Hi Kyrill,
On 11/12/2019 10:22 AM, Kyrill Tkachov wrote:
Hi Mihail,
On 10/23/19 3:24 PM, Mihail Ionescu wrote:
[PATCH, GCC/ARM, 8/10] Do lazy store & load inline when calling nscall
function
Hi,
=== Context ===
This patch is part of a patch series to add support for Armv8.1-M
Mainline Security Extensions architecture. Its purpose is to generate
lazy store and load instruction inline when calling a function with the
cmse_nonsecure_call attribute with the soft or softfp floating-point
ABI.
=== Patch description ===
This patch adds two new patterns for the VLSTM and VLLDM instructions.
cmse_nonsecure_call_inline_register_clear is then modified to
generate VLSTM and VLLDM respectively before and after calls to
functions with the cmse_nonsecure_call attribute in order to have lazy
saving, clearing and restoring of VFP registers. Since these
instructions do not do writeback of the base register, the stack is
adjusted
prior the lazy store and after the lazy load with appropriate frame
debug notes to describe the effect on the CFA register.
As with CLRM, VSCCLRM and VSTR/VLDR, the instruction is modeled as an
unspecified operation to the memory pointed to by the base register.
ChangeLog entries are as follows:
*** gcc/ChangeLog ***
2019-10-23 Mihail-Calin Ionescu <mihail.ione...@arm.com>
2019-10-23 Thomas Preud'homme <thomas.preudho...@arm.com>
* config/arm/arm.c (arm_add_cfa_adjust_cfa_note): Declare early.
(cmse_nonsecure_call_inline_register_clear): Define new
lazy_fpclear
variable as true when floating-point ABI is not hard. Replace
check against TARGET_HARD_FLOAT_ABI by checks against
lazy_fpclear.
Generate VLSTM and VLLDM instruction respectively before and
after a function call to cmse_nonsecure_call function.
* config/arm/unspecs.md (VUNSPEC_VLSTM): Define unspec.
(VUNSPEC_VLLDM): Likewise.
* config/arm/vfp.md (lazy_store_multiple_insn): New define_insn.
(lazy_load_multiple_insn): Likewise.
*** gcc/testsuite/ChangeLog ***
2019-10-23 Mihail-Calin Ionescu <mihail.ione...@arm.com>
2019-10-23 Thomas Preud'homme <thomas.preudho...@arm.com>
* gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c: Add check
for VLSTM and
VLLDM.
* gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c: Likewise.
* gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c: Likewise.
Testing: bootstrapped on arm-linux-gnueabihf and testsuite shows no
regression.
Is this ok for trunk?
Best regards,
Mihail
############### Attachment also inlined for ease of reply
###############
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index
bcc86d50a10f11d9672258442089a0aa5c450b2f..b10f996c023e830ca24ff83fcbab335caf85d4cb
100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -186,6 +186,7 @@ static int arm_register_move_cost (machine_mode,
reg_class_t, reg_class_t);
static int arm_memory_move_cost (machine_mode, reg_class_t, bool);
static void emit_constant_insn (rtx cond, rtx pattern);
static rtx_insn *emit_set_insn (rtx, rtx);
+static void arm_add_cfa_adjust_cfa_note (rtx, int, rtx, rtx);
static rtx emit_multi_reg_push (unsigned long, unsigned long);
static void arm_emit_multi_reg_pop (unsigned long);
static int vfp_emit_fstmd (int, int);
@@ -17830,6 +17831,9 @@ cmse_nonsecure_call_inline_register_clear (void)
FOR_BB_INSNS (bb, insn)
{
bool clear_callee_saved = TARGET_HAVE_FPCTX_CMSE;
+ /* frame = VFP regs + FPSCR + VPR. */
+ unsigned lazy_store_stack_frame_size =
+ (LAST_VFP_REGNUM - FIRST_VFP_REGNUM + 1 + 2) *
UNITS_PER_WORD;
unsigned long callee_saved_mask =
((1 << (LAST_HI_REGNUM + 1)) - 1)
& ~((1 << (LAST_ARG_REGNUM + 1)) - 1);
@@ -17847,7 +17851,7 @@ cmse_nonsecure_call_inline_register_clear (void)
CUMULATIVE_ARGS args_so_far_v;
cumulative_args_t args_so_far;
tree arg_type, fntype;
- bool first_param = true;
+ bool first_param = true, lazy_fpclear = !TARGET_HARD_FLOAT_ABI;
function_args_iterator args_iter;
uint32_t padding_bits_to_clear[4] = {0U, 0U, 0U, 0U};
@@ -17881,7 +17885,7 @@ cmse_nonsecure_call_inline_register_clear (void)
-mfloat-abi=hard. For -mfloat-abi=softfp we will be
using the
lazy store and loads which clear both caller- and
callee-saved
registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ if (!lazy_fpclear)
{
auto_sbitmap float_bitmap (maxregno + 1);
@@ -17965,8 +17969,23 @@ cmse_nonsecure_call_inline_register_clear (void)
disabled for pop (see below). */
RTX_FRAME_RELATED_P (push_insn) = 0;
+ /* Lazy store multiple. */
+ if (lazy_fpclear)
+ {
+ rtx imm;
+ rtx_insn *add_insn;
+
+ imm = gen_int_mode (- lazy_store_stack_frame_size,
SImode);
+ add_insn = emit_insn (gen_addsi3 (stack_pointer_rtx,
+ stack_pointer_rtx, imm));
+ arm_add_cfa_adjust_cfa_note (add_insn,
+ -
lazy_store_stack_frame_size,
+ stack_pointer_rtx,
+ stack_pointer_rtx);
+ emit_insn (gen_lazy_store_multiple_insn
(stack_pointer_rtx));
+ }
/* Save VFP callee-saved registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ else
{
vfp_emit_fstmd (D7_VFP_REGNUM + 1,
(max_fp_regno - D7_VFP_REGNUM) / 2);
@@ -17992,8 +18011,21 @@ cmse_nonsecure_call_inline_register_clear (void)
start_sequence ();
+ /* Lazy load multiple done as part of libcall in
Armv8-M. */
+ if (lazy_fpclear)
+ {
+ rtx imm = gen_int_mode (lazy_store_stack_frame_size,
SImode);
+ emit_insn (gen_lazy_load_multiple_insn
(stack_pointer_rtx));
+ rtx_insn *add_insn =
+ emit_insn (gen_addsi3 (stack_pointer_rtx,
+ stack_pointer_rtx, imm));
+ arm_add_cfa_adjust_cfa_note (add_insn,
+ lazy_store_stack_frame_size,
+ stack_pointer_rtx,
+ stack_pointer_rtx);
+ }
/* Restore VFP callee-saved registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ else
{
int nb_callee_saved_vfp_regs =
(max_fp_regno - D7_VFP_REGNUM) / 2;
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index
ad072705525cc3c4035a22b5f99546bcd0e79ec5..9c9a68ae4f0a3d45f4c730f274b85f0b1ff00348
100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -177,6 +177,10 @@
VUNSPEC_CLRM_APSR ; Represent the clearing of APSR with clrm
instruction.
VUNSPEC_VSCCLRM_VPR ; Represent the clearing of VPR with vscclrm
; instruction.
+ VUNSPEC_VLSTM ; Represent the lazy store multiple
with vlstm
+ ; instruction.
+ VUNSPEC_VLLDM ; Represent the lazy load multiple
with vlldm
+ ; instruction.
])
;; Enumerators for NEON unspecs.
diff --git a/gcc/config/arm/vfp.md b/gcc/config/arm/vfp.md
index
2bf928f32626ce2731ebdfedffbbf64d806eff53..d3807acdd4d3691da63dcc5d6b3d5d8aad4bfe0e
100644
--- a/gcc/config/arm/vfp.md
+++ b/gcc/config/arm/vfp.md
@@ -1677,6 +1677,30 @@
(set_attr "type" "mov_reg")]
)
+(define_insn "lazy_store_multiple_insn"
+ [(set (match_operand:SI 0 "s_register_operand" "+&rk")
+ (plus:SI (match_dup 0) (const_int -4)))
+ (unspec_volatile [(const_int 0)
+ (mem:SI (plus:SI (match_dup 0) (const_int -4)))]
+ VUNSPEC_VLSTM)]
+ "use_cmse && reload_completed"
+ "vlstm%?\\t%0"
+ [(set_attr "predicable" "yes")
+ (set_attr "type" "store_4")]
+)
+
+(define_insn "lazy_load_multiple_insn"
+ [(set (match_operand:SI 0 "s_register_operand" "+&rk")
+ (plus:SI (match_dup 0) (const_int 4)))
+ (unspec_volatile:SI [(const_int 0)
+ (mem:SI (match_dup 0))]
+ VUNSPEC_VLLDM)]
+ "use_cmse && reload_completed"
+ "vlldm%?\\t%0"
+ [(set_attr "predicable" "yes")
+ (set_attr "type" "load_4")]
+)
+
Same question on the representation as for an earlier patch.
Why aren't we using one of the POST_INC addressing modes to represent this?
Patch looks good otherwise.
Thanks,
Kyrill
The patterns are now updated to use post_{inc/dec}
Regards,
Mihail
(define_insn_and_split "*cmpsf_split_vfp"
[(set (reg:CCFP CC_REGNUM)
(compare:CCFP (match_operand:SF 0 "s_register_operand" "t")
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
index
07a6719b4f1a260a3461f7408e278dd6e71f60d3..52d22427de79c6a76fbe32b8df7f76b4b286249c
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r1, r5, r6, r7, r8, r9, r10,
fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
index
ca2961ac18ccacec6907b1d1d217c6c2e28072e7..40026d5ee1cc62b4acf48be9619ccd69ef4ead7b
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
@@ -8,7 +8,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7,
r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
index
7a1abb51fcf9a62a24583e792953845f21bbed49..6edc1f6ed7e6bc27024056375db4a2d30c3ea3c4
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
@@ -10,7 +10,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9,
r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
index
90aadffb7aa14ceeea22232148c11e9543eee0e7..8d05576add940c277e5a13f7aab99e6807c1553d
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
@@ -9,7 +9,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7,
r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
index
28f2e86dfaa89902d1c04fc2890c5445b5bb0af5..1f0a14742781b7340685338901dbfab9b700b779
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9,
r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
index
15d3b682c798dd6635ed6b90d9aa8e705fefa265..842794181087ddbd5ce59680035a0cb61ce5682e
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
@@ -12,7 +12,9 @@
/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r1, r5, r6, r7, r8, r9, r10,
fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
index
3d48859028ab8dd22d9ffed7c95ece59c2ed937e..38c9d5457034d2427413bcce7e7be6bad80f7a67
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
@@ -9,7 +9,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7,
r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git
a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
index
0e2dcae36927d2c7187ca2b60c935504268476bc..6a17bd322fcc4e7e00ea289ee7373db9d8c37a87
100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9,
r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10,
fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 32f51626c71610799f0c422f206a7de18ddc249d..1169cba37fc7d76f84cb060f0d6d118fdeeaba18 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -187,6 +187,7 @@ static int arm_register_move_cost (machine_mode, reg_class_t, reg_class_t);
static int arm_memory_move_cost (machine_mode, reg_class_t, bool);
static void emit_constant_insn (rtx cond, rtx pattern);
static rtx_insn *emit_set_insn (rtx, rtx);
+static void arm_add_cfa_adjust_cfa_note (rtx, int, rtx, rtx);
static rtx emit_multi_reg_push (unsigned long, unsigned long);
static void arm_emit_multi_reg_pop (unsigned long);
static int vfp_emit_fstmd (int, int);
@@ -18208,6 +18209,9 @@ cmse_nonsecure_call_inline_register_clear (void)
FOR_BB_INSNS (bb, insn)
{
bool clear_callee_saved = TARGET_HAVE_FPCXT_CMSE;
+ /* frame = VFP regs + FPSCR + VPR. */
+ unsigned lazy_store_stack_frame_size
+ = (LAST_VFP_REGNUM - FIRST_VFP_REGNUM + 1 + 2) * UNITS_PER_WORD;
unsigned long callee_saved_mask
= ((1 << (LAST_HI_REGNUM + 1)) - 1)
& ~((1 << (LAST_ARG_REGNUM + 1)) - 1);
@@ -18225,7 +18229,7 @@ cmse_nonsecure_call_inline_register_clear (void)
CUMULATIVE_ARGS args_so_far_v;
cumulative_args_t args_so_far;
tree arg_type, fntype;
- bool first_param = true;
+ bool first_param = true, lazy_fpclear = !TARGET_HARD_FLOAT_ABI;
function_args_iterator args_iter;
uint32_t padding_bits_to_clear[4] = {0U, 0U, 0U, 0U};
@@ -18259,7 +18263,7 @@ cmse_nonsecure_call_inline_register_clear (void)
-mfloat-abi=hard. For -mfloat-abi=softfp we will be using the
lazy store and loads which clear both caller- and callee-saved
registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ if (!lazy_fpclear)
{
auto_sbitmap float_bitmap (maxregno + 1);
@@ -18343,8 +18347,23 @@ cmse_nonsecure_call_inline_register_clear (void)
disabled for pop (see below). */
RTX_FRAME_RELATED_P (push_insn) = 0;
+ /* Lazy store multiple. */
+ if (lazy_fpclear)
+ {
+ rtx imm;
+ rtx_insn *add_insn;
+
+ imm = gen_int_mode (- lazy_store_stack_frame_size, SImode);
+ add_insn = emit_insn (gen_addsi3 (stack_pointer_rtx,
+ stack_pointer_rtx, imm));
+ arm_add_cfa_adjust_cfa_note (add_insn,
+ - lazy_store_stack_frame_size,
+ stack_pointer_rtx,
+ stack_pointer_rtx);
+ emit_insn (gen_lazy_store_multiple_insn (stack_pointer_rtx));
+ }
/* Save VFP callee-saved registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ else
{
vfp_emit_fstmd (D7_VFP_REGNUM + 1,
(max_fp_regno - D7_VFP_REGNUM) / 2);
@@ -18370,8 +18389,21 @@ cmse_nonsecure_call_inline_register_clear (void)
start_sequence ();
+ /* Lazy load multiple done as part of libcall in Armv8-M. */
+ if (lazy_fpclear)
+ {
+ rtx imm = gen_int_mode (lazy_store_stack_frame_size, SImode);
+ emit_insn (gen_lazy_load_multiple_insn (stack_pointer_rtx));
+ rtx_insn *add_insn =
+ emit_insn (gen_addsi3 (stack_pointer_rtx,
+ stack_pointer_rtx, imm));
+ arm_add_cfa_adjust_cfa_note (add_insn,
+ lazy_store_stack_frame_size,
+ stack_pointer_rtx,
+ stack_pointer_rtx);
+ }
/* Restore VFP callee-saved registers. */
- if (TARGET_HARD_FLOAT_ABI)
+ else
{
int nb_callee_saved_vfp_regs =
(max_fp_regno - D7_VFP_REGNUM) / 2;
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 335b2a6d4a2cdc8bca807b5bf3e623d7a165922a..430d03d319ec1515d2408cdc904d52890238ba92 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -215,6 +215,10 @@
VUNSPEC_CLRM_APSR ; Represent the clearing of APSR with clrm instruction.
VUNSPEC_VSCCLRM_VPR ; Represent the clearing of VPR with vscclrm
; instruction.
+ VUNSPEC_VLSTM ; Represent the lazy store multiple with vlstm
+ ; instruction.
+ VUNSPEC_VLLDM ; Represent the lazy load multiple with vlldm
+ ; instruction.
])
;; Enumerators for NEON unspecs.
diff --git a/gcc/config/arm/vfp.md b/gcc/config/arm/vfp.md
index a2d8b80374f7198e00a05d35b31d4946c5f1491f..c91e750a687652d103f9952312d3625ca4e1c977 100644
--- a/gcc/config/arm/vfp.md
+++ b/gcc/config/arm/vfp.md
@@ -1673,6 +1673,30 @@
(set_attr "type" "mov_reg")]
)
+(define_insn "lazy_store_multiple_insn"
+ [(set (match_operand:SI 0 "s_register_operand" "+&rk")
+ (post_dec:SI (match_dup 0)))
+ (unspec_volatile [(const_int 0)
+ (mem:SI (post_dec:SI (match_dup 0)))]
+ VUNSPEC_VLSTM)]
+ "use_cmse && reload_completed"
+ "vlstm%?\\t%0"
+ [(set_attr "predicable" "yes")
+ (set_attr "type" "store_4")]
+)
+
+(define_insn "lazy_load_multiple_insn"
+ [(set (match_operand:SI 0 "s_register_operand" "+&rk")
+ (post_inc:SI (match_dup 0)))
+ (unspec_volatile:SI [(const_int 0)
+ (mem:SI (match_dup 0))]
+ VUNSPEC_VLLDM)]
+ "use_cmse && reload_completed"
+ "vlldm%?\\t%0"
+ [(set_attr "predicable" "yes")
+ (set_attr "type" "load_4")]
+)
+
(define_insn_and_split "*cmpsf_split_vfp"
[(set (reg:CCFP CC_REGNUM)
(compare:CCFP (match_operand:SF 0 "s_register_operand" "t")
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
index 07a6719b4f1a260a3461f7408e278dd6e71f60d3..52d22427de79c6a76fbe32b8df7f76b4b286249c 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r1, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
index ca2961ac18ccacec6907b1d1d217c6c2e28072e7..40026d5ee1cc62b4acf48be9619ccd69ef4ead7b 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7.c
@@ -8,7 +8,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
index 7a1abb51fcf9a62a24583e792953845f21bbed49..6edc1f6ed7e6bc27024056375db4a2d30c3ea3c4 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8.c
@@ -10,7 +10,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* { dg-final { scan-assembler-not "vmov" } } */
/* { dg-final { scan-assembler-not "vmsr" } } */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
index 90aadffb7aa14ceeea22232148c11e9543eee0e7..8d05576add940c277e5a13f7aab99e6807c1553d 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7.c
@@ -9,7 +9,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
index 28f2e86dfaa89902d1c04fc2890c5445b5bb0af5..1f0a14742781b7340685338901dbfab9b700b779 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
index 15d3b682c798dd6635ed6b90d9aa8e705fefa265..842794181087ddbd5ce59680035a0cb61ce5682e 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13.c
@@ -12,7 +12,9 @@
/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r1, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
index 3d48859028ab8dd22d9ffed7c95ece59c2ed937e..38c9d5457034d2427413bcce7e7be6bad80f7a67 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7.c
@@ -9,7 +9,9 @@
/* { dg-final { scan-assembler "lsrs\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "lsls\tr4, r4, #1" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r0, r1, r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
index 0e2dcae36927d2c7187ca2b60c935504268476bc..6a17bd322fcc4e7e00ea289ee7373db9d8c37a87 100644
--- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8.c
@@ -11,7 +11,9 @@
/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
+/* { dg-final { scan-assembler "vlstm\tsp" } } */
/* { dg-final { scan-assembler "clrm\t\{r2, r3, r5, r6, r7, r8, r9, r10, fp, ip, APSR\}" } } */
+/* { dg-final { scan-assembler "vlldm\tsp" } } */
/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
/* Now we check that we use the correct intrinsic to call. */
