riscv: Improve flush_tlb_kernel_range()

This function used to simply flush the whole tlb of all harts, be more
subtile and try to only flush the range.

The problem is that we can only use PAGE_SIZE as stride since we don't know
the size of the underlying mapping and then this function will be improved
only if the size of the region to flush is < threshold * PAGE_SIZE.
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> # On RZ/Five SMARC
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://lore.kernel.org/r/20231030133027.19542-5-alexghiti@rivosinc.comSigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/include/asm/tlbflush.h

@@ -40,6 +40,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -56,15 +57,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	local_flush_tlb_all();
 }
 
-#define flush_tlb_mm(mm) flush_tlb_all()
-#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
-
 /* Flush a range of kernel pages */
 static inline void flush_tlb_kernel_range(unsigned long start,
 	unsigned long end)
 {
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
+#define flush_tlb_mm(mm) flush_tlb_all()
+#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#endif /* !CONFIG_SMP || !CONFIG_MMU */
+
 #endif /* _ASM_RISCV_TLBFLUSH_H */

arch/riscv/mm/tlbflush.c

@@ -97,11 +97,14 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 			      unsigned long size, unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	struct cpumask *cmask = mm_cpumask(mm);
+	const struct cpumask *cmask;
 	unsigned long asid = FLUSH_TLB_NO_ASID;
-	unsigned int cpuid;
 	bool broadcast;
 
+	if (mm) {
+		unsigned int cpuid;
+
+		cmask = mm_cpumask(mm);
 		if (cpumask_empty(cmask))
 			return;
 
@@ -111,6 +114,10 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 
 		if (static_branch_unlikely(&use_asid_allocator))
 			asid = atomic_long_read(&mm->context.id) & asid_mask;
+	} else {
+		cmask = cpu_online_mask;
+		broadcast = true;
+	}
 
 	if (broadcast) {
 		if (riscv_use_ipi_for_rfence()) {
@@ -128,6 +135,7 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 		local_flush_tlb_range_asid(start, size, stride, asid);
 	}
 
+	if (mm)
 		put_cpu();
 }
 
@@ -179,6 +187,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 
 	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
 }
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)