[gcc r12-9945] LoongArch: Implement __builtin_thread_pointer for TLS.

[gcc r12-9945] LoongArch: Implement __builtin_thread_pointer for TLS.

[LuluCheng]

https://gcc.gnu.org/g:41aab8301d79b35b60f9ba95913b484988ed08e1

commit r12-9945-g41aab8301d79b35b60f9ba95913b484988ed08e1
Author: chenxiaolong <chenxiaolong@loongson.cn>
Date:   Tue Oct 24 14:40:14 2023 +0800

    LoongArch: Implement __builtin_thread_pointer for TLS.
    
    gcc/ChangeLog:
    
            * config/loongarch/loongarch.md (get_thread_pointer<mode>):Adds the
            instruction template corresponding to the __builtin_thread_pointer
            function.
            * doc/extend.texi:Add the __builtin_thread_pointer function support
            description to the documentation.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/loongarch/builtin_thread_pointer.c: New test.
    
    (cherry picked from commit 1b30ef7cea773e0af527dbf821e0be42b6a264f8)

Diff:
---
 gcc/config/loongarch/loongarch.md                  |   7 ++
 gcc/doc/extend.texi                                | 134 +++++++++++++++++++++
 .../gcc.target/loongarch/builtin_thread_pointer.c  |  10 ++
 3 files changed, 151 insertions(+)

diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index a64142c7a780..b49e058407c7 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -93,6 +93,7 @@
 
 (define_constants
   [(RETURN_ADDR_REGNUM		1)
+   (TP_REGNUM			2)
    (T0_REGNUM			12)
    (T1_REGNUM			13)
    (S0_REGNUM			23)
@@ -3295,6 +3296,12 @@
   [(set_attr "length" "0")
    (set_attr "type" "ghost")])
 
+;; Named pattern for expanding thread pointer reference.
+(define_expand "get_thread_pointer<mode>"
+  [(set (match_operand:P 0 "register_operand" "=r")
+	(reg:P TP_REGNUM))]
+  "HAVE_AS_TLS"
+  {})
 \f
 (define_split
   [(match_operand 0 "small_data_pattern")]
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 33a776a7978c..0eb9bdcfac51 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -14618,6 +14618,7 @@ instructions, but allow the compiler to schedule those calls.
 * Blackfin Built-in Functions::
 * BPF Built-in Functions::
 * FR-V Built-in Functions::
+* LoongArch Base Built-in Functions::
 * MIPS DSP Built-in Functions::
 * MIPS Paired-Single Support::
 * MIPS Loongson Built-in Functions::
@@ -16068,6 +16069,139 @@ Use the @code{nldub} instruction to load the contents of address @var{x}
 into the data cache.  The instruction is issued in slot I1@.
 @end table
 
+@node LoongArch Base Built-in Functions
+@subsection LoongArch Base Built-in Functions
+
+These built-in functions are available for LoongArch.
+
+Data Type Description:
+@itemize
+@item @code{imm0_31}, a compile-time constant in range 0 to 31;
+@item @code{imm0_16383}, a compile-time constant in range 0 to 16383;
+@item @code{imm0_32767}, a compile-time constant in range 0 to 32767;
+@item @code{imm_n2048_2047}, a compile-time constant in range -2048 to 2047;
+@end itemize
+
+The intrinsics provided are listed below:
+@smallexample
+    unsigned int __builtin_loongarch_movfcsr2gr (imm0_31)
+    void __builtin_loongarch_movgr2fcsr (imm0_31, unsigned int)
+    void __builtin_loongarch_cacop_d (imm0_31, unsigned long int, imm_n2048_2047)
+    unsigned int __builtin_loongarch_cpucfg (unsigned int)
+    void __builtin_loongarch_asrtle_d (long int, long int)
+    void __builtin_loongarch_asrtgt_d (long int, long int)
+    long int __builtin_loongarch_lddir_d (long int, imm0_31)
+    void __builtin_loongarch_ldpte_d (long int, imm0_31)
+
+    int __builtin_loongarch_crc_w_b_w (char, int)
+    int __builtin_loongarch_crc_w_h_w (short, int)
+    int __builtin_loongarch_crc_w_w_w (int, int)
+    int __builtin_loongarch_crc_w_d_w (long int, int)
+    int __builtin_loongarch_crcc_w_b_w (char, int)
+    int __builtin_loongarch_crcc_w_h_w (short, int)
+    int __builtin_loongarch_crcc_w_w_w (int, int)
+    int __builtin_loongarch_crcc_w_d_w (long int, int)
+
+    unsigned int __builtin_loongarch_csrrd_w (imm0_16383)
+    unsigned int __builtin_loongarch_csrwr_w (unsigned int, imm0_16383)
+    unsigned int __builtin_loongarch_csrxchg_w (unsigned int, unsigned int, imm0_16383)
+    unsigned long int __builtin_loongarch_csrrd_d (imm0_16383)
+    unsigned long int __builtin_loongarch_csrwr_d (unsigned long int, imm0_16383)
+    unsigned long int __builtin_loongarch_csrxchg_d (unsigned long int, unsigned long int, imm0_16383)
+
+    unsigned char __builtin_loongarch_iocsrrd_b (unsigned int)
+    unsigned short __builtin_loongarch_iocsrrd_h (unsigned int)
+    unsigned int __builtin_loongarch_iocsrrd_w (unsigned int)
+    unsigned long int __builtin_loongarch_iocsrrd_d (unsigned int)
+    void __builtin_loongarch_iocsrwr_b (unsigned char, unsigned int)
+    void __builtin_loongarch_iocsrwr_h (unsigned short, unsigned int)
+    void __builtin_loongarch_iocsrwr_w (unsigned int, unsigned int)
+    void __builtin_loongarch_iocsrwr_d (unsigned long int, unsigned int)
+
+    void __builtin_loongarch_dbar (imm0_32767)
+    void __builtin_loongarch_ibar (imm0_32767)
+
+    void __builtin_loongarch_syscall (imm0_32767)
+    void __builtin_loongarch_break (imm0_32767)
+@end smallexample
+
+@emph{Note:}Since the control register is divided into 32-bit and 64-bit,
+but the access instruction is not distinguished. So GCC renames the control
+instructions when implementing intrinsics.
+
+Take the csrrd instruction as an example, built-in functions are implemented as follows:
+@smallexample
+  __builtin_loongarch_csrrd_w  // When reading the 32-bit control register use.
+  __builtin_loongarch_csrrd_d  // When reading the 64-bit control register use.
+@end smallexample
+
+For the convenience of use, the built-in functions are encapsulated,
+the encapsulated functions and @code{__drdtime_t, __rdtime_t} are
+defined in the @code{larchintrin.h}. So if you call the following
+function you need to include @code{larchintrin.h}.
+
+@smallexample
+     typedef struct drdtime@{
+            unsigned long dvalue;
+            unsigned long dtimeid;
+     @} __drdtime_t;
+
+     typedef struct rdtime@{
+            unsigned int value;
+            unsigned int timeid;
+     @} __rdtime_t;
+@end smallexample
+
+@smallexample
+    __drdtime_t __rdtime_d (void)
+    __rdtime_t  __rdtimel_w (void)
+    __rdtime_t  __rdtimeh_w (void)
+    unsigned int  __movfcsr2gr (imm0_31)
+    void __movgr2fcsr (imm0_31, unsigned int)
+    void __cacop_d (imm0_31, unsigned long, imm_n2048_2047)
+    unsigned int  __cpucfg (unsigned int)
+    void __asrtle_d (long int, long int)
+    void __asrtgt_d (long int, long int)
+    long int  __lddir_d (long int, imm0_31)
+    void __ldpte_d (long int, imm0_31)
+
+    int  __crc_w_b_w (char, int)
+    int  __crc_w_h_w (short, int)
+    int  __crc_w_w_w (int, int)
+    int  __crc_w_d_w (long int, int)
+    int  __crcc_w_b_w (char, int)
+    int  __crcc_w_h_w (short, int)
+    int  __crcc_w_w_w (int, int)
+    int  __crcc_w_d_w (long int, int)
+
+    unsigned int  __csrrd_w (imm0_16383)
+    unsigned int  __csrwr_w (unsigned int, imm0_16383)
+    unsigned int  __csrxchg_w (unsigned int, unsigned int, imm0_16383)
+    unsigned long  __csrrd_d (imm0_16383)
+    unsigned long  __csrwr_d (unsigned long, imm0_16383)
+    unsigned long  __csrxchg_d (unsigned long, unsigned long, imm0_16383)
+
+    unsigned char   __iocsrrd_b (unsigned int)
+    unsigned short  __iocsrrd_h (unsigned int)
+    unsigned int  __iocsrrd_w (unsigned int)
+    unsigned long  __iocsrrd_d (unsigned int)
+    void __iocsrwr_b (unsigned char, unsigned int)
+    void __iocsrwr_h (unsigned short, unsigned int)
+    void __iocsrwr_w (unsigned int, unsigned int)
+    void __iocsrwr_d (unsigned long, unsigned int)
+
+    void __dbar (imm0_32767)
+    void __ibar (imm0_32767)
+
+    void __syscall (imm0_32767)
+    void __break (imm0_32767)
+@end smallexample
+
+Returns the value that is currently set in the @samp{tp} register.
+@smallexample
+    void * __builtin_thread_pointer (void)
+@end smallexample
+
 @node MIPS DSP Built-in Functions
 @subsection MIPS DSP Built-in Functions
 
diff --git a/gcc/testsuite/gcc.target/loongarch/builtin_thread_pointer.c b/gcc/testsuite/gcc.target/loongarch/builtin_thread_pointer.c
new file mode 100644
index 000000000000..541e3b143bd2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/builtin_thread_pointer.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target tls_native } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler "or\t\\\$r4,\\\$r2,\\\$r0" } } */
+
+void *
+get_tp ()
+{
+  return __builtin_thread_pointer ();
+}