riscv: mm: Broadcast kernel TLB flushes only when needed

__flush_tlb_range() avoids broadcasting TLB flushes when an mm context
is only active on the local CPU. Apply this same optimization to TLB
flushes of kernel memory when only one CPU is online. This check can be
constant-folded when SMP is disabled.

Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20240327045035.368512-5-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 0435605b07d0bc4c10014ac8379f83dd50dd3b9d..da821315d43ee3ac0af23588fe7250d6f922972b 100644 (file)
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -103,22 +103,15 @@ static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
                              unsigned long start, unsigned long size,
                              unsigned long stride)
 {
-       bool broadcast;
+       unsigned int cpu;
 
        if (cpumask_empty(cmask))
                return;
 
-       if (cmask != cpu_online_mask) {
-               unsigned int cpuid;
+       cpu = get_cpu();
 
-               cpuid = get_cpu();
-               /* check if the tlbflush needs to be sent to other CPUs */
-               broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-       } else {
-               broadcast = true;
-       }
-
-       if (!broadcast) {
+       /* Check if the TLB flush needs to be sent to other CPUs. */
+       if (cpumask_any_but(cmask, cpu) >= nr_cpu_ids) {
                local_flush_tlb_range_asid(start, size, stride, asid);
        } else if (riscv_use_sbi_for_rfence()) {
                sbi_remote_sfence_vma_asid(cmask, start, size, asid);
@@ -132,8 +125,7 @@ static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
                on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1);
        }
 
-       if (cmask != cpu_online_mask)
-               put_cpu();
+       put_cpu();
 }
 
 static inline unsigned long get_mm_asid(struct mm_struct *mm)