[v3,1/8] eal: add initial support for RISC-V architecture
Checks
Commit Message
From: Michal Mazurek <maz@semihalf.com>
Add all necessary elements for DPDK to compile and run EAL on SiFive
Freedom U740 SoC which is based on SiFive U74-MC (ISA: rv64imafdc)
core complex.
This includes:
- EAL library implementation for rv64imafdc ISA.
- meson build structure for 'riscv' architecture. RTE_ARCH_RISCV define
is added for architecture identification.
- xmm_t structure operation stubs as there is no vector support in the
U74 core.
Compilation was tested on Ubuntu and Arch Linux using riscv64 toolchain.
Clang compilation currently not supported due to issues with missing
relocation relaxation.
Two rte_rdtsc() schemes are provided: stable low-resolution using rdtime
(default) and unstable high-resolution using rdcycle. User can override
the scheme by defining RTE_RISCV_RDTSC_USE_HPM=1 during compile time of
both DPDK and the application. The reasoning for this is as follows.
The RISC-V ISA mandates that clock read by rdtime has to be of constant
period and synchronized between all hardware threads within 1 tick
(chapter 10.1 in version 20191213 of RISC-V spec).
However this clock may not be of high-enough frequency for dataplane
uses. I.e. on HiFive Unmatched (FU740) it is 1MHz.
There is a high-resolution alternative in form of rdcycle which is
clocked at the core clock frequency. The drawbacks are that it may be
disabled during sleep (WFI) and its frequency might change due to DVFS.
The platform is currently marked as linux-only because rte_cycles
implementation uses the timebase-frequency device-tree node read through
the proc file system. Such approach was chosen because Linux kernel
depends on the presence of this device-tree node.
The i40e PMD driver is disabled on RISC-V as the rv64gc ISA has no vector
operations.
The compilation of following modules has been disabled by this commit
and will be re-enabled in later commits as fixes are introduced:
net/ixgbe, net/memif, net/tap, example/l3fwd.
Known checkpatch errors/warnings:
- ERROR:COMPLEX_MACRO in rte_atomic.h and rte_cycles.h due to inline
assembly declarations.
- vector_size compiler attribute used in rte_vect.h directly.
- rte_*mb() used directly in rte_atomic.h to reduce code duplication.
- __atomic_thread_fence() used to implement rte_atomic_thread_fence().
Sponsored-by: Frank Zhao <Frank.Zhao@starfivetech.com>
Sponsored-by: Sam Grove <sam.grove@sifive.com>
Signed-off-by: Michal Mazurek <maz@semihalf.com>
Signed-off-by: Stanislaw Kardach <kda@semihalf.com>
---
Depends-on: series-22867 ("test/ring: remove excessive inlining")
Depends-on: series-22868 ("lpm: add a scalar version of lookupx4 function")
Depends-on: series-22869 ("examples/l3fwd: fix scalar LPM compilation")
---
MAINTAINERS | 6 +
app/test/test_xmmt_ops.h | 16 ++
config/meson.build | 2 +
config/riscv/meson.build | 143 ++++++++++++++++++
config/riscv/riscv64_linux_gcc | 17 +++
config/riscv/riscv64_sifive_u740_linux_gcc | 19 +++
doc/guides/contributing/design.rst | 2 +-
.../linux_gsg/cross_build_dpdk_for_riscv.rst | 125 +++++++++++++++
doc/guides/linux_gsg/index.rst | 1 +
doc/guides/nics/features.rst | 5 +
doc/guides/nics/features/default.ini | 1 +
doc/guides/rel_notes/release_22_07.rst | 8 +
drivers/net/i40e/meson.build | 6 +
drivers/net/ixgbe/meson.build | 6 +
drivers/net/memif/meson.build | 5 +
drivers/net/tap/meson.build | 5 +
examples/l3fwd/meson.build | 6 +
lib/eal/riscv/include/meson.build | 23 +++
lib/eal/riscv/include/rte_atomic.h | 52 +++++++
lib/eal/riscv/include/rte_byteorder.h | 44 ++++++
lib/eal/riscv/include/rte_cpuflags.h | 55 +++++++
lib/eal/riscv/include/rte_cycles.h | 105 +++++++++++++
lib/eal/riscv/include/rte_io.h | 21 +++
lib/eal/riscv/include/rte_mcslock.h | 18 +++
lib/eal/riscv/include/rte_memcpy.h | 63 ++++++++
lib/eal/riscv/include/rte_pause.h | 31 ++++
lib/eal/riscv/include/rte_pflock.h | 17 +++
lib/eal/riscv/include/rte_power_intrinsics.h | 22 +++
lib/eal/riscv/include/rte_prefetch.h | 50 ++++++
lib/eal/riscv/include/rte_rwlock.h | 44 ++++++
lib/eal/riscv/include/rte_spinlock.h | 67 ++++++++
lib/eal/riscv/include/rte_ticketlock.h | 21 +++
lib/eal/riscv/include/rte_vect.h | 55 +++++++
lib/eal/riscv/meson.build | 11 ++
lib/eal/riscv/rte_cpuflags.c | 122 +++++++++++++++
lib/eal/riscv/rte_cycles.c | 77 ++++++++++
lib/eal/riscv/rte_hypervisor.c | 13 ++
lib/eal/riscv/rte_power_intrinsics.c | 56 +++++++
meson.build | 2 +
39 files changed, 1341 insertions(+), 1 deletion(-)
create mode 100644 config/riscv/meson.build
create mode 100644 config/riscv/riscv64_linux_gcc
create mode 100644 config/riscv/riscv64_sifive_u740_linux_gcc
create mode 100644 doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
create mode 100644 lib/eal/riscv/include/meson.build
create mode 100644 lib/eal/riscv/include/rte_atomic.h
create mode 100644 lib/eal/riscv/include/rte_byteorder.h
create mode 100644 lib/eal/riscv/include/rte_cpuflags.h
create mode 100644 lib/eal/riscv/include/rte_cycles.h
create mode 100644 lib/eal/riscv/include/rte_io.h
create mode 100644 lib/eal/riscv/include/rte_mcslock.h
create mode 100644 lib/eal/riscv/include/rte_memcpy.h
create mode 100644 lib/eal/riscv/include/rte_pause.h
create mode 100644 lib/eal/riscv/include/rte_pflock.h
create mode 100644 lib/eal/riscv/include/rte_power_intrinsics.h
create mode 100644 lib/eal/riscv/include/rte_prefetch.h
create mode 100644 lib/eal/riscv/include/rte_rwlock.h
create mode 100644 lib/eal/riscv/include/rte_spinlock.h
create mode 100644 lib/eal/riscv/include/rte_ticketlock.h
create mode 100644 lib/eal/riscv/include/rte_vect.h
create mode 100644 lib/eal/riscv/meson.build
create mode 100644 lib/eal/riscv/rte_cpuflags.c
create mode 100644 lib/eal/riscv/rte_cycles.c
create mode 100644 lib/eal/riscv/rte_hypervisor.c
create mode 100644 lib/eal/riscv/rte_power_intrinsics.c
Comments
On 5/10/22 17:48, Stanislaw Kardach wrote:
> From: Michal Mazurek <maz@semihalf.com>
>
> Add all necessary elements for DPDK to compile and run EAL on SiFive
> Freedom U740 SoC which is based on SiFive U74-MC (ISA: rv64imafdc)
> core complex.
>
> This includes:
>
> - EAL library implementation for rv64imafdc ISA.
> - meson build structure for 'riscv' architecture. RTE_ARCH_RISCV define
> is added for architecture identification.
> - xmm_t structure operation stubs as there is no vector support in the
> U74 core.
>
> Compilation was tested on Ubuntu and Arch Linux using riscv64 toolchain.
> Clang compilation currently not supported due to issues with missing
> relocation relaxation.
>
> Two rte_rdtsc() schemes are provided: stable low-resolution using rdtime
> (default) and unstable high-resolution using rdcycle. User can override
> the scheme by defining RTE_RISCV_RDTSC_USE_HPM=1 during compile time of
> both DPDK and the application. The reasoning for this is as follows.
> The RISC-V ISA mandates that clock read by rdtime has to be of constant
> period and synchronized between all hardware threads within 1 tick
> (chapter 10.1 in version 20191213 of RISC-V spec).
> However this clock may not be of high-enough frequency for dataplane
> uses. I.e. on HiFive Unmatched (FU740) it is 1MHz.
> There is a high-resolution alternative in form of rdcycle which is
> clocked at the core clock frequency. The drawbacks are that it may be
> disabled during sleep (WFI) and its frequency might change due to DVFS.
>
> The platform is currently marked as linux-only because rte_cycles
> implementation uses the timebase-frequency device-tree node read through
> the proc file system. Such approach was chosen because Linux kernel
> depends on the presence of this device-tree node.
>
> The i40e PMD driver is disabled on RISC-V as the rv64gc ISA has no vector
> operations.
>
> The compilation of following modules has been disabled by this commit
> and will be re-enabled in later commits as fixes are introduced:
> net/ixgbe, net/memif, net/tap, example/l3fwd.
>
> Known checkpatch errors/warnings:
>
> - ERROR:COMPLEX_MACRO in rte_atomic.h and rte_cycles.h due to inline
> assembly declarations.
> - vector_size compiler attribute used in rte_vect.h directly.
> - rte_*mb() used directly in rte_atomic.h to reduce code duplication.
> - __atomic_thread_fence() used to implement rte_atomic_thread_fence().
>
> Sponsored-by: Frank Zhao <Frank.Zhao@starfivetech.com>
> Sponsored-by: Sam Grove <sam.grove@sifive.com>
> Signed-off-by: Michal Mazurek <maz@semihalf.com>
> Signed-off-by: Stanislaw Kardach <kda@semihalf.com>
> ---
> Depends-on: series-22867 ("test/ring: remove excessive inlining")
> Depends-on: series-22868 ("lpm: add a scalar version of lookupx4 function")
> Depends-on: series-22869 ("examples/l3fwd: fix scalar LPM compilation")
> ---
> MAINTAINERS | 6 +
> app/test/test_xmmt_ops.h | 16 ++
> config/meson.build | 2 +
> config/riscv/meson.build | 143 ++++++++++++++++++
> config/riscv/riscv64_linux_gcc | 17 +++
> config/riscv/riscv64_sifive_u740_linux_gcc | 19 +++
> doc/guides/contributing/design.rst | 2 +-
> .../linux_gsg/cross_build_dpdk_for_riscv.rst | 125 +++++++++++++++
> doc/guides/linux_gsg/index.rst | 1 +
> doc/guides/nics/features.rst | 5 +
> doc/guides/nics/features/default.ini | 1 +
> doc/guides/rel_notes/release_22_07.rst | 8 +
> drivers/net/i40e/meson.build | 6 +
> drivers/net/ixgbe/meson.build | 6 +
> drivers/net/memif/meson.build | 5 +
> drivers/net/tap/meson.build | 5 +
> examples/l3fwd/meson.build | 6 +
> lib/eal/riscv/include/meson.build | 23 +++
> lib/eal/riscv/include/rte_atomic.h | 52 +++++++
> lib/eal/riscv/include/rte_byteorder.h | 44 ++++++
> lib/eal/riscv/include/rte_cpuflags.h | 55 +++++++
> lib/eal/riscv/include/rte_cycles.h | 105 +++++++++++++
> lib/eal/riscv/include/rte_io.h | 21 +++
> lib/eal/riscv/include/rte_mcslock.h | 18 +++
> lib/eal/riscv/include/rte_memcpy.h | 63 ++++++++
> lib/eal/riscv/include/rte_pause.h | 31 ++++
> lib/eal/riscv/include/rte_pflock.h | 17 +++
> lib/eal/riscv/include/rte_power_intrinsics.h | 22 +++
> lib/eal/riscv/include/rte_prefetch.h | 50 ++++++
> lib/eal/riscv/include/rte_rwlock.h | 44 ++++++
> lib/eal/riscv/include/rte_spinlock.h | 67 ++++++++
> lib/eal/riscv/include/rte_ticketlock.h | 21 +++
> lib/eal/riscv/include/rte_vect.h | 55 +++++++
> lib/eal/riscv/meson.build | 11 ++
> lib/eal/riscv/rte_cpuflags.c | 122 +++++++++++++++
> lib/eal/riscv/rte_cycles.c | 77 ++++++++++
> lib/eal/riscv/rte_hypervisor.c | 13 ++
> lib/eal/riscv/rte_power_intrinsics.c | 56 +++++++
> meson.build | 2 +
> 39 files changed, 1341 insertions(+), 1 deletion(-)
> create mode 100644 config/riscv/meson.build
> create mode 100644 config/riscv/riscv64_linux_gcc
> create mode 100644 config/riscv/riscv64_sifive_u740_linux_gcc
> create mode 100644 doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
> create mode 100644 lib/eal/riscv/include/meson.build
> create mode 100644 lib/eal/riscv/include/rte_atomic.h
> create mode 100644 lib/eal/riscv/include/rte_byteorder.h
> create mode 100644 lib/eal/riscv/include/rte_cpuflags.h
> create mode 100644 lib/eal/riscv/include/rte_cycles.h
> create mode 100644 lib/eal/riscv/include/rte_io.h
> create mode 100644 lib/eal/riscv/include/rte_mcslock.h
> create mode 100644 lib/eal/riscv/include/rte_memcpy.h
> create mode 100644 lib/eal/riscv/include/rte_pause.h
> create mode 100644 lib/eal/riscv/include/rte_pflock.h
> create mode 100644 lib/eal/riscv/include/rte_power_intrinsics.h
> create mode 100644 lib/eal/riscv/include/rte_prefetch.h
> create mode 100644 lib/eal/riscv/include/rte_rwlock.h
> create mode 100644 lib/eal/riscv/include/rte_spinlock.h
> create mode 100644 lib/eal/riscv/include/rte_ticketlock.h
> create mode 100644 lib/eal/riscv/include/rte_vect.h
> create mode 100644 lib/eal/riscv/meson.build
> create mode 100644 lib/eal/riscv/rte_cpuflags.c
> create mode 100644 lib/eal/riscv/rte_cycles.c
> create mode 100644 lib/eal/riscv/rte_hypervisor.c
> create mode 100644 lib/eal/riscv/rte_power_intrinsics.c
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 8f4e9c3479..7fb6dccc41 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -296,6 +296,12 @@ F: drivers/*/*/*_altivec.*
> F: app/*/*_altivec.*
> F: examples/*/*_altivec.*
>
> +RISC-V
> +M: Stanislaw Kardach <kda@semihalf.com>
> +F: config/riscv/
> +F: doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
> +F: lib/eal/riscv/
> +
> Intel x86
> M: Bruce Richardson <bruce.richardson@intel.com>
> M: Konstantin Ananyev <konstantin.v.ananyev@yandex.ru>
> diff --git a/app/test/test_xmmt_ops.h b/app/test/test_xmmt_ops.h
> index 3a82d5ecac..55f256599e 100644
> --- a/app/test/test_xmmt_ops.h
> +++ b/app/test/test_xmmt_ops.h
> @@ -1,5 +1,8 @@
> /* SPDX-License-Identifier: BSD-3-Clause
> * Copyright(c) 2015 Cavium, Inc
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> */
>
> #ifndef _TEST_XMMT_OPS_H_
> @@ -49,6 +52,19 @@ vect_set_epi32(int i3, int i2, int i1, int i0)
> return data;
> }
>
> +#elif defined(RTE_ARCH_RISCV)
> +
> +#define vect_loadu_sil128(p) vect_load_128(p)
> +
> +/* sets the 4 signed 32-bit integer values and returns the xmm_t variable */
> +static __rte_always_inline xmm_t
> +vect_set_epi32(int i3, int i2, int i1, int i0)
> +{
> + xmm_t data = (xmm_t){i0, i1, i2, i3};
> +
> + return data;
> +}
> +
> #endif
>
> #endif /* _TEST_XMMT_OPS_H_ */
> diff --git a/config/meson.build b/config/meson.build
> index 7134e80e8d..7f7b6c92fd 100644
> --- a/config/meson.build
> +++ b/config/meson.build
> @@ -121,6 +121,8 @@ if cpu_instruction_set == 'generic'
> cpu_instruction_set = 'generic'
> elif host_machine.cpu_family().startswith('ppc')
> cpu_instruction_set = 'power8'
> + elif host_machine.cpu_family().startswith('riscv')
> + cpu_instruction_set = 'riscv'
> endif
> endif
>
> diff --git a/config/riscv/meson.build b/config/riscv/meson.build
> new file mode 100644
> index 0000000000..0c16c31fc2
> --- /dev/null
> +++ b/config/riscv/meson.build
> @@ -0,0 +1,143 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2017 Intel Corporation.
> +# Copyright(c) 2017 Cavium, Inc
> +# Copyright(c) 2021 PANTHEON.tech s.r.o.
> +# Copyright(c) 2022 StarFive
> +# Copyright(c) 2022 SiFive
> +# Copyright(c) 2022 Semihalf
> +
> +if not is_linux
> + error('Only Linux is supported at this point in time.')
> +endif
> +
> +if not dpdk_conf.get('RTE_ARCH_64')
> + error('Only 64-bit compiles are supported for this platform type')
> +endif
> +
> +dpdk_conf.set('RTE_ARCH', 'riscv')
> +dpdk_conf.set('RTE_ARCH_RISCV', 1)
> +dpdk_conf.set('RTE_FORCE_INTRINSICS', 1)
> +
> +# common flags to all riscv builds, with lowest priority
> +flags_common = [
> + ['RTE_ARCH_RISCV', true],
> + ['RTE_CACHE_LINE_SIZE', 64],
> + # Set this to true if target emulates U-mode TIME CSR via M or S mode trap.
> + # This allows to remove a FENCE on rte_rdtsc_precise() as trap effectively
> + # acts as one.
> + ['RTE_RISCV_EMU_UTIME', false],
> + # Set this to true if target emulates U-mode CYCLE CSR via M or S mode trap.
> + # This allows to remove a FENCE on rte_rdtsc_precise() as trap effectively
> + # acts as one.
> + ['RTE_RISCV_EMU_UCYCLE', false],
> + # Manually set wall time clock frequency for the target. If 0, then it is
> + # read from /proc/device-tree/cpus/timebase-frequency. This property is
> + # guaranteed on Linux, as riscv time_init() requires it.
> + ['RTE_RISCV_TIME_FREQ', 0],
> +]
> +
> +## SoC-specific options.
> +# The priority is like this: arch > vendor > common.
> +#
> +# Note that currently there's no way of getting vendor/microarchitecture id
> +# values in userspace which is why the logic of choosing the right flag
> +# combination is strictly based on the values passed from a cross-file.
> +vendor_generic = {
> + 'description': 'Generic RISC-V',
> + 'flags': [
> + ['RTE_MACHINE', '"riscv"'],
> + ['RTE_USE_C11_MEM_MODEL', true],
> + ['RTE_MAX_LCORE', 128],
> + ['RTE_MAX_NUMA_NODES', 2]
> + ],
> + 'arch_config': {
> + 'generic': {'machine_args': ['-march=rv64gc']}
> + }
> +}
> +
> +arch_config_riscv = {
> + '0x8000000000000007': {
> + 'machine_args': ['-march=rv64gc', '-mtune=sifive-7-series'],
> + 'flags': [
> + ['RTE_RISCV_EMU_UTIME', true],
> + ['RTE_RISCV_EMU_UCYCLE', true]
> + ]
> + },
> +}
> +
> +vendor_sifive = {
> + 'description': 'SiFive',
> + 'flags': [
> + ['RTE_MACHINE', '"riscv"'],
> + ['RTE_USE_C11_MEM_MODEL', true],
> + ['RTE_MAX_LCORE', 4],
> + ['RTE_MAX_NUMA_NODES', 1],
> + ],
> + 'arch_config': arch_config_riscv
> +}
> +
> +vendors = {
> + 'generic': vendor_generic,
> + '0x489': vendor_sifive
> +}
> +
> +# Native/cross vendor/arch detection
> +if not meson.is_cross_build()
> + if machine == 'default'
> + # default build
> + vendor_id = 'generic'
> + arch_id = 'generic'
> + message('generic RISC-V')
> + else
> + vendor_id = 'generic'
> + arch_id = 'generic'
> + warning('RISC-V arch discovery not available, using generic!')
> + endif
> +else
> + # cross build
> + vendor_id = meson.get_cross_property('vendor_id')
> + arch_id = meson.get_cross_property('arch_id')
> +endif
> +
> +if vendors.has_key(vendor_id)
> + vendor_config = vendors[vendor_id]
> +else
> + error('Unsupported RISC-V vendor: @0@. '.format(vendor_id) +
> + 'Please add support for it or use the generic ' +
> + '(-Dmachine=generic) build.')
> +endif
> +
> +message('RISC-V vendor: ' + vendor_config['description'])
> +message('RISC-V architecture id: ' + arch_id)
> +
> +arch_config = vendor_config['arch_config']
> +if arch_config.has_key(arch_id)
> + # use the specified arch_id machine args if found
> + arch_config = arch_config[arch_id]
> +else
> + # unknown micro-architecture id
> + error('Unsupported architecture @0@ of vendor @1@. '
> + .format(arch_id, vendor_id) +
> + 'Please add support for it or use the generic ' +
> + '(-Dmachine=generic) build.')
> +endif
> +
> +# Concatenate flags respecting priorities.
> +dpdk_flags = flags_common + vendor_config['flags'] + arch_config.get('flags', [])
> +
> +# apply supported machine args
> +machine_args = [] # Clear previous machine args
> +foreach flag: arch_config['machine_args']
> + if cc.has_argument(flag)
> + machine_args += flag
> + endif
> +endforeach
> +
> +# apply flags
> +foreach flag: dpdk_flags
> + if flag.length() > 0
> + dpdk_conf.set(flag[0], flag[1])
> + endif
> +endforeach
> +message('Using machine args: @0@'.format(machine_args))
> +
> diff --git a/config/riscv/riscv64_linux_gcc b/config/riscv/riscv64_linux_gcc
> new file mode 100644
> index 0000000000..04248d7ecb
> --- /dev/null
> +++ b/config/riscv/riscv64_linux_gcc
> @@ -0,0 +1,17 @@
> +[binaries]
> +c = 'riscv64-linux-gnu-gcc'
> +cpp = 'riscv64-linux-gnu-g++'
> +ar = 'riscv64-linux-gnu-ar'
> +strip = 'riscv64-linux-gnu-strip'
> +pcap-config = ''
> +pkgconfig = 'riscv64-linux-gnu-pkg-config'
> +
> +[host_machine]
> +system = 'linux'
> +cpu_family = 'riscv64'
> +cpu = 'rv64gc'
> +endian = 'little'
> +
> +[properties]
> +vendor_id = 'generic'
> +arch_id = 'generic'
> diff --git a/config/riscv/riscv64_sifive_u740_linux_gcc b/config/riscv/riscv64_sifive_u740_linux_gcc
> new file mode 100644
> index 0000000000..7b5ad2562d
> --- /dev/null
> +++ b/config/riscv/riscv64_sifive_u740_linux_gcc
> @@ -0,0 +1,19 @@
> +[binaries]
> +c = 'riscv64-unknown-linux-gnu-gcc'
> +cpp = 'riscv64-unknown-linux-gnu-g++'
> +ar = 'riscv64-unknown-linux-gnu-ar'
> +strip = 'riscv64-unknown-linux-gnu-strip'
> +pcap-config = ''
> +pkgconfig = 'riscv64-unknown-linux-gnu-pkg-config'
> +
> +[host_machine]
> +system = 'linux'
> +cpu_family = 'riscv64'
> +cpu = 'rv64gc'
> +endian = 'little'
> +
> +[properties]
> +vendor_id = '0x489'
> +arch_id = '0x8000000000000007'
> +max_lcores = 4
> +max_numa_nodes = 1
> diff --git a/doc/guides/contributing/design.rst b/doc/guides/contributing/design.rst
> index d5ca8b4d9c..0383afe5c8 100644
> --- a/doc/guides/contributing/design.rst
> +++ b/doc/guides/contributing/design.rst
> @@ -42,7 +42,7 @@ Per Architecture Sources
> The following macro options can be used:
>
> * ``RTE_ARCH`` is a string that contains the name of the architecture.
> -* ``RTE_ARCH_I686``, ``RTE_ARCH_X86_64``, ``RTE_ARCH_X86_X32``, ``RTE_ARCH_PPC_64``, ``RTE_ARCH_ARM``, ``RTE_ARCH_ARMv7`` or ``RTE_ARCH_ARM64`` are defined only if we are building for those architectures.
> +* ``RTE_ARCH_I686``, ``RTE_ARCH_X86_64``, ``RTE_ARCH_X86_X32``, ``RTE_ARCH_PPC_64``, ``RTE_ARCH_RISCV``, ``RTE_ARCH_ARM``, ``RTE_ARCH_ARMv7`` or ``RTE_ARCH_ARM64`` are defined only if we are building for those architectures.
>
> Per Execution Environment Sources
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> diff --git a/doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst b/doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
> new file mode 100644
> index 0000000000..9907b35a1d
> --- /dev/null
> +++ b/doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
> @@ -0,0 +1,125 @@
> +.. SPDX-License-Identifier: BSD-3-Clause
> + Copyright(c) 2020 ARM Corporation.
> + Copyright(c) 2022 StarFive
> + Copyright(c) 2022 SiFive
> + Copyright(c) 2022 Semihalf
> +
> +Cross compiling DPDK for RISC-V
> +===============================
> +
> +This chapter describes how to cross compile DPDK for RISC-V from x86 build
> +hosts.
> +
> +.. note::
> +
> + While it's possible to compile DPDK natively on a RISC-V host, it is
> + currently recommended to cross-compile as Linux kernel does not offer any
> + way for userspace to discover the vendor and architecture identifiers of the
> + CPU and therefore any per-chip optimization options have to be chosen via
> + a cross-file or ``c_args``.
> +
> +
> +Prerequisites
> +-------------
> +
> +
> +Linux kernel
> +~~~~~~~~~~~~
> +
> +It is recommended to use Linux kernel built from
> +`SiFive Freedom Unleashed SDK <https://github.com/sifive/freedom-u-sdk>`_.
How would the Unleashed SDK help on a later board or a board from a
different vendor?
Why wouldn't an upstream kernel work?
I suggest to eliminate this misleading section.
> +
> +
> +Meson prerequisites
> +~~~~~~~~~~~~~~~~~~~
> +
> +Meson depends on pkgconfig to find the dependencies.
> +The package ``pkg-config-riscv64-linux-gnu`` is required for RISC-V.
> +To install it in Ubuntu::
> +
> + sudo apt install pkg-config-riscv64-linux-gnu
This package does not exist in the current Ubuntu LTS (22.04, Jammy).
Setting environment variables PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH,
PKG_CONFIG_SYSROOT_DIR properly should do the job with the normal
pkg-config.
> +
> +
> +GNU toolchain
> +-------------
> +
> +
> +Obtain the cross toolchain
> +~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +The build process was tested using:
> +
> +* Ubuntu toolchain (the ``crossbuild-essential-riscv64`` package).
> +
> +* Latest `RISC-V GNU toolchain
> + <https://github.com/riscv/riscv-gnu-toolchain/releases>`_ on Ubuntu or Arch
> + Linux.
> +
> +Alternatively the toolchain may be built straight from the source, to do that
> +follow the instructions on the riscv-gnu-toolchain github page.
> +
> +
> +Unzip and add into the PATH
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +This step is only required for the riscv-gnu-toolchain. The Ubuntu toolchain is
> +in the PATH already.
> +
> +.. code-block:: console
> +
> + tar -xvf riscv64-glibc-ubuntu-20.04-<version>.tar.gz
You can install the glibc package with apt-get after adding the
architecture with sudo dpkg --add-architecture riscv64. See
https://wiki.debian.org/CrossCompiling.
> + export PATH=$PATH:<cross_install_dir>/riscv/bin
> +
> +
> +Cross Compiling DPDK with GNU toolchain using Meson
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +To cross-compile DPDK for a desired target machine use the following command::
> +
> + meson cross-build --cross-file <target_machine_configuration>
> + ninja -C cross-build
> +
> +For example if the target machine is a generic rv64gc RISC-V, use the following
> +command::
> +
> + meson riscv64-build-gcc --cross-file config/riscv/riscv64_linux_gcc
> + ninja -C riscv64-build-gcc
> +
> +If riscv-gnu-toolchain is used, binary names should be updated to match. Update the following lines in the cross-file:
> +
> +.. code-block:: console
> +
> + [binaries]
> + c = 'riscv64-unknown-linux-gnu-gcc'
> + cpp = 'riscv64-unknown-linux-gnu-g++'
> + ar = 'riscv64-unknown-linux-gnu-ar'
> + strip = 'riscv64-unknown-linux-gnu-strip'
> + ...
> +
> +Some toolchains (such as freedom-u-sdk one) require also setting ``--sysroot``,
> +otherwise include paths might not be resolved. To do so, add the appropriate
> +paths to the cross-file:
> +
> +.. code-block:: console
> +
> + [properties]
> + ...
> + c_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> + cpp_args = c_args
> + c_link_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> + cpp_link_args = c_link_args
> + ...
> +
> +
> +Supported cross-compilation targets
> +-----------------------------------
> +
> +Currently the following targets are supported:
> +
> +* Generic rv64gc ISA: ``config/riscv/riscv64_linux_gcc``
> +
> +* SiFive U740 SoC: ``config/riscv/riscv64_sifive_u740_linux_gcc``
Why do we need a special config for the Unmatched board that is not sold
anymore? Doesn't the Unmatched board work with the genenric config?
I assume a single configuriation file for the generic target is enough.
Best regards
Heinrich
> +
> +To add a new target support, ``config/riscv/meson.build`` has to be modified by
> +adding a new vendor/architecture id and a corresponding cross-file has to be
> +added to ``config/riscv`` directory.
> diff --git a/doc/guides/linux_gsg/index.rst b/doc/guides/linux_gsg/index.rst
> index 16a9a67260..747552c385 100644
> --- a/doc/guides/linux_gsg/index.rst
> +++ b/doc/guides/linux_gsg/index.rst
> @@ -14,6 +14,7 @@ Getting Started Guide for Linux
> sys_reqs
> build_dpdk
> cross_build_dpdk_for_arm64
> + cross_build_dpdk_for_riscv
> linux_drivers
> build_sample_apps
> linux_eal_parameters
> diff --git a/doc/guides/nics/features.rst b/doc/guides/nics/features.rst
> index 21bedb743f..6c4fa74bc7 100644
> --- a/doc/guides/nics/features.rst
> +++ b/doc/guides/nics/features.rst
> @@ -855,6 +855,11 @@ x86-64
>
> Support 64bits x86 architecture.
>
> +rv64
> +----
> +
> +Support 64-bit RISC-V architecture.
> +
>
> .. _nic_features_usage_doc:
>
> diff --git a/doc/guides/nics/features/default.ini b/doc/guides/nics/features/default.ini
> index b1d18ac62c..02198682c6 100644
> --- a/doc/guides/nics/features/default.ini
> +++ b/doc/guides/nics/features/default.ini
> @@ -74,6 +74,7 @@ ARMv8 =
> Power8 =
> x86-32 =
> x86-64 =
> +rv64 =
> Usage doc =
> Design doc =
> Perf doc =
> diff --git a/doc/guides/rel_notes/release_22_07.rst b/doc/guides/rel_notes/release_22_07.rst
> index 4ae91dd94d..e014247bc0 100644
> --- a/doc/guides/rel_notes/release_22_07.rst
> +++ b/doc/guides/rel_notes/release_22_07.rst
> @@ -55,6 +55,14 @@ New Features
> Also, make sure to start the actual text at the margin.
> =======================================================
>
> +* **Added initial RISC-V architecture support.***
> +
> + Added EAL implementation for RISC-V architecture. The initial device the
> + porting was tested on is a HiFive Unmatched development board based on the
> + SiFive Freedom U740 SoC. In theory this implementation should work with any
> + ``rv64gc`` ISA compatible implementation with MMU supporting a reasonable
> + address space size (U740 uses sv39 MMU).
> +
> * **Updated Intel iavf driver.**
>
> * Added Tx QoS queue rate limitation support.
> diff --git a/drivers/net/i40e/meson.build b/drivers/net/i40e/meson.build
> index efc5f93e35..a4c1c9079a 100644
> --- a/drivers/net/i40e/meson.build
> +++ b/drivers/net/i40e/meson.build
> @@ -1,6 +1,12 @@
> # SPDX-License-Identifier: BSD-3-Clause
> # Copyright(c) 2017 Intel Corporation
>
> +if arch_subdir == 'riscv'
> + build = false
> + reason = 'riscv arch not supported'
> + subdir_done()
> +endif
> +
> cflags += ['-DPF_DRIVER',
> '-DVF_DRIVER',
> '-DINTEGRATED_VF',
> diff --git a/drivers/net/ixgbe/meson.build b/drivers/net/ixgbe/meson.build
> index 162f8d5f46..88539e97d5 100644
> --- a/drivers/net/ixgbe/meson.build
> +++ b/drivers/net/ixgbe/meson.build
> @@ -1,6 +1,12 @@
> # SPDX-License-Identifier: BSD-3-Clause
> # Copyright(c) 2017 Intel Corporation
>
> +if arch_subdir == 'riscv'
> + build = false
> + reason = 'riscv arch not supported'
> + subdir_done()
> +endif
> +
> cflags += ['-DRTE_LIBRTE_IXGBE_BYPASS']
>
> subdir('base')
> diff --git a/drivers/net/memif/meson.build b/drivers/net/memif/meson.build
> index 680bc8631c..9afb495953 100644
> --- a/drivers/net/memif/meson.build
> +++ b/drivers/net/memif/meson.build
> @@ -5,6 +5,11 @@ if not is_linux
> build = false
> reason = 'only supported on Linux'
> endif
> +if arch_subdir == 'riscv'
> + build = false
> + reason = 'riscv arch not supported'
> + subdir_done()
> +endif
>
> sources = files(
> 'memif_socket.c',
> diff --git a/drivers/net/tap/meson.build b/drivers/net/tap/meson.build
> index c09713a67b..3efac9ac07 100644
> --- a/drivers/net/tap/meson.build
> +++ b/drivers/net/tap/meson.build
> @@ -5,6 +5,11 @@ if not is_linux
> build = false
> reason = 'only supported on Linux'
> endif
> +if arch_subdir == 'riscv'
> + build = false
> + reason = 'riscv arch not supported'
> + subdir_done()
> +endif
> sources = files(
> 'rte_eth_tap.c',
> 'tap_bpf_api.c',
> diff --git a/examples/l3fwd/meson.build b/examples/l3fwd/meson.build
> index 0830b3eb31..75fa19b7fe 100644
> --- a/examples/l3fwd/meson.build
> +++ b/examples/l3fwd/meson.build
> @@ -6,6 +6,12 @@
> # To build this example as a standalone application with an already-installed
> # DPDK instance, use 'make'
>
> +if dpdk_conf.has('RTE_ARCH_RISCV')
> + build = false
> + reason = 'riscv arch not supported'
> + subdir_done()
> +endif
> +
> allow_experimental_apis = true
> deps += ['hash', 'lpm', 'fib', 'eventdev']
> sources = files(
> diff --git a/lib/eal/riscv/include/meson.build b/lib/eal/riscv/include/meson.build
> new file mode 100644
> index 0000000000..7f6e4a5b1e
> --- /dev/null
> +++ b/lib/eal/riscv/include/meson.build
> @@ -0,0 +1,23 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2022 StarFive
> +# Copyright(c) 2022 SiFive
> +# Copyright(c) 2022 Semihalf
> +
> +arch_headers = files(
> + 'rte_atomic.h',
> + 'rte_byteorder.h',
> + 'rte_cpuflags.h',
> + 'rte_cycles.h',
> + 'rte_io.h',
> + 'rte_mcslock.h',
> + 'rte_memcpy.h',
> + 'rte_pause.h',
> + 'rte_pflock.h',
> + 'rte_power_intrinsics.h',
> + 'rte_prefetch.h',
> + 'rte_rwlock.h',
> + 'rte_spinlock.h',
> + 'rte_ticketlock.h',
> + 'rte_vect.h',
> +)
> +install_headers(arch_headers, subdir: get_option('include_subdir_arch'))
> diff --git a/lib/eal/riscv/include/rte_atomic.h b/lib/eal/riscv/include/rte_atomic.h
> new file mode 100644
> index 0000000000..4b4633c914
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_atomic.h
> @@ -0,0 +1,52 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + * All rights reserved.
> + */
> +
> +#ifndef RTE_ATOMIC_RISCV_H
> +#define RTE_ATOMIC_RISCV_H
> +
> +#ifndef RTE_FORCE_INTRINSICS
> +# error Platform must be built with RTE_FORCE_INTRINSICS
> +#endif
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include <stdint.h>
> +#include <rte_common.h>
> +#include <rte_config.h>
> +#include "generic/rte_atomic.h"
> +
> +#define rte_mb() asm volatile("fence rw, rw" : : : "memory")
> +
> +#define rte_wmb() asm volatile("fence w, w" : : : "memory")
> +
> +#define rte_rmb() asm volatile("fence r, r" : : : "memory")
> +
> +#define rte_smp_mb() rte_mb()
> +
> +#define rte_smp_wmb() rte_wmb()
> +
> +#define rte_smp_rmb() rte_rmb()
> +
> +#define rte_io_mb() asm volatile("fence iorw, iorw" : : : "memory")
> +
> +#define rte_io_wmb() asm volatile("fence orw, ow" : : : "memory")
> +
> +#define rte_io_rmb() asm volatile("fence ir, ir" : : : "memory")
> +
> +static __rte_always_inline void
> +rte_atomic_thread_fence(int memorder)
> +{
> + __atomic_thread_fence(memorder);
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_ATOMIC_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_byteorder.h b/lib/eal/riscv/include/rte_byteorder.h
> new file mode 100644
> index 0000000000..21893505d6
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_byteorder.h
> @@ -0,0 +1,44 @@
> +/*
> + * SPDX-License-Identifier: BSD-3-Clause
> + * Inspired from FreeBSD src/sys/powerpc/include/endian.h
> + * Copyright(c) 1987, 1991, 1993
> + * The Regents of the University of California. All rights reserved.
> + */
> +
> +#ifndef RTE_BYTEORDER_RISCV_H
> +#define RTE_BYTEORDER_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include <stdint.h>
> +#include <rte_common.h>
> +#include "generic/rte_byteorder.h"
> +
> +#ifndef RTE_BYTE_ORDER
> +#define RTE_BYTE_ORDER RTE_LITTLE_ENDIAN
> +#endif
> +
> +#define rte_cpu_to_le_16(x) (x)
> +#define rte_cpu_to_le_32(x) (x)
> +#define rte_cpu_to_le_64(x) (x)
> +
> +#define rte_cpu_to_be_16(x) rte_bswap16(x)
> +#define rte_cpu_to_be_32(x) rte_bswap32(x)
> +#define rte_cpu_to_be_64(x) rte_bswap64(x)
> +
> +#define rte_le_to_cpu_16(x) (x)
> +#define rte_le_to_cpu_32(x) (x)
> +#define rte_le_to_cpu_64(x) (x)
> +
> +#define rte_be_to_cpu_16(x) rte_bswap16(x)
> +#define rte_be_to_cpu_32(x) rte_bswap32(x)
> +#define rte_be_to_cpu_64(x) rte_bswap64(x)
> +
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_BYTEORDER_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_cpuflags.h b/lib/eal/riscv/include/rte_cpuflags.h
> new file mode 100644
> index 0000000000..66e787f898
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_cpuflags.h
> @@ -0,0 +1,55 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2014 IBM Corporation
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_CPUFLAGS_RISCV_H
> +#define RTE_CPUFLAGS_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +/**
> + * Enumeration of all CPU features supported
> + */
> +enum rte_cpu_flag_t {
> + RTE_CPUFLAG_RISCV_ISA_A, /* Atomic */
> + RTE_CPUFLAG_RISCV_ISA_B, /* Bit-Manipulation */
> + RTE_CPUFLAG_RISCV_ISA_C, /* Compressed instruction */
> + RTE_CPUFLAG_RISCV_ISA_D, /* Double precision floating-point */
> + RTE_CPUFLAG_RISCV_ISA_E, /* RV32E ISA */
> + RTE_CPUFLAG_RISCV_ISA_F, /* Single precision floating-point */
> + RTE_CPUFLAG_RISCV_ISA_G, /* Extension pack (IMAFD, Zicsr, Zifencei) */
> + RTE_CPUFLAG_RISCV_ISA_H, /* Hypervisor */
> + RTE_CPUFLAG_RISCV_ISA_I, /* RV32I/RV64I/IRV128I base ISA */
> + RTE_CPUFLAG_RISCV_ISA_J, /* Dynamic Translation Language */
> + RTE_CPUFLAG_RISCV_ISA_K, /* Reserved */
> + RTE_CPUFLAG_RISCV_ISA_L, /* Decimal Floating-Point */
> + RTE_CPUFLAG_RISCV_ISA_M, /* Integer Multiply/Divide */
> + RTE_CPUFLAG_RISCV_ISA_N, /* User-level interrupts */
> + RTE_CPUFLAG_RISCV_ISA_O, /* Reserved */
> + RTE_CPUFLAG_RISCV_ISA_P, /* Packed-SIMD */
> + RTE_CPUFLAG_RISCV_ISA_Q, /* Quad-precision floating-points */
> + RTE_CPUFLAG_RISCV_ISA_R, /* Reserved */
> + RTE_CPUFLAG_RISCV_ISA_S, /* Supervisor mode */
> + RTE_CPUFLAG_RISCV_ISA_T, /* Transactional memory */
> + RTE_CPUFLAG_RISCV_ISA_U, /* User mode */
> + RTE_CPUFLAG_RISCV_ISA_V, /* Vector */
> + RTE_CPUFLAG_RISCV_ISA_W, /* Reserved */
> + RTE_CPUFLAG_RISCV_ISA_X, /* Non-standard extension present */
> + RTE_CPUFLAG_RISCV_ISA_Y, /* Reserved */
> + RTE_CPUFLAG_RISCV_ISA_Z, /* Reserved */
> + /* The last item */
> + RTE_CPUFLAG_NUMFLAGS,/**< This should always be the last! */
> +};
> +
> +#include "generic/rte_cpuflags.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_CPUFLAGS_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_cycles.h b/lib/eal/riscv/include/rte_cycles.h
> new file mode 100644
> index 0000000000..8353cea853
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_cycles.h
> @@ -0,0 +1,105 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2015 Cavium, Inc
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_CYCLES_RISCV_H
> +#define RTE_CYCLES_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_cycles.h"
> +
> +#ifndef RTE_RISCV_RDTSC_USE_HPM
> +#define RTE_RISCV_RDTSC_USE_HPM 0
> +#endif
> +
> +#define RV64_CSRR(reg, value) \
> + asm volatile("csrr %0, " #reg : "=r" (value) : : "memory")
> +
> +/** Read wall time counter */
> +static __rte_always_inline uint64_t
> +__rte_riscv_rdtime(void)
> +{
> + uint64_t tsc;
> + RV64_CSRR(time, tsc);
> + return tsc;
> +}
> +
> +/** Read wall time counter ensuring no re-ordering */
> +static __rte_always_inline uint64_t
> +__rte_riscv_rdtime_precise(void)
> +{
> +#if !defined(RTE_RISCV_EMU_UTIME)
> + asm volatile("fence" : : : "memory");
> +#endif
> + return __rte_riscv_rdtime();
> +}
> +
> +/** Read hart cycle counter */
> +static __rte_always_inline uint64_t
> +__rte_riscv_rdcycle(void)
> +{
> + uint64_t tsc;
> + RV64_CSRR(cycle, tsc);
> + return tsc;
> +}
> +
> +/** Read hart cycle counter ensuring no re-ordering */
> +static __rte_always_inline uint64_t
> +__rte_riscv_rdcycle_precise(void)
> +{
> +#if !defined(RTE_RISCV_EMU_UCYCLE)
> + asm volatile("fence" : : : "memory");
> +#endif
> + return __rte_riscv_rdcycle();
> +}
> +
> +/**
> + * Read the time base register.
> + *
> + * @return
> + * The time base for this lcore.
> + */
> +static __rte_always_inline uint64_t
> +rte_rdtsc(void)
> +{
> + /**
> + * By default TIME userspace counter is used. Although it's frequency
> + * may not be enough for all applications.
> + */
> + if (!RTE_RISCV_RDTSC_USE_HPM)
> + return __rte_riscv_rdtime();
> + /**
> + * Alternatively HPM's CYCLE counter may be used. However this counter
> + * is not guaranteed by ISA to either be stable frequency or always
> + * enabled for userspace access (it may trap to kernel or firmware).
> + */
> + return __rte_riscv_rdcycle();
> +}
> +
> +static inline uint64_t
> +rte_rdtsc_precise(void)
> +{
> + if (!RTE_RISCV_RDTSC_USE_HPM)
> + return __rte_riscv_rdtime_precise();
> + return __rte_riscv_rdcycle_precise();
> +}
> +
> +static __rte_always_inline uint64_t
> +rte_get_tsc_cycles(void)
> +{
> + return rte_rdtsc();
> +}
> +
> +#undef RV64_CSRR
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_CYCLES_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_io.h b/lib/eal/riscv/include/rte_io.h
> new file mode 100644
> index 0000000000..29659c9590
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_io.h
> @@ -0,0 +1,21 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2016 Cavium, Inc
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_IO_RISCV_H
> +#define RTE_IO_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_io.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_IO_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_mcslock.h b/lib/eal/riscv/include/rte_mcslock.h
> new file mode 100644
> index 0000000000..b517cd5fc5
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_mcslock.h
> @@ -0,0 +1,18 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2019 Arm Limited
> + */
> +
> +#ifndef RTE_MCSLOCK_RISCV_H
> +#define RTE_MCSLOCK_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_mcslock.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_MCSLOCK_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_memcpy.h b/lib/eal/riscv/include/rte_memcpy.h
> new file mode 100644
> index 0000000000..e34f19396e
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_memcpy.h
> @@ -0,0 +1,63 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_MEMCPY_RISCV_H
> +#define RTE_MEMCPY_RISCV_H
> +
> +#include <stdint.h>
> +#include <string.h>
> +
> +#include "rte_common.h"
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_memcpy.h"
> +
> +static inline void
> +rte_mov16(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 16);
> +}
> +
> +static inline void
> +rte_mov32(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 32);
> +}
> +
> +static inline void
> +rte_mov48(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 48);
> +}
> +
> +static inline void
> +rte_mov64(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 64);
> +}
> +
> +static inline void
> +rte_mov128(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 128);
> +}
> +
> +static inline void
> +rte_mov256(uint8_t *dst, const uint8_t *src)
> +{
> + memcpy(dst, src, 256);
> +}
> +
> +#define rte_memcpy(d, s, n) memcpy((d), (s), (n))
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_MEMCPY_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_pause.h b/lib/eal/riscv/include/rte_pause.h
> new file mode 100644
> index 0000000000..c24c1f32e8
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_pause.h
> @@ -0,0 +1,31 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_PAUSE_RISCV_H
> +#define RTE_PAUSE_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "rte_atomic.h"
> +
> +#include "generic/rte_pause.h"
> +
> +static inline void rte_pause(void)
> +{
> + /* Insert pause hint directly to be compatible with old compilers.
> + * This will work even on platforms without Zihintpause extension
> + * because this is a FENCE hint instruction which evaluates to NOP then.
> + */
> + asm volatile(".int 0x0100000F"::: "memory");
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_PAUSE_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_pflock.h b/lib/eal/riscv/include/rte_pflock.h
> new file mode 100644
> index 0000000000..ce6ca02aca
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_pflock.h
> @@ -0,0 +1,17 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2021 Microsoft Corporation
> + */
> +#ifndef RTE_PFLOCK_RISCV_H
> +#define RTE_PFLOCK_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_pflock.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_PFLOCK_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_power_intrinsics.h b/lib/eal/riscv/include/rte_power_intrinsics.h
> new file mode 100644
> index 0000000000..636e58e71f
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_power_intrinsics.h
> @@ -0,0 +1,22 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_POWER_INTRINSIC_RISCV_H
> +#define RTE_POWER_INTRINSIC_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include <rte_common.h>
> +
> +#include "generic/rte_power_intrinsics.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_POWER_INTRINSIC_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_prefetch.h b/lib/eal/riscv/include/rte_prefetch.h
> new file mode 100644
> index 0000000000..966d9e2687
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_prefetch.h
> @@ -0,0 +1,50 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2014 IBM Corporation
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_PREFETCH_RISCV_H
> +#define RTE_PREFETCH_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include <rte_common.h>
> +#include "generic/rte_prefetch.h"
> +
> +static inline void rte_prefetch0(const volatile void *p)
> +{
> + RTE_SET_USED(p);
> +}
> +
> +static inline void rte_prefetch1(const volatile void *p)
> +{
> + RTE_SET_USED(p);
> +}
> +
> +static inline void rte_prefetch2(const volatile void *p)
> +{
> + RTE_SET_USED(p);
> +}
> +
> +static inline void rte_prefetch_non_temporal(const volatile void *p)
> +{
> + /* non-temporal version not available, fallback to rte_prefetch0 */
> + rte_prefetch0(p);
> +}
> +
> +__rte_experimental
> +static inline void
> +rte_cldemote(const volatile void *p)
> +{
> + RTE_SET_USED(p);
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_PREFETCH_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_rwlock.h b/lib/eal/riscv/include/rte_rwlock.h
> new file mode 100644
> index 0000000000..9cdaf1b0ef
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_rwlock.h
> @@ -0,0 +1,44 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_RWLOCK_RISCV_H
> +#define RTE_RWLOCK_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_rwlock.h"
> +
> +static inline void
> +rte_rwlock_read_lock_tm(rte_rwlock_t *rwl)
> +{
> + rte_rwlock_read_lock(rwl);
> +}
> +
> +static inline void
> +rte_rwlock_read_unlock_tm(rte_rwlock_t *rwl)
> +{
> + rte_rwlock_read_unlock(rwl);
> +}
> +
> +static inline void
> +rte_rwlock_write_lock_tm(rte_rwlock_t *rwl)
> +{
> + rte_rwlock_write_lock(rwl);
> +}
> +
> +static inline void
> +rte_rwlock_write_unlock_tm(rte_rwlock_t *rwl)
> +{
> + rte_rwlock_write_unlock(rwl);
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_RWLOCK_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_spinlock.h b/lib/eal/riscv/include/rte_spinlock.h
> new file mode 100644
> index 0000000000..6af430735c
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_spinlock.h
> @@ -0,0 +1,67 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2015 RehiveTech. All rights reserved.
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_SPINLOCK_RISCV_H
> +#define RTE_SPINLOCK_RISCV_H
> +
> +#ifndef RTE_FORCE_INTRINSICS
> +# error Platform must be built with RTE_FORCE_INTRINSICS
> +#endif
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include <rte_common.h>
> +#include "generic/rte_spinlock.h"
> +
> +static inline int rte_tm_supported(void)
> +{
> + return 0;
> +}
> +
> +static inline void
> +rte_spinlock_lock_tm(rte_spinlock_t *sl)
> +{
> + rte_spinlock_lock(sl); /* fall-back */
> +}
> +
> +static inline int
> +rte_spinlock_trylock_tm(rte_spinlock_t *sl)
> +{
> + return rte_spinlock_trylock(sl);
> +}
> +
> +static inline void
> +rte_spinlock_unlock_tm(rte_spinlock_t *sl)
> +{
> + rte_spinlock_unlock(sl);
> +}
> +
> +static inline void
> +rte_spinlock_recursive_lock_tm(rte_spinlock_recursive_t *slr)
> +{
> + rte_spinlock_recursive_lock(slr); /* fall-back */
> +}
> +
> +static inline void
> +rte_spinlock_recursive_unlock_tm(rte_spinlock_recursive_t *slr)
> +{
> + rte_spinlock_recursive_unlock(slr);
> +}
> +
> +static inline int
> +rte_spinlock_recursive_trylock_tm(rte_spinlock_recursive_t *slr)
> +{
> + return rte_spinlock_recursive_trylock(slr);
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_SPINLOCK_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_ticketlock.h b/lib/eal/riscv/include/rte_ticketlock.h
> new file mode 100644
> index 0000000000..b8d2a4f937
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_ticketlock.h
> @@ -0,0 +1,21 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2019 Arm Limited
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_TICKETLOCK_RISCV_H
> +#define RTE_TICKETLOCK_RISCV_H
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#include "generic/rte_ticketlock.h"
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_TICKETLOCK_RISCV_H */
> diff --git a/lib/eal/riscv/include/rte_vect.h b/lib/eal/riscv/include/rte_vect.h
> new file mode 100644
> index 0000000000..4600521c20
> --- /dev/null
> +++ b/lib/eal/riscv/include/rte_vect.h
> @@ -0,0 +1,55 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#ifndef RTE_VECT_RISCV_H
> +#define RTE_VECT_RISCV_H
> +
> +#include <stdint.h>
> +#include "generic/rte_vect.h"
> +#include "rte_common.h"
> +
> +#ifdef __cplusplus
> +extern "C" {
> +#endif
> +
> +#define RTE_VECT_DEFAULT_SIMD_BITWIDTH RTE_VECT_SIMD_DISABLED
> +
> +typedef int32_t xmm_t __attribute__((vector_size(16)));
> +
> +#define XMM_SIZE (sizeof(xmm_t))
> +#define XMM_MASK (XMM_SIZE - 1)
> +
> +typedef union rte_xmm {
> + xmm_t x;
> + uint8_t u8[XMM_SIZE / sizeof(uint8_t)];
> + uint16_t u16[XMM_SIZE / sizeof(uint16_t)];
> + uint32_t u32[XMM_SIZE / sizeof(uint32_t)];
> + uint64_t u64[XMM_SIZE / sizeof(uint64_t)];
> + double pd[XMM_SIZE / sizeof(double)];
> +} __rte_aligned(8) rte_xmm_t;
> +
> +static inline xmm_t
> +vect_load_128(void *p)
> +{
> + xmm_t ret = *((xmm_t *)p);
> + return ret;
> +}
> +
> +static inline xmm_t
> +vect_and(xmm_t data, xmm_t mask)
> +{
> + rte_xmm_t ret = (rte_xmm_t)data;
> + rte_xmm_t m = (rte_xmm_t)mask;
> + ret.u64[0] &= m.u64[0];
> + ret.u64[1] &= m.u64[1];
> + return ret.x;
> +}
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* RTE_VECT_RISCV_H */
> diff --git a/lib/eal/riscv/meson.build b/lib/eal/riscv/meson.build
> new file mode 100644
> index 0000000000..dca1106aae
> --- /dev/null
> +++ b/lib/eal/riscv/meson.build
> @@ -0,0 +1,11 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2017 Intel Corporation.
> +
> +subdir('include')
> +
> +sources += files(
> + 'rte_cpuflags.c',
> + 'rte_cycles.c',
> + 'rte_hypervisor.c',
> + 'rte_power_intrinsics.c',
> +)
> diff --git a/lib/eal/riscv/rte_cpuflags.c b/lib/eal/riscv/rte_cpuflags.c
> new file mode 100644
> index 0000000000..4f6d29b947
> --- /dev/null
> +++ b/lib/eal/riscv/rte_cpuflags.c
> @@ -0,0 +1,122 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#include "rte_cpuflags.h"
> +
> +#include <elf.h>
> +#include <fcntl.h>
> +#include <assert.h>
> +#include <unistd.h>
> +#include <string.h>
> +
> +#ifndef AT_HWCAP
> +#define AT_HWCAP 16
> +#endif
> +
> +#ifndef AT_HWCAP2
> +#define AT_HWCAP2 26
> +#endif
> +
> +#ifndef AT_PLATFORM
> +#define AT_PLATFORM 15
> +#endif
> +
> +enum cpu_register_t {
> + REG_NONE = 0,
> + REG_HWCAP,
> + REG_HWCAP2,
> + REG_PLATFORM,
> + REG_MAX
> +};
> +
> +typedef uint32_t hwcap_registers_t[REG_MAX];
> +
> +/**
> + * Struct to hold a processor feature entry
> + */
> +struct feature_entry {
> + uint32_t reg;
> + uint32_t bit;
> +#define CPU_FLAG_NAME_MAX_LEN 64
> + char name[CPU_FLAG_NAME_MAX_LEN];
> +};
> +
> +#define FEAT_DEF(name, reg, bit) \
> + [RTE_CPUFLAG_##name] = {reg, bit, #name},
> +
> +typedef Elf64_auxv_t _Elfx_auxv_t;
> +
> +const struct feature_entry rte_cpu_feature_table[] = {
> + FEAT_DEF(RISCV_ISA_A, REG_HWCAP, 0)
> + FEAT_DEF(RISCV_ISA_B, REG_HWCAP, 1)
> + FEAT_DEF(RISCV_ISA_C, REG_HWCAP, 2)
> + FEAT_DEF(RISCV_ISA_D, REG_HWCAP, 3)
> + FEAT_DEF(RISCV_ISA_E, REG_HWCAP, 4)
> + FEAT_DEF(RISCV_ISA_F, REG_HWCAP, 5)
> + FEAT_DEF(RISCV_ISA_G, REG_HWCAP, 6)
> + FEAT_DEF(RISCV_ISA_H, REG_HWCAP, 7)
> + FEAT_DEF(RISCV_ISA_I, REG_HWCAP, 8)
> + FEAT_DEF(RISCV_ISA_J, REG_HWCAP, 9)
> + FEAT_DEF(RISCV_ISA_K, REG_HWCAP, 10)
> + FEAT_DEF(RISCV_ISA_L, REG_HWCAP, 11)
> + FEAT_DEF(RISCV_ISA_M, REG_HWCAP, 12)
> + FEAT_DEF(RISCV_ISA_N, REG_HWCAP, 13)
> + FEAT_DEF(RISCV_ISA_O, REG_HWCAP, 14)
> + FEAT_DEF(RISCV_ISA_P, REG_HWCAP, 15)
> + FEAT_DEF(RISCV_ISA_Q, REG_HWCAP, 16)
> + FEAT_DEF(RISCV_ISA_R, REG_HWCAP, 17)
> + FEAT_DEF(RISCV_ISA_S, REG_HWCAP, 18)
> + FEAT_DEF(RISCV_ISA_T, REG_HWCAP, 19)
> + FEAT_DEF(RISCV_ISA_U, REG_HWCAP, 20)
> + FEAT_DEF(RISCV_ISA_V, REG_HWCAP, 21)
> + FEAT_DEF(RISCV_ISA_W, REG_HWCAP, 22)
> + FEAT_DEF(RISCV_ISA_X, REG_HWCAP, 23)
> + FEAT_DEF(RISCV_ISA_Y, REG_HWCAP, 24)
> + FEAT_DEF(RISCV_ISA_Z, REG_HWCAP, 25)
> +};
> +/*
> + * Read AUXV software register and get cpu features for ARM
> + */
> +static void
> +rte_cpu_get_features(hwcap_registers_t out)
> +{
> + out[REG_HWCAP] = rte_cpu_getauxval(AT_HWCAP);
> + out[REG_HWCAP2] = rte_cpu_getauxval(AT_HWCAP2);
> +}
> +
> +/*
> + * Checks if a particular flag is available on current machine.
> + */
> +int
> +rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
> +{
> + const struct feature_entry *feat;
> + hwcap_registers_t regs = {0};
> +
> + if (feature >= RTE_CPUFLAG_NUMFLAGS)
> + return -ENOENT;
> +
> + feat = &rte_cpu_feature_table[feature];
> + if (feat->reg == REG_NONE)
> + return -EFAULT;
> +
> + rte_cpu_get_features(regs);
> + return (regs[feat->reg] >> feat->bit) & 1;
> +}
> +
> +const char *
> +rte_cpu_get_flag_name(enum rte_cpu_flag_t feature)
> +{
> + if (feature >= RTE_CPUFLAG_NUMFLAGS)
> + return NULL;
> + return rte_cpu_feature_table[feature].name;
> +}
> +
> +void
> +rte_cpu_get_intrinsics_support(struct rte_cpu_intrinsics *intrinsics)
> +{
> + memset(intrinsics, 0, sizeof(*intrinsics));
> +}
> diff --git a/lib/eal/riscv/rte_cycles.c b/lib/eal/riscv/rte_cycles.c
> new file mode 100644
> index 0000000000..358f271311
> --- /dev/null
> +++ b/lib/eal/riscv/rte_cycles.c
> @@ -0,0 +1,77 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2015 Cavium, Inc
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#include <stdio.h>
> +
> +#include "eal_private.h"
> +#include "rte_byteorder.h"
> +#include "rte_cycles.h"
> +#include "rte_log.h"
> +
> +/** Read generic counter frequency */
> +static uint64_t
> +__rte_riscv_timefrq(void)
> +{
> +#define TIMEBASE_FREQ_SIZE 8
> + if (RTE_RISCV_TIME_FREQ > 0)
> + return RTE_RISCV_TIME_FREQ;
> + uint8_t buf[TIMEBASE_FREQ_SIZE];
> + ssize_t cnt;
> + FILE *file;
> +
> + file = fopen("/proc/device-tree/cpus/timebase-frequency", "rb");
> + if (!file)
> + goto fail;
> +
> + cnt = fread(buf, 1, TIMEBASE_FREQ_SIZE, file);
> + fclose(file);
> + switch (cnt) {
> + case 8:
> + return rte_be_to_cpu_64(*(uint64_t *)buf);
> + case 4:
> + return rte_be_to_cpu_32(*(uint32_t *)buf);
> + default:
> + break;
> + }
> +fail:
> + RTE_LOG(WARNING, EAL, "Unable to read timebase-frequency from FDT.\n");
> + return 0;
> +}
> +
> +uint64_t
> +get_tsc_freq_arch(void)
> +{
> + RTE_LOG(NOTICE, EAL, "TSC using RISC-V %s.\n",
> + RTE_RISCV_RDTSC_USE_HPM ? "rdcycle" : "rdtime");
> + if (!RTE_RISCV_RDTSC_USE_HPM)
> + return __rte_riscv_timefrq();
> +#define CYC_PER_1MHZ 1E6
> + /*
> + * Use real time clock to estimate current cycle frequency
> + */
> + uint64_t ticks, frq;
> + uint64_t start_ticks, cur_ticks;
> + uint64_t start_cycle, end_cycle;
> +
> + /* Do not proceed unless clock frequency can be obtained. */
> + frq = __rte_riscv_timefrq();
> + if (!frq)
> + return 0;
> +
> + /* Number of ticks for 1/10 second */
> + ticks = frq / 10;
> +
> + start_ticks = __rte_riscv_rdtime_precise();
> + start_cycle = rte_rdtsc_precise();
> + do {
> + cur_ticks = __rte_riscv_rdtime();
> + } while ((cur_ticks - start_ticks) < ticks);
> + end_cycle = rte_rdtsc_precise();
> +
> + /* Adjust the cycles to next 1Mhz */
> + return RTE_ALIGN_MUL_CEIL((end_cycle - start_cycle) * 10, CYC_PER_1MHZ);
> +}
> diff --git a/lib/eal/riscv/rte_hypervisor.c b/lib/eal/riscv/rte_hypervisor.c
> new file mode 100644
> index 0000000000..92b5435993
> --- /dev/null
> +++ b/lib/eal/riscv/rte_hypervisor.c
> @@ -0,0 +1,13 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#include "rte_hypervisor.h"
> +
> +enum rte_hypervisor
> +rte_hypervisor_get(void)
> +{
> + return RTE_HYPERVISOR_UNKNOWN;
> +}
> diff --git a/lib/eal/riscv/rte_power_intrinsics.c b/lib/eal/riscv/rte_power_intrinsics.c
> new file mode 100644
> index 0000000000..240e7b6b87
> --- /dev/null
> +++ b/lib/eal/riscv/rte_power_intrinsics.c
> @@ -0,0 +1,56 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2022 StarFive
> + * Copyright(c) 2022 SiFive
> + * Copyright(c) 2022 Semihalf
> + */
> +
> +#include "rte_power_intrinsics.h"
> +
> +/**
> + * This function is not supported on RISC-V 64
> + */
> +int
> +rte_power_monitor(const struct rte_power_monitor_cond *pmc,
> + const uint64_t tsc_timestamp)
> +{
> + RTE_SET_USED(pmc);
> + RTE_SET_USED(tsc_timestamp);
> +
> + return -ENOTSUP;
> +}
> +
> +/**
> + * This function is not supported on RISC-V 64
> + */
> +int
> +rte_power_pause(const uint64_t tsc_timestamp)
> +{
> + RTE_SET_USED(tsc_timestamp);
> +
> + return -ENOTSUP;
> +}
> +
> +/**
> + * This function is not supported on RISC-V 64
> + */
> +int
> +rte_power_monitor_wakeup(const unsigned int lcore_id)
> +{
> + RTE_SET_USED(lcore_id);
> +
> + return -ENOTSUP;
> +}
> +
> +/**
> + * This function is not supported on RISC-V 64
> + */
> +int
> +rte_power_monitor_multi(const struct rte_power_monitor_cond pmc[],
> + const uint32_t num, const uint64_t tsc_timestamp)
> +{
> + RTE_SET_USED(pmc);
> + RTE_SET_USED(num);
> + RTE_SET_USED(tsc_timestamp);
> +
> + return -ENOTSUP;
> +}
> diff --git a/meson.build b/meson.build
> index 937f6110c0..a8db04a1ee 100644
> --- a/meson.build
> +++ b/meson.build
> @@ -50,6 +50,8 @@ elif host_machine.cpu_family().startswith('arm') or host_machine.cpu_family().st
> arch_subdir = 'arm'
> elif host_machine.cpu_family().startswith('ppc')
> arch_subdir = 'ppc'
> +elif host_machine.cpu_family().startswith('riscv')
> + arch_subdir = 'riscv'
> endif
>
> # configure the build, and make sure configs here and in config folder are
On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt
<heinrich.schuchardt@canonical.com> wrote:
<snip>
> > +Linux kernel
> > +~~~~~~~~~~~~
> > +
> > +It is recommended to use Linux kernel built from
> > +`SiFive Freedom Unleashed SDK <https://github.com/sifive/freedom-u-sdk>`_.
>
> How would the Unleashed SDK help on a later board or a board from a
> different vendor?
This SDK is for both Unleashed and Unmatched. The naming is a bit misleading.
>
> Why wouldn't an upstream kernel work?
At the point of writing it was missing patches related to PCI resource
mapping exposure to userspace. Right now it's there.
>
> I suggest to eliminate this misleading section.
I'll re-test with the latest upstream kernel and rephrase that this
should work with Linux kernel >= x.y.z.
>
> > +
> > +
> > +Meson prerequisites
> > +~~~~~~~~~~~~~~~~~~~
> > +
> > +Meson depends on pkgconfig to find the dependencies.
> > +The package ``pkg-config-riscv64-linux-gnu`` is required for RISC-V.
> > +To install it in Ubuntu::
> > +
> > + sudo apt install pkg-config-riscv64-linux-gnu
>
> This package does not exist in the current Ubuntu LTS (22.04, Jammy).
>
> Setting environment variables PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH,
> PKG_CONFIG_SYSROOT_DIR properly should do the job with the normal
> pkg-config.
Do you happen to know why was this package removed?
Given that, is there a Ubuntu manual page or tool somewhere specifying
the correct values to obtain for a given arch?
>
> > +
> > +
> > +GNU toolchain
> > +-------------
> > +
> > +
> > +Obtain the cross toolchain
> > +~~~~~~~~~~~~~~~~~~~~~~~~~~
> > +
> > +The build process was tested using:
> > +
> > +* Ubuntu toolchain (the ``crossbuild-essential-riscv64`` package).
> > +
> > +* Latest `RISC-V GNU toolchain
> > + <https://github.com/riscv/riscv-gnu-toolchain/releases>`_ on Ubuntu or Arch
> > + Linux.
> > +
> > +Alternatively the toolchain may be built straight from the source, to do that
> > +follow the instructions on the riscv-gnu-toolchain github page.
> > +
> > +
> > +Unzip and add into the PATH
> > +~~~~~~~~~~~~~~~~~~~~~~~~~~~
> > +
> > +This step is only required for the riscv-gnu-toolchain. The Ubuntu toolchain is
> > +in the PATH already.
> > +
> > +.. code-block:: console
> > +
> > + tar -xvf riscv64-glibc-ubuntu-20.04-<version>.tar.gz
>
> You can install the glibc package with apt-get after adding the
> architecture with sudo dpkg --add-architecture riscv64. See
> https://wiki.debian.org/CrossCompiling.
>
This guide is supposed to target also Arch where this toolchain should
work properly. That's why in previous section I'm mentioning
crossbuild-essential-riscv64 and RISC-V GNU toolchain from github
separately.
> > + export PATH=$PATH:<cross_install_dir>/riscv/bin
> > +
> > +
> > +Cross Compiling DPDK with GNU toolchain using Meson
> > +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> > +
> > +To cross-compile DPDK for a desired target machine use the following command::
> > +
> > + meson cross-build --cross-file <target_machine_configuration>
> > + ninja -C cross-build
> > +
> > +For example if the target machine is a generic rv64gc RISC-V, use the following
> > +command::
> > +
> > + meson riscv64-build-gcc --cross-file config/riscv/riscv64_linux_gcc
> > + ninja -C riscv64-build-gcc
> > +
> > +If riscv-gnu-toolchain is used, binary names should be updated to match. Update the following lines in the cross-file:
> > +
> > +.. code-block:: console
> > +
> > + [binaries]
> > + c = 'riscv64-unknown-linux-gnu-gcc'
> > + cpp = 'riscv64-unknown-linux-gnu-g++'
> > + ar = 'riscv64-unknown-linux-gnu-ar'
> > + strip = 'riscv64-unknown-linux-gnu-strip'
> > + ...
> > +
> > +Some toolchains (such as freedom-u-sdk one) require also setting ``--sysroot``,
> > +otherwise include paths might not be resolved. To do so, add the appropriate
> > +paths to the cross-file:
> > +
> > +.. code-block:: console
> > +
> > + [properties]
> > + ...
> > + c_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> > + cpp_args = c_args
> > + c_link_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> > + cpp_link_args = c_link_args
> > + ...
> > +
> > +
> > +Supported cross-compilation targets
> > +-----------------------------------
> > +
> > +Currently the following targets are supported:
> > +
> > +* Generic rv64gc ISA: ``config/riscv/riscv64_linux_gcc``
> > +
> > +* SiFive U740 SoC: ``config/riscv/riscv64_sifive_u740_linux_gcc``
>
> Why do we need a special config for the Unmatched board that is not sold
> anymore? Doesn't the Unmatched board work with the genenric config?
I wasn't aware that they did discontinue it. As far as I can see it's
due to supply chain issues, maybe that means it'll get back? Generic
config works just fine for the Unmatched. However config for Unmatched
enables certain optimizations that are valid there. I.e. when reading
RIME or CYCLE registers in a precise way, normally a fence should be
inserted before reading it. However on Unmatched read to both counters
is emulated through a call to firmware (SBI) in userspace, eliminating
the need for the fence.
>
> I assume a single configuriation file for the generic target is enough.
>
> Best regards
>
> Heinrich
>
On 5/13/22 10:42, Stanisław Kardach wrote:
> On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt
> <heinrich.schuchardt@canonical.com> wrote:
> <snip>
>>> +Linux kernel
>>> +~~~~~~~~~~~~
>>> +
>>> +It is recommended to use Linux kernel built from
>>> +`SiFive Freedom Unleashed SDK <https://github.com/sifive/freedom-u-sdk>`_.
>>
>> How would the Unleashed SDK help on a later board or a board from a
>> different vendor?
> This SDK is for both Unleashed and Unmatched. The naming is a bit misleading.
>>
>> Why wouldn't an upstream kernel work?
> At the point of writing it was missing patches related to PCI resource
> mapping exposure to userspace. Right now it's there.
>>
>> I suggest to eliminate this misleading section.
> I'll re-test with the latest upstream kernel and rephrase that this
> should work with Linux kernel >= x.y.z.
>>
>>> +
>>> +
>>> +Meson prerequisites
>>> +~~~~~~~~~~~~~~~~~~~
>>> +
>>> +Meson depends on pkgconfig to find the dependencies.
>>> +The package ``pkg-config-riscv64-linux-gnu`` is required for RISC-V.
>>> +To install it in Ubuntu::
>>> +
>>> + sudo apt install pkg-config-riscv64-linux-gnu
>>
>> This package does not exist in the current Ubuntu LTS (22.04, Jammy).
>>
>> Setting environment variables PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH,
>> PKG_CONFIG_SYSROOT_DIR properly should do the job with the normal
>> pkg-config.
> Do you happen to know why was this package removed?
The Debian maintainer introduced this change in package
gcc-defaults-ports. The change log does not give a reason.
> Given that, is there a Ubuntu manual page or tool somewhere specifying
> the correct values to obtain for a given arch?
The values might depend on the Linux distribution.
In Ubuntu the .pc files are in
/usr/lib/riscv64-linux-gnu/pkgconfig
/usr/lib/pkgconfig
/usr/share/pkgconfig
>
>>
>>> +
>>> +
>>> +GNU toolchain
>>> +-------------
>>> +
>>> +
>>> +Obtain the cross toolchain
>>> +~~~~~~~~~~~~~~~~~~~~~~~~~~
>>> +
>>> +The build process was tested using:
>>> +
>>> +* Ubuntu toolchain (the ``crossbuild-essential-riscv64`` package).
>>> +
>>> +* Latest `RISC-V GNU toolchain
>>> + <https://github.com/riscv/riscv-gnu-toolchain/releases>`_ on Ubuntu or Arch
>>> + Linux.
>>> +
>>> +Alternatively the toolchain may be built straight from the source, to do that
>>> +follow the instructions on the riscv-gnu-toolchain github page.
>>> +
>>> +
>>> +Unzip and add into the PATH
>>> +~~~~~~~~~~~~~~~~~~~~~~~~~~~
>>> +
>>> +This step is only required for the riscv-gnu-toolchain. The Ubuntu toolchain is
>>> +in the PATH already.
>>> +
>>> +.. code-block:: console
>>> +
>>> + tar -xvf riscv64-glibc-ubuntu-20.04-<version>.tar.gz
>>
>> You can install the glibc package with apt-get after adding the
>> architecture with sudo dpkg --add-architecture riscv64. See
>> https://wiki.debian.org/CrossCompiling.
>>
> This guide is supposed to target also Arch where this toolchain should
> work properly. That's why in previous section I'm mentioning
> crossbuild-essential-riscv64 and RISC-V GNU toolchain from github
> separately.
>>> + export PATH=$PATH:<cross_install_dir>/riscv/bin
>>> +
>>> +
>>> +Cross Compiling DPDK with GNU toolchain using Meson
>>> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>>> +
>>> +To cross-compile DPDK for a desired target machine use the following command::
>>> +
>>> + meson cross-build --cross-file <target_machine_configuration>
>>> + ninja -C cross-build
>>> +
>>> +For example if the target machine is a generic rv64gc RISC-V, use the following
>>> +command::
>>> +
>>> + meson riscv64-build-gcc --cross-file config/riscv/riscv64_linux_gcc
>>> + ninja -C riscv64-build-gcc
>>> +
>>> +If riscv-gnu-toolchain is used, binary names should be updated to match. Update the following lines in the cross-file:
>>> +
>>> +.. code-block:: console
>>> +
>>> + [binaries]
>>> + c = 'riscv64-unknown-linux-gnu-gcc'
>>> + cpp = 'riscv64-unknown-linux-gnu-g++'
>>> + ar = 'riscv64-unknown-linux-gnu-ar'
>>> + strip = 'riscv64-unknown-linux-gnu-strip'
>>> + ...
>>> +
>>> +Some toolchains (such as freedom-u-sdk one) require also setting ``--sysroot``,
>>> +otherwise include paths might not be resolved. To do so, add the appropriate
>>> +paths to the cross-file:
>>> +
>>> +.. code-block:: console
>>> +
>>> + [properties]
>>> + ...
>>> + c_args = ['--sysroot', '<path/to/toolchain/sysroot>']
>>> + cpp_args = c_args
>>> + c_link_args = ['--sysroot', '<path/to/toolchain/sysroot>']
>>> + cpp_link_args = c_link_args
>>> + ...
>>> +
>>> +
>>> +Supported cross-compilation targets
>>> +-----------------------------------
>>> +
>>> +Currently the following targets are supported:
>>> +
>>> +* Generic rv64gc ISA: ``config/riscv/riscv64_linux_gcc``
>>> +
>>> +* SiFive U740 SoC: ``config/riscv/riscv64_sifive_u740_linux_gcc``
>>
>> Why do we need a special config for the Unmatched board that is not sold
>> anymore? Doesn't the Unmatched board work with the genenric config?
> I wasn't aware that they did discontinue it. As far as I can see it's
> due to supply chain issues, maybe that means it'll get back? Generic
https://forums.sifive.com/t/sifive-update-on-hifive-unmatched-boards-in-2022/5569?s=09
:
"we’ve decided to focus on the next generation SiFive HiFive development
systems rather than trying to put together another build of the HiFive
Unmatched platform in 2022."
> config works just fine for the Unmatched. However config for Unmatched
> enables certain optimizations that are valid there. I.e. when reading
> RIME or CYCLE registers in a precise way, normally a fence should be
> inserted before reading it. However on Unmatched read to both counters
> is emulated through a call to firmware (SBI) in userspace, eliminating
> the need for the fence.
Distributions like Ubuntu will only build a single configuration. It is
preferable to read vendor_id and arch_id via an SBI call at runtime to
switch code paths.
Isn't the saving gained by removing the fence irrelevant compared to the
duration of an SBI call?
Best regards
Heinrich
>>
>> I assume a single configuration file for the generic target is enough.
>>
>> Best regards
>>
>> Heinrich
>>
On Fri, May 13, 2022 at 12:52 PM Heinrich Schuchardt
<heinrich.schuchardt@canonical.com> wrote:
>
> On 5/13/22 10:42, Stanisław Kardach wrote:
> > On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt
> > <heinrich.schuchardt@canonical.com> wrote:
> > <snip>
> >>> +Linux kernel
> >>> +~~~~~~~~~~~~
> >>> +
> >>> +It is recommended to use Linux kernel built from
> >>> +`SiFive Freedom Unleashed SDK <https://github.com/sifive/freedom-u-sdk>`_.
> >>
> >> How would the Unleashed SDK help on a later board or a board from a
> >> different vendor?
> > This SDK is for both Unleashed and Unmatched. The naming is a bit misleading.
> >>
> >> Why wouldn't an upstream kernel work?
> > At the point of writing it was missing patches related to PCI resource
> > mapping exposure to userspace. Right now it's there.
> >>
> >> I suggest to eliminate this misleading section.
> > I'll re-test with the latest upstream kernel and rephrase that this
> > should work with Linux kernel >= x.y.z.
> >>
> >>> +
> >>> +
> >>> +Meson prerequisites
> >>> +~~~~~~~~~~~~~~~~~~~
> >>> +
> >>> +Meson depends on pkgconfig to find the dependencies.
> >>> +The package ``pkg-config-riscv64-linux-gnu`` is required for RISC-V.
> >>> +To install it in Ubuntu::
> >>> +
> >>> + sudo apt install pkg-config-riscv64-linux-gnu
> >>
> >> This package does not exist in the current Ubuntu LTS (22.04, Jammy).
> >>
> >> Setting environment variables PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH,
> >> PKG_CONFIG_SYSROOT_DIR properly should do the job with the normal
> >> pkg-config.
> > Do you happen to know why was this package removed?
>
> The Debian maintainer introduced this change in package
> gcc-defaults-ports. The change log does not give a reason.
>
> > Given that, is there a Ubuntu manual page or tool somewhere specifying
> > the correct values to obtain for a given arch?
>
> The values might depend on the Linux distribution.
>
> In Ubuntu the .pc files are in
>
> /usr/lib/riscv64-linux-gnu/pkgconfig
> /usr/lib/pkgconfig
> /usr/share/pkgconfig
OK, I'll describe those for Ubuntu path.
>
> >
> >>
> >>> +
> >>> +
> >>> +GNU toolchain
> >>> +-------------
> >>> +
> >>> +
> >>> +Obtain the cross toolchain
> >>> +~~~~~~~~~~~~~~~~~~~~~~~~~~
> >>> +
> >>> +The build process was tested using:
> >>> +
> >>> +* Ubuntu toolchain (the ``crossbuild-essential-riscv64`` package).
> >>> +
> >>> +* Latest `RISC-V GNU toolchain
> >>> + <https://github.com/riscv/riscv-gnu-toolchain/releases>`_ on Ubuntu or Arch
> >>> + Linux.
> >>> +
> >>> +Alternatively the toolchain may be built straight from the source, to do that
> >>> +follow the instructions on the riscv-gnu-toolchain github page.
> >>> +
> >>> +
> >>> +Unzip and add into the PATH
> >>> +~~~~~~~~~~~~~~~~~~~~~~~~~~~
> >>> +
> >>> +This step is only required for the riscv-gnu-toolchain. The Ubuntu toolchain is
> >>> +in the PATH already.
> >>> +
> >>> +.. code-block:: console
> >>> +
> >>> + tar -xvf riscv64-glibc-ubuntu-20.04-<version>.tar.gz
> >>
> >> You can install the glibc package with apt-get after adding the
> >> architecture with sudo dpkg --add-architecture riscv64. See
> >> https://wiki.debian.org/CrossCompiling.
> >>
> > This guide is supposed to target also Arch where this toolchain should
> > work properly. That's why in previous section I'm mentioning
> > crossbuild-essential-riscv64 and RISC-V GNU toolchain from github
> > separately.
> >>> + export PATH=$PATH:<cross_install_dir>/riscv/bin
> >>> +
> >>> +
> >>> +Cross Compiling DPDK with GNU toolchain using Meson
> >>> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> >>> +
> >>> +To cross-compile DPDK for a desired target machine use the following command::
> >>> +
> >>> + meson cross-build --cross-file <target_machine_configuration>
> >>> + ninja -C cross-build
> >>> +
> >>> +For example if the target machine is a generic rv64gc RISC-V, use the following
> >>> +command::
> >>> +
> >>> + meson riscv64-build-gcc --cross-file config/riscv/riscv64_linux_gcc
> >>> + ninja -C riscv64-build-gcc
> >>> +
> >>> +If riscv-gnu-toolchain is used, binary names should be updated to match. Update the following lines in the cross-file:
> >>> +
> >>> +.. code-block:: console
> >>> +
> >>> + [binaries]
> >>> + c = 'riscv64-unknown-linux-gnu-gcc'
> >>> + cpp = 'riscv64-unknown-linux-gnu-g++'
> >>> + ar = 'riscv64-unknown-linux-gnu-ar'
> >>> + strip = 'riscv64-unknown-linux-gnu-strip'
> >>> + ...
> >>> +
> >>> +Some toolchains (such as freedom-u-sdk one) require also setting ``--sysroot``,
> >>> +otherwise include paths might not be resolved. To do so, add the appropriate
> >>> +paths to the cross-file:
> >>> +
> >>> +.. code-block:: console
> >>> +
> >>> + [properties]
> >>> + ...
> >>> + c_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> >>> + cpp_args = c_args
> >>> + c_link_args = ['--sysroot', '<path/to/toolchain/sysroot>']
> >>> + cpp_link_args = c_link_args
> >>> + ...
> >>> +
> >>> +
> >>> +Supported cross-compilation targets
> >>> +-----------------------------------
> >>> +
> >>> +Currently the following targets are supported:
> >>> +
> >>> +* Generic rv64gc ISA: ``config/riscv/riscv64_linux_gcc``
> >>> +
> >>> +* SiFive U740 SoC: ``config/riscv/riscv64_sifive_u740_linux_gcc``
> >>
> >> Why do we need a special config for the Unmatched board that is not sold
> >> anymore? Doesn't the Unmatched board work with the genenric config?
> > I wasn't aware that they did discontinue it. As far as I can see it's
> > due to supply chain issues, maybe that means it'll get back? Generic
>
> https://forums.sifive.com/t/sifive-update-on-hifive-unmatched-boards-in-2022/5569?s=09
> :
>
> "we’ve decided to focus on the next generation SiFive HiFive development
> systems rather than trying to put together another build of the HiFive
> Unmatched platform in 2022."
I did not know that, thank you.
>
> > config works just fine for the Unmatched. However config for Unmatched
> > enables certain optimizations that are valid there. I.e. when reading
> > RIME or CYCLE registers in a precise way, normally a fence should be
> > inserted before reading it. However on Unmatched read to both counters
> > is emulated through a call to firmware (SBI) in userspace, eliminating
> > the need for the fence.
>
> Distributions like Ubuntu will only build a single configuration.
I understand however there are also platform specific configs for
Aarch64 here (Graviton, ThunderX, CnXk to name a few) so it's not that
uncommon. Plus distro packages although useful for orchestration
environments such as accelerating OpenStack Neutron (or other
orchestrated networking packages), there will still be people
compiling DPDK locally, be it via company-wide Yocto server to package
for specific HW or just integrating DPDK statically in their projects
(to not pay the cost of a dynamic lib call).
> It is preferable to read vendor_id and arch_id via an SBI call at runtime
> to switch code paths.
Right, but SBI call can only be made from S-mode (so kernel), right?
Issuing "ecall" from U-mode (userspace) will transfer control to
kernel. AFAIK it is KVM that emulates or forwards SBI calls further
but that's in qemu scope.
I was trying to figure out how to get this data from Linux to decide
at build time but it's not in the /proc/cpuinfo (it only prints DTS's
"compatible" for the CPU). Deciding at runtime is costly because you
either need a functor call or self-modifying code (similar to how
Linux handles Compare-And-Swap on Aarch64).
>
> Isn't the saving gained by removing the fence irrelevant compared to the
> duration of an SBI call?
Yes, that is most likely but I was not able to measure it, because the
access to the time source on Unmatched is emulated, so it's hard to
reason.
Other thing that this config triggers (or more precisely the vendor_id
and arch_id) is "-mtune" value which I believe still contains some
compiler tweaks for the platform.
Given all that I can remove the current infrastructure in
config/riscv/meson.build and the related sifive config but I'd prefer
not to. I'm pretty sure it'll come in handy when a new RISC-V platform
comes in (and serve as a reference for new developers). There is a
warning in meson.build noting the lack of ability to detect the
current platform. When someone implements it in Linux, that'll be a
single place to change. Even then the configs won't become useless due
to cross-compiling for a specific target.
Best Regards,
Stanislaw Kardach
On Fri, 13 May 2022 08:50:34 +0200
Heinrich Schuchardt <heinrich.schuchardt@canonical.com> wrote:
> On 5/10/22 17:48, Stanislaw Kardach wrote:
> > From: Michal Mazurek <maz@semihalf.com>
> >
> > Add all necessary elements for DPDK to compile and run EAL on SiFive
> > Freedom U740 SoC which is based on SiFive U74-MC (ISA: rv64imafdc)
> > core complex.
> >
> > This includes:
> >
> > - EAL library implementation for rv64imafdc ISA.
> > - meson build structure for 'riscv' architecture. RTE_ARCH_RISCV define
> > is added for architecture identification.
> > - xmm_t structure operation stubs as there is no vector support in the
> > U74 core.
> >
> > Compilation was tested on Ubuntu and Arch Linux using riscv64 toolchain.
> > Clang compilation currently not supported due to issues with missing
> > relocation relaxation.
> >
> > Two rte_rdtsc() schemes are provided: stable low-resolution using rdtime
> > (default) and unstable high-resolution using rdcycle. User can override
> > the scheme by defining RTE_RISCV_RDTSC_USE_HPM=1 during compile time of
> > both DPDK and the application. The reasoning for this is as follows.
> > The RISC-V ISA mandates that clock read by rdtime has to be of constant
> > period and synchronized between all hardware threads within 1 tick
> > (chapter 10.1 in version 20191213 of RISC-V spec).
> > However this clock may not be of high-enough frequency for dataplane
> > uses. I.e. on HiFive Unmatched (FU740) it is 1MHz.
> > There is a high-resolution alternative in form of rdcycle which is
> > clocked at the core clock frequency. The drawbacks are that it may be
> > disabled during sleep (WFI) and its frequency might change due to DVFS.
Choosing at compile time is ok for embedded but is undesireable for DPDK
in a distribution. It sounds like the low-res is equivalent to hpet
and the unstable is same as x86 TSC. Therefore why not follow that
precedent and do the same thing?
On Fri, May 13, 2022 at 5:37 PM Stephen Hemminger
<stephen@networkplumber.org> wrote:
>
> On Fri, 13 May 2022 08:50:34 +0200
> Heinrich Schuchardt <heinrich.schuchardt@canonical.com> wrote:
>
> > On 5/10/22 17:48, Stanislaw Kardach wrote:
> > > From: Michal Mazurek <maz@semihalf.com>
> > >
> > > Add all necessary elements for DPDK to compile and run EAL on SiFive
> > > Freedom U740 SoC which is based on SiFive U74-MC (ISA: rv64imafdc)
> > > core complex.
> > >
> > > This includes:
> > >
> > > - EAL library implementation for rv64imafdc ISA.
> > > - meson build structure for 'riscv' architecture. RTE_ARCH_RISCV define
> > > is added for architecture identification.
> > > - xmm_t structure operation stubs as there is no vector support in the
> > > U74 core.
> > >
> > > Compilation was tested on Ubuntu and Arch Linux using riscv64 toolchain.
> > > Clang compilation currently not supported due to issues with missing
> > > relocation relaxation.
> > >
> > > Two rte_rdtsc() schemes are provided: stable low-resolution using rdtime
> > > (default) and unstable high-resolution using rdcycle. User can override
> > > the scheme by defining RTE_RISCV_RDTSC_USE_HPM=1 during compile time of
> > > both DPDK and the application. The reasoning for this is as follows.
> > > The RISC-V ISA mandates that clock read by rdtime has to be of constant
> > > period and synchronized between all hardware threads within 1 tick
> > > (chapter 10.1 in version 20191213 of RISC-V spec).
> > > However this clock may not be of high-enough frequency for dataplane
> > > uses. I.e. on HiFive Unmatched (FU740) it is 1MHz.
> > > There is a high-resolution alternative in form of rdcycle which is
> > > clocked at the core clock frequency. The drawbacks are that it may be
> > > disabled during sleep (WFI) and its frequency might change due to DVFS.
>
> Choosing at compile time is ok for embedded but is undesireable for DPDK
> in a distribution. It sounds like the low-res is equivalent to hpet
> and the unstable is same as x86 TSC.
AFAIK, TSC has constant frequency on newer processors (see [1] for a
somewhat related Linux patch). To quote Intel
Software Developer’s Manual Volume 3, pt. 17.17.1:
The invariant TSC will run at a constant rate in all ACPI
P-, C-. and T-states. This is the architectural behavior moving
forward.
> Therefore why not follow that
> precedent and do the same thing?
>
Here the situation is more akin to ARMv8 with it's low-resolution
CNTVCT and PMU based PMCCNTR. The former is always available in
userspace (EL0) while access to the latter needs to be enabled via
CSRs in kernel.
RDCYCLE on RISC-V is essentially the same as PMCCNTR, except that by
default it's enabled (governed by OpenSBI firmware - see [2]). However
it does not have the stable nature of TSC in RISC-V spec. AFAIK on ARM
this has been dealt with similarly to x86, ARMv8.6-a forces a 1GHz
frequency for CNTVCT.
So I based my implementation on the current ARM platform approach.
Given that it seems RDCYCLE will remain enabled in userspace (see
[2]), I can simplify this to use RDCYCLE if current ARM approach is
not preferred.
[1] https://patchwork.kernel.org/project/kvm/patch/20140422191200.328459410@amt.cnet/
[2] http://lists.infradead.org/pipermail/opensbi/2021-June/001219.html
@@ -296,6 +296,12 @@ F: drivers/*/*/*_altivec.*
F: app/*/*_altivec.*
F: examples/*/*_altivec.*
+RISC-V
+M: Stanislaw Kardach <kda@semihalf.com>
+F: config/riscv/
+F: doc/guides/linux_gsg/cross_build_dpdk_for_riscv.rst
+F: lib/eal/riscv/
+
Intel x86
M: Bruce Richardson <bruce.richardson@intel.com>
M: Konstantin Ananyev <konstantin.v.ananyev@yandex.ru>
@@ -1,5 +1,8 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2015 Cavium, Inc
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
*/
#ifndef _TEST_XMMT_OPS_H_
@@ -49,6 +52,19 @@ vect_set_epi32(int i3, int i2, int i1, int i0)
return data;
}
+#elif defined(RTE_ARCH_RISCV)
+
+#define vect_loadu_sil128(p) vect_load_128(p)
+
+/* sets the 4 signed 32-bit integer values and returns the xmm_t variable */
+static __rte_always_inline xmm_t
+vect_set_epi32(int i3, int i2, int i1, int i0)
+{
+ xmm_t data = (xmm_t){i0, i1, i2, i3};
+
+ return data;
+}
+
#endif
#endif /* _TEST_XMMT_OPS_H_ */
@@ -121,6 +121,8 @@ if cpu_instruction_set == 'generic'
cpu_instruction_set = 'generic'
elif host_machine.cpu_family().startswith('ppc')
cpu_instruction_set = 'power8'
+ elif host_machine.cpu_family().startswith('riscv')
+ cpu_instruction_set = 'riscv'
endif
endif
new file mode 100644
@@ -0,0 +1,143 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2017 Intel Corporation.
+# Copyright(c) 2017 Cavium, Inc
+# Copyright(c) 2021 PANTHEON.tech s.r.o.
+# Copyright(c) 2022 StarFive
+# Copyright(c) 2022 SiFive
+# Copyright(c) 2022 Semihalf
+
+if not is_linux
+ error('Only Linux is supported at this point in time.')
+endif
+
+if not dpdk_conf.get('RTE_ARCH_64')
+ error('Only 64-bit compiles are supported for this platform type')
+endif
+
+dpdk_conf.set('RTE_ARCH', 'riscv')
+dpdk_conf.set('RTE_ARCH_RISCV', 1)
+dpdk_conf.set('RTE_FORCE_INTRINSICS', 1)
+
+# common flags to all riscv builds, with lowest priority
+flags_common = [
+ ['RTE_ARCH_RISCV', true],
+ ['RTE_CACHE_LINE_SIZE', 64],
+ # Set this to true if target emulates U-mode TIME CSR via M or S mode trap.
+ # This allows to remove a FENCE on rte_rdtsc_precise() as trap effectively
+ # acts as one.
+ ['RTE_RISCV_EMU_UTIME', false],
+ # Set this to true if target emulates U-mode CYCLE CSR via M or S mode trap.
+ # This allows to remove a FENCE on rte_rdtsc_precise() as trap effectively
+ # acts as one.
+ ['RTE_RISCV_EMU_UCYCLE', false],
+ # Manually set wall time clock frequency for the target. If 0, then it is
+ # read from /proc/device-tree/cpus/timebase-frequency. This property is
+ # guaranteed on Linux, as riscv time_init() requires it.
+ ['RTE_RISCV_TIME_FREQ', 0],
+]
+
+## SoC-specific options.
+# The priority is like this: arch > vendor > common.
+#
+# Note that currently there's no way of getting vendor/microarchitecture id
+# values in userspace which is why the logic of choosing the right flag
+# combination is strictly based on the values passed from a cross-file.
+vendor_generic = {
+ 'description': 'Generic RISC-V',
+ 'flags': [
+ ['RTE_MACHINE', '"riscv"'],
+ ['RTE_USE_C11_MEM_MODEL', true],
+ ['RTE_MAX_LCORE', 128],
+ ['RTE_MAX_NUMA_NODES', 2]
+ ],
+ 'arch_config': {
+ 'generic': {'machine_args': ['-march=rv64gc']}
+ }
+}
+
+arch_config_riscv = {
+ '0x8000000000000007': {
+ 'machine_args': ['-march=rv64gc', '-mtune=sifive-7-series'],
+ 'flags': [
+ ['RTE_RISCV_EMU_UTIME', true],
+ ['RTE_RISCV_EMU_UCYCLE', true]
+ ]
+ },
+}
+
+vendor_sifive = {
+ 'description': 'SiFive',
+ 'flags': [
+ ['RTE_MACHINE', '"riscv"'],
+ ['RTE_USE_C11_MEM_MODEL', true],
+ ['RTE_MAX_LCORE', 4],
+ ['RTE_MAX_NUMA_NODES', 1],
+ ],
+ 'arch_config': arch_config_riscv
+}
+
+vendors = {
+ 'generic': vendor_generic,
+ '0x489': vendor_sifive
+}
+
+# Native/cross vendor/arch detection
+if not meson.is_cross_build()
+ if machine == 'default'
+ # default build
+ vendor_id = 'generic'
+ arch_id = 'generic'
+ message('generic RISC-V')
+ else
+ vendor_id = 'generic'
+ arch_id = 'generic'
+ warning('RISC-V arch discovery not available, using generic!')
+ endif
+else
+ # cross build
+ vendor_id = meson.get_cross_property('vendor_id')
+ arch_id = meson.get_cross_property('arch_id')
+endif
+
+if vendors.has_key(vendor_id)
+ vendor_config = vendors[vendor_id]
+else
+ error('Unsupported RISC-V vendor: @0@. '.format(vendor_id) +
+ 'Please add support for it or use the generic ' +
+ '(-Dmachine=generic) build.')
+endif
+
+message('RISC-V vendor: ' + vendor_config['description'])
+message('RISC-V architecture id: ' + arch_id)
+
+arch_config = vendor_config['arch_config']
+if arch_config.has_key(arch_id)
+ # use the specified arch_id machine args if found
+ arch_config = arch_config[arch_id]
+else
+ # unknown micro-architecture id
+ error('Unsupported architecture @0@ of vendor @1@. '
+ .format(arch_id, vendor_id) +
+ 'Please add support for it or use the generic ' +
+ '(-Dmachine=generic) build.')
+endif
+
+# Concatenate flags respecting priorities.
+dpdk_flags = flags_common + vendor_config['flags'] + arch_config.get('flags', [])
+
+# apply supported machine args
+machine_args = [] # Clear previous machine args
+foreach flag: arch_config['machine_args']
+ if cc.has_argument(flag)
+ machine_args += flag
+ endif
+endforeach
+
+# apply flags
+foreach flag: dpdk_flags
+ if flag.length() > 0
+ dpdk_conf.set(flag[0], flag[1])
+ endif
+endforeach
+message('Using machine args: @0@'.format(machine_args))
+
new file mode 100644
@@ -0,0 +1,17 @@
+[binaries]
+c = 'riscv64-linux-gnu-gcc'
+cpp = 'riscv64-linux-gnu-g++'
+ar = 'riscv64-linux-gnu-ar'
+strip = 'riscv64-linux-gnu-strip'
+pcap-config = ''
+pkgconfig = 'riscv64-linux-gnu-pkg-config'
+
+[host_machine]
+system = 'linux'
+cpu_family = 'riscv64'
+cpu = 'rv64gc'
+endian = 'little'
+
+[properties]
+vendor_id = 'generic'
+arch_id = 'generic'
new file mode 100644
@@ -0,0 +1,19 @@
+[binaries]
+c = 'riscv64-unknown-linux-gnu-gcc'
+cpp = 'riscv64-unknown-linux-gnu-g++'
+ar = 'riscv64-unknown-linux-gnu-ar'
+strip = 'riscv64-unknown-linux-gnu-strip'
+pcap-config = ''
+pkgconfig = 'riscv64-unknown-linux-gnu-pkg-config'
+
+[host_machine]
+system = 'linux'
+cpu_family = 'riscv64'
+cpu = 'rv64gc'
+endian = 'little'
+
+[properties]
+vendor_id = '0x489'
+arch_id = '0x8000000000000007'
+max_lcores = 4
+max_numa_nodes = 1
@@ -42,7 +42,7 @@ Per Architecture Sources
The following macro options can be used:
* ``RTE_ARCH`` is a string that contains the name of the architecture.
-* ``RTE_ARCH_I686``, ``RTE_ARCH_X86_64``, ``RTE_ARCH_X86_X32``, ``RTE_ARCH_PPC_64``, ``RTE_ARCH_ARM``, ``RTE_ARCH_ARMv7`` or ``RTE_ARCH_ARM64`` are defined only if we are building for those architectures.
+* ``RTE_ARCH_I686``, ``RTE_ARCH_X86_64``, ``RTE_ARCH_X86_X32``, ``RTE_ARCH_PPC_64``, ``RTE_ARCH_RISCV``, ``RTE_ARCH_ARM``, ``RTE_ARCH_ARMv7`` or ``RTE_ARCH_ARM64`` are defined only if we are building for those architectures.
Per Execution Environment Sources
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
new file mode 100644
@@ -0,0 +1,125 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2020 ARM Corporation.
+ Copyright(c) 2022 StarFive
+ Copyright(c) 2022 SiFive
+ Copyright(c) 2022 Semihalf
+
+Cross compiling DPDK for RISC-V
+===============================
+
+This chapter describes how to cross compile DPDK for RISC-V from x86 build
+hosts.
+
+.. note::
+
+ While it's possible to compile DPDK natively on a RISC-V host, it is
+ currently recommended to cross-compile as Linux kernel does not offer any
+ way for userspace to discover the vendor and architecture identifiers of the
+ CPU and therefore any per-chip optimization options have to be chosen via
+ a cross-file or ``c_args``.
+
+
+Prerequisites
+-------------
+
+
+Linux kernel
+~~~~~~~~~~~~
+
+It is recommended to use Linux kernel built from
+`SiFive Freedom Unleashed SDK <https://github.com/sifive/freedom-u-sdk>`_.
+
+
+Meson prerequisites
+~~~~~~~~~~~~~~~~~~~
+
+Meson depends on pkgconfig to find the dependencies.
+The package ``pkg-config-riscv64-linux-gnu`` is required for RISC-V.
+To install it in Ubuntu::
+
+ sudo apt install pkg-config-riscv64-linux-gnu
+
+
+GNU toolchain
+-------------
+
+
+Obtain the cross toolchain
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The build process was tested using:
+
+* Ubuntu toolchain (the ``crossbuild-essential-riscv64`` package).
+
+* Latest `RISC-V GNU toolchain
+ <https://github.com/riscv/riscv-gnu-toolchain/releases>`_ on Ubuntu or Arch
+ Linux.
+
+Alternatively the toolchain may be built straight from the source, to do that
+follow the instructions on the riscv-gnu-toolchain github page.
+
+
+Unzip and add into the PATH
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This step is only required for the riscv-gnu-toolchain. The Ubuntu toolchain is
+in the PATH already.
+
+.. code-block:: console
+
+ tar -xvf riscv64-glibc-ubuntu-20.04-<version>.tar.gz
+ export PATH=$PATH:<cross_install_dir>/riscv/bin
+
+
+Cross Compiling DPDK with GNU toolchain using Meson
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To cross-compile DPDK for a desired target machine use the following command::
+
+ meson cross-build --cross-file <target_machine_configuration>
+ ninja -C cross-build
+
+For example if the target machine is a generic rv64gc RISC-V, use the following
+command::
+
+ meson riscv64-build-gcc --cross-file config/riscv/riscv64_linux_gcc
+ ninja -C riscv64-build-gcc
+
+If riscv-gnu-toolchain is used, binary names should be updated to match. Update the following lines in the cross-file:
+
+.. code-block:: console
+
+ [binaries]
+ c = 'riscv64-unknown-linux-gnu-gcc'
+ cpp = 'riscv64-unknown-linux-gnu-g++'
+ ar = 'riscv64-unknown-linux-gnu-ar'
+ strip = 'riscv64-unknown-linux-gnu-strip'
+ ...
+
+Some toolchains (such as freedom-u-sdk one) require also setting ``--sysroot``,
+otherwise include paths might not be resolved. To do so, add the appropriate
+paths to the cross-file:
+
+.. code-block:: console
+
+ [properties]
+ ...
+ c_args = ['--sysroot', '<path/to/toolchain/sysroot>']
+ cpp_args = c_args
+ c_link_args = ['--sysroot', '<path/to/toolchain/sysroot>']
+ cpp_link_args = c_link_args
+ ...
+
+
+Supported cross-compilation targets
+-----------------------------------
+
+Currently the following targets are supported:
+
+* Generic rv64gc ISA: ``config/riscv/riscv64_linux_gcc``
+
+* SiFive U740 SoC: ``config/riscv/riscv64_sifive_u740_linux_gcc``
+
+To add a new target support, ``config/riscv/meson.build`` has to be modified by
+adding a new vendor/architecture id and a corresponding cross-file has to be
+added to ``config/riscv`` directory.
@@ -14,6 +14,7 @@ Getting Started Guide for Linux
sys_reqs
build_dpdk
cross_build_dpdk_for_arm64
+ cross_build_dpdk_for_riscv
linux_drivers
build_sample_apps
linux_eal_parameters
@@ -855,6 +855,11 @@ x86-64
Support 64bits x86 architecture.
+rv64
+----
+
+Support 64-bit RISC-V architecture.
+
.. _nic_features_usage_doc:
@@ -74,6 +74,7 @@ ARMv8 =
Power8 =
x86-32 =
x86-64 =
+rv64 =
Usage doc =
Design doc =
Perf doc =
@@ -55,6 +55,14 @@ New Features
Also, make sure to start the actual text at the margin.
=======================================================
+* **Added initial RISC-V architecture support.***
+
+ Added EAL implementation for RISC-V architecture. The initial device the
+ porting was tested on is a HiFive Unmatched development board based on the
+ SiFive Freedom U740 SoC. In theory this implementation should work with any
+ ``rv64gc`` ISA compatible implementation with MMU supporting a reasonable
+ address space size (U740 uses sv39 MMU).
+
* **Updated Intel iavf driver.**
* Added Tx QoS queue rate limitation support.
@@ -1,6 +1,12 @@
# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2017 Intel Corporation
+if arch_subdir == 'riscv'
+ build = false
+ reason = 'riscv arch not supported'
+ subdir_done()
+endif
+
cflags += ['-DPF_DRIVER',
'-DVF_DRIVER',
'-DINTEGRATED_VF',
@@ -1,6 +1,12 @@
# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2017 Intel Corporation
+if arch_subdir == 'riscv'
+ build = false
+ reason = 'riscv arch not supported'
+ subdir_done()
+endif
+
cflags += ['-DRTE_LIBRTE_IXGBE_BYPASS']
subdir('base')
@@ -5,6 +5,11 @@ if not is_linux
build = false
reason = 'only supported on Linux'
endif
+if arch_subdir == 'riscv'
+ build = false
+ reason = 'riscv arch not supported'
+ subdir_done()
+endif
sources = files(
'memif_socket.c',
@@ -5,6 +5,11 @@ if not is_linux
build = false
reason = 'only supported on Linux'
endif
+if arch_subdir == 'riscv'
+ build = false
+ reason = 'riscv arch not supported'
+ subdir_done()
+endif
sources = files(
'rte_eth_tap.c',
'tap_bpf_api.c',
@@ -6,6 +6,12 @@
# To build this example as a standalone application with an already-installed
# DPDK instance, use 'make'
+if dpdk_conf.has('RTE_ARCH_RISCV')
+ build = false
+ reason = 'riscv arch not supported'
+ subdir_done()
+endif
+
allow_experimental_apis = true
deps += ['hash', 'lpm', 'fib', 'eventdev']
sources = files(
new file mode 100644
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2022 StarFive
+# Copyright(c) 2022 SiFive
+# Copyright(c) 2022 Semihalf
+
+arch_headers = files(
+ 'rte_atomic.h',
+ 'rte_byteorder.h',
+ 'rte_cpuflags.h',
+ 'rte_cycles.h',
+ 'rte_io.h',
+ 'rte_mcslock.h',
+ 'rte_memcpy.h',
+ 'rte_pause.h',
+ 'rte_pflock.h',
+ 'rte_power_intrinsics.h',
+ 'rte_prefetch.h',
+ 'rte_rwlock.h',
+ 'rte_spinlock.h',
+ 'rte_ticketlock.h',
+ 'rte_vect.h',
+)
+install_headers(arch_headers, subdir: get_option('include_subdir_arch'))
new file mode 100644
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ * All rights reserved.
+ */
+
+#ifndef RTE_ATOMIC_RISCV_H
+#define RTE_ATOMIC_RISCV_H
+
+#ifndef RTE_FORCE_INTRINSICS
+# error Platform must be built with RTE_FORCE_INTRINSICS
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdint.h>
+#include <rte_common.h>
+#include <rte_config.h>
+#include "generic/rte_atomic.h"
+
+#define rte_mb() asm volatile("fence rw, rw" : : : "memory")
+
+#define rte_wmb() asm volatile("fence w, w" : : : "memory")
+
+#define rte_rmb() asm volatile("fence r, r" : : : "memory")
+
+#define rte_smp_mb() rte_mb()
+
+#define rte_smp_wmb() rte_wmb()
+
+#define rte_smp_rmb() rte_rmb()
+
+#define rte_io_mb() asm volatile("fence iorw, iorw" : : : "memory")
+
+#define rte_io_wmb() asm volatile("fence orw, ow" : : : "memory")
+
+#define rte_io_rmb() asm volatile("fence ir, ir" : : : "memory")
+
+static __rte_always_inline void
+rte_atomic_thread_fence(int memorder)
+{
+ __atomic_thread_fence(memorder);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_ATOMIC_RISCV_H */
new file mode 100644
@@ -0,0 +1,44 @@
+/*
+ * SPDX-License-Identifier: BSD-3-Clause
+ * Inspired from FreeBSD src/sys/powerpc/include/endian.h
+ * Copyright(c) 1987, 1991, 1993
+ * The Regents of the University of California. All rights reserved.
+ */
+
+#ifndef RTE_BYTEORDER_RISCV_H
+#define RTE_BYTEORDER_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdint.h>
+#include <rte_common.h>
+#include "generic/rte_byteorder.h"
+
+#ifndef RTE_BYTE_ORDER
+#define RTE_BYTE_ORDER RTE_LITTLE_ENDIAN
+#endif
+
+#define rte_cpu_to_le_16(x) (x)
+#define rte_cpu_to_le_32(x) (x)
+#define rte_cpu_to_le_64(x) (x)
+
+#define rte_cpu_to_be_16(x) rte_bswap16(x)
+#define rte_cpu_to_be_32(x) rte_bswap32(x)
+#define rte_cpu_to_be_64(x) rte_bswap64(x)
+
+#define rte_le_to_cpu_16(x) (x)
+#define rte_le_to_cpu_32(x) (x)
+#define rte_le_to_cpu_64(x) (x)
+
+#define rte_be_to_cpu_16(x) rte_bswap16(x)
+#define rte_be_to_cpu_32(x) rte_bswap32(x)
+#define rte_be_to_cpu_64(x) rte_bswap64(x)
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_BYTEORDER_RISCV_H */
new file mode 100644
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2014 IBM Corporation
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_CPUFLAGS_RISCV_H
+#define RTE_CPUFLAGS_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Enumeration of all CPU features supported
+ */
+enum rte_cpu_flag_t {
+ RTE_CPUFLAG_RISCV_ISA_A, /* Atomic */
+ RTE_CPUFLAG_RISCV_ISA_B, /* Bit-Manipulation */
+ RTE_CPUFLAG_RISCV_ISA_C, /* Compressed instruction */
+ RTE_CPUFLAG_RISCV_ISA_D, /* Double precision floating-point */
+ RTE_CPUFLAG_RISCV_ISA_E, /* RV32E ISA */
+ RTE_CPUFLAG_RISCV_ISA_F, /* Single precision floating-point */
+ RTE_CPUFLAG_RISCV_ISA_G, /* Extension pack (IMAFD, Zicsr, Zifencei) */
+ RTE_CPUFLAG_RISCV_ISA_H, /* Hypervisor */
+ RTE_CPUFLAG_RISCV_ISA_I, /* RV32I/RV64I/IRV128I base ISA */
+ RTE_CPUFLAG_RISCV_ISA_J, /* Dynamic Translation Language */
+ RTE_CPUFLAG_RISCV_ISA_K, /* Reserved */
+ RTE_CPUFLAG_RISCV_ISA_L, /* Decimal Floating-Point */
+ RTE_CPUFLAG_RISCV_ISA_M, /* Integer Multiply/Divide */
+ RTE_CPUFLAG_RISCV_ISA_N, /* User-level interrupts */
+ RTE_CPUFLAG_RISCV_ISA_O, /* Reserved */
+ RTE_CPUFLAG_RISCV_ISA_P, /* Packed-SIMD */
+ RTE_CPUFLAG_RISCV_ISA_Q, /* Quad-precision floating-points */
+ RTE_CPUFLAG_RISCV_ISA_R, /* Reserved */
+ RTE_CPUFLAG_RISCV_ISA_S, /* Supervisor mode */
+ RTE_CPUFLAG_RISCV_ISA_T, /* Transactional memory */
+ RTE_CPUFLAG_RISCV_ISA_U, /* User mode */
+ RTE_CPUFLAG_RISCV_ISA_V, /* Vector */
+ RTE_CPUFLAG_RISCV_ISA_W, /* Reserved */
+ RTE_CPUFLAG_RISCV_ISA_X, /* Non-standard extension present */
+ RTE_CPUFLAG_RISCV_ISA_Y, /* Reserved */
+ RTE_CPUFLAG_RISCV_ISA_Z, /* Reserved */
+ /* The last item */
+ RTE_CPUFLAG_NUMFLAGS,/**< This should always be the last! */
+};
+
+#include "generic/rte_cpuflags.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_CPUFLAGS_RISCV_H */
new file mode 100644
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015 Cavium, Inc
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_CYCLES_RISCV_H
+#define RTE_CYCLES_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_cycles.h"
+
+#ifndef RTE_RISCV_RDTSC_USE_HPM
+#define RTE_RISCV_RDTSC_USE_HPM 0
+#endif
+
+#define RV64_CSRR(reg, value) \
+ asm volatile("csrr %0, " #reg : "=r" (value) : : "memory")
+
+/** Read wall time counter */
+static __rte_always_inline uint64_t
+__rte_riscv_rdtime(void)
+{
+ uint64_t tsc;
+ RV64_CSRR(time, tsc);
+ return tsc;
+}
+
+/** Read wall time counter ensuring no re-ordering */
+static __rte_always_inline uint64_t
+__rte_riscv_rdtime_precise(void)
+{
+#if !defined(RTE_RISCV_EMU_UTIME)
+ asm volatile("fence" : : : "memory");
+#endif
+ return __rte_riscv_rdtime();
+}
+
+/** Read hart cycle counter */
+static __rte_always_inline uint64_t
+__rte_riscv_rdcycle(void)
+{
+ uint64_t tsc;
+ RV64_CSRR(cycle, tsc);
+ return tsc;
+}
+
+/** Read hart cycle counter ensuring no re-ordering */
+static __rte_always_inline uint64_t
+__rte_riscv_rdcycle_precise(void)
+{
+#if !defined(RTE_RISCV_EMU_UCYCLE)
+ asm volatile("fence" : : : "memory");
+#endif
+ return __rte_riscv_rdcycle();
+}
+
+/**
+ * Read the time base register.
+ *
+ * @return
+ * The time base for this lcore.
+ */
+static __rte_always_inline uint64_t
+rte_rdtsc(void)
+{
+ /**
+ * By default TIME userspace counter is used. Although it's frequency
+ * may not be enough for all applications.
+ */
+ if (!RTE_RISCV_RDTSC_USE_HPM)
+ return __rte_riscv_rdtime();
+ /**
+ * Alternatively HPM's CYCLE counter may be used. However this counter
+ * is not guaranteed by ISA to either be stable frequency or always
+ * enabled for userspace access (it may trap to kernel or firmware).
+ */
+ return __rte_riscv_rdcycle();
+}
+
+static inline uint64_t
+rte_rdtsc_precise(void)
+{
+ if (!RTE_RISCV_RDTSC_USE_HPM)
+ return __rte_riscv_rdtime_precise();
+ return __rte_riscv_rdcycle_precise();
+}
+
+static __rte_always_inline uint64_t
+rte_get_tsc_cycles(void)
+{
+ return rte_rdtsc();
+}
+
+#undef RV64_CSRR
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_CYCLES_RISCV_H */
new file mode 100644
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2016 Cavium, Inc
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_IO_RISCV_H
+#define RTE_IO_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_io.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_IO_RISCV_H */
new file mode 100644
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Arm Limited
+ */
+
+#ifndef RTE_MCSLOCK_RISCV_H
+#define RTE_MCSLOCK_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_mcslock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_MCSLOCK_RISCV_H */
new file mode 100644
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_MEMCPY_RISCV_H
+#define RTE_MEMCPY_RISCV_H
+
+#include <stdint.h>
+#include <string.h>
+
+#include "rte_common.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_memcpy.h"
+
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 16);
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 32);
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 48);
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 64);
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 128);
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+ memcpy(dst, src, 256);
+}
+
+#define rte_memcpy(d, s, n) memcpy((d), (s), (n))
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_MEMCPY_RISCV_H */
new file mode 100644
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_PAUSE_RISCV_H
+#define RTE_PAUSE_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "rte_atomic.h"
+
+#include "generic/rte_pause.h"
+
+static inline void rte_pause(void)
+{
+ /* Insert pause hint directly to be compatible with old compilers.
+ * This will work even on platforms without Zihintpause extension
+ * because this is a FENCE hint instruction which evaluates to NOP then.
+ */
+ asm volatile(".int 0x0100000F"::: "memory");
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_PAUSE_RISCV_H */
new file mode 100644
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Microsoft Corporation
+ */
+#ifndef RTE_PFLOCK_RISCV_H
+#define RTE_PFLOCK_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_pflock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_PFLOCK_RISCV_H */
new file mode 100644
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_POWER_INTRINSIC_RISCV_H
+#define RTE_POWER_INTRINSIC_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+
+#include "generic/rte_power_intrinsics.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_POWER_INTRINSIC_RISCV_H */
new file mode 100644
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2014 IBM Corporation
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_PREFETCH_RISCV_H
+#define RTE_PREFETCH_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_prefetch.h"
+
+static inline void rte_prefetch0(const volatile void *p)
+{
+ RTE_SET_USED(p);
+}
+
+static inline void rte_prefetch1(const volatile void *p)
+{
+ RTE_SET_USED(p);
+}
+
+static inline void rte_prefetch2(const volatile void *p)
+{
+ RTE_SET_USED(p);
+}
+
+static inline void rte_prefetch_non_temporal(const volatile void *p)
+{
+ /* non-temporal version not available, fallback to rte_prefetch0 */
+ rte_prefetch0(p);
+}
+
+__rte_experimental
+static inline void
+rte_cldemote(const volatile void *p)
+{
+ RTE_SET_USED(p);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_PREFETCH_RISCV_H */
new file mode 100644
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_RWLOCK_RISCV_H
+#define RTE_RWLOCK_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_rwlock.h"
+
+static inline void
+rte_rwlock_read_lock_tm(rte_rwlock_t *rwl)
+{
+ rte_rwlock_read_lock(rwl);
+}
+
+static inline void
+rte_rwlock_read_unlock_tm(rte_rwlock_t *rwl)
+{
+ rte_rwlock_read_unlock(rwl);
+}
+
+static inline void
+rte_rwlock_write_lock_tm(rte_rwlock_t *rwl)
+{
+ rte_rwlock_write_lock(rwl);
+}
+
+static inline void
+rte_rwlock_write_unlock_tm(rte_rwlock_t *rwl)
+{
+ rte_rwlock_write_unlock(rwl);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_RWLOCK_RISCV_H */
new file mode 100644
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015 RehiveTech. All rights reserved.
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_SPINLOCK_RISCV_H
+#define RTE_SPINLOCK_RISCV_H
+
+#ifndef RTE_FORCE_INTRINSICS
+# error Platform must be built with RTE_FORCE_INTRINSICS
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_spinlock.h"
+
+static inline int rte_tm_supported(void)
+{
+ return 0;
+}
+
+static inline void
+rte_spinlock_lock_tm(rte_spinlock_t *sl)
+{
+ rte_spinlock_lock(sl); /* fall-back */
+}
+
+static inline int
+rte_spinlock_trylock_tm(rte_spinlock_t *sl)
+{
+ return rte_spinlock_trylock(sl);
+}
+
+static inline void
+rte_spinlock_unlock_tm(rte_spinlock_t *sl)
+{
+ rte_spinlock_unlock(sl);
+}
+
+static inline void
+rte_spinlock_recursive_lock_tm(rte_spinlock_recursive_t *slr)
+{
+ rte_spinlock_recursive_lock(slr); /* fall-back */
+}
+
+static inline void
+rte_spinlock_recursive_unlock_tm(rte_spinlock_recursive_t *slr)
+{
+ rte_spinlock_recursive_unlock(slr);
+}
+
+static inline int
+rte_spinlock_recursive_trylock_tm(rte_spinlock_recursive_t *slr)
+{
+ return rte_spinlock_recursive_trylock(slr);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_SPINLOCK_RISCV_H */
new file mode 100644
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Arm Limited
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_TICKETLOCK_RISCV_H
+#define RTE_TICKETLOCK_RISCV_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_ticketlock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_TICKETLOCK_RISCV_H */
new file mode 100644
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#ifndef RTE_VECT_RISCV_H
+#define RTE_VECT_RISCV_H
+
+#include <stdint.h>
+#include "generic/rte_vect.h"
+#include "rte_common.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define RTE_VECT_DEFAULT_SIMD_BITWIDTH RTE_VECT_SIMD_DISABLED
+
+typedef int32_t xmm_t __attribute__((vector_size(16)));
+
+#define XMM_SIZE (sizeof(xmm_t))
+#define XMM_MASK (XMM_SIZE - 1)
+
+typedef union rte_xmm {
+ xmm_t x;
+ uint8_t u8[XMM_SIZE / sizeof(uint8_t)];
+ uint16_t u16[XMM_SIZE / sizeof(uint16_t)];
+ uint32_t u32[XMM_SIZE / sizeof(uint32_t)];
+ uint64_t u64[XMM_SIZE / sizeof(uint64_t)];
+ double pd[XMM_SIZE / sizeof(double)];
+} __rte_aligned(8) rte_xmm_t;
+
+static inline xmm_t
+vect_load_128(void *p)
+{
+ xmm_t ret = *((xmm_t *)p);
+ return ret;
+}
+
+static inline xmm_t
+vect_and(xmm_t data, xmm_t mask)
+{
+ rte_xmm_t ret = (rte_xmm_t)data;
+ rte_xmm_t m = (rte_xmm_t)mask;
+ ret.u64[0] &= m.u64[0];
+ ret.u64[1] &= m.u64[1];
+ return ret.x;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_VECT_RISCV_H */
new file mode 100644
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2017 Intel Corporation.
+
+subdir('include')
+
+sources += files(
+ 'rte_cpuflags.c',
+ 'rte_cycles.c',
+ 'rte_hypervisor.c',
+ 'rte_power_intrinsics.c',
+)
new file mode 100644
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#include "rte_cpuflags.h"
+
+#include <elf.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+
+#ifndef AT_HWCAP
+#define AT_HWCAP 16
+#endif
+
+#ifndef AT_HWCAP2
+#define AT_HWCAP2 26
+#endif
+
+#ifndef AT_PLATFORM
+#define AT_PLATFORM 15
+#endif
+
+enum cpu_register_t {
+ REG_NONE = 0,
+ REG_HWCAP,
+ REG_HWCAP2,
+ REG_PLATFORM,
+ REG_MAX
+};
+
+typedef uint32_t hwcap_registers_t[REG_MAX];
+
+/**
+ * Struct to hold a processor feature entry
+ */
+struct feature_entry {
+ uint32_t reg;
+ uint32_t bit;
+#define CPU_FLAG_NAME_MAX_LEN 64
+ char name[CPU_FLAG_NAME_MAX_LEN];
+};
+
+#define FEAT_DEF(name, reg, bit) \
+ [RTE_CPUFLAG_##name] = {reg, bit, #name},
+
+typedef Elf64_auxv_t _Elfx_auxv_t;
+
+const struct feature_entry rte_cpu_feature_table[] = {
+ FEAT_DEF(RISCV_ISA_A, REG_HWCAP, 0)
+ FEAT_DEF(RISCV_ISA_B, REG_HWCAP, 1)
+ FEAT_DEF(RISCV_ISA_C, REG_HWCAP, 2)
+ FEAT_DEF(RISCV_ISA_D, REG_HWCAP, 3)
+ FEAT_DEF(RISCV_ISA_E, REG_HWCAP, 4)
+ FEAT_DEF(RISCV_ISA_F, REG_HWCAP, 5)
+ FEAT_DEF(RISCV_ISA_G, REG_HWCAP, 6)
+ FEAT_DEF(RISCV_ISA_H, REG_HWCAP, 7)
+ FEAT_DEF(RISCV_ISA_I, REG_HWCAP, 8)
+ FEAT_DEF(RISCV_ISA_J, REG_HWCAP, 9)
+ FEAT_DEF(RISCV_ISA_K, REG_HWCAP, 10)
+ FEAT_DEF(RISCV_ISA_L, REG_HWCAP, 11)
+ FEAT_DEF(RISCV_ISA_M, REG_HWCAP, 12)
+ FEAT_DEF(RISCV_ISA_N, REG_HWCAP, 13)
+ FEAT_DEF(RISCV_ISA_O, REG_HWCAP, 14)
+ FEAT_DEF(RISCV_ISA_P, REG_HWCAP, 15)
+ FEAT_DEF(RISCV_ISA_Q, REG_HWCAP, 16)
+ FEAT_DEF(RISCV_ISA_R, REG_HWCAP, 17)
+ FEAT_DEF(RISCV_ISA_S, REG_HWCAP, 18)
+ FEAT_DEF(RISCV_ISA_T, REG_HWCAP, 19)
+ FEAT_DEF(RISCV_ISA_U, REG_HWCAP, 20)
+ FEAT_DEF(RISCV_ISA_V, REG_HWCAP, 21)
+ FEAT_DEF(RISCV_ISA_W, REG_HWCAP, 22)
+ FEAT_DEF(RISCV_ISA_X, REG_HWCAP, 23)
+ FEAT_DEF(RISCV_ISA_Y, REG_HWCAP, 24)
+ FEAT_DEF(RISCV_ISA_Z, REG_HWCAP, 25)
+};
+/*
+ * Read AUXV software register and get cpu features for ARM
+ */
+static void
+rte_cpu_get_features(hwcap_registers_t out)
+{
+ out[REG_HWCAP] = rte_cpu_getauxval(AT_HWCAP);
+ out[REG_HWCAP2] = rte_cpu_getauxval(AT_HWCAP2);
+}
+
+/*
+ * Checks if a particular flag is available on current machine.
+ */
+int
+rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
+{
+ const struct feature_entry *feat;
+ hwcap_registers_t regs = {0};
+
+ if (feature >= RTE_CPUFLAG_NUMFLAGS)
+ return -ENOENT;
+
+ feat = &rte_cpu_feature_table[feature];
+ if (feat->reg == REG_NONE)
+ return -EFAULT;
+
+ rte_cpu_get_features(regs);
+ return (regs[feat->reg] >> feat->bit) & 1;
+}
+
+const char *
+rte_cpu_get_flag_name(enum rte_cpu_flag_t feature)
+{
+ if (feature >= RTE_CPUFLAG_NUMFLAGS)
+ return NULL;
+ return rte_cpu_feature_table[feature].name;
+}
+
+void
+rte_cpu_get_intrinsics_support(struct rte_cpu_intrinsics *intrinsics)
+{
+ memset(intrinsics, 0, sizeof(*intrinsics));
+}
new file mode 100644
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2015 Cavium, Inc
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#include <stdio.h>
+
+#include "eal_private.h"
+#include "rte_byteorder.h"
+#include "rte_cycles.h"
+#include "rte_log.h"
+
+/** Read generic counter frequency */
+static uint64_t
+__rte_riscv_timefrq(void)
+{
+#define TIMEBASE_FREQ_SIZE 8
+ if (RTE_RISCV_TIME_FREQ > 0)
+ return RTE_RISCV_TIME_FREQ;
+ uint8_t buf[TIMEBASE_FREQ_SIZE];
+ ssize_t cnt;
+ FILE *file;
+
+ file = fopen("/proc/device-tree/cpus/timebase-frequency", "rb");
+ if (!file)
+ goto fail;
+
+ cnt = fread(buf, 1, TIMEBASE_FREQ_SIZE, file);
+ fclose(file);
+ switch (cnt) {
+ case 8:
+ return rte_be_to_cpu_64(*(uint64_t *)buf);
+ case 4:
+ return rte_be_to_cpu_32(*(uint32_t *)buf);
+ default:
+ break;
+ }
+fail:
+ RTE_LOG(WARNING, EAL, "Unable to read timebase-frequency from FDT.\n");
+ return 0;
+}
+
+uint64_t
+get_tsc_freq_arch(void)
+{
+ RTE_LOG(NOTICE, EAL, "TSC using RISC-V %s.\n",
+ RTE_RISCV_RDTSC_USE_HPM ? "rdcycle" : "rdtime");
+ if (!RTE_RISCV_RDTSC_USE_HPM)
+ return __rte_riscv_timefrq();
+#define CYC_PER_1MHZ 1E6
+ /*
+ * Use real time clock to estimate current cycle frequency
+ */
+ uint64_t ticks, frq;
+ uint64_t start_ticks, cur_ticks;
+ uint64_t start_cycle, end_cycle;
+
+ /* Do not proceed unless clock frequency can be obtained. */
+ frq = __rte_riscv_timefrq();
+ if (!frq)
+ return 0;
+
+ /* Number of ticks for 1/10 second */
+ ticks = frq / 10;
+
+ start_ticks = __rte_riscv_rdtime_precise();
+ start_cycle = rte_rdtsc_precise();
+ do {
+ cur_ticks = __rte_riscv_rdtime();
+ } while ((cur_ticks - start_ticks) < ticks);
+ end_cycle = rte_rdtsc_precise();
+
+ /* Adjust the cycles to next 1Mhz */
+ return RTE_ALIGN_MUL_CEIL((end_cycle - start_cycle) * 10, CYC_PER_1MHZ);
+}
new file mode 100644
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#include "rte_hypervisor.h"
+
+enum rte_hypervisor
+rte_hypervisor_get(void)
+{
+ return RTE_HYPERVISOR_UNKNOWN;
+}
new file mode 100644
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 StarFive
+ * Copyright(c) 2022 SiFive
+ * Copyright(c) 2022 Semihalf
+ */
+
+#include "rte_power_intrinsics.h"
+
+/**
+ * This function is not supported on RISC-V 64
+ */
+int
+rte_power_monitor(const struct rte_power_monitor_cond *pmc,
+ const uint64_t tsc_timestamp)
+{
+ RTE_SET_USED(pmc);
+ RTE_SET_USED(tsc_timestamp);
+
+ return -ENOTSUP;
+}
+
+/**
+ * This function is not supported on RISC-V 64
+ */
+int
+rte_power_pause(const uint64_t tsc_timestamp)
+{
+ RTE_SET_USED(tsc_timestamp);
+
+ return -ENOTSUP;
+}
+
+/**
+ * This function is not supported on RISC-V 64
+ */
+int
+rte_power_monitor_wakeup(const unsigned int lcore_id)
+{
+ RTE_SET_USED(lcore_id);
+
+ return -ENOTSUP;
+}
+
+/**
+ * This function is not supported on RISC-V 64
+ */
+int
+rte_power_monitor_multi(const struct rte_power_monitor_cond pmc[],
+ const uint32_t num, const uint64_t tsc_timestamp)
+{
+ RTE_SET_USED(pmc);
+ RTE_SET_USED(num);
+ RTE_SET_USED(tsc_timestamp);
+
+ return -ENOTSUP;
+}
@@ -50,6 +50,8 @@ elif host_machine.cpu_family().startswith('arm') or host_machine.cpu_family().st
arch_subdir = 'arm'
elif host_machine.cpu_family().startswith('ppc')
arch_subdir = 'ppc'
+elif host_machine.cpu_family().startswith('riscv')
+ arch_subdir = 'riscv'
endif
# configure the build, and make sure configs here and in config folder are