RISC-V: Limit the scope of TLB shootdowns

RISC-V systems perform TLB shootdows via the SBI, which currently
performs an IPI to each of the remote harts which then performs a local
TLB flush.  This process is a bit on the slow side, but we can at least
speed it up for some common cases by restricting the set of harts to
shoot down to the actual set of harts that are currently participating
in the given mm context, as opposed to the entire system.

This should provide a measurable performance increase, but we haven't
measured it.  Regardless, it seems like obviously the right thing to do
here.

Signed-off-by: Andrew Waterman <andrew@sifive.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>

arch/riscv/include/asm/tlbflush.h

@@ -36,7 +36,14 @@ static inline void local_flush_tlb_page(unsigned long addr)
 
 #define flush_tlb_all() local_flush_tlb_all()
 #define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
-#define flush_tlb_range(vma, start, end) local_flush_tlb_all()
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	local_flush_tlb_all();
+}
+
+#define flush_tlb_mm(mm) flush_tlb_all()
 
 #else /* CONFIG_SMP */
 
@@ -45,16 +52,13 @@ static inline void local_flush_tlb_page(unsigned long addr)
 #define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
 #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
 #define flush_tlb_range(vma, start, end) \
-	sbi_remote_sfence_vma(0, start, (end) - (start))
+	sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \
+			      start, (end) - (start))
+#define flush_tlb_mm(mm) \
+	sbi_remote_sfence_vma(mm_cpumask(mm)->bits, 0, -1)
 
 #endif /* CONFIG_SMP */
 
-/* Flush the TLB entries of the specified mm context */
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	flush_tlb_all();
-}
-
 /* Flush a range of kernel pages */
 static inline void flush_tlb_kernel_range(unsigned long start,
 	unsigned long end)