@@ -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]
@@ -74,6 +74,7 @@
cfi_startproc
.align 2
_dl_tlsdesc_return:
+ DELOUSE(0)
ldr PTR_REG (0), [x0, #PTR_SIZE]
RET
cfi_endproc
@@ -96,6 +97,7 @@ _dl_tlsdesc_return_lazy:
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,#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
@@ -125,6 +127,7 @@ _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. */
+ DELOUSE(0)
ldar PTR_REG (zr), [x0]
ldr PTR_REG (0), [x0, #PTR_SIZE]
mrs x1, tpidr_el0
@@ -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. */
@@ -188,6 +192,7 @@ _dl_tlsdesc_dynamic:
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,#PTR_SIZE] here happens after the initialization of td->arg. */
+ DELOUSE(0)
ldar PTR_REG (zr), [x0]
ldr PTR_REG (1), [x0,#PTR_SIZE]
ldr PTR_REG (0), [x4]
@@ -279,12 +284,14 @@ _dl_tlsdesc_resolve_rela:
SAVE_Q_REGISTERS
+ DELOUSE(3)
ldr PTR_REG (1), [x3, #PTR_SIZE]
bl _dl_tlsdesc_resolve_rela_fixup
RESTORE_Q_REGISTERS
ldr x0, [sp, #32+16*8]
+ DELOUSE(0)
ldr PTR_REG (1), [x0]
blr x1
@@ -346,6 +353,7 @@ _dl_tlsdesc_resolve_hold:
RESTORE_Q_REGISTERS
ldr x0, [sp, #32+16*9]
+ DELOUSE(0)
ldr PTR_REG (1), [x0]
blr x1
@@ -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
@@ -33,6 +33,7 @@ END (_setjmp)
libc_hidden_def (_setjmp)
ENTRY (__sigsetjmp)
+ DELOUSE(0)
1:
stp x19, x20, [x0, #JB_X19<<3]
@@ -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
@@ -25,10 +25,12 @@
# 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)
@@ -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
@@ -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]
@@ -34,6 +34,7 @@
.text
ENTRY (__setcontext)
+ DELOUSE(0)
/* Save a copy of UCP. */
mov x9, x0
@@ -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]