OpenCloudOS-Kernel/arch/riscv/kernel/hibernate.c

428 lines
10 KiB
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);