[PATCH net] octeontx2: use arch_extension to enable LSE

[Emanuele Rocca]

Instead of using ".cpu generic+lse", use ".arch_extension lse" to
enable LSE.

The ".cpu generic+lse" directive replaces the assembler's current feature
set with generic+lse, dropping other previously enabled features. In
contrast, ".arch_extension lse" enables LSE while preserving the current
feature set.

For example, the following code is rejected with "selected processor does
not support retaa", because ".cpu generic+lse" drops PAuth even though it
was enabled by armv9-a:

 .arch armv9-a
 .text
 .cpu generic+lse
 retaa

We encountered this issue while building the kernel with GCC configured
using --with-arch=armv9-a. Since Armv9-A includes pointer authentication,
GCC can assume that PAuth instructions are available and may use retaa
when generating PAuth-protected returns.

Fixes: caa2da34fd25a ("octeontx2-pf: Initialize and config queues")
Signed-off-by: Emanuele Rocca <emanuele.rocca@xxxxxxx>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h | 2 +-
 include/linux/soc/marvell/octeontx2/asm.h                | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index eecee612b7b2..c525c557b38e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -786,7 +786,7 @@ static inline u64 otx2_atomic64_add(u64 incr, void __iomem *addr)
 	u64 __iomem *ptr = addr;
 	u64 result;
 
-	__asm__ volatile(".cpu   generic+lse\n"
+	__asm__ volatile(".arch_extension lse\n"
 			 "ldadd %x[i], %x[r], [%[b]]"
 			 : [r]"=r"(result), "+m"(*ptr)
 			 : [i]"r"(incr), [b]"r"(ptr)
diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h
index d683251a0b40..a9d29f5d6eeb 100644
--- a/include/linux/soc/marvell/octeontx2/asm.h
+++ b/include/linux/soc/marvell/octeontx2/asm.h
@@ -17,7 +17,7 @@
 #define otx2_lmt_flush(ioaddr)                          \
 ({                                                      \
 	u64 result = 0;                                 \
-	__asm__ volatile(".cpu  generic+lse\n"          \
+	__asm__ volatile(".arch_extension lse\n"	\
 			 "ldeor xzr, %x[rf], [%[rs]]"   \
 			 : [rf]"=r" (result)            \
 			 : [rs]"r" (ioaddr));           \
@@ -30,7 +30,7 @@
  */
 #define cn10k_lmt_flush(val, addr)			\
 ({							\
-	__asm__ volatile(".cpu  generic+lse\n"		\
+	__asm__ volatile(".arch_extension lse\n"	\
 			 "steorl %x[rf],[%[rs]]"		\
 			 : [rf] "+r"(val)		\
 			 : [rs] "r"(addr));		\
@@ -40,7 +40,7 @@ static inline u64 otx2_atomic64_fetch_add(u64 incr, u64 *ptr)
 {
 	u64 result;
 
-	asm volatile (".cpu  generic+lse\n"
+	asm volatile (".arch_extension lse\n"
 		      "ldadda %x[i], %x[r], [%[b]]"
 		      : [r] "=r" (result), "+m" (*ptr)
 		      : [i] "r" (incr), [b] "r" (ptr)
-- 
2.47.3