riscv: mm: Add support for Svinval extension

The Svinval extension splits SFENCE.VMA instruction into finer-grained
invalidation and ordering operations and is mandatory for RVA23S64 profile.
When Svinval is enabled the local_flush_tlb_range_threshold_asid function
should use the following sequence to optimize the tlb flushes instead of
a simple sfence.vma:

sfence.w.inval
svinval.vma
  .
  .
svinval.vma
sfence.inval.ir

The maximum number of consecutive svinval.vma instructions that
can be executed in local_flush_tlb_range_threshold_asid function
is limited to 64. This is required to avoid soft lockups and the
approach is similar to that used in arm64.

Signed-off-by: Mayuresh Chitale <[email protected]>
Reviewed-by: Andrew Jones <[email protected]>
Reviewed-by: Alexandre Ghiti <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexandre Ghiti <[email protected]>
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: mdchitale

arch/riscv/mm/tlbflush.c

@@ -7,6 +7,27 @@
 #include <linux/mmu_notifier.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
+#include <asm/cpufeature.h>
+
+#define has_svinval()	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
+
+static inline void local_sfence_inval_ir(void)
+{
+	asm volatile(SFENCE_INVAL_IR() ::: "memory");
+}
+
+static inline void local_sfence_w_inval(void)
+{
+	asm volatile(SFENCE_W_INVAL() ::: "memory");
+}
+
+static inline void local_sinval_vma(unsigned long vma, unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		asm volatile(SINVAL_VMA(%0, %1) : : "r" (vma), "r" (asid) : "memory");
+	else
+		asm volatile(SINVAL_VMA(%0, zero) : : "r" (vma) : "memory");
+}
 
 /*
  * Flush entire TLB if number of entries to be flushed is greater
@@ -27,6 +48,16 @@ static void local_flush_tlb_range_threshold_asid(unsigned long start,
 		return;
 	}
 
+	if (has_svinval()) {
+		local_sfence_w_inval();
+		for (i = 0; i < nr_ptes_in_range; ++i) {
+			local_sinval_vma(start, asid);
+			start += stride;
+		}
+		local_sfence_inval_ir();
+		return;
+	}
+
 	for (i = 0; i < nr_ptes_in_range; ++i) {
 		local_flush_tlb_page_asid(start, asid);
 		start += stride;