[v1] eal/arm: fix clang build of native target
Checks
Commit Message
When doing Clang build with '-mcpu=native' on N1 platform, build failed
with:
../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
error: instruction requires: lse
__ATOMIC128_CAS_OP(__cas_128_release, "caspl")
This is because native detection for Neoverse N1 was added in Clang-11.
Prior version of Clang's assembler doesn't know LSE support on hardware.
Fixed this for Clang earlier than version 11 by specifying architecture
for assembler.
Referred to [1] for this fix.
Fixes: 7e2c3e17fe2c ("eal/arm64: add 128-bit atomic compare exchange")
Cc: stable@dpdk.org
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e0d5896bd356cd577f9710a02d7a474cdf58426b
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
lib/librte_eal/arm/include/rte_atomic_64.h | 4 ++++
1 file changed, 4 insertions(+)
Comments
On Thu, Nov 12, 2020 at 4:02 PM Ruifeng Wang <ruifeng.wang@arm.com> wrote:
>
> When doing Clang build with '-mcpu=native' on N1 platform, build failed
> with:
> ../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
> error: instruction requires: lse
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
>
> This is because native detection for Neoverse N1 was added in Clang-11.
> Prior version of Clang's assembler doesn't know LSE support on hardware.
> Fixed this for Clang earlier than version 11 by specifying architecture
> for assembler.
> Referred to [1] for this fix.
>
> Fixes: 7e2c3e17fe2c ("eal/arm64: add 128-bit atomic compare exchange")
> Cc: stable@dpdk.org
>
> [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e0d5896bd356cd577f9710a02d7a474cdf58426b
>
> Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
> ---
> lib/librte_eal/arm/include/rte_atomic_64.h | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/lib/librte_eal/arm/include/rte_atomic_64.h b/lib/librte_eal/arm/include/rte_atomic_64.h
> index 2cef88629..7fcd17466 100644
> --- a/lib/librte_eal/arm/include/rte_atomic_64.h
> +++ b/lib/librte_eal/arm/include/rte_atomic_64.h
> @@ -46,6 +46,8 @@ rte_atomic_thread_fence(int memorder)
> /*------------------------ 128 bit atomic operations -------------------------*/
>
> #if defined(__ARM_FEATURE_ATOMICS) || defined(RTE_ARM_FEATURE_ATOMICS)
> +#define __LSE_PREAMBLE ".arch armv8-a+lse\n"
> +
> #define __ATOMIC128_CAS_OP(cas_op_name, op_string) \
> static __rte_noinline rte_int128_t \
> cas_op_name(rte_int128_t *dst, rte_int128_t old, rte_int128_t updated) \
> @@ -59,6 +61,7 @@ cas_op_name(rte_int128_t *dst, rte_int128_t old, rte_int128_t updated) \
> register uint64_t x2 __asm("x2") = (uint64_t)updated.val[0]; \
> register uint64_t x3 __asm("x3") = (uint64_t)updated.val[1]; \
> asm volatile( \
> + __LSE_PREAMBLE \
> op_string " %[old0], %[old1], %[upd0], %[upd1], [%[dst]]" \
> : [old0] "+r" (x0), \
> [old1] "+r" (x1) \
> @@ -76,6 +79,7 @@ __ATOMIC128_CAS_OP(__cas_128_acquire, "caspa")
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
> __ATOMIC128_CAS_OP(__cas_128_acq_rel, "caspal")
>
> +#undef __LSE_PREAMBLE
> #undef __ATOMIC128_CAS_OP
>
> #endif
> --
> 2.20.1
>
<snip>
>
> When doing Clang build with '-mcpu=native' on N1 platform, build failed
> with:
> ../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
> error: instruction requires: lse
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
>
> This is because native detection for Neoverse N1 was added in Clang-11.
> Prior version of Clang's assembler doesn't know LSE support on hardware.
> Fixed this for Clang earlier than version 11 by specifying architecture for
> assembler.
> Referred to [1] for this fix.
>
> Fixes: 7e2c3e17fe2c ("eal/arm64: add 128-bit atomic compare exchange")
> Cc: stable@dpdk.org
>
> [1]
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i
> d=e0d5896bd356cd577f9710a02d7a474cdf58426b
>
> Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> ---
> lib/librte_eal/arm/include/rte_atomic_64.h | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/lib/librte_eal/arm/include/rte_atomic_64.h
> b/lib/librte_eal/arm/include/rte_atomic_64.h
> index 2cef88629..7fcd17466 100644
> --- a/lib/librte_eal/arm/include/rte_atomic_64.h
> +++ b/lib/librte_eal/arm/include/rte_atomic_64.h
> @@ -46,6 +46,8 @@ rte_atomic_thread_fence(int memorder)
> /*------------------------ 128 bit atomic operations -------------------------*/
>
> #if defined(__ARM_FEATURE_ATOMICS) ||
> defined(RTE_ARM_FEATURE_ATOMICS)
> +#define __LSE_PREAMBLE ".arch armv8-a+lse\n"
> +
> #define __ATOMIC128_CAS_OP(cas_op_name, op_string) \
> static __rte_noinline rte_int128_t \
> cas_op_name(rte_int128_t *dst, rte_int128_t old, rte_int128_t updated)
> \
> @@ -59,6 +61,7 @@ cas_op_name(rte_int128_t *dst, rte_int128_t old,
> rte_int128_t updated) \
> register uint64_t x2 __asm("x2") = (uint64_t)updated.val[0]; \
> register uint64_t x3 __asm("x3") = (uint64_t)updated.val[1]; \
> asm volatile( \
> + __LSE_PREAMBLE
> \
> op_string " %[old0], %[old1], %[upd0], %[upd1], [%[dst]]" \
> : [old0] "+r" (x0), \
> [old1] "+r" (x1) \
> @@ -76,6 +79,7 @@ __ATOMIC128_CAS_OP(__cas_128_acquire, "caspa")
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
> __ATOMIC128_CAS_OP(__cas_128_acq_rel, "caspal")
>
> +#undef __LSE_PREAMBLE
> #undef __ATOMIC128_CAS_OP
>
> #endif
> --
> 2.20.1
> > When doing Clang build with '-mcpu=native' on N1 platform, build failed
> > with:
> > ../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
> > error: instruction requires: lse
> > __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
> >
> > This is because native detection for Neoverse N1 was added in Clang-11.
> > Prior version of Clang's assembler doesn't know LSE support on hardware.
> > Fixed this for Clang earlier than version 11 by specifying architecture for
> > assembler.
> > Referred to [1] for this fix.
> >
> > Fixes: 7e2c3e17fe2c ("eal/arm64: add 128-bit atomic compare exchange")
> > Cc: stable@dpdk.org
> >
> > [1]
> > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i
> > d=e0d5896bd356cd577f9710a02d7a474cdf58426b
> >
> > Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Applied, thanks
@@ -46,6 +46,8 @@ rte_atomic_thread_fence(int memorder)
/*------------------------ 128 bit atomic operations -------------------------*/
#if defined(__ARM_FEATURE_ATOMICS) || defined(RTE_ARM_FEATURE_ATOMICS)
+#define __LSE_PREAMBLE ".arch armv8-a+lse\n"
+
#define __ATOMIC128_CAS_OP(cas_op_name, op_string) \
static __rte_noinline rte_int128_t \
cas_op_name(rte_int128_t *dst, rte_int128_t old, rte_int128_t updated) \
@@ -59,6 +61,7 @@ cas_op_name(rte_int128_t *dst, rte_int128_t old, rte_int128_t updated) \
register uint64_t x2 __asm("x2") = (uint64_t)updated.val[0]; \
register uint64_t x3 __asm("x3") = (uint64_t)updated.val[1]; \
asm volatile( \
+ __LSE_PREAMBLE \
op_string " %[old0], %[old1], %[upd0], %[upd1], [%[dst]]" \
: [old0] "+r" (x0), \
[old1] "+r" (x1) \
@@ -76,6 +79,7 @@ __ATOMIC128_CAS_OP(__cas_128_acquire, "caspa")
__ATOMIC128_CAS_OP(__cas_128_release, "caspl")
__ATOMIC128_CAS_OP(__cas_128_acq_rel, "caspal")
+#undef __LSE_PREAMBLE
#undef __ATOMIC128_CAS_OP
#endif