Merge tag 'riscv-for-linus-6.4-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Support for hibernation

 - The .rela.dyn section has been moved to the init area

 - A fix for the SBI probing to allow for implementation-defined
   behavior

 - Various other fixes and cleanups throughout the tree

* tag 'riscv-for-linus-6.4-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  RISC-V: include cpufeature.h in cpufeature.c
  riscv: Move .rela.dyn to the init sections
  dt-bindings: riscv: explicitly mention assumption of Zicsr & Zifencei support
  riscv: compat_syscall_table: Fixup compile warning
  RISC-V: fixup in-flight collision with ARCH_WANT_OPTIMIZE_VMEMMAP rename
  RISC-V: fix sifive and thead section mismatches in errata
  RISC-V: Align SBI probe implementation with spec
  riscv: mm: remove redundant parameter of create_fdt_early_page_table
  riscv: Adjust dependencies of HAVE_DYNAMIC_FTRACE selection
  RISC-V: Add arch functions to support hibernation/suspend-to-disk
  RISC-V: mm: Enable huge page support to kernel_page_present() function
  RISC-V: Factor out common code of __cpu_resume_enter()
  RISC-V: Change suspend_save_csrs and suspend_restore_csrs to public function

Documentation/devicetree/bindings/riscv/cpus.yaml

@@ -86,6 +86,12 @@ properties:
       User-Level ISA document, available from
       https://riscv.org/specifications/
 
+      Due to revisions of the ISA specification, some deviations
+      have arisen over time.
+      Notably, riscv,isa was defined prior to the creation of the
+      Zicsr and Zifencei extensions and thus "i" implies
+      "zicsr_zifencei".
+
       While the isa strings in ISA specification are case
       insensitive, letters in the riscv,isa string must be all
       lowercase to simplify parsing.

arch/riscv/Kconfig

@@ -47,16 +47,16 @@ config RISCV
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
-	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL
+	select ARCH_WANT_OPTIMIZE_VMEMMAP
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if !MMU
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select CPU_PM if CPU_IDLE
+	select CPU_PM if CPU_IDLE || HIBERNATION
 	select EDAC_SUPPORT
 	select GENERIC_ARCH_TOPOLOGY
 	select GENERIC_ATOMIC64 if !64BIT
@@ -142,12 +142,23 @@ config RISCV
 	select TRACE_IRQFLAGS_SUPPORT
 	select UACCESS_MEMCPY if !MMU
 	select ZONE_DMA32 if 64BIT
-	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8)
+	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 
+config CLANG_SUPPORTS_DYNAMIC_FTRACE
+	def_bool CC_IS_CLANG
+	# https://github.com/llvm/llvm-project/commit/6ab8927931851bb42b2c93a00801dc499d7d9b1e
+	depends on CLANG_VERSION >= 130000
+	# https://github.com/ClangBuiltLinux/linux/issues/1817
+	depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600))
+
+config GCC_SUPPORTS_DYNAMIC_FTRACE
+	def_bool CC_IS_GCC
+	depends on $(cc-option,-fpatchable-function-entry=8)
+
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
@@ -788,6 +799,12 @@ menu "Power management options"
 
 source "kernel/power/Kconfig"
 
+config ARCH_HIBERNATION_POSSIBLE
+	def_bool y
+
+config ARCH_HIBERNATION_HEADER
+	def_bool HIBERNATION
+
 endmenu # "Power management options"
 
 menu "CPU Power Management"

arch/riscv/errata/sifive/errata.c

@@ -82,11 +82,9 @@ static void __init_or_module warn_miss_errata(u32 miss_errata)
 	pr_warn("----------------------------------------------------------------\n");
 }
 
-void __init_or_module sifive_errata_patch_func(struct alt_entry *begin,
-					       struct alt_entry *end,
-					       unsigned long archid,
-					       unsigned long impid,
-					       unsigned int stage)
+void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			      unsigned long archid, unsigned long impid,
+			      unsigned int stage)
 {
 	struct alt_entry *alt;
 	u32 cpu_req_errata;

arch/riscv/errata/thead/errata.c

@@ -83,9 +83,9 @@ static u32 thead_errata_probe(unsigned int stage,
 	return cpu_req_errata;
 }
 
-void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
-					      unsigned long archid, unsigned long impid,
-					      unsigned int stage)
+void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage)
 {
 	struct alt_entry *alt;
 	u32 cpu_req_errata = thead_errata_probe(stage, archid, impid);

arch/riscv/include/asm/assembler.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com>
+ */
+
+#ifndef __ASSEMBLY__
+#error "Only include this from assembly code"
+#endif
+
+#ifndef __ASM_ASSEMBLER_H
+#define __ASM_ASSEMBLER_H
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+/*
+ * suspend_restore_csrs - restore CSRs
+ */
+	.macro suspend_restore_csrs
+		REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+		csrw	CSR_EPC, t0
+		REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+		csrw	CSR_STATUS, t0
+		REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+		csrw	CSR_TVAL, t0
+		REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+		csrw	CSR_CAUSE, t0
+	.endm
+
+/*
+ * suspend_restore_regs - Restore registers (except A0 and T0-T6)
+ */
+	.macro suspend_restore_regs
+		REG_L	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+		REG_L	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+		REG_L	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+		REG_L	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+		REG_L	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+		REG_L	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+		REG_L	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+		REG_L	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+		REG_L	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+		REG_L	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+		REG_L	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+		REG_L	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+		REG_L	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+		REG_L	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+		REG_L	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+		REG_L	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+		REG_L	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+		REG_L	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+		REG_L	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+		REG_L	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+		REG_L	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+		REG_L	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+		REG_L	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+	.endm
+
+/*
+ * copy_page - copy 1 page (4KB) of data from source to destination
+ * @a0 - destination
+ * @a1 - source
+ */
+	.macro	copy_page a0, a1
+		lui	a2, 0x1
+		add	a2, a2, a0
+1 :
+		REG_L	t0, 0(a1)
+		REG_L	t1, SZREG(a1)
+
+		REG_S	t0, 0(a0)
+		REG_S	t1, SZREG(a0)
+
+		addi	a0, a0, 2 * SZREG
+		addi	a1, a1, 2 * SZREG
+		bne	a2, a0, 1b
+	.endm
+
+#endif	/* __ASM_ASSEMBLER_H */

arch/riscv/include/asm/sbi.h

@@ -295,7 +295,7 @@ int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid);
-int sbi_probe_extension(int ext);
+long 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)

arch/riscv/include/asm/suspend.h

@@ -21,6 +21,11 @@ struct suspend_context {
 #endif
 };
 
+/*
+ * Used by hibernation core and cleared during resume sequence
+ */
+extern int in_suspend;
+
 /* Low-level CPU suspend entry function */
 int __cpu_suspend_enter(struct suspend_context *context);
 
@@ -33,4 +38,21 @@ int cpu_suspend(unsigned long arg,
 /* Low-level CPU resume entry function */
 int __cpu_resume_enter(unsigned long hartid, unsigned long context);
 
+/* Used to save and restore the CSRs */
+void suspend_save_csrs(struct suspend_context *context);
+void suspend_restore_csrs(struct suspend_context *context);
+
+/* Low-level API to support hibernation */
+int swsusp_arch_suspend(void);
+int swsusp_arch_resume(void);
+int arch_hibernation_header_save(void *addr, unsigned int max_size);
+int arch_hibernation_header_restore(void *addr);
+int __hibernate_cpu_resume(void);
+
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
+asmlinkage void hibernate_restore_image(unsigned long resume_satp, unsigned long satp_temp,
+					unsigned long cpu_resume);
+asmlinkage int hibernate_core_restore_code(void);
 #endif

arch/riscv/kernel/Makefile

@@ -9,6 +9,7 @@ CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
 
 ifdef CONFIG_KEXEC
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
@@ -64,6 +65,7 @@ obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 
 obj-$(CONFIG_CPU_PM)		+= suspend_entry.o suspend.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o hibernate-asm.o
 
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o

arch/riscv/kernel/asm-offsets.c

@@ -9,6 +9,7 @@
 #include <linux/kbuild.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/suspend.h>
 #include <asm/kvm_host.h>
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
@@ -116,6 +117,10 @@ void asm_offsets(void)
 
 	OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
 
+	OFFSET(HIBERN_PBE_ADDR, pbe, address);
+	OFFSET(HIBERN_PBE_ORIG, pbe, orig_address);
+	OFFSET(HIBERN_PBE_NEXT, pbe, next);
+
 	OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero);
 	OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra);
 	OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp);

arch/riscv/kernel/cpu_ops.c

@@ -27,7 +27,7 @@ const struct cpu_operations cpu_ops_spinwait = {
 void __init cpu_set_ops(int cpuid)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
-	if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
+	if (sbi_probe_extension(SBI_EXT_HSM)) {
 		if (!cpuid)
 			pr_info("SBI HSM extension detected\n");
 		cpu_ops[cpuid] = &cpu_ops_sbi;

arch/riscv/kernel/cpufeature.c

@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/hwcap.h>
 #include <asm/patch.h>
 #include <asm/processor.h>

arch/riscv/kernel/hibernate-asm.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Hibernation low level support for RISCV.
+ *
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com>
+ */
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+#include <asm/csr.h>
+
+#include <linux/linkage.h>
+
+/*
+ * int __hibernate_cpu_resume(void)
+ * Switch back to the hibernated image's page table prior to restoring the CPU
+ * context.
+ *
+ * Always returns 0
+ */
+ENTRY(__hibernate_cpu_resume)
+	/* switch to hibernated image's page table. */
+	csrw CSR_SATP, s0
+	sfence.vma
+
+	REG_L	a0, hibernate_cpu_context
+
+	suspend_restore_csrs
+	suspend_restore_regs
+
+	/* Return zero value. */
+	mv	a0, zero
+
+	ret
+END(__hibernate_cpu_resume)
+
+/*
+ * Prepare to restore the image.
+ * a0: satp of saved page tables.
+ * a1: satp of temporary page tables.
+ * a2: cpu_resume.
+ */
+ENTRY(hibernate_restore_image)
+	mv	s0, a0
+	mv	s1, a1
+	mv	s2, a2
+	REG_L	s4, restore_pblist
+	REG_L	a1, relocated_restore_code
+
+	jalr	a1
+END(hibernate_restore_image)
+
+/*
+ * The below code will be executed from a 'safe' page.
+ * It first switches to the temporary page table, then starts to copy the pages
+ * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume()
+ * to restore the CPU context.
+ */
+ENTRY(hibernate_core_restore_code)
+	/* switch to temp page table. */
+	csrw satp, s1
+	sfence.vma
+.Lcopy:
+	/* The below code will restore the hibernated image. */
+	REG_L	a1, HIBERN_PBE_ADDR(s4)
+	REG_L	a0, HIBERN_PBE_ORIG(s4)
+
+	copy_page a0, a1
+
+	REG_L	s4, HIBERN_PBE_NEXT(s4)
+	bnez	s4, .Lcopy
+
+	jalr	s2
+END(hibernate_core_restore_code)

arch/riscv/kernel/hibernate.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Hibernation support for RISCV
+ *
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com>
+ */
+
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
+#include <asm/set_memory.h>
+#include <asm/smp.h>
+#include <asm/suspend.h>
+
+#include <linux/cpu.h>
+#include <linux/memblock.h>
+#include <linux/pm.h>
+#include <linux/sched.h>
+#include <linux/suspend.h>
+#include <linux/utsname.h>
+
+/* The logical cpu number we should resume on, initialised to a non-cpu number. */
+static int sleep_cpu = -EINVAL;
+
+/* Pointer to the temporary resume page table. */
+static pgd_t *resume_pg_dir;
+
+/* CPU context to be saved. */
+struct suspend_context *hibernate_cpu_context;
+EXPORT_SYMBOL_GPL(hibernate_cpu_context);
+
+unsigned long relocated_restore_code;
+EXPORT_SYMBOL_GPL(relocated_restore_code);
+
+/**
+ * struct arch_hibernate_hdr_invariants - container to store kernel build version.
+ * @uts_version: to save the build number and date so that we do not resume with
+ *		a different kernel.
+ */
+struct arch_hibernate_hdr_invariants {
+	char		uts_version[__NEW_UTS_LEN + 1];
+};
+
+/**
+ * struct arch_hibernate_hdr - helper parameters that help us to restore the image.
+ * @invariants: container to store kernel build version.
+ * @hartid: to make sure same boot_cpu executes the hibernate/restore code.
+ * @saved_satp: original page table used by the hibernated image.
+ * @restore_cpu_addr: the kernel's image address to restore the CPU context.
+ */
+static struct arch_hibernate_hdr {
+	struct arch_hibernate_hdr_invariants invariants;
+	unsigned long	hartid;
+	unsigned long	saved_satp;
+	unsigned long	restore_cpu_addr;
+} resume_hdr;
+
+static void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
+{
+	memset(i, 0, sizeof(*i));
+	memcpy(i->uts_version, init_utsname()->version, sizeof(i->uts_version));
+}
+
+/*
+ * Check if the given pfn is in the 'nosave' section.
+ */
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin);
+	unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1);
+
+	return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn));
+}
+
+void notrace save_processor_state(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+}
+
+void notrace restore_processor_state(void)
+{
+}
+
+/*
+ * Helper parameters need to be saved to the hibernation image header.
+ */
+int arch_hibernation_header_save(void *addr, unsigned int max_size)
+{
+	struct arch_hibernate_hdr *hdr = addr;
+
+	if (max_size < sizeof(*hdr))
+		return -EOVERFLOW;
+
+	arch_hdr_invariants(&hdr->invariants);
+
+	hdr->hartid = cpuid_to_hartid_map(sleep_cpu);
+	hdr->saved_satp = csr_read(CSR_SATP);
+	hdr->restore_cpu_addr = (unsigned long)__hibernate_cpu_resume;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(arch_hibernation_header_save);
+
+/*
+ * Retrieve the helper parameters from the hibernation image header.
+ */
+int arch_hibernation_header_restore(void *addr)
+{
+	struct arch_hibernate_hdr_invariants invariants;
+	struct arch_hibernate_hdr *hdr = addr;
+	int ret = 0;
+
+	arch_hdr_invariants(&invariants);
+
+	if (memcmp(&hdr->invariants, &invariants, sizeof(invariants))) {
+		pr_crit("Hibernate image not generated by this kernel!\n");
+		return -EINVAL;
+	}
+
+	sleep_cpu = riscv_hartid_to_cpuid(hdr->hartid);
+	if (sleep_cpu < 0) {
+		pr_crit("Hibernated on a CPU not known to this kernel!\n");
+		sleep_cpu = -EINVAL;
+		return -EINVAL;
+	}
+
+#ifdef CONFIG_SMP
+	ret = bringup_hibernate_cpu(sleep_cpu);
+	if (ret) {
+		sleep_cpu = -EINVAL;
+		return ret;
+	}
+#endif
+	resume_hdr = *hdr;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_hibernation_header_restore);
+
+int swsusp_arch_suspend(void)
+{
+	int ret = 0;
+
+	if (__cpu_suspend_enter(hibernate_cpu_context)) {
+		sleep_cpu = smp_processor_id();
+		suspend_save_csrs(hibernate_cpu_context);
+		ret = swsusp_save();
+	} else {
+		suspend_restore_csrs(hibernate_cpu_context);
+		flush_tlb_all();
+		flush_icache_all();
+
+		/*
+		 * Tell the hibernation core that we've just restored the memory.
+		 */
+		in_suspend = 0;
+		sleep_cpu = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int temp_pgtable_map_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
+				unsigned long end, pgprot_t prot)
+{
+	pte_t *src_ptep;
+	pte_t *dst_ptep;
+
+	if (pmd_none(READ_ONCE(*dst_pmdp))) {
+		dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_ptep)
+			return -ENOMEM;
+
+		pmd_populate_kernel(NULL, dst_pmdp, dst_ptep);
+	}
+
+	dst_ptep = pte_offset_kernel(dst_pmdp, start);
+	src_ptep = pte_offset_kernel(src_pmdp, start);
+
+	do {
+		pte_t pte = READ_ONCE(*src_ptep);
+
+		if (pte_present(pte))
+			set_pte(dst_ptep, __pte(pte_val(pte) | pgprot_val(prot)));
+	} while (dst_ptep++, src_ptep++, start += PAGE_SIZE, start < end);
+
+	return 0;
+}
+
+static int temp_pgtable_map_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
+				unsigned long end, pgprot_t prot)
+{
+	unsigned long next;
+	unsigned long ret;
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
+
+	if (pud_none(READ_ONCE(*dst_pudp))) {
+		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pmdp)
+			return -ENOMEM;
+
+		pud_populate(NULL, dst_pudp, dst_pmdp);
+	}
+
+	dst_pmdp = pmd_offset(dst_pudp, start);
+	src_pmdp = pmd_offset(src_pudp, start);
+
+	do {
+		pmd_t pmd = READ_ONCE(*src_pmdp);
+
+		next = pmd_addr_end(start, end);
+
+		if (pmd_none(pmd))
+			continue;
+
+		if (pmd_leaf(pmd)) {
+			set_pmd(dst_pmdp, __pmd(pmd_val(pmd) | pgprot_val(prot)));
+		} else {
+			ret = temp_pgtable_map_pte(dst_pmdp, src_pmdp, start, next, prot);
+			if (ret)
+				return -ENOMEM;
+		}
+	} while (dst_pmdp++, src_pmdp++, start = next, start != end);
+
+	return 0;
+}
+
+static int temp_pgtable_map_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start,
+				unsigned long end, pgprot_t prot)
+{
+	unsigned long next;
+	unsigned long ret;
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
+
+	if (p4d_none(READ_ONCE(*dst_p4dp))) {
+		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pudp)
+			return -ENOMEM;
+
+		p4d_populate(NULL, dst_p4dp, dst_pudp);
+	}
+
+	dst_pudp = pud_offset(dst_p4dp, start);
+	src_pudp = pud_offset(src_p4dp, start);
+
+	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
+		next = pud_addr_end(start, end);
+
+		if (pud_none(pud))
+			continue;
+
+		if (pud_leaf(pud)) {
+			set_pud(dst_pudp, __pud(pud_val(pud) | pgprot_val(prot)));
+		} else {
+			ret = temp_pgtable_map_pmd(dst_pudp, src_pudp, start, next, prot);
+			if (ret)
+				return -ENOMEM;
+		}
+	} while (dst_pudp++, src_pudp++, start = next, start != end);
+
+	return 0;
+}
+
+static int temp_pgtable_map_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+				unsigned long end, pgprot_t prot)
+{
+	unsigned long next;
+	unsigned long ret;
+	p4d_t *dst_p4dp;
+	p4d_t *src_p4dp;
+
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_p4dp = (p4d_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_p4dp)
+			return -ENOMEM;
+
+		pgd_populate(NULL, dst_pgdp, dst_p4dp);
+	}
+
+	dst_p4dp = p4d_offset(dst_pgdp, start);
+	src_p4dp = p4d_offset(src_pgdp, start);
+
+	do {
+		p4d_t p4d = READ_ONCE(*src_p4dp);
+
+		next = p4d_addr_end(start, end);
+
+		if (p4d_none(p4d))
+			continue;
+
+		if (p4d_leaf(p4d)) {
+			set_p4d(dst_p4dp, __p4d(p4d_val(p4d) | pgprot_val(prot)));
+		} else {
+			ret = temp_pgtable_map_pud(dst_p4dp, src_p4dp, start, next, prot);
+			if (ret)
+				return -ENOMEM;
+		}
+	} while (dst_p4dp++, src_p4dp++, start = next, start != end);
+
+	return 0;
+}
+
+static int temp_pgtable_mapping(pgd_t *pgdp, unsigned long start, unsigned long end, pgprot_t prot)
+{
+	pgd_t *dst_pgdp = pgd_offset_pgd(pgdp, start);
+	pgd_t *src_pgdp = pgd_offset_k(start);
+	unsigned long next;
+	unsigned long ret;
+
+	do {
+		pgd_t pgd = READ_ONCE(*src_pgdp);
+
+		next = pgd_addr_end(start, end);
+
+		if (pgd_none(pgd))
+			continue;
+
+		if (pgd_leaf(pgd)) {
+			set_pgd(dst_pgdp, __pgd(pgd_val(pgd) | pgprot_val(prot)));
+		} else {
+			ret = temp_pgtable_map_p4d(dst_pgdp, src_pgdp, start, next, prot);
+			if (ret)
+				return -ENOMEM;
+		}
+	} while (dst_pgdp++, src_pgdp++, start = next, start != end);
+
+	return 0;
+}
+
+static unsigned long relocate_restore_code(void)
+{
+	void *page = (void *)get_safe_page(GFP_ATOMIC);
+
+	if (!page)
+		return -ENOMEM;
+
+	copy_page(page, hibernate_core_restore_code);
+
+	/* Make the page containing the relocated code executable. */
+	set_memory_x((unsigned long)page, 1);
+
+	return (unsigned long)page;
+}
+
+int swsusp_arch_resume(void)
+{
+	unsigned long end = (unsigned long)pfn_to_virt(max_low_pfn);
+	unsigned long start = PAGE_OFFSET;
+	int ret;
+
+	/*
+	 * Memory allocated by get_safe_page() will be dealt with by the hibernation core,
+	 * we don't need to free it here.
+	 */
+	resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!resume_pg_dir)
+		return -ENOMEM;
+
+	/*
+	 * Create a temporary page table and map the whole linear region as executable and
+	 * writable.
+	 */
+	ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE | _PAGE_EXEC));
+	if (ret)
+		return ret;
+
+	/* Move the restore code to a new page so that it doesn't get overwritten by itself. */
+	relocated_restore_code = relocate_restore_code();
+	if (relocated_restore_code == -ENOMEM)
+		return -ENOMEM;
+
+	/*
+	 * Map the __hibernate_cpu_resume() address to the temporary page table so that the
+	 * restore code can jumps to it after finished restore the image. The next execution
+	 * code doesn't find itself in a different address space after switching over to the
+	 * original page table used by the hibernated image.
+	 * The __hibernate_cpu_resume() mapping is unnecessary for RV32 since the kernel and
+	 * linear addresses are identical, but different for RV64. To ensure consistency, we
+	 * map it for both RV32 and RV64 kernels.
+	 * Additionally, we should ensure that the page is writable before restoring the image.
+	 */
+	start = (unsigned long)resume_hdr.restore_cpu_addr;
+	end = start + PAGE_SIZE;
+
+	ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE));
+	if (ret)
+		return ret;
+
+	hibernate_restore_image(resume_hdr.saved_satp, (PFN_DOWN(__pa(resume_pg_dir)) | satp_mode),
+				resume_hdr.restore_cpu_addr);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP_SMP
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	if (sleep_cpu < 0) {
+		pr_err("Failing to resume from hibernate on an unknown CPU\n");
+		return -ENODEV;
+	}
+
+	return freeze_secondary_cpus(sleep_cpu);
+}
+#endif
+
+static int __init riscv_hibernate_init(void)
+{
+	hibernate_cpu_context = kzalloc(sizeof(*hibernate_cpu_context), GFP_KERNEL);
+
+	if (WARN_ON(!hibernate_cpu_context))
+		return -ENOMEM;
+
+	return 0;
+}
+
+early_initcall(riscv_hibernate_init);

arch/riscv/kernel/sbi.c

@@ -524,19 +524,18 @@ static void sbi_srst_power_off(void)
  * sbi_probe_extension() - Check if an SBI extension ID is supported or not.
  * @extid: The extension ID to be probed.
  *
- * Return: Extension specific nonzero value f yes, -ENOTSUPP otherwise.
+ * Return: 1 or an extension specific nonzero value if yes, 0 otherwise.
  */
-int sbi_probe_extension(int extid)
+long sbi_probe_extension(int extid)
 {
 	struct sbiret ret;
 
 	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
 			0, 0, 0, 0, 0);
 	if (!ret.error)
-		if (ret.value)
-			return ret.value;
+		return ret.value;
 
-	return -ENOTSUPP;
+	return 0;
 }
 EXPORT_SYMBOL(sbi_probe_extension);
 
@@ -599,26 +598,26 @@ void __init sbi_init(void)
 	if (!sbi_spec_is_0_1()) {
 		pr_info("SBI implementation ID=0x%lx Version=0x%lx\n",
 			sbi_get_firmware_id(), sbi_get_firmware_version());
-		if (sbi_probe_extension(SBI_EXT_TIME) > 0) {
+		if (sbi_probe_extension(SBI_EXT_TIME)) {
 			__sbi_set_timer = __sbi_set_timer_v02;
 			pr_info("SBI TIME extension detected\n");
 		} else {
 			__sbi_set_timer = __sbi_set_timer_v01;
 		}
-		if (sbi_probe_extension(SBI_EXT_IPI) > 0) {
+		if (sbi_probe_extension(SBI_EXT_IPI)) {
 			__sbi_send_ipi	= __sbi_send_ipi_v02;
 			pr_info("SBI IPI extension detected\n");
 		} else {
 			__sbi_send_ipi	= __sbi_send_ipi_v01;
 		}
-		if (sbi_probe_extension(SBI_EXT_RFENCE) > 0) {
+		if (sbi_probe_extension(SBI_EXT_RFENCE)) {
 			__sbi_rfence	= __sbi_rfence_v02;
 			pr_info("SBI RFENCE extension detected\n");
 		} else {
 			__sbi_rfence	= __sbi_rfence_v01;
 		}
 		if ((sbi_spec_version >= sbi_mk_version(0, 3)) &&
-		    (sbi_probe_extension(SBI_EXT_SRST) > 0)) {
+		    sbi_probe_extension(SBI_EXT_SRST)) {
 			pr_info("SBI SRST extension detected\n");
 			pm_power_off = sbi_srst_power_off;
 			sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot;

arch/riscv/kernel/suspend.c

@@ -8,7 +8,7 @@
 #include <asm/csr.h>
 #include <asm/suspend.h>
 
-static void suspend_save_csrs(struct suspend_context *context)
+void suspend_save_csrs(struct suspend_context *context)
 {
 	context->scratch = csr_read(CSR_SCRATCH);
 	context->tvec = csr_read(CSR_TVEC);
@@ -29,7 +29,7 @@ static void suspend_save_csrs(struct suspend_context *context)
 #endif
 }
 
-static void suspend_restore_csrs(struct suspend_context *context)
+void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, context->scratch);
 	csr_write(CSR_TVEC, context->tvec);

arch/riscv/kernel/suspend_entry.S

@@ -7,6 +7,7 @@
 #include <linux/linkage.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/assembler.h>
 #include <asm/csr.h>
 #include <asm/xip_fixup.h>
 
@@ -83,39 +84,10 @@ ENTRY(__cpu_resume_enter)
 	add	a0, a1, zero
 
 	/* Restore CSRs */
-	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
-	csrw	CSR_EPC, t0
-	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
-	csrw	CSR_STATUS, t0
-	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
-	csrw	CSR_TVAL, t0
-	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
-	csrw	CSR_CAUSE, t0
+	suspend_restore_csrs
 
 	/* Restore registers (except A0 and T0-T6) */
-	REG_L	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
-	REG_L	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
-	REG_L	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
-	REG_L	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
-	REG_L	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
-	REG_L	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
-	REG_L	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
-	REG_L	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
-	REG_L	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
-	REG_L	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
-	REG_L	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
-	REG_L	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
-	REG_L	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
-	REG_L	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
-	REG_L	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
-	REG_L	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
-	REG_L	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
-	REG_L	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
-	REG_L	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
-	REG_L	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
-	REG_L	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
-	REG_L	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
-	REG_L	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+	suspend_restore_regs
 
 	/* Return zero value */
 	add	a0, zero, zero

arch/riscv/kernel/vmlinux.lds.S

@@ -104,6 +104,12 @@ SECTIONS
 		*(.rel.dyn*)
 	}
 
+	.rela.dyn : ALIGN(8) {
+		__rela_dyn_start = .;
+		*(.rela .rela*)
+		__rela_dyn_end = .;
+	}
+
 	__init_data_end = .;
 
 	. = ALIGN(8);
@@ -130,12 +136,6 @@ SECTIONS
 		*(.sdata*)
 	}
 
-	.rela.dyn : ALIGN(8) {
-		__rela_dyn_start = .;
-		*(.rela .rela*)
-		__rela_dyn_end = .;
-	}
-
 	.got : { *(.got*) }
 
 #ifdef CONFIG_RELOCATABLE

arch/riscv/kvm/main.c

@@ -80,7 +80,7 @@ static int __init riscv_kvm_init(void)
 		return -ENODEV;
 	}
 
-	if (sbi_probe_extension(SBI_EXT_RFENCE) <= 0) {
+	if (!sbi_probe_extension(SBI_EXT_RFENCE)) {
 		kvm_info("require SBI RFENCE extension\n");
 		return -ENODEV;
 	}

arch/riscv/mm/init.c

@@ -919,8 +919,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
  * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
  * entry.
  */
-static void __init create_fdt_early_page_table(pgd_t *pgdir,
-					       uintptr_t fix_fdt_va,
+static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
 					       uintptr_t dtb_pa)
 {
 	uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
@@ -1132,8 +1131,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	create_kernel_page_table(early_pg_dir, true);
 
 	/* Setup early mapping for FDT early scan */
-	create_fdt_early_page_table(early_pg_dir,
-				    __fix_to_virt(FIX_FDT), dtb_pa);
+	create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa);
 
 	/*
 	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap

arch/riscv/mm/pageattr.c

@@ -217,18 +217,26 @@ bool kernel_page_present(struct page *page)
 	pgd = pgd_offset_k(addr);
 	if (!pgd_present(*pgd))
 		return false;
+	if (pgd_leaf(*pgd))
+		return true;
 
 	p4d = p4d_offset(pgd, addr);
 	if (!p4d_present(*p4d))
 		return false;
+	if (p4d_leaf(*p4d))
+		return true;
 
 	pud = pud_offset(p4d, addr);
 	if (!pud_present(*pud))
 		return false;
+	if (pud_leaf(*pud))
+		return true;
 
 	pmd = pmd_offset(pud, addr);
 	if (!pmd_present(*pmd))
 		return false;
+	if (pmd_leaf(*pmd))
+		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
 	return pte_present(*pte);

drivers/cpuidle/cpuidle-riscv-sbi.c

@@ -613,7 +613,7 @@ static int __init sbi_cpuidle_init(void)
 	 * 2) SBI HSM extension is available
 	 */
 	if ((sbi_spec_version < sbi_mk_version(0, 3)) ||
-	    sbi_probe_extension(SBI_EXT_HSM) <= 0) {
+	    !sbi_probe_extension(SBI_EXT_HSM)) {
 		pr_info("HSM suspend not available\n");
 		return 0;
 	}

drivers/perf/riscv_pmu_sbi.c

@@ -924,7 +924,7 @@ static int __init pmu_sbi_devinit(void)
 	struct platform_device *pdev;
 
 	if (sbi_spec_version < sbi_mk_version(0, 3) ||
-	    sbi_probe_extension(SBI_EXT_PMU) <= 0) {
+	    !sbi_probe_extension(SBI_EXT_PMU)) {
 		return 0;
 	}