RISC-V: Add support for dl_runtime_profile (BZ #31151)

Code is mostly inspired from the LoongArch one, which has a similar ABI,
with minor changes to support riscv32 and register differences.

This fixes elf/tst-sprof-basic. This also fixes elf/tst-audit1,
elf/tst-audit2 and elf/tst-audit8 with recent binutils snapshots when
--enable-bind-now is used.

Resolves: BZ #31151

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>

4 files changed, 225 insertions, 1 deletions

diff --git a/sysdeps/riscv/Makefile b/sysdeps/riscv/Makefile
index 8fb10b164f..c08753ae8a 100644
--- a/sysdeps/riscv/Makefile
+++ b/sysdeps/riscv/Makefile
@@ -2,6 +2,10 @@ ifeq ($(subdir),misc)
 sysdep_headers += sys/asm.h
 endif
 
+ifeq ($(subdir),elf)
+gen-as-const-headers += dl-link.sym
+endif
+
 # RISC-V's assembler also needs to know about PIC as it changes the definition
 # of some assembler macros.
 ASFLAGS-.os += $(pic-ccflag)
diff --git a/sysdeps/riscv/dl-link.sym b/sysdeps/riscv/dl-link.sym
new file mode 100644
index 0000000000..b430a064c9
--- /dev/null
+++ b/sysdeps/riscv/dl-link.sym
@@ -0,0 +1,18 @@
+#include <stddef.h>
+#include <sysdep.h>
+#include <link.h>
+
+DL_SIZEOF_RG            sizeof(struct La_riscv_regs)
+DL_SIZEOF_RV            sizeof(struct La_riscv_retval)
+
+DL_OFFSET_RG_A0         offsetof(struct La_riscv_regs, lr_reg)
+#ifndef __riscv_float_abi_soft
+DL_OFFSET_RG_FA0        offsetof(struct La_riscv_regs, lr_fpreg)
+#endif
+DL_OFFSET_RG_RA         offsetof(struct La_riscv_regs, lr_ra)
+DL_OFFSET_RG_SP         offsetof(struct La_riscv_regs, lr_sp)
+
+DL_OFFSET_RV_A0         offsetof(struct La_riscv_retval, lrv_a0)
+#ifndef __riscv_float_abi_soft
+DL_OFFSET_RV_FA0        offsetof(struct La_riscv_retval, lrv_fa0)
+#endif
diff --git a/sysdeps/riscv/dl-machine.h b/sysdeps/riscv/dl-machine.h
index c0c9bd93ad..48aee81aa9 100644
--- a/sysdeps/riscv/dl-machine.h
+++ b/sysdeps/riscv/dl-machine.h
@@ -313,13 +313,38 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
   if (l->l_info[DT_JMPREL])
     {
       extern void _dl_runtime_resolve (void) __attribute__ ((visibility ("hidden")));
+      extern void _dl_runtime_profile (void) __attribute__ ((visibility ("hidden")));
       ElfW(Addr) *gotplt = (ElfW(Addr) *) D_PTR (l, l_info[DT_PLTGOT]);
       /* If a library is prelinked but we have to relocate anyway,
 	 we have to be able to undo the prelinking of .got.plt.
 	 The prelinker saved the address of .plt for us here.  */
       if (gotplt[1])
 	l->l_mach.plt = gotplt[1] + l->l_addr;
-      gotplt[0] = (ElfW(Addr)) &_dl_runtime_resolve;
+      /* The gotplt[0] entry contains the address of a function which gets
+	 called to get the address of a so far unresolved function and
+	 jump to it.  The profiling extension of the dynamic linker allows
+	 to intercept the calls to collect information.  In this case we
+	 don't store the address in the GOT so that all future calls also
+	 end in this function.  */
+#ifdef SHARED
+      if (profile != 0)
+	{
+	  gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile;
+
+	  if (GLRO(dl_profile) != NULL
+	      && _dl_name_match_p (GLRO(dl_profile), l))
+	    /* Say that we really want profiling and the timers are
+	       started.  */
+	    GL(dl_profile_map) = l;
+	}
+      else
+#endif
+	{
+	  /* 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.  */
+	  gotplt[0] = (ElfW(Addr)) &_dl_runtime_resolve;
+	}
       gotplt[1] = (ElfW(Addr)) l;
     }
 
diff --git a/sysdeps/riscv/dl-trampoline.S b/sysdeps/riscv/dl-trampoline.S
index dec304180b..ecaee0540e 100644
--- a/sysdeps/riscv/dl-trampoline.S
+++ b/sysdeps/riscv/dl-trampoline.S
@@ -20,6 +20,8 @@
 #include <sysdep.h>
 #include <sys/asm.h>
 
+#include "dl-link.h"
+
 /* Assembler veneer called from the PLT header code for lazy loading.
    The PLT header passes its own args in t0-t2.  */
 
@@ -88,3 +90,178 @@ ENTRY (_dl_runtime_resolve)
   # Invoke the callee.
   jr t1
 END (_dl_runtime_resolve)
+
+#if !defined PROF && defined SHARED
+ENTRY (_dl_runtime_profile)
+  /* RISC-V we get called with:
+  t0          linkr_map pointer
+  t1          the scaled offset stored in t0, which can be used
+              to calculate the offset of the current symbol in .rela.plt
+  t2          %hi(%pcrel(.got.plt)) stored in t2, no use in this function
+  t3          dl resolver entry point, no use in this function
+
+  Stack frame layout with hard float:
+     RV64      RV32
+  [sp, #96] [sp, #48]  La_riscv_regs
+  [sp, #48] [sp, #24]  La_riscv_retval
+  [sp, #40] [sp, #20]  frame size return from pltenter
+  [sp, #32] [sp, #16]  dl_profile_call saved a1
+  [sp, #24] [sp, #12]  dl_profile_call saved a0
+  [sp, #16] [sp,  #8]  T1
+  [sp,  #0] [sp,  #0]  ra, fp   <- fp
+   */
+
+# define OFFSET_T1              2*SZREG
+# define OFFSET_SAVED_CALL_A0   OFFSET_T1 + SZREG
+# define OFFSET_SAVED_CALL_A1   OFFSET_SAVED_CALL_A0 + SZREG
+# define OFFSET_FS              OFFSET_SAVED_CALL_A1 + SZREG
+# define OFFSET_RV              OFFSET_FS + SZREG
+# define OFFSET_RG              OFFSET_RV + DL_SIZEOF_RV
+
+# define SF_SIZE                (-(-(OFFSET_RG + DL_SIZEOF_RG) & ALMASK))
+
+  # Save arguments to stack.
+  add sp, sp, -SF_SIZE
+  REG_S ra, 0(sp)
+  REG_S fp, SZREG(sp)
+
+  mv fp, sp
+
+  REG_S a0, OFFSET_RG + DL_OFFSET_RG_A0 + 0*SZREG(fp)
+  REG_S a1, OFFSET_RG + DL_OFFSET_RG_A0 + 1*SZREG(fp)
+  REG_S a2, OFFSET_RG + DL_OFFSET_RG_A0 + 2*SZREG(fp)
+  REG_S a3, OFFSET_RG + DL_OFFSET_RG_A0 + 3*SZREG(fp)
+  REG_S a4, OFFSET_RG + DL_OFFSET_RG_A0 + 4*SZREG(fp)
+  REG_S a5, OFFSET_RG + DL_OFFSET_RG_A0 + 5*SZREG(fp)
+  REG_S a6, OFFSET_RG + DL_OFFSET_RG_A0 + 6*SZREG(fp)
+  REG_S a7, OFFSET_RG + DL_OFFSET_RG_A0 + 7*SZREG(fp)
+
+#ifndef __riscv_float_abi_soft
+  FREG_S fa0, OFFSET_RG + DL_OFFSET_RG_FA0 + 0*SZFREG(fp)
+  FREG_S fa1, OFFSET_RG + DL_OFFSET_RG_FA0 + 1*SZFREG(fp)
+  FREG_S fa2, OFFSET_RG + DL_OFFSET_RG_FA0 + 2*SZFREG(fp)
+  FREG_S fa3, OFFSET_RG + DL_OFFSET_RG_FA0 + 3*SZFREG(fp)
+  FREG_S fa4, OFFSET_RG + DL_OFFSET_RG_FA0 + 4*SZFREG(fp)
+  FREG_S fa5, OFFSET_RG + DL_OFFSET_RG_FA0 + 5*SZFREG(fp)
+  FREG_S fa6, OFFSET_RG + DL_OFFSET_RG_FA0 + 6*SZFREG(fp)
+  FREG_S fa7, OFFSET_RG + DL_OFFSET_RG_FA0 + 7*SZFREG(fp)
+#endif
+
+  # Update .got.plt and obtain runtime address of callee.
+  slli a1, t1, 1
+  mv a0, t0
+  add a1, a1, t1          # link map
+  mv a2, ra               # return addr
+  addi a3, fp, OFFSET_RG  # La_riscv_regs pointer
+  addi a4, fp, OFFSET_FS  # frame size return from pltenter
+
+  REG_S a0, OFFSET_SAVED_CALL_A0(fp)
+  REG_S a1, OFFSET_SAVED_CALL_A1(fp)
+
+  la t2, _dl_profile_fixup
+  jalr t2
+
+  REG_L t3, OFFSET_FS(fp)
+  bgez t3, 1f
+
+  # Save the return.
+  mv t4, a0
+
+  # Restore arguments from stack.
+  REG_L a0, OFFSET_RG + DL_OFFSET_RG_A0 + 0*SZREG(fp)
+  REG_L a1, OFFSET_RG + DL_OFFSET_RG_A0 + 1*SZREG(fp)
+  REG_L a2, OFFSET_RG + DL_OFFSET_RG_A0 + 2*SZREG(fp)
+  REG_L a3, OFFSET_RG + DL_OFFSET_RG_A0 + 3*SZREG(fp)
+  REG_L a4, OFFSET_RG + DL_OFFSET_RG_A0 + 4*SZREG(fp)
+  REG_L a5, OFFSET_RG + DL_OFFSET_RG_A0 + 5*SZREG(fp)
+  REG_L a6, OFFSET_RG + DL_OFFSET_RG_A0 + 6*SZREG(fp)
+  REG_L a7, OFFSET_RG + DL_OFFSET_RG_A0 + 7*SZREG(fp)
+
+#ifndef __riscv_float_abi_soft
+  FREG_L fa0, OFFSET_RG + DL_OFFSET_RG_FA0 + 0*SZFREG(fp)
+  FREG_L fa1, OFFSET_RG + DL_OFFSET_RG_FA0 + 1*SZFREG(fp)
+  FREG_L fa2, OFFSET_RG + DL_OFFSET_RG_FA0 + 2*SZFREG(fp)
+  FREG_L fa3, OFFSET_RG + DL_OFFSET_RG_FA0 + 3*SZFREG(fp)
+  FREG_L fa4, OFFSET_RG + DL_OFFSET_RG_FA0 + 4*SZFREG(fp)
+  FREG_L fa5, OFFSET_RG + DL_OFFSET_RG_FA0 + 5*SZFREG(fp)
+  FREG_L fa6, OFFSET_RG + DL_OFFSET_RG_FA0 + 6*SZFREG(fp)
+  FREG_L fa7, OFFSET_RG + DL_OFFSET_RG_FA0 + 7*SZFREG(fp)
+#endif
+
+  REG_L ra, 0(fp)
+  REG_L fp, SZREG(fp)
+
+  addi sp, sp, SF_SIZE
+  jr t4
+
+1:
+  # The new frame size is in t3.
+  sub sp, fp, t3
+  andi sp, sp, ALMASK
+
+  REG_S a0, OFFSET_T1(fp)
+
+  mv a0, sp
+  addi a1, fp, SF_SIZE
+  mv a2, t3
+  la t4, memcpy
+  jalr t4
+
+  REG_L t4, OFFSET_T1(fp)
+
+  # Call the function.
+  REG_L a0, OFFSET_RG + DL_OFFSET_RG_A0 + 0*SZREG(fp)
+  REG_L a1, OFFSET_RG + DL_OFFSET_RG_A0 + 1*SZREG(fp)
+  REG_L a2, OFFSET_RG + DL_OFFSET_RG_A0 + 2*SZREG(fp)
+  REG_L a3, OFFSET_RG + DL_OFFSET_RG_A0 + 3*SZREG(fp)
+  REG_L a4, OFFSET_RG + DL_OFFSET_RG_A0 + 4*SZREG(fp)
+  REG_L a5, OFFSET_RG + DL_OFFSET_RG_A0 + 5*SZREG(fp)
+  REG_L a6, OFFSET_RG + DL_OFFSET_RG_A0 + 6*SZREG(fp)
+  REG_L a7, OFFSET_RG + DL_OFFSET_RG_A0 + 7*SZREG(fp)
+
+#ifndef __riscv_float_abi_soft
+  FREG_L fa0, OFFSET_RG + DL_OFFSET_RG_FA0 + 0*SZFREG(fp)
+  FREG_L fa1, OFFSET_RG + DL_OFFSET_RG_FA0 + 1*SZFREG(fp)
+  FREG_L fa2, OFFSET_RG + DL_OFFSET_RG_FA0 + 2*SZFREG(fp)
+  FREG_L fa3, OFFSET_RG + DL_OFFSET_RG_FA0 + 3*SZFREG(fp)
+  FREG_L fa4, OFFSET_RG + DL_OFFSET_RG_FA0 + 4*SZFREG(fp)
+  FREG_L fa5, OFFSET_RG + DL_OFFSET_RG_FA0 + 5*SZFREG(fp)
+  FREG_L fa6, OFFSET_RG + DL_OFFSET_RG_FA0 + 6*SZFREG(fp)
+  FREG_L fa7, OFFSET_RG + DL_OFFSET_RG_FA0 + 7*SZFREG(fp)
+#endif
+  jalr t4
+
+  REG_S a0, OFFSET_SAVED_CALL_A0 + DL_OFFSET_RV_A0(fp)
+  REG_S a1, OFFSET_SAVED_CALL_A0 + DL_OFFSET_RV_A0 + SZREG(fp)
+
+#ifndef __riscv_float_abi_soft
+  FREG_S fa0, OFFSET_SAVED_CALL_A0 + DL_OFFSET_RV_FA0(fp)
+  FREG_S fa1, OFFSET_SAVED_CALL_A0 + DL_OFFSET_RV_FA0 + SZFREG(fp)
+#endif
+
+  # Setup call to pltexit.
+  REG_L a0, OFFSET_SAVED_CALL_A0(fp)
+  REG_L a1, OFFSET_SAVED_CALL_A0 + SZREG(fp)
+  addi a2, fp, OFFSET_RG
+  addi a3, fp, OFFSET_RV
+  la t4, _dl_audit_pltexit
+  jalr t4
+
+  REG_L a0, OFFSET_RV + DL_OFFSET_RV_A0(fp)
+  REG_L a1, OFFSET_RV + DL_OFFSET_RV_A0 + SZREG(fp)
+
+#ifndef __riscv_float_abi_soft
+  FREG_L fa0, OFFSET_RV + DL_OFFSET_RV_FA0(fp)
+  FREG_L fa1, OFFSET_RV + DL_OFFSET_RV_FA0 + SZFREG(fp)
+#endif
+
+  # RA from within La_riscv_reg.
+  REG_L ra, OFFSET_RG + DL_OFFSET_RG_RA(fp)
+  mv sp, fp
+  ADDI sp, sp, SF_SIZE
+  REG_S fp, SZREG(fp)
+
+  jr ra
+
+END (_dl_runtime_profile)
+#endif /* SHARED */