PTR_REG (0), PTR_REG (1)
RESTORE_Q_REGISTERS
@@ -279,13 +283,15 @@ _dl_tlsdesc_resolve_rela:
SAVE_Q_REGISTERS
- ldr x1, [x3, #8]
+ DELOUSE (3)
+ ldr PTR_REG (1), [x3, #PTR_SIZE]
bl _dl_tlsdesc_resolve_rela_fixup
RESTORE_Q_REGISTERS
ldr x0, [sp, #32+16*8]
- ldr x1, [x0]
+ DELOUSE (0)
+ ldr PTR_REG (1), [x0]
blr x1
ldp x1, x4, [sp, #32+16*0]
@@ -346,7 +352,8 @@ _dl_tlsdesc_resolve_hold:
RESTORE_Q_REGISTERS
ldr x0, [sp, #32+16*9]
- ldr x1, [x0]
+ DELOUSE (0)
+ ldr PTR_REG (1), [x0]
blr x1
ldp x1, x2, [sp, #32+16*0]
@@ -22,9 +22,13 @@
#include "dl-link.h"
#define ip0 x16
+#define ip0l PTR_REG (16)
#define ip1 x17
#define lr x30
+/* RELA relocatons are 3 pointers */
+#define RELA_SIZE (PTR_SIZE * 3)
+
.text
.globl _dl_runtime_resolve
.type _dl_runtime_resolve, #function
@@ -79,7 +83,7 @@ _dl_runtime_resolve:
cfi_rel_offset (q1, 80+7*16)
/* Get pointer to linker struct. */
- ldr x0, [ip0, #-8]
+ ldr PTR_REG (0), [ip0, #-PTR_SIZE]
/* Prepare to call _dl_fixup(). */
ldr x1, [sp, 80+8*16] /* Recover &PLTGOT[n] */
@@ -87,7 +91,7 @@ _dl_runtime_resolve:
sub x1, x1, ip0
add x1, x1, x1, lsl #1
lsl x1, x1, #3
- sub x1, x1, #192
+ sub x1, x1, #(RELA_SIZE<<3)
lsr x1, x1, #3
/* Call fixup routine. */
@@ -191,7 +195,7 @@ _dl_runtime_profile:
stp x0, x1, [x29, #OFFSET_RG + DL_OFFSET_RG_SP]
/* Get pointer to linker struct. */
- ldr x0, [ip0, #-8]
+ ldr PTR_REG (0), [ip0, #-PTR_SIZE]
/* Prepare to call _dl_profile_fixup(). */
ldr x1, [x29, OFFSET_PLTGOTN] /* Recover &PLTGOT[n] */
@@ -199,7 +203,7 @@ _dl_runtime_profile:
sub x1, x1, ip0
add x1, x1, x1, lsl #1
lsl x1, x1, #3
- sub x1, x1, #192
+ sub x1, x1, #(RELA_SIZE<<3)
lsr x1, x1, #3
stp x0, x1, [x29, #OFFSET_SAVED_CALL_X0]
@@ -210,8 +214,8 @@ _dl_runtime_profile:
add x4, x29, #OFFSET_FS /* address of framesize */
bl _dl_profile_fixup
- ldr ip0, [x29, #OFFSET_FS] /* framesize == 0 */
- cmp ip0, #0
+ ldr ip0l, [x29, #OFFSET_FS] /* framesize == 0 */
+ cmp ip0l, #0
bge 1f
cfi_remember_state
@@ -243,7 +247,7 @@ _dl_runtime_profile:
1:
/* The new frame size is in ip0. */
- sub x1, x29, ip0
+ sub PTR_REG (1), PTR_REG (29), ip0l
and sp, x1, #0xfffffffffffffff0
str x0, [x29, #OFFSET_T1]
@@ -27,7 +27,7 @@
((void *) (address) < (void *) demangle (jmpbuf[JB_SP]))
#define _JMPBUF_CFA_UNWINDS_ADJ(jmpbuf, context, adj) \
- _JMPBUF_UNWINDS_ADJ (jmpbuf, (void *) _Unwind_GetCFA (context), adj)
+ _JMPBUF_UNWINDS_ADJ (jmpbuf, (void *) (size_t) _Unwind_GetCFA (context), adj)
#define _JMPBUF_UNWINDS_ADJ(_jmpbuf, _address, _adj) \
((uintptr_t) (_address) - (_adj) < _jmpbuf_sp (_jmpbuf) - (_adj))
@@ -47,6 +47,9 @@
#define mask x13
ENTRY_ALIGN (memcmp, 6)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
cbz limit, L(ret0)
eor tmp1, src1, src2
tst tmp1, #7
@@ -61,6 +61,10 @@
ENTRY_ALIGN (memmove, 6)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
+
sub tmp1, dstin, src
cmp count, 96
ccmp tmp1, count, 2, hi
@@ -71,6 +75,10 @@ END (memmove)
libc_hidden_builtin_def (memmove)
ENTRY (memcpy)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
+
prfm PLDL1KEEP, [src]
add srcend, src, count
add dstend, dstin, count
@@ -39,6 +39,9 @@
ENTRY_ALIGN (__memset, 6)
+ DELOUSE (0)
+ DELOUSE (2)
+
dup v0.16B, valw
add dstend, dstin, count
@@ -32,6 +32,8 @@
#define __SIZEOF_PTHREAD_BARRIER_T 32
#define __SIZEOF_PTHREAD_BARRIERATTR_T 8
+#define __PTHREAD_RWLOCK_INT_FLAGS_SHARED 1
+
/* Thread identifiers. The structure of the attribute type is not
exposed on purpose. */
@@ -21,7 +21,11 @@
#endif
+#ifdef __ILP32__
+#define __SIZEOF_SEM_T 16
+#else
#define __SIZEOF_SEM_T 32
+#endif
/* Value returned if `sem_open' failed. */
@@ -33,6 +33,7 @@ END (_setjmp)
libc_hidden_def (_setjmp)
ENTRY (__sigsetjmp)
+ DELOUSE (0)
1:
stp x19, x20, [x0, #JB_X19<<3]
@@ -42,7 +43,7 @@ ENTRY (__sigsetjmp)
stp x27, x28, [x0, #JB_X27<<3]
#ifdef PTR_MANGLE
- PTR_MANGLE (x4, x30, x3, x2)
+ PTR_MANGLE (4, 30, 3, 2)
stp x29, x4, [x0, #JB_X29<<3]
#else
stp x29, x30, [x0, #JB_X29<<3]
@@ -57,7 +58,7 @@ ENTRY (__sigsetjmp)
stp d14, d15, [x0, #JB_D14<<3]
#ifdef PTR_MANGLE
mov x4, sp
- PTR_MANGLE (x5, x4, x3, x2)
+ PTR_MANGLE (5, 4, 3, 2)
str x5, [x0, #JB_SP<<3]
#else
mov x2, sp
@@ -16,6 +16,8 @@
License along with the GNU C Library. If not, see
<http://www.gnu.org/licenses/>. */
+#include <sysdep.h>
+
/* This is the canonical entry point, usually the first thing in the text
segment.
@@ -25,7 +27,7 @@
At this entry point, most registers' values are unspecified, except:
- x0 Contains a function pointer to be registered with `atexit'.
+ x0/w0 Contains a function pointer to be registered with `atexit'.
This is how the dynamic linker arranges to have DT_FINI
functions called for shared libraries that have been loaded
before this code runs.
@@ -52,26 +54,26 @@ _start:
mov x5, x0
/* Load argc and a pointer to argv */
- ldr x1, [sp, #0]
- add x2, sp, #8
+ ldr PTR_REG (1), [sp, #0]
+ add x2, sp, #PTR_SIZE
/* Setup stack limit in argument register */
mov x6, sp
#ifdef SHARED
adrp x0, :got:main
- ldr x0, [x0, #:got_lo12:main]
+ ldr PTR_REG (0), [x0, #:got_lo12:main]
adrp x3, :got:__libc_csu_init
- ldr x3, [x3, #:got_lo12:__libc_csu_init]
+ ldr PTR_REG (3), [x3, #:got_lo12:__libc_csu_init]
adrp x4, :got:__libc_csu_fini
- ldr x4, [x4, #:got_lo12:__libc_csu_fini]
+ ldr PTR_REG (4), [x4, #:got_lo12:__libc_csu_fini]
#else
/* Set up the other arguments in registers */
- ldr x0, =main
- ldr x3, =__libc_csu_init
- ldr x4, =__libc_csu_fini
+ ldr PTR_REG (0), =main
+ ldr PTR_REG (3), =__libc_csu_init
+ ldr PTR_REG (4), =__libc_csu_fini
#endif
/* __libc_start_main (main, argc, argv, init, fini, rtld_fini,
@@ -62,6 +62,7 @@
/* Locals and temporaries. */
ENTRY (strchr)
+ DELOUSE (0)
mov wtmp2, #0x0401
movk wtmp2, #0x4010, lsl #16
dup vrepchr.16b, chrin
@@ -60,6 +60,7 @@
identify exactly which byte is causing the termination. */
ENTRY (__strchrnul)
+ DELOUSE (0)
/* Magic constant 0x40100401 to allow us to identify which lane
matches the termination condition. */
mov wtmp2, #0x0401
@@ -49,6 +49,8 @@
/* Start of performance-critical section -- one 64B cache line. */
ENTRY_ALIGN(strcmp, 6)
+ DELOUSE (0)
+ DELOUSE (1)
eor tmp1, src1, src2
mov zeroones, #REP8_01
tst tmp1, #7
@@ -91,6 +91,8 @@
#define MIN_PAGE_SIZE (1 << MIN_PAGE_P2)
ENTRY_ALIGN (STRCPY, 6)
+ DELOUSE (0)
+ DELOUSE (1)
/* For moderately short strings, the fastest way to do the copy is to
calculate the length of the string in the same way as strlen, then
essentially do a memcpy of the result. This avoids the need for
@@ -85,6 +85,8 @@
boundary. */
ENTRY_ALIGN (__strlen, 6)
+ DELOUSE (0)
+ DELOUSE (1)
and tmp1, srcin, MIN_PAGE_SIZE - 1
mov zeroones, REP8_01
cmp tmp1, MIN_PAGE_SIZE - 16
@@ -51,6 +51,9 @@
#define endloop x15
ENTRY_ALIGN_AND_PAD (strncmp, 6, 7)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
cbz limit, L(ret0)
eor tmp1, src1, src2
mov zeroones, #REP8_01
@@ -50,6 +50,9 @@
#define REP8_80 0x8080808080808080
ENTRY_ALIGN_AND_PAD (__strnlen, 6, 9)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
cbz limit, L(hit_limit)
mov zeroones, #REP8_01
bic src, srcin, #15
@@ -68,6 +68,7 @@
identify exactly which byte is causing the termination, and why. */
ENTRY(strrchr)
+ DELOUSE (0)
cbz x1, L(null_search)
/* Magic constant 0x40100401 to allow us to identify which lane
matches the requested byte. Magic constant 0x80200802 used
@@ -16,8 +16,25 @@
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
+#ifndef _AARCH64_SYSDEP_H
+#define _AARCH64_SYSDEP_H
+
#include <sysdeps/generic/sysdep.h>
+#ifdef __LP64__
+# define AARCH64_R(NAME) R_AARCH64_ ## NAME
+# define PTR_REG(n) x##n
+# define PTR_LOG_SIZE 3
+# define DELOUSE(n)
+#else
+# define AARCH64_R(NAME) R_AARCH64_P32_ ## NAME
+# define PTR_REG(n) w##n
+# define PTR_LOG_SIZE 2
+# define DELOUSE(n) mov w##n, w##n
+#endif
+
+#define PTR_SIZE (1<<PTR_LOG_SIZE)
+
#ifdef __ASSEMBLER__
/* Syntactic details of assembler. */
@@ -107,16 +124,18 @@
# define L(name) .L##name
#endif
-/* Load or store to/from a pc-relative EXPR into/from R, using T. */
-#define LDST_PCREL(OP, R, T, EXPR) \
- adrp T, EXPR; \
- OP R, [T, #:lo12:EXPR];\
+/* Load or store to/from a pc-relative EXPR into/from R, using T.
+ Note R and T are register numbers and not register names. */
+#define LDST_PCREL(OP, R, T, EXPR) \
+ adrp x##T, EXPR; \
+ OP PTR_REG (R), [x##T, #:lo12:EXPR]; \
-/* Load or store to/from a got-relative EXPR into/from R, using T. */
-#define LDST_GLOBAL(OP, R, T, EXPR) \
- adrp T, :got:EXPR; \
- ldr T, [T, #:got_lo12:EXPR];\
- OP R, [T];
+/* Load or store to/from a got-relative EXPR into/from R, using T.
+ Note R and T are register numbers and not register names. */
+#define LDST_GLOBAL(OP, R, T, EXPR) \
+ adrp x##T, :got:EXPR; \
+ ldr PTR_REG (T), [x##T, #:got_lo12:EXPR]; \
+ OP PTR_REG (R), [x##T];
/* Since C identifiers are not normally prefixed with an underscore
on this system, the asm identifier `syscall_error' intrudes on the
@@ -125,3 +144,5 @@
#define mcount _mcount
#endif /* __ASSEMBLER__ */
+
+#endif /* _AARCH64_SYSDEP_H */
@@ -25,11 +25,17 @@
#define __O_NOFOLLOW 0100000
#define __O_DIRECT 0200000
-#define __O_LARGEFILE 0
+#ifdef __ILP32__
+# define __O_LARGEFILE 0400000
+#else
+# define __O_LARGEFILE 0
+#endif
+#ifdef __LP64__
# define F_GETLK64 5
# define F_SETLK64 6
# define F_SETLKW64 7
+#endif
struct flock
{
@@ -39,6 +39,13 @@
*/
.text
ENTRY(__clone)
+ DELOUSE (0)
+ DELOUSE (1)
+ DELOUSE (2)
+ DELOUSE (3)
+ DELOUSE (4)
+ DELOUSE (5)
+ DELOUSE (6)
/* Save args for the child. */
mov x10, x0
mov x11, x2
@@ -18,7 +18,11 @@
#include <ldconfig.h>
+#ifdef __LP64__
#define _DL_CACHE_DEFAULT_ID (FLAG_AARCH64_LIB64 | FLAG_ELF_LIBC6)
+#else
+#define _DL_CACHE_DEFAULT_ID (FLAG_AARCH64_LIB32 | FLAG_ELF_LIBC6)
+#endif
#define _dl_cache_check_flags(flags) \
((flags) == _DL_CACHE_DEFAULT_ID)
@@ -27,18 +31,25 @@
do \
{ \
size_t len = strlen (dir); \
- char path[len + 3]; \
+ char path[len + 6]; \
memcpy (path, dir, len + 1); \
if (len >= 6 && ! memcmp (path + len - 6, "/lib64", 6)) \
{ \
len -= 2; \
path[len] = '\0'; \
} \
+ if (len >= 9 && ! memcmp (path + len - 9, "/libilp32", 9))\
+ { \
+ len -= 5; \
+ path[len] = '\0'; \
+ } \
add_dir (path); \
if (len >= 4 && ! memcmp (path + len - 4, "/lib", 4)) \
{ \
memcpy (path + len, "64", 3); \
add_dir (path); \
+ memcpy (path + len, "ilp32", 6); \
+ add_dir (path); \
} \
} while (0)
@@ -30,6 +30,7 @@
.text
ENTRY(__getcontext)
+ DELOUSE (0)
/* The saved context will return to the getcontext() call point
with a return value of 0 */
str xzr, [x0, oX0 + 0 * SZREG]
@@ -90,7 +91,7 @@ ENTRY(__getcontext)
/* Grab the signal mask */
/* rt_sigprocmask (SIG_BLOCK, NULL, &ucp->uc_sigmask, _NSIG8) */
- add x2, x0, #UCONTEXT_SIGMASK
+ add PTR_REG (2), PTR_REG (0), #UCONTEXT_SIGMASK
mov x0, SIG_BLOCK
mov x1, 0
mov x3, _NSIG8
@@ -27,17 +27,21 @@ int (*VDSO_SYMBOL(clock_getres)) (clockid_t, struct timespec *);
static inline void
_libc_vdso_platform_setup (void)
{
- PREPARE_VERSION (linux2639, "LINUX_2.6.39", 123718537);
+#ifdef __LP64__
+ PREPARE_VERSION (linux_version, "LINUX_2.6.39", 123718537);
+#else
+ PREPARE_VERSION (linux_version, "LINUX_4.9", 61765625);
+#endif
- void *p = _dl_vdso_vsym ("__kernel_gettimeofday", &linux2639);
+ void *p = _dl_vdso_vsym ("__kernel_gettimeofday", &linux_version);
PTR_MANGLE (p);
VDSO_SYMBOL(gettimeofday) = p;
- p = _dl_vdso_vsym ("__kernel_clock_gettime", &linux2639);
+ p = _dl_vdso_vsym ("__kernel_clock_gettime", &linux_version);
PTR_MANGLE (p);
VDSO_SYMBOL(clock_gettime) = p;
- p = _dl_vdso_vsym ("__kernel_clock_getres", &linux2639);
+ p = _dl_vdso_vsym ("__kernel_clock_getres", &linux_version);
PTR_MANGLE (p);
VDSO_SYMBOL(clock_getres) = p;
}
@@ -21,6 +21,8 @@
#define SYSDEP_KNOWN_INTERPRETER_NAMES \
{ "/lib/ld-linux-aarch64.so.1", FLAG_ELF_LIBC6 }, \
{ "/lib/ld-linux-aarch64_be.so.1", FLAG_ELF_LIBC6 }, \
+ { "/lib/ld-linux-aarch64_ilp32.so.1", FLAG_ELF_LIBC6 }, \
+ { "/lib/ld-linux-aarch64_be_ilp32.so.1", FLAG_ELF_LIBC6 }, \
{ "/lib/ld-linux.so.3", FLAG_ELF_LIBC6 }, \
{ "/lib/ld-linux-armhf.so.3", FLAG_ELF_LIBC6 },
#define SYSDEP_KNOWN_LIBRARY_NAMES \
@@ -34,6 +34,7 @@
.text
ENTRY (__setcontext)
+ DELOUSE (0)
/* Save a copy of UCP. */
mov x9, x0
@@ -19,7 +19,7 @@
#include <sys/ucontext.h>
#define SIGCONTEXT siginfo_t *_si, struct ucontext *
-#define GET_PC(ctx) ((void *) (ctx)->uc_mcontext.pc)
+#define GET_PC(ctx) ((void *) (size_t) (ctx)->uc_mcontext.pc)
/* There is no reliable way to get the sigcontext unless we use a
three-argument signal handler. */
@@ -27,6 +27,7 @@
.text
ENTRY(__swapcontext)
+ DELOUSE (0)
/* Set the value returned when swapcontext() returns in this context. */
str xzr, [x0, oX0 + 0 * SZREG]
@@ -250,12 +250,14 @@
(!defined SHARED && (IS_IN (libc) \
|| IS_IN (libpthread))))
# ifdef __ASSEMBLER__
+/* Note, dst, src, guard, and tmp are all register numbers rather than
+ register names so they will work with both ILP32 and LP64. */
# define PTR_MANGLE(dst, src, guard, tmp) \
LDST_PCREL (ldr, guard, tmp, C_SYMBOL_NAME(__pointer_chk_guard_local)); \
PTR_MANGLE2 (dst, src, guard)
/* Use PTR_MANGLE2 for efficiency if guard is already loaded. */
# define PTR_MANGLE2(dst, src, guard)\
- eor dst, src, guard
+ eor x##dst, x##src, x##guard
# define PTR_DEMANGLE(dst, src, guard, tmp)\
PTR_MANGLE (dst, src, guard, tmp)
# define PTR_DEMANGLE2(dst, src, guard)\
@@ -268,12 +270,14 @@ extern uintptr_t __pointer_chk_guard_local attribute_relro attribute_hidden;
# endif
#else
# ifdef __ASSEMBLER__
+/* Note, dst, src, guard, and tmp are all register numbers rather than
+ register names so they will work with both ILP32 and LP64. */
# define PTR_MANGLE(dst, src, guard, tmp) \
LDST_GLOBAL (ldr, guard, tmp, C_SYMBOL_NAME(__pointer_chk_guard)); \
PTR_MANGLE2 (dst, src, guard)
/* Use PTR_MANGLE2 for efficiency if guard is already loaded. */
# define PTR_MANGLE2(dst, src, guard)\
- eor dst, src, guard
+ eor x##dst, x##src, x##guard
# define PTR_DEMANGLE(dst, src, guard, tmp)\
PTR_MANGLE (dst, src, guard, tmp)
# define PTR_DEMANGLE2(dst, src, guard)\