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 <[email protected]>.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Anup Patel <[email protected]>
[[email protected]: 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 <[email protected]>

Author: Christoph Hellwig

arch/riscv/Kconfig

@@ -26,14 +26,14 @@ config RISCV
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
+	select GENERIC_STRNCPY_FROM_USER if MMU
+	select GENERIC_STRNLEN_USER if MMU
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_ATOMIC64 if !64BIT
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_CONTIGUOUS
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -50,6 +50,7 @@ config RISCV
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_MSI if PCI
 	select RISCV_TIMER
+	select UACCESS_MEMCPY if !MMU
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_ARCH_TOPOLOGY if SMP
 	select ARCH_HAS_PTE_SPECIAL
@@ -60,7 +61,7 @@ config RISCV
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select SPARSEMEM_STATIC if 32BIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
-	select HAVE_ARCH_MMAP_RND_BITS
+	select HAVE_ARCH_MMAP_RND_BITS if MMU
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
@@ -75,6 +76,7 @@ config ARCH_MMAP_RND_BITS_MAX
 # set if we run in machine mode, cleared if we run in supervisor mode
 config RISCV_M_MODE
 	bool
+	default !MMU
 
 # set if we are running in S-mode and can use SBI calls
 config RISCV_SBI
@@ -83,7 +85,11 @@ config RISCV_SBI
 	default y
 
 config MMU
-	def_bool y
+	bool "MMU-based Paged Memory Management Support"
+	default y
+	help
+	  Select if you want MMU-based virtualised addressing space
+	  support by paged memory management. If unsure, say 'Y'.
 
 config ZONE_DMA32
 	bool
@@ -102,6 +108,7 @@ config PA_BITS
 config PAGE_OFFSET
 	hex
 	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
+	default 0x80000000 if 64BIT && !MMU
 	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
 
@@ -145,7 +152,7 @@ config GENERIC_HWEIGHT
 	def_bool y
 
 config FIX_EARLYCON_MEM
-	def_bool y
+	def_bool CONFIG_MMU
 
 config PGTABLE_LEVELS
 	int
@@ -170,6 +177,7 @@ config ARCH_RV32I
 	select GENERIC_LIB_ASHRDI3
 	select GENERIC_LIB_LSHRDI3
 	select GENERIC_LIB_UCMPDI2
+	select MMU
 
 config ARCH_RV64I
 	bool "RV64I"
@@ -178,9 +186,9 @@ config ARCH_RV64I
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select SWIOTLB
+	select HAVE_DYNAMIC_FTRACE if MMU
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
+	select SWIOTLB if MMU
 
 endchoice
 

arch/riscv/configs/nommu_virt_defconfig

@@ -0,0 +1,78 @@
+# CONFIG_CPU_ISOLATION is not set
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_EXPERT=y
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_FHANDLE is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_IO_URING is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+# CONFIG_MEMBARRIER is not set
+# CONFIG_KALLSYMS is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_SLAB_MERGE_DEFAULT is not set
+# CONFIG_MMU is not set
+CONFIG_MAXPHYSMEM_2GB=y
+CONFIG_SMP=y
+CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0"
+CONFIG_CMDLINE_FORCE=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
+# CONFIG_EFI_PARTITION is not set
+# CONFIG_MQ_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_KYBER is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+CONFIG_VIRTIO_BLK=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_LDISC_AUTOLOAD is not set
+# CONFIG_DEVMEM is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_LCD_CLASS_DEVICE is not set
+# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_SIFIVE_PLIC=y
+# CONFIG_VALIDATE_FS_PARSER is not set
+CONFIG_EXT2_FS=y
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_LSM="[]"
+CONFIG_PRINTK_TIME=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set

arch/riscv/include/asm/cache.h

@@ -11,4 +11,12 @@
 
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+/*
+ * RISC-V requires the stack pointer to be 16-byte aligned, so ensure that
+ * the flat loader aligns it accordingly.
+ */
+#ifndef CONFIG_MMU
+#define ARCH_SLAB_MINALIGN	16
+#endif
+
 #endif /* _ASM_RISCV_CACHE_H */

arch/riscv/include/asm/elf.h

@@ -56,16 +56,16 @@ extern unsigned long elf_hwcap;
  */
 #define ELF_PLATFORM	(NULL)
 
+#ifdef CONFIG_MMU
 #define ARCH_DLINFO						\
 do {								\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
 		(elf_addr_t)current->mm->context.vdso);		\
 } while (0)
-
-
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 	int uses_interp);
+#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_ELF_H */

arch/riscv/include/asm/fixmap.h

@@ -11,6 +11,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_MMU
 /*
  * Here we define all the compile-time 'special' virtual addresses.
  * The point is to have a constant address at compile time, but to
@@ -42,4 +43,5 @@ extern void __set_fixmap(enum fixed_addresses idx,
 
 #include <asm-generic/fixmap.h>
 
+#endif /* CONFIG_MMU */
 #endif /* _ASM_RISCV_FIXMAP_H */

arch/riscv/include/asm/futex.h

@@ -12,6 +12,12 @@
 #include <linux/errno.h>
 #include <asm/asm.h>
 
+/* We don't even really need the extable code, but for now keep it simple */
+#ifndef CONFIG_MMU
+#define __enable_user_access()		do { } while (0)
+#define __disable_user_access()		do { } while (0)
+#endif
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
 {								\
 	uintptr_t tmp;						\

arch/riscv/include/asm/io.h

@@ -24,8 +24,10 @@
 /*
  *  I/O port access constants.
  */
+#ifdef CONFIG_MMU
 #define IO_SPACE_LIMIT		(PCI_IO_SIZE - 1)
 #define PCI_IOBASE		((void __iomem *)PCI_IO_START)
+#endif /* CONFIG_MMU */
 
 /*
  * Emulation routines for the port-mapped IO space used by some PCI drivers.

arch/riscv/include/asm/mmio.h

@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <asm/mmiowb.h>
 
+#ifdef CONFIG_MMU
 void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
 /*
@@ -26,6 +27,9 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 #define ioremap_wt(addr, size) ioremap((addr), (size))
 
 void iounmap(volatile void __iomem *addr);
+#else
+#define pgprot_noncached(x)	(x)
+#endif /* CONFIG_MMU */
 
 /* Generic IO read/write.  These perform native-endian accesses. */
 #define __raw_writeb __raw_writeb

arch/riscv/include/asm/mmu.h

@@ -10,6 +10,9 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
+#ifndef CONFIG_MMU
+	unsigned long	end_brk;
+#endif
 	void *vdso;
 #ifdef CONFIG_SMP
 	/* A local icache flush is needed before user execution can resume. */

arch/riscv/include/asm/page.h

@@ -88,8 +88,14 @@ typedef struct page *pgtable_t;
 #define PTE_FMT "%08lx"
 #endif
 
+#ifdef CONFIG_MMU
 extern unsigned long va_pa_offset;
 extern unsigned long pfn_base;
+#define ARCH_PFN_OFFSET		(pfn_base)
+#else
+#define va_pa_offset		0
+#define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
+#endif /* CONFIG_MMU */
 
 extern unsigned long max_low_pfn;
 extern unsigned long min_low_pfn;
@@ -112,11 +118,9 @@ extern unsigned long min_low_pfn;
 
 #ifdef CONFIG_FLATMEM
 #define pfn_valid(pfn) \
-	(((pfn) >= pfn_base) && (((pfn)-pfn_base) < max_mapnr))
+	(((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr))
 #endif
 
-#define ARCH_PFN_OFFSET		(pfn_base)
-
 #endif /* __ASSEMBLY__ */
 
 #define virt_addr_valid(vaddr)	(pfn_valid(virt_to_pfn(vaddr)))

arch/riscv/include/asm/pgalloc.h

@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <asm/tlb.h>
 
+#ifdef CONFIG_MMU
 #include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -81,5 +82,6 @@ do {                                    \
 	pgtable_pte_page_dtor(pte);     \
 	tlb_remove_page((tlb), pte);    \
 } while (0)
+#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_PGALLOC_H */