* [v1 01/24] eal/loongarch: add atomic operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 15:52 ` Stephen Hemminger
2022-05-28 9:32 ` [v1 02/24] eal/loongarch: add byte order " Min Zhou
` (22 subsequent siblings)
23 siblings, 1 reply; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds architecture specific atomic operations for
LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_atomic.h | 401 +++++++++++++++++++++++++
1 file changed, 401 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_atomic.h
diff --git a/lib/eal/loongarch/include/rte_atomic.h b/lib/eal/loongarch/include/rte_atomic.h
new file mode 100644
index 0000000000..4c7526b85d
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_atomic.h
@@ -0,0 +1,401 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_ATOMIC_LOONGARCH_H_
+#define _RTE_ATOMIC_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdint.h>
+#include "generic/rte_atomic.h"
+
+/**
+ * LoongArch Synchronize
+ */
+static inline void synchronize(void)
+{
+ __asm__ __volatile__("dbar 0":::"memory");
+}
+
+/**
+ * General memory barrier.
+ *
+ * Guarantees that the LOAD and STORE operations generated before the
+ * barrier occur before the LOAD and STORE operations generated after.
+ * This function is architecture dependent.
+ */
+#define rte_mb() synchronize()
+
+/**
+ * Write memory barrier.
+ *
+ * Guarantees that the STORE operations generated before the barrier
+ * occur before the STORE operations generated after.
+ * This function is architecture dependent.
+ */
+#define rte_wmb() synchronize()
+
+/**
+ * Read memory barrier.
+ *
+ * Guarantees that the LOAD operations generated before the barrier
+ * occur before the LOAD operations generated after.
+ * This function is architecture dependent.
+ */
+#define rte_rmb() synchronize()
+
+#define rte_smp_mb() rte_mb()
+
+#define rte_smp_wmb() rte_mb()
+
+#define rte_smp_rmb() rte_mb()
+
+#define rte_io_mb() rte_mb()
+
+#define rte_io_wmb() rte_mb()
+
+#define rte_io_rmb() rte_mb()
+
+#define rte_io_mb() rte_mb()
+
+#define rte_cio_wmb() rte_wmb()
+
+#define rte_cio_rmb() rte_rmb()
+
+#define smp_mb__before_llsc()
+
+#define smp_llsc_mb()
+
+static __rte_always_inline void
+rte_atomic_thread_fence(int memorder)
+{
+ __atomic_thread_fence(memorder);
+}
+
+/*
+ * Helper Functions
+ */
+#define ATOMIC32_OP(op, I, asm_op) \
+static inline void la_atomic32_##op(rte_atomic32_t *v, int32_t i) \
+{ \
+ __asm__ __volatile__( \
+ "am"#asm_op"_db.w $zero, %[i], %[cnt]\n" \
+ : [cnt] "+ZB" (v->cnt) \
+ : [i] "r" (I) \
+ : "memory" \
+ ); \
+}
+
+#define ATOMIC32_OP_RETURN(op, I, asm_op) \
+static inline int32_t la_atomic32_##op##_and_return(rte_atomic32_t *v, int32_t i) \
+{ \
+ int32_t result; \
+ \
+ __asm__ __volatile__( \
+ "am"#asm_op"_db.w %1, %2, %0\n" \
+ : "+ZB" (v->cnt), "=&r" (result) \
+ : "r" (I) \
+ : "memory" \
+ ); \
+ \
+ return result + I; \
+}
+ATOMIC32_OP(add, i, add)
+ATOMIC32_OP(sub, -i, add)
+ATOMIC32_OP_RETURN(add, i, add)
+ATOMIC32_OP_RETURN(sub, -i, add)
+
+#define ATOMIC64_OP(op, I, asm_op) \
+static inline void la_atomic64_##op(rte_atomic64_t *v, int64_t i) \
+{ \
+ __asm__ __volatile__( \
+ "am"#asm_op"_db.d $zero, %[i], %[cnt]\n" \
+ : [cnt] "+ZB" (v->cnt) \
+ : [i] "r" (I) \
+ : "memory" \
+ ); \
+}
+#define ATOMIC64_OP_RETURN(op, I, asm_op) \
+static inline int64_t la_atomic64_##op##_and_return(rte_atomic64_t *v, int64_t i) \
+{ \
+ int64_t result; \
+ \
+ __asm__ __volatile__( \
+ "am"#asm_op"_db.d %1, %2, %0\n" \
+ : "+ZB" (v->cnt), "=&r" (result) \
+ : "r" (I) \
+ : "memory" \
+ ); \
+ \
+ return result + I; \
+}
+ATOMIC64_OP(add, i, add)
+ATOMIC64_OP(sub, -i, add)
+ATOMIC64_OP_RETURN(add, i, add)
+ATOMIC64_OP_RETURN(sub, -i, add)
+
+static inline int
+loongarch_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src)
+{
+ uint32_t res = 0, temp = 0;
+ __asm__ __volatile__(
+ "1: ll.w %[tmp], %[dst]\n"
+ " li.w %[res], 0\n"
+ " bne %[tmp], %[exp], 2f\n"
+ " move %[tmp], %[src]\n"
+ " sc.w %[tmp], %[dst]\n"
+ " li.w %[res], 1\n"
+ " beqz %[tmp], 1b\n"
+ "2:\n"
+ : [res] "=&r"(res),
+ [tmp] "+&r"(temp),
+ [dst] "+m"(*dst)
+ : [src] "r"(src),
+ [exp] "r"(exp),
+ "m"(*dst)
+ : "memory"
+ );
+
+ return res;
+}
+
+static inline int
+loongarch_atomic64_cmpset(volatile uint64_t *dst, uint64_t exp, uint64_t src)
+{
+ uint32_t res = 0;
+ uint64_t temp = 0;
+ __asm__ __volatile__(
+ "1: ll.d %[tmp], %[dst]\n"
+ " li.d %[res], 0\n"
+ " bne %[tmp], %[exp], 2f\n"
+ " move %[tmp], %[src]\n"
+ " sc.d %[tmp], %[dst]\n"
+ " li.d %[res], 1\n"
+ " beqz %[tmp], 1b\n"
+ "2:\n"
+ : [res] "=&r"(res),
+ [tmp] "+&r"(temp),
+ [dst] "+m"(*dst)
+ : [src] "r"(src),
+ [exp] "r"(exp),
+ "m"(*dst)
+ : "memory"
+ );
+
+ return res;
+}
+
+#ifndef RTE_FORCE_INTRINSICS
+static inline int
+rte_atomic16_cmpset(volatile uint16_t *dst, uint16_t exp, uint16_t src)
+{
+ return __sync_bool_compare_and_swap(dst, exp, src);
+}
+
+static inline int rte_atomic16_test_and_set(rte_atomic16_t *v)
+{
+ return rte_atomic16_cmpset((volatile uint16_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic16_inc(rte_atomic16_t *v)
+{
+ rte_atomic16_add(v, 1);
+}
+
+static inline void
+rte_atomic16_dec(rte_atomic16_t *v)
+{
+ rte_atomic16_sub(v, 1);
+}
+
+static inline int rte_atomic16_inc_and_test(rte_atomic16_t *v)
+{
+ return __sync_add_and_fetch(&v->cnt, 1) == 0;
+}
+
+static inline int rte_atomic16_dec_and_test(rte_atomic16_t *v)
+{
+ return __sync_sub_and_fetch(&v->cnt, 1) == 0;
+}
+
+static inline uint16_t
+rte_atomic16_exchange(volatile uint16_t *dst, uint16_t val)
+{
+ return __atomic_exchange_2(dst, val, __ATOMIC_SEQ_CST);
+}
+
+/*------------------------- 32 bit atomic operations -------------------------*/
+
+static inline int
+rte_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src)
+{
+ return loongarch_atomic32_cmpset(dst, exp, src);
+}
+
+static inline int rte_atomic32_test_and_set(rte_atomic32_t *v)
+{
+ return rte_atomic32_cmpset((volatile uint32_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic32_inc(rte_atomic32_t *v)
+{
+ la_atomic32_add(v, 1);
+}
+
+static inline void
+rte_atomic32_dec(rte_atomic32_t *v)
+{
+ la_atomic32_sub(v, 1);
+}
+
+static inline int rte_atomic32_inc_and_test(rte_atomic32_t *v)
+{
+ return la_atomic32_add_and_return(v, 1) == 0;
+}
+
+static inline int rte_atomic32_dec_and_test(rte_atomic32_t *v)
+{
+ return la_atomic32_sub_and_return(v, 1) == 0;
+}
+
+static inline uint32_t
+rte_atomic32_exchange(volatile uint32_t *dst, uint32_t val)
+{
+ uint32_t retval;
+
+ __asm__ __volatile__ (
+ "amswap_db.w %1, %z2, %0\n"
+ : "+ZB" (*dst), "=&r" (retval)
+ : "Jr" (val)
+ : "memory"
+ );
+
+ return retval;
+
+}
+/*------------------------- 64 bit atomic operations -------------------------*/
+static inline int
+rte_atomic64_cmpset(volatile uint64_t *dst, uint64_t exp, uint64_t src)
+{
+ return loongarch_atomic64_cmpset(dst, exp, src);
+}
+
+static inline void
+rte_atomic64_init(rte_atomic64_t *v)
+{
+ __asm__ __volatile__(
+ "amand_db.d $zero, $zero, %[rj]\n"
+ : [rj]"+ZB"(v->cnt)
+ );
+}
+
+static inline int64_t
+rte_atomic64_read(rte_atomic64_t *v)
+{
+ int64_t res = 0;
+
+ __asm__ __volatile__(
+ "amadd_db.d %[res], $zero, %[cnt]\n"
+ : [res]"=&r"(res), [cnt]"+ZB"(v->cnt)
+ :
+ );
+ return res;
+
+}
+
+static inline void
+rte_atomic64_set(rte_atomic64_t *v, int64_t new_value)
+{
+ __asm__ __volatile__(
+ "amswap_db.d $zero, %[nv], %[cnt]\n"
+ : [cnt]"+ZB"(v->cnt)
+ : [nv]"r"(new_value)
+ );
+}
+
+static inline void
+rte_atomic64_add(rte_atomic64_t *v, int64_t inc)
+{
+ la_atomic64_add(v, inc);
+}
+
+static inline void
+rte_atomic64_sub(rte_atomic64_t *v, int64_t dec)
+{
+ la_atomic64_sub(v, dec);
+}
+
+static inline void
+rte_atomic64_inc(rte_atomic64_t *v)
+{
+ la_atomic64_add(v, 1);
+}
+
+static inline void
+rte_atomic64_dec(rte_atomic64_t *v)
+{
+ la_atomic64_sub(v, 1);
+}
+
+static inline int64_t
+rte_atomic64_add_return(rte_atomic64_t *v, int64_t inc)
+{
+ return la_atomic64_add_and_return(v, inc);
+}
+
+static inline int64_t
+rte_atomic64_sub_return(rte_atomic64_t *v, int64_t dec)
+{
+ return la_atomic64_sub_and_return(v, dec);
+}
+
+static inline int rte_atomic64_inc_and_test(rte_atomic64_t *v)
+{
+ return la_atomic64_add_and_return(v, 1) == 0;
+}
+
+static inline int rte_atomic64_dec_and_test(rte_atomic64_t *v)
+{
+ return la_atomic64_sub_and_return(v, 1) == 0;
+}
+
+static inline int rte_atomic64_test_and_set(rte_atomic64_t *v)
+{
+ return rte_atomic64_cmpset((volatile uint64_t *)&v->cnt, 0, 1);
+}
+
+static inline void rte_atomic64_clear(rte_atomic64_t *v)
+{
+ rte_atomic64_set(v, 0);
+}
+
+static inline uint64_t __xchg_u64(volatile uint64_t *m, uint64_t val)
+{
+ uint64_t retval;
+ __asm__ __volatile__ (
+ "amswap_db.d %1, %z2, %0\n"
+ : "+ZB" (*m), "=&r" (retval)
+ : "Jr" (val)
+ : "memory"
+ );
+
+ return retval;
+}
+
+static inline uint64_t
+rte_atomic64_exchange(volatile uint64_t *dst, uint64_t val)
+{
+ return __xchg_u64(dst, val);
+}
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ATOMIC_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* Re: [v1 01/24] eal/loongarch: add atomic operations for LoongArch
2022-05-28 9:32 ` [v1 01/24] eal/loongarch: add atomic operations for LoongArch Min Zhou
@ 2022-05-28 15:52 ` Stephen Hemminger
2022-05-30 1:00 ` zhoumin
0 siblings, 1 reply; 29+ messages in thread
From: Stephen Hemminger @ 2022-05-28 15:52 UTC (permalink / raw)
To: Min Zhou
Cc: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev, dev,
maobibo
On Sat, 28 May 2022 17:32:48 +0800
Min Zhou <zhoumin@loongson.cn> wrote:
> This patch adds architecture specific atomic operations for
> LoongArch architecture.
>
> Signed-off-by: Min Zhou <zhoumin@loongson.cn>
DPDK has adopted std atomics. Could you please fix your toolchain
to support that instead.
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [v1 01/24] eal/loongarch: add atomic operations for LoongArch
2022-05-28 15:52 ` Stephen Hemminger
@ 2022-05-30 1:00 ` zhoumin
0 siblings, 0 replies; 29+ messages in thread
From: zhoumin @ 2022-05-30 1:00 UTC (permalink / raw)
To: Stephen Hemminger
Cc: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev, dev,
maobibo
[-- Attachment #1: Type: text/plain, Size: 498 bytes --]
Stephen,
Thanks for your comments! I'm evaluating the atomic operations of
LoongArch toolchain. An updated patch will come later.
On 2022/5/28 下午11:52, Stephen Hemminger wrote:
> On Sat, 28 May 2022 17:32:48 +0800
> Min Zhou<zhoumin@loongson.cn> wrote:
>
>> This patch adds architecture specific atomic operations for
>> LoongArch architecture.
>>
>> Signed-off-by: Min Zhou<zhoumin@loongson.cn>
> DPDK has adopted std atomics. Could you please fix your toolchain
> to support that instead.
[-- Attachment #2: Type: text/html, Size: 1143 bytes --]
^ permalink raw reply [flat|nested] 29+ messages in thread
* [v1 02/24] eal/loongarch: add byte order operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
2022-05-28 9:32 ` [v1 01/24] eal/loongarch: add atomic operations for LoongArch Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 03/24] eal/loongarch: add cpu cycle " Min Zhou
` (21 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds architecture specific byte order operations
for LoongArch architecture. LoongArch bit designations are
always little-endian.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_byteorder.h | 46 +++++++++++++++++++++++
1 file changed, 46 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_byteorder.h
diff --git a/lib/eal/loongarch/include/rte_byteorder.h b/lib/eal/loongarch/include/rte_byteorder.h
new file mode 100644
index 0000000000..2cda010256
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_byteorder.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_BYTEORDER_LOONGARCH_H_
+#define _RTE_BYTEORDER_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_byteorder.h"
+
+#ifndef RTE_FORCE_INTRINSICS
+#define rte_bswap16(x) rte_constant_bswap16(x)
+#define rte_bswap32(x) rte_constant_bswap32(x)
+#define rte_bswap64(x) rte_constant_bswap64(x)
+#endif
+
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
+#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)
+
+#else /* RTE_BIG_ENDIAN */
+#error "LoongArch not support big endian!"
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_BYTEORDER_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 03/24] eal/loongarch: add cpu cycle operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
2022-05-28 9:32 ` [v1 01/24] eal/loongarch: add atomic operations for LoongArch Min Zhou
2022-05-28 9:32 ` [v1 02/24] eal/loongarch: add byte order " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 04/24] eal/loongarch: add prefetch " Min Zhou
` (20 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds architecture specific cpu cycle operations for
LoongArch. The RDTIME.D instruction is used to read constant
frequency timer information including counter value. The CPUCFG
instruction is used to dynamically identify which features of
LoongArch are implemented in the running processor during the
execution of the software. We can use this instruction to calculate
the frequency used by the timer.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_cycles.h | 53 ++++++++++++++++++++++++++
lib/eal/loongarch/rte_cycles.c | 45 ++++++++++++++++++++++
2 files changed, 98 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_cycles.h
create mode 100644 lib/eal/loongarch/rte_cycles.c
diff --git a/lib/eal/loongarch/include/rte_cycles.h b/lib/eal/loongarch/include/rte_cycles.h
new file mode 100644
index 0000000000..1f8f957faf
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_cycles.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_CYCLES_LOONGARCH_H_
+#define _RTE_CYCLES_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_cycles.h"
+
+static inline uint64_t
+get_cycle_count(void)
+{
+ uint64_t count;
+
+ __asm__ __volatile__ (
+ "rdtime.d %[cycles], $zero\n"
+ : [cycles] "=r" (count)
+ ::
+ );
+ return count;
+}
+
+/**
+ * Read the time base register.
+ *
+ * @return
+ * The time base for this lcore.
+ */
+static inline uint64_t
+rte_rdtsc(void)
+{
+ return get_cycle_count();
+}
+
+static inline uint64_t
+rte_rdtsc_precise(void)
+{
+ rte_mb();
+ return rte_rdtsc();
+}
+
+static inline uint64_t
+rte_get_tsc_cycles(void) { return rte_rdtsc(); }
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_CYCLES_LOONGARCH_H_ */
diff --git a/lib/eal/loongarch/rte_cycles.c b/lib/eal/loongarch/rte_cycles.c
new file mode 100644
index 0000000000..582601d335
--- /dev/null
+++ b/lib/eal/loongarch/rte_cycles.c
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "eal_private.h"
+
+#define LOONGARCH_CPUCFG4 0x4
+#define CPUCFG4_CCFREQ_MASK 0xFFFFFFFF
+#define CPUCFG4_CCFREQ_SHIFT 0
+
+#define LOONGARCH_CPUCFG5 0x5
+#define CPUCFG5_CCMUL_MASK 0xFFFF
+#define CPUCFG5_CCMUL_SHIFT 0
+
+#define CPUCFG5_CCDIV_MASK 0xFFFF0000
+#define CPUCFG5_CCDIV_SHIFT 16
+
+static __rte_noinline uint32_t
+read_cpucfg(int arg)
+{
+ int ret = 0;
+
+ __asm__ __volatile__ (
+ "cpucfg %[var], %[index]\n"
+ : [var]"=r"(ret)
+ : [index]"r"(arg)
+ :
+ );
+
+ return ret;
+}
+
+uint64_t
+get_tsc_freq_arch(void)
+{
+ uint32_t base_freq, mul_factor, div_factor;
+
+ base_freq = read_cpucfg(LOONGARCH_CPUCFG4);
+ mul_factor = (read_cpucfg(LOONGARCH_CPUCFG5) & CPUCFG5_CCMUL_MASK) >>
+ CPUCFG5_CCMUL_SHIFT;
+ div_factor = (read_cpucfg(LOONGARCH_CPUCFG5) & CPUCFG5_CCDIV_MASK) >>
+ CPUCFG5_CCDIV_SHIFT;
+
+ return base_freq * mul_factor / div_factor;
+}
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 04/24] eal/loongarch: add prefetch operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (2 preceding siblings ...)
2022-05-28 9:32 ` [v1 03/24] eal/loongarch: add cpu cycle " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 05/24] eal/loongarch: add spinlock " Min Zhou
` (19 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds architecture specific prefetch operations
for LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_prefetch.h | 47 ++++++++++++++++++++++++
1 file changed, 47 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_prefetch.h
diff --git a/lib/eal/loongarch/include/rte_prefetch.h b/lib/eal/loongarch/include/rte_prefetch.h
new file mode 100644
index 0000000000..0fd9262ea8
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_prefetch.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_PREFETCH_LOONGARCH_H_
+#define _RTE_PREFETCH_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_prefetch.h"
+
+static inline void rte_prefetch0(const volatile void *p)
+{
+ __builtin_prefetch((const void *)(uintptr_t)p, 0, 3);
+}
+
+static inline void rte_prefetch1(const volatile void *p)
+{
+ __builtin_prefetch((const void *)(uintptr_t)p, 0, 2);
+}
+
+static inline void rte_prefetch2(const volatile void *p)
+{
+ __builtin_prefetch((const void *)(uintptr_t)p, 0, 1);
+}
+
+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_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 05/24] eal/loongarch: add spinlock operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (3 preceding siblings ...)
2022-05-28 9:32 ` [v1 04/24] eal/loongarch: add prefetch " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 15:54 ` Stephen Hemminger
2022-05-28 9:32 ` [v1 06/24] eal/loongarch: add cpu flag checks " Min Zhou
` (18 subsequent siblings)
23 siblings, 1 reply; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds spinlock operations for LoongArch architecture.
These implementations refer to GLIBC pthread_spin_xxlock(). The
underlying implementation is based on LoongArch atomic
instructions (ie, AMSWAP_DB.W).
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_spinlock.h | 93 ++++++++++++++++++++++++
1 file changed, 93 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_spinlock.h
diff --git a/lib/eal/loongarch/include/rte_spinlock.h b/lib/eal/loongarch/include/rte_spinlock.h
new file mode 100644
index 0000000000..6b565dc4d9
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_spinlock.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_SPINLOCK_LOONGARCH_H_
+#define _RTE_SPINLOCK_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_spinlock.h"
+
+#ifndef RTE_FORCE_INTRINSICS
+/*
+ * These implementations refer to GLIBC pthread_spin_xxlock().
+ */
+static inline void
+rte_spinlock_lock(rte_spinlock_t *sl)
+{
+ int val = 0;
+
+ if (rte_atomic32_exchange((volatile uint32_t *)&sl->locked, 1) == 0)
+ return;
+
+ do {
+ do {
+ val = sl->locked;
+ } while (val != 0);
+
+ } while (rte_atomic32_exchange((volatile uint32_t *)&sl->locked, 1) == 1);
+}
+
+static inline void
+rte_spinlock_unlock(rte_spinlock_t *sl)
+{
+ sl->locked = 0;
+}
+
+static inline int
+rte_spinlock_trylock(rte_spinlock_t *sl)
+{
+ return rte_atomic32_exchange((volatile uint32_t *)&sl->locked, 1) == 0;
+}
+#endif
+
+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_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* Re: [v1 05/24] eal/loongarch: add spinlock operations for LoongArch
2022-05-28 9:32 ` [v1 05/24] eal/loongarch: add spinlock " Min Zhou
@ 2022-05-28 15:54 ` Stephen Hemminger
2022-05-30 1:09 ` zhoumin
0 siblings, 1 reply; 29+ messages in thread
From: Stephen Hemminger @ 2022-05-28 15:54 UTC (permalink / raw)
To: Min Zhou
Cc: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev, dev,
maobibo
On Sat, 28 May 2022 17:32:52 +0800
Min Zhou <zhoumin@loongson.cn> wrote:
> This patch adds spinlock operations for LoongArch architecture.
> These implementations refer to GLIBC pthread_spin_xxlock(). The
> underlying implementation is based on LoongArch atomic
> instructions (ie, AMSWAP_DB.W).
>
> Signed-off-by: Min Zhou <zhoumin@loongson.cn>
If you supported std atomics, then the g eneric code
could work here.
^ permalink raw reply [flat|nested] 29+ messages in thread
* Re: [v1 05/24] eal/loongarch: add spinlock operations for LoongArch
2022-05-28 15:54 ` Stephen Hemminger
@ 2022-05-30 1:09 ` zhoumin
0 siblings, 0 replies; 29+ messages in thread
From: zhoumin @ 2022-05-30 1:09 UTC (permalink / raw)
To: Stephen Hemminger
Cc: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev, dev,
maobibo
[-- Attachment #1: Type: text/plain, Size: 636 bytes --]
Stephen,
Thanks for your comments! I'm evaluating the generic code of spinlock
on std atomics of LoongArch toolchain. An updated patch will come later.
On 2022/5/28 下午11:54, Stephen Hemminger wrote:
> On Sat, 28 May 2022 17:32:52 +0800
> Min Zhou<zhoumin@loongson.cn> wrote:
>
>> This patch adds spinlock operations for LoongArch architecture.
>> These implementations refer to GLIBC pthread_spin_xxlock(). The
>> underlying implementation is based on LoongArch atomic
>> instructions (ie, AMSWAP_DB.W).
>>
>> Signed-off-by: Min Zhou<zhoumin@loongson.cn>
> If you supported std atomics, then the g eneric code
> could work here.
[-- Attachment #2: Type: text/html, Size: 1275 bytes --]
^ permalink raw reply [flat|nested] 29+ messages in thread
* [v1 06/24] eal/loongarch: add cpu flag checks for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (4 preceding siblings ...)
2022-05-28 9:32 ` [v1 05/24] eal/loongarch: add spinlock " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 07/24] eal/loongarch: add dummy vector memcpy " Min Zhou
` (17 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch uses aux vector software register to get CPU flags
and add CPU flag checking support for LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_cpuflags.h | 39 ++++++++++
lib/eal/loongarch/rte_cpuflags.c | 94 ++++++++++++++++++++++++
2 files changed, 133 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_cpuflags.h
create mode 100644 lib/eal/loongarch/rte_cpuflags.c
diff --git a/lib/eal/loongarch/include/rte_cpuflags.h b/lib/eal/loongarch/include/rte_cpuflags.h
new file mode 100644
index 0000000000..d9121a00a8
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_cpuflags.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_CPUFLAGS_LOONGARCH_H_
+#define _RTE_CPUFLAGS_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Enumeration of all CPU features supported
+ */
+enum rte_cpu_flag_t {
+ RTE_CPUFLAG_CPUCFG = 0,
+ RTE_CPUFLAG_LAM,
+ RTE_CPUFLAG_UAL,
+ RTE_CPUFLAG_FPU,
+ RTE_CPUFLAG_LSX,
+ RTE_CPUFLAG_LASX,
+ RTE_CPUFLAG_CRC32,
+ RTE_CPUFLAG_COMPLEX,
+ RTE_CPUFLAG_CRYPTO,
+ RTE_CPUFLAG_LVZ,
+ RTE_CPUFLAG_LBT_X86,
+ RTE_CPUFLAG_LBT_ARM,
+ RTE_CPUFLAG_LBT_MIPS,
+ /* The last item */
+ RTE_CPUFLAG_NUMFLAGS /**< This should always be the last! */
+};
+
+#include "generic/rte_cpuflags.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_CPUFLAGS_LOONGARCH_H_ */
diff --git a/lib/eal/loongarch/rte_cpuflags.c b/lib/eal/loongarch/rte_cpuflags.c
new file mode 100644
index 0000000000..4abcd0fdb3
--- /dev/null
+++ b/lib/eal/loongarch/rte_cpuflags.c
@@ -0,0 +1,94 @@
+/*
+ * SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "rte_cpuflags.h"
+
+#include <elf.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+
+/* Symbolic values for the entries in the auxiliary table */
+#define AT_HWCAP 16
+#define AT_HWCAP2 26
+
+/* software based registers */
+enum cpu_register_t {
+ REG_NONE = 0,
+ REG_HWCAP,
+ REG_MAX
+};
+
+typedef uint32_t hwcap_registers_t[REG_MAX];
+
+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},
+
+const struct feature_entry rte_cpu_feature_table[] = {
+ FEAT_DEF(CPUCFG, REG_HWCAP, 0)
+ FEAT_DEF(LAM, REG_HWCAP, 1)
+ FEAT_DEF(UAL, REG_HWCAP, 2)
+ FEAT_DEF(FPU, REG_HWCAP, 3)
+ FEAT_DEF(LSX, REG_HWCAP, 4)
+ FEAT_DEF(LASX, REG_HWCAP, 5)
+ FEAT_DEF(CRC32, REG_HWCAP, 6)
+ FEAT_DEF(COMPLEX, REG_HWCAP, 7)
+ FEAT_DEF(CRYPTO, REG_HWCAP, 8)
+ FEAT_DEF(LVZ, REG_HWCAP, 9)
+ FEAT_DEF(LBT_X86, REG_HWCAP, 10)
+ FEAT_DEF(LBT_ARM, REG_HWCAP, 11)
+ FEAT_DEF(LBT_MIPS, REG_HWCAP, 12)
+};
+
+/*
+ * Read AUXV software register and get cpu features for LoongArch
+ */
+static void
+rte_cpu_get_features(hwcap_registers_t out)
+{
+ out[REG_HWCAP] = rte_cpu_getauxval(AT_HWCAP);
+}
+
+/*
+ * 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));
+}
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 07/24] eal/loongarch: add dummy vector memcpy for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (5 preceding siblings ...)
2022-05-28 9:32 ` [v1 06/24] eal/loongarch: add cpu flag checks " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 08/24] eal/loongarch: add io operations " Min Zhou
` (16 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
The hardware instructions based vector implementation for memcpy
will come later. At present, this dummy implementation can also
work.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_memcpy.h | 193 +++++++++++++++++++++++++
lib/eal/loongarch/include/rte_vect.h | 47 ++++++
2 files changed, 240 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_memcpy.h
create mode 100644 lib/eal/loongarch/include/rte_vect.h
diff --git a/lib/eal/loongarch/include/rte_memcpy.h b/lib/eal/loongarch/include/rte_memcpy.h
new file mode 100644
index 0000000000..98dc3dfc3b
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_memcpy.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_MEMCPY_LOONGARCH_H_
+#define _RTE_MEMCPY_LOONGARCH_H_
+
+#include <stdint.h>
+#include <string.h>
+#include <rte_vect.h>
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_memcpy.h"
+
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+ *(xmm_t *)dst = *(const xmm_t *)src;
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16);
+ rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16);
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16);
+ rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16);
+ rte_mov16((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16);
+ rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16);
+ rte_mov16((uint8_t *)dst + 2 * 16, (const uint8_t *)src + 2 * 16);
+ rte_mov16((uint8_t *)dst + 3 * 16, (const uint8_t *)src + 3 * 16);
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16);
+ rte_mov16((uint8_t *)dst + 1 * 16, (const uint8_t *)src + 1 * 16);
+ rte_mov16((uint8_t *)dst + 2 * 16, (const uint8_t *)src + 2 * 16);
+ rte_mov16((uint8_t *)dst + 3 * 16, (const uint8_t *)src + 3 * 16);
+ rte_mov16((uint8_t *)dst + 4 * 16, (const uint8_t *)src + 4 * 16);
+ rte_mov16((uint8_t *)dst + 5 * 16, (const uint8_t *)src + 5 * 16);
+ rte_mov16((uint8_t *)dst + 6 * 16, (const uint8_t *)src + 6 * 16);
+ rte_mov16((uint8_t *)dst + 7 * 16, (const uint8_t *)src + 7 * 16);
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov128(dst, src);
+ rte_mov128(dst + 128, src + 128);
+}
+
+#define rte_memcpy(dst, src, n) \
+ rte_memcpy_func((dst), (src), (n))
+
+static inline void *
+rte_memcpy_func(void *dst, const void *src, size_t n)
+{
+ void *ret = dst;
+
+ /* We can't copy < 16 bytes using XMM registers so do it manually. */
+ if (n < 16) {
+ if (n & 0x01) {
+ *(uint8_t *)dst = *(const uint8_t *)src;
+ dst = (uint8_t *)dst + 1;
+ src = (const uint8_t *)src + 1;
+ }
+ if (n & 0x02) {
+ *(uint16_t *)dst = *(const uint16_t *)src;
+ dst = (uint16_t *)dst + 1;
+ src = (const uint16_t *)src + 1;
+ }
+ if (n & 0x04) {
+ *(uint32_t *)dst = *(const uint32_t *)src;
+ dst = (uint32_t *)dst + 1;
+ src = (const uint32_t *)src + 1;
+ }
+ if (n & 0x08)
+ *(uint64_t *)dst = *(const uint64_t *)src;
+ return ret;
+ }
+
+ /* Special fast cases for <= 128 bytes */
+ if (n <= 32) {
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
+ return ret;
+ }
+
+ if (n <= 64) {
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
+ return ret;
+ }
+
+ if (n <= 128) {
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov64((uint8_t *)dst - 64 + n,
+ (const uint8_t *)src - 64 + n);
+ return ret;
+ }
+
+ /*
+ * For large copies > 128 bytes. This combination of 256, 64 and 16 byte
+ * copies was found to be faster than doing 128 and 32 byte copies as
+ * well.
+ */
+ for ( ; n >= 256; n -= 256) {
+ rte_mov256((uint8_t *)dst, (const uint8_t *)src);
+ dst = (uint8_t *)dst + 256;
+ src = (const uint8_t *)src + 256;
+ }
+
+ /*
+ * We split the remaining bytes (which will be less than 256) into
+ * 64byte (2^6) chunks.
+ * Using incrementing integers in the case labels of a switch statement
+ * encourages the compiler to use a jump table. To get incrementing
+ * integers, we shift the 2 relevant bits to the LSB position to first
+ * get decrementing integers, and then subtract.
+ */
+ switch (3 - (n >> 6)) {
+ case 0x00:
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ n -= 64;
+ dst = (uint8_t *)dst + 64;
+ src = (const uint8_t *)src + 64; /* fallthrough */
+ case 0x01:
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ n -= 64;
+ dst = (uint8_t *)dst + 64;
+ src = (const uint8_t *)src + 64; /* fallthrough */
+ case 0x02:
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ n -= 64;
+ dst = (uint8_t *)dst + 64;
+ src = (const uint8_t *)src + 64; /* fallthrough */
+ default:
+ break;
+ }
+
+ /*
+ * We split the remaining bytes (which will be less than 64) into
+ * 16byte (2^4) chunks, using the same switch structure as above.
+ */
+ switch (3 - (n >> 4)) {
+ case 0x00:
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ n -= 16;
+ dst = (uint8_t *)dst + 16;
+ src = (const uint8_t *)src + 16; /* fallthrough */
+ case 0x01:
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ n -= 16;
+ dst = (uint8_t *)dst + 16;
+ src = (const uint8_t *)src + 16; /* fallthrough */
+ case 0x02:
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ n -= 16;
+ dst = (uint8_t *)dst + 16;
+ src = (const uint8_t *)src + 16; /* fallthrough */
+ default:
+ break;
+ }
+
+ /* Copy any remaining bytes, without going beyond end of buffers */
+ if (n != 0)
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
+ return ret;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_MEMCPY_LOONGARCH_H_ */
diff --git a/lib/eal/loongarch/include/rte_vect.h b/lib/eal/loongarch/include/rte_vect.h
new file mode 100644
index 0000000000..f13a5931ef
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_vect.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_VECT_LOONGARCH_H_
+#define _RTE_VECT_LOONGARCH_H_
+
+#include <stdint.h>
+#include <sys/param.h>
+#include "rte_common.h"
+#include "generic/rte_vect.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define RTE_VECT_DEFAULT_SIMD_BITWIDTH RTE_VECT_SIMD_256
+
+typedef union xmm {
+ int8_t i8[16];
+ int16_t i16[8];
+ int32_t i32[4];
+ int64_t i64[2];
+ uint8_t u8[16];
+ uint16_t u16[8];
+ uint32_t u32[4];
+ uint64_t u64[2];
+ double pd[2];
+} __rte_aligned(16) xmm_t;
+
+#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(16) rte_xmm_t;
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 08/24] eal/loongarch: add io operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (6 preceding siblings ...)
2022-05-28 9:32 ` [v1 07/24] eal/loongarch: add dummy vector memcpy " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 09/24] eal/loongarch: add mcslock " Min Zhou
` (15 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds io operations for LoongArch architecture. Let it
uses generic I/O implementation.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_io.h | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_io.h
diff --git a/lib/eal/loongarch/include/rte_io.h b/lib/eal/loongarch/include/rte_io.h
new file mode 100644
index 0000000000..af152a727a
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_io.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_IO_LOONGARCH_H_
+#define _RTE_IO_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_io.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_IO_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 09/24] eal/loongarch: add mcslock operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (7 preceding siblings ...)
2022-05-28 9:32 ` [v1 08/24] eal/loongarch: add io operations " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 10/24] eal/loongarch: add pause " Min Zhou
` (14 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds mcslock operations for LoongArch architecture.
Let it uses generic mcslock implementation.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_mcslock.h | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_mcslock.h
diff --git a/lib/eal/loongarch/include/rte_mcslock.h b/lib/eal/loongarch/include/rte_mcslock.h
new file mode 100644
index 0000000000..c4484b66fa
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_mcslock.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_MCSLOCK_LOONGARCH_H_
+#define _RTE_MCSLOCK_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_mcslock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_MCSLOCK_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 10/24] eal/loongarch: add pause operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (8 preceding siblings ...)
2022-05-28 9:32 ` [v1 09/24] eal/loongarch: add mcslock " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 11/24] eal/loongarch: add pflock " Min Zhou
` (13 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds architecture specific pause operations for
LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_pause.h | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_pause.h
diff --git a/lib/eal/loongarch/include/rte_pause.h b/lib/eal/loongarch/include/rte_pause.h
new file mode 100644
index 0000000000..438de23128
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_pause.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_PAUSE_LOONGARCH_H_
+#define _RTE_PAUSE_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "rte_atomic.h"
+
+#include "generic/rte_pause.h"
+
+static inline void rte_pause(void)
+{
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_PAUSE_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 11/24] eal/loongarch: add pflock operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (9 preceding siblings ...)
2022-05-28 9:32 ` [v1 10/24] eal/loongarch: add pause " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:32 ` [v1 12/24] eal/loongarch: add rwlock " Min Zhou
` (12 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds pflock operations for LoongArch architecture.
Let it uses generic pflock implementation.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_pflock.h | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_pflock.h
diff --git a/lib/eal/loongarch/include/rte_pflock.h b/lib/eal/loongarch/include/rte_pflock.h
new file mode 100644
index 0000000000..39cc066f65
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_pflock.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+#ifndef _RTE_PFLOCK_LOONGARCH_H_
+#define _RTE_PFLOCK_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_pflock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_PFLOCK_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 12/24] eal/loongarch: add rwlock operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (10 preceding siblings ...)
2022-05-28 9:32 ` [v1 11/24] eal/loongarch: add pflock " Min Zhou
@ 2022-05-28 9:32 ` Min Zhou
2022-05-28 9:33 ` [v1 13/24] eal/loongarch: add ticketlock " Min Zhou
` (11 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:32 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds rwlock operations for LoongArch architecture.
The implementation is based on lib/eal/ppc/include/rte_rwlock.h.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_rwlock.h | 42 ++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_rwlock.h
diff --git a/lib/eal/loongarch/include/rte_rwlock.h b/lib/eal/loongarch/include/rte_rwlock.h
new file mode 100644
index 0000000000..aac6f60120
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_rwlock.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_RWLOCK_LOONGARCH_H_
+#define _RTE_RWLOCK_LOONGARCH_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_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 13/24] eal/loongarch: add ticketlock operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (11 preceding siblings ...)
2022-05-28 9:32 ` [v1 12/24] eal/loongarch: add rwlock " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 14/24] eal/loongarch: add power " Min Zhou
` (10 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds ticketlock operations for LoongArch architecture.
Let it uses generic ticketlock implementation.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/include/rte_ticketlock.h | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_ticketlock.h
diff --git a/lib/eal/loongarch/include/rte_ticketlock.h b/lib/eal/loongarch/include/rte_ticketlock.h
new file mode 100644
index 0000000000..3959bcae7b
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_ticketlock.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_TICKETLOCK_LOONGARCH_H_
+#define _RTE_TICKETLOCK_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_ticketlock.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_TICKETLOCK_LOONGARCH_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 14/24] eal/loongarch: add power operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (12 preceding siblings ...)
2022-05-28 9:33 ` [v1 13/24] eal/loongarch: add ticketlock " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 15/24] eal/loongarch: add hypervisor " Min Zhou
` (9 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds power operations for LoongArch architecture. In
fact, these operations are temporarily not supported on LoongArch.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
.../loongarch/include/rte_power_intrinsics.h | 20 ++++++++
lib/eal/loongarch/rte_power_intrinsics.c | 51 +++++++++++++++++++
2 files changed, 71 insertions(+)
create mode 100644 lib/eal/loongarch/include/rte_power_intrinsics.h
create mode 100644 lib/eal/loongarch/rte_power_intrinsics.c
diff --git a/lib/eal/loongarch/include/rte_power_intrinsics.h b/lib/eal/loongarch/include/rte_power_intrinsics.h
new file mode 100644
index 0000000000..b6a2c0d82e
--- /dev/null
+++ b/lib/eal/loongarch/include/rte_power_intrinsics.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_POWER_INTRINSIC_LOONGARCH_H_
+#define _RTE_POWER_INTRINSIC_LOONGARCH_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+
+#include "generic/rte_power_intrinsics.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_POWER_INTRINSIC_LOONGARCH_H_ */
diff --git a/lib/eal/loongarch/rte_power_intrinsics.c b/lib/eal/loongarch/rte_power_intrinsics.c
new file mode 100644
index 0000000000..3dd1375ce4
--- /dev/null
+++ b/lib/eal/loongarch/rte_power_intrinsics.c
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "rte_power_intrinsics.h"
+
+/**
+ * This function is not supported on LOONGARCH.
+ */
+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 LOONGARCH.
+ */
+int
+rte_power_pause(const uint64_t tsc_timestamp)
+{
+ RTE_SET_USED(tsc_timestamp);
+
+ return -ENOTSUP;
+}
+
+/**
+ * This function is not supported on LOONGARCH.
+ */
+int
+rte_power_monitor_wakeup(const unsigned int lcore_id)
+{
+ RTE_SET_USED(lcore_id);
+
+ return -ENOTSUP;
+}
+
+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;
+}
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 15/24] eal/loongarch: add hypervisor operations for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (13 preceding siblings ...)
2022-05-28 9:33 ` [v1 14/24] eal/loongarch: add power " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 16/24] mem: add huge page size definition " Min Zhou
` (8 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds hypervisor operations for LoongArch architecture.
In fact, these operations are currently not supported on LoongArch.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/loongarch/rte_hypervisor.c | 11 +++++++++++
1 file changed, 11 insertions(+)
create mode 100644 lib/eal/loongarch/rte_hypervisor.c
diff --git a/lib/eal/loongarch/rte_hypervisor.c b/lib/eal/loongarch/rte_hypervisor.c
new file mode 100644
index 0000000000..d044906f71
--- /dev/null
+++ b/lib/eal/loongarch/rte_hypervisor.c
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "rte_hypervisor.h"
+
+enum rte_hypervisor
+rte_hypervisor_get(void)
+{
+ return RTE_HYPERVISOR_UNKNOWN;
+}
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 16/24] mem: add huge page size definition for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (14 preceding siblings ...)
2022-05-28 9:33 ` [v1 15/24] eal/loongarch: add hypervisor " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 17/24] eal/linux: set eal base address " Min Zhou
` (7 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
LoongArch architecture has a different huge page size (32MB) than
other architectures. This patch adds a new huge page size for
LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/include/rte_memory.h | 1 +
lib/eal/include/rte_memzone.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/lib/eal/include/rte_memory.h b/lib/eal/include/rte_memory.h
index 68b069fd04..dd9e6c0b89 100644
--- a/lib/eal/include/rte_memory.h
+++ b/lib/eal/include/rte_memory.h
@@ -30,6 +30,7 @@ extern "C" {
#define RTE_PGSIZE_256K (1ULL << 18)
#define RTE_PGSIZE_2M (1ULL << 21)
#define RTE_PGSIZE_16M (1ULL << 24)
+#define RTE_PGSIZE_32M (1ULL << 25)
#define RTE_PGSIZE_256M (1ULL << 28)
#define RTE_PGSIZE_512M (1ULL << 29)
#define RTE_PGSIZE_1G (1ULL << 30)
diff --git a/lib/eal/include/rte_memzone.h b/lib/eal/include/rte_memzone.h
index 5db1210831..8129ba363b 100644
--- a/lib/eal/include/rte_memzone.h
+++ b/lib/eal/include/rte_memzone.h
@@ -35,6 +35,7 @@ extern "C" {
#define RTE_MEMZONE_1GB 0x00000002 /**< Use 1GB pages. */
#define RTE_MEMZONE_16MB 0x00000100 /**< Use 16MB pages. */
#define RTE_MEMZONE_16GB 0x00000200 /**< Use 16GB pages. */
+#define RTE_MEMZONE_32MB 0x00000400 /**< Use 32MB pages. */
#define RTE_MEMZONE_256KB 0x00010000 /**< Use 256KB pages. */
#define RTE_MEMZONE_256MB 0x00020000 /**< Use 256MB pages. */
#define RTE_MEMZONE_512MB 0x00040000 /**< Use 512MB pages. */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 17/24] eal/linux: set eal base address for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (15 preceding siblings ...)
2022-05-28 9:33 ` [v1 16/24] mem: add huge page size definition " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 18/24] meson: introduce LoongArch architecture Min Zhou
` (6 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch sets a different eal base address for LoongArch
architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
lib/eal/linux/eal_memory.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/lib/eal/linux/eal_memory.c b/lib/eal/linux/eal_memory.c
index c890c42106..60fc8cc6ca 100644
--- a/lib/eal/linux/eal_memory.c
+++ b/lib/eal/linux/eal_memory.c
@@ -77,7 +77,11 @@ uint64_t eal_get_baseaddr(void)
* rte_mem_check_dma_mask for ensuring all memory is within supported
* range.
*/
+#if defined(RTE_ARCH_LOONGARCH)
+ return 0x7000000000ULL;
+#else
return 0x100000000ULL;
+#endif
}
/*
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 18/24] meson: introduce LoongArch architecture
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (16 preceding siblings ...)
2022-05-28 9:33 ` [v1 17/24] eal/linux: set eal base address " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 19/24] lpm: add dummy vector implementation for LoongArch Min Zhou
` (5 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds some meson.build files for building DPDK on
LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
.../loongarch/loongarch_loongarch64_linux_gcc | 16 +++++++
config/loongarch/meson.build | 46 +++++++++++++++++++
lib/eal/loongarch/include/meson.build | 21 +++++++++
lib/eal/loongarch/meson.build | 11 +++++
meson.build | 2 +
5 files changed, 96 insertions(+)
create mode 100644 config/loongarch/loongarch_loongarch64_linux_gcc
create mode 100644 config/loongarch/meson.build
create mode 100644 lib/eal/loongarch/include/meson.build
create mode 100644 lib/eal/loongarch/meson.build
diff --git a/config/loongarch/loongarch_loongarch64_linux_gcc b/config/loongarch/loongarch_loongarch64_linux_gcc
new file mode 100644
index 0000000000..ca94dab705
--- /dev/null
+++ b/config/loongarch/loongarch_loongarch64_linux_gcc
@@ -0,0 +1,16 @@
+[binaries]
+c = 'loongarch64-linux-gnu-gcc'
+cpp = 'loongarch64-linux-gnu-cpp'
+ar = 'loongarch64-linux-gnu-gcc-ar'
+strip = 'loongarch64-linux-gnu-strip'
+pcap-config = ''
+
+[host_machine]
+system = 'linux'
+cpu_family = 'loongarch64'
+cpu = '3a5000'
+endian = 'little'
+
+[properties]
+implementor_id = 'generic'
+implementor_pn = 'default'
diff --git a/config/loongarch/meson.build b/config/loongarch/meson.build
new file mode 100644
index 0000000000..8d76ae1a19
--- /dev/null
+++ b/config/loongarch/meson.build
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2022 Loongson Technology Corporation Limited
+
+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', 'loongarch')
+dpdk_conf.set('RTE_ARCH_LOONGARCH', 1)
+dpdk_conf.set('RTE_ARCH_NO_VECTOR', 1)
+
+# for checking defines we need to use the correct compiler flags
+march_opt = '-march=@0@'.format(machine)
+
+machine_args_generic = [
+ ['default', ['-march=loongarch64']],
+]
+
+flags_generic = [
+ ['RTE_MACHINE', '"loongarch64"'],
+ ['RTE_MAX_LCORE', 64],
+ ['RTE_MAX_NUMA_NODES', 16],
+ ['RTE_CACHE_LINE_SIZE', 64]]
+
+impl_generic = ['Generic loongarch', flags_generic, machine_args_generic]
+
+machine = []
+machine_args = []
+
+machine = impl_generic
+impl_pn = 'default'
+
+message('Implementer : ' + machine[0])
+foreach flag: machine[1]
+ if flag.length() > 0
+dpdk_conf.set(flag[0], flag[1])
+ endif
+endforeach
+
+foreach marg: machine[2]
+ if marg[0] == impl_pn
+ foreach f: marg[1]
+ machine_args += f
+ endforeach
+ endif
+endforeach
+message(machine_args)
diff --git a/lib/eal/loongarch/include/meson.build b/lib/eal/loongarch/include/meson.build
new file mode 100644
index 0000000000..d5699c5373
--- /dev/null
+++ b/lib/eal/loongarch/include/meson.build
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2022 Loongson Technology Corporation Limited
+
+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/loongarch/meson.build b/lib/eal/loongarch/meson.build
new file mode 100644
index 0000000000..e14b1ed431
--- /dev/null
+++ b/lib/eal/loongarch/meson.build
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2022 Loongson Technology Corporation Limited
+
+subdir('include')
+
+sources += files(
+ 'rte_cpuflags.c',
+ 'rte_cycles.c',
+ 'rte_hypervisor.c',
+ 'rte_power_intrinsics.c',
+)
diff --git a/meson.build b/meson.build
index 937f6110c0..573844dd2e 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('loongarch')
+ arch_subdir = 'loongarch'
endif
# configure the build, and make sure configs here and in config folder are
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 19/24] lpm: add dummy vector implementation for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (17 preceding siblings ...)
2022-05-28 9:33 ` [v1 18/24] meson: introduce LoongArch architecture Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 20/24] ixgbe: " Min Zhou
` (4 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
The hardware instructions based vector implementation will come
in a future patch. This dummy implementation can also work.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
app/test/test_xmmt_ops.h | 17 ++++++
lib/lpm/meson.build | 1 +
lib/lpm/rte_lpm.h | 2 +
lib/lpm/rte_lpm_lsx.h | 129 +++++++++++++++++++++++++++++++++++++++
4 files changed, 149 insertions(+)
create mode 100644 lib/lpm/rte_lpm_lsx.h
diff --git a/app/test/test_xmmt_ops.h b/app/test/test_xmmt_ops.h
index 3a82d5ecac..7b2c3c37dd 100644
--- a/app/test/test_xmmt_ops.h
+++ b/app/test/test_xmmt_ops.h
@@ -49,6 +49,23 @@ vect_set_epi32(int i3, int i2, int i1, int i0)
return data;
}
+#elif defined(RTE_ARCH_LOONGARCH)
+/* loads the xmm_t value from address p(does not need to be 16-byte aligned)*/
+static __rte_always_inline xmm_t
+vect_loadu_sil128(void *p)
+{
+ xmm_t data;
+ data = *(const xmm_t *)p;
+ return data;
+}
+
+/* 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){.u32 = {i0, i1, i2, i3} };
+ return data;
+}
#endif
#endif /* _TEST_XMMT_OPS_H_ */
diff --git a/lib/lpm/meson.build b/lib/lpm/meson.build
index 78d91d3421..66df44b9b4 100644
--- a/lib/lpm/meson.build
+++ b/lib/lpm/meson.build
@@ -16,6 +16,7 @@ indirect_headers += files(
'rte_lpm_neon.h',
'rte_lpm_sse.h',
'rte_lpm_sve.h',
+ 'rte_lpm_lsx.h',
)
deps += ['hash']
deps += ['rcu']
diff --git a/lib/lpm/rte_lpm.h b/lib/lpm/rte_lpm.h
index eb91960e81..7e94821212 100644
--- a/lib/lpm/rte_lpm.h
+++ b/lib/lpm/rte_lpm.h
@@ -405,6 +405,8 @@ rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
#endif
#elif defined(RTE_ARCH_PPC_64)
#include "rte_lpm_altivec.h"
+#elif defined(RTE_ARCH_LOONGARCH)
+#include "rte_lpm_lsx.h"
#else
#include "rte_lpm_sse.h"
#endif
diff --git a/lib/lpm/rte_lpm_lsx.h b/lib/lpm/rte_lpm_lsx.h
new file mode 100644
index 0000000000..07942571e7
--- /dev/null
+++ b/lib/lpm/rte_lpm_lsx.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _RTE_LPM_LSX_H_
+#define _RTE_LPM_LSX_H_
+
+#include <rte_branch_prediction.h>
+#include <rte_byteorder.h>
+#include <rte_common.h>
+#include <rte_vect.h>
+#include <rte_lpm.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef RTE_ARCH_NO_VECTOR
+static inline void
+rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
+ uint32_t defv)
+{
+ xmm_t i24;
+ rte_xmm_t i8;
+ uint32_t tbl[4];
+ uint64_t idx, pt, pt2;
+ const uint32_t *ptbl;
+ int i;
+
+ const uint32_t mask = UINT8_MAX;
+ xmm_t mask8_tmp = (xmm_t){.u32 = {mask, mask, mask, mask} };
+
+ const xmm_t mask8 = mask8_tmp;
+
+ /*
+ * RTE_LPM_VALID_EXT_ENTRY_BITMASK for 2 LPM entries
+ * as one 64-bit value (0x0300000003000000).
+ */
+ const uint64_t mask_xv =
+ ((uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK |
+ (uint64_t)RTE_LPM_VALID_EXT_ENTRY_BITMASK << 32);
+
+ /*
+ * RTE_LPM_LOOKUP_SUCCESS for 2 LPM entries
+ * as one 64-bit value (0x0100000001000000).
+ */
+ const uint64_t mask_v =
+ ((uint64_t)RTE_LPM_LOOKUP_SUCCESS |
+ (uint64_t)RTE_LPM_LOOKUP_SUCCESS << 32);
+
+ /* get 4 indexes for tbl24[]. */
+ for (i = 0; i < 4; i++)
+ i24.u32[i] = ip.u32[i] >> CHAR_BIT;
+
+ /* extract values from tbl24[] */
+ idx = i24.i64[0];
+
+ ptbl = (const uint32_t *)&lpm->tbl24[(uint32_t)idx];
+ tbl[0] = *ptbl;
+ ptbl = (const uint32_t *)&lpm->tbl24[idx >> 32];
+ tbl[1] = *ptbl;
+
+ idx = i24.i64[1];
+
+ ptbl = (const uint32_t *)&lpm->tbl24[(uint32_t)idx];
+ tbl[2] = *ptbl;
+ ptbl = (const uint32_t *)&lpm->tbl24[idx >> 32];
+ tbl[3] = *ptbl;
+
+ /* get 4 indexes for tbl8[]. */
+ for (i = 0; i < 2; i++)
+ i8.x.u64[i] = ip.u64[i] & mask8.u64[i];
+
+ pt = (uint64_t)tbl[0] |
+ (uint64_t)tbl[1] << 32;
+ pt2 = (uint64_t)tbl[2] |
+ (uint64_t)tbl[3] << 32;
+
+ /* search successfully finished for all 4 IP addresses. */
+ if (likely((pt & mask_xv) == mask_v) &&
+ likely((pt2 & mask_xv) == mask_v)) {
+ *(uint64_t *)hop = pt & RTE_LPM_MASKX4_RES;
+ *(uint64_t *)(hop + 2) = pt2 & RTE_LPM_MASKX4_RES;
+ return;
+ }
+
+ if (unlikely((pt & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+ RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+ i8.u32[0] = i8.u32[0] +
+ (tbl[0] & 0x00FFFFFF) * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+ ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[0]];
+ tbl[0] = *ptbl;
+ }
+ if (unlikely((pt >> 32 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+ RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+ i8.u32[1] = i8.u32[1] +
+ (tbl[1] & 0x00FFFFFF) * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+ ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[1]];
+ tbl[1] = *ptbl;
+ }
+ if (unlikely((pt2 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+ RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+ i8.u32[2] = i8.u32[2] +
+ (tbl[2] & 0x00FFFFFF) * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+ ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[2]];
+ tbl[2] = *ptbl;
+ }
+ if (unlikely((pt2 >> 32 & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
+ RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
+ i8.u32[3] = i8.u32[3] +
+ (tbl[3] & 0x00FFFFFF) * RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
+ ptbl = (const uint32_t *)&lpm->tbl8[i8.u32[3]];
+ tbl[3] = *ptbl;
+ }
+
+ hop[0] = (tbl[0] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[0] & 0x00FFFFFF : defv;
+ hop[1] = (tbl[1] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[1] & 0x00FFFFFF : defv;
+ hop[2] = (tbl[2] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[2] & 0x00FFFFFF : defv;
+ hop[3] = (tbl[3] & RTE_LPM_LOOKUP_SUCCESS) ? tbl[3] & 0x00FFFFFF : defv;
+}
+#else
+#error "The current version of LoongArch does not support vector!"
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_LPM_LSX_H_ */
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 20/24] ixgbe: add dummy vector implementation for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (18 preceding siblings ...)
2022-05-28 9:33 ` [v1 19/24] lpm: add dummy vector implementation for LoongArch Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 21/24] i40e: " Min Zhou
` (3 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
The purpose of this patch is used to fix building issues for
LoongArch architecture. The hardware instructions based vector
implementation will come in a future patch.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_lsx.c | 60 ++++++++++++++++++++++++++
drivers/net/ixgbe/meson.build | 2 +
2 files changed, 62 insertions(+)
create mode 100644 drivers/net/ixgbe/ixgbe_rxtx_vec_lsx.c
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_lsx.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_lsx.c
new file mode 100644
index 0000000000..412c8f937a
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_lsx.c
@@ -0,0 +1,60 @@
+/*
+ * SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "base/ixgbe_common.h"
+#include "ixgbe_ethdev.h"
+#include "ixgbe_rxtx.h"
+
+/* The vector support will come later */
+#ifdef RTE_ARCH_NO_VECTOR
+int
+ixgbe_rx_vec_dev_conf_condition_check(__rte_unused struct rte_eth_dev *dev)
+{
+ return -1;
+}
+
+uint16_t
+ixgbe_recv_pkts_vec(__rte_unused void *rx_queue,
+ __rte_unused struct rte_mbuf **rx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+
+uint16_t
+ixgbe_recv_scattered_pkts_vec(__rte_unused void *rx_queue,
+ __rte_unused struct rte_mbuf **rx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+
+int
+ixgbe_rxq_vec_setup(__rte_unused struct ixgbe_rx_queue *rxq)
+{
+ return -1;
+}
+
+uint16_t
+ixgbe_xmit_fixed_burst_vec(__rte_unused void *tx_queue,
+ __rte_unused struct rte_mbuf **tx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+
+int
+ixgbe_txq_vec_setup(__rte_unused struct ixgbe_tx_queue *txq)
+{
+ return -1;
+}
+
+void
+ixgbe_rx_queue_release_mbufs_vec(__rte_unused struct ixgbe_rx_queue *rxq)
+{
+}
+#else
+#error "The current version of LoongArch does not support vector!"
+#endif
diff --git a/drivers/net/ixgbe/meson.build b/drivers/net/ixgbe/meson.build
index 162f8d5f46..33c9a58ac8 100644
--- a/drivers/net/ixgbe/meson.build
+++ b/drivers/net/ixgbe/meson.build
@@ -29,6 +29,8 @@ if arch_subdir == 'x86'
endif
elif arch_subdir == 'arm'
sources += files('ixgbe_rxtx_vec_neon.c')
+elif arch_subdir == 'loongarch'
+ sources += files('ixgbe_rxtx_vec_lsx.c')
endif
includes += include_directories('base')
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 21/24] i40e: add dummy vector implementation for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (19 preceding siblings ...)
2022-05-28 9:33 ` [v1 20/24] ixgbe: " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 22/24] tap: add system call number " Min Zhou
` (2 subsequent siblings)
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
The purpose of this patch is used to fix building issues for
LoongArch architecture. The hardware instructions based vector
implementation will come in a future patch.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
drivers/net/i40e/i40e_rxtx_vec_lsx.c | 54 ++++++++++++++++++++++++++++
drivers/net/i40e/meson.build | 2 ++
2 files changed, 56 insertions(+)
create mode 100644 drivers/net/i40e/i40e_rxtx_vec_lsx.c
diff --git a/drivers/net/i40e/i40e_rxtx_vec_lsx.c b/drivers/net/i40e/i40e_rxtx_vec_lsx.c
new file mode 100644
index 0000000000..727dc178f2
--- /dev/null
+++ b/drivers/net/i40e/i40e_rxtx_vec_lsx.c
@@ -0,0 +1,54 @@
+/*
+ * SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Loongson Technology Corporation Limited
+ */
+
+#include "i40e_ethdev.h"
+#include "i40e_rxtx.h"
+
+/* The vector support will come later */
+#ifdef RTE_ARCH_NO_VECTOR
+uint16_t
+i40e_recv_scattered_pkts_vec(__rte_unused void *rx_queue,
+ __rte_unused struct rte_mbuf **rx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+
+uint16_t
+i40e_recv_pkts_vec(__rte_unused void *rx_queue,
+ __rte_unused struct rte_mbuf **rx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+uint16_t
+i40e_xmit_fixed_burst_vec(__rte_unused void *tx_queue,
+ __rte_unused struct rte_mbuf **tx_pkts,
+ __rte_unused uint16_t nb_pkts)
+{
+ return 0;
+}
+void __rte_cold
+i40e_rx_queue_release_mbufs_vec(__rte_unused struct i40e_rx_queue *rxq)
+{
+}
+int __rte_cold
+i40e_rxq_vec_setup(__rte_unused struct i40e_rx_queue *rxq)
+{
+ return -1;
+}
+int __rte_cold
+i40e_txq_vec_setup(__rte_unused struct i40e_tx_queue *txq)
+{
+ return -1;
+}
+int __rte_cold
+i40e_rx_vec_dev_conf_condition_check(__rte_unused struct rte_eth_dev *dev)
+{
+ return -1;
+}
+#else
+#error "The current version of LoongArch does not support vector!"
+#endif
diff --git a/drivers/net/i40e/meson.build b/drivers/net/i40e/meson.build
index efc5f93e35..9775f05da1 100644
--- a/drivers/net/i40e/meson.build
+++ b/drivers/net/i40e/meson.build
@@ -75,6 +75,8 @@ elif arch_subdir == 'ppc'
sources += files('i40e_rxtx_vec_altivec.c')
elif arch_subdir == 'arm'
sources += files('i40e_rxtx_vec_neon.c')
+elif arch_subdir == 'loongarch'
+ sources += files('i40e_rxtx_vec_lsx.c')
endif
headers = files('rte_pmd_i40e.h')
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 22/24] tap: add system call number for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (20 preceding siblings ...)
2022-05-28 9:33 ` [v1 21/24] i40e: " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 23/24] memif: " Min Zhou
2022-05-28 9:33 ` [v1 24/24] maintainers: claim responsibility " Min Zhou
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds system call number of bpf for LoongArch
architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
drivers/net/tap/tap_bpf.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/tap/tap_bpf.h b/drivers/net/tap/tap_bpf.h
index f0b9fc7a2c..b1c9600ed8 100644
--- a/drivers/net/tap/tap_bpf.h
+++ b/drivers/net/tap/tap_bpf.h
@@ -93,7 +93,7 @@ union bpf_attr {
# define __NR_bpf 321
# elif defined(__arm__)
# define __NR_bpf 386
-# elif defined(__aarch64__)
+# elif defined(__aarch64__) || defined(__loongarch__)
# define __NR_bpf 280
# elif defined(__sparc__)
# define __NR_bpf 349
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 23/24] memif: add system call number for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (21 preceding siblings ...)
2022-05-28 9:33 ` [v1 22/24] tap: add system call number " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
2022-05-28 9:33 ` [v1 24/24] maintainers: claim responsibility " Min Zhou
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds system call number of memfd_create for LoongArch
architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
drivers/net/memif/rte_eth_memif.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/memif/rte_eth_memif.h b/drivers/net/memif/rte_eth_memif.h
index a5ee23d42e..b751037b79 100644
--- a/drivers/net/memif/rte_eth_memif.h
+++ b/drivers/net/memif/rte_eth_memif.h
@@ -174,7 +174,7 @@ const char *memif_version(void);
#define __NR_memfd_create 1073742143
#elif defined __arm__
#define __NR_memfd_create 385
-#elif defined __aarch64__
+#elif defined __aarch64__ || defined __loongarch__
#define __NR_memfd_create 279
#elif defined __powerpc__
#define __NR_memfd_create 360
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread* [v1 24/24] maintainers: claim responsibility for LoongArch
2022-05-28 9:32 [v1 00/24] Support LoongArch architecture Min Zhou
` (22 preceding siblings ...)
2022-05-28 9:33 ` [v1 23/24] memif: " Min Zhou
@ 2022-05-28 9:33 ` Min Zhou
23 siblings, 0 replies; 29+ messages in thread
From: Min Zhou @ 2022-05-28 9:33 UTC (permalink / raw)
To: thomas, david.marchand, bruce.richardson, anatoly.burakov,
qiming.yang, Yuying.Zhang, jgrajcia, konstantin.v.ananyev
Cc: dev, maobibo
This patch adds claim responsibility for LoongArch architecture.
Signed-off-by: Min Zhou <zhoumin@loongson.cn>
---
MAINTAINERS | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 17a0559ee7..69ea00cddf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -269,6 +269,15 @@ F: lib/eal/include/rte_random.h
F: lib/eal/common/rte_random.c
F: app/test/test_rand_perf.c
+LoongArch
+M: Min Zhou <zhoumin@loongson.cn>
+F: config/loongarch/
+F: lib/eal/loongarch/
+F: lib/*/*_lsx.*
+F: drivers/*/*/*_lsx.*
+F: app/*/*_lsx.*
+F: examples/*/*_lsx.*
+
ARM v7
M: Jan Viktorin <viktorin@rehivetech.com>
M: Ruifeng Wang <ruifeng.wang@arm.com>
--
2.31.1
^ permalink raw reply [flat|nested] 29+ messages in thread