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 <[e-mail]>
Signed-off-by: Palmer Dabbelt <[e-mail]>

arch/riscv/include/asm/cacheflush.h

···
 
 #undef flush_icache_range
 #undef flush_icache_user_range
+#undef flush_dcache_page
 
 static inline void local_flush_icache_all(void)
 {
 	asm volatile ("fence.i" ::: "memory");
 }
 
+#define PG_dcache_clean PG_arch_1
+
+static inline void flush_dcache_page(struct page *page)
+{
+	if (test_bit(PG_dcache_clean, &page->flags))
+		clear_bit(PG_dcache_clean, &page->flags);
+}
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range(start, end) flush_icache_all()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_all()
+
 #ifndef CONFIG_SMP
 
-#define flush_icache_range(start, end) local_flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()
+#define flush_icache_all() local_flush_icache_all()
+#define flush_icache_mm(mm, local) flush_icache_all()
 
 #else /* CONFIG_SMP */
 
-#define flush_icache_range(start, end) sbi_remote_fence_i(0)
-#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)
+#define flush_icache_all() sbi_remote_fence_i(0)
+void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 

arch/riscv/include/asm/mmu.h

···
 
 typedef struct {
 	void *vdso;
+#ifdef CONFIG_SMP
+	/* A local icache flush is needed before user execution can resume. */
+	cpumask_t icache_stale_mask;
+#endif
 } mm_context_t;
 
 #endif /* __ASSEMBLY__ */

arch/riscv/include/asm/mmu_context.h

···
 /*
  * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
···
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm,
 	struct task_struct *task)
···
 	csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
 }
 
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU.  RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches.  To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart.  This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+	unsigned int cpu = smp_processor_id();
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_flush_icache_all();
+	}
+#endif
+}
+
 static inline void switch_mm(struct mm_struct *prev,
 	struct mm_struct *next, struct task_struct *task)
 {
 	if (likely(prev != next)) {
+		/*
+		 * Mark the current MM context as inactive, and the next as
+		 * active.  This is at least used by the icache flushing
+		 * routines in order to determine who should
+		 */
+		unsigned int cpu = smp_processor_id();
+
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
 		set_pgdir(next->pgd);
 		local_flush_tlb_all();
+
+		flush_icache_deferred(next);
 	}
 }
 

arch/riscv/include/asm/pgtable.h

···
 #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);
···
 	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)
 {
···
 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

arch/riscv/include/asm/tlbflush.h

···
 
 #ifdef CONFIG_MMU
 
+#include <linux/mm_types.h>
+
 /* Flush entire local TLB */
 static inline void local_flush_tlb_all(void)
 {

arch/riscv/kernel/smp.c

···
 {
 	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_flush_icache_all();
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+	local |= cpumask_empty(&others);
+	if (mm != current->active_mm || !local)
+		sbi_remote_fence_i(others.bits);
+	else {
+		/*
+		 * It's assumed that at least one strongly ordered operation is
+		 * performed on this hart between setting a hart's cpumask bit
+		 * and scheduling this MM context on that hart.  Sending an SBI
+		 * remote message will do this, but in the case where no
+		 * messages are sent we still need to order this hart's writes
+		 * with flush_icache_deferred().
+		 */
+		smp_mb();
+	}
+
+	preempt_enable();
+}

arch/riscv/mm/Makefile

···
 obj-y += fault.o
 obj-y += extable.o
 obj-y += ioremap.o
+obj-y += cacheflush.o

arch/riscv/mm/cacheflush.c

···
+/*
+ * Copyright (C) 2017 SiFive
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+void flush_icache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		flush_icache_all();
+}