#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
+#include <linux/entry-common.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/audit.h>
-#include <linux/seccomp.h>
#include <linux/signal.h>
#include <linux/export.h>
#include <linux/context_tracking.h>
#include <asm/syscall.h>
#include <asm/irq_stack.h>
-#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
-/* Check that the stack and regs on entry from user mode are sane. */
-static noinstr void check_user_regs(struct pt_regs *regs)
-{
- if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
- /*
- * Make sure that the entry code gave us a sensible EFLAGS
- * register. Native because we want to check the actual CPU
- * state, not the interrupt state as imagined by Xen.
- */
- unsigned long flags = native_save_fl();
- WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
- X86_EFLAGS_NT));
-
- /* We think we came from user mode. Make sure pt_regs agrees. */
- WARN_ON_ONCE(!user_mode(regs));
-
- /*
- * All entries from user mode (except #DF) should be on the
- * normal thread stack and should have user pt_regs in the
- * correct location.
- */
- WARN_ON_ONCE(!on_thread_stack());
- WARN_ON_ONCE(regs != task_pt_regs(current));
- }
-}
-
-#ifdef CONFIG_CONTEXT_TRACKING
-/**
- * enter_from_user_mode - Establish state when coming from user mode
- *
- * Syscall entry disables interrupts, but user mode is traced as interrupts
- * enabled. Also with NO_HZ_FULL RCU might be idle.
- *
- * 1) Tell lockdep that interrupts are disabled
- * 2) Invoke context tracking if enabled to reactivate RCU
- * 3) Trace interrupts off state
- */
-static noinstr void enter_from_user_mode(struct pt_regs *regs)
-{
- enum ctx_state state = ct_state();
-
- check_user_regs(regs);
- lockdep_hardirqs_off(CALLER_ADDR0);
- user_exit_irqoff();
-
- instrumentation_begin();
- CT_WARN_ON(state != CONTEXT_USER);
- trace_hardirqs_off_finish();
- instrumentation_end();
-}
-#else
-static __always_inline void enter_from_user_mode(struct pt_regs *regs)
-{
- check_user_regs(regs);
- lockdep_hardirqs_off(CALLER_ADDR0);
- instrumentation_begin();
- trace_hardirqs_off_finish();
- instrumentation_end();
-}
-#endif
-
/**
* exit_to_user_mode - Fixup state when exiting to user mode
*
lockdep_hardirqs_on(CALLER_ADDR0);
}
-static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
-{
-#ifdef CONFIG_X86_64
- if (arch == AUDIT_ARCH_X86_64) {
- audit_syscall_entry(regs->orig_ax, regs->di,
- regs->si, regs->dx, regs->r10);
- } else
-#endif
- {
- audit_syscall_entry(regs->orig_ax, regs->bx,
- regs->cx, regs->dx, regs->si);
- }
-}
-
-/*
- * Returns the syscall nr to run (which should match regs->orig_ax) or -1
- * to skip the syscall.
- */
-static long syscall_trace_enter(struct pt_regs *regs)
-{
- u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
-
- struct thread_info *ti = current_thread_info();
- unsigned long ret = 0;
- u32 work;
-
- work = READ_ONCE(ti->flags);
-
- if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
- ret = tracehook_report_syscall_entry(regs);
- if (ret || (work & _TIF_SYSCALL_EMU))
- return -1L;
- }
-
-#ifdef CONFIG_SECCOMP
- /*
- * Do seccomp after ptrace, to catch any tracer changes.
- */
- if (work & _TIF_SECCOMP) {
- struct seccomp_data sd;
-
- sd.arch = arch;
- sd.nr = regs->orig_ax;
- sd.instruction_pointer = regs->ip;
-#ifdef CONFIG_X86_64
- if (arch == AUDIT_ARCH_X86_64) {
- sd.args[0] = regs->di;
- sd.args[1] = regs->si;
- sd.args[2] = regs->dx;
- sd.args[3] = regs->r10;
- sd.args[4] = regs->r8;
- sd.args[5] = regs->r9;
- } else
-#endif
- {
- sd.args[0] = regs->bx;
- sd.args[1] = regs->cx;
- sd.args[2] = regs->dx;
- sd.args[3] = regs->si;
- sd.args[4] = regs->di;
- sd.args[5] = regs->bp;
- }
-
- ret = __secure_computing(&sd);
- if (ret == -1)
- return ret;
- }
-#endif
-
- if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_enter(regs, regs->orig_ax);
-
- do_audit_syscall_entry(regs, arch);
-
- return ret ?: regs->orig_ax;
-}
-
#define EXIT_TO_USERMODE_LOOP_FLAGS \
(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
_TIF_NEED_RESCHED | _TIF_PATCH_PENDING)
exit_to_user_mode();
}
-static noinstr long syscall_enter(struct pt_regs *regs, unsigned long nr)
-{
- struct thread_info *ti;
-
- enter_from_user_mode(regs);
- instrumentation_begin();
-
- local_irq_enable();
- ti = current_thread_info();
- if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
- nr = syscall_trace_enter(regs);
-
- instrumentation_end();
- return nr;
-}
-
#ifdef CONFIG_X86_64
__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
- nr = syscall_enter(regs, nr);
+ nr = syscall_enter_from_user_mode(regs, nr);
instrumentation_begin();
if (likely(nr < NR_syscalls)) {
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
{
+ unsigned int nr = (unsigned int)regs->orig_ax;
+
if (IS_ENABLED(CONFIG_IA32_EMULATION))
current_thread_info()->status |= TS_COMPAT;
/*
* orig_ax, the unsigned int return value truncates it. This may
* or may not be necessary, but it matches the old asm behavior.
*/
- return syscall_enter(regs, (unsigned int)regs->orig_ax);
+ return (unsigned int)syscall_enter_from_user_mode(regs, nr);
}
/*
* solves the problem of kernel mode pagefaults which can schedule, which
* is not possible after invoking rcu_irq_enter() without undoing it.
*
- * For user mode entries enter_from_user_mode() must be invoked to
+ * For user mode entries irqentry_enter_from_user_mode() must be invoked to
* establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
* would not be possible.
*
};
if (user_mode(regs)) {
- enter_from_user_mode(regs);
+ irqentry_enter_from_user_mode(regs);
return ret;
}
/*
* If RCU is not watching then the same careful
* sequence vs. lockdep and tracing is required
- * as in enter_from_user_mode().
+ * as in irqentry_enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
rcu_irq_enter();
}
}
-/**
- * idtentry_enter_user - Handle state tracking on idtentry from user mode
- * @regs: Pointer to pt_regs of interrupted context
- *
- * Invokes enter_from_user_mode() to establish the proper context for
- * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
- */
-void noinstr idtentry_enter_user(struct pt_regs *regs)
-{
- enter_from_user_mode(regs);
-}
-
/**
* idtentry_exit_user - Handle return from exception to user mode
* @regs: Pointer to pt_regs (exception entry regs)
projects / linux-2.6-microblaze.git / commitdiff