x86/entry: Remove exception_enter() from most trap handlers

On 64-bit kernels, we don't need it any more: we handle context
tracking directly on entry from user mode and exit to user mode.

On 32-bit kernels, we don't support context tracking at all, so
these callbacks had no effect.

Note: this doesn't change do_page_fault().  Before we do that,
we need to make sure that there is no code that can page fault
from kernel mode with CONTEXT_USER.  The 32-bit fast system call
stack argument code is the only offender I'm aware of right now.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/ae22f4dfebd799c916574089964592be218151f9.1435952415.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Andy Lutomirski 2015-07-03 12:44:32 -07:00 committed by Ingo Molnar
parent 02bc7768fe
commit 8c84014f3b
5 changed files with 27 additions and 69 deletions

View File

@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void);
asmlinkage void smp_deferred_error_interrupt(void);
#endif
extern enum ctx_state ist_enter(struct pt_regs *regs);
extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state);
extern void ist_enter(struct pt_regs *regs);
extern void ist_exit(struct pt_regs *regs);
extern void ist_begin_non_atomic(struct pt_regs *regs);
extern void ist_end_non_atomic(void);

View File

@ -1029,7 +1029,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
{
struct mca_config *cfg = &mca_cfg;
struct mce m, *final;
enum ctx_state prev_state;
int i;
int worst = 0;
int severity;
@ -1055,7 +1054,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
int flags = MF_ACTION_REQUIRED;
int lmce = 0;
prev_state = ist_enter(regs);
ist_enter(regs);
this_cpu_inc(mce_exception_count);
@ -1227,7 +1226,7 @@ out:
local_irq_disable();
ist_end_non_atomic();
done:
ist_exit(regs, prev_state);
ist_exit(regs);
}
EXPORT_SYMBOL_GPL(do_machine_check);

View File

@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly;
/* Machine check handler for Pentium class Intel CPUs: */
static void pentium_machine_check(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
u32 loaddr, hi, lotype;
prev_state = ist_enter(regs);
ist_enter(regs);
rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
ist_exit(regs, prev_state);
ist_exit(regs);
}
/* Set up machine check reporting for processors with Intel style MCE: */

View File

@ -15,12 +15,12 @@
/* Machine check handler for WinChip C6: */
static void winchip_machine_check(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state = ist_enter(regs);
ist_enter(regs);
printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
ist_exit(regs, prev_state);
ist_exit(regs);
}
/* Set up machine check reporting on the Winchip C6 series */

View File

@ -108,13 +108,10 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
preempt_count_dec();
}
enum ctx_state ist_enter(struct pt_regs *regs)
void ist_enter(struct pt_regs *regs)
{
enum ctx_state prev_state;
if (user_mode(regs)) {
/* Other than that, we're just an exception. */
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
} else {
/*
* We might have interrupted pretty much anything. In
@ -123,32 +120,25 @@ enum ctx_state ist_enter(struct pt_regs *regs)
* but we need to notify RCU.
*/
rcu_nmi_enter();
prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */
}
/*
* We are atomic because we're on the IST stack (or we're on x86_32,
* in which case we still shouldn't schedule).
*
* This must be after exception_enter(), because exception_enter()
* won't do anything if in_interrupt() returns true.
* We are atomic because we're on the IST stack; or we're on
* x86_32, in which case we still shouldn't schedule; or we're
* on x86_64 and entered from user mode, in which case we're
* still atomic unless ist_begin_non_atomic is called.
*/
preempt_count_add(HARDIRQ_OFFSET);
/* This code is a bit fragile. Test it. */
rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work");
return prev_state;
}
void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
void ist_exit(struct pt_regs *regs)
{
/* Must be before exception_exit. */
preempt_count_sub(HARDIRQ_OFFSET);
if (user_mode(regs))
return exception_exit(prev_state);
else
if (!user_mode(regs))
rcu_nmi_exit();
}
@ -162,7 +152,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
* a double fault, it can be safe to schedule. ist_begin_non_atomic()
* begins a non-atomic section within an ist_enter()/ist_exit() region.
* Callers are responsible for enabling interrupts themselves inside
* the non-atomic section, and callers must call is_end_non_atomic()
* the non-atomic section, and callers must call ist_end_non_atomic()
* before ist_exit().
*/
void ist_begin_non_atomic(struct pt_regs *regs)
@ -289,7 +279,6 @@ NOKPROBE_SYMBOL(do_trap);
static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
unsigned long trapnr, int signr)
{
enum ctx_state prev_state = exception_enter();
siginfo_t info;
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@ -300,8 +289,6 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
do_trap(trapnr, signr, str, regs, error_code,
fill_trap_info(regs, signr, trapnr, &info));
}
exception_exit(prev_state);
}
#define DO_ERROR(trapnr, signr, str, name) \
@ -353,7 +340,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
}
#endif
ist_enter(regs); /* Discard prev_state because we won't return. */
ist_enter(regs);
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
tsk->thread.error_code = error_code;
@ -373,15 +360,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
const struct bndcsr *bndcsr;
siginfo_t *info;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
if (notify_die(DIE_TRAP, "bounds", regs, error_code,
X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
goto exit;
return;
conditional_sti(regs);
if (!user_mode(regs))
@ -438,9 +423,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
die("bounds", regs, error_code);
}
exit:
exception_exit(prev_state);
return;
exit_trap:
/*
* This path out is for all the cases where we could not
@ -450,36 +434,33 @@ exit_trap:
* time..
*/
do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
exception_exit(prev_state);
}
dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk;
enum ctx_state prev_state;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
conditional_sti(regs);
if (v8086_mode(regs)) {
local_irq_enable();
handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
goto exit;
return;
}
tsk = current;
if (!user_mode(regs)) {
if (fixup_exception(regs))
goto exit;
return;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
die("general protection fault", regs, error_code);
goto exit;
return;
}
tsk->thread.error_code = error_code;
@ -495,16 +476,12 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
exit:
exception_exit(prev_state);
}
NOKPROBE_SYMBOL(do_general_protection);
/* May run on IST stack. */
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
#ifdef CONFIG_DYNAMIC_FTRACE
/*
* ftrace must be first, everything else may cause a recursive crash.
@ -517,7 +494,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
if (poke_int3_handler(regs))
return;
prev_state = ist_enter(regs);
ist_enter(regs);
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@ -544,7 +521,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
preempt_conditional_cli(regs);
debug_stack_usage_dec();
exit:
ist_exit(regs, prev_state);
ist_exit(regs);
}
NOKPROBE_SYMBOL(do_int3);
@ -620,12 +597,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret);
dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
enum ctx_state prev_state;
int user_icebp = 0;
unsigned long dr6;
int si_code;
prev_state = ist_enter(regs);
ist_enter(regs);
get_debugreg(dr6, 6);
@ -700,7 +676,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
debug_stack_usage_dec();
exit:
ist_exit(regs, prev_state);
ist_exit(regs);
}
NOKPROBE_SYMBOL(do_debug);
@ -752,23 +728,15 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
math_error(regs, error_code, X86_TRAP_MF);
exception_exit(prev_state);
}
dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
math_error(regs, error_code, X86_TRAP_XF);
exception_exit(prev_state);
}
dotraplinkage void
@ -780,9 +748,6 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
enum ctx_state prev_state;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
BUG_ON(use_eager_fpu());
@ -794,7 +759,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
info.regs = regs;
math_emulate(&info);
exception_exit(prev_state);
return;
}
#endif
@ -802,7 +766,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
#ifdef CONFIG_X86_32
conditional_sti(regs);
#endif
exception_exit(prev_state);
}
NOKPROBE_SYMBOL(do_device_not_available);
@ -810,9 +773,7 @@ NOKPROBE_SYMBOL(do_device_not_available);
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
siginfo_t info;
enum ctx_state prev_state;
prev_state = exception_enter();
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
local_irq_enable();
@ -825,7 +786,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
&info);
}
exception_exit(prev_state);
}
#endif