summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/riscv/include/asm/mmu.h2
-rw-r--r--arch/riscv/include/asm/pgtable.h2
-rw-r--r--arch/riscv/include/asm/tlbflush.h18
-rw-r--r--arch/riscv/mm/context.c10
-rw-r--r--arch/riscv/mm/tlbflush.c28
5 files changed, 42 insertions, 18 deletions
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 0099dc116168..5ff1f19fd45c 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,6 +19,8 @@ typedef struct {
#ifdef CONFIG_SMP
/* A local icache flush is needed before user execution can resume. */
cpumask_t icache_stale_mask;
+ /* A local tlb flush is needed before user execution can resume. */
+ cpumask_t tlb_stale_mask;
#endif
} mm_context_t;
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index c61ae83aadee..2359f1f9bda9 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -415,7 +415,7 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
* Relying on flush_tlb_fix_spurious_fault would suffice, but
* the extra traps reduce performance. So, eagerly SFENCE.VMA.
*/
- local_flush_tlb_page(address);
+ flush_tlb_page(vma, address);
}
#define __HAVE_ARCH_UPDATE_MMU_TLB
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 801019381dea..907b9efd39a8 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -22,6 +22,24 @@ static inline void local_flush_tlb_page(unsigned long addr)
{
ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
}
+
+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");
+}
+
#else /* CONFIG_MMU */
#define local_flush_tlb_all() do { } while (0)
#define local_flush_tlb_page(addr) do { } while (0)
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 7acbfbd14557..80ce9caba8d2 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -196,6 +196,16 @@ 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)
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 37ed760d007c..ce7dfc81bb3f 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -5,23 +5,7 @@
#include <linux/sched.h>
#include <asm/sbi.h>
#include <asm/mmu_context.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");
-}
+#include <asm/tlbflush.h>
void flush_tlb_all(void)
{
@@ -31,6 +15,7 @@ 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;
@@ -44,6 +29,15 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
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);
+
if (broadcast) {
sbi_remote_sfence_vma_asid(cmask, start, size, asid);
} else if (size <= stride) {