3 files changed, 44 insertions, 33 deletions

diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 80ce9caba8d2..12e22e7330e7 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -22,7 +22,7 @@ DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
 
 static unsigned long asid_bits;
 static unsigned long num_asids;
-static unsigned long asid_mask;
+unsigned long asid_mask;
 
 static atomic_long_t current_version;
 
@@ -196,16 +196,6 @@ switch_mm_fast:
 
 	if (need_flush_tlb)
 		local_flush_tlb_all();
-#ifdef CONFIG_SMP
-	else {
-		cpumask_t *mask = &mm->context.tlb_stale_mask;
-
-		if (cpumask_test_cpu(cpu, mask)) {
-			cpumask_clear_cpu(cpu, mask);
-			local_flush_tlb_all_asid(cntx & asid_mask);
-		}
-	}
-#endif
 }
 
 static void set_mm_noasid(struct mm_struct *mm)
@@ -215,12 +205,24 @@ static void set_mm_noasid(struct mm_struct *mm)
 	local_flush_tlb_all();
 }
 
-static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
 {
-	if (static_branch_unlikely(&use_asid_allocator))
-		set_mm_asid(mm, cpu);
-	else
-		set_mm_noasid(mm);
+	/*
+	 * The mm_cpumask indicates which harts' TLBs contain the virtual
+	 * address mapping of the mm. Compared to noasid, using asid
+	 * can't guarantee that stale TLB entries are invalidated because
+	 * the asid mechanism wouldn't flush TLB for every switch_mm for
+	 * performance. So when using asid, keep all CPUs footmarks in
+	 * cpumask() until mm reset.
+	 */
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (static_branch_unlikely(&use_asid_allocator)) {
+		set_mm_asid(next, cpu);
+	} else {
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		set_mm_noasid(next);
+	}
 }
 
 static int __init asids_init(void)
@@ -274,7 +276,8 @@ static int __init asids_init(void)
 }
 early_initcall(asids_init);
 #else
-static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
 {
 	/* Nothing to do here when there is no MMU */
 }
@@ -327,10 +330,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 */
 	cpu = smp_processor_id();
 
-	cpumask_clear_cpu(cpu, mm_cpumask(prev));
-	cpumask_set_cpu(cpu, mm_cpumask(next));
-
-	set_mm(next, cpu);
+	set_mm(prev, next, cpu);
 
 	flush_icache_deferred(next, cpu);
 }
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 460f785f6e09..d5f3e501dffb 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -143,6 +143,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 		no_context(regs, addr);
 		return;
 	}
+	if (pud_leaf(*pud_k))
+		goto flush_tlb;
 
 	/*
 	 * Since the vmalloc area is global, it is unnecessary
@@ -153,6 +155,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 		no_context(regs, addr);
 		return;
 	}
+	if (pmd_leaf(*pmd_k))
+		goto flush_tlb;
 
 	/*
 	 * Make sure the actual PTE exists as well to
@@ -172,6 +176,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * ordering constraint, not a cache flush; it is
 	 * necessary even after writing invalid entries.
 	 */
+flush_tlb:
 	local_flush_tlb_page(addr);
 }
 
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index ce7dfc81bb3f..ef701fa83f36 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -5,7 +5,23 @@
 #include <linux/sched.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
-#include <asm/tlbflush.h>
+
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma x0, %0"
+			:
+			: "r" (asid)
+			: "memory");
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+		unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma %0, %1"
+			:
+			: "r" (addr), "r" (asid)
+			: "memory");
+}
 
 void flush_tlb_all(void)
 {
@@ -15,7 +31,6 @@ void flush_tlb_all(void)
 static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 				  unsigned long size, unsigned long stride)
 {
-	struct cpumask *pmask = &mm->context.tlb_stale_mask;
 	struct cpumask *cmask = mm_cpumask(mm);
 	unsigned int cpuid;
 	bool broadcast;
@@ -27,16 +42,7 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 	/* check if the tlbflush needs to be sent to other CPUs */
 	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
 	if (static_branch_unlikely(&use_asid_allocator)) {
-		unsigned long asid = atomic_long_read(&mm->context.id);
-
-		/*
-		 * TLB will be immediately flushed on harts concurrently
-		 * executing this MM context. TLB flush on other harts
-		 * is deferred until this MM context migrates there.
-		 */
-		cpumask_setall(pmask);
-		cpumask_clear_cpu(cpuid, pmask);
-		cpumask_andnot(pmask, pmask, cmask);
+		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
 
 		if (broadcast) {
 			sbi_remote_sfence_vma_asid(cmask, start, size, asid);