This is the mail archive of the
glibc-cvs@sourceware.org
mailing list for the glibc project.
GNU C Library master sources branch release/2.20/master updated. glibc-2.20-30-g4cf2b4e
- From: stli at sourceware dot org
- To: glibc-cvs at sourceware dot org
- Date: 4 Apr 2016 11:28:05 -0000
- Subject: GNU C Library master sources branch release/2.20/master updated. glibc-2.20-30-g4cf2b4e
This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "GNU C Library master sources".
The branch, release/2.20/master has been updated
via 4cf2b4e80a41f96f1b867f253547241871827ef1 (commit)
via 4b7ba5b8c4722d610862744c619bcaa5ad655385 (commit)
via 3058f7487e5b98f7af0219f77464294000c84bf0 (commit)
via 66cdb5b20df45c4eb28ab27ebcfb67ef023338e3 (commit)
via 7af8c37714ece3f02716f17e59631ada0c0ee0d9 (commit)
from adba20cf74bc6ea3910afe57d40ed755c92c2ddb (commit)
Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.
- Log -----------------------------------------------------------------
http://sourceware.org/git/gitweb.cgi?p=glibc.git;a=commitdiff;h=4cf2b4e80a41f96f1b867f253547241871827ef1
commit 4cf2b4e80a41f96f1b867f253547241871827ef1
Author: Stefan Liebler <stli@linux.vnet.ibm.com>
Date: Mon Apr 4 13:20:27 2016 +0200
S390: Extend structs La_s390_regs / La_s390_retval with vector-registers.
Starting with z13, vector registers can also occur as argument registers.
Thus the passed input/output register structs for
la_s390_[32|64]_gnu_plt[enter|exit] functions should reflect those new
registers. This patch extends these structs La_s390_regs and La_s390_retval
and adjusts _dl_runtime_profile() to handle those fields in case of
running on a z13 machine.
ChangeLog:
* sysdeps/s390/bits/link.h: (La_s390_vr) New typedef.
(La_s390_32_regs): Append vector register lr_v24-lr_v31.
(La_s390_64_regs): Likewise.
(La_s390_32_retval): Append vector register lrv_v24.
(La_s390_64_retval): Likeweise.
* sysdeps/s390/s390-32/dl-trampoline.h (_dl_runtime_profile):
Handle extended structs La_s390_32_regs and La_s390_32_retval.
* sysdeps/s390/s390-64/dl-trampoline.h (_dl_runtime_profile):
Handle extended structs La_s390_64_regs and La_s390_64_retval.
(cherry picked from commit 5cdd1989d1d2f135d02e66250f37ba8e767f9772)
diff --git a/ChangeLog b/ChangeLog
index bcacb57..c47c0b5 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,17 @@
2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+ * sysdeps/s390/bits/link.h: (La_s390_vr) New typedef.
+ (La_s390_32_regs): Append vector register lr_v24-lr_v31.
+ (La_s390_64_regs): Likewise.
+ (La_s390_32_retval): Append vector register lrv_v24.
+ (La_s390_64_retval): Likeweise.
+ * sysdeps/s390/s390-32/dl-trampoline.h (_dl_runtime_profile):
+ Handle extended structs La_s390_32_regs and La_s390_32_retval.
+ * sysdeps/s390/s390-64/dl-trampoline.h (_dl_runtime_profile):
+ Handle extended structs La_s390_64_regs and La_s390_64_retval.
+
+2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+
* sysdeps/s390/s390-32/dl-trampoline.S: Include dl-trampoline.h twice
to create a non-vector/vector version for _dl_runtime_resolve and
_dl_runtime_profile. Move implementation to ...
diff --git a/sysdeps/s390/bits/link.h b/sysdeps/s390/bits/link.h
index a5ab546..9de8ebe 100644
--- a/sysdeps/s390/bits/link.h
+++ b/sysdeps/s390/bits/link.h
@@ -19,6 +19,9 @@
# error "Never include <bits/link.h> directly; use <link.h> instead."
#endif
+#if defined HAVE_S390_VX_ASM_SUPPORT
+typedef char La_s390_vr[16];
+#endif
#if __ELF_NATIVE_CLASS == 32
@@ -32,6 +35,16 @@ typedef struct La_s390_32_regs
uint32_t lr_r6;
double lr_fp0;
double lr_fp2;
+# if defined HAVE_S390_VX_ASM_SUPPORT
+ La_s390_vr lr_v24;
+ La_s390_vr lr_v25;
+ La_s390_vr lr_v26;
+ La_s390_vr lr_v27;
+ La_s390_vr lr_v28;
+ La_s390_vr lr_v29;
+ La_s390_vr lr_v30;
+ La_s390_vr lr_v31;
+# endif
} La_s390_32_regs;
/* Return values for calls from PLT on s390-32. */
@@ -40,6 +53,9 @@ typedef struct La_s390_32_retval
uint32_t lrv_r2;
uint32_t lrv_r3;
double lrv_fp0;
+# if defined HAVE_S390_VX_ASM_SUPPORT
+ La_s390_vr lrv_v24;
+# endif
} La_s390_32_retval;
@@ -77,6 +93,16 @@ typedef struct La_s390_64_regs
double lr_fp2;
double lr_fp4;
double lr_fp6;
+# if defined HAVE_S390_VX_ASM_SUPPORT
+ La_s390_vr lr_v24;
+ La_s390_vr lr_v25;
+ La_s390_vr lr_v26;
+ La_s390_vr lr_v27;
+ La_s390_vr lr_v28;
+ La_s390_vr lr_v29;
+ La_s390_vr lr_v30;
+ La_s390_vr lr_v31;
+# endif
} La_s390_64_regs;
/* Return values for calls from PLT on s390-64. */
@@ -84,6 +110,9 @@ typedef struct La_s390_64_retval
{
uint64_t lrv_r2;
double lrv_fp0;
+# if defined HAVE_S390_VX_ASM_SUPPORT
+ La_s390_vr lrv_v24;
+# endif
} La_s390_64_retval;
diff --git a/sysdeps/s390/s390-32/dl-trampoline.h b/sysdeps/s390/s390-32/dl-trampoline.h
index 5627567..086449f 100644
--- a/sysdeps/s390/s390-32/dl-trampoline.h
+++ b/sysdeps/s390/s390-32/dl-trampoline.h
@@ -112,28 +112,31 @@ _dl_runtime_resolve:
cfi_startproc
.align 16
_dl_runtime_profile:
- stm %r2,%r6,32(%r15) # save registers
- cfi_offset (r2, -64) # + r6 needed as arg for
- cfi_offset (r3, -60) # _dl_profile_fixup
- cfi_offset (r4, -56)
- cfi_offset (r5, -52)
- cfi_offset (r6, -48)
- std %f0,56(%r15)
- cfi_offset (f0, -40)
- std %f2,64(%r15)
- cfi_offset (f2, -32)
st %r12,12(%r15) # r12 is used as backup of r15
cfi_offset (r12, -84)
st %r14,16(%r15)
cfi_offset (r14, -80)
lr %r12,%r15 # backup stack pointer
cfi_def_cfa_register (12)
+ ahi %r15,-264 # create stack frame:
+ # 96 + sizeof(La_s390_32_regs)
+ st %r12,0(%r15) # save backchain
+
+ stm %r2,%r6,96(%r15) # save registers
+ cfi_offset (r2, -264) # + r6 needed as arg for
+ cfi_offset (r3, -260) # _dl_profile_fixup
+ cfi_offset (r4, -256)
+ cfi_offset (r5, -252)
+ cfi_offset (r6, -248)
+ std %f0,120(%r15)
+ cfi_offset (f0, -240)
+ std %f2,128(%r15)
+ cfi_offset (f2, -232)
#ifdef RESTORE_VRS
- ahi %r15,-224 # create stack frame
.machine push
.machine "z13"
.machinemode "zarch_nohighgprs"
- vstm %v24,%v31,96(%r15) # store call-clobbered vr arguments
+ vstm %v24,%v31,136(%r15) # store call-clobbered vr arguments
cfi_offset (v24, -224)
cfi_offset (v25, -208)
cfi_offset (v26, -192)
@@ -143,31 +146,31 @@ _dl_runtime_profile:
cfi_offset (v30, -128)
cfi_offset (v31, -112)
.machine pop
-#else
- ahi %r15,-96 # create stack frame
#endif
- st %r12,0(%r15) # save backchain
+
lm %r2,%r3,24(%r12) # load arguments saved by PLT
lr %r4,%r14 # return address as third parameter
basr %r1,0
0: l %r14,6f-0b(%r1)
- la %r5,32(%r12) # pointer to struct La_s390_32_regs
+ la %r5,96(%r15) # pointer to struct La_s390_32_regs
la %r6,20(%r12) # long int * framesize
bas %r14,0(%r14,%r1) # call resolver
lr %r1,%r2 # function addr returned in r2
- ld %f0,56(%r12) # restore call-clobbered arg fprs
- ld %f2,64(%r12)
+ ld %f0,120(%r15) # restore call-clobbered arg fprs
+ ld %f2,128(%r15)
#ifdef RESTORE_VRS
.machine push
.machine "z13"
.machinemode "zarch_nohighgprs"
- vlm %v24,%v31,96(%r15) # restore call-clobbered arg vrs
+ vlm %v24,%v31,136(%r15) # restore call-clobbered arg vrs
.machine pop
#endif
icm %r0,15,20(%r12) # load & test framesize
jnm 2f
- lm %r2,%r6,32(%r12)
+ lm %r2,%r6,96(%r15) # framesize < 0 means no pltexit call
+ # so we can do a tail call without
+ # copying the arg overflow area
lr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
l %r14,16(%r15) # restore registers
@@ -175,7 +178,9 @@ _dl_runtime_profile:
br %r1 # tail-call to the resolved function
cfi_def_cfa_register (12)
-2: jz 4f # framesize == 0 ?
+2: la %r4,96(%r15) # pointer to struct La_s390_32_regs
+ st %r4,32(%r12)
+ jz 4f # framesize == 0 ?
ahi %r0,7 # align framesize to 8
lhi %r2,-8
nr %r0,%r2
@@ -188,24 +193,35 @@ _dl_runtime_profile:
la %r2,8(%r2)
la %r3,8(%r3)
brct %r0,3b
-4: lm %r2,%r6,32(%r12) # load register parameters
+4: lm %r2,%r6,0(%r4) # load register parameters
basr %r14,%r1 # call resolved function
- stm %r2,%r3,72(%r12) # store return values r2, r3, f0
- std %f0,80(%r12) # to struct La_s390_32_retval
- lm %r2,%r3,24(%r12) # load arguments saved by PLT
+ stm %r2,%r3,40(%r12) # store return values r2, r3, f0
+ std %f0,48(%r12) # to struct La_s390_32_retval
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vst %v24,56(%r12) # store return value v24
+ .machine pop
+#endif
+ lm %r2,%r4,24(%r12) # r2, r3: load arguments saved by PLT
+ # r4: pointer to struct La_s390_32_regs
basr %r1,0
5: l %r14,7f-5b(%r1)
- la %r4,32(%r12) # pointer to struct La_s390_32_regs
- la %r5,72(%r12) # pointer to struct La_s390_32_retval
+ la %r5,40(%r12) # pointer to struct La_s390_32_retval
bas %r14,0(%r14,%r1) # call _dl_call_pltexit
lr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
l %r14,16(%r15) # restore registers
l %r12,12(%r15)
- l %r2,72(%r15) # restore return values
- l %r3,76(%r15)
- ld %f0,80(%r15)
+ lm %r2,%r3,40(%r15) # restore return values
+ ld %f0,48(%r15)
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vl %v24,56(%r15) # restore return value v24
+ .machine pop
+#endif
br %r14
6: .long _dl_profile_fixup - 0b
diff --git a/sysdeps/s390/s390-64/dl-trampoline.h b/sysdeps/s390/s390-64/dl-trampoline.h
index 658e3a3..33ea3de 100644
--- a/sysdeps/s390/s390-64/dl-trampoline.h
+++ b/sysdeps/s390/s390-64/dl-trampoline.h
@@ -109,31 +109,34 @@ _dl_runtime_resolve:
cfi_startproc
.align 16
_dl_runtime_profile:
- stmg %r2,%r6,64(%r15) # save call-clobbered arg regs
- cfi_offset (r2, -96) # + r6 needed as arg for
- cfi_offset (r3, -88) # _dl_profile_fixup
- cfi_offset (r4, -80)
- cfi_offset (r5, -72)
- cfi_offset (r6, -64)
- std %f0,104(%r15)
- cfi_offset (f0, -56)
- std %f2,112(%r15)
- cfi_offset (f2, -48)
- std %f4,120(%r15)
- cfi_offset (f4, -40)
- std %f6,128(%r15)
- cfi_offset (f6, -32)
stg %r12,24(%r15) # r12 is used as backup of r15
cfi_offset (r12, -136)
stg %r14,32(%r15)
cfi_offset (r14, -128)
lgr %r12,%r15 # backup stack pointer
cfi_def_cfa_register (12)
+ aghi %r15,-360 # create stack frame:
+ # 160 + sizeof(La_s390_64_regs)
+ stg %r12,0(%r15) # save backchain
+
+ stmg %r2,%r6,160(%r15) # save call-clobbered arg regs
+ cfi_offset (r2, -360) # + r6 needed as arg for
+ cfi_offset (r3, -352) # _dl_profile_fixup
+ cfi_offset (r4, -344)
+ cfi_offset (r5, -336)
+ cfi_offset (r6, -328)
+ std %f0,200(%r15)
+ cfi_offset (f0, -320)
+ std %f2,208(%r15)
+ cfi_offset (f2, -312)
+ std %f4,216(%r15)
+ cfi_offset (f4, -304)
+ std %f6,224(%r15)
+ cfi_offset (f6, -296)
#ifdef RESTORE_VRS
- aghi %r15,-288 # create stack frame
.machine push
.machine "z13"
- vstm %v24,%v31,160(%r15)# store call-clobbered vector argument registers
+ vstm %v24,%v31,232(%r15) # store call-clobbered vector arguments
cfi_offset (v24, -288)
cfi_offset (v25, -272)
cfi_offset (v26, -256)
@@ -143,31 +146,28 @@ _dl_runtime_profile:
cfi_offset (v30, -192)
cfi_offset (v31, -176)
.machine pop
-#else
- aghi %r15,-160 # create stack frame
#endif
- stg %r12,0(%r15) # save backchain
lmg %r2,%r3,48(%r12) # load arguments saved by PLT
lgr %r4,%r14 # return address as third parameter
- la %r5,64(%r12) # pointer to struct La_s390_64_regs
+ la %r5,160(%r15) # pointer to struct La_s390_64_regs
la %r6,40(%r12) # long int * framesize
brasl %r14,_dl_profile_fixup # call resolver
lgr %r1,%r2 # function addr returned in r2
- ld %f0,104(%r12) # restore call-clobbered arg fprs
- ld %f2,112(%r12)
- ld %f4,120(%r12)
- ld %f6,128(%r12)
+ ld %f0,200(%r15) # restore call-clobbered arg fprs
+ ld %f2,208(%r15)
+ ld %f4,216(%r15)
+ ld %f6,224(%r15)
#ifdef RESTORE_VRS
.machine push
.machine "z13"
- vlm %v24,%v31,160(%r15) # restore call-clobbered arg vrs
+ vlm %v24,%v31,232(%r15) # restore call-clobbered arg vrs
.machine pop
#endif
lg %r0,40(%r12) # load framesize
ltgr %r0,%r0
jnm 1f
- lmg %r2,%r6,64(%r12) # framesize < 0 means no pltexit call
+ lmg %r2,%r6,160(%r15) # framesize < 0 means no pltexit call
# so we can do a tail call without
# copying the arg overflow area
lgr %r15,%r12 # remove stack frame
@@ -177,7 +177,9 @@ _dl_runtime_profile:
br %r1 # tail-call to resolved function
cfi_def_cfa_register (12)
-1: jz 4f # framesize == 0 ?
+1: la %r4,160(%r15) # pointer to struct La_s390_64_regs
+ stg %r4,64(%r12)
+ jz 4f # framesize == 0 ?
aghi %r0,7 # align framesize to 8
nill %r0,0xfff8
slgr %r15,%r0 # make room for framesize bytes
@@ -189,21 +191,33 @@ _dl_runtime_profile:
la %r2,8(%r2) # depending on framesize
la %r3,8(%r3)
brctg %r0,3b
-4: lmg %r2,%r6,64(%r12) # restore call-clobbered arg gprs
+4: lmg %r2,%r6,0(%r4) # restore call-clobbered arg gprs
basr %r14,%r1 # call resolved function
- stg %r2,136(%r12) # store return values r2, f0
- std %f0,144(%r12) # to struct La_s390_64_retval
- lmg %r2,%r3,48(%r12) # load arguments saved by PLT
- la %r4,64(%r12) # pointer to struct La_s390_64_regs
- la %r5,136(%r12) # pointer to struct La_s390_64_retval
+ stg %r2,72(%r12) # store return values r2, f0
+ std %f0,80(%r12) # to struct La_s390_64_retval
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vst %v24,88(%r12) # store return value v24
+ .machine pop
+#endif
+ lmg %r2,%r4,48(%r12) # r2, r3: load arguments saved by PLT
+ # r4: pointer to struct La_s390_64_regs
+ la %r5,72(%r12) # pointer to struct La_s390_64_retval
brasl %r14,_dl_call_pltexit
lgr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
lg %r14,32(%r15) # restore registers
lg %r12,24(%r15)
- lg %r2,136(%r15) # restore return values
- ld %f0,144(%r15)
+ lg %r2,72(%r15) # restore return values
+ ld %f0,80(%r15)
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vl %v24,88(%r15) # restore return value v24
+ .machine pop
+#endif
br %r14 # Jump back to caller
cfi_endproc
http://sourceware.org/git/gitweb.cgi?p=glibc.git;a=commitdiff;h=4b7ba5b8c4722d610862744c619bcaa5ad655385
commit 4b7ba5b8c4722d610862744c619bcaa5ad655385
Author: Stefan Liebler <stli@linux.vnet.ibm.com>
Date: Mon Apr 4 13:20:27 2016 +0200
S390: Save and restore fprs/vrs while resolving symbols.
On s390, no fpr/vrs were saved while resolving a symbol
via _dl_runtime_resolve/_dl_runtime_profile.
According to the abi, the fpr-arguments are defined as call clobbered.
In leaf-functions, gcc 4.9 and newer can use fprs for saving/restoring gprs
instead of saving them to the stack.
If gcc do this in one of the resolver-functions, then the floating point
arguments of a library-function are invalid for the first library-function-call.
Thus, this patch saves/restores the fprs around the resolving code.
The same could occur for vector registers. Furthermore an ifunc-resolver
could also clobber the vector/floating point argument registers.
Thus this patch provides the further variants _dl_runtime_resolve_vx/
_dl_runtime_profile_vx, which are used if the kernel claims, that
we run on a machine with vector registers.
Furthermore, if _dl_runtime_profile calls _dl_call_pltexit,
the pointers to inregs-/outregs-structs were setup invalid.
Now they point to the correct location in the stack-frame.
Before branching back to the caller, the return values are now
restored instead of containing the return values of the
_dl_call_pltexit() call.
On s390-32, an endless loop occurs if _dl_call_pltexit() should be called.
Now, this code-path branches to this function instead of just after the
preceding basr-instruction.
ChangeLog:
* sysdeps/s390/s390-32/dl-trampoline.S: Include dl-trampoline.h twice
to create a non-vector/vector version for _dl_runtime_resolve and
_dl_runtime_profile. Move implementation to ...
* sysdeps/s390/s390-32/dl-trampoline.h: ... here.
(_dl_runtime_resolve) Save and restore fpr/vrs.
(_dl_runtime_profile) Save and restore vrs and fix some issues
if _dl_call_pltexit is called.
* sysdeps/s390/s390-32/dl-machine.h (elf_machine_runtime_setup):
Choose the correct resolver function if running on a machine with vx.
* sysdeps/s390/s390-64/dl-trampoline.S: Include dl-trampoline.h twice
to create a non-vector/vector version for _dl_runtime_resolve and
_dl_runtime_profile. Move implementation to ...
* sysdeps/s390/s390-64/dl-trampoline.h: ... here.
(_dl_runtime_resolve) Save and restore fpr/vrs.
(_dl_runtime_profile) Save and restore vrs and fix some issues
* sysdeps/s390/s390-64/dl-machine.h: (elf_machine_runtime_setup):
Choose the correct resolver function if running on a machine with vx.
(cherry picked from commit 4603c51ef7989d7eb800cdd6f42aab206f891077
and commit d8a012c5c9e4bfc1b8db2bc6deacb85b44a2e1eb)
diff --git a/ChangeLog b/ChangeLog
index c68136c..bcacb57 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,25 @@
2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+ * sysdeps/s390/s390-32/dl-trampoline.S: Include dl-trampoline.h twice
+ to create a non-vector/vector version for _dl_runtime_resolve and
+ _dl_runtime_profile. Move implementation to ...
+ * sysdeps/s390/s390-32/dl-trampoline.h: ... here.
+ (_dl_runtime_resolve) Save and restore fpr/vrs.
+ (_dl_runtime_profile) Save and restore vrs and fix some issues
+ if _dl_call_pltexit is called.
+ * sysdeps/s390/s390-32/dl-machine.h (elf_machine_runtime_setup):
+ Choose the correct resolver function if running on a machine with vx.
+ * sysdeps/s390/s390-64/dl-trampoline.S: Include dl-trampoline.h twice
+ to create a non-vector/vector version for _dl_runtime_resolve and
+ _dl_runtime_profile. Move implementation to ...
+ * sysdeps/s390/s390-64/dl-trampoline.h: ... here.
+ (_dl_runtime_resolve) Save and restore fpr/vrs.
+ (_dl_runtime_profile) Save and restore vrs and fix some issues
+ * sysdeps/s390/s390-64/dl-machine.h: (elf_machine_runtime_setup):
+ Choose the correct resolver function if running on a machine with vx.
+
+2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+
* config.h.in (HAVE_S390_VX_ASM_SUPPORT): New macro undefine.
* sysdeps/s390/configure.ac: Add test for S390 vector instruction
assembler support.
diff --git a/sysdeps/s390/s390-32/dl-machine.h b/sysdeps/s390/s390-32/dl-machine.h
index 527233b..4539592 100644
--- a/sysdeps/s390/s390-32/dl-machine.h
+++ b/sysdeps/s390/s390-32/dl-machine.h
@@ -89,6 +89,11 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
{
extern void _dl_runtime_resolve (Elf32_Word);
extern void _dl_runtime_profile (Elf32_Word);
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ extern void _dl_runtime_resolve_vx (Elf32_Word);
+ extern void _dl_runtime_profile_vx (Elf32_Word);
+#endif
+
if (l->l_info[DT_JMPREL] && lazy)
{
@@ -116,7 +121,14 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
end in this function. */
if (__glibc_unlikely (profile))
{
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ if (GLRO(dl_hwcap) & HWCAP_S390_VX)
+ got[2] = (Elf32_Addr) &_dl_runtime_profile_vx;
+ else
+ got[2] = (Elf32_Addr) &_dl_runtime_profile;
+#else
got[2] = (Elf32_Addr) &_dl_runtime_profile;
+#endif
if (GLRO(dl_profile) != NULL
&& _dl_name_match_p (GLRO(dl_profile), l))
@@ -125,9 +137,18 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
GL(dl_profile_map) = l;
}
else
- /* This function will get called to fix up the GOT entry indicated by
- the offset on the stack, and then jump to the resolved address. */
- got[2] = (Elf32_Addr) &_dl_runtime_resolve;
+ {
+ /* This function will get called to fix up the GOT entry indicated by
+ the offset on the stack, and then jump to the resolved address. */
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ if (GLRO(dl_hwcap) & HWCAP_S390_VX)
+ got[2] = (Elf32_Addr) &_dl_runtime_resolve_vx;
+ else
+ got[2] = (Elf32_Addr) &_dl_runtime_resolve;
+#else
+ got[2] = (Elf32_Addr) &_dl_runtime_resolve;
+#endif
+ }
}
return lazy;
diff --git a/sysdeps/s390/s390-32/dl-trampoline.S b/sysdeps/s390/s390-32/dl-trampoline.S
index d3a8548..85e73d9 100644
--- a/sysdeps/s390/s390-32/dl-trampoline.S
+++ b/sysdeps/s390/s390-32/dl-trampoline.S
@@ -16,130 +16,18 @@
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
-/* This code is used in dl-runtime.c to call the `fixup' function
- and then redirect to the address it returns. */
-
-/* The PLT stubs will call _dl_runtime_resolve/_dl_runtime_profile
- * with the following linkage:
- * r2 - r6 : parameter registers
- * f0, f2 : floating point parameter registers
- * 24(r15), 28(r15) : PLT arguments PLT1, PLT2
- * 96(r15) : additional stack parameters
- * The normal clobber rules for function calls apply:
- * r0 - r5 : call clobbered
- * r6 - r13 : call saved
- * r14 : return address (call clobbered)
- * r15 : stack pointer (call saved)
- * f4, f6 : call saved
- * f0 - f3, f5, f7 - f15 : call clobbered
- */
-
#include <sysdep.h>
.text
- .globl _dl_runtime_resolve
- .type _dl_runtime_resolve, @function
- cfi_startproc
- .align 16
-_dl_runtime_resolve:
- stm %r2,%r5,32(%r15) # save registers
- st %r14,8(%r15)
- cfi_offset (r14, -88)
- lr %r0,%r15 # create stack frame
- ahi %r15,-96
- cfi_adjust_cfa_offset (96)
- st 0,0(%r15)
- lm %r2,%r3,120(%r15) # load args saved by PLT
- basr %r1,0
-0: l %r14,1f-0b(%r1)
- bas %r14,0(%r14,%r1) # call resolver
- lr %r1,%r2 # function addr returned in r2
- ahi %r15,96 # remove stack frame
- cfi_adjust_cfa_offset (-96)
- l %r14,8(15) # restore registers
- lm %r2,%r5,32(%r15)
- br %r1
-1: .long _dl_fixup - 0b
- cfi_endproc
- .size _dl_runtime_resolve, .-_dl_runtime_resolve
-
-
-#ifndef PROF
- .globl _dl_runtime_profile
- .type _dl_runtime_profile, @function
- cfi_startproc
- .align 16
-_dl_runtime_profile:
- stm %r2,%r6,32(%r15) # save registers
- std %f0,56(%r15)
- std %f2,64(%r15)
- st %r6,8(%r15)
- st %r12,12(%r15)
- st %r14,16(%r15)
- cfi_offset (r6, -64)
- cfi_offset (f0, -40)
- cfi_offset (f2, -32)
- cfi_offset (r12, -84)
- cfi_offset (r14, -80)
- lr %r12,%r15 # create stack frame
- cfi_def_cfa_register (12)
- ahi %r15,-96
- st %r12,0(%r15)
- lm %r2,%r3,24(%r12) # load arguments saved by PLT
- lr %r4,%r14 # return address as third parameter
- basr %r1,0
-0: l %r14,6f-0b(%r1)
- la %r5,32(%r12) # pointer to struct La_s390_32_regs
- la %r6,20(%r12) # long int * framesize
- bas %r14,0(%r14,%r1) # call resolver
- lr %r1,%r2 # function addr returned in r2
- icm %r0,15,20(%r12) # load & test framesize
- jnm 2f
-
- lm %r2,%r6,32(%r12)
- ld %f0,56(%r12)
- ld %f2,64(%r12)
- lr %r15,%r12 # remove stack frame
- cfi_def_cfa_register (15)
- l %r14,16(%r15) # restore registers
- l %r12,12(%r15)
- br %r1 # tail-call to the resolved function
-
- cfi_def_cfa_register (12)
-2: jz 4f # framesize == 0 ?
- ahi %r0,7 # align framesize to 8
- lhi %r2,-8
- nr %r0,%r2
- slr %r15,%r0 # make room for framesize bytes
- st %r12,0(%r15)
- la %r2,96(%r15)
- la %r3,96(%r12)
- srl %r0,3
-3: mvc 0(8,%r2),0(%r3) # copy additional parameters
- la %r2,8(%r2)
- la %r3,8(%r3)
- brct %r0,3b
-4: lm %r2,%r6,32(%r12) # load register parameters
- ld %f0,56(%r12)
- ld %f2,64(%r12)
- basr %r14,%r1 # call resolved function
- stm %r2,%r3,72(%r12)
- std %f0,80(%r12)
- lm %r2,%r3,24(%r12) # load arguments saved by PLT
- basr %r1,0
-5: l %r14,7f-5b(%r1)
- la %r4,32(%r12) # pointer to struct La_s390_32_regs
- la %r5,72(%r12) # pointer to struct La_s390_32_retval
- basr %r14,%r1 # call _dl_call_pltexit
-
- lr %r15,%r12 # remove stack frame
- cfi_def_cfa_register (15)
- l %r14,16(%r15) # restore registers
- l %r12,12(%r15)
- br %r14
-
-6: .long _dl_profile_fixup - 0b
-7: .long _dl_call_pltexit - 5b
- cfi_endproc
- .size _dl_runtime_profile, .-_dl_runtime_profile
+/* Create variant of _dl_runtime_resolve/profile for machines before z13.
+ No vector registers are saved/restored. */
+#include <dl-trampoline.h>
+
+#if defined HAVE_S390_VX_ASM_SUPPORT
+/* Create variant of _dl_runtime_resolve/profile for z13 and newer.
+ The vector registers are saved/restored, too.*/
+# define _dl_runtime_resolve _dl_runtime_resolve_vx
+# define _dl_runtime_profile _dl_runtime_profile_vx
+# define RESTORE_VRS
+# include <dl-trampoline.h>
#endif
diff --git a/sysdeps/s390/s390-32/dl-trampoline.S b/sysdeps/s390/s390-32/dl-trampoline.h
similarity index 58%
copy from sysdeps/s390/s390-32/dl-trampoline.S
copy to sysdeps/s390/s390-32/dl-trampoline.h
index d3a8548..5627567 100644
--- a/sysdeps/s390/s390-32/dl-trampoline.S
+++ b/sysdeps/s390/s390-32/dl-trampoline.h
@@ -1,5 +1,5 @@
/* PLT trampolines. s390 version.
- Copyright (C) 2005-2014 Free Software Foundation, Inc.
+ Copyright (C) 2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
@@ -23,40 +23,82 @@
* with the following linkage:
* r2 - r6 : parameter registers
* f0, f2 : floating point parameter registers
+ * v24, v26, v28, v30, v25, v27, v29, v31 : vector parameter registers
* 24(r15), 28(r15) : PLT arguments PLT1, PLT2
* 96(r15) : additional stack parameters
* The normal clobber rules for function calls apply:
* r0 - r5 : call clobbered
- * r6 - r13 : call saved
+ * r6 - r13 : call saved
* r14 : return address (call clobbered)
* r15 : stack pointer (call saved)
* f4, f6 : call saved
* f0 - f3, f5, f7 - f15 : call clobbered
+ * v0 - v3, v5, v7 - v15 : bytes 0-7 overlap with fprs: call clobbered
+ bytes 8-15: call clobbered
+ * v4, v6 : bytes 0-7 overlap with f4, f6: call saved
+ bytes 8-15: call clobbered
+ * v16 - v31 : call clobbered
*/
-#include <sysdep.h>
- .text
.globl _dl_runtime_resolve
.type _dl_runtime_resolve, @function
cfi_startproc
.align 16
_dl_runtime_resolve:
stm %r2,%r5,32(%r15) # save registers
+ cfi_offset (r2, -64)
+ cfi_offset (r3, -60)
+ cfi_offset (r4, -56)
+ cfi_offset (r5, -52)
+ std %f0,56(%r15)
+ cfi_offset (f0, -40)
+ std %f2,64(%r15)
+ cfi_offset (f2, -32)
st %r14,8(%r15)
cfi_offset (r14, -88)
- lr %r0,%r15 # create stack frame
- ahi %r15,-96
+ lr %r0,%r15
+ lm %r2,%r3,24(%r15) # load args saved by PLT
+#ifdef RESTORE_VRS
+ ahi %r15,-224 # create stack frame
+ cfi_adjust_cfa_offset (224)
+ .machine push
+ .machine "z13"
+ .machinemode "zarch_nohighgprs"
+ vstm %v24,%v31,96(%r15) # store call-clobbered vr arguments
+ cfi_offset (v24, -224)
+ cfi_offset (v25, -208)
+ cfi_offset (v26, -192)
+ cfi_offset (v27, -176)
+ cfi_offset (v28, -160)
+ cfi_offset (v29, -144)
+ cfi_offset (v30, -128)
+ cfi_offset (v31, -112)
+ .machine pop
+#else
+ ahi %r15,-96 # create stack frame
cfi_adjust_cfa_offset (96)
- st 0,0(%r15)
- lm %r2,%r3,120(%r15) # load args saved by PLT
+#endif
+ st %r0,0(%r15) # write backchain
basr %r1,0
0: l %r14,1f-0b(%r1)
- bas %r14,0(%r14,%r1) # call resolver
+ bas %r14,0(%r14,%r1) # call _dl_fixup
lr %r1,%r2 # function addr returned in r2
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ .machinemode "zarch_nohighgprs"
+ vlm %v24,%v31,96(%r15) # restore vector registers
+ .machine pop
+ ahi %r15,224 # remove stack frame
+ cfi_adjust_cfa_offset (-224)
+#else
ahi %r15,96 # remove stack frame
cfi_adjust_cfa_offset (-96)
+#endif
l %r14,8(15) # restore registers
+ ld %f0,56(%r15)
+ ld %f2,64(%r15)
lm %r2,%r5,32(%r15)
br %r1
1: .long _dl_fixup - 0b
@@ -71,20 +113,40 @@ _dl_runtime_resolve:
.align 16
_dl_runtime_profile:
stm %r2,%r6,32(%r15) # save registers
+ cfi_offset (r2, -64) # + r6 needed as arg for
+ cfi_offset (r3, -60) # _dl_profile_fixup
+ cfi_offset (r4, -56)
+ cfi_offset (r5, -52)
+ cfi_offset (r6, -48)
std %f0,56(%r15)
- std %f2,64(%r15)
- st %r6,8(%r15)
- st %r12,12(%r15)
- st %r14,16(%r15)
- cfi_offset (r6, -64)
cfi_offset (f0, -40)
+ std %f2,64(%r15)
cfi_offset (f2, -32)
+ st %r12,12(%r15) # r12 is used as backup of r15
cfi_offset (r12, -84)
+ st %r14,16(%r15)
cfi_offset (r14, -80)
- lr %r12,%r15 # create stack frame
+ lr %r12,%r15 # backup stack pointer
cfi_def_cfa_register (12)
- ahi %r15,-96
- st %r12,0(%r15)
+#ifdef RESTORE_VRS
+ ahi %r15,-224 # create stack frame
+ .machine push
+ .machine "z13"
+ .machinemode "zarch_nohighgprs"
+ vstm %v24,%v31,96(%r15) # store call-clobbered vr arguments
+ cfi_offset (v24, -224)
+ cfi_offset (v25, -208)
+ cfi_offset (v26, -192)
+ cfi_offset (v27, -176)
+ cfi_offset (v28, -160)
+ cfi_offset (v29, -144)
+ cfi_offset (v30, -128)
+ cfi_offset (v31, -112)
+ .machine pop
+#else
+ ahi %r15,-96 # create stack frame
+#endif
+ st %r12,0(%r15) # save backchain
lm %r2,%r3,24(%r12) # load arguments saved by PLT
lr %r4,%r14 # return address as third parameter
basr %r1,0
@@ -93,12 +155,19 @@ _dl_runtime_profile:
la %r6,20(%r12) # long int * framesize
bas %r14,0(%r14,%r1) # call resolver
lr %r1,%r2 # function addr returned in r2
+ ld %f0,56(%r12) # restore call-clobbered arg fprs
+ ld %f2,64(%r12)
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ .machinemode "zarch_nohighgprs"
+ vlm %v24,%v31,96(%r15) # restore call-clobbered arg vrs
+ .machine pop
+#endif
icm %r0,15,20(%r12) # load & test framesize
jnm 2f
lm %r2,%r6,32(%r12)
- ld %f0,56(%r12)
- ld %f2,64(%r12)
lr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
l %r14,16(%r15) # restore registers
@@ -111,7 +180,7 @@ _dl_runtime_profile:
lhi %r2,-8
nr %r0,%r2
slr %r15,%r0 # make room for framesize bytes
- st %r12,0(%r15)
+ st %r12,0(%r15) # save backchain
la %r2,96(%r15)
la %r3,96(%r12)
srl %r0,3
@@ -120,22 +189,23 @@ _dl_runtime_profile:
la %r3,8(%r3)
brct %r0,3b
4: lm %r2,%r6,32(%r12) # load register parameters
- ld %f0,56(%r12)
- ld %f2,64(%r12)
basr %r14,%r1 # call resolved function
- stm %r2,%r3,72(%r12)
- std %f0,80(%r12)
+ stm %r2,%r3,72(%r12) # store return values r2, r3, f0
+ std %f0,80(%r12) # to struct La_s390_32_retval
lm %r2,%r3,24(%r12) # load arguments saved by PLT
basr %r1,0
5: l %r14,7f-5b(%r1)
la %r4,32(%r12) # pointer to struct La_s390_32_regs
la %r5,72(%r12) # pointer to struct La_s390_32_retval
- basr %r14,%r1 # call _dl_call_pltexit
+ bas %r14,0(%r14,%r1) # call _dl_call_pltexit
lr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
l %r14,16(%r15) # restore registers
l %r12,12(%r15)
+ l %r2,72(%r15) # restore return values
+ l %r3,76(%r15)
+ ld %f0,80(%r15)
br %r14
6: .long _dl_profile_fixup - 0b
diff --git a/sysdeps/s390/s390-64/dl-machine.h b/sysdeps/s390/s390-64/dl-machine.h
index e48d355..c65c850 100644
--- a/sysdeps/s390/s390-64/dl-machine.h
+++ b/sysdeps/s390/s390-64/dl-machine.h
@@ -26,6 +26,7 @@
#include <sys/param.h>
#include <string.h>
#include <link.h>
+#include <sysdeps/s390/dl-procinfo.h>
#include <dl-irel.h>
#define ELF_MACHINE_IRELATIVE R_390_IRELATIVE
@@ -78,6 +79,10 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
{
extern void _dl_runtime_resolve (Elf64_Word);
extern void _dl_runtime_profile (Elf64_Word);
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ extern void _dl_runtime_resolve_vx (Elf64_Word);
+ extern void _dl_runtime_profile_vx (Elf64_Word);
+#endif
if (l->l_info[DT_JMPREL] && lazy)
{
@@ -105,7 +110,14 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
end in this function. */
if (__glibc_unlikely (profile))
{
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ if (GLRO(dl_hwcap) & HWCAP_S390_VX)
+ got[2] = (Elf64_Addr) &_dl_runtime_profile_vx;
+ else
+ got[2] = (Elf64_Addr) &_dl_runtime_profile;
+#else
got[2] = (Elf64_Addr) &_dl_runtime_profile;
+#endif
if (GLRO(dl_profile) != NULL
&& _dl_name_match_p (GLRO(dl_profile), l))
@@ -114,9 +126,18 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
GL(dl_profile_map) = l;
}
else
- /* This function will get called to fix up the GOT entry indicated by
- the offset on the stack, and then jump to the resolved address. */
- got[2] = (Elf64_Addr) &_dl_runtime_resolve;
+ {
+ /* This function will get called to fix up the GOT entry indicated by
+ the offset on the stack, and then jump to the resolved address. */
+#if defined HAVE_S390_VX_ASM_SUPPORT
+ if (GLRO(dl_hwcap) & HWCAP_S390_VX)
+ got[2] = (Elf64_Addr) &_dl_runtime_resolve_vx;
+ else
+ got[2] = (Elf64_Addr) &_dl_runtime_resolve;
+#else
+ got[2] = (Elf64_Addr) &_dl_runtime_resolve;
+#endif
+ }
}
return lazy;
diff --git a/sysdeps/s390/s390-64/dl-trampoline.S b/sysdeps/s390/s390-64/dl-trampoline.S
index 87c6d50..f089266 100644
--- a/sysdeps/s390/s390-64/dl-trampoline.S
+++ b/sysdeps/s390/s390-64/dl-trampoline.S
@@ -16,126 +16,18 @@
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
-/* The PLT stubs will call _dl_runtime_resolve/_dl_runtime_profile
- * with the following linkage:
- * r2 - r6 : parameter registers
- * f0, f2, f4, f6 : floating point parameter registers
- * 48(r15), 56(r15) : PLT arguments PLT1, PLT2
- * 160(r15) : additional stack parameters
- * The normal clobber rules for function calls apply:
- * r0 - r5 : call clobbered
- * r6 - r13 : call saved
- * r14 : return address (call clobbered)
- * r15 : stack pointer (call saved)
- * f1, f3, f5, f7 : call saved
- * f0 - f3, f5, f7 - f15 : call clobbered
- */
-
#include <sysdep.h>
.text
- .globl _dl_runtime_resolve
- .type _dl_runtime_resolve, @function
- cfi_startproc
- .align 16
-_dl_runtime_resolve:
- stmg %r2,%r5,64(15) # save call-clobbered argument registers
- stg %r14,96(15)
- cfi_offset (r14, -64)
- lgr %r0,%r15
- aghi %r15,-160 # create stack frame
- cfi_adjust_cfa_offset (160)
- stg %r0,0(%r15) # write backchain
- lmg %r2,%r3,208(%r15)# load args saved by PLT
- brasl %r14,_dl_fixup # call fixup
- lgr %r1,%r2 # function addr returned in r2
- aghi %r15,160 # remove stack frame
- cfi_adjust_cfa_offset (-160)
- lg %r14,96(15) # restore registers
- lmg %r2,%r5,64(15)
- br %r1
- cfi_endproc
- .size _dl_runtime_resolve, .-_dl_runtime_resolve
-
-
-#ifndef PROF
- .globl _dl_runtime_profile
- .type _dl_runtime_profile, @function
- cfi_startproc
- .align 16
-_dl_runtime_profile:
- stmg %r2,%r6,64(%r15) # save call-clobbered arg regs
- std %f0,104(%r15) # + r6 needed as arg for
- std %f2,112(%r15) # _dl_profile_fixup
- std %f4,120(%r15)
- std %f6,128(%r15)
- stg %r12,24(%r15) # r12 is used as backup of r15
- stg %r14,32(%r15)
- cfi_offset (r6, -96)
- cfi_offset (f0, -56)
- cfi_offset (f2, -48)
- cfi_offset (f4, -40)
- cfi_offset (f6, -32)
- cfi_offset (r12, -136)
- cfi_offset (r14, -128)
- lgr %r12,%r15 # backup stack pointer
- cfi_def_cfa_register (12)
- aghi %r15,-160 # create stack frame
- stg %r12,0(%r15) # save backchain
- lmg %r2,%r3,48(%r12) # load arguments saved by PLT
- lgr %r4,%r14 # return address as third parameter
- la %r5,64(%r12) # pointer to struct La_s390_32_regs
- la %r6,40(%r12) # long int * framesize
- brasl %r14,_dl_profile_fixup # call resolver
- lgr %r1,%r2 # function addr returned in r2
- lg %r0,40(%r12) # load framesize
- ltgr %r0,%r0
- jnm 1f
-
- lmg %r2,%r6,64(%r12) # framesize < 0 means no pltexit call
- ld %f0,104(%r12) # so we can do a tail call without
- ld %f2,112(%r12) # copying the arg overflow area
- ld %f4,120(%r12)
- ld %f6,128(%r12)
-
- lgr %r15,%r12 # remove stack frame
- cfi_def_cfa_register (15)
- lg %r14,32(%r15) # restore registers
- lg %r12,24(%r15)
- br %r1 # tail-call to resolved function
-
- cfi_def_cfa_register (12)
-1: jz 4f # framesize == 0 ?
- aghi %r0,7 # align framesize to 8
- nill %r0,0xfff8
- slgr %r15,%r0 # make room for framesize bytes
- stg %r12,0(%r15)
- la %r2,160(%r15)
- la %r3,160(%r12)
- srlg %r0,%r0,3
-3: mvc 0(8,%r2),0(%r3) # copy additional parameters
- la %r2,8(%r2)
- la %r3,8(%r3)
- brctg %r0,3b
-4: lmg %r2,%r6,64(%r12) # load register parameters
- ld %f0,104(%r12) # restore call-clobbered arg regs
- ld %f2,112(%r12)
- ld %f4,120(%r12)
- ld %f6,128(%r12)
- basr %r14,%r1 # call resolved function
- stg %r2,136(%r12)
- std %f0,144(%r12)
- lmg %r2,%r3,48(%r12) # load arguments saved by PLT
- la %r4,32(%r12) # pointer to struct La_s390_32_regs
- la %r5,72(%r12) # pointer to struct La_s390_32_retval
- brasl %r14,_dl_call_pltexit
-
- lgr %r15,%r12 # remove stack frame
- cfi_def_cfa_register (15)
- lg %r14,32(%r15) # restore registers
- lg %r12,24(%r15)
- br %r14
-
- cfi_endproc
- .size _dl_runtime_profile, .-_dl_runtime_profile
+/* Create variant of _dl_runtime_resolve/profile for machines before z13.
+ No vector registers are saved/restored. */
+#include <dl-trampoline.h>
+
+#if defined HAVE_S390_VX_ASM_SUPPORT
+/* Create variant of _dl_runtime_resolve/profile for z13 and newer.
+ The vector registers are saved/restored, too.*/
+# define _dl_runtime_resolve _dl_runtime_resolve_vx
+# define _dl_runtime_profile _dl_runtime_profile_vx
+# define RESTORE_VRS
+# include <dl-trampoline.h>
#endif
diff --git a/sysdeps/s390/s390-64/dl-trampoline.S b/sysdeps/s390/s390-64/dl-trampoline.h
similarity index 53%
copy from sysdeps/s390/s390-64/dl-trampoline.S
copy to sysdeps/s390/s390-64/dl-trampoline.h
index 87c6d50..658e3a3 100644
--- a/sysdeps/s390/s390-64/dl-trampoline.S
+++ b/sysdeps/s390/s390-64/dl-trampoline.h
@@ -1,5 +1,5 @@
/* PLT trampolines. s390x version.
- Copyright (C) 2005-2014 Free Software Foundation, Inc.
+ Copyright (C) 2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
@@ -20,6 +20,7 @@
* with the following linkage:
* r2 - r6 : parameter registers
* f0, f2, f4, f6 : floating point parameter registers
+ * v24, v26, v28, v30, v25, v27, v29, v31 : vector parameter registers
* 48(r15), 56(r15) : PLT arguments PLT1, PLT2
* 160(r15) : additional stack parameters
* The normal clobber rules for function calls apply:
@@ -27,32 +28,76 @@
* r6 - r13 : call saved
* r14 : return address (call clobbered)
* r15 : stack pointer (call saved)
- * f1, f3, f5, f7 : call saved
- * f0 - f3, f5, f7 - f15 : call clobbered
+ * f0 - f7 : call clobbered
+ * f8 - f15 : call saved
+ * v0 - v7 : bytes 0-7 overlap with f0-f7: call clobbered
+ bytes 8-15: call clobbered
+ * v8 - v15 : bytes 0-7 overlap with f8-f15: call saved
+ bytes 8-15: call clobbered
+ * v16 - v31 : call clobbered
*/
-#include <sysdep.h>
-
- .text
.globl _dl_runtime_resolve
.type _dl_runtime_resolve, @function
cfi_startproc
.align 16
_dl_runtime_resolve:
- stmg %r2,%r5,64(15) # save call-clobbered argument registers
+ stmg %r2,%r5,64(%r15) # save call-clobbered argument registers
+ cfi_offset (r2, -96)
+ cfi_offset (r3, -88)
+ cfi_offset (r4, -80)
+ cfi_offset (r5, -72)
+ std %f0,104(%r15)
+ cfi_offset (f0, -56)
+ std %f2,112(%r15)
+ cfi_offset (f2, -48)
+ std %f4,120(%r15)
+ cfi_offset (f4, -40)
+ std %f6,128(%r15)
+ cfi_offset (f6, -32)
stg %r14,96(15)
cfi_offset (r14, -64)
+ lmg %r2,%r3,48(%r15) # load args for fixup saved by PLT
lgr %r0,%r15
- aghi %r15,-160 # create stack frame
+#ifdef RESTORE_VRS
+ aghi %r15,-288 # create stack frame
+ cfi_adjust_cfa_offset (288)
+ .machine push
+ .machine "z13"
+ vstm %v24,%v31,160(%r15)# store call-clobbered vector argument registers
+ cfi_offset (v24, -288)
+ cfi_offset (v25, -272)
+ cfi_offset (v26, -256)
+ cfi_offset (v27, -240)
+ cfi_offset (v28, -224)
+ cfi_offset (v29, -208)
+ cfi_offset (v30, -192)
+ cfi_offset (v31, -176)
+ .machine pop
+#else
+ aghi %r15,-160 # create stack frame
cfi_adjust_cfa_offset (160)
+#endif
stg %r0,0(%r15) # write backchain
- lmg %r2,%r3,208(%r15)# load args saved by PLT
- brasl %r14,_dl_fixup # call fixup
+ brasl %r14,_dl_fixup # call _dl_fixup
lgr %r1,%r2 # function addr returned in r2
- aghi %r15,160 # remove stack frame
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vlm %v24,%v31,160(%r15)# restore vector registers
+ .machine pop
+ aghi %r15,288 # remove stack frame
+ cfi_adjust_cfa_offset (-288)
+#else
+ aghi %r15,160 # remove stack frame
cfi_adjust_cfa_offset (-160)
- lg %r14,96(15) # restore registers
- lmg %r2,%r5,64(15)
+#endif
+ lg %r14,96(%r15) # restore registers
+ ld %f0,104(%r15)
+ ld %f2,112(%r15)
+ ld %f4,120(%r15)
+ ld %f6,128(%r15)
+ lmg %r2,%r5,64(%r15)
br %r1
cfi_endproc
.size _dl_runtime_resolve, .-_dl_runtime_resolve
@@ -65,39 +110,66 @@ _dl_runtime_resolve:
.align 16
_dl_runtime_profile:
stmg %r2,%r6,64(%r15) # save call-clobbered arg regs
- std %f0,104(%r15) # + r6 needed as arg for
- std %f2,112(%r15) # _dl_profile_fixup
- std %f4,120(%r15)
- std %f6,128(%r15)
- stg %r12,24(%r15) # r12 is used as backup of r15
- stg %r14,32(%r15)
- cfi_offset (r6, -96)
+ cfi_offset (r2, -96) # + r6 needed as arg for
+ cfi_offset (r3, -88) # _dl_profile_fixup
+ cfi_offset (r4, -80)
+ cfi_offset (r5, -72)
+ cfi_offset (r6, -64)
+ std %f0,104(%r15)
cfi_offset (f0, -56)
+ std %f2,112(%r15)
cfi_offset (f2, -48)
+ std %f4,120(%r15)
cfi_offset (f4, -40)
+ std %f6,128(%r15)
cfi_offset (f6, -32)
+ stg %r12,24(%r15) # r12 is used as backup of r15
cfi_offset (r12, -136)
+ stg %r14,32(%r15)
cfi_offset (r14, -128)
lgr %r12,%r15 # backup stack pointer
cfi_def_cfa_register (12)
+#ifdef RESTORE_VRS
+ aghi %r15,-288 # create stack frame
+ .machine push
+ .machine "z13"
+ vstm %v24,%v31,160(%r15)# store call-clobbered vector argument registers
+ cfi_offset (v24, -288)
+ cfi_offset (v25, -272)
+ cfi_offset (v26, -256)
+ cfi_offset (v27, -240)
+ cfi_offset (v28, -224)
+ cfi_offset (v29, -208)
+ cfi_offset (v30, -192)
+ cfi_offset (v31, -176)
+ .machine pop
+#else
aghi %r15,-160 # create stack frame
+#endif
stg %r12,0(%r15) # save backchain
lmg %r2,%r3,48(%r12) # load arguments saved by PLT
lgr %r4,%r14 # return address as third parameter
- la %r5,64(%r12) # pointer to struct La_s390_32_regs
+ la %r5,64(%r12) # pointer to struct La_s390_64_regs
la %r6,40(%r12) # long int * framesize
brasl %r14,_dl_profile_fixup # call resolver
lgr %r1,%r2 # function addr returned in r2
+ ld %f0,104(%r12) # restore call-clobbered arg fprs
+ ld %f2,112(%r12)
+ ld %f4,120(%r12)
+ ld %f6,128(%r12)
+#ifdef RESTORE_VRS
+ .machine push
+ .machine "z13"
+ vlm %v24,%v31,160(%r15) # restore call-clobbered arg vrs
+ .machine pop
+#endif
lg %r0,40(%r12) # load framesize
ltgr %r0,%r0
jnm 1f
lmg %r2,%r6,64(%r12) # framesize < 0 means no pltexit call
- ld %f0,104(%r12) # so we can do a tail call without
- ld %f2,112(%r12) # copying the arg overflow area
- ld %f4,120(%r12)
- ld %f6,128(%r12)
-
+ # so we can do a tail call without
+ # copying the arg overflow area
lgr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
lg %r14,32(%r15) # restore registers
@@ -109,32 +181,30 @@ _dl_runtime_profile:
aghi %r0,7 # align framesize to 8
nill %r0,0xfff8
slgr %r15,%r0 # make room for framesize bytes
- stg %r12,0(%r15)
+ stg %r12,0(%r15) # save backchain
la %r2,160(%r15)
la %r3,160(%r12)
srlg %r0,%r0,3
3: mvc 0(8,%r2),0(%r3) # copy additional parameters
- la %r2,8(%r2)
+ la %r2,8(%r2) # depending on framesize
la %r3,8(%r3)
brctg %r0,3b
-4: lmg %r2,%r6,64(%r12) # load register parameters
- ld %f0,104(%r12) # restore call-clobbered arg regs
- ld %f2,112(%r12)
- ld %f4,120(%r12)
- ld %f6,128(%r12)
+4: lmg %r2,%r6,64(%r12) # restore call-clobbered arg gprs
basr %r14,%r1 # call resolved function
- stg %r2,136(%r12)
- std %f0,144(%r12)
+ stg %r2,136(%r12) # store return values r2, f0
+ std %f0,144(%r12) # to struct La_s390_64_retval
lmg %r2,%r3,48(%r12) # load arguments saved by PLT
- la %r4,32(%r12) # pointer to struct La_s390_32_regs
- la %r5,72(%r12) # pointer to struct La_s390_32_retval
+ la %r4,64(%r12) # pointer to struct La_s390_64_regs
+ la %r5,136(%r12) # pointer to struct La_s390_64_retval
brasl %r14,_dl_call_pltexit
lgr %r15,%r12 # remove stack frame
cfi_def_cfa_register (15)
lg %r14,32(%r15) # restore registers
lg %r12,24(%r15)
- br %r14
+ lg %r2,136(%r15) # restore return values
+ ld %f0,144(%r15)
+ br %r14 # Jump back to caller
cfi_endproc
.size _dl_runtime_profile, .-_dl_runtime_profile
http://sourceware.org/git/gitweb.cgi?p=glibc.git;a=commitdiff;h=3058f7487e5b98f7af0219f77464294000c84bf0
commit 3058f7487e5b98f7af0219f77464294000c84bf0
Author: Stefan Liebler <stli@linux.vnet.ibm.com>
Date: Mon Apr 4 13:20:26 2016 +0200
S390: configure check for vector instruction support in assembler.
The S390 specific test checks if the assembler has support for the new z13
vector instructions by compiling a vector instruction. The .machine and
.machinemode directives are needed to compile the vector instruction without
-march=z13 option on 31/64 bit.
On success the macro HAVE_S390_VX_ASM_SUPPORT is defined. This macro is used
to determine if the optimized functions can be build without compile errors.
If the used assembler lacks vector support, then a warning is dumped while
configuring and only the common code functions are build.
The z13 instruction support was introduced in
"[Committed] S/390: Add support for IBM z13."
(https://sourceware.org/ml/binutils/2015-01/msg00197.html)
ChangeLog:
* config.h.in (HAVE_S390_VX_ASM_SUPPORT): New macro undefine.
* sysdeps/s390/configure.ac: Add test for S390 vector instruction
assembler support.
* sysdeps/s390/configure: Regenerated.
(cherry picked from commit 4f0a1cea34c05fb2acc16f1a2d291f53230eb4fb)
diff --git a/ChangeLog b/ChangeLog
index 3ecc89b..c68136c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,12 @@
2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+ * config.h.in (HAVE_S390_VX_ASM_SUPPORT): New macro undefine.
+ * sysdeps/s390/configure.ac: Add test for S390 vector instruction
+ assembler support.
+ * sysdeps/s390/configure: Regenerated.
+
+2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+
* sysdeps/s390/dl-procinfo.c (_dl_s390_cap_flags): Add z13.
* sysdeps/s390/dl-procinfo.h (_DL_PLATFORMS_COUNT): Increased.
diff --git a/config.h.in b/config.h.in
index 7da1a9f..2b98d4a 100644
--- a/config.h.in
+++ b/config.h.in
@@ -97,6 +97,9 @@
/* Define if assembler supports AVX512. */
#undef HAVE_AVX512_ASM_SUPPORT
+/* Define if assembler supports vector instructions on S390. */
+#undef HAVE_S390_VX_ASM_SUPPORT
+
/* Define if assembler supports Intel MPX. */
#undef HAVE_MPX_SUPPORT
diff --git a/sysdeps/s390/configure b/sysdeps/s390/configure
index 6948cc2..9e182f7 100644
--- a/sysdeps/s390/configure
+++ b/sysdeps/s390/configure
@@ -104,5 +104,46 @@ if test "$enable_lock_elision" = yes && test "$libc_cv_gcc_builtin_tbegin" = no
critic_missing="$critic_missing The used GCC has no support for __builtin_tbegin, which is needed for lock-elision on target S390."
fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for S390 vector instruction support" >&5
+$as_echo_n "checking for S390 vector instruction support... " >&6; }
+if ${libc_cv_asm_s390_vx+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat > conftest.c <<\EOF
+void testvecinsn ()
+{
+ __asm__ (".machine \"z13\" \n\t"
+ ".machinemode \"zarch_nohighgprs\" \n\t"
+ "vistrbs %%v16,%%v17 \n\t"
+ "locghie %%r1,0" : :);
+}
+EOF
+if { ac_try='${CC-cc} --shared conftest.c -o conftest.o &> /dev/null'
+ { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_try\""; } >&5
+ (eval $ac_try) 2>&5
+ ac_status=$?
+ $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+ test $ac_status = 0; }; } ;
+then
+ libc_cv_asm_s390_vx=yes
+else
+ libc_cv_asm_s390_vx=no
+fi
+rm -f conftest*
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_asm_s390_vx" >&5
+$as_echo "$libc_cv_asm_s390_vx" >&6; }
+
+if test "$libc_cv_asm_s390_vx" = yes ;
+then
+ $as_echo "#define HAVE_S390_VX_ASM_SUPPORT 1" >>confdefs.h
+
+else
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Use binutils with vector-support in order to use optimized implementations." >&5
+$as_echo "$as_me: WARNING: Use binutils with vector-support in order to use optimized implementations." >&2;}
+fi
+
+
test -n "$critic_missing" && as_fn_error $? "
*** $critic_missing" "$LINENO" 5
diff --git a/sysdeps/s390/configure.ac b/sysdeps/s390/configure.ac
index 493e9a4..4da134e 100644
--- a/sysdeps/s390/configure.ac
+++ b/sysdeps/s390/configure.ac
@@ -36,5 +36,34 @@ if test "$enable_lock_elision" = yes && test "$libc_cv_gcc_builtin_tbegin" = no
critic_missing="$critic_missing The used GCC has no support for __builtin_tbegin, which is needed for lock-elision on target S390."
fi
+
+AC_CACHE_CHECK(for S390 vector instruction support, libc_cv_asm_s390_vx, [dnl
+cat > conftest.c <<\EOF
+void testvecinsn ()
+{
+ __asm__ (".machine \"z13\" \n\t"
+ ".machinemode \"zarch_nohighgprs\" \n\t"
+ "vistrbs %%v16,%%v17 \n\t"
+ "locghie %%r1,0" : :);
+}
+EOF
+dnl
+dnl test, if assembler supports S390 vector instructions
+if AC_TRY_COMMAND([${CC-cc} --shared conftest.c -o conftest.o &> /dev/null]) ;
+then
+ libc_cv_asm_s390_vx=yes
+else
+ libc_cv_asm_s390_vx=no
+fi
+rm -f conftest* ])
+
+if test "$libc_cv_asm_s390_vx" = yes ;
+then
+ AC_DEFINE(HAVE_S390_VX_ASM_SUPPORT)
+else
+ AC_MSG_WARN([Use binutils with vector-support in order to use optimized implementations.])
+fi
+
+
test -n "$critic_missing" && AC_MSG_ERROR([
*** $critic_missing])
http://sourceware.org/git/gitweb.cgi?p=glibc.git;a=commitdiff;h=66cdb5b20df45c4eb28ab27ebcfb67ef023338e3
commit 66cdb5b20df45c4eb28ab27ebcfb67ef023338e3
Author: Stefan Liebler <stli@linux.vnet.ibm.com>
Date: Mon Apr 4 13:20:26 2016 +0200
S390: Add new s390 platform.
The new IBM z13 is added to platform string array.
The macro _DL_PLATFORMS_COUNT is incremented to 8,
because it was not incremented by commit
"S/390: Sync AUXV capabilities and archs with kernel".
ChangeLog:
* sysdeps/s390/dl-procinfo.c (_dl_s390_cap_flags): Add z13.
* sysdeps/s390/dl-procinfo.h (_DL_PLATFORMS_COUNT): Increased.
(cherry picked from commit a1b0488fc9df3d895a2e5eefbcd348d3f7fe0e52)
diff --git a/ChangeLog b/ChangeLog
index 729a7f6..3ecc89b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,10 @@
2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+ * sysdeps/s390/dl-procinfo.c (_dl_s390_cap_flags): Add z13.
+ * sysdeps/s390/dl-procinfo.h (_DL_PLATFORMS_COUNT): Increased.
+
+2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+
* sysdeps/s390/dl-procinfo.c (_dl_s390_platforms): Add vector flag.
* sysdeps/s390/dl-procinfo.h: Add vector capability.
* sysdeps/unix/sysv/linux/s390/bits/hwcap.h (HWCAP_S390_VX): Define.
diff --git a/sysdeps/s390/dl-procinfo.c b/sysdeps/s390/dl-procinfo.c
index 73c7ff9..aef2ba5 100644
--- a/sysdeps/s390/dl-procinfo.c
+++ b/sysdeps/s390/dl-procinfo.c
@@ -62,11 +62,11 @@ PROCINFO_CLASS const char _dl_s390_cap_flags[12][9]
#if !defined PROCINFO_DECL && defined SHARED
._dl_s390_platforms
#else
-PROCINFO_CLASS const char _dl_s390_platforms[7][7]
+PROCINFO_CLASS const char _dl_s390_platforms[8][7]
#endif
#ifndef PROCINFO_DECL
= {
- "g5", "z900", "z990", "z9-109", "z10", "z196", "zEC12"
+ "g5", "z900", "z990", "z9-109", "z10", "z196", "zEC12", "z13"
}
#endif
#if !defined SHARED || defined PROCINFO_DECL
diff --git a/sysdeps/s390/dl-procinfo.h b/sysdeps/s390/dl-procinfo.h
index 382cd7a..9ba0f63 100644
--- a/sysdeps/s390/dl-procinfo.h
+++ b/sysdeps/s390/dl-procinfo.h
@@ -23,7 +23,7 @@
#define _DL_HWCAP_COUNT 12
-#define _DL_PLATFORMS_COUNT 5
+#define _DL_PLATFORMS_COUNT 8
/* The kernel provides up to 32 capability bits with elf_hwcap. */
#define _DL_FIRST_PLATFORM 32
http://sourceware.org/git/gitweb.cgi?p=glibc.git;a=commitdiff;h=7af8c37714ece3f02716f17e59631ada0c0ee0d9
commit 7af8c37714ece3f02716f17e59631ada0c0ee0d9
Author: Stefan Liebler <stli@linux.vnet.ibm.com>
Date: Mon Apr 4 13:20:26 2016 +0200
S390: Add hwcaps value for vector facility.
The HWCAP_S390_VX flag in hwcap field of auxiliary vector indicates
if the vector facility is available and the kernel is aware of it.
This can be tested with LD_SHOW_AUXV=1 <prog>.
Currently it does not show te, because it was not incremented
by commit "S/390: Add hwcap value for transactional execution.".
Thus _DL_HWCAP_COUNT is incremented by two.
ChangeLog:
* sysdeps/s390/dl-procinfo.c (_dl_s390_platforms): Add vector flag.
* sysdeps/s390/dl-procinfo.h: Add vector capability.
* sysdeps/unix/sysv/linux/s390/bits/hwcap.h (HWCAP_S390_VX): Define.
(cherry picked from commit 4e28fa80886c71e6aaf85016b82ce981c0f12e6d)
diff --git a/ChangeLog b/ChangeLog
index 13634d7..729a7f6 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2016-04-04 Stefan Liebler <stli@linux.vnet.ibm.com>
+
+ * sysdeps/s390/dl-procinfo.c (_dl_s390_platforms): Add vector flag.
+ * sysdeps/s390/dl-procinfo.h: Add vector capability.
+ * sysdeps/unix/sysv/linux/s390/bits/hwcap.h (HWCAP_S390_VX): Define.
+
2016-03-02 Stefan Liebler <stli@linux.vnet.ibm.com>
[BZ #19682]
diff --git a/sysdeps/s390/dl-procinfo.c b/sysdeps/s390/dl-procinfo.c
index 89f8ebe..73c7ff9 100644
--- a/sysdeps/s390/dl-procinfo.c
+++ b/sysdeps/s390/dl-procinfo.c
@@ -46,11 +46,11 @@
#if !defined PROCINFO_DECL && defined SHARED
._dl_s390_cap_flags
#else
-PROCINFO_CLASS const char _dl_s390_cap_flags[11][9]
+PROCINFO_CLASS const char _dl_s390_cap_flags[12][9]
#endif
#ifndef PROCINFO_DECL
= {
- "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", "edat", "etf3eh", "highgprs", "te"
+ "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", "edat", "etf3eh", "highgprs", "te", "vx"
}
#endif
#if !defined SHARED || defined PROCINFO_DECL
diff --git a/sysdeps/s390/dl-procinfo.h b/sysdeps/s390/dl-procinfo.h
index 65322db..382cd7a 100644
--- a/sysdeps/s390/dl-procinfo.h
+++ b/sysdeps/s390/dl-procinfo.h
@@ -21,7 +21,7 @@
#define _DL_PROCINFO_H 1
#include <ldsodefs.h>
-#define _DL_HWCAP_COUNT 10
+#define _DL_HWCAP_COUNT 12
#define _DL_PLATFORMS_COUNT 5
@@ -50,6 +50,7 @@ enum
HWCAP_S390_ETF3EH = 1 << 8,
HWCAP_S390_HIGH_GPRS = 1 << 9,
HWCAP_S390_TE = 1 << 10,
+ HWCAP_S390_VX = 1 << 11,
};
#define HWCAP_IMPORTANT (HWCAP_S390_ZARCH | HWCAP_S390_LDISP \
diff --git a/sysdeps/unix/sysv/linux/s390/bits/hwcap.h b/sysdeps/unix/sysv/linux/s390/bits/hwcap.h
index f4659fc..f1f4688 100644
--- a/sysdeps/unix/sysv/linux/s390/bits/hwcap.h
+++ b/sysdeps/unix/sysv/linux/s390/bits/hwcap.h
@@ -35,3 +35,4 @@
#define HWCAP_S390_ETF3EH 256
#define HWCAP_S390_HIGH_GPRS 512
#define HWCAP_S390_TE 1024
+#define HWCAP_S390_VX 2048
-----------------------------------------------------------------------
Summary of changes:
ChangeLog | 50 ++++++
config.h.in | 3 +
sysdeps/s390/bits/link.h | 29 ++++
sysdeps/s390/configure | 41 +++++
sysdeps/s390/configure.ac | 29 ++++
sysdeps/s390/dl-procinfo.c | 8 +-
sysdeps/s390/dl-procinfo.h | 5 +-
sysdeps/s390/s390-32/dl-machine.h | 27 +++-
sysdeps/s390/s390-32/dl-trampoline.S | 134 ++---------------
sysdeps/s390/s390-32/dl-trampoline.h | 231 +++++++++++++++++++++++++++++
sysdeps/s390/s390-64/dl-machine.h | 27 +++-
sysdeps/s390/s390-64/dl-trampoline.S | 130 ++---------------
sysdeps/s390/s390-64/dl-trampoline.h | 225 ++++++++++++++++++++++++++++
sysdeps/unix/sysv/linux/s390/bits/hwcap.h | 1 +
14 files changed, 686 insertions(+), 254 deletions(-)
create mode 100644 sysdeps/s390/s390-32/dl-trampoline.h
create mode 100644 sysdeps/s390/s390-64/dl-trampoline.h
hooks/post-receive
--
GNU C Library master sources