riscv: fix the IPI missing issue in nommu mode

This patch fixes the IPI(inner processor interrupt) missing issue. It
failed because it used hartid_mask to iterate for_each_cpu(), however the
cpu_mask and hartid_mask may not be always the same. It will never send the
IPI to hartid 4 because it will be skipped in for_each_cpu loop in my case.

We can reproduce this case in Qemu sifive_u machine by this command.
qemu-system-riscv64 -nographic -smp 5 -m 1G -M sifive_u -kernel \
arch/riscv/boot/loader

It will hang in csd_lock_wait(csd) because the csd_unlock(csd) is not
called. It is not called because hartid 4 doesn't receive the IPI to
release this lock. The caller hart doesn't send the IPI to hartid 4 is
because of hartid 4 is skipped in for_each_cpu(). It will be skipped is
because "(cpu) < nr_cpu_ids" is not true. The hartid is 4 and nr_cpu_ids
is 4. Therefore it should use cpumask in for_each_cpu() instead of
hartid_mask.

        /* Send a message to all CPUs in the map */
        arch_send_call_function_ipi_mask(cfd->cpumask_ipi);

        if (wait) {
                for_each_cpu(cpu, cfd->cpumask) {
                        call_single_data_t *csd;
			csd = per_cpu_ptr(cfd->csd, cpu);
                        csd_lock_wait(csd);
                }
        }

        for ((cpu) = -1;                                \
                (cpu) = cpumask_next((cpu), (mask)),    \
                (cpu) < nr_cpu_ids;)

It could boot to login console after this patch applied.

Fixes: b2d36b5668f6 ("riscv: provide native clint access for M-mode")
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>

arch/riscv/include/asm/clint.h

@@ -15,12 +15,12 @@ static inline void clint_send_ipi_single(unsigned long hartid)
 	writel(1, clint_ipi_base + hartid);
 }
 
-static inline void clint_send_ipi_mask(const struct cpumask *hartid_mask)
+static inline void clint_send_ipi_mask(const struct cpumask *mask)
 {
-	int hartid;
+	int cpu;
 
-	for_each_cpu(hartid, hartid_mask)
-		clint_send_ipi_single(hartid);
+	for_each_cpu(cpu, mask)
+		clint_send_ipi_single(cpuid_to_hartid_map(cpu));
 }
 
 static inline void clint_clear_ipi(unsigned long hartid)

arch/riscv/kernel/smp.c

@@ -96,7 +96,7 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
 	if (IS_ENABLED(CONFIG_RISCV_SBI))
 		sbi_send_ipi(cpumask_bits(&hartid_mask));
 	else
-		clint_send_ipi_mask(&hartid_mask);
+		clint_send_ipi_mask(mask);
 }
 
 static void send_ipi_single(int cpu, enum ipi_message_type op)