results in the system call being skipped immediately.
- seccomp syscall wired up
- For best performance, an arch should use seccomp_phase1 and
- seccomp_phase2 directly. It should call seccomp_phase1 for all
- syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
- need to be called from a ptrace-safe context. It must then
- call seccomp_phase2 if seccomp_phase1 returns anything other
- than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
-
- As an additional optimization, an arch may provide seccomp_data
- directly to seccomp_phase1; this avoids multiple calls
- to the syscall_xyz helpers for every syscall.
-
config SECCOMP_FILTER
def_bool y
depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
config CPU_NO_EFFICIENT_FFS
def_bool n
+config HAVE_ARCH_VMAP_STACK
+ def_bool n
+ help
+ An arch should select this symbol if it can support kernel stacks
+ in vmalloc space. This means:
+
+ - vmalloc space must be large enough to hold many kernel stacks.
+ This may rule out many 32-bit architectures.
+
+ - Stacks in vmalloc space need to work reliably. For example, if
+ vmap page tables are created on demand, either this mechanism
+ needs to work while the stack points to a virtual address with
+ unpopulated page tables or arch code (switch_to() and switch_mm(),
+ most likely) needs to ensure that the stack's page table entries
+ are populated before running on a possibly unpopulated stack.
+
+ - If the stack overflows into a guard page, something reasonable
+ should happen. The definition of "reasonable" is flexible, but
+ instantly rebooting without logging anything would be unfriendly.
+
+config VMAP_STACK
+ default y
+ bool "Use a virtually-mapped stack"
+ depends on HAVE_ARCH_VMAP_STACK && !KASAN
+ ---help---
+ Enable this if you want the use virtually-mapped kernel stacks
+ with guard pages. This causes kernel stack overflows to be
+ caught immediately rather than causing difficult-to-diagnose
+ corruption.
+
+ This is presently incompatible with KASAN because KASAN expects
+ the stack to map directly to the KASAN shadow map using a formula
+ that is incorrect if the stack is in vmalloc space.
+
source "kernel/gcov/Kconfig"
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_EBPF_JIT if X86_64
+ select HAVE_ARCH_VMAP_STACK if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_EXIT_THREAD
select HAVE_FENTRY if X86_64
select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_FUNCTION_GRAPH_FP_TEST
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
#include <asm/x86_init.h>
#include <asm/reboot.h>
-static int kvmclock = 1;
+static int kvmclock __ro_after_init = 1;
static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
static cycle_t kvm_sched_clock_offset;
put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+ x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
".popsection");
/* identity function, which can be inlined */
- u32 _paravirt_ident_32(u32 x)
+ u32 notrace _paravirt_ident_32(u32 x)
{
return x;
}
- u64 _paravirt_ident_64(u64 x)
+ u64 notrace _paravirt_ident_64(u64 x)
{
return x;
}
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
#endif
-struct pv_mmu_ops pv_mmu_ops = {
+struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
.read_cr2 = native_read_cr2,
.write_cr2 = native_write_cr2,
struct list_head vmcs02_pool;
int vmcs02_num;
u64 vmcs01_tsc_offset;
+ bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
/*
bool pi_pending;
u16 posted_intr_nv;
+ unsigned long *msr_bitmap;
+
struct hrtimer preemption_timer;
bool preemption_timer_expired;
static unsigned long *vmx_msr_bitmap_longmode;
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;
- static unsigned long *vmx_msr_bitmap_nested;
static unsigned long *vmx_vmread_bitmap;
static unsigned long *vmx_vmwrite_bitmap;
new.control) != old.control);
}
+ static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+ {
+ vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
/* Setup TSC multiplier */
if (kvm_has_tsc_control &&
- vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
- vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
- vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
- }
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+ decache_tsc_multiplier(vmx);
vmx_vcpu_pi_load(vcpu, cpu);
vmx->host_pkru = read_pkru();
unsigned long *msr_bitmap;
if (is_guest_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_nested;
+ msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
else if (cpu_has_secondary_exec_ctrls() &&
(vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
if (!vmx_msr_bitmap_longmode_x2apic)
goto out4;
- if (nested) {
- vmx_msr_bitmap_nested =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_nested)
- goto out5;
- }
-
vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmread_bitmap)
goto out6;
memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
- if (nested)
- memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
out7:
free_page((unsigned long)vmx_vmread_bitmap);
out6:
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
- out5:
free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
out4:
free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_a);
free_page((unsigned long)vmx_vmwrite_bitmap);
free_page((unsigned long)vmx_vmread_bitmap);
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
free_kvm_area();
}
return 1;
}
+ if (cpu_has_vmx_msr_bitmap()) {
+ vmx->nested.msr_bitmap =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx->nested.msr_bitmap)
+ goto out_msr_bitmap;
+ }
+
vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
- return -ENOMEM;
+ goto out_cached_vmcs12;
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
- if (!shadow_vmcs) {
- kfree(vmx->nested.cached_vmcs12);
- return -ENOMEM;
- }
+ if (!shadow_vmcs)
+ goto out_shadow_vmcs;
/* mark vmcs as shadow */
shadow_vmcs->revision_id |= (1u << 31);
/* init shadow vmcs */
skip_emulated_instruction(vcpu);
nested_vmx_succeed(vcpu);
return 1;
+
+ out_shadow_vmcs:
+ kfree(vmx->nested.cached_vmcs12);
+
+ out_cached_vmcs12:
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+
+ out_msr_bitmap:
+ return -ENOMEM;
}
/*
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
nested_release_vmcs12(vmx);
+ if (vmx->nested.msr_bitmap) {
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+ vmx->nested.msr_bitmap = NULL;
+ }
if (enable_shadow_vmcs)
free_vmcs(vmx->nested.current_shadow_vmcs);
kfree(vmx->nested.cached_vmcs12);
{
u32 sec_exec_control;
+ /* Postpone execution until vmcs01 is the current VMCS. */
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ return;
+ }
+
/*
* There is not point to enable virtualize x2apic without enable
* apicv
{
int msr;
struct page *page;
- unsigned long *msr_bitmap;
+ unsigned long *msr_bitmap_l1;
+ unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
+ /* This shortcut is ok because we support only x2APIC MSRs so far. */
if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
return false;
WARN_ON(1);
return false;
}
- msr_bitmap = (unsigned long *)kmap(page);
- if (!msr_bitmap) {
+ msr_bitmap_l1 = (unsigned long *)kmap(page);
+ if (!msr_bitmap_l1) {
nested_release_page_clean(page);
WARN_ON(1);
return false;
}
+ memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+
if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
if (nested_cpu_has_apic_reg_virt(vmcs12))
for (msr = 0x800; msr <= 0x8ff; msr++)
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
msr, MSR_TYPE_R);
- /* TPR is allowed */
- nested_vmx_disable_intercept_for_msr(msr_bitmap,
- vmx_msr_bitmap_nested,
+
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_TASKPRI >> 4),
MSR_TYPE_R | MSR_TYPE_W);
+
if (nested_cpu_has_vid(vmcs12)) {
- /* EOI and self-IPI are allowed */
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_EOI >> 4),
MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
MSR_TYPE_W);
}
- } else {
- /*
- * Enable reading intercept of all the x2apic
- * MSRs. We should not rely on vmcs12 to do any
- * optimizations here, it may have been modified
- * by L1.
- */
- for (msr = 0x800; msr <= 0x8ff; msr++)
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- msr,
- MSR_TYPE_R);
-
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_TASKPRI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_EOI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
- MSR_TYPE_W);
}
kunmap(page);
nested_release_page_clean(page);
}
if (cpu_has_vmx_msr_bitmap() &&
- exec_control & CPU_BASED_USE_MSR_BITMAPS) {
- nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
- /* MSR_BITMAP will be set by following vmx_set_efer. */
- } else
+ exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+ nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+ ; /* MSR_BITMAP will be set by following vmx_set_efer. */
+ else
exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
/*
vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
else
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
if (enable_vpid) {
/*
else
vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_VMX_PREEMPTION_TIMER);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
+
+ if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+ vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+ vmx_set_virtual_x2apic_mode(vcpu,
+ vcpu->arch.apic_base & X2APIC_ENABLE);
+ }
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;
~FEATURE_CONTROL_LMCE;
}
-static struct kvm_x86_ops vmx_x86_ops = {
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.hardware_setup = hardware_setup,
* You need to add an if/def entry if you introduce a new memory region
* compatible with KASLR. Your entry must be in logical order with memory
* layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to
+ * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
* ensure that this order is correct and won't be changed.
*/
static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-static const unsigned long vaddr_end = VMEMMAP_START;
+
+#if defined(CONFIG_X86_ESPFIX64)
+static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
+#elif defined(CONFIG_EFI)
+static const unsigned long vaddr_end = EFI_VA_START;
+#else
+static const unsigned long vaddr_end = __START_KERNEL_map;
+#endif
/* Default values */
unsigned long page_offset_base = __PAGE_OFFSET_BASE;
EXPORT_SYMBOL(page_offset_base);
unsigned long vmalloc_base = __VMALLOC_BASE;
EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base = __VMEMMAP_BASE;
+EXPORT_SYMBOL(vmemmap_base);
/*
* Memory regions randomized by KASLR (except modules that use a separate logic
} kaslr_regions[] = {
{ &page_offset_base, 64/* Maximum */ },
{ &vmalloc_base, VMALLOC_SIZE_TB },
+ { &vmemmap_base, 1 },
};
/* Get size in bytes used by the memory region */
*/
static inline bool kaslr_memory_enabled(void)
{
- return kaslr_enabled() && !config_enabled(CONFIG_KASAN);
+ return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
}
/* Initialize base and padding for each memory region randomized with KASLR */
struct rnd_state rand_state;
unsigned long remain_entropy;
+ /*
+ * All these BUILD_BUG_ON checks ensures the memory layout is
+ * consistent with the vaddr_start/vaddr_end variables.
+ */
+ BUILD_BUG_ON(vaddr_start >= vaddr_end);
+ BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+ vaddr_end >= EFI_VA_START);
+ BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
+ config_enabled(CONFIG_EFI)) &&
+ vaddr_end >= __START_KERNEL_map);
+ BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
if (!kaslr_memory_enabled())
return;
save_stack_trace_tsk(task, &trace);
for (i = 0; i < trace.nr_entries; i++) {
- seq_printf(m, "[<%pK>] %pS\n",
+ seq_printf(m, "[<%pK>] %pB\n",
(void *)entries[i], (void *)entries[i]);
}
unlock_trace(task);
static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
- struct mm_struct *mm;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
- mm = get_task_mm(task);
+ exe_file = get_task_exe_file(task);
put_task_struct(task);
- if (!mm)
- return -ENOENT;
- exe_file = get_mm_exe_file(mm);
- mmput(mm);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
-# if THREAD_SIZE >= PAGE_SIZE
-static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
- int node)
+# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
{
+#ifdef CONFIG_VMAP_STACK
+ void *stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
+ VMALLOC_START, VMALLOC_END,
+ THREADINFO_GFP | __GFP_HIGHMEM,
+ PAGE_KERNEL,
+ 0, node,
+ __builtin_return_address(0));
+
+ /*
+ * We can't call find_vm_area() in interrupt context, and
+ * free_thread_stack() can be called in interrupt context,
+ * so cache the vm_struct.
+ */
+ if (stack)
+ tsk->stack_vm_area = find_vm_area(stack);
+ return stack;
+#else
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
THREAD_SIZE_ORDER);
return page ? page_address(page) : NULL;
+#endif
}
-static inline void free_thread_stack(unsigned long *stack)
+static inline void free_thread_stack(struct task_struct *tsk)
{
- __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
+ if (task_stack_vm_area(tsk))
+ vfree(tsk->stack);
+ else
+ __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
}
# else
static struct kmem_cache *thread_stack_cache;
return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_stack(unsigned long *stack)
+static void free_thread_stack(struct task_struct *tsk)
{
- kmem_cache_free(thread_stack_cache, stack);
+ kmem_cache_free(thread_stack_cache, tsk->stack);
}
void thread_stack_cache_init(void)
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(unsigned long *stack, int account)
+static void account_kernel_stack(struct task_struct *tsk, int account)
{
- /* All stack pages are in the same zone and belong to the same memcg. */
- struct page *first_page = virt_to_page(stack);
+ void *stack = task_stack_page(tsk);
+ struct vm_struct *vm = task_stack_vm_area(tsk);
+
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
+ if (vm) {
+ int i;
+
+ BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+ mod_zone_page_state(page_zone(vm->pages[i]),
+ NR_KERNEL_STACK_KB,
+ PAGE_SIZE / 1024 * account);
+ }
- mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
- THREAD_SIZE / 1024 * account);
+ /* All stack pages belong to the same memcg. */
+ memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
+ } else {
+ /*
+ * All stack pages are in the same zone and belong to the
+ * same memcg.
+ */
+ struct page *first_page = virt_to_page(stack);
- memcg_kmem_update_page_stat(
- first_page, MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
+ mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
+ THREAD_SIZE / 1024 * account);
+
+ memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
+ }
}
void free_task(struct task_struct *tsk)
{
- account_kernel_stack(tsk->stack, -1);
+ account_kernel_stack(tsk, -1);
arch_release_thread_stack(tsk->stack);
- free_thread_stack(tsk->stack);
+ free_thread_stack(tsk);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
{
struct task_struct *tsk;
unsigned long *stack;
+ struct vm_struct *stack_vm_area;
int err;
if (node == NUMA_NO_NODE)
if (!stack)
goto free_tsk;
+ stack_vm_area = task_stack_vm_area(tsk);
+
err = arch_dup_task_struct(tsk, orig);
+
+ /*
+ * arch_dup_task_struct() clobbers the stack-related fields. Make
+ * sure they're properly initialized before using any stack-related
+ * functions again.
+ */
+ tsk->stack = stack;
+#ifdef CONFIG_VMAP_STACK
+ tsk->stack_vm_area = stack_vm_area;
+#endif
+
if (err)
goto free_stack;
- tsk->stack = stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(stack, 1);
+ account_kernel_stack(tsk, 1);
kcov_task_init(tsk);
return tsk;
free_stack:
- free_thread_stack(stack);
+ free_thread_stack(tsk);
free_tsk:
free_task_struct(tsk);
return NULL;
}
EXPORT_SYMBOL(get_mm_exe_file);
+ /**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+ struct file *get_task_exe_file(struct task_struct *task)
+ {
+ struct file *exe_file = NULL;
+ struct mm_struct *mm;
+
+ task_lock(task);
+ mm = task->mm;
+ if (mm) {
+ if (!(task->flags & PF_KTHREAD))
+ exe_file = get_mm_exe_file(mm);
+ }
+ task_unlock(task);
+ return exe_file;
+ }
+ EXPORT_SYMBOL(get_task_exe_file);
+
/**
* get_task_mm - acquire a reference to the task's mm
*
deactivate_mm(tsk, mm);
/*
- * If we're exiting normally, clear a user-space tid field if
- * requested. We leave this alone when dying by signal, to leave
- * the value intact in a core dump, and to save the unnecessary
- * trouble, say, a killed vfork parent shouldn't touch this mm.
- * Userland only wants this done for a sys_exit.
+ * Signal userspace if we're not exiting with a core dump
+ * because we want to leave the value intact for debugging
+ * purposes.
*/
if (tsk->clear_child_tid) {
- if (!(tsk->flags & PF_SIGNALED) &&
+ if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
success = 1; /* we're going to change ->state */
cpu = task_cpu(p);
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * [S] p->on_rq = 1; [L] P->state
+ * UNLOCK rq->lock -----.
+ * \
+ * +--- RMB
+ * schedule() /
+ * LOCK rq->lock -----'
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ *
+ * Pairs with the UNLOCK+LOCK on rq->lock from the
+ * last wakeup of our task and the schedule that got our task
+ * current.
+ */
+ smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
goto stat;
balance_callback(rq);
}
-STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */
static inline void sched_submit_work(struct task_struct *tsk)
{