void __init efi_call_phys_epilog(pgd_t *save_pgd)
{
/*
* After the lock is released, the original page table is restored.
*/
int pgd_idx, i;
int nr_pgds;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
write_cr3((unsigned long)save_pgd);
__flush_tlb_all();
return;
}
nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
if (!(pgd_val(*pgd) & _PAGE_PRESENT))
continue;
for (i = 0; i < PTRS_PER_P4D; i++) {
p4d = p4d_offset(pgd,
pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
if (!(p4d_val(*p4d) & _PAGE_PRESENT))
continue;
pud = (pud_t *)p4d_page_vaddr(*p4d);
pud_free(&init_mm, pud);
}
p4d = (p4d_t *)pgd_page_vaddr(*pgd);
p4d_free(&init_mm, p4d);
}
kfree(save_pgd);
__flush_tlb_all();
early_code_mapping_set_exec(0);
}
static void do_flush_tlb_all(void *info)
{
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
if (read_pda(mmu_state) == TLBSTATE_LAZY)
leave_mm(cpu);
}
static void do_flush_tlb_all(void* info)
{
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY)
leave_mm(cpu);
}
static inline void do_flush_tlb_all_local(void)
{
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
if (cpu_tlbstate[cpu].state == TLBSTATE_LAZY)
leave_mm(cpu);
}
static void do_flush_tlb_all(void *info)
{
unsigned long cpu = smp_processor_id();
__flush_tlb_all();
if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
leave_mm(cpu);
}
static void __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
{
pmd_t *pmd = pmd_offset(pud,0);
spin_lock(&init_mm.page_table_lock);
phys_pmd_init(pmd, address, end);
spin_unlock(&init_mm.page_table_lock);
__flush_tlb_all();
}
/*
* Activate a secondary processor.
*/
notrace static void __cpuinit start_secondary(void *unused)
{
/*
* Don't put *anything* before cpu_init(), SMP booting is too
* fragile that we want to limit the things done here to the
* most necessary things.
*/
cpu_init();
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
* Check TSC synchronization with the BP:
*/
check_tsc_sync_target();
/*
* We need to hold call_lock, so there is no inconsistency
* between the time smp_call_function() determines number of
* IPI recipients, and the time when the determination is made
* for which cpus receive the IPI. Holding this
* lock helps us to not include this cpu in a currently in progress
* smp_call_function().
*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
*/
ipi_call_lock();
lock_vector_lock();
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
ipi_call_unlock();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
x86_platform.nmi_init();
/* enable local interrupts */
local_irq_enable();
/* to prevent fake stack check failure in clock setup */
boot_init_stack_canary();
x86_cpuinit.setup_percpu_clockev();
wmb();
cpu_idle();
}
/*
* Activate a secondary processor.
*/
notrace static void __cpuinit start_secondary(void *unused)
{
/*
* Don't put *anything* before cpu_init(), SMP booting is too
* fragile that we want to limit the things done here to the
* most necessary things.
*/
cpu_init();
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
* Check TSC synchronization with the BP:
*/
check_tsc_sync_target();
/*
* Enable the espfix hack for this CPU
*/
#ifdef CONFIG_X86_ESPFIX64
init_espfix_ap();
#endif
/*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
*/
lock_vector_lock();
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
x86_platform.nmi_init();
/* enable local interrupts */
local_irq_enable();
/* to prevent fake stack check failure in clock setup */
boot_init_stack_canary();
x86_cpuinit.setup_percpu_clockev();
wmb();
cpu_startup_entry(CPUHP_ONLINE);
}
static void flush_kernel_map(void *dummy)
{
/* Could use CLFLUSH here if the CPU supports it (Hammer,P4) */
if (boot_cpu_data.x86_model >= 4)
wbinvd();
/* Flush all to work around Errata in early athlons regarding
* large page flushing.
*/
__flush_tlb_all();
}
void __init efi_call_phys_epilog(void)
{
/*
* After the lock is released, the original page table is restored.
*/
set_pgd(pgd_offset_k(0x0UL), save_pgd);
__flush_tlb_all();
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
/*==========================================================================*
* Name: smp_flush_tlb_all
*
* Description: This routine flushes all processes TLBs.
* 1.Request other CPU to execute 'flush_tlb_all_ipi()'.
* 2.Execute 'do_flush_tlb_all_local()'.
*
* Born on Date: 2002.02.05
*
* Arguments: NONE
*
* Returns: void (cannot fail)
*
* Modification log:
* Date Who Description
* ---------- --- --------------------------------------------------------
*
*==========================================================================*/
void smp_flush_tlb_all(void)
{
unsigned long flags;
preempt_disable();
local_irq_save(flags);
__flush_tlb_all();
local_irq_restore(flags);
smp_call_function(flush_tlb_all_ipi, NULL, 1);
preempt_enable();
}
void __init efi_call_phys_prelog(void)
{
unsigned long vaddress;
early_code_mapping_set_exec(1);
local_irq_save(efi_flags);
vaddress = (unsigned long)__va(0x0UL);
save_pgd = *pgd_offset_k(0x0UL);
set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
__flush_tlb_all();
}
void __init efi_call_phys_epilog(pgd_t *save_pgd)
{
struct desc_ptr gdt_descr;
gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
load_cr3(save_pgd);
__flush_tlb_all();
}
void __init efi_call_phys_epilog(void)
{
int pgd;
int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
for (pgd = 0; pgd < n_pgds; pgd++)
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
kfree(save_pgd);
__flush_tlb_all();
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
void kernel_map_pages(struct page *page, int numpages, int enable)
{
if (PageHighMem(page))
return;
/* the return value is ignored - the calls cannot fail,
* large pages are disabled at boot time.
*/
change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
/* we should perform an IPI and flush all tlbs,
* but that can deadlock->flush only current cpu.
*/
__flush_tlb_all();
}
/*
* Activate a secondary processor.
*/
static void notrace start_secondary(void *unused)
{
/*
* Don't put *anything* before cpu_init(), SMP booting is too
* fragile that we want to limit the things done here to the
* most necessary things.
*/
cpu_init();
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
* Check TSC synchronization with the BP:
*/
check_tsc_sync_target();
/*
* Lock vector_lock and initialize the vectors on this cpu
* before setting the cpu online. We must set it online with
* vector_lock held to prevent a concurrent setup/teardown
* from seeing a half valid vector space.
*/
lock_vector_lock();
setup_vector_irq(smp_processor_id());
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
cpu_set_state_online(smp_processor_id());
x86_platform.nmi_init();
/* enable local interrupts */
local_irq_enable();
/* to prevent fake stack check failure in clock setup */
boot_init_stack_canary();
x86_cpuinit.setup_percpu_clockev();
wmb();
cpu_startup_entry(CPUHP_ONLINE);
}
void __init efi_call_phys_epilog(pgd_t *save_pgd)
{
/*
* After the lock is released, the original page table is restored.
*/
int pgd_idx;
int nr_pgds;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
write_cr3((unsigned long)save_pgd);
__flush_tlb_all();
return;
}
nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
kfree(save_pgd);
__flush_tlb_all();
early_code_mapping_set_exec(0);
}
pgd_t * __init efi_call_phys_prolog(void)
{
struct desc_ptr gdt_descr;
pgd_t *save_pgd;
/* Current pgd is swapper_pg_dir, we'll restore it later: */
save_pgd = swapper_pg_dir;
load_cr3(initial_page_table);
__flush_tlb_all();
gdt_descr.address = __pa(get_cpu_gdt_table(0));
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
return save_pgd;
}
void __init efi_call_phys_epilog(void)
{
struct desc_ptr gdt_descr;
gdt_descr.address = get_cpu_gdt_table(0);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
clone_pgd_range(swapper_pg_dir, efi_bak_pg_dir_pointer, KERNEL_PGD_PTRS);
/*
* After the lock is released, the original page table is restored.
*/
__flush_tlb_all();
local_irq_restore(efi_rt_eflags);
}
void __init efi_call_phys_epilog(void)
{
/*
* After the lock is released, the original page table is restored.
*/
int pgd;
int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
if (!efi_enabled(EFI_OLD_MEMMAP))
return;
for (pgd = 0; pgd < n_pgds; pgd++)
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
kfree(save_pgd);
__flush_tlb_all();
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
void __init efi_call_phys_prelog(void)
{
unsigned long vaddress;
int pgd;
int n_pgds;
early_code_mapping_set_exec(1);
local_irq_save(efi_flags);
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
for (pgd = 0; pgd < n_pgds; pgd++) {
save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
}
__flush_tlb_all();
}
void __init efi_call_phys_epilog(void)
{
/*
* After the lock is released, the original page table is restored.
*/
int pgd;
int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
for (pgd = 0; pgd < n_pgds; pgd++)
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
kfree(save_pgd);
#ifdef CONFIG_PAX_PER_CPU_PGD
load_cr3(get_cpu_pgd(smp_processor_id(), kernel));
#endif
__flush_tlb_all();
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
void __init efi_call_phys_prelog(void)
{
struct desc_ptr gdt_descr;
local_irq_save(efi_rt_eflags);
clone_pgd_range(efi_bak_pg_dir_pointer, swapper_pg_dir, KERNEL_PGD_PTRS);
clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
/*
* After the lock is released, the original page table is restored.
*/
__flush_tlb_all();
gdt_descr.address = (struct desc_struct *)__pa(get_cpu_gdt_table(0));
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
}
void efi_call_phys_prelog(void)
{
unsigned long cr4;
unsigned long temp;
struct desc_ptr gdt_descr;
local_irq_save(efi_rt_eflags);
/*
* If I don't have PAE, I should just duplicate two entries in page
* directory. If I have PAE, I just need to duplicate one entry in
* page directory.
*/
cr4 = read_cr4();
if (cr4 & X86_CR4_PAE) {
efi_bak_pg_dir_pointer[0].pgd =
swapper_pg_dir[pgd_index(0)].pgd;
swapper_pg_dir[0].pgd =
swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
} else {
efi_bak_pg_dir_pointer[0].pgd =
swapper_pg_dir[pgd_index(0)].pgd;
efi_bak_pg_dir_pointer[1].pgd =
swapper_pg_dir[pgd_index(0x400000)].pgd;
swapper_pg_dir[pgd_index(0)].pgd =
swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
temp = PAGE_OFFSET + 0x400000;
swapper_pg_dir[pgd_index(0x400000)].pgd =
swapper_pg_dir[pgd_index(temp)].pgd;
}
/*
* After the lock is released, the original page table is restored.
*/
__flush_tlb_all();
gdt_descr.address = __pa(get_cpu_gdt_table(0));
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
}
/* Setup the direct mapping of the physical memory at PAGE_OFFSET.
This runs before bootmem is initialized and gets pages directly from the
physical memory. To access them they are temporarily mapped. */
void __init_refok init_memory_mapping(unsigned long start, unsigned long end)
{
unsigned long next;
Dprintk("init_memory_mapping\n");
/*
* Find space for the kernel direct mapping tables.
* Later we should allocate these tables in the local node of the memory
* mapped. Unfortunately this is done currently before the nodes are
* discovered.
*/
if (!after_bootmem)
find_early_table_space(end);
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
for (; start < end; start = next) {
unsigned long pud_phys;
pgd_t *pgd = pgd_offset_k(start);
pud_t *pud;
if (after_bootmem)
pud = pud_offset(pgd, start & PGDIR_MASK);
else
pud = alloc_low_page(&pud_phys);
next = start + PGDIR_SIZE;
if (next > end)
next = end;
phys_pud_init(pud, __pa(start), __pa(next));
if (!after_bootmem)
set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
unmap_low_page(pud);
}
if (!after_bootmem)
mmu_cr4_features = read_cr4();
__flush_tlb_all();
}
/*
* Enables/disables executability of a given kernel page and
* returns the previous setting.
*/
int __init set_kernel_exec(unsigned long vaddr, int enable)
{
pte_t *pte;
int ret = 1;
if (!nx_enabled)
goto out;
pte = lookup_address(vaddr);
BUG_ON(!pte);
if (!pte_exec_kernel(*pte))
ret = 0;
if (enable)
pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
else
pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
__flush_tlb_all();
out:
return ret;
}
void __init efi_call_phys_prolog(void)
{
struct desc_ptr gdt_descr;
#ifdef CONFIG_PAX_KERNEXEC
struct desc_struct d;
#endif
local_irq_save(efi_rt_eflags);
load_cr3(initial_page_table);
__flush_tlb_all();
#ifdef CONFIG_PAX_KERNEXEC
pack_descriptor(&d, 0, 0xFFFFF, 0x9B, 0xC);
write_gdt_entry(get_cpu_gdt_table(0), GDT_ENTRY_KERNEXEC_EFI_CS, &d, DESCTYPE_S);
pack_descriptor(&d, 0, 0xFFFFF, 0x93, 0xC);
write_gdt_entry(get_cpu_gdt_table(0), GDT_ENTRY_KERNEXEC_EFI_DS, &d, DESCTYPE_S);
#endif
gdt_descr.address = __pa(get_cpu_gdt_table(0));
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
}
/*
* paging_init() sets up the page tables - note that the first 8MB are
* already mapped by head.S.
*
* This routines also unmaps the page at virtual kernel address 0, so
* that we can trap those pesky NULL-reference errors in the kernel.
*/
void __init paging_init(void)
{
#ifdef CONFIG_X86_PAE
set_nx();
if (nx_enabled)
printk("NX (Execute Disable) protection: active\n");
#endif
pagetable_init();
load_cr3(swapper_pg_dir);
#ifdef CONFIG_X86_PAE
/*
* We will bail out later - printk doesn't work right now so
* the user would just see a hanging kernel.
*/
if (cpu_has_pae)
set_in_cr4(X86_CR4_PAE);
#endif
__flush_tlb_all();
kmap_init();
}
static void __init zap_identity_mappings(void)
{
pgd_t *pgd = pgd_offset_k(0UL);
pgd_clear(pgd);
__flush_tlb_all();
}
void __init kasan_init(void)
{
int i;
void *shadow_cpu_entry_begin, *shadow_cpu_entry_end;
#ifdef CONFIG_KASAN_INLINE
register_die_notifier(&kasan_die_notifier);
#endif
memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt));
/*
* We use the same shadow offset for 4- and 5-level paging to
* facilitate boot-time switching between paging modes.
* As result in 5-level paging mode KASAN_SHADOW_START and
* KASAN_SHADOW_END are not aligned to PGD boundary.
*
* KASAN_SHADOW_START doesn't share PGD with anything else.
* We claim whole PGD entry to make things easier.
*
* KASAN_SHADOW_END lands in the last PGD entry and it collides with
* bunch of things like kernel code, modules, EFI mapping, etc.
* We need to take extra steps to not overwrite them.
*/
if (pgtable_l5_enabled()) {
void *ptr;
ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
memcpy(tmp_p4d_table, (void *)ptr, sizeof(tmp_p4d_table));
set_pgd(&early_top_pgt[pgd_index(KASAN_SHADOW_END)],
__pgd(__pa(tmp_p4d_table) | _KERNPG_TABLE));
}
load_cr3(early_top_pgt);
__flush_tlb_all();
clear_pgds(KASAN_SHADOW_START & PGDIR_MASK, KASAN_SHADOW_END);
kasan_populate_early_shadow((void *)(KASAN_SHADOW_START & PGDIR_MASK),
kasan_mem_to_shadow((void *)PAGE_OFFSET));
for (i = 0; i < E820_MAX_ENTRIES; i++) {
if (pfn_mapped[i].end == 0)
break;
map_range(&pfn_mapped[i]);
}
shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE;
shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
shadow_cpu_entry_begin = (void *)round_down(
(unsigned long)shadow_cpu_entry_begin, PAGE_SIZE);
shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE +
CPU_ENTRY_AREA_MAP_SIZE);
shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
shadow_cpu_entry_end = (void *)round_up(
(unsigned long)shadow_cpu_entry_end, PAGE_SIZE);
kasan_populate_early_shadow(
kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
shadow_cpu_entry_begin);
kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
(unsigned long)shadow_cpu_entry_end, 0);
kasan_populate_early_shadow(shadow_cpu_entry_end,
kasan_mem_to_shadow((void *)__START_KERNEL_map));
kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
(unsigned long)kasan_mem_to_shadow(_end),
early_pfn_to_nid(__pa(_stext)));
kasan_populate_early_shadow(kasan_mem_to_shadow((void *)MODULES_END),
(void *)KASAN_SHADOW_END);
load_cr3(init_top_pgt);
__flush_tlb_all();
/*
* kasan_early_shadow_page has been used as early shadow memory, thus
* it may contain some garbage. Now we can clear and write protect it,
* since after the TLB flush no one should write to it.
*/
memset(kasan_early_shadow_page, 0, PAGE_SIZE);
for (i = 0; i < PTRS_PER_PTE; i++) {
pte_t pte;
pgprot_t prot;
prot = __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC);
pgprot_val(prot) &= __default_kernel_pte_mask;
pte = __pte(__pa(kasan_early_shadow_page) | pgprot_val(prot));
set_pte(&kasan_early_shadow_pte[i], pte);
}
/* Flush TLBs again to be sure that write protection applied. */
__flush_tlb_all();
init_task.kasan_depth = 0;
pr_info("KernelAddressSanitizer initialized\n");
}
