riscv: add nommu support

The kernel runs in M-mode without using page tables, and thus can't run
bare metal without help from additional firmware.

Most of the patch is just stubbing out code not needed without page
tables, but there is an interesting detail in the signals implementation:

 - The normal RISC-V syscall ABI only implements rt_sigreturn as VDSO
   entry point, but the ELF VDSO is not supported for nommu Linux.
   We instead copy the code to call the syscall onto the stack.

In addition to enabling the nommu code a new defconfig for a small
kernel image that can run in nommu mode on qemu is also provided, to run
a kernel in qemu you can use the following command line:

qemu-system-riscv64 -smp 2 -m 64 -machine virt -nographic \
	-kernel arch/riscv/boot/loader \
	-drive file=rootfs.ext2,format=raw,id=hd0 \
	-device virtio-blk-device,drive=hd0

Contains contributions from Damien Le Moal <Damien.LeMoal@wdc.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
[paul.walmsley@sifive.com: updated to apply; add CONFIG_MMU guards
 around PCI_IOBASE definition to fix build issues; fixed checkpatch
 issues; move the PCI_IO_* and VMEMMAP address space macros along
 with the others; resolve sparse warning]
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>

4 files changed, 34 insertions, 3 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 2dca51046899..f40205cb9a22 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -25,9 +25,8 @@ obj-y	+= time.o
 obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o
 obj-y	+= stacktrace.o
-obj-y	+= vdso.o
 obj-y	+= cacheinfo.o
-obj-y	+= vdso/
+obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_M_MODE)	+= clint.o
 obj-$(CONFIG_FPU)		+= fpu.o
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b84f8d7f4911..89aecba63f49 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -398,6 +398,10 @@ ENTRY(__switch_to)
 	ret
 ENDPROC(__switch_to)
 
+#ifndef CONFIG_MMU
+#define do_page_fault do_trap_unknown
+#endif
+
 	.section ".rodata"
 	/* Exception vector table */
 ENTRY(excp_vect_table)
@@ -419,3 +423,10 @@ ENTRY(excp_vect_table)
 	RISCV_PTR do_page_fault   /* store page fault */
 excp_vect_table_end:
 END(excp_vect_table)
+
+#ifndef CONFIG_MMU
+ENTRY(__user_rt_sigreturn)
+	li a7, __NR_rt_sigreturn
+	scall
+END(__user_rt_sigreturn)
+#endif
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 64eb8beb228e..84a6f0a4b120 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -109,8 +109,10 @@ clear_bss_done:
 	la sp, init_thread_union + THREAD_SIZE
 	mv a0, s1
 	call setup_vm
+#ifdef CONFIG_MMU
 	la a0, early_pg_dir
 	call relocate
+#endif /* CONFIG_MMU */
 
 	/* Restore C environment */
 	la tp, init_task
@@ -121,6 +123,7 @@ clear_bss_done:
 	call parse_dtb
 	tail start_kernel
 
+#ifdef CONFIG_MMU
 relocate:
 	/* Relocate return address */
 	li a1, PAGE_OFFSET
@@ -171,6 +174,7 @@ relocate:
 	sfence.vma
 
 	ret
+#endif /* CONFIG_MMU */
 
 .Lsecondary_start:
 #ifdef CONFIG_SMP
@@ -196,9 +200,11 @@ relocate:
 	beqz tp, .Lwait_for_cpu_up
 	fence
 
+#ifdef CONFIG_MMU
 	/* Enable virtual memory and relocate to virtual address */
 	la a0, swapper_pg_dir
 	call relocate
+#endif
 
 	tail smp_callin
 #endif
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index b7f9a5565c4b..17ba190e84a5 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -17,11 +17,16 @@
 #include <asm/switch_to.h>
 #include <asm/csr.h>
 
+extern u32 __user_rt_sigreturn[2];
+
 #define DEBUG_SIG 0
 
 struct rt_sigframe {
 	struct siginfo info;
 	struct ucontext uc;
+#ifndef CONFIG_MMU
+	u32 sigreturn_code[2];
+#endif
 };
 
 #ifdef CONFIG_FPU
@@ -166,7 +171,6 @@ static inline void __user *get_sigframe(struct ksignal *ksig,
 	return (void __user *)sp;
 }
 
-
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	struct pt_regs *regs)
 {
@@ -189,8 +193,19 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 		return -EFAULT;
 
 	/* Set up to return from userspace. */
+#ifdef CONFIG_MMU
 	regs->ra = (unsigned long)VDSO_SYMBOL(
 		current->mm->context.vdso, rt_sigreturn);
+#else
+	/*
+	 * For the nommu case we don't have a VDSO.  Instead we push two
+	 * instructions to call the rt_sigreturn syscall onto the user stack.
+	 */
+	if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn,
+			 sizeof(frame->sigreturn_code)))
+		return -EFAULT;
+	regs->ra = (unsigned long)&frame->sigreturn_code;
+#endif /* CONFIG_MMU */
 
 	/*
 	 * Set up registers for signal handler.