RISC-V: Flush I$ when making a dirty page executable

The RISC-V ISA allows for instruction caches that are not coherent WRT
stores, even on a single hart.  As a result, we need to explicitly flush
the instruction cache whenever marking a dirty page as executable in
order to preserve the correct system behavior.

Local instruction caches aren't that scary (our implementations actually
flush the cache, but RISC-V is defined to allow higher-performance
implementations to exist), but RISC-V defines no way to perform an
instruction cache shootdown.  When explicitly asked to do so we can
shoot down remote instruction caches via an IPI, but this is a bit on
the slow side.

Instead of requiring an IPI to all harts whenever marking a page as
executable, we simply flush the currently running harts.  In order to
maintain correct behavior, we additionally mark every other hart as
needing a deferred instruction cache which will be taken before anything
runs on it.

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

1 files changed, 32 insertions, 26 deletions

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 3399257780b2..2cbd92ed1629 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -178,28 +178,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr)
 #define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
 #define pte_unmap(pte)			((void)(pte))
 
-/*
- * Certain architectures need to do special things when PTEs within
- * a page table are directly modified.  Thus, the following hook is
- * made available.
- */
-static inline void set_pte(pte_t *ptep, pte_t pteval)
-{
-	*ptep = pteval;
-}
-
-static inline void set_pte_at(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep, pte_t pteval)
-{
-	set_pte(ptep, pteval);
-}
-
-static inline void pte_clear(struct mm_struct *mm,
-	unsigned long addr, pte_t *ptep)
-{
-	set_pte_at(mm, addr, ptep, __pte(0));
-}
-
 static inline int pte_present(pte_t pte)
 {
 	return (pte_val(pte) & _PAGE_PRESENT);
@@ -210,21 +188,22 @@ static inline int pte_none(pte_t pte)
 	return (pte_val(pte) == 0);
 }
 
-/* static inline int pte_read(pte_t pte) */
-
 static inline int pte_write(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_WRITE;
 }
 
+static inline int pte_exec(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_EXEC;
+}
+
 static inline int pte_huge(pte_t pte)
 {
 	return pte_present(pte)
 		&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
 }
 
-/* static inline int pte_exec(pte_t pte) */
-
 static inline int pte_dirty(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_DIRTY;
@@ -311,6 +290,33 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 	return pte_val(pte_a) == pte_val(pte_b);
 }
 
+/*
+ * Certain architectures need to do special things when PTEs within
+ * a page table are directly modified.  Thus, the following hook is
+ * made available.
+ */
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	*ptep = pteval;
+}
+
+void flush_icache_pte(pte_t pte);
+
+static inline void set_pte_at(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep, pte_t pteval)
+{
+	if (pte_present(pteval) && pte_exec(pteval))
+		flush_icache_pte(pteval);
+
+	set_pte(ptep, pteval);
+}
+
+static inline void pte_clear(struct mm_struct *mm,
+	unsigned long addr, pte_t *ptep)
+{
+	set_pte_at(mm, addr, ptep, __pte(0));
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long address, pte_t *ptep,