[RFC PATCH v2 2/5] x86: Support for Static Trampolines

[madvenka@linux.microsoft.com]

From: "Madhavan T. Venkataraman" <madvenka@linux.microsoft.com>

	- Define the arch-specific initialization function ffi_tramp_arch ()
	  that returns trampoline size information to common code.

	- Define the trampoline code mapping and data mapping sizes.

	- Define the trampoline code table statically.

	- Introduce a tiny prolog for each ABI handling function. The ABI
	  handlers addressed are:

	  	- ffi_closure_unix64
		- ffi_closure_unix64_sse
		- ffi_closure_win64

	  Their prolog functions are called:

		- ffi_closure_unix64_alt
		- ffi_closure_unix64_sse_alt
		- ffi_closure_win64_alt

	  The legacy trampoline jumps to the ABI handler. The static
	  trampoline jumps to the prolog function. The prolog function uses
	  the information provided by the static trampoline, sets things up
	  for the ABI handler and then jumps to the ABI handler.

	- Call ffi_closure_tramp_init () in ffi_prep_closure_loc () to
	  initialize static trampoline parameters.

Signed-off-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com>
---
 src/x86/ffi64.c      | 34 ++++++++++++++++++++++--
 src/x86/ffiw64.c     | 10 +++++++
 src/x86/internal64.h | 10 +++++++
 src/x86/unix64.S     | 62 ++++++++++++++++++++++++++++++++++++++++++++
 src/x86/win64.S      | 12 +++++++++
 5 files changed, 126 insertions(+), 2 deletions(-)

diff --git a/src/x86/ffi64.c b/src/x86/ffi64.c
index 39f9598..17c3117 100644
--- a/src/x86/ffi64.c
+++ b/src/x86/ffi64.c
@@ -713,7 +713,9 @@ ffi_call_go (ffi_cif *cif, void (*fn)(void), void *rvalue,
 #endif /* FFI_GO_CLOSURES */
 
 extern void ffi_closure_unix64(void) FFI_HIDDEN;
+extern void ffi_closure_unix64_alt(void) FFI_HIDDEN;
 extern void ffi_closure_unix64_sse(void) FFI_HIDDEN;
+extern void ffi_closure_unix64_sse_alt(void) FFI_HIDDEN;
 
 #ifndef __ILP32__
 extern ffi_status
@@ -742,6 +744,7 @@ ffi_prep_closure_loc (ffi_closure* closure,
     0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00
   };
   void (*dest)(void);
+  void (*dest_alt)(void);
   char *tramp = closure->tramp;
 
 #ifndef __ILP32__
@@ -752,13 +755,28 @@ ffi_prep_closure_loc (ffi_closure* closure,
     return FFI_BAD_ABI;
 
   if (cif->flags & UNIX64_FLAG_XMM_ARGS)
-    dest = ffi_closure_unix64_sse;
+    {
+      dest = ffi_closure_unix64_sse;
+      dest_alt = ffi_closure_unix64_sse_alt;
+    }
   else
-    dest = ffi_closure_unix64;
+    {
+      dest = ffi_closure_unix64;
+      dest_alt = ffi_closure_unix64_alt;
+    }
+
+  if (ffi_tramp_is_present(closure))
+    {
+      /* Initialize the static trampoline's parameters. */
+      ffi_tramp_set_parms (closure->ftramp, dest_alt, closure);
+      goto out;
+    }
 
+  /* Initialize the dynamic trampoline. */
   memcpy (tramp, trampoline, sizeof(trampoline));
   *(UINT64 *)(tramp + sizeof (trampoline)) = (uintptr_t)dest;
 
+out:
   closure->cif = cif;
   closure->fun = fun;
   closure->user_data = user_data;
@@ -892,4 +910,16 @@ ffi_prep_go_closure (ffi_go_closure* closure, ffi_cif* cif,
 
 #endif /* FFI_GO_CLOSURES */
 
+#if defined(FFI_EXEC_STATIC_TRAMP)
+void *
+ffi_tramp_arch (size_t *tramp_size, size_t *map_size)
+{
+  extern void *trampoline_code_table;
+
+  *tramp_size = UNIX64_TRAMP_SIZE;
+  *map_size = UNIX64_TRAMP_MAP_SIZE;
+  return &trampoline_code_table;
+}
+#endif
+
 #endif /* __x86_64__ */
diff --git a/src/x86/ffiw64.c b/src/x86/ffiw64.c
index a43a9eb..df81d66 100644
--- a/src/x86/ffiw64.c
+++ b/src/x86/ffiw64.c
@@ -187,6 +187,7 @@ EFI64(ffi_call_go)(ffi_cif *cif, void (*fn)(void), void *rvalue,
 
 
 extern void ffi_closure_win64(void) FFI_HIDDEN;
+extern void ffi_closure_win64_alt(void) FFI_HIDDEN;
 
 #ifdef FFI_GO_CLOSURES
 extern void ffi_go_closure_win64(void) FFI_HIDDEN;
@@ -220,9 +221,18 @@ EFI64(ffi_prep_closure_loc)(ffi_closure* closure,
       return FFI_BAD_ABI;
     }
 
+  if (ffi_tramp_is_present(closure))
+    {
+      /* Initialize the static trampoline's parameters. */
+      ffi_tramp_set_parms (closure->ftramp, ffi_closure_win64_alt, closure);
+      goto out;
+    }
+
+  /* Initialize the dynamic trampoline. */
   memcpy (tramp, trampoline, sizeof(trampoline));
   *(UINT64 *)(tramp + sizeof (trampoline)) = (uintptr_t)ffi_closure_win64;
 
+out:
   closure->cif = cif;
   closure->fun = fun;
   closure->user_data = user_data;
diff --git a/src/x86/internal64.h b/src/x86/internal64.h
index 512e955..272b914 100644
--- a/src/x86/internal64.h
+++ b/src/x86/internal64.h
@@ -20,3 +20,13 @@
 #define UNIX64_FLAG_RET_IN_MEM	(1 << 10)
 #define UNIX64_FLAG_XMM_ARGS	(1 << 11)
 #define UNIX64_SIZE_SHIFT	12
+
+#if defined(FFI_EXEC_STATIC_TRAMP)
+/*
+ * For the trampoline code table mapping, a mapping size of 4K (base page size)
+ * is chosen.
+ */
+#define UNIX64_TRAMP_MAP_SHIFT	12
+#define UNIX64_TRAMP_MAP_SIZE	(1 << UNIX64_TRAMP_MAP_SHIFT)
+#define UNIX64_TRAMP_SIZE	40
+#endif
diff --git a/src/x86/unix64.S b/src/x86/unix64.S
index 89d7db1..0e0de61 100644
--- a/src/x86/unix64.S
+++ b/src/x86/unix64.S
@@ -270,6 +270,17 @@ L(UW6):
 L(UW7):
 ENDF(C(ffi_closure_unix64_sse))
 
+	.balign	2
+	.globl	C(ffi_closure_unix64_sse_alt)
+	FFI_HIDDEN(C(ffi_closure_unix64_sse_alt))
+
+C(ffi_closure_unix64_sse_alt):
+	_CET_ENDBR
+	movq	8(%rsp), %r10
+	addq	$16, %rsp
+	jmp	C(ffi_closure_unix64_sse)
+ENDF(C(ffi_closure_unix64_sse_alt))
+
 	.balign	2
 	.globl	C(ffi_closure_unix64)
 	FFI_HIDDEN(C(ffi_closure_unix64))
@@ -400,6 +411,17 @@ L(la):	call	PLT(C(abort))
 L(UW11):
 ENDF(C(ffi_closure_unix64))
 
+	.balign	8
+	.globl	C(ffi_closure_unix64_alt)
+	FFI_HIDDEN(C(ffi_closure_unix64_alt))
+
+C(ffi_closure_unix64_alt):
+	_CET_ENDBR
+	movq	8(%rsp), %r10
+	addq	$16, %rsp
+	jmp	C(ffi_closure_unix64)
+	ENDF(C(ffi_closure_unix64_alt))
+
 	.balign	2
 	.globl	C(ffi_go_closure_unix64_sse)
 	FFI_HIDDEN(C(ffi_go_closure_unix64_sse))
@@ -456,6 +478,46 @@ L(sse_entry2):
 L(UW17):
 ENDF(C(ffi_go_closure_unix64))
 
+#if defined(FFI_EXEC_STATIC_TRAMP)
+/*
+ * The trampoline uses register r10. It saves the original value of r10 on
+ * the stack.
+ *
+ * The trampoline has two parameters - target code to jump to and data for
+ * the target code. The trampoline extracts the parameters from its parameter
+ * block (see tramp_table_map()). The trampoline saves the data address on
+ * the stack. Finally, it jumps to the target code.
+ *
+ * The target code can choose to:
+ *
+ * - restore the value of r10
+ * - load the data address in a register
+ * - restore the stack pointer to what it was when the trampoline was invoked.
+ */
+	.align	UNIX64_TRAMP_MAP_SIZE
+	.globl	trampoline_code_table
+	FFI_HIDDEN(C(trampoline_code_table))
+
+C(trampoline_code_table):
+	.rept	UNIX64_TRAMP_MAP_SIZE / UNIX64_TRAMP_SIZE
+	endbr64
+	subq	$16, %rsp		/* Make space on the stack */
+	movq	%r10, (%rsp)		/* Save %r10 on stack */
+	movq	4077(%rip), %r10	/* Copy data into %r10 */
+	movq	%r10, 8(%rsp)		/* Save data on stack */
+	movq	4073(%rip), %r10	/* Copy code into %r10 */
+	jmp	*%r10			/* Jump to code */
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	.endr
+ENDF(C(trampoline_code_table))
+	.align	UNIX64_TRAMP_MAP_SIZE
+#endif /* FFI_EXEC_STATIC_TRAMP */
+
 /* Sadly, OSX cctools-as doesn't understand .cfi directives at all.  */
 
 #ifdef __APPLE__
diff --git a/src/x86/win64.S b/src/x86/win64.S
index 8315e8b..6ca3068 100644
--- a/src/x86/win64.S
+++ b/src/x86/win64.S
@@ -234,6 +234,18 @@ C(ffi_closure_win64):
 
 	cfi_endproc
 	SEH(.seh_endproc)
+
+	.align	8
+	.globl	C(ffi_closure_win64_alt)
+	FFI_HIDDEN(C(ffi_closure_win64_alt))
+
+	SEH(.seh_proc ffi_closure_win64_alt)
+C(ffi_closure_win64_alt):
+	_CET_ENDBR
+	movq	8(%rsp), %r10
+	addq	$16, %rsp
+	jmp	C(ffi_closure_win64)
+	SEH(.seh_endproc)
 #endif /* __x86_64__ */
 
 #if defined __ELF__ && defined __linux__
-- 
2.27.0