riscv: move switch_mm to its own file

switch_mm is an expensive operations that has two users.
flush_icache_deferred is only called within switch_mm and can be moved
together. The function is expected to be more complicated when ASID
support is added, so clean up eagerly.

By moving them to a separate file we also removes some excessive
dependency of tlbflush.h and cacheflush.h.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>

2 files changed, 70 insertions, 0 deletions

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index b68aac701803..0f1295d8731f 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -9,3 +9,4 @@ obj-y += fault.o
 obj-y += extable.o
 obj-y += ioremap.o
 obj-y += cacheflush.o
+obj-y += context.o
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
new file mode 100644
index 000000000000..89ceb3cbe218
--- /dev/null
+++ b/arch/riscv/mm/context.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/mm.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+/*
+ * 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
+}
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	struct task_struct *task)
+{
+	unsigned int cpu;
+
+	if (unlikely(prev == next))
+		return;
+
+	/*
+	 * 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 be flushed.
+	 */
+	cpu = smp_processor_id();
+
+	cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+
+	/*
+	 * Use the old spbtr name instead of using the current satp
+	 * name to support binutils 2.29 which doesn't know about the
+	 * privileged ISA 1.10 yet.
+	 */
+	csr_write(sptbr, virt_to_pfn(next->pgd) | SATP_MODE);
+	local_flush_tlb_all();
+
+	flush_icache_deferred(next);
+}