From patchwork Thu Mar 23 04:56:04 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: JeeHeng Sia X-Patchwork-Id: 73802 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a5d:604a:0:0:0:0:0 with SMTP id j10csp2725784wrt; Wed, 22 Mar 2023 22:07:34 -0700 (PDT) X-Google-Smtp-Source: AK7set+bXkOBq2xMMX945/+1jvjJGtCHShQpjBDivym8aurHhlz+XjyJfXdaCzdhZtvhoivABaca X-Received: by 2002:aa7:c84e:0:b0:4fb:e9b8:ca5a with SMTP id g14-20020aa7c84e000000b004fbe9b8ca5amr8951985edt.40.1679548054656; Wed, 22 Mar 2023 22:07:34 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1679548054; cv=none; d=google.com; s=arc-20160816; b=ZRioZCBf7adSZO0VEKijVgmThKJexNCvic16hUcW89k9n28IbO76lEuk4VDVTklAvn 7vXTSoIkJYFOFccEAuImqQKZFmHTazhfHQDhjv4cMazCZxTLXpZDHiHm/QemWJTbBxOM DtFocVzo2LYPfk2Elem7A+cKlwP3WHoHDYx3MI2DlycQtQdedgzlipQ4CuJUXqoFgakE nHMaazWns1ybbxAd36G1zqcigyNqiDm01ZgNxBy+UNHMnqdWQXVsXx6DO3BVsJBqfumW mqp6kQvv1IB04EReGf8whjzQjBTU60Zhvm4ysUkUs2fEM7SggsFTBfvNnKF1OVTLgjv6 WuFg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from; bh=QizGjHbmJwfvkF+54q3Sy00oSK+GJsjXX3e8Xqjb6EA=; b=v/5dDCVLvYHQghPbAZmHeYl0iIXfik9G/dMRrp4KEh+bM6r8B1Q8RJZDxTnz5N7BAm 1JtgT1y5VLzGWFjnDEqoIAw8z/ZbkwsGc6yJpel8SYqf50P6TO9Bib+dRVMhpbasdxuO ssrRv6O3WflIjcSs9T5xx6SIyRPkINe30PJGUL8OsvQDW5Bpk54GSWG3Wj0u7sx4WZ0d 8RvOlCvYSvf8qXH06tFJ9+pGAb6azpLAWVDyCF6SXJIkiRW/9ekRSJaeT0J7boaUx+PA pQXp1gEMi4vSC3OEnruzlnyd7FLBWhWDfnDNtEWPBMgDZpAgXzFMRL1VueeoDpeXLXXi GHzg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: from out1.vger.email (out1.vger.email. [2620:137:e000::1:20]) by mx.google.com with ESMTP id i23-20020a056402055700b004fd03dd5f0dsi14474859edx.563.2023.03.22.22.07.11; Wed, 22 Mar 2023 22:07:34 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; Authentication-Results: mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229917AbjCWE47 convert rfc822-to-8bit (ORCPT + 99 others); Thu, 23 Mar 2023 00:56:59 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33570 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229991AbjCWE4e (ORCPT ); Thu, 23 Mar 2023 00:56:34 -0400 Received: from fd01.gateway.ufhost.com (fd01.gateway.ufhost.com [61.152.239.71]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5DEEE2B9F4 for ; Wed, 22 Mar 2023 21:56:31 -0700 (PDT) Received: from EXMBX165.cuchost.com (unknown [175.102.18.54]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "EXMBX165", Issuer "EXMBX165" (not verified)) by fd01.gateway.ufhost.com (Postfix) with ESMTP id 9256024E3E0; Thu, 23 Mar 2023 12:56:29 +0800 (CST) Received: from EXMBX066.cuchost.com (172.16.7.66) by EXMBX165.cuchost.com (172.16.6.75) with Microsoft SMTP Server (TLS) id 15.0.1497.42; Thu, 23 Mar 2023 12:56:29 +0800 Received: from jsia-virtual-machine.localdomain (202.188.176.82) by EXMBX066.cuchost.com (172.16.6.66) with Microsoft SMTP Server (TLS) id 15.0.1497.42; Thu, 23 Mar 2023 12:56:26 +0800 From: Sia Jee Heng To: , , CC: , , , , , Conor Dooley Subject: [PATCH v7 4/4] RISC-V: Add arch functions to support hibernation/suspend-to-disk Date: Thu, 23 Mar 2023 12:56:04 +0800 Message-ID: <20230323045604.536099-5-jeeheng.sia@starfivetech.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230323045604.536099-1-jeeheng.sia@starfivetech.com> References: <20230323045604.536099-1-jeeheng.sia@starfivetech.com> MIME-Version: 1.0 X-Originating-IP: [202.188.176.82] X-ClientProxiedBy: EXCAS066.cuchost.com (172.16.6.26) To EXMBX066.cuchost.com (172.16.6.66) X-YovoleRuleAgent: yovoleflag X-Spam-Status: No, score=-0.0 required=5.0 tests=RCVD_IN_MSPIKE_H2, SPF_HELO_PASS,SPF_PASS autolearn=unavailable autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1761133781290992233?= X-GMAIL-MSGID: =?utf-8?q?1761133781290992233?= Low level Arch functions were created to support hibernation. swsusp_arch_suspend() relies code from __cpu_suspend_enter() to write cpu state onto the stack, then calling swsusp_save() to save the memory image. Arch specific hibernation header is implemented and is utilized by the arch_hibernation_header_restore() and arch_hibernation_header_save() functions. The arch specific hibernation header consists of satp, hartid, and the cpu_resume address. The kernel built version is also need to be saved into the hibernation image header to making sure only the same kernel is restore when resume. swsusp_arch_resume() creates a temporary page table that covering only the linear map. It copies the restore code to a 'safe' page, then start to restore the memory image. Once completed, it restores the original kernel's page table. It then calls into __hibernate_cpu_resume() to restore the CPU context. Finally, it follows the normal hibernation path back to the hibernation core. To enable hibernation/suspend to disk into RISCV, the below config need to be enabled: - CONFIG_ARCH_HIBERNATION_HEADER - CONFIG_ARCH_HIBERNATION_POSSIBLE Signed-off-by: Sia Jee Heng Reviewed-by: Ley Foon Tan Reviewed-by: Mason Huo Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones --- arch/riscv/Kconfig | 6 + arch/riscv/include/asm/assembler.h | 20 ++ arch/riscv/include/asm/suspend.h | 19 ++ arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/asm-offsets.c | 5 + arch/riscv/kernel/hibernate-asm.S | 77 ++++++ arch/riscv/kernel/hibernate.c | 427 +++++++++++++++++++++++++++++ 7 files changed, 555 insertions(+) create mode 100644 arch/riscv/kernel/hibernate-asm.S create mode 100644 arch/riscv/kernel/hibernate.c diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..473c2a1a6884 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -707,6 +707,12 @@ 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" diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h index ba59d38f8937..44b1457d3e95 100644 --- a/arch/riscv/include/asm/assembler.h +++ b/arch/riscv/include/asm/assembler.h @@ -59,4 +59,24 @@ 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 */ diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 67e047445662..02f87867389a 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/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); @@ -36,4 +41,18 @@ 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 diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 4cf303a779ab..daab341d55e4 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -64,6 +64,7 @@ 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 diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index df9444397908..d6a75aac1d27 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -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); diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S new file mode 100644 index 000000000000..effaf5ca5da0 --- /dev/null +++ b/arch/riscv/kernel/hibernate-asm.S @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Hibernation low level support for RISCV. + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include + +#include + +/* + * 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) diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c new file mode 100644 index 000000000000..264b2dcdd67e --- /dev/null +++ b/arch/riscv/kernel/hibernate.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hibernation support for RISCV + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* 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);