RISC-V: Allow userspace to flush the instruction cache

Despite RISC-V having a direct 'fence.i' instruction available to
userspace (which we can't trap!), that's not actually viable when
running on Linux because the kernel might schedule a process on another
hart.  There is no way for userspace to handle this without invoking the
kernel (as it doesn't know the thread->hart mappings), so we've defined
a RISC-V specific system call to flush the instruction cache.

This patch adds both a system call and a VDSO entry.  If possible, we'd
like to avoid having the system call be considered part of the
user-facing ABI and instead restrict that to the VDSO entry -- both just
in general to avoid having additional user-visible ABI to maintain, and
because we'd prefer that users just call the VDSO entry because there
might be a better way to do this in the future (ie, one that doesn't
require entering the kernel).

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

1 files changed, 32 insertions, 0 deletions

diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 4351be7d0533..c6c037eabaf6 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <asm/cmpxchg.h>
 #include <asm/unistd.h>
+#include <asm/cacheflush.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -47,3 +48,34 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
 }
 #endif /* !CONFIG_64BIT */
+
+#ifdef CONFIG_SMP
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+	uintptr_t, flags)
+{
+	struct mm_struct *mm = current->mm;
+	bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
+
+	/* Check the reserved flags. */
+	if (unlikely(flags & !SYS_RISCV_FLUSH_ICACHE_ALL))
+		return -EINVAL;
+
+	flush_icache_mm(mm, local);
+
+	return 0;
+}
+#endif