From: "Luke Zhuang" <[email protected]>

Per the RISC-V psABI, the TLSDESC resolver clobbers a0 and t0 in the
base case.  With the new psABI update
(https://github.com/riscv-non-isa/riscv-elf-psabi-doc/pull/496),
when the V extension is enabled, it additionally clobbers all vector
registers and vector CSRs.

Mirroring how AArch64 handles SVE clobbers in its TLSDESC
implementation (<80c13ac5>), this patch splits the TLSDESC pattern
into a define_expand that dispatches to two define_insn variants:
tlsdesc_base for the non-vector case (clobbering only a0 and t0),
and tlsdesc_vec for the vector case (additionally clobbering all
V-regs using 4xlmul8 register groups, and 4 vector CSRs
vl/vtype/vxrm/vxstat).

Three new tests are added covering GPR, vector register, and vector
CSR clobber behavior.

gcc/ChangeLog:

        * config/riscv/riscv.md (VXSAT_REGNUM): New constant.
        (@tlsdesc<mode>): Convert to define_expand.
        (tlsdesc_base<mode>): New define_insn for non-vector case.
        (tlsdesc_vec<mode>): New define_insn with vector register and
        CSR clobbers.

gcc/testsuite/ChangeLog:

        * gcc.target/riscv/tlsdesc_clobber.c: New test.
        * gcc.target/riscv/tlsdesc_clobber_v.c: New test.
        * gcc.target/riscv/tlsdesc_clobber_v_csr.c: New test.
---
 gcc/config/riscv/riscv.md                     | 50 +++++++++++++++--
 .../gcc.target/riscv/tlsdesc_clobber.c        | 29 ++++++++++
 .../gcc.target/riscv/tlsdesc_clobber_v.c      | 56 +++++++++++++++++++
 .../gcc.target/riscv/tlsdesc_clobber_v_csr.c  | 39 +++++++++++++
 4 files changed, 169 insertions(+), 5 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/tlsdesc_clobber.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v_csr.c

diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index b90bfe0745a..0d2c8bd9ac6 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -181,6 +181,7 @@
    (VTYPE_REGNUM               67)
    (VXRM_REGNUM                        68)
    (FRM_REGNUM                 69)
+   (VXSAT_REGNUM               70)
 ])
 
 (include "predicates.md")
@@ -2473,13 +2474,52 @@
    (set_attr "type" "load")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "@tlsdesc<mode>"
+(define_expand "@tlsdesc<mode>"
+  [(unspec:P [(match_operand:P 0 "symbolic_operand" "")]
+            UNSPEC_TLSDESC)]
+  "TARGET_TLSDESC"
+{
+  if (TARGET_VECTOR)
+    emit_insn (gen_tlsdesc_vec<mode> (operands[0]));
+  else
+    emit_insn (gen_tlsdesc_base<mode> (operands[0]));
+  DONE;
+})
+
+;; Base TLSDESC: clobbers a0 and t0 only (no V extension).
+(define_insn "tlsdesc_base<mode>"
   [(set (reg:P A0_REGNUM)
-       (unspec:P
-           [(match_operand:P 0 "symbolic_operand" "")]
-           UNSPEC_TLSDESC))
+       (unspec:P [(match_operand:P 0 "symbolic_operand" "")]
+                 UNSPEC_TLSDESC))
    (clobber (reg:P T0_REGNUM))]
-  "TARGET_TLSDESC"
+  "TARGET_TLSDESC && !TARGET_VECTOR"
+  {
+    return ".LT%=: auipc\ta0,%%tlsdesc_hi(%0)\;"
+           "<load>\tt0,%%tlsdesc_load_lo(.LT%=)(a0)\;"
+           "addi\ta0,a0,%%tlsdesc_add_lo(.LT%=)\;"
+           "jalr\tt0,t0,%%tlsdesc_call(.LT%=)";
+  }
+  [(set_attr "type" "multi")
+   (set_attr "length" "16")
+   (set_attr "mode" "<MODE>")])
+
+;; TLSDESC with V extension: additionally clobbers all 32 vector registers
+;; (using LMUL=8 groups: v0, v8, v16, v24 each cover 8 physical registers)
+;; and vector CSRs (vl, vtype, vxrm, vxsat) per the psABI.
+(define_insn "tlsdesc_vec<mode>"
+  [(set (reg:P A0_REGNUM)
+       (unspec:P [(match_operand:P 0 "symbolic_operand" "")]
+                 UNSPEC_TLSDESC))
+   (clobber (reg:P T0_REGNUM))
+   (clobber (reg:RVVM8QI 96))
+   (clobber (reg:RVVM8QI 104))
+   (clobber (reg:RVVM8QI 112))
+   (clobber (reg:RVVM8QI 120))
+   (clobber (reg:SI VL_REGNUM))
+   (clobber (reg:SI VTYPE_REGNUM))
+   (clobber (reg:SI VXRM_REGNUM))
+   (clobber (reg:SI VXSAT_REGNUM))]
+  "TARGET_TLSDESC && TARGET_VECTOR"
   {
     return ".LT%=: auipc\ta0,%%tlsdesc_hi(%0)\;"
            "<load>\tt0,%%tlsdesc_load_lo(.LT%=)(a0)\;"
diff --git a/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber.c 
b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber.c
new file mode 100644
index 00000000000..6a004d6820f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber.c
@@ -0,0 +1,29 @@
+/* Verify that the TLSDESC resolver only clobbers a0 and t0 while assuming
+   all other registers as preserved per its custom ABI (no vector case),
+   which is different from a normal call.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target tls_native } */
+/* { dg-options "-O2 -fpic -mtls-dialect=desc -march=rv64gc -mabi=lp64d" } */
+/* { dg-require-effective-target fpic } */
+
+extern __thread int tls_var;
+
+long
+test_clobber (long a, long b, long c, long d)
+{
+  /* a=a0, b=a1, c=a2, d=a3.
+     TLSDESC clobbers a0 and t0 only, so the compiler must save/restore
+     a0 (by stack or mv or whatever), but should not do the same thing
+     for a1-a3 like a normal call.  */
+  tls_var = 1;
+  return a + b + c + d;
+}
+
+/* The TLSDESC call should be present.  */
+/* { dg-final { scan-assembler-times {jalr\tt0,} 1 } } */
+
+/* ra/a1-a3 should NOT be moved to s-regs or saved to stack.  */
+/* { dg-final { scan-assembler-not {mv\ts[0-9]+,a[0-9]+} } } */
+/* { dg-final { scan-assembler-not {sd\ta[0-9]+,.*\(sp\)} } } */
+/* { dg-final { scan-assembler-not {sd\tra,.*\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v.c 
b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v.c
new file mode 100644
index 00000000000..a5fb350f76e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v.c
@@ -0,0 +1,56 @@
+/* Verify that when the V extension is enabled, the TLSDESC resolver clobbers
+   all vector registers per the psABI.  The compiler must save/restore any
+   live vector registers across the TLSDESC call.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target tls_native } */
+/* { dg-options "-O2 -fpic -mtls-dialect=desc -march=rv64gcv -mabi=lp64d" } */
+/* { dg-require-effective-target fpic } */
+
+extern __thread int tls_var;
+
+void
+test_vector_reg_clobber (void)
+{
+  __rvv_int32m1_t v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12;
+
+  /* Write two v-regs.  */
+  asm volatile ("# def v1" : "=vr"(v1));
+  asm volatile ("# def v2" : "=vr"(v2));
+  asm volatile ("# def v3" : "=vr"(v3));
+  asm volatile ("# def v4" : "=vr"(v4));
+  asm volatile ("# def v5" : "=vr"(v5));
+  asm volatile ("# def v6" : "=vr"(v6));
+  asm volatile ("# def v7" : "=vr"(v7));
+  asm volatile ("# def v8" : "=vr"(v8));
+  asm volatile ("# def v9" : "=vr"(v9));
+  asm volatile ("# def v10" : "=vr"(v10));
+  asm volatile ("# def v11" : "=vr"(v11));
+  asm volatile ("# def v12" : "=vr"(v12));
+
+  /* TLSDESC call — clobbers all vector regs.  */
+  asm volatile ("" ::: "memory");  /* Prevent scheduling...  */
+  tls_var = 1;
+  asm volatile ("" ::: "memory");  /* Prevent scheduling...  */
+
+  /* Read the two v-regs; their live-range spans across the TLSDESC call,
+     so the compiler must emit vector store/load pairs to preserve them.  */
+  asm volatile ("# use v1" : : "vr"(v1));
+  asm volatile ("# use v2" : : "vr"(v2));
+  asm volatile ("# use v3" : : "vr"(v3));
+  asm volatile ("# use v4" : : "vr"(v4));
+  asm volatile ("# use v5" : : "vr"(v5));
+  asm volatile ("# use v6" : : "vr"(v6));
+  asm volatile ("# use v7" : : "vr"(v7));
+  asm volatile ("# use v8" : : "vr"(v8));
+  asm volatile ("# use v9" : : "vr"(v9));
+  asm volatile ("# use v10" : : "vr"(v10));
+  asm volatile ("# use v11" : : "vr"(v11));
+  asm volatile ("# use v12" : : "vr"(v12));
+}
+
+/* { dg-final { scan-assembler-times {jalr\tt0,} 1 } } */
+
+/* Vector stores before and loads after the TLSDESC call.  */
+/* { dg-final { scan-assembler-times {\tvs[0-9]+r\.v\t} 12 } } */
+/* { dg-final { scan-assembler-times {\tvl[0-9]+re[0-9]+\.v\t} 12 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v_csr.c 
b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v_csr.c
new file mode 100644
index 00000000000..ffb9c9a61a4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/tlsdesc_clobber_v_csr.c
@@ -0,0 +1,39 @@
+/* Verify that when the V extension is enabled, the TLSDESC resolver clobbers
+   vector CSRs (vl, vtype, vxrm, vxsat) per the psABI.  The compiler must
+   re-emit a vsetvli after the TLSDESC call to recover the vector status. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target tls_native } */
+/* { dg-options "-O2 -fpic -mtls-dialect=desc -march=rv64gcv -mabi=lp64d" } */
+/* { dg-require-effective-target fpic } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+extern __thread int tls_var;
+
+void
+test_vector_csr_clobber (v4si *in, v4si *out)
+{
+  v4si vec;
+
+  /* A pair of local load/store whose live-range does not span accross
+     the TLSDESC.  It has a special size format so it needs a vsetvli.  */
+  vec = *in;
+  *out = vec;
+
+  /* TLSDESC call — clobbers all vector CSRs including vl/vtype.  */
+  asm volatile ("" ::: "memory");  /* Prevent scheduling...  */
+  tls_var = 1;
+  asm volatile ("" ::: "memory");  /* Prevent scheduling...  */
+
+   /* Another pair of local load/store. But since TLSDESC clobbers vl/vtype, we
+     must re-emit a vsetvli here.  */
+  vec = *in;
+  *out = vec;
+}
+
+/* { dg-final { scan-assembler-times {jalr\tt0,} 1 } } */
+
+/* Two vsetvli: one before each vector segment.  The second is needed because
+   TLSDESC clobbers vl/vtype.  */
+/* { dg-final { scan-assembler-times {vsetvli|vsetivli} 2 } } */
-- 
2.47.1

Reply via email to