[dpdk-dev] [PATCH] build: add more implementers' IDs and PNs for Arm platforms

[Herbert Guan]

1) Add native PN option '-march=native' to allow automatic detection.
   Set 'arm_force_native_march' to 'true' in config/arm/meson.build
   to use native PN option.
2) Add implementer_pn option for part num selection in cross compile
3) Add known Arm cortex PN support
4) Add known implementers' IDs (use generic flags/archs by default)
5) Sync build options with config/common_armv8a_linuxapp

Signed-off-by: Herbert Guan <herbert.guan at arm.com>
---
 config/arm/arm64_armv8_linuxapp_gcc | 14 ++++++
 config/arm/meson.build              | 99 ++++++++++++++++++++++++++++---------
 2 files changed, 91 insertions(+), 22 deletions(-)

diff --git a/config/arm/arm64_armv8_linuxapp_gcc b/config/arm/arm64_armv8_linuxapp_gcc
index 3b4d3c4..987c02f 100644
--- a/config/arm/arm64_armv8_linuxapp_gcc
+++ b/config/arm/arm64_armv8_linuxapp_gcc
@@ -2,9 +2,23 @@
 c = 'aarch64-linux-gnu-gcc'
 cpp = 'aarch64-linux-gnu-cpp'
 ar = 'aarch64-linux-gnu-gcc-ar'
+strip = 'aarch64-linux-gnu-strip'
 
 [host_machine]
 system = 'linux'
 cpu_family = 'aarch64'
 cpu = 'armv8-a'
 endian = 'little'
+
+[properties]
+implementor_id = 'generic'
+
+# Valid options for Arm's implementor_pn:
+# 'default': valid for all armv8-a architectures (default value)
+# '0xd03':   cortex-a53
+# '0xd04':   cortex-a35
+# '0xd07':   cortex-a57
+# '0xd08':   cortex-a72
+# '0xd09':   cortex-a73
+# '0xd0a':   cortex-a75
+implementor_pn = 'default'
diff --git a/config/arm/meson.build b/config/arm/meson.build
index a5bfb96..4e788a4 100644
--- a/config/arm/meson.build
+++ b/config/arm/meson.build
@@ -5,15 +5,48 @@
 # for checking defines we need to use the correct compiler flags
 march_opt = '-march=@0@'.format(machine)
 
+arm_force_native_march = false
+
 machine_args_generic = [
-	['default', ['-march=armv8-a+crc+crypto']]]
+	['default', ['-march=armv8-a']],
+	['native', ['-march=native']],
+	['0xd03', ['-mcpu=cortex-a53']],
+	['0xd04', ['-mcpu=cortex-a35']],
+	['0xd07', ['-mcpu=cortex-a57']],
+	['0xd08', ['-mcpu=cortex-a72']],
+	['0xd09', ['-mcpu=cortex-a73']],
+	['0xd0a', ['-mcpu=cortex-a75']],
+]
 machine_args_cavium = [
 	['default', ['-march=armv8-a+crc+crypto','-mcpu=thunderx']],
+	['native', ['-march=native']],
 	['0xa1', ['-mcpu=thunderxt88']],
 	['0xa2', ['-mcpu=thunderxt81']],
 	['0xa3', ['-mcpu=thunderxt83']]]
 
-flags_generic = [[]]
+flags_common_default = [
+	# Accelarate rte_memcpy. Be sure to run unit test (memcpy_perf_autotest)
+	# to determine the best threshold in code. Refer to notes in source file
+	# (lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h) for more info.
+	['RTE_ARCH_ARM64_MEMCPY', false],
+	#	['RTE_ARM64_MEMCPY_ALIGNED_THRESHOLD', 2048],
+	#	['RTE_ARM64_MEMCPY_UNALIGNED_THRESHOLD', 512],
+	# Leave below RTE_ARM64_MEMCPY_xxx options commented out, unless there're
+	# strong reasons.
+	#	['RTE_ARM64_MEMCPY_SKIP_GCC_VER_CHECK', false],
+	#	['RTE_ARM64_MEMCPY_ALIGN_MASK', 0xF],
+	#	['RTE_ARM64_MEMCPY_STRICT_ALIGN', false],
+
+	['RTE_LIBRTE_FM10K_PMD', false],
+	['RTE_LIBRTE_SFC_EFX_PMD', false],
+	['RTE_LIBRTE_AVP_PMD', false],
+
+	['RTE_SCHED_VECTOR', false],
+]
+
+flags_generic = [
+	['RTE_MACHINE', '"armv8a"'],
+	['RTE_CACHE_LINE_SIZE', 128]]
 flags_cavium = [
 	['RTE_MACHINE', '"thunderx"'],
 	['RTE_CACHE_LINE_SIZE', 128],
@@ -22,8 +55,21 @@ flags_cavium = [
 	['RTE_MAX_VFIO_GROUPS', 128],
 	['RTE_RING_USE_C11_MEM_MODEL', false]]
 
+## Arm implementer ID (ARM DDI 0487C.a, Section G7.2.106, Page G7-5321)
 impl_generic = ['Generic armv8', flags_generic, machine_args_generic]
+impl_0x41 = ['Arm', flags_generic, machine_args_generic]
+impl_0x42 = ['Broadcom', flags_generic, machine_args_generic]
 impl_0x43 = ['Cavium', flags_cavium, machine_args_cavium]
+impl_0x44 = ['DEC', flags_generic, machine_args_generic]
+impl_0x49 = ['Infineon', flags_generic, machine_args_generic]
+impl_0x4d = ['Motorola', flags_generic, machine_args_generic]
+impl_0x4e = ['NVIDIA', flags_generic, machine_args_generic]
+impl_0x50 = ['AppliedMicro', flags_generic, machine_args_generic]
+impl_0x51 = ['Qualcomm', flags_generic, machine_args_generic]
+impl_0x53 = ['Samsung', flags_generic, machine_args_generic]
+impl_0x56 = ['Marvell', flags_generic, machine_args_generic]
+impl_0x69 = ['Intel', flags_generic, machine_args_generic]
+
 
 if cc.get_define('__clang__') != ''
 	dpdk_conf.set_quoted('RTE_TOOLCHAIN', 'clang')
@@ -55,19 +101,31 @@ else
 				meson.current_source_dir(), 'armv8_machine.py'))
 		cmd = run_command(detect_vendor.path())
 		if cmd.returncode() == 0
-			cmd_output = cmd.stdout().strip().split(' ')
+			cmd_output = cmd.stdout().to_lower().strip().split(' ')
 		endif
 		# Set to generic if variable is not found
 		machine = get_variable('impl_' + cmd_output[0], 'generic')
+		if machine == 'generic'
+			machine = impl_generic
+			cmd_output = cmd_generic
+		endif
+		impl_pn = cmd_output[3]
+		if arm_force_native_march == true
+			impl_pn = 'native'
+		endif
 	else
 		impl_id = meson.get_cross_property('implementor_id', 'generic')
+		impl_pn = meson.get_cross_property('implementor_pn', 'default')
 		machine = get_variable('impl_' + impl_id)
 	endif
 
-	if machine == 'generic'
-		machine = impl_generic
-		cmd_output = cmd_generic
-	endif
+	# Apply Common Defaults. These settings may be overwritten by machine
+	# settings later.
+	foreach flag: flags_common_default
+		if flag.length() > 0
+			dpdk_conf.set(flag[0], flag[1])
+		endif
+	endforeach
 
 	message('Implementer : ' + machine[0])
 	foreach flag: machine[1]
@@ -79,22 +137,19 @@ else
 	# for gcc versions > 7
 	if cc.version().version_compare(
 			'<7.0') or cmd_output.length() == 0
-		foreach marg: machine[2]
-			if marg[0] == 'default'
-				foreach f: marg[1]
-					machine_args += f
-				endforeach
-			endif
-		endforeach
-	else
-		foreach marg: machine[2]
-			if marg[0] == cmd_output[3]
-				foreach f: marg[1]
-					machine_args += f
-				endforeach
-			endif
-		endforeach
+		if not meson.is_cross_build() and arm_force_native_march == true
+			impl_pn = 'native'
+		else
+			impl_pn = 'default'
+		endif
 	endif
+	foreach marg: machine[2]
+		if marg[0] == impl_pn
+			foreach f: marg[1]
+				machine_args += f
+			endforeach
+		endif
+	endforeach
 endif
 message(machine_args)
 
-- 
1.8.3.1