* This file handles the architecture-dependent parts of process handling..
*/
-#include <stdarg.h>
-
+#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/interrupt.h>
-#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
-#include <linux/random.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
+#include <linux/ftrace.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
-#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
+#include <asm/ds.h>
+#include <asm/debugreg.h>
asmlinkage extern void ret_from_fork(void);
-unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
+DEFINE_PER_CPU(unsigned long, old_rsp);
+static DEFINE_PER_CPU(unsigned char, is_idle);
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
{
atomic_notifier_chain_register(&idle_notifier, n);
}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
void enter_idle(void)
{
- write_pda(isidle, 1);
+ percpu_write(is_idle, 1);
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
static void __exit_idle(void)
{
- if (test_and_clear_bit_pda(0, isidle) == 0)
+ if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
return;
atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}
void cpu_idle(void)
{
current_thread_info()->status |= TS_POLLING;
+
+ /*
+ * If we're the non-boot CPU, nothing set the stack canary up
+ * for us. CPU0 already has it initialized but no harm in
+ * doing it again. This is a good place for updating it, as
+ * we wont ever return from this function (so the invalid
+ * canaries already on the stack wont ever trigger).
+ */
+ boot_init_stack_canary();
+
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick(1);
}
/* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs *regs)
+void __show_regs(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned int fsindex, gsindex;
unsigned int ds, cs, es;
- printk("\n");
- print_modules();
- printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n",
- current->pid, current->comm, print_tainted(),
- init_utsname()->release,
- (int)strcspn(init_utsname()->version, " "),
- init_utsname()->version);
- printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
+ show_regs_common();
+ printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
printk_address(regs->ip, 1);
- printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss,
+ printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss,
regs->sp, regs->flags);
- printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
+ printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
regs->ax, regs->bx, regs->cx);
- printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
+ printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",
regs->dx, regs->si, regs->di);
- printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
+ printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n",
regs->bp, regs->r8, regs->r9);
- printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
+ printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n",
regs->r10, regs->r11, regs->r12);
- printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
+ printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
regs->r13, regs->r14, regs->r15);
asm("movl %%ds,%0" : "=r" (ds));
rdmsrl(MSR_GS_BASE, gs);
rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+ if (!all)
+ return;
+
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
cr4 = read_cr4();
- printk(KERN_INFO "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+ printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
fs, fsindex, gs, gsindex, shadowgs);
- printk(KERN_INFO "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+ printk(KERN_DEFAULT "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
es, cr0);
- printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
+ printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
cr4);
get_debugreg(d0, 0);
get_debugreg(d1, 1);
get_debugreg(d2, 2);
- printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+ printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
get_debugreg(d3, 3);
get_debugreg(d6, 6);
get_debugreg(d7, 7);
- printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
-}
-
-void show_regs(struct pt_regs *regs)
-{
- printk(KERN_INFO "CPU %d:", smp_processor_id());
- __show_regs(regs);
- show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
-}
-
-/*
- * Free current thread data structures etc..
- */
-void exit_thread(void)
-{
- struct task_struct *me = current;
- struct thread_struct *t = &me->thread;
-
- if (me->thread.io_bitmap_ptr) {
- struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
-
- kfree(t->io_bitmap_ptr);
- t->io_bitmap_ptr = NULL;
- clear_thread_flag(TIF_IO_BITMAP);
- /*
- * Careful, clear this in the TSS too:
- */
- memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
- t->io_bitmap_max = 0;
- put_cpu();
- }
-#ifdef CONFIG_X86_DS
- /* Free any DS contexts that have not been properly released. */
- if (unlikely(t->ds_ctx)) {
- /* we clear debugctl to make sure DS is not used. */
- update_debugctlmsr(0);
- ds_free(t->ds_ctx);
- }
-#endif /* CONFIG_X86_DS */
-}
-
-void flush_thread(void)
-{
- struct task_struct *tsk = current;
-
- if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
- clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
- if (test_tsk_thread_flag(tsk, TIF_IA32)) {
- clear_tsk_thread_flag(tsk, TIF_IA32);
- } else {
- set_tsk_thread_flag(tsk, TIF_IA32);
- current_thread_info()->status |= TS_COMPAT;
- }
- }
- clear_tsk_thread_flag(tsk, TIF_DEBUG);
-
- tsk->thread.debugreg0 = 0;
- tsk->thread.debugreg1 = 0;
- tsk->thread.debugreg2 = 0;
- tsk->thread.debugreg3 = 0;
- tsk->thread.debugreg6 = 0;
- tsk->thread.debugreg7 = 0;
- memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- /*
- * Forget coprocessor state..
- */
- tsk->fpu_counter = 0;
- clear_fpu(tsk);
- clear_used_math();
+ printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}
void release_thread(struct task_struct *dead_task)
unlazy_fpu(tsk);
}
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long unused,
struct task_struct *p, struct pt_regs *regs)
{
*childregs = *regs;
childregs->ax = 0;
- childregs->sp = sp;
- if (sp == ~0UL)
+ if (user_mode(regs))
+ childregs->sp = sp;
+ else
childregs->sp = (unsigned long)childregs;
p->thread.sp = (unsigned long) childregs;
p->thread.fs = me->thread.fs;
p->thread.gs = me->thread.gs;
+ p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
savesegment(fs, p->thread.fsindex);
savesegment(es, p->thread.es);
savesegment(ds, p->thread.ds);
+ err = -ENOMEM;
+ memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
if (!p->thread.io_bitmap_ptr) {
if (err)
goto out;
}
+
+ clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+ p->thread.ds_ctx = NULL;
+
+ clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
+ p->thread.debugctlmsr = 0;
+
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
+
return err;
}
-void
-start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
+static void
+start_thread_common(struct pt_regs *regs, unsigned long new_ip,
+ unsigned long new_sp,
+ unsigned int _cs, unsigned int _ss, unsigned int _ds)
{
loadsegment(fs, 0);
- loadsegment(es, 0);
- loadsegment(ds, 0);
+ loadsegment(es, _ds);
+ loadsegment(ds, _ds);
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
- write_pda(oldrsp, new_sp);
- regs->cs = __USER_CS;
- regs->ss = __USER_DS;
- regs->flags = 0x200;
+ percpu_write(old_rsp, new_sp);
+ regs->cs = _cs;
+ regs->ss = _ss;
+ regs->flags = X86_EFLAGS_IF;
set_fs(USER_DS);
/*
* Free the old FP and other extended state
*/
free_thread_xstate(current);
}
-EXPORT_SYMBOL_GPL(start_thread);
-
-static void hard_disable_TSC(void)
-{
- write_cr4(read_cr4() | X86_CR4_TSD);
-}
-void disable_TSC(void)
-{
- preempt_disable();
- if (!test_and_set_thread_flag(TIF_NOTSC))
- /*
- * Must flip the CPU state synchronously with
- * TIF_NOTSC in the current running context.
- */
- hard_disable_TSC();
- preempt_enable();
-}
-
-static void hard_enable_TSC(void)
-{
- write_cr4(read_cr4() & ~X86_CR4_TSD);
-}
-
-static void enable_TSC(void)
-{
- preempt_disable();
- if (test_and_clear_thread_flag(TIF_NOTSC))
- /*
- * Must flip the CPU state synchronously with
- * TIF_NOTSC in the current running context.
- */
- hard_enable_TSC();
- preempt_enable();
-}
-
-int get_tsc_mode(unsigned long adr)
-{
- unsigned int val;
-
- if (test_thread_flag(TIF_NOTSC))
- val = PR_TSC_SIGSEGV;
- else
- val = PR_TSC_ENABLE;
-
- return put_user(val, (unsigned int __user *)adr);
-}
-
-int set_tsc_mode(unsigned int val)
+void
+start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
- if (val == PR_TSC_SIGSEGV)
- disable_TSC();
- else if (val == PR_TSC_ENABLE)
- enable_TSC();
- else
- return -EINVAL;
-
- return 0;
+ start_thread_common(regs, new_ip, new_sp,
+ __USER_CS, __USER_DS, 0);
}
-/*
- * This special macro can be used to load a debugging register
- */
-#define loaddebug(thread, r) set_debugreg(thread->debugreg ## r, r)
-
-static inline void __switch_to_xtra(struct task_struct *prev_p,
- struct task_struct *next_p,
- struct tss_struct *tss)
+#ifdef CONFIG_IA32_EMULATION
+void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
- struct thread_struct *prev, *next;
- unsigned long debugctl;
-
- prev = &prev_p->thread,
- next = &next_p->thread;
-
- debugctl = prev->debugctlmsr;
-
-#ifdef CONFIG_X86_DS
- {
- unsigned long ds_prev = 0, ds_next = 0;
-
- if (prev->ds_ctx)
- ds_prev = (unsigned long)prev->ds_ctx->ds;
- if (next->ds_ctx)
- ds_next = (unsigned long)next->ds_ctx->ds;
-
- if (ds_next != ds_prev) {
- /*
- * We clear debugctl to make sure DS
- * is not in use when we change it:
- */
- debugctl = 0;
- update_debugctlmsr(0);
- wrmsrl(MSR_IA32_DS_AREA, ds_next);
- }
- }
-#endif /* CONFIG_X86_DS */
-
- if (next->debugctlmsr != debugctl)
- update_debugctlmsr(next->debugctlmsr);
-
- if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
- loaddebug(next, 0);
- loaddebug(next, 1);
- loaddebug(next, 2);
- loaddebug(next, 3);
- /* no 4 and 5 */
- loaddebug(next, 6);
- loaddebug(next, 7);
- }
-
- if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
- test_tsk_thread_flag(next_p, TIF_NOTSC)) {
- /* prev and next are different */
- if (test_tsk_thread_flag(next_p, TIF_NOTSC))
- hard_disable_TSC();
- else
- hard_enable_TSC();
- }
-
- if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
- /*
- * Copy the relevant range of the IO bitmap.
- * Normally this is 128 bytes or less:
- */
- memcpy(tss->io_bitmap, next->io_bitmap_ptr,
- max(prev->io_bitmap_max, next->io_bitmap_max));
- } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
- /*
- * Clear any possible leftover bits:
- */
- memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
- }
-
-#ifdef CONFIG_X86_PTRACE_BTS
- if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
- ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
-
- if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
- ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif /* CONFIG_X86_PTRACE_BTS */
+ start_thread_common(regs, new_ip, new_sp,
+ __USER32_CS, __USER32_DS, __USER32_DS);
}
+#endif
/*
* switch_to(x,y) should switch tasks from x to y.
* - could test fs/gs bitsliced
*
* Kprobes not supported here. Set the probe on schedule instead.
+ * Function graph tracer not supported too.
*/
-struct task_struct *
+__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
unsigned fsindex, gsindex;
+ bool preload_fpu;
+
+ /*
+ * If the task has used fpu the last 5 timeslices, just do a full
+ * restore of the math state immediately to avoid the trap; the
+ * chances of needing FPU soon are obviously high now
+ */
+ preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
/* we're going to use this soon, after a few expensive things */
- if (next_p->fpu_counter > 5)
+ if (preload_fpu)
prefetch(next->xstate);
/*
load_TLS(next, cpu);
+ /* Must be after DS reload */
+ unlazy_fpu(prev_p);
+
+ /* Make sure cpu is ready for new context */
+ if (preload_fpu)
+ clts();
+
/*
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* done before math_state_restore, so the TS bit is up
* to date.
*/
- arch_leave_lazy_cpu_mode();
+ arch_end_context_switch(next_p);
/*
* Switch FS and GS.
wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
prev->gsindex = gsindex;
- /* Must be after DS reload */
- unlazy_fpu(prev_p);
-
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = read_pda(oldrsp);
- write_pda(oldrsp, next->usersp);
- write_pda(pcurrent, next_p);
+ prev->usersp = percpu_read(old_rsp);
+ percpu_write(old_rsp, next->usersp);
+ percpu_write(current_task, next_p);
- write_pda(kernelstack,
+ percpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - PDA_STACKOFFSET);
-#ifdef CONFIG_CC_STACKPROTECTOR
- write_pda(stack_canary, next_p->stack_canary);
- /*
- * Build time only check to make sure the stack_canary is at
- * offset 40 in the pda; this is a gcc ABI requirement
- */
- BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
-#endif
+ THREAD_SIZE - KERNEL_STACK_OFFSET);
/*
* Now maybe reload the debug registers and handle I/O bitmaps
task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
__switch_to_xtra(prev_p, next_p, tss);
- /* If the task has used fpu the last 5 timeslices, just do a full
- * restore of the math state immediately to avoid the trap; the
- * chances of needing FPU soon are obviously high now
- *
- * tsk_used_math() checks prevent calling math_state_restore(),
- * which can sleep in the case of !tsk_used_math()
+ /*
+ * Preload the FPU context, now that we've determined that the
+ * task is likely to be using it.
*/
- if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
- math_state_restore();
- return prev_p;
-}
+ if (preload_fpu)
+ __math_state_restore();
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage
-long sys_execve(char __user *name, char __user * __user *argv,
- char __user * __user *envp, struct pt_regs *regs)
-{
- long error;
- char *filename;
-
- filename = getname(name);
- error = PTR_ERR(filename);
- if (IS_ERR(filename))
- return error;
- error = do_execve(filename, argv, envp, regs);
- putname(filename);
- return error;
+ return prev_p;
}
void set_personality_64bit(void)
current->personality &= ~READ_IMPLIES_EXEC;
}
-asmlinkage long sys_fork(struct pt_regs *regs)
+void set_personality_ia32(void)
{
- return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL);
-}
+ /* inherit personality from parent */
-asmlinkage long
-sys_clone(unsigned long clone_flags, unsigned long newsp,
- void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
-{
- if (!newsp)
- newsp = regs->sp;
- return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
-}
+ /* Make sure to be in 32bit mode */
+ set_thread_flag(TIF_IA32);
+ current->personality |= force_personality32;
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage long sys_vfork(struct pt_regs *regs)
-{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0,
- NULL, NULL);
+ /* Prepare the first "return" to user space */
+ current_thread_info()->status |= TS_COMPAT;
}
unsigned long get_wchan(struct task_struct *p)
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
stack = (unsigned long)task_stack_page(p);
- if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE)
+ if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
return 0;
fp = *(u64 *)(p->thread.sp);
do {
if (fp < (unsigned long)stack ||
- fp > (unsigned long)stack+THREAD_SIZE)
+ fp >= (unsigned long)stack+THREAD_SIZE)
return 0;
ip = *(u64 *)(fp+8);
if (!in_sched_functions(ip))
return do_arch_prctl(current, code, addr);
}
-unsigned long arch_align_stack(unsigned long sp)
-{
- if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
- sp -= get_random_int() % 8192;
- return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
+unsigned long KSTK_ESP(struct task_struct *task)
{
- unsigned long range_end = mm->brk + 0x02000000;
- return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+ return (test_tsk_thread_flag(task, TIF_IA32)) ?
+ (task_pt_regs(task)->sp) : ((task)->thread.usersp);
}