riscv: Use IPIs for remote cache/TLB flushes by default

An IPI backend is always required in an SMP configuration, but an SBI
implementation is not. For example, SBI will be unavailable when the
kernel runs in M mode. For this reason, consider IPI delivery of cache
and TLB flushes to be the base case, and any other implementation (such
as the SBI remote fence extension) to be an optimization.

Generally, if IPIs can be delivered without firmware assistance, they
are assumed to be faster than SBI calls due to the SBI context switch
overhead. However, when SBI is used as the IPI backend, then the context
switch cost must be paid anyway, and performing the cache/TLB flush
directly in the SBI implementation is more efficient than injecting an
interrupt to S-mode. This is the only existing scenario where
riscv_ipi_set_virq_range() is called with use_for_rfence set to false.

sbi_ipi_init() already checks riscv_ipi_have_virq_range(), so it only
calls riscv_ipi_set_virq_range() when no other IPI device is available.
This allows moving the static key and dropping the use_for_rfence
parameter. This decouples the static key from the irqchip driver probe
order.

Furthermore, the static branch only makes sense when CONFIG_RISCV_SBI is
enabled. Optherwise, IPIs must be used. Add a fallback definition of
riscv_use_sbi_for_rfence() which handles this case and removes the need
to check CONFIG_RISCV_SBI elsewhere, such as in cacheflush.c.

Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240327045035.368512-4-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

2 files changed, 16 insertions, 20 deletions

diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index bc61ee5975e4..d76fc73e594b 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -21,7 +21,7 @@ void flush_icache_all(void)
 {
 	local_flush_icache_all();
 
-	if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
+	if (riscv_use_sbi_for_rfence())
 		sbi_remote_fence_i(NULL);
 	else
 		on_each_cpu(ipi_remote_fence_i, NULL, 1);
@@ -69,8 +69,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 * with flush_icache_deferred().
 		 */
 		smp_mb();
-	} else if (IS_ENABLED(CONFIG_RISCV_SBI) &&
-		   !riscv_use_ipi_for_rfence()) {
+	} else if (riscv_use_sbi_for_rfence()) {
 		sbi_remote_fence_i(&others);
 	} else {
 		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 893566e004b7..0435605b07d0 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -79,10 +79,10 @@ static void __ipi_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	if (riscv_use_ipi_for_rfence())
-		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
-	else
+	if (riscv_use_sbi_for_rfence())
 		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
+	else
+		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
 }
 
 struct flush_tlb_range_data {
@@ -103,7 +103,6 @@ static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
 			      unsigned long start, unsigned long size,
 			      unsigned long stride)
 {
-	struct flush_tlb_range_data ftd;
 	bool broadcast;
 
 	if (cpumask_empty(cmask))
@@ -119,20 +118,18 @@ static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
 		broadcast = true;
 	}
 
-	if (broadcast) {
-		if (riscv_use_ipi_for_rfence()) {
-			ftd.asid = asid;
-			ftd.start = start;
-			ftd.size = size;
-			ftd.stride = stride;
-			on_each_cpu_mask(cmask,
-					 __ipi_flush_tlb_range_asid,
-					 &ftd, 1);
-		} else
-			sbi_remote_sfence_vma_asid(cmask,
-						   start, size, asid);
-	} else {
+	if (!broadcast) {
 		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);
+	} else {
+		struct flush_tlb_range_data ftd;
+
+		ftd.asid = asid;
+		ftd.start = start;
+		ftd.size = size;
+		ftd.stride = stride;
+		on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1);
 	}
 
 	if (cmask != cpu_online_mask)