riscv: implement remote sfence.i using IPIs

The RISC-V ISA only supports flushing the instruction cache for the
local CPU core.  Currently we always offload the remote TLB flushing to
the SBI, which then issues an IPI under the hoods.  But with M-mode
we do not have an SBI so we have to do it ourselves.   IPI to the
other nodes using the existing kernel helpers instead if we have
native clint support and thus can IPI directly from the kernel.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Anup Patel <[email protected]>
[[email protected]: cleaned up code comment]
Signed-off-by: Paul Walmsley <[email protected]>

Author: Christoph Hellwig

arch/riscv/include/asm/sbi.h

@@ -94,5 +94,8 @@ static inline void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
 {
 	SBI_CALL_4(SBI_REMOTE_SFENCE_VMA_ASID, hart_mask, start, size, asid);
 }
+#else /* CONFIG_RISCV_SBI */
+/* stub for code that is only reachable under IS_ENABLED(CONFIG_RISCV_SBI): */
+void sbi_remote_fence_i(const unsigned long *hart_mask);
 #endif /* CONFIG_RISCV_SBI */
 #endif /* _ASM_RISCV_SBI_H */

arch/riscv/mm/cacheflush.c

@@ -10,9 +10,17 @@
 
 #include <asm/sbi.h>
 
+static void ipi_remote_fence_i(void *info)
+{
+	return local_flush_icache_all();
+}
+
 void flush_icache_all(void)
 {
-	sbi_remote_fence_i(NULL);
+	if (IS_ENABLED(CONFIG_RISCV_SBI))
+		sbi_remote_fence_i(NULL);
+	else
+		on_each_cpu(ipi_remote_fence_i, NULL, 1);
 }
 
 /*
@@ -28,7 +36,7 @@ void flush_icache_all(void)
 void flush_icache_mm(struct mm_struct *mm, bool local)
 {
 	unsigned int cpu;
-	cpumask_t others, hmask, *mask;
+	cpumask_t others, *mask;
 
 	preempt_disable();
 
@@ -46,10 +54,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 	 */
 	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
 	local |= cpumask_empty(&others);
-	if (mm != current->active_mm || !local) {
-		riscv_cpuid_to_hartid_mask(&others, &hmask);
-		sbi_remote_fence_i(hmask.bits);
-	} else {
+	if (mm == current->active_mm && local) {
 		/*
 		 * It's assumed that at least one strongly ordered operation is
 		 * performed on this hart between setting a hart's cpumask bit
@@ -59,6 +64,13 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 * with flush_icache_deferred().
 		 */
 		smp_mb();
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
+		cpumask_t hartid_mask;
+
+		riscv_cpuid_to_hartid_mask(&others, &hartid_mask);
+		sbi_remote_fence_i(cpumask_bits(&hartid_mask));
+	} else {
+		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
 	}
 
 	preempt_enable();