VERSION = 5
PATCHLEVEL = 13
SUBLEVEL = 0
-EXTRAVERSION = -rc3
-NAME = Frozen Wasteland
+EXTRAVERSION =
+NAME = Opossums on Parade
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
# Limit inlining across translation units to reduce binary size
KBUILD_LDFLAGS += -mllvm -import-instr-limit=5
+
+# Check for frame size exceeding threshold during prolog/epilog insertion
+# when using lld < 13.0.0.
+ifneq ($(CONFIG_FRAME_WARN),0)
+ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0)
+KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN)
+endif
+endif
endif
ifdef CONFIG_LTO
endif
ifeq ($(CONFIG_RELR),y)
- LDFLAGS_vmlinux += --pack-dyn-relocs=relr
+ LDFLAGS_vmlinux += --pack-dyn-relocs=relr --use-android-relr-tags
endif
# We never want expected sections to be placed heuristically by the
#ifdef CONFIG_CPU_IDLE
extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index);
+#define __cpuidle_method_section __used __section("__cpuidle_method_of_table")
#else
static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index) { return -ENODEV; }
+#define __cpuidle_method_section __maybe_unused /* drop silently */
#endif
/* Common ARM WFI state */
#define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops) \
static const struct of_cpuidle_method __cpuidle_method_of_table_##name \
- __used __section("__cpuidle_method_of_table") \
- = { .method = _method, .ops = _ops }
+ __cpuidle_method_section = { .method = _method, .ops = _ops }
extern int arm_cpuidle_suspend(int index);
extern int arm_cpuidle_init(int cpu);
+ struct arm_cpuidle_irq_context { };
+
+ #define arm_cpuidle_save_irq_context(c) (void)c
+ #define arm_cpuidle_restore_irq_context(c) (void)c
+
#endif
#define __ARM_KVM_ASM_H__
#include <asm/hyp_image.h>
+ #include <asm/insn.h>
#include <asm/virt.h>
#define ARM_EXIT_WITH_SERROR_BIT 31
#define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18
#define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19
#define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20
+#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21
#ifndef __ASSEMBLY__
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
+
extern u64 __vgic_v3_get_gic_config(void);
extern u64 __vgic_v3_read_vmcr(void);
extern void __vgic_v3_write_vmcr(u32 vmcr);
* Copyright (C) 2013 Linaro Limited.
* Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org>
*/
+ #include <linux/extable.h>
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/kprobes.h>
- #include <linux/extable.h>
- #include <linux/slab.h>
- #include <linux/stop_machine.h>
#include <linux/sched/debug.h>
#include <linux/set_memory.h>
+ #include <linux/slab.h>
+ #include <linux/stop_machine.h>
#include <linux/stringify.h>
+ #include <linux/uaccess.h>
#include <linux/vmalloc.h>
- #include <asm/traps.h>
- #include <asm/ptrace.h>
+
#include <asm/cacheflush.h>
- #include <asm/debug-monitors.h>
#include <asm/daifflags.h>
- #include <asm/system_misc.h>
+ #include <asm/debug-monitors.h>
#include <asm/insn.h>
- #include <linux/uaccess.h>
#include <asm/irq.h>
+ #include <asm/patching.h>
+ #include <asm/ptrace.h>
#include <asm/sections.h>
+ #include <asm/system_misc.h>
+ #include <asm/traps.h>
#include "decode-insn.h"
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
- * We increment the nmissed count for accounting,
- * we can also use npre/npostfault count for accounting
- * these specific fault cases.
- */
- kprobes_inc_nmissed_count(cur);
-
- /*
- * We come here because instructions in the pre/post
- * handler caused the page_fault, this could happen
- * if handler tries to access user space by
- * copy_from_user(), get_user() etc. Let the
- * user-specified handler try to fix it first.
- */
- if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
- return 1;
-
- /*
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
- #include <linux/lockdep.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/nospec.h>
#include <linux/prctl.h>
#include <asm/alternative.h>
- #include <asm/arch_gicv3.h>
#include <asm/compat.h>
#include <asm/cpufeature.h>
#include <asm/cacheflush.h>
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
- static void noinstr __cpu_do_idle(void)
- {
- dsb(sy);
- wfi();
- }
-
- static void noinstr __cpu_do_idle_irqprio(void)
- {
- unsigned long pmr;
- unsigned long daif_bits;
-
- daif_bits = read_sysreg(daif);
- write_sysreg(daif_bits | PSR_I_BIT | PSR_F_BIT, daif);
-
- /*
- * Unmask PMR before going idle to make sure interrupts can
- * be raised.
- */
- pmr = gic_read_pmr();
- gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-
- __cpu_do_idle();
-
- gic_write_pmr(pmr);
- write_sysreg(daif_bits, daif);
- }
-
- /*
- * cpu_do_idle()
- *
- * Idle the processor (wait for interrupt).
- *
- * If the CPU supports priority masking we must do additional work to
- * ensure that interrupts are not masked at the PMR (because the core will
- * not wake up if we block the wake up signal in the interrupt controller).
- */
- void noinstr cpu_do_idle(void)
- {
- if (system_uses_irq_prio_masking())
- __cpu_do_idle_irqprio();
- else
- __cpu_do_idle();
- }
-
- /*
- * This is our default idle handler.
- */
- void noinstr arch_cpu_idle(void)
- {
- /*
- * This should do all the clock switching and wait for interrupt
- * tricks
- */
- cpu_do_idle();
- raw_local_irq_enable();
- }
-
#ifdef CONFIG_HOTPLUG_CPU
void arch_cpu_idle_dead(void)
{
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
+ /*
+ * For the benefit of the unwinder, set up childregs->stackframe
+ * as the final frame for the new task.
+ */
+ p->thread.cpu_context.fp = (unsigned long)childregs->stackframe;
ptrace_hw_copy_thread(p);
write_sysreg(val, cntkctl_el1);
}
+ static void compat_thread_switch(struct task_struct *next)
+ {
+ if (!is_compat_thread(task_thread_info(next)))
+ return;
+
+ if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+ set_tsk_thread_flag(next, TIF_NOTIFY_RESUME);
+ }
+
static void update_sctlr_el1(u64 sctlr)
{
/*
ssbs_thread_switch(next);
erratum_1418040_thread_switch(prev, next);
ptrauth_thread_switch_user(next);
+ compat_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
struct stackframe frame;
unsigned long stack_page, ret = 0;
int count = 0;
- if (!p || p == current || p->state == TASK_RUNNING)
+ if (!p || p == current || task_is_running(p))
return 0;
stack_page = (unsigned long)try_get_task_stack(p);
*/
void arch_setup_new_exec(void)
{
- current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+ unsigned long mmflags = 0;
+
+ if (is_compat_task()) {
+ mmflags = MMCF_AARCH32;
+ if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+ set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+ }
+ current->mm->context.flags = mmflags;
ptrauth_thread_init_user();
mte_thread_init_user();
core_initcall(tagged_addr_init);
#endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */
- asmlinkage void __sched arm64_preempt_schedule_irq(void)
- {
- lockdep_assert_irqs_disabled();
-
- /*
- * Preempting a task from an IRQ means we leave copies of PSTATE
- * on the stack. cpufeature's enable calls may modify PSTATE, but
- * resuming one of these preempted tasks would undo those changes.
- *
- * Only allow a task to be preempted once cpufeatures have been
- * enabled.
- */
- if (system_capabilities_finalized())
- preempt_schedule_irq();
- }
-
#ifdef CONFIG_BINFMT_ELF
int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
bool has_interp, bool is_interp)
* page tables.
*/
secondary_data.task = idle;
- secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
update_cpu_boot_status(CPU_MMU_OFF);
- __flush_dcache_area(&secondary_data, sizeof(secondary_data));
/* Now bring the CPU into our world */
ret = boot_secondary(cpu, idle);
pr_crit("CPU%u: failed to come online\n", cpu);
secondary_data.task = NULL;
- secondary_data.stack = NULL;
- __flush_dcache_area(&secondary_data, sizeof(secondary_data));
status = READ_ONCE(secondary_data.status);
if (status == CPU_MMU_OFF)
status = READ_ONCE(__early_cpu_boot_status);
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
const struct cpu_operations *ops;
- unsigned int cpu;
-
- cpu = task_cpu(current);
- set_my_cpu_offset(per_cpu_offset(cpu));
+ unsigned int cpu = smp_processor_id();
/*
* All kernel threads share the same mm context; grab a
init_gic_priority_masking();
rcu_cpu_starting(cpu);
- preempt_disable();
trace_hardirqs_off();
/*
pr_crit("CPU%u: cpu didn't die\n", cpu);
return;
}
- pr_notice("CPU%u: shutdown\n", cpu);
+ pr_debug("CPU%u: shutdown\n", cpu);
/*
* Now that the dying CPU is beyond the point of no return w.r.t.
void __init smp_prepare_boot_cpu(void)
{
+ /*
+ * The runtime per-cpu areas have been allocated by
+ * setup_per_cpu_areas(), and CPU0's boot time per-cpu area will be
+ * freed shortly, so we must move over to the runtime per-cpu area.
+ */
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
cpuinfo_store_boot_cpu();
}
}
+ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
+ {
+ if (likely(!vcpu_mode_is_32bit(vcpu)))
+ return false;
+
+ return !system_supports_32bit_el0() ||
+ static_branch_unlikely(&arm64_mismatched_32bit_el0);
+ }
+
/**
* kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
* @vcpu: The VCPU pointer
return ret;
}
- if (run->immediate_exit)
- return -EINTR;
-
vcpu_load(vcpu);
+ if (run->immediate_exit) {
+ ret = -EINTR;
+ goto out;
+ }
+
kvm_sigset_activate(vcpu);
ret = 1;
* with the asymmetric AArch32 case), return to userspace with
* a fatal error.
*/
- if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+ if (vcpu_mode_is_bad_32bit(vcpu)) {
/*
* As we have caught the guest red-handed, decide that
* it isn't fit for purpose anymore by making the vcpu
}
kvm_sigset_deactivate(vcpu);
+
+out:
+ /*
+ * In the unlikely event that we are returning to userspace
+ * with pending exceptions or PC adjustment, commit these
+ * adjustments in order to give userspace a consistent view of
+ * the vcpu state. Note that this relies on __kvm_adjust_pc()
+ * being preempt-safe on VHE.
+ */
+ if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION |
+ KVM_ARM64_INCREMENT_PC)))
+ kvm_call_hyp(__kvm_adjust_pc, vcpu);
vcpu_put(vcpu);
return ret;
if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
stage2_unmap_vm(vcpu->kvm);
else
- __flush_icache_all();
+ icache_inval_all_pou();
}
vcpu_reset_hcr(vcpu);
#include <nvhe/trap_handler.h>
struct hyp_pool hpool;
-struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
unsigned long hyp_nr_cpus;
#define hyp_percpu_size ((unsigned long)__per_cpu_end - \
static void *hyp_pgt_base;
static void *host_s2_mem_pgt_base;
static void *host_s2_dev_pgt_base;
+static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
static int divide_memory_pool(void *virt, unsigned long size)
{
for (i = 0; i < hyp_nr_cpus; i++) {
params = per_cpu_ptr(&kvm_init_params, i);
params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd);
- __flush_dcache_area(params, sizeof(*params));
+ dcache_clean_inval_poc((unsigned long)params,
+ (unsigned long)params + sizeof(*params));
}
}
next = pmd_addr_end(addr, end);
/* try section mapping first */
- if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
+ if (((addr | next | phys) & ~PMD_MASK) == 0 &&
(flags & NO_BLOCK_MAPPINGS) == 0) {
pmd_set_huge(pmdp, phys, prot);
*/
BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
- if (rodata_full || crash_mem_map || debug_pagealloc_enabled())
+ if (rodata_full || crash_mem_map || debug_pagealloc_enabled() ||
+ IS_ENABLED(CONFIG_KFENCE))
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
}
#endif
- #if !ARM64_SWAPPER_USES_SECTION_MAPS
+ #if !ARM64_KERNEL_USES_PMD_MAPS
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
return vmemmap_populate_basepages(start, end, node, altmap);
}
- #else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
+ #else /* !ARM64_KERNEL_USES_PMD_MAPS */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
return 0;
}
- #endif /* !ARM64_SWAPPER_USES_SECTION_MAPS */
+ #endif /* !ARM64_KERNEL_USES_PMD_MAPS */
+
+ #ifdef CONFIG_MEMORY_HOTPLUG
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
- #ifdef CONFIG_MEMORY_HOTPLUG
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
unmap_hotplug_range(start, end, true, altmap);
free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
- #endif
}
+ #endif /* CONFIG_MEMORY_HOTPLUG */
static inline pud_t *fixmap_pud(unsigned long addr)
{
static DEFINE_STATIC_KEY_TRUE(deferred_pages);
/*
- * Calling kasan_free_pages() only after deferred memory initialization
+ * Calling kasan_poison_pages() only after deferred memory initialization
* has completed. Poisoning pages during deferred memory init will greatly
* lengthen the process and cause problem in large memory systems as the
* deferred pages initialization is done with interrupt disabled.
* on-demand allocation and then freed again before the deferred pages
* initialization is done, but this is not likely to happen.
*/
- static inline void kasan_free_nondeferred_pages(struct page *page, int order,
- bool init, fpi_t fpi_flags)
+ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
{
- if (static_branch_unlikely(&deferred_pages))
- return;
- if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
- (fpi_flags & FPI_SKIP_KASAN_POISON))
- return;
- kasan_free_pages(page, order, init);
+ return static_branch_unlikely(&deferred_pages) ||
+ (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+ (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+ PageSkipKASanPoison(page);
}
/* Returns true if the struct page for the pfn is uninitialised */
return false;
}
#else
- static inline void kasan_free_nondeferred_pages(struct page *page, int order,
- bool init, fpi_t fpi_flags)
+ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
{
- if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
- (fpi_flags & FPI_SKIP_KASAN_POISON))
- return;
- kasan_free_pages(page, order, init);
+ return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+ (fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+ PageSkipKASanPoison(page);
}
static inline bool early_page_uninitialised(unsigned long pfn)
return ret;
}
- static void kernel_init_free_pages(struct page *page, int numpages)
+ static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
{
int i;
+ if (zero_tags) {
+ for (i = 0; i < numpages; i++)
+ tag_clear_highpage(page + i);
+ return;
+ }
+
/* s390's use of memset() could override KASAN redzones. */
kasan_disable_current();
for (i = 0; i < numpages; i++) {
unsigned int order, bool check_free, fpi_t fpi_flags)
{
int bad = 0;
- bool init;
+ bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
VM_BUG_ON_PAGE(PageTail(page), page);
* With hardware tag-based KASAN, memory tags must be set before the
* page becomes unavailable via debug_pagealloc or arch_free_page.
*/
- init = want_init_on_free();
- if (init && !kasan_has_integrated_init())
- kernel_init_free_pages(page, 1 << order);
- kasan_free_nondeferred_pages(page, order, init, fpi_flags);
+ if (kasan_has_integrated_init()) {
+ if (!skip_kasan_poison)
+ kasan_free_pages(page, order);
+ } else {
+ bool init = want_init_on_free();
+
+ if (init)
+ kernel_init_free_pages(page, 1 << order, false);
+ if (!skip_kasan_poison)
+ kasan_poison_pages(page, order, init);
+ }
/*
* arch_free_page() can make the page's contents inaccessible. s390
inline void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags)
{
- bool init;
-
set_page_private(page, 0);
set_page_refcounted(page);
* kasan_alloc_pages and kernel_init_free_pages must be
* kept together to avoid discrepancies in behavior.
*/
- init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
- kasan_alloc_pages(page, order, init);
- if (init && !kasan_has_integrated_init())
- kernel_init_free_pages(page, 1 << order);
+ if (kasan_has_integrated_init()) {
+ kasan_alloc_pages(page, order, gfp_flags);
+ } else {
+ bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
+
+ kasan_unpoison_pages(page, order, init);
+ if (init)
+ kernel_init_free_pages(page, 1 << order,
+ gfp_flags & __GFP_ZEROTAGS);
+ }
set_page_owner(page, order, gfp_flags);
}
* Skip populated array elements to determine if any pages need
* to be allocated before disabling IRQs.
*/
- while (page_array && page_array[nr_populated] && nr_populated < nr_pages)
+ while (page_array && nr_populated < nr_pages && page_array[nr_populated])
nr_populated++;
+ /* Already populated array? */
+ if (unlikely(page_array && nr_pages - nr_populated == 0))
+ return nr_populated;
+
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
del_page_from_free_list(page_head, zone, page_order);
break_down_buddy_pages(zone, page_head, page, 0,
page_order, migratetype);
+ if (!is_migrate_isolate(migratetype))
+ __mod_zone_freepage_state(zone, -1, migratetype);
ret = true;
break;
}