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)
{
}

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_obj(*hibernate_cpu_context);

	if (WARN_ON(!hibernate_cpu_context))
		return -ENOMEM;

	return 0;
}

early_initcall(riscv_hibernate_init);