[PATCH v2] aarch64: push the set of rules before falling into slow path

[Shuo Wang]

It is supposed to save the rules for the instructions before falling into slow path.

Tested in glibc-2.28 before fixing:
Thread 2 "xxxxxxx" hit Breakpoint 1, _dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:149
149		stp	x1,  x2, [sp, #-32]!
Missing separate debuginfos, use: dnf debuginfo-install libgcc-7.3.0-20190804.h24.aarch64
(gdb) ni
_dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:150
150		stp	x3,  x4, [sp, #16]
(gdb) 
_dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:157
157		mrs	x4, tpidr_el0
(gdb) 
158		ldr	PTR_REG (1), [x0,#TLSDESC_ARG]
(gdb) 
159		ldr	PTR_REG (0), [x4,#TCBHEAD_DTV]
(gdb) 
160		ldr	PTR_REG (3), [x1,#TLSDESC_GEN_COUNT]
(gdb) 
161		ldr	PTR_REG (2), [x0,#DTV_COUNTER]
(gdb) 
162		cmp	PTR_REG (3), PTR_REG (2)
(gdb) 
163		b.hi	2f
(gdb) 
165		ldp	PTR_REG (2), PTR_REG (3), [x1,#TLSDESC_MODID]
(gdb) 
166		add	PTR_REG (0), PTR_REG (0), PTR_REG (2), lsl #(PTR_LOG_SIZE + 1)
(gdb) 
167		ldr	PTR_REG (0), [x0] /* Load val member of DTV entry.  */
(gdb) 
168		cmp	PTR_REG (0), #TLS_DTV_UNALLOCATED
(gdb) 
169		b.eq	2f
(gdb) bt
#0  _dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:169
#1  0x0000ffffbe4fbb44 in OurFunction (threadId=4294967295)
    at /home/test/test_function.c:30
#2  0x0000000000400c08 in initaaa () at thread.c:58
#3  0x0000000000400c50 in thread_proc (param=0x0) at thread.c:71
#4  0x0000ffffbf6918bc in start_thread (arg=0xfffffffff29f) at pthread_create.c:486
#5  0x0000ffffbf5669ec in thread_start () at ../sysdeps/unix/sysv/linux/aarch64/clone.S:78
(gdb) ni
_dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:184
184		stp	x29, x30, [sp,#-16*NSAVEXREGPAIRS]!
(gdb) bt
#0  _dl_tlsdesc_dynamic () at ../sysdeps/aarch64/dl-tlsdesc.S:184
#1  0x0000ffffbe4fbb44 in OurFunction (threadId=4294967295)
    at /home/test/test_function.c:30
#2  0x0000000000000000 in ?? ()
Backtrace stopped: previous frame identical to this frame (corrupt stack?)

Co-authored-by: liqingqing <liqingqing3@huawei.com>
---
 sysdeps/aarch64/dl-tlsdesc.S | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sysdeps/aarch64/dl-tlsdesc.S b/sysdeps/aarch64/dl-tlsdesc.S
index 425e45a50f..4777262be1 100644
--- a/sysdeps/aarch64/dl-tlsdesc.S
+++ b/sysdeps/aarch64/dl-tlsdesc.S
@@ -170,6 +170,7 @@ _dl_tlsdesc_dynamic:
 	ldr	PTR_REG (0), [x0] /* Load val member of DTV entry.  */
 	cmp	PTR_REG (0), #TLS_DTV_UNALLOCATED
 	b.eq	2f
+	cfi_remember_state
 	sub	PTR_REG (3), PTR_REG (3), PTR_REG (4)
 	add	PTR_REG (0), PTR_REG (0), PTR_REG (3)
 1:
@@ -183,6 +184,7 @@ _dl_tlsdesc_dynamic:
 	   callee will trash.  */
 
 	/* Save the remaining registers that we must treat as caller save.  */
+	cfi_restore_state
 # if HAVE_AARCH64_PAC_RET
 	PACIASP
 	cfi_window_save
-- 
2.23.0