Merge tag 'riscv-for-linus-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "This contains a handful of new features:

   - Partial support for the Kendryte K210.

     There are still a few outstanding issues that I have patches for,
     but I don't actually have a board to test them so they're not
     included yet.

   - SBI v0.2 support.

   - Fixes to support for building with LLVM-based toolchains. The
     resulting images are known not to boot yet.

  I don't anticipate a part two, but I'll probably have something early
  in the RCs to finish up the K210 support"

* tag 'riscv-for-linus-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (38 commits)
  riscv: create a loader.bin boot image for Kendryte SoC
  riscv: Kendryte K210 default config
  riscv: Add Kendryte K210 device tree
  riscv: Select required drivers for Kendryte SOC
  riscv: Add Kendryte K210 SoC support
  riscv: Add SOC early init support
  riscv: Unaligned load/store handling for M_MODE
  RISC-V: Support cpu hotplug
  RISC-V: Add supported for ordered booting method using HSM
  RISC-V: Add SBI HSM extension definitions
  RISC-V: Export SBI error to linux error mapping function
  RISC-V: Add cpu_ops and modify default booting method
  RISC-V: Move relocate and few other functions out of __init
  RISC-V: Implement new SBI v0.2 extensions
  RISC-V: Introduce a new config for SBI v0.1
  RISC-V: Add SBI v0.2 extension definitions
  RISC-V: Add basic support for SBI v0.2
  RISC-V: Mark existing SBI as 0.1 SBI.
  riscv: Use macro definition instead of magic number
  riscv: Add support to dump the kernel page tables
  ...

arch/riscv/Kconfig

@@ -20,7 +20,6 @@ config RISCV
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_CPU_DEVICES
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
@@ -29,6 +28,7 @@ config RISCV
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_IOREMAP
+	select GENERIC_PTDUMP if MMU
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ASM_MODVERSIONS
@@ -58,6 +58,9 @@ config RISCV
 	select HAVE_EBPF_JIT
 	select EDAC_SUPPORT
 	select ARCH_HAS_GIGANTIC_PAGE
+	select ARCH_HAS_SET_DIRECT_MAP
+	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select SPARSEMEM_STATIC if 32BIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
@@ -129,6 +132,9 @@ config ARCH_SELECT_MEMORY_MODEL
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 
+config ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	def_bool y
+
 config SYS_SUPPORTS_HUGETLBFS
 	def_bool y
 
@@ -247,6 +253,17 @@ config NR_CPUS
 	depends on SMP
 	default "8"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	select GENERIC_IRQ_MIGRATION
+	help
+
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
+	  Say N if you want to disable CPU hotplug.
+
 choice
 	prompt "CPU Tuning"
 	default TUNE_GENERIC
@@ -307,6 +324,13 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
+config RISCV_SBI_V01
+	bool "SBI v0.1 support"
+	default y
+	depends on RISCV_SBI
+	help
+	  This config allows kernel to use SBI v0.1 APIs. This will be
+	  deprecated in future once legacy M-mode software are no longer in use.
 endmenu
 
 menu "Boot options"

arch/riscv/Kconfig.socs

@@ -20,4 +20,14 @@ config SOC_VIRT
        help
          This enables support for QEMU Virt Machine.
 
+config SOC_KENDRYTE
+	bool "Kendryte K210 SoC"
+	depends on !MMU
+	select BUILTIN_DTB
+	select SERIAL_SIFIVE if TTY
+	select SERIAL_SIFIVE_CONSOLE if TTY
+	select SIFIVE_PLIC
+	help
+	  This enables support for Kendryte K210 SoC platform hardware.
+
 endmenu

arch/riscv/Makefile

@@ -85,12 +85,12 @@ PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
 
-ifeq ($(CONFIG_RISCV_M_MODE),y)
-KBUILD_IMAGE := $(boot)/loader
+ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_KENDRYTE),yy)
+KBUILD_IMAGE := $(boot)/loader.bin
 else
 KBUILD_IMAGE := $(boot)/Image.gz
 endif
-BOOT_TARGETS := Image Image.gz loader
+BOOT_TARGETS := Image Image.gz loader loader.bin
 
 all:	$(notdir $(KBUILD_IMAGE))
 

arch/riscv/boot/Makefile

@@ -41,6 +41,9 @@ $(obj)/Image.lzma: $(obj)/Image FORCE
 $(obj)/Image.lzo: $(obj)/Image FORCE
 	$(call if_changed,lzo)
 
+$(obj)/loader.bin: $(obj)/loader FORCE
+	$(call if_changed,objcopy)
+
 install:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"

arch/riscv/boot/dts/Makefile

 # SPDX-License-Identifier: GPL-2.0
 subdir-y += sifive
+subdir-y += kendryte

arch/riscv/boot/dts/kendryte/Makefile

+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_SOC_KENDRYTE) += k210.dtb

arch/riscv/boot/dts/kendryte/k210.dts

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+/dts-v1/;
+
+#include "k210.dtsi"
+
+/ {
+	model = "Kendryte K210 generic";
+	compatible = "kendryte,k210";
+
+	chosen {
+		bootargs = "earlycon console=ttySIF0";
+		stdout-path = "serial0";
+	};
+};
+
+&uarths0 {
+	status = "okay";
+};
+

arch/riscv/boot/dts/kendryte/k210.dtsi

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Sean Anderson <seanga2@gmail.com>
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <dt-bindings/clock/k210-clk.h>
+
+/ {
+	/*
+	 * Although the K210 is a 64-bit CPU, the address bus is only 32-bits
+	 * wide, and the upper half of all addresses is ignored.
+	 */
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "kendryte,k210";
+
+	aliases {
+		serial0 = &uarths0;
+	};
+
+	/*
+	 * The K210 has an sv39 MMU following the priviledge specification v1.9.
+	 * Since this is a non-ratified draft specification, the kernel does not
+	 * support it and the K210 support enabled only for the !MMU case.
+	 * Be consistent with this by setting the CPUs MMU type to "none".
+	 */
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		timebase-frequency = <7800000>;
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			reg = <0>;
+			compatible = "kendryte,k210", "sifive,rocket0", "riscv";
+			riscv,isa = "rv64imafdc";
+			mmu-type = "none";
+			i-cache-size = <0x8000>;
+			i-cache-block-size = <64>;
+			d-cache-size = <0x8000>;
+			d-cache-block-size = <64>;
+			clocks = <&sysctl K210_CLK_CPU>;
+			clock-frequency = <390000000>;
+			cpu0_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				interrupt-controller;
+				compatible = "riscv,cpu-intc";
+			};
+		};
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			reg = <1>;
+			compatible = "kendryte,k210", "sifive,rocket0", "riscv";
+			riscv,isa = "rv64imafdc";
+			mmu-type = "none";
+			i-cache-size = <0x8000>;
+			i-cache-block-size = <64>;
+			d-cache-size = <0x8000>;
+			d-cache-block-size = <64>;
+			clocks = <&sysctl K210_CLK_CPU>;
+			clock-frequency = <390000000>;
+			cpu1_intc: interrupt-controller {
+				#interrupt-cells = <1>;
+				interrupt-controller;
+				compatible = "riscv,cpu-intc";
+			};
+		};
+	};
+
+	sram: memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x400000>,
+		      <0x80400000 0x200000>,
+		      <0x80600000 0x200000>;
+		reg-names = "sram0", "sram1", "aisram";
+	};
+
+	clocks {
+		in0: oscillator {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <26000000>;
+		};
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "kendryte,k210-soc", "simple-bus";
+		ranges;
+		interrupt-parent = <&plic0>;
+
+		sysctl: sysctl@50440000 {
+			compatible = "kendryte,k210-sysctl", "simple-mfd";
+			reg = <0x50440000 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clint0: interrupt-controller@2000000 {
+			compatible = "riscv,clint0";
+			reg = <0x2000000 0xC000>;
+			interrupts-extended = <&cpu0_intc 3>,  <&cpu1_intc 3>;
+			clocks = <&sysctl K210_CLK_ACLK>;
+		};
+
+		plic0: interrupt-controller@c000000 {
+			#interrupt-cells = <1>;
+			interrupt-controller;
+			compatible = "kendryte,k210-plic0", "riscv,plic0";
+			reg = <0xC000000 0x4000000>;
+			interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 0xffffffff>,
+					      <&cpu1_intc 11>, <&cpu1_intc 0xffffffff>;
+			riscv,ndev = <65>;
+			riscv,max-priority = <7>;
+		};
+
+		uarths0: serial@38000000 {
+			compatible = "kendryte,k210-uarths", "sifive,uart0";
+			reg = <0x38000000 0x1000>;
+			interrupts = <33>;
+			clocks = <&sysctl K210_CLK_CPU>;
+		};
+	};
+};

arch/riscv/configs/defconfig

@@ -128,3 +128,4 @@ CONFIG_DEBUG_BLOCK_EXT_DEVT=y
 # CONFIG_FTRACE is not set
 # CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_MEMTEST=y
+# CONFIG_SYSFS_SYSCALL is not set

arch/riscv/configs/nommu_k210_defconfig

+# CONFIG_CPU_ISOLATION is not set
+CONFIG_LOG_BUF_SHIFT=15
+CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_INITRAMFS_FORCE=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_BOOT_CONFIG is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=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_EMBEDDED=y
+# 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_SOC_KENDRYTE=y
+CONFIG_MAXPHYSMEM_2GB=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_CMDLINE="earlycon console=ttySIF0"
+CONFIG_CMDLINE_FORCE=y
+CONFIG_USE_BUILTIN_DTB=y
+CONFIG_BUILTIN_DTB_SOURCE="kendryte/k210"
+# CONFIG_BLOCK 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_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_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_VIRTIO_MENU is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_LSM="[]"
+CONFIG_PRINTK_TIME=y
+# CONFIG_DEBUG_MISC is not set
+# 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/configs/rv32_defconfig

@@ -124,3 +124,4 @@ CONFIG_DEBUG_BLOCK_EXT_DEVT=y
 # CONFIG_FTRACE is not set
 # CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_MEMTEST=y
+# CONFIG_SYSFS_SYSCALL is not set

arch/riscv/include/asm/bug.h

@@ -19,6 +19,14 @@
 #define __BUG_INSN_32	_UL(0x00100073) /* ebreak */
 #define __BUG_INSN_16	_UL(0x9002) /* c.ebreak */
 
+#define GET_INSN_LENGTH(insn)						\
+({									\
+	unsigned long __len;						\
+	__len = ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ?	\
+		4UL : 2UL;						\
+	__len;								\
+})
+
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS

arch/riscv/include/asm/cacheflush.h

@@ -85,7 +85,7 @@ static inline void flush_dcache_page(struct page *page)
  * 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()
+#define flush_icache_user_range(vma, pg, addr, len) flush_icache_mm(vma->vm_mm, 0)
 
 #ifndef CONFIG_SMP
 

arch/riscv/include/asm/cpu_ops.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ * Based on arch/arm64/include/asm/cpu_ops.h
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:		Name of the boot protocol.
+ * @cpu_prepare:	Early one-time preparation step for a cpu. If there
+ *			is a mechanism for doing so, tests whether it is
+ *			possible to boot the given HART.
+ * @cpu_start:		Boots a cpu into the kernel.
+ * @cpu_disable:	Prepares a cpu to die. May fail for some
+ *			mechanism-specific reason, which will cause the hot
+ *			unplug to be aborted. Called from the cpu to be killed.
+ * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
+ *			the cpu being stopped.
+ * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
+ *			cpu.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_prepare)(unsigned int cpu);
+	int		(*cpu_start)(unsigned int cpu,
+				     struct task_struct *tidle);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_stop)(void);
+	int		(*cpu_is_stopped)(unsigned int cpu);
+#endif
+};
+
+extern const struct cpu_operations *cpu_ops[NR_CPUS];
+void __init cpu_set_ops(int cpu);
+void cpu_update_secondary_bootdata(unsigned int cpuid,
+				   struct task_struct *tidle);
+
+#endif /* ifndef __ASM_CPU_OPS_H */

arch/riscv/include/asm/current.h

@@ -17,6 +17,8 @@
 
 struct task_struct;
 
+register struct task_struct *riscv_current_is_tp __asm__("tp");
+
 /*
  * This only works because "struct thread_info" is at offset 0 from "struct
  * task_struct".  This constraint seems to be necessary on other architectures
@@ -26,8 +28,7 @@ struct task_struct;
  */
 static __always_inline struct task_struct *get_current(void)
 {
-	register struct task_struct *tp __asm__("tp");
-	return tp;
+	return riscv_current_is_tp;
 }
 
 #define current get_current()

arch/riscv/include/asm/fixmap.h

@@ -27,6 +27,8 @@ enum fixed_addresses {
 	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
 	FIX_PTE,
 	FIX_PMD,
+	FIX_TEXT_POKE1,
+	FIX_TEXT_POKE0,
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_fixed_addresses
 };

arch/riscv/include/asm/kasan.h

@@ -13,7 +13,7 @@
 #define KASAN_SHADOW_SCALE_SHIFT	3
 
 #define KASAN_SHADOW_SIZE	(UL(1) << (38 - KASAN_SHADOW_SCALE_SHIFT))
-#define KASAN_SHADOW_START	0xffffffc000000000 /* 2^64 - 2^38 */
+#define KASAN_SHADOW_START	KERN_VIRT_START /* 2^64 - 2^38 */
 #define KASAN_SHADOW_END	(KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
 
 #define KASAN_SHADOW_OFFSET	(KASAN_SHADOW_END - (1ULL << \

arch/riscv/include/asm/patch.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef _ASM_RISCV_PATCH_H
+#define _ASM_RISCV_PATCH_H
+
+int riscv_patch_text_nosync(void *addr, const void *insns, size_t len);
+int riscv_patch_text(void *addr, u32 insn);
+
+#endif /* _ASM_RISCV_PATCH_H */

arch/riscv/include/asm/pgtable.h

@@ -448,6 +448,16 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
+/*
+ * In the RV64 Linux scheme, we give the user half of the virtual-address space
+ * and give the kernel the other (upper) half.
+ */
+#ifdef CONFIG_64BIT
+#define KERN_VIRT_START	(-(BIT(CONFIG_VA_BITS)) + TASK_SIZE)
+#else
+#define KERN_VIRT_START	FIXADDR_START
+#endif
+
 /*
  * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
  * Note that PGDIR_SIZE must evenly divide TASK_SIZE.

arch/riscv/include/asm/ptdump.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#ifndef _ASM_RISCV_PTDUMP_H
+#define _ASM_RISCV_PTDUMP_H
+
+void ptdump_check_wx(void);
+
+#endif /* _ASM_RISCV_PTDUMP_H */

arch/riscv/include/asm/sbi.h

 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2015 Regents of the University of California
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
  */
 
 #ifndef _ASM_RISCV_SBI_H
@@ -9,96 +10,148 @@
 #include <linux/types.h>
 
 #ifdef CONFIG_RISCV_SBI
-#define SBI_SET_TIMER 0
-#define SBI_CONSOLE_PUTCHAR 1
-#define SBI_CONSOLE_GETCHAR 2
-#define SBI_CLEAR_IPI 3
-#define SBI_SEND_IPI 4
-#define SBI_REMOTE_FENCE_I 5
-#define SBI_REMOTE_SFENCE_VMA 6
-#define SBI_REMOTE_SFENCE_VMA_ASID 7
-#define SBI_SHUTDOWN 8
-
-#define SBI_CALL(which, arg0, arg1, arg2, arg3) ({		\
-	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);	\
-	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);	\
-	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);	\
-	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);	\
-	register uintptr_t a7 asm ("a7") = (uintptr_t)(which);	\
-	asm volatile ("ecall"					\
-		      : "+r" (a0)				\
-		      : "r" (a1), "r" (a2), "r" (a3), "r" (a7)	\
-		      : "memory");				\
-	a0;							\
-})
-
-/* Lazy implementations until SBI is finalized */
-#define SBI_CALL_0(which) SBI_CALL(which, 0, 0, 0, 0)
-#define SBI_CALL_1(which, arg0) SBI_CALL(which, arg0, 0, 0, 0)
-#define SBI_CALL_2(which, arg0, arg1) SBI_CALL(which, arg0, arg1, 0, 0)
-#define SBI_CALL_3(which, arg0, arg1, arg2) \
-		SBI_CALL(which, arg0, arg1, arg2, 0)
-#define SBI_CALL_4(which, arg0, arg1, arg2, arg3) \
-		SBI_CALL(which, arg0, arg1, arg2, arg3)
-
-static inline void sbi_console_putchar(int ch)
-{
-	SBI_CALL_1(SBI_CONSOLE_PUTCHAR, ch);
-}
+enum sbi_ext_id {
+#ifdef CONFIG_RISCV_SBI_V01
+	SBI_EXT_0_1_SET_TIMER = 0x0,
+	SBI_EXT_0_1_CONSOLE_PUTCHAR = 0x1,
+	SBI_EXT_0_1_CONSOLE_GETCHAR = 0x2,
+	SBI_EXT_0_1_CLEAR_IPI = 0x3,
+	SBI_EXT_0_1_SEND_IPI = 0x4,
+	SBI_EXT_0_1_REMOTE_FENCE_I = 0x5,
+	SBI_EXT_0_1_REMOTE_SFENCE_VMA = 0x6,
+	SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID = 0x7,
+	SBI_EXT_0_1_SHUTDOWN = 0x8,
+#endif
+	SBI_EXT_BASE = 0x10,
+	SBI_EXT_TIME = 0x54494D45,
+	SBI_EXT_IPI = 0x735049,
+	SBI_EXT_RFENCE = 0x52464E43,
+	SBI_EXT_HSM = 0x48534D,
+};
 
-static inline int sbi_console_getchar(void)
-{
-	return SBI_CALL_0(SBI_CONSOLE_GETCHAR);
-}
+enum sbi_ext_base_fid {
+	SBI_EXT_BASE_GET_SPEC_VERSION = 0,
+	SBI_EXT_BASE_GET_IMP_ID,
+	SBI_EXT_BASE_GET_IMP_VERSION,
+	SBI_EXT_BASE_PROBE_EXT,
+	SBI_EXT_BASE_GET_MVENDORID,
+	SBI_EXT_BASE_GET_MARCHID,
+	SBI_EXT_BASE_GET_MIMPID,
+};
 
-static inline void sbi_set_timer(uint64_t stime_value)
-{
-#if __riscv_xlen == 32
-	SBI_CALL_2(SBI_SET_TIMER, stime_value, stime_value >> 32);
-#else
-	SBI_CALL_1(SBI_SET_TIMER, stime_value);
-#endif
-}
+enum sbi_ext_time_fid {
+	SBI_EXT_TIME_SET_TIMER = 0,
+};
 
-static inline void sbi_shutdown(void)
-{
-	SBI_CALL_0(SBI_SHUTDOWN);
-}
+enum sbi_ext_ipi_fid {
+	SBI_EXT_IPI_SEND_IPI = 0,
+};
 
-static inline void sbi_clear_ipi(void)
-{
-	SBI_CALL_0(SBI_CLEAR_IPI);
-}
+enum sbi_ext_rfence_fid {
+	SBI_EXT_RFENCE_REMOTE_FENCE_I = 0,
+	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+	SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+	SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+};
 
-static inline void sbi_send_ipi(const unsigned long *hart_mask)
-{
-	SBI_CALL_1(SBI_SEND_IPI, hart_mask);
-}
+enum sbi_ext_hsm_fid {
+	SBI_EXT_HSM_HART_START = 0,
+	SBI_EXT_HSM_HART_STOP,
+	SBI_EXT_HSM_HART_STATUS,
+};
+
+enum sbi_hsm_hart_status {
+	SBI_HSM_HART_STATUS_STARTED = 0,
+	SBI_HSM_HART_STATUS_STOPPED,
+	SBI_HSM_HART_STATUS_START_PENDING,
+	SBI_HSM_HART_STATUS_STOP_PENDING,
+};
+
+#define SBI_SPEC_VERSION_DEFAULT	0x1
+#define SBI_SPEC_VERSION_MAJOR_SHIFT	24
+#define SBI_SPEC_VERSION_MAJOR_MASK	0x7f
+#define SBI_SPEC_VERSION_MINOR_MASK	0xffffff
+
+/* SBI return error codes */
+#define SBI_SUCCESS		0
+#define SBI_ERR_FAILURE		-1
+#define SBI_ERR_NOT_SUPPORTED	-2
+#define SBI_ERR_INVALID_PARAM	-3
+#define SBI_ERR_DENIED		-4
+#define SBI_ERR_INVALID_ADDRESS	-5
 
-static inline void sbi_remote_fence_i(const unsigned long *hart_mask)
+extern unsigned long sbi_spec_version;
+struct sbiret {
+	long error;
+	long value;
+};
+
+int sbi_init(void);
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5);
+
+void sbi_console_putchar(int ch);
+int sbi_console_getchar(void);
+void sbi_set_timer(uint64_t stime_value);
+void sbi_shutdown(void);
+void sbi_clear_ipi(void);
+void sbi_send_ipi(const unsigned long *hart_mask);
+void sbi_remote_fence_i(const unsigned long *hart_mask);
+void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size);
+
+void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid);
+int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size);
+int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long vmid);
+int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size);
+int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid);
+int sbi_probe_extension(int ext);
+
+/* Check if current SBI specification version is 0.1 or not */
+static inline int sbi_spec_is_0_1(void)
 {
-	SBI_CALL_1(SBI_REMOTE_FENCE_I, hart_mask);
+	return (sbi_spec_version == SBI_SPEC_VERSION_DEFAULT) ? 1 : 0;
 }
 
-static inline void sbi_remote_sfence_vma(const unsigned long *hart_mask,
-					 unsigned long start,
-					 unsigned long size)
+/* Get the major version of SBI */
+static inline unsigned long sbi_major_version(void)
 {
-	SBI_CALL_3(SBI_REMOTE_SFENCE_VMA, hart_mask, start, size);
+	return (sbi_spec_version >> SBI_SPEC_VERSION_MAJOR_SHIFT) &
+		SBI_SPEC_VERSION_MAJOR_MASK;
 }
 
-static inline void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
-					      unsigned long start,
-					      unsigned long size,
-					      unsigned long asid)
+/* Get the minor version of SBI */
+static inline unsigned long sbi_minor_version(void)
 {
-	SBI_CALL_4(SBI_REMOTE_SFENCE_VMA_ASID, hart_mask, start, size, asid);
+	return sbi_spec_version & SBI_SPEC_VERSION_MINOR_MASK;
 }
+
+int sbi_err_map_linux_errno(int err);
 #else /* CONFIG_RISCV_SBI */
 /* stubs for code that is only reachable under IS_ENABLED(CONFIG_RISCV_SBI): */
 void sbi_set_timer(uint64_t stime_value);
 void sbi_clear_ipi(void);
 void sbi_send_ipi(const unsigned long *hart_mask);
 void sbi_remote_fence_i(const unsigned long *hart_mask);
+void sbi_init(void);
 #endif /* CONFIG_RISCV_SBI */
 #endif /* _ASM_RISCV_SBI_H */

arch/riscv/include/asm/set_memory.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#ifndef _ASM_RISCV_SET_MEMORY_H
+#define _ASM_RISCV_SET_MEMORY_H
+
+#ifndef __ASSEMBLY__
+/*
+ * Functions to change memory attributes.
+ */
+#ifdef CONFIG_MMU
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+#else
+static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
+#endif
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+void set_kernel_text_ro(void);
+void set_kernel_text_rw(void);
+#else
+static inline void set_kernel_text_ro(void) { }
+static inline void set_kernel_text_rw(void) { }
+#endif
+
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_ARCH_HAS_STRICT_KERNEL_RWX
+#ifdef CONFIG_64BIT
+#define SECTION_ALIGN (1 << 21)
+#else
+#define SECTION_ALIGN (1 << 22)
+#endif
+#else /* !CONFIG_ARCH_HAS_STRICT_KERNEL_RWX */
+#define SECTION_ALIGN L1_CACHE_BYTES
+#endif /* CONFIG_ARCH_HAS_STRICT_KERNEL_RWX */
+
+#endif /* _ASM_RISCV_SET_MEMORY_H */

arch/riscv/include/asm/smp.h

@@ -43,6 +43,13 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
  */
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
+#if defined CONFIG_HOTPLUG_CPU
+int __cpu_disable(void);
+void __cpu_die(unsigned int cpu);
+void cpu_stop(void);
+#else
+#endif /* CONFIG_HOTPLUG_CPU */
+
 #else
 
 static inline void show_ipi_stats(struct seq_file *p, int prec)
@@ -61,5 +68,22 @@ static inline unsigned long cpuid_to_hartid_map(int cpu)
 	return boot_cpu_hartid;
 }
 
+static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
+					      struct cpumask *out)
+{
+	cpumask_clear(out);
+	cpumask_set_cpu(boot_cpu_hartid, out);
+}
+
 #endif /* CONFIG_SMP */
+
+#if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
+bool cpu_has_hotplug(unsigned int cpu);
+#else
+static inline bool cpu_has_hotplug(unsigned int cpu)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_RISCV_SMP_H */

arch/riscv/include/asm/soc.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_SOC_H
+#define _ASM_RISCV_SOC_H
+
+#include <linux/of.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+#define SOC_EARLY_INIT_DECLARE(name, compat, fn)			\
+	static const struct of_device_id __soc_early_init__##name	\
+		__used __section(__soc_early_init_table)		\
+		 = { .compatible = compat, .data = fn  }
+
+void soc_early_init(void);
+
+extern unsigned long __soc_early_init_table_start;
+extern unsigned long __soc_early_init_table_end;
+
+#endif

arch/riscv/kernel/Makefile

@@ -4,12 +4,14 @@
 #
 
 ifdef CONFIG_FTRACE
-CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_ftrace.o	= -pg
+CFLAGS_REMOVE_patch.o	= -pg
 endif
 
 extra-y += head.o
 extra-y += vmlinux.lds
 
+obj-y	+= soc.o
 obj-y	+= cpu.o
 obj-y	+= cpufeature.o
 obj-y	+= entry.o
@@ -26,12 +28,15 @@ obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o
 obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
+obj-y	+= patch.o
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_M_MODE)	+= clint.o
+obj-$(CONFIG_RISCV_M_MODE)	+= clint.o traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SMP)		+= cpu_ops.o
+obj-$(CONFIG_SMP)		+= cpu_ops_spinwait.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 
@@ -42,5 +47,9 @@ obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 obj-$(CONFIG_RISCV_SBI)		+= sbi.o
+ifeq ($(CONFIG_RISCV_SBI), y)
+obj-$(CONFIG_SMP) += cpu_ops_sbi.o
+endif
+obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
 
 clean:

arch/riscv/kernel/cpu-hotplug.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/cpu.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+
+void cpu_stop(void);
+void arch_cpu_idle_dead(void)
+{
+	cpu_stop();
+}
+
+bool cpu_has_hotplug(unsigned int cpu)
+{
+	if (cpu_ops[cpu]->cpu_stop)
+		return true;
+
+	return false;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	int ret = 0;
+	unsigned int cpu = smp_processor_id();
+
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+		return -EOPNOTSUPP;
+
+	if (cpu_ops[cpu]->cpu_disable)
+		ret = cpu_ops[cpu]->cpu_disable(cpu);
+
+	if (ret)
+		return ret;
+
+	remove_cpu_topology(cpu);
+	set_cpu_online(cpu, false);
+	irq_migrate_all_off_this_cpu();
+
+	return ret;
+}
+
+/*
+ * Called on the thread which is asking for a CPU to be shutdown.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (!cpu_wait_death(cpu, 5)) {
+		pr_err("CPU %u: didn't die\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: off\n", cpu);
+
+	/* Verify from the firmware if the cpu is really stopped*/
+	if (cpu_ops[cpu]->cpu_is_stopped)
+		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (ret)
+		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ */
+void cpu_stop(void)
+{
+	idle_task_exit();
+
+	(void)cpu_report_death();
+
+	cpu_ops[smp_processor_id()]->cpu_stop();
+	/* It should never reach here */
+	BUG();
+}

arch/riscv/kernel/cpu_ops.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+
+void *__cpu_up_stack_pointer[NR_CPUS];
+void *__cpu_up_task_pointer[NR_CPUS];
+
+extern const struct cpu_operations cpu_ops_sbi;
+extern const struct cpu_operations cpu_ops_spinwait;
+
+void cpu_update_secondary_bootdata(unsigned int cpuid,
+				   struct task_struct *tidle)
+{
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
+		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
+}
+
+void __init cpu_set_ops(int cpuid)
+{
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
+		if (!cpuid)
+			pr_info("SBI v0.2 HSM extension detected\n");
+		cpu_ops[cpuid] = &cpu_ops_sbi;
+	} else
+#endif
+		cpu_ops[cpuid] = &cpu_ops_spinwait;
+}

arch/riscv/kernel/cpu_ops_sbi.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HSM extension and cpu_ops implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+extern char secondary_start_sbi[];
+const struct cpu_operations cpu_ops_sbi;
+
+static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
+			      unsigned long priv)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START,
+			hartid, saddr, priv, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_hsm_hart_stop(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0);
+
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+static int sbi_hsm_hart_get_status(unsigned long hartid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS,
+			hartid, 0, 0, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return ret.value;
+}
+#endif
+
+static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	int rc;
+	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	cpu_update_secondary_bootdata(cpuid, tidle);
+	rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
+
+	return rc;
+}
+
+static int sbi_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_cpu_disable(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_stop)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void sbi_cpu_stop(void)
+{
+	int ret;
+
+	ret = sbi_hsm_hart_stop();
+	pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
+}
+
+static int sbi_cpu_is_stopped(unsigned int cpuid)
+{
+	int rc;
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	rc = sbi_hsm_hart_get_status(hartid);
+
+	if (rc == SBI_HSM_HART_STATUS_STOPPED)
+		return 0;
+	return rc;
+}
+#endif
+
+const struct cpu_operations cpu_ops_sbi = {
+	.name		= "sbi",
+	.cpu_prepare	= sbi_cpu_prepare,
+	.cpu_start	= sbi_cpu_start,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= sbi_cpu_disable,
+	.cpu_stop	= sbi_cpu_stop,
+	.cpu_is_stopped	= sbi_cpu_is_stopped,
+#endif
+};

arch/riscv/kernel/cpu_ops_spinwait.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations cpu_ops_spinwait;
+
+static int spinwait_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_spinwait.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	/*
+	 * In this protocol, all cpus boot on their own accord.  _start
+	 * selects the first cpu to boot the kernel and causes the remainder
+	 * of the cpus to spin in a loop waiting for their stack pointer to be
+	 * setup by that main cpu.  Writing to bootdata
+	 * (i.e __cpu_up_stack_pointer) signals to the spinning cpus that they
+	 * can continue the boot process.
+	 */
+	cpu_update_secondary_bootdata(cpuid, tidle);
+
+	return 0;
+}
+
+const struct cpu_operations cpu_ops_spinwait = {
+	.name		= "spinwait",
+	.cpu_prepare	= spinwait_cpu_prepare,
+	.cpu_start	= spinwait_cpu_start,
+};

arch/riscv/kernel/entry.S

@@ -13,17 +13,11 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 
-	.text
-	.altmacro
-
-/*
- * Prepares to enter a system call or exception by saving all registers to the
- * stack.
- */
-	.macro SAVE_ALL
-	LOCAL _restore_kernel_tpsp
-	LOCAL _save_context
+#if !IS_ENABLED(CONFIG_PREEMPTION)
+.set resume_kernel, restore_all
+#endif
 
+ENTRY(handle_exception)
 	/*
 	 * If coming from userspace, preserve the user thread pointer and load
 	 * the kernel thread pointer.  If we came from the kernel, the scratch
@@ -90,77 +84,6 @@ _save_context:
 	REG_S s3, PT_BADADDR(sp)
 	REG_S s4, PT_CAUSE(sp)
 	REG_S s5, PT_TP(sp)
-	.endm
-
-/*
- * Prepares to return from a system call or exception by restoring all
- * registers from the stack.
- */
-	.macro RESTORE_ALL
-	REG_L a0, PT_STATUS(sp)
-	/*
-	 * The current load reservation is effectively part of the processor's
-	 * state, in the sense that load reservations cannot be shared between
-	 * different hart contexts.  We can't actually save and restore a load
-	 * reservation, so instead here we clear any existing reservation --
-	 * it's always legal for implementations to clear load reservations at
-	 * any point (as long as the forward progress guarantee is kept, but
-	 * we'll ignore that here).
-	 *
-	 * Dangling load reservations can be the result of taking a trap in the
-	 * middle of an LR/SC sequence, but can also be the result of a taken
-	 * forward branch around an SC -- which is how we implement CAS.  As a
-	 * result we need to clear reservations between the last CAS and the
-	 * jump back to the new context.  While it is unlikely the store
-	 * completes, implementations are allowed to expand reservations to be
-	 * arbitrarily large.
-	 */
-	REG_L  a2, PT_EPC(sp)
-	REG_SC x0, a2, PT_EPC(sp)
-
-	csrw CSR_STATUS, a0
-	csrw CSR_EPC, a2
-
-	REG_L x1,  PT_RA(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	REG_L x5,  PT_T0(sp)
-	REG_L x6,  PT_T1(sp)
-	REG_L x7,  PT_T2(sp)
-	REG_L x8,  PT_S0(sp)
-	REG_L x9,  PT_S1(sp)
-	REG_L x10, PT_A0(sp)
-	REG_L x11, PT_A1(sp)
-	REG_L x12, PT_A2(sp)
-	REG_L x13, PT_A3(sp)
-	REG_L x14, PT_A4(sp)
-	REG_L x15, PT_A5(sp)
-	REG_L x16, PT_A6(sp)
-	REG_L x17, PT_A7(sp)
-	REG_L x18, PT_S2(sp)
-	REG_L x19, PT_S3(sp)
-	REG_L x20, PT_S4(sp)
-	REG_L x21, PT_S5(sp)
-	REG_L x22, PT_S6(sp)
-	REG_L x23, PT_S7(sp)
-	REG_L x24, PT_S8(sp)
-	REG_L x25, PT_S9(sp)
-	REG_L x26, PT_S10(sp)
-	REG_L x27, PT_S11(sp)
-	REG_L x28, PT_T3(sp)
-	REG_L x29, PT_T4(sp)
-	REG_L x30, PT_T5(sp)
-	REG_L x31, PT_T6(sp)
-
-	REG_L x2,  PT_SP(sp)
-	.endm
-
-#if !IS_ENABLED(CONFIG_PREEMPTION)
-.set resume_kernel, restore_all
-#endif
-
-ENTRY(handle_exception)
-	SAVE_ALL
 
 	/*
 	 * Set the scratch register to 0, so that if a recursive exception
@@ -291,7 +214,63 @@ resume_userspace:
 	csrw CSR_SCRATCH, tp
 
 restore_all:
-	RESTORE_ALL
+	REG_L a0, PT_STATUS(sp)
+	/*
+	 * The current load reservation is effectively part of the processor's
+	 * state, in the sense that load reservations cannot be shared between
+	 * different hart contexts.  We can't actually save and restore a load
+	 * reservation, so instead here we clear any existing reservation --
+	 * it's always legal for implementations to clear load reservations at
+	 * any point (as long as the forward progress guarantee is kept, but
+	 * we'll ignore that here).
+	 *
+	 * Dangling load reservations can be the result of taking a trap in the
+	 * middle of an LR/SC sequence, but can also be the result of a taken
+	 * forward branch around an SC -- which is how we implement CAS.  As a
+	 * result we need to clear reservations between the last CAS and the
+	 * jump back to the new context.  While it is unlikely the store
+	 * completes, implementations are allowed to expand reservations to be
+	 * arbitrarily large.
+	 */
+	REG_L  a2, PT_EPC(sp)
+	REG_SC x0, a2, PT_EPC(sp)
+
+	csrw CSR_STATUS, a0
+	csrw CSR_EPC, a2
+
+	REG_L x1,  PT_RA(sp)
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	REG_L x2,  PT_SP(sp)
+
 #ifdef CONFIG_RISCV_M_MODE
 	mret
 #else

arch/riscv/kernel/ftrace.c

@@ -8,6 +8,7 @@
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/patch.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 static int ftrace_check_current_call(unsigned long hook_pos,
@@ -46,20 +47,14 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 {
 	unsigned int call[2];
 	unsigned int nops[2] = {NOP4, NOP4};
-	int ret = 0;
 
 	make_call(hook_pos, target, call);
 
-	/* replace the auipc-jalr pair at once */
-	ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
-				 MCOUNT_INSN_SIZE);
-	/* return must be -EPERM on write error */
-	if (ret)
+	/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
+	if (riscv_patch_text_nosync
+	    ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
-	smp_mb();
-	flush_icache_range((void *)hook_pos, (void *)hook_pos + MCOUNT_INSN_SIZE);
-
 	return 0;
 }
 

arch/riscv/kernel/head.S

@@ -14,7 +14,7 @@
 #include <asm/hwcap.h>
 #include <asm/image.h>
 
-__INIT
+__HEAD
 ENTRY(_start)
 	/*
 	 * Image header expected by Linux boot-loaders. The image header data
@@ -45,8 +45,111 @@ ENTRY(_start)
 	.ascii RISCV_IMAGE_MAGIC2
 	.word 0
 
-.global _start_kernel
-_start_kernel:
+.align 2
+#ifdef CONFIG_MMU
+relocate:
+	/* Relocate return address */
+	li a1, PAGE_OFFSET
+	la a2, _start
+	sub a1, a1, a2
+	add ra, ra, a1
+
+	/* Point stvec to virtual address of intruction after satp write */
+	la a2, 1f
+	add a2, a2, a1
+	csrw CSR_TVEC, a2
+
+	/* Compute satp for kernel page tables, but don't load it yet */
+	srl a2, a0, PAGE_SHIFT
+	li a1, SATP_MODE
+	or a2, a2, a1
+
+	/*
+	 * Load trampoline page directory, which will cause us to trap to
+	 * stvec if VA != PA, or simply fall through if VA == PA.  We need a
+	 * full fence here because setup_vm() just wrote these PTEs and we need
+	 * to ensure the new translations are in use.
+	 */
+	la a0, trampoline_pg_dir
+	srl a0, a0, PAGE_SHIFT
+	or a0, a0, a1
+	sfence.vma
+	csrw CSR_SATP, a0
+.align 2
+1:
+	/* Set trap vector to spin forever to help debug */
+	la a0, .Lsecondary_park
+	csrw CSR_TVEC, a0
+
+	/* Reload the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+	/*
+	 * Switch to kernel page tables.  A full fence is necessary in order to
+	 * avoid using the trampoline translations, which are only correct for
+	 * the first superpage.  Fetching the fence is guarnteed to work
+	 * because that first superpage is translated the same way.
+	 */
+	csrw CSR_SATP, a2
+	sfence.vma
+
+	ret
+#endif /* CONFIG_MMU */
+#ifdef CONFIG_SMP
+	.global secondary_start_sbi
+secondary_start_sbi:
+	/* Mask all interrupts */
+	csrw CSR_IE, zero
+	csrw CSR_IP, zero
+
+	/* Load the global pointer */
+	.option push
+	.option norelax
+		la gp, __global_pointer$
+	.option pop
+
+	/*
+	 * Disable FPU to detect illegal usage of
+	 * floating point in kernel space
+	 */
+	li t0, SR_FS
+	csrc CSR_STATUS, t0
+
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
+
+	slli a3, a0, LGREG
+	la a4, __cpu_up_stack_pointer
+	la a5, __cpu_up_task_pointer
+	add a4, a3, a4
+	add a5, a3, a5
+	REG_L sp, (a4)
+	REG_L tp, (a5)
+
+	.global secondary_start_common
+secondary_start_common:
+
+#ifdef CONFIG_MMU
+	/* Enable virtual memory and relocate to virtual address */
+	la a0, swapper_pg_dir
+	call relocate
+#endif
+	tail smp_callin
+#endif /* CONFIG_SMP */
+
+.Lsecondary_park:
+	/* We lack SMP support or have too many harts, so park this hart */
+	wfi
+	j .Lsecondary_park
+
+END(_start)
+
+	__INIT
+ENTRY(_start_kernel)
 	/* Mask all interrupts */
 	csrw CSR_IE, zero
 	csrw CSR_IP, zero
@@ -131,62 +234,10 @@ clear_bss_done:
 	call kasan_early_init
 #endif
 	/* Start the kernel */
+	call soc_early_init
 	call parse_dtb
 	tail start_kernel
 
-#ifdef CONFIG_MMU
-relocate:
-	/* Relocate return address */
-	li a1, PAGE_OFFSET
-	la a2, _start
-	sub a1, a1, a2
-	add ra, ra, a1
-
-	/* Point stvec to virtual address of intruction after satp write */
-	la a2, 1f
-	add a2, a2, a1
-	csrw CSR_TVEC, a2
-
-	/* Compute satp for kernel page tables, but don't load it yet */
-	srl a2, a0, PAGE_SHIFT
-	li a1, SATP_MODE
-	or a2, a2, a1
-
-	/*
-	 * Load trampoline page directory, which will cause us to trap to
-	 * stvec if VA != PA, or simply fall through if VA == PA.  We need a
-	 * full fence here because setup_vm() just wrote these PTEs and we need
-	 * to ensure the new translations are in use.
-	 */
-	la a0, trampoline_pg_dir
-	srl a0, a0, PAGE_SHIFT
-	or a0, a0, a1
-	sfence.vma
-	csrw CSR_SATP, a0
-.align 2
-1:
-	/* Set trap vector to spin forever to help debug */
-	la a0, .Lsecondary_park
-	csrw CSR_TVEC, a0
-
-	/* Reload the global pointer */
-.option push
-.option norelax
-	la gp, __global_pointer$
-.option pop
-
-	/*
-	 * Switch to kernel page tables.  A full fence is necessary in order to
-	 * avoid using the trampoline translations, which are only correct for
-	 * the first superpage.  Fetching the fence is guarnteed to work
-	 * because that first superpage is translated the same way.
-	 */
-	csrw CSR_SATP, a2
-	sfence.vma
-
-	ret
-#endif /* CONFIG_MMU */
-
 .Lsecondary_start:
 #ifdef CONFIG_SMP
 	/* Set trap vector to spin forever to help debug */
@@ -211,16 +262,10 @@ 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
+	tail secondary_start_common
 #endif
 
-	tail smp_callin
-#endif
-
-END(_start)
+END(_start_kernel)
 
 #ifdef CONFIG_RISCV_M_MODE
 ENTRY(reset_regs)
@@ -301,13 +346,6 @@ ENTRY(reset_regs)
 END(reset_regs)
 #endif /* CONFIG_RISCV_M_MODE */
 
-.section ".text", "ax",@progbits
-.align 2
-.Lsecondary_park:
-	/* We lack SMP support or have too many harts, so park this hart */
-	wfi
-	j .Lsecondary_park
-
 __PAGE_ALIGNED_BSS
 	/* Empty zero page */
 	.balign PAGE_SIZE

arch/riscv/kernel/patch.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <asm/kprobes.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+
+struct riscv_insn_patch {
+	void *addr;
+	u32 insn;
+	atomic_t cpu_count;
+};
+
+#ifdef CONFIG_MMU
+static DEFINE_RAW_SPINLOCK(patch_lock);
+
+static void __kprobes *patch_map(void *addr, int fixmap)
+{
+	uintptr_t uintaddr = (uintptr_t) addr;
+	struct page *page;
+
+	if (core_kernel_text(uintaddr))
+		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
+	else
+		return addr;
+
+	BUG_ON(!page);
+
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+					 (uintaddr & ~PAGE_MASK));
+}
+
+static void __kprobes patch_unmap(int fixmap)
+{
+	clear_fixmap(fixmap);
+}
+
+static int __kprobes riscv_insn_write(void *addr, const void *insn, size_t len)
+{
+	void *waddr = addr;
+	bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
+	unsigned long flags = 0;
+	int ret;
+
+	raw_spin_lock_irqsave(&patch_lock, flags);
+
+	if (across_pages)
+		patch_map(addr + len, FIX_TEXT_POKE1);
+
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	ret = probe_kernel_write(waddr, insn, len);
+
+	patch_unmap(FIX_TEXT_POKE0);
+
+	if (across_pages)
+		patch_unmap(FIX_TEXT_POKE1);
+
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+	return ret;
+}
+#else
+static int __kprobes riscv_insn_write(void *addr, const void *insn, size_t len)
+{
+	return probe_kernel_write(addr, insn, len);
+}
+#endif /* CONFIG_MMU */
+
+int __kprobes riscv_patch_text_nosync(void *addr, const void *insns, size_t len)
+{
+	u32 *tp = addr;
+	int ret;
+
+	ret = riscv_insn_write(tp, insns, len);
+
+	if (!ret)
+		flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
+
+	return ret;
+}
+
+static int __kprobes riscv_patch_text_cb(void *data)
+{
+	struct riscv_insn_patch *patch = data;
+	int ret = 0;
+
+	if (atomic_inc_return(&patch->cpu_count) == 1) {
+		ret =
+		    riscv_patch_text_nosync(patch->addr, &patch->insn,
+					    GET_INSN_LENGTH(patch->insn));
+		atomic_inc(&patch->cpu_count);
+	} else {
+		while (atomic_read(&patch->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		smp_mb();
+	}
+
+	return ret;
+}
+
+int __kprobes riscv_patch_text(void *addr, u32 insn)
+{
+	struct riscv_insn_patch patch = {
+		.addr = addr,
+		.insn = insn,
+		.cpu_count = ATOMIC_INIT(0),
+	};
+
+	return stop_machine_cpuslocked(riscv_patch_text_cb,
+				       &patch, cpu_online_mask);
+}

arch/riscv/kernel/process.c

@@ -22,6 +22,8 @@
 #include <asm/switch_to.h>
 #include <asm/thread_info.h>
 
+unsigned long gp_in_global __asm__("gp");
+
 extern asmlinkage void ret_from_fork(void);
 extern asmlinkage void ret_from_kernel_thread(void);
 
@@ -107,9 +109,8 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 	/* p->thread holds context to be restored by __switch_to() */
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* Kernel thread */
-		const register unsigned long gp __asm__ ("gp");
 		memset(childregs, 0, sizeof(struct pt_regs));
-		childregs->gp = gp;
+		childregs->gp = gp_in_global;
 		/* Supervisor/Machine, irqs on: */
 		childregs->status = SR_PP | SR_PIE;
 

arch/riscv/kernel/setup.c

@@ -16,12 +16,14 @@
 #include <linux/of_platform.h>
 #include <linux/sched/task.h>
 #include <linux/swiotlb.h>
+#include <linux/smp.h>
 
 #include <asm/clint.h>
+#include <asm/cpu_ops.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
-#include <asm/smp.h>
+#include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
 #include <asm/kasan.h>
@@ -39,9 +41,14 @@ struct screen_info screen_info = {
 };
 #endif
 
-/* The lucky hart to first increment this variable will boot the other cores */
-atomic_t hart_lottery;
+/*
+ * The lucky hart to first increment this variable will boot the other cores.
+ * This is used before the kernel initializes the BSS so it can't be in the
+ * BSS.
+ */
+atomic_t hart_lottery __section(.sdata);
 unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 void __init parse_dtb(void)
 {
@@ -79,9 +86,28 @@ void __init setup_arch(char **cmdline_p)
 	kasan_init();
 #endif
 
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	sbi_init();
+#endif
+
 #ifdef CONFIG_SMP
 	setup_smp();
 #endif
 
 	riscv_fill_hwcap();
 }
+
+static int __init topology_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+		cpu->hotpluggable = cpu_has_hotplug(i);
+		register_cpu(cpu, i);
+	}
+
+	return 0;
+}
+subsys_initcall(topology_init);

arch/riscv/kernel/smpboot.c

@@ -25,6 +25,7 @@
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
 #include <asm/clint.h>
+#include <asm/cpu_ops.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -34,8 +35,6 @@
 
 #include "head.h"
 
-void *__cpu_up_stack_pointer[NR_CPUS];
-void *__cpu_up_task_pointer[NR_CPUS];
 static DECLARE_COMPLETION(cpu_running);
 
 void __init smp_prepare_boot_cpu(void)
@@ -46,6 +45,7 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
+	int ret;
 
 	/* This covers non-smp usecase mandated by "nosmp" option */
 	if (max_cpus == 0)
@@ -54,6 +54,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(cpuid) {
 		if (cpuid == smp_processor_id())
 			continue;
+		if (cpu_ops[cpuid]->cpu_prepare) {
+			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
+			if (ret)
+				continue;
+		}
 		set_cpu_present(cpuid, true);
 	}
 }
@@ -65,6 +70,8 @@ void __init setup_smp(void)
 	bool found_boot_cpu = false;
 	int cpuid = 1;
 
+	cpu_set_ops(0);
+
 	for_each_of_cpu_node(dn) {
 		hart = riscv_of_processor_hartid(dn);
 		if (hart < 0)
@@ -92,36 +99,38 @@ void __init setup_smp(void)
 			cpuid, nr_cpu_ids);
 
 	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
+			cpu_set_ops(cpuid);
 			set_cpu_possible(cpuid, true);
+		}
 	}
 }
 
+int start_secondary_cpu(int cpu, struct task_struct *tidle)
+{
+	if (cpu_ops[cpu]->cpu_start)
+		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+
+	return -EOPNOTSUPP;
+}
+
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int ret = 0;
-	int hartid = cpuid_to_hartid_map(cpu);
 	tidle->thread_info.cpu = cpu;
 
-	/*
-	 * On RISC-V systems, all harts boot on their own accord.  Our _start
-	 * selects the first hart to boot the kernel and causes the remainder
-	 * of the harts to spin in a loop waiting for their stack pointer to be
-	 * setup by that main hart.  Writing __cpu_up_stack_pointer signals to
-	 * the spinning harts that they can continue the boot process.
-	 */
-	smp_mb();
-	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
-		  task_stack_page(tidle) + THREAD_SIZE);
-	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
-
-	lockdep_assert_held(&cpu_running);
-	wait_for_completion_timeout(&cpu_running,
+	ret = start_secondary_cpu(cpu, tidle);
+	if (!ret) {
+		lockdep_assert_held(&cpu_running);
+		wait_for_completion_timeout(&cpu_running,
 					    msecs_to_jiffies(1000));
 
-	if (!cpu_online(cpu)) {
-		pr_crit("CPU%u: failed to come online\n", cpu);
-		ret = -EIO;
+		if (!cpu_online(cpu)) {
+			pr_crit("CPU%u: failed to come online\n", cpu);
+			ret = -EIO;
+		}
+	} else {
+		pr_crit("CPU%u: failed to start\n", cpu);
 	}
 
 	return ret;
@@ -134,7 +143,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 /*
  * C entry point for a secondary processor.
  */
-asmlinkage __visible void __init smp_callin(void)
+asmlinkage __visible void smp_callin(void)
 {
 	struct mm_struct *mm = &init_mm;
 

arch/riscv/kernel/soc.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/init.h>
+#include <linux/libfdt.h>
+#include <asm/pgtable.h>
+#include <asm/soc.h>
+
+/*
+ * This is called extremly early, before parse_dtb(), to allow initializing
+ * SoC hardware before memory or any device driver initialization.
+ */
+void __init soc_early_init(void)
+{
+	void (*early_fn)(const void *fdt);
+	const struct of_device_id *s;
+	const void *fdt = dtb_early_va;
+
+	for (s = (void *)&__soc_early_init_table_start;
+	     (void *)s < (void *)&__soc_early_init_table_end; s++) {
+		if (!fdt_node_check_compatible(fdt, 0, s->compatible)) {
+			early_fn = s->data;
+			early_fn(fdt);
+			return;
+		}
+	}
+}

arch/riscv/kernel/stacktrace.c

@@ -19,6 +19,8 @@ struct stackframe {
 	unsigned long ra;
 };
 
+register unsigned long sp_in_global __asm__("sp");
+
 void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			     bool (*fn)(unsigned long, void *), void *arg)
 {
@@ -29,7 +31,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 		sp = user_stack_pointer(regs);
 		pc = instruction_pointer(regs);
 	} else if (task == NULL || task == current) {
-		const register unsigned long current_sp __asm__ ("sp");
+		const register unsigned long current_sp = sp_in_global;
 		fp = (unsigned long)__builtin_frame_address(0);
 		sp = current_sp;
 		pc = (unsigned long)walk_stackframe;
@@ -73,8 +75,7 @@ static void notrace walk_stackframe(struct task_struct *task,
 		sp = user_stack_pointer(regs);
 		pc = instruction_pointer(regs);
 	} else if (task == NULL || task == current) {
-		const register unsigned long current_sp __asm__ ("sp");
-		sp = current_sp;
+		sp = sp_in_global;
 		pc = (unsigned long)walk_stackframe;
 	} else {
 		/* task blocked in __switch_to */

arch/riscv/kernel/traps.c

@@ -97,12 +97,33 @@ DO_ERROR_INFO(do_trap_insn_fault,
 	SIGSEGV, SEGV_ACCERR, "instruction access fault");
 DO_ERROR_INFO(do_trap_insn_illegal,
 	SIGILL, ILL_ILLOPC, "illegal instruction");
-DO_ERROR_INFO(do_trap_load_misaligned,
-	SIGBUS, BUS_ADRALN, "load address misaligned");
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
+#ifndef CONFIG_RISCV_M_MODE
+DO_ERROR_INFO(do_trap_load_misaligned,
+	SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
 DO_ERROR_INFO(do_trap_store_misaligned,
-	SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned");
+	SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
+#else
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+
+asmlinkage void do_trap_load_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_load(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - load address misaligned");
+}
+
+asmlinkage void do_trap_store_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_store(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - store (or AMO) address misaligned");
+}
+#endif
 DO_ERROR_INFO(do_trap_store_fault,
 	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
 DO_ERROR_INFO(do_trap_ecall_u,
@@ -118,7 +139,8 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 
 	if (probe_kernel_address((bug_insn_t *)pc, insn))
 		return 0;
-	return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL);
+
+	return GET_INSN_LENGTH(insn);
 }
 
 asmlinkage __visible void do_trap_break(struct pt_regs *regs)
@@ -147,7 +169,7 @@ int is_valid_bugaddr(unsigned long pc)
 }
 #endif /* CONFIG_GENERIC_BUG */
 
-void __init trap_init(void)
+void trap_init(void)
 {
 	/*
 	 * Set sup0 scratch register to 0, indicating to exception vector

arch/riscv/kernel/vmlinux.lds.S

@@ -9,7 +9,9 @@
 #include <asm/page.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
+#include <asm/set_memory.h>
 
+#include <linux/sizes.h>
 OUTPUT_ARCH(riscv)
 ENTRY(_start)
 
@@ -20,10 +22,18 @@ SECTIONS
 	/* Beginning of code and text segment */
 	. = LOAD_OFFSET;
 	_start = .;
-	__init_begin = .;
 	HEAD_TEXT_SECTION
+	. = ALIGN(PAGE_SIZE);
+
+	__init_begin = .;
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
+	. = ALIGN(8);
+	__soc_early_init_table : {
+		__soc_early_init_table_start = .;
+		KEEP(*(__soc_early_init_table))
+		__soc_early_init_table_end = .;
+	}
 	/* we have to discard exit text and such at runtime, not link time */
 	.exit.text :
 	{
@@ -36,6 +46,7 @@ SECTIONS
 	PERCPU_SECTION(L1_CACHE_BYTES)
 	__init_end = .;
 
+	. = ALIGN(SECTION_ALIGN);
 	.text : {
 		_text = .;
 		_stext = .;
@@ -53,24 +64,26 @@ SECTIONS
 
 	/* Start of data section */
 	_sdata = .;
-	RO_DATA(L1_CACHE_BYTES)
+	RO_DATA(SECTION_ALIGN)
 	.srodata : {
 		*(.srodata*)
 	}
 
+	EXCEPTION_TABLE(0x10)
+
+	. = ALIGN(SECTION_ALIGN);
+	_data = .;
+
 	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	.sdata : {
 		__global_pointer$ = . + 0x800;
 		*(.sdata*)
 		/* End of data section */
 		_edata = .;
-		*(.sbss*)
 	}
 
 	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
 
-	EXCEPTION_TABLE(0x10)
-
 	.rel.dyn : {
 		*(.rel.dyn*)
 	}

arch/riscv/lib/uaccess.S

@@ -3,14 +3,12 @@
 #include <asm/asm.h>
 #include <asm/csr.h>
 
-	.altmacro
 	.macro fixup op reg addr lbl
-	LOCAL _epc
-_epc:
+100:
 	\op \reg, \addr
 	.section __ex_table,"a"
 	.balign RISCV_SZPTR
-	RISCV_PTR _epc, \lbl
+	RISCV_PTR 100b, \lbl
 	.previous
 	.endm
 

arch/riscv/mm/Makefile

@@ -7,7 +7,7 @@ endif
 
 obj-y += init.o
 obj-y += extable.o
-obj-$(CONFIG_MMU) += fault.o
+obj-$(CONFIG_MMU) += fault.o pageattr.o
 obj-y += cacheflush.o
 obj-y += context.o
 
@@ -15,6 +15,7 @@ ifeq ($(CONFIG_MMU),y)
 obj-$(CONFIG_SMP) += tlbflush.o
 endif
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_KASAN)   += kasan_init.o
 
 ifdef CONFIG_KASAN

arch/riscv/mm/hugetlbpage.c

@@ -4,14 +4,12 @@
 
 int pud_huge(pud_t pud)
 {
-	return pud_present(pud) &&
-		(pud_val(pud) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pud_leaf(pud);
 }
 
 int pmd_huge(pmd_t pmd)
 {
-	return pmd_present(pmd) &&
-		(pmd_val(pmd) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pmd_leaf(pmd);
 }
 
 static __init int setup_hugepagesz(char *opt)

arch/riscv/mm/init.c

@@ -12,6 +12,7 @@
 #include <linux/sizes.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <linux/set_memory.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -477,6 +478,17 @@ static void __init setup_vm_final(void)
 	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
 	local_flush_tlb_all();
 }
+
+void free_initmem(void)
+{
+	unsigned long init_begin = (unsigned long)__init_begin;
+	unsigned long init_end = (unsigned long)__init_end;
+
+	/* Make the region as non-execuatble. */
+	set_memory_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT);
+	free_initmem_default(POISON_FREE_INITMEM);
+}
+
 #else
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
@@ -488,6 +500,38 @@ static inline void setup_vm_final(void)
 }
 #endif /* CONFIG_MMU */
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+void set_kernel_text_rw(void)
+{
+	unsigned long text_start = (unsigned long)_text;
+	unsigned long text_end = (unsigned long)_etext;
+
+	set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long text_start = (unsigned long)_text;
+	unsigned long text_end = (unsigned long)_etext;
+
+	set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT);
+}
+
+void mark_rodata_ro(void)
+{
+	unsigned long text_start = (unsigned long)_text;
+	unsigned long text_end = (unsigned long)_etext;
+	unsigned long rodata_start = (unsigned long)__start_rodata;
+	unsigned long data_start = (unsigned long)_data;
+	unsigned long max_low = (unsigned long)(__va(PFN_PHYS(max_low_pfn)));
+
+	set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT);
+	set_memory_ro(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(data_start, (max_low - data_start) >> PAGE_SHIFT);
+}
+#endif
+
 void __init paging_init(void)
 {
 	setup_vm_final();

arch/riscv/mm/pageattr.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/pagewalk.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/bitops.h>
+
+struct pageattr_masks {
+	pgprot_t set_mask;
+	pgprot_t clear_mask;
+};
+
+static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
+{
+	struct pageattr_masks *masks = walk->private;
+	unsigned long new_val = val;
+
+	new_val &= ~(pgprot_val(masks->clear_mask));
+	new_val |= (pgprot_val(masks->set_mask));
+
+	return new_val;
+}
+
+static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pgd_t val = READ_ONCE(*pgd);
+
+	if (pgd_leaf(val)) {
+		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
+		set_pgd(pgd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	p4d_t val = READ_ONCE(*p4d);
+
+	if (p4d_leaf(val)) {
+		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
+		set_p4d(p4d, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pud_t val = READ_ONCE(*pud);
+
+	if (pud_leaf(val)) {
+		val = __pud(set_pageattr_masks(pud_val(val), walk));
+		set_pud(pud, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pmd_t val = READ_ONCE(*pmd);
+
+	if (pmd_leaf(val)) {
+		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
+		set_pmd(pmd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pte_t val = READ_ONCE(*pte);
+
+	val = __pte(set_pageattr_masks(pte_val(val), walk));
+	set_pte(pte, val);
+
+	return 0;
+}
+
+static int pageattr_pte_hole(unsigned long addr, unsigned long next,
+			     int depth, struct mm_walk *walk)
+{
+	/* Nothing to do here */
+	return 0;
+}
+
+const static struct mm_walk_ops pageattr_ops = {
+	.pgd_entry = pageattr_pgd_entry,
+	.p4d_entry = pageattr_p4d_entry,
+	.pud_entry = pageattr_pud_entry,
+	.pmd_entry = pageattr_pmd_entry,
+	.pte_entry = pageattr_pte_entry,
+	.pte_hole = pageattr_pte_hole,
+};
+
+static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
+			pgprot_t clear_mask)
+{
+	int ret;
+	unsigned long start = addr;
+	unsigned long end = start + PAGE_SIZE * numpages;
+	struct pageattr_masks masks = {
+		.set_mask = set_mask,
+		.clear_mask = clear_mask
+	};
+
+	if (!numpages)
+		return 0;
+
+	down_read(&init_mm.mmap_sem);
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+	up_read(&init_mm.mmap_sem);
+
+	flush_tlb_kernel_range(start, end);
+
+	return ret;
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ),
+			    __pgprot(_PAGE_WRITE));
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE),
+			    __pgprot(0));
+}
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_EXEC), __pgprot(0));
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_EXEC));
+}
+
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	unsigned long start = (unsigned long)page_address(page);
+	unsigned long end = start + PAGE_SIZE;
+	struct pageattr_masks masks = {
+		.set_mask = __pgprot(0),
+		.clear_mask = __pgprot(_PAGE_PRESENT)
+	};
+
+	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	unsigned long start = (unsigned long)page_address(page);
+	unsigned long end = start + PAGE_SIZE;
+	struct pageattr_masks masks = {
+		.set_mask = PAGE_KERNEL,
+		.clear_mask = __pgprot(0)
+	};
+
+	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+}
+
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	if (enable)
+		__set_memory((unsigned long)page_address(page), numpages,
+			     __pgprot(_PAGE_PRESENT), __pgprot(0));
+	else
+		__set_memory((unsigned long)page_address(page), numpages,
+			     __pgprot(0), __pgprot(_PAGE_PRESENT));
+}

arch/riscv/mm/ptdump.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/ptdump.h>
+
+#include <asm/ptdump.h>
+#include <asm/pgtable.h>
+#include <asm/kasan.h>
+
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)	\
+({					\
+	if (m)				\
+		seq_printf(m, fmt);	\
+})
+
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
+struct pg_state {
+	struct ptdump_state ptdump;
+	struct seq_file *seq;
+	const struct addr_marker *marker;
+	unsigned long start_address;
+	unsigned long start_pa;
+	unsigned long last_pa;
+	int level;
+	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
+};
+
+/* Address marker */
+struct addr_marker {
+	unsigned long start_address;
+	const char *name;
+};
+
+static struct addr_marker address_markers[] = {
+#ifdef CONFIG_KASAN
+	{KASAN_SHADOW_START,	"Kasan shadow start"},
+	{KASAN_SHADOW_END,	"Kasan shadow end"},
+#endif
+	{FIXADDR_START,		"Fixmap start"},
+	{FIXADDR_TOP,		"Fixmap end"},
+	{PCI_IO_START,		"PCI I/O start"},
+	{PCI_IO_END,		"PCI I/O end"},
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	{VMEMMAP_START,		"vmemmap start"},
+	{VMEMMAP_END,		"vmemmap end"},
+#endif
+	{VMALLOC_START,		"vmalloc() area"},
+	{VMALLOC_END,		"vmalloc() end"},
+	{PAGE_OFFSET,		"Linear mapping"},
+	{-1, NULL},
+};
+
+/* Page Table Entry */
+struct prot_bits {
+	u64 mask;
+	u64 val;
+	const char *set;
+	const char *clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+	{
+		.mask = _PAGE_SOFT,
+		.val = _PAGE_SOFT,
+		.set = "RSW",
+		.clear = "   ",
+	}, {
+		.mask = _PAGE_DIRTY,
+		.val = _PAGE_DIRTY,
+		.set = "D",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_ACCESSED,
+		.val = _PAGE_ACCESSED,
+		.set = "A",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_GLOBAL,
+		.val = _PAGE_GLOBAL,
+		.set = "G",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_USER,
+		.val = _PAGE_USER,
+		.set = "U",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_EXEC,
+		.val = _PAGE_EXEC,
+		.set = "X",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_WRITE,
+		.val = _PAGE_WRITE,
+		.set = "W",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_READ,
+		.val = _PAGE_READ,
+		.set = "R",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_PRESENT,
+		.val = _PAGE_PRESENT,
+		.set = "V",
+		.clear = ".",
+	}
+};
+
+/* Page Level */
+struct pg_level {
+	const char *name;
+	u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+	{ /* pgd */
+		.name = "PGD",
+	}, { /* p4d */
+		.name = (CONFIG_PGTABLE_LEVELS > 4) ? "P4D" : "PGD",
+	}, { /* pud */
+		.name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
+	}, { /* pmd */
+		.name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
+	}, { /* pte */
+		.name = "PTE",
+	},
+};
+
+static void dump_prot(struct pg_state *st)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(pte_bits); i++) {
+		const char *s;
+
+		if ((st->current_prot & pte_bits[i].mask) == pte_bits[i].val)
+			s = pte_bits[i].set;
+		else
+			s = pte_bits[i].clear;
+
+		if (s)
+			pt_dump_seq_printf(st->seq, " %s", s);
+	}
+}
+
+#ifdef CONFIG_64BIT
+#define ADDR_FORMAT	"0x%016lx"
+#else
+#define ADDR_FORMAT	"0x%08lx"
+#endif
+static void dump_addr(struct pg_state *st, unsigned long addr)
+{
+	static const char units[] = "KMGTPE";
+	const char *unit = units;
+	unsigned long delta;
+
+	pt_dump_seq_printf(st->seq, ADDR_FORMAT "-" ADDR_FORMAT "   ",
+			   st->start_address, addr);
+
+	pt_dump_seq_printf(st->seq, " " ADDR_FORMAT " ", st->start_pa);
+	delta = (addr - st->start_address) >> 10;
+
+	while (!(delta & 1023) && unit[1]) {
+		delta >>= 10;
+		unit++;
+	}
+
+	pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+			   pg_level[st->level].name);
+}
+
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+
+	if ((st->current_prot & (_PAGE_WRITE | _PAGE_EXEC)) !=
+	    (_PAGE_WRITE | _PAGE_EXEC))
+		return;
+
+	WARN_ONCE(1, "riscv/mm: Found insecure W+X mapping at address %p/%pS\n",
+		  (void *)st->start_address, (void *)st->start_address);
+
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_page(struct ptdump_state *pt_st, unsigned long addr,
+		      int level, unsigned long val)
+{
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	u64 pa = PFN_PHYS(pte_pfn(__pte(val)));
+	u64 prot = 0;
+
+	if (level >= 0)
+		prot = val & pg_level[level].mask;
+
+	if (st->level == -1) {
+		st->level = level;
+		st->current_prot = prot;
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+	} else if (prot != st->current_prot ||
+		   level != st->level || addr >= st->marker[1].start_address) {
+		if (st->current_prot) {
+			note_prot_wx(st, addr);
+			dump_addr(st, addr);
+			dump_prot(st);
+			pt_dump_seq_puts(st->seq, "\n");
+		}
+
+		while (addr >= st->marker[1].start_address) {
+			st->marker++;
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n",
+					   st->marker->name);
+		}
+
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		st->current_prot = prot;
+		st->level = level;
+	} else {
+		st->last_pa = pa;
+	}
+}
+
+static void ptdump_walk(struct seq_file *s)
+{
+	struct pg_state st = {
+		.seq = s,
+		.marker = address_markers,
+		.level = -1,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{KERN_VIRT_START, ULONG_MAX},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+}
+
+void ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = (struct addr_marker[]) {
+			{0, NULL},
+			{-1, NULL},
+		},
+		.level = -1,
+		.check_wx = true,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{KERN_VIRT_START, ULONG_MAX},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+
+	if (st.wx_pages)
+		pr_warn("Checked W+X mappings: failed, %lu W+X pages found\n",
+			st.wx_pages);
+	else
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk(m);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+
+static int ptdump_init(void)
+{
+	unsigned int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
+			pg_level[i].mask |= pte_bits[j].mask;
+
+	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+			    &ptdump_fops);
+
+	return 0;
+}
+
+device_initcall(ptdump_init);

drivers/soc/Kconfig

@@ -22,5 +22,6 @@ source "drivers/soc/ux500/Kconfig"
 source "drivers/soc/versatile/Kconfig"
 source "drivers/soc/xilinx/Kconfig"
 source "drivers/soc/zte/Kconfig"
+source "drivers/soc/kendryte/Kconfig"
 
 endmenu

drivers/soc/Makefile

@@ -28,3 +28,4 @@ obj-$(CONFIG_ARCH_U8500)	+= ux500/
 obj-$(CONFIG_PLAT_VERSATILE)	+= versatile/
 obj-y				+= xilinx/
 obj-$(CONFIG_ARCH_ZX)		+= zte/
+obj-$(CONFIG_SOC_KENDRYTE)	+= kendryte/

drivers/soc/kendryte/Kconfig

+# SPDX-License-Identifier: GPL-2.0
+
+if SOC_KENDRYTE
+
+config K210_SYSCTL
+	bool "Kendryte K210 system controller"
+	default y
+	depends on RISCV
+	help
+	  Enables controlling the K210 various clocks and to enable
+	  general purpose use of the extra 2MB of SRAM normally
+	  reserved for the AI engine.
+
+endif

drivers/soc/kendryte/Makefile

+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_K210_SYSCTL)	+= k210-sysctl.o

drivers/soc/kendryte/k210-sysctl.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2019 Christoph Hellwig.
+ * Copyright (c) 2019 Western Digital Corporation or its affiliates.
+ */
+#include <linux/types.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/bitfield.h>
+#include <asm/soc.h>
+
+#define K210_SYSCTL_CLK0_FREQ		26000000UL
+
+/* Registers base address */
+#define K210_SYSCTL_SYSCTL_BASE_ADDR	0x50440000ULL
+
+/* Registers */
+#define K210_SYSCTL_PLL0		0x08
+#define K210_SYSCTL_PLL1		0x0c
+/* clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */
+#define   PLL_RESET		(1 << 20)
+#define   PLL_PWR		(1 << 21)
+#define   PLL_INTFB		(1 << 22)
+#define   PLL_BYPASS		(1 << 23)
+#define   PLL_TEST		(1 << 24)
+#define   PLL_OUT_EN		(1 << 25)
+#define   PLL_TEST_EN		(1 << 26)
+#define K210_SYSCTL_PLL_LOCK		0x18
+#define   PLL0_LOCK1		(1 << 0)
+#define   PLL0_LOCK2		(1 << 1)
+#define   PLL0_SLIP_CLEAR	(1 << 2)
+#define   PLL0_TEST_CLK_OUT	(1 << 3)
+#define   PLL1_LOCK1		(1 << 8)
+#define   PLL1_LOCK2		(1 << 9)
+#define   PLL1_SLIP_CLEAR	(1 << 10)
+#define   PLL1_TEST_CLK_OUT	(1 << 11)
+#define   PLL2_LOCK1		(1 << 16)
+#define   PLL2_LOCK2		(1 << 16)
+#define   PLL2_SLIP_CLEAR	(1 << 18)
+#define   PLL2_TEST_CLK_OUT	(1 << 19)
+#define K210_SYSCTL_CLKSEL0	0x20
+#define   CLKSEL_ACLK		(1 << 0)
+#define K210_SYSCTL_CLKEN_CENT		0x28
+#define   CLKEN_CPU		(1 << 0)
+#define   CLKEN_SRAM0		(1 << 1)
+#define   CLKEN_SRAM1		(1 << 2)
+#define   CLKEN_APB0		(1 << 3)
+#define   CLKEN_APB1		(1 << 4)
+#define   CLKEN_APB2		(1 << 5)
+#define K210_SYSCTL_CLKEN_PERI		0x2c
+#define   CLKEN_ROM		(1 << 0)
+#define   CLKEN_DMA		(1 << 1)
+#define   CLKEN_AI		(1 << 2)
+#define   CLKEN_DVP		(1 << 3)
+#define   CLKEN_FFT		(1 << 4)
+#define   CLKEN_GPIO		(1 << 5)
+#define   CLKEN_SPI0		(1 << 6)
+#define   CLKEN_SPI1		(1 << 7)
+#define   CLKEN_SPI2		(1 << 8)
+#define   CLKEN_SPI3		(1 << 9)
+#define   CLKEN_I2S0		(1 << 10)
+#define   CLKEN_I2S1		(1 << 11)
+#define   CLKEN_I2S2		(1 << 12)
+#define   CLKEN_I2C0		(1 << 13)
+#define   CLKEN_I2C1		(1 << 14)
+#define   CLKEN_I2C2		(1 << 15)
+#define   CLKEN_UART1		(1 << 16)
+#define   CLKEN_UART2		(1 << 17)
+#define   CLKEN_UART3		(1 << 18)
+#define   CLKEN_AES		(1 << 19)
+#define   CLKEN_FPIO		(1 << 20)
+#define   CLKEN_TIMER0		(1 << 21)
+#define   CLKEN_TIMER1		(1 << 22)
+#define   CLKEN_TIMER2		(1 << 23)
+#define   CLKEN_WDT0		(1 << 24)
+#define   CLKEN_WDT1		(1 << 25)
+#define   CLKEN_SHA		(1 << 26)
+#define   CLKEN_OTP		(1 << 27)
+#define   CLKEN_RTC		(1 << 29)
+
+struct k210_sysctl {
+	void __iomem		*regs;
+	struct clk_hw		hw;
+};
+
+static void k210_set_bits(u32 val, void __iomem *reg)
+{
+	writel(readl(reg) | val, reg);
+}
+
+static void k210_clear_bits(u32 val, void __iomem *reg)
+{
+	writel(readl(reg) & ~val, reg);
+}
+
+static void k210_pll1_enable(void __iomem *regs)
+{
+	u32 val;
+
+	val = readl(regs + K210_SYSCTL_PLL1);
+	val &= ~GENMASK(19, 0);				/* clkr1 = 0 */
+	val |= FIELD_PREP(GENMASK(9, 4), 0x3B);		/* clkf1 = 59 */
+	val |= FIELD_PREP(GENMASK(13, 10), 0x3);	/* clkod1 = 3 */
+	val |= FIELD_PREP(GENMASK(19, 14), 0x3B);	/* bwadj1 = 59 */
+	writel(val, regs + K210_SYSCTL_PLL1);
+
+	k210_clear_bits(PLL_BYPASS, regs + K210_SYSCTL_PLL1);
+	k210_set_bits(PLL_PWR, regs + K210_SYSCTL_PLL1);
+
+	/*
+	 * Reset the pll. The magic NOPs come from the Kendryte reference SDK.
+	 */
+	k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1);
+	k210_set_bits(PLL_RESET, regs + K210_SYSCTL_PLL1);
+	nop();
+	nop();
+	k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1);
+
+	for (;;) {
+		val = readl(regs + K210_SYSCTL_PLL_LOCK);
+		if (val & PLL1_LOCK2)
+			break;
+		writel(val | PLL1_SLIP_CLEAR, regs + K210_SYSCTL_PLL_LOCK);
+	}
+
+	k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL1);
+}
+
+static unsigned long k210_sysctl_clk_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct k210_sysctl *s = container_of(hw, struct k210_sysctl, hw);
+	u32 clksel0, pll0;
+	u64 pll0_freq, clkr0, clkf0, clkod0;
+
+	/*
+	 * If the clock selector is not set, use the base frequency.
+	 * Otherwise, use PLL0 frequency with a frequency divisor.
+	 */
+	clksel0 = readl(s->regs + K210_SYSCTL_CLKSEL0);
+	if (!(clksel0 & CLKSEL_ACLK))
+		return K210_SYSCTL_CLK0_FREQ;
+
+	/*
+	 * Get PLL0 frequency:
+	 * freq = base frequency * clkf0 / (clkr0 * clkod0)
+	 */
+	pll0 = readl(s->regs + K210_SYSCTL_PLL0);
+	clkr0 = 1 + FIELD_GET(GENMASK(3, 0), pll0);
+	clkf0 = 1 + FIELD_GET(GENMASK(9, 4), pll0);
+	clkod0 = 1 + FIELD_GET(GENMASK(13, 10), pll0);
+	pll0_freq = clkf0 * K210_SYSCTL_CLK0_FREQ / (clkr0 * clkod0);
+
+	/* Get the frequency divisor from the clock selector */
+	return pll0_freq / (2ULL << FIELD_GET(0x00000006, clksel0));
+}
+
+static const struct clk_ops k210_sysctl_clk_ops = {
+	.recalc_rate	= k210_sysctl_clk_recalc_rate,
+};
+
+static const struct clk_init_data k210_clk_init_data = {
+	.name		= "k210-sysctl-pll1",
+	.ops		= &k210_sysctl_clk_ops,
+};
+
+static int k210_sysctl_probe(struct platform_device *pdev)
+{
+	struct k210_sysctl *s;
+	int error;
+
+	pr_info("Kendryte K210 SoC sysctl\n");
+
+	s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	s->regs = devm_ioremap_resource(&pdev->dev,
+			platform_get_resource(pdev, IORESOURCE_MEM, 0));
+	if (IS_ERR(s->regs))
+		return PTR_ERR(s->regs);
+
+	s->hw.init = &k210_clk_init_data;
+	error = devm_clk_hw_register(&pdev->dev, &s->hw);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register clk");
+		return error;
+	}
+
+	error = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get,
+					    &s->hw);
+	if (error) {
+		dev_err(&pdev->dev, "adding clk provider failed\n");
+		return error;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id k210_sysctl_of_match[] = {
+	{ .compatible = "kendryte,k210-sysctl", },
+	{}
+};
+
+static struct platform_driver k210_sysctl_driver = {
+	.driver	= {
+		.name		= "k210-sysctl",
+		.of_match_table	= k210_sysctl_of_match,
+	},
+	.probe			= k210_sysctl_probe,
+};
+
+static int __init k210_sysctl_init(void)
+{
+	return platform_driver_register(&k210_sysctl_driver);
+}
+core_initcall(k210_sysctl_init);
+
+/*
+ * This needs to be called very early during initialization, given that
+ * PLL1 needs to be enabled to be able to use all SRAM.
+ */
+static void __init k210_soc_early_init(const void *fdt)
+{
+	void __iomem *regs;
+
+	regs = ioremap(K210_SYSCTL_SYSCTL_BASE_ADDR, 0x1000);
+	if (!regs)
+		panic("K210 sysctl ioremap");
+
+	/* Enable PLL1 to make the KPU SRAM useable */
+	k210_pll1_enable(regs);
+
+	k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL0);
+
+	k210_set_bits(CLKEN_CPU | CLKEN_SRAM0 | CLKEN_SRAM1,
+		      regs + K210_SYSCTL_CLKEN_CENT);
+	k210_set_bits(CLKEN_ROM | CLKEN_TIMER0 | CLKEN_RTC,
+		      regs + K210_SYSCTL_CLKEN_PERI);
+
+	k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_CLKSEL0);
+
+	iounmap(regs);
+}
+SOC_EARLY_INIT_DECLARE(generic_k210, "kendryte,k210", k210_soc_early_init);

include/dt-bindings/clock/k210-clk.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+#ifndef K210_CLK_H
+#define K210_CLK_H
+
+/*
+ * Arbitrary identifiers for clocks.
+ * The structure is: in0 -> pll0 -> aclk -> cpu
+ *
+ * Since we use the hardware defaults for now, set all these to the same clock.
+ */
+#define K210_CLK_PLL0   0
+#define K210_CLK_PLL1   0
+#define K210_CLK_ACLK   0
+#define K210_CLK_CPU    0
+
+#endif /* K210_CLK_H */