Re: [RFC v6 2/9] build: Implement libnative library and the build machinery for libnative

[Helge Deller]

On 9/12/23 23:28, Yeqi Fu wrote:

This commit implements a shared library, where native functions are
rewritten as special instructions. At runtime, user programs load
the shared library, and special instructions are executed when
native functions are called.


Hello Yeqi,

I like the idea of speeding up linux-user with your approach.
Do you have a git tree which I can pull for testing (or please
mention the base commit your patches are based on)?

How does the emulation behaves if a guest has bugs and accesses
wrong memory locations, e.g.:
memcpy(NULL, "Hello", 6)
Will it segfault the same way as if it would have run natively?
At least I think the signal IP addresses will be different.

Regarding you implemenation:


diff --git a/common-user/native/libnative.S b/common-user/native/libnative.S
new file mode 100644
index 00..bc51dabedf
--- /dev/null
+++ b/common-user/native/libnative.S
@@ -0,0 +1,51 @@
+.macro special_instr sym
+#if defined(__i386__)


you use here #ifdefs,


+ ud0 \sym-1f, %eax; 1:
+#elif defined(__x86_64__)
+ ud0 \sym(%rip), %eax
+#elif defined(__arm__) || defined(__aarch64__)
+ hlt 0x
+1:  .word   \sym - 1b
+#elif defined(__mips__)
+ syscall 0x
+1:  .word   \sym - 1b
+#else
+# error
+#endif
+.endm
+
+.macro ret_instr
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)


and here again,


+ ret
+#elif defined(__arm__)
+ bx lr
+#elif defined(__mips__)
+ jr $ra
+#else
+# error
+#endif
+.endm
+
+/* Symbols of native functions */
+
+.macro define_function name
+ .text
+\name:
+ special_instr 9f


and here the pointer to the string.


+ ret_instr
+ .globl \name
+ .type \name, %function
+ .size \name, . - \name
+
+ .section .rodata
+9:  .asciz  "\name"
+.endm


IMHO, I think it would be easier if you just do:

+/* wrapper for native functions */
+
+.macro define_function name
+ .text
+ .align 8  /* function is 8-byte aligned */
+\name:
+/* every arch has up to 8 bytes for trigger and return instruction */
+#if defined(__i386__)
+ ud0 0, %eax
+ ret
+#elif defined(__x86_64__)
+ ud0 0, %eax
+ ret
+#elif defined(__mips__)
+ syscall 0x
+ jr $ra
+#<...more ifdef for arches...>
+#endif
+
+/* the native function name is stored 8 bytes behind \name symbol: */
+ .align 8
+ .asciz  "\name"
+
+ .globl \name
+ .type \name, %function
+ .size \name, . - \name
+.endm

with that you
- save some bytes, code & pointers
- don't need to load the pointer to the native function string (as it's
  always stored as ascii 8 bytes behind the function itself)
- don't need to adjust the IP
- simplifies the asm code and reduced the ifdefs
- ...

Helge


+
+define_function memcmp
+define_function memcpy
+define_function memset
+define_function strcat
+define_function strcmp
+define_function strcpy
+define_function strncmp
+define_function strncpy

[RFC v6 2/9] build: Implement libnative library and the build machinery for libnative

[Yeqi Fu]

This commit implements a shared library, where native functions are
rewritten as special instructions. At runtime, user programs load
the shared library, and special instructions are executed when
native functions are called.

Signed-off-by: Yeqi Fu 
---
 Makefile|  2 ++
 common-user/native/Makefile.include |  8 +
 common-user/native/Makefile.target  | 22 +
 common-user/native/libnative.S  | 51 +
 configure   | 39 ++
 5 files changed, 122 insertions(+)
 create mode 100644 common-user/native/Makefile.include
 create mode 100644 common-user/native/Makefile.target
 create mode 100644 common-user/native/libnative.S

diff --git a/Makefile b/Makefile
index 5d48dfac18..6f6147b40f 100644
--- a/Makefile
+++ b/Makefile
@@ -182,6 +182,8 @@ SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory --quiet)
 
 include $(SRC_PATH)/tests/Makefile.include
 
+include $(SRC_PATH)/common-user/native/Makefile.include
+
 all: recurse-all
 
 ROMS_RULES=$(foreach t, all clean distclean, $(addsuffix /$(t), $(ROMS)))
diff --git a/common-user/native/Makefile.include 
b/common-user/native/Makefile.include
new file mode 100644
index 00..65b10fddac
--- /dev/null
+++ b/common-user/native/Makefile.include
@@ -0,0 +1,8 @@
+.PHONY: build-native
+build-native: $(NATIVE_TARGETS:%=build-native-library-%)
+$(NATIVE_TARGETS:%=build-native-library-%): build-native-library-%:
+   $(call quiet-command, \
+   $(MAKE) -C common-user/native/$* $(SUBDIR_MAKEFLAGS), \
+   "BUILD","$* native library")
+
+all: build-native
diff --git a/common-user/native/Makefile.target 
b/common-user/native/Makefile.target
new file mode 100644
index 00..65d90102e2
--- /dev/null
+++ b/common-user/native/Makefile.target
@@ -0,0 +1,22 @@
+# -*- Mode: makefile -*-
+#
+# Library for native calls
+#
+
+all:
+-include ../../../config-host.mak
+-include config-target.mak
+
+CFLAGS+=-shared -D $(TARGET_NAME)
+LDFLAGS+=
+
+SRC = $(SRC_PATH)/common-user/native/libnative.S
+LIBNATIVE = libnative.so
+
+all: $(LIBNATIVE)
+
+$(LIBNATIVE): $(SRC)
+   $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(EXTRA_NATIVE_CALL_FLAGS) $< -o $@ 
$(LDFLAGS)
+
+clean:
+   rm -f $(LIBNATIVE)
diff --git a/common-user/native/libnative.S b/common-user/native/libnative.S
new file mode 100644
index 00..bc51dabedf
--- /dev/null
+++ b/common-user/native/libnative.S
@@ -0,0 +1,51 @@
+.macro special_instr sym
+#if defined(__i386__)
+ ud0 \sym-1f, %eax; 1:
+#elif defined(__x86_64__)
+ ud0 \sym(%rip), %eax
+#elif defined(__arm__) || defined(__aarch64__)
+ hlt 0x
+1:  .word   \sym - 1b
+#elif defined(__mips__)
+ syscall 0x
+1:  .word   \sym - 1b
+#else
+# error
+#endif
+.endm
+
+.macro ret_instr
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+ ret
+#elif defined(__arm__)
+ bx lr
+#elif defined(__mips__)
+ jr $ra
+#else
+# error
+#endif
+.endm
+
+/* Symbols of native functions */
+
+.macro define_function name
+ .text
+\name:
+ special_instr 9f
+ ret_instr
+ .globl \name
+ .type \name, %function
+ .size \name, . - \name
+
+ .section .rodata
+9:  .asciz  "\name"
+.endm
+
+define_function memcmp
+define_function memcpy
+define_function memset
+define_function strcat
+define_function strcmp
+define_function strcpy
+define_function strncmp
+define_function strncpy
diff --git a/configure b/configure
index 7a1e463d9c..de533b27a2 100755
--- a/configure
+++ b/configure
@@ -1826,6 +1826,45 @@ if test "$tcg" = "enabled"; then
 fi
 )
 
+# common-user/native configuration
+(mkdir -p common-user/native
+
+native_targets=
+for target in $target_list; do
+  case $target in
+*-softmmu)
+continue
+;;
+  esac
+
+  # native call is only supported on these architectures
+  arch=${target%%-*}
+  config_target_mak=common-user/native/${target}/config-target.mak
+  case $arch in
+i386|x86_64|arm|aarch64|mips|mips64)
+  if test -f cross-build/${target}/config-target.mak; then
+mkdir -p "common-user/native/${target}"
+ln -srf cross-build/${target}/config-target.mak "$config_target_mak"
+if test $arch = arm; then
+  echo "EXTRA_NATIVE_CALL_FLAGS=-marm" >> "$config_target_mak"
+fi
+if test $arch = $cpu || \
+  { test $arch = i386 && test $cpu = x86_64; } || \
+  { test $arch = arm && test $cpu = aarch64; } || \
+  { test $arch = mips && test $cpu = mips64; }; then
+  echo "LD_PREFIX=/" >> "$config_target_mak"
+fi
+echo "LIBNATIVE=$PWD/common-user/native/${target}/libnative.so" >> 
"$config_target_mak"
+ln -sf ${source_path}/common-user/native/Makefile.target 
common-user/native/${target}/Makefile
+native_targets="$native_targets ${target}"
+  fi
+;;
+  esac
+done
+
+echo