linux/arch/arm64/include/asm/exception.h
Mark Rutland 23529049c6 arm64: entry: fix non-NMI user<->kernel transitions
When built with PROVE_LOCKING, NO_HZ_FULL, and CONTEXT_TRACKING_FORCE
will WARN() at boot time that interrupts are enabled when we call
context_tracking_user_enter(), despite the DAIF flags indicating that
IRQs are masked.

The problem is that we're not tracking IRQ flag changes accurately, and
so lockdep believes interrupts are enabled when they are not (and
vice-versa). We can shuffle things so to make this more accurate. For
kernel->user transitions there are a number of constraints we need to
consider:

1) When we call __context_tracking_user_enter() HW IRQs must be disabled
   and lockdep must be up-to-date with this.

2) Userspace should be treated as having IRQs enabled from the PoV of
   both lockdep and tracing.

3) As context_tracking_user_enter() stops RCU from watching, we cannot
   use RCU after calling it.

4) IRQ flag tracing and lockdep have state that must be manipulated
   before RCU is disabled.

... with similar constraints applying for user->kernel transitions, with
the ordering reversed.

The generic entry code has enter_from_user_mode() and
exit_to_user_mode() helpers to handle this. We can't use those directly,
so we add arm64 copies for now (without the instrumentation markers
which aren't used on arm64). These replace the existing user_exit() and
user_exit_irqoff() calls spread throughout handlers, and the exception
unmasking is left as-is.

Note that:

* The accounting for debug exceptions from userspace now happens in
  el0_dbg() and ret_to_user(), so this is removed from
  debug_exception_enter() and debug_exception_exit(). As
  user_exit_irqoff() wakes RCU, the userspace-specific check is removed.

* The accounting for syscalls now happens in el0_svc(),
  el0_svc_compat(), and ret_to_user(), so this is removed from
  el0_svc_common(). This does not adversely affect the workaround for
  erratum 1463225, as this does not depend on any of the state tracking.

* In ret_to_user() we mask interrupts with local_daif_mask(), and so we
  need to inform lockdep and tracing. Here a trace_hardirqs_off() is
  sufficient and safe as we have not yet exited kernel context and RCU
  is usable.

* As PROVE_LOCKING selects TRACE_IRQFLAGS, the ifdeferry in entry.S only
  needs to check for the latter.

* EL0 SError handling will be dealt with in a subsequent patch, as this
  needs to be treated as an NMI.

Prior to this patch, booting an appropriately-configured kernel would
result in spats as below:

| DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())
| WARNING: CPU: 2 PID: 1 at kernel/locking/lockdep.c:5280 check_flags.part.54+0x1dc/0x1f0
| Modules linked in:
| CPU: 2 PID: 1 Comm: init Not tainted 5.10.0-rc3 #3
| Hardware name: linux,dummy-virt (DT)
| pstate: 804003c5 (Nzcv DAIF +PAN -UAO -TCO BTYPE=--)
| pc : check_flags.part.54+0x1dc/0x1f0
| lr : check_flags.part.54+0x1dc/0x1f0
| sp : ffff80001003bd80
| x29: ffff80001003bd80 x28: ffff66ce801e0000
| x27: 00000000ffffffff x26: 00000000000003c0
| x25: 0000000000000000 x24: ffffc31842527258
| x23: ffffc31842491368 x22: ffffc3184282d000
| x21: 0000000000000000 x20: 0000000000000001
| x19: ffffc318432ce000 x18: 0080000000000000
| x17: 0000000000000000 x16: ffffc31840f18a78
| x15: 0000000000000001 x14: ffffc3184285c810
| x13: 0000000000000001 x12: 0000000000000000
| x11: ffffc318415857a0 x10: ffffc318406614c0
| x9 : ffffc318415857a0 x8 : ffffc31841f1d000
| x7 : 647261685f706564 x6 : ffffc3183ff7c66c
| x5 : ffff66ce801e0000 x4 : 0000000000000000
| x3 : ffffc3183fe00000 x2 : ffffc31841500000
| x1 : e956dc24146b3500 x0 : 0000000000000000
| Call trace:
|  check_flags.part.54+0x1dc/0x1f0
|  lock_is_held_type+0x10c/0x188
|  rcu_read_lock_sched_held+0x70/0x98
|  __context_tracking_enter+0x310/0x350
|  context_tracking_enter.part.3+0x5c/0xc8
|  context_tracking_user_enter+0x6c/0x80
|  finish_ret_to_user+0x2c/0x13cr

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20201130115950.22492-8-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
2020-11-30 12:11:38 +00:00

55 lines
1.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/exception.h
*
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_EXCEPTION_H
#define __ASM_EXCEPTION_H
#include <asm/esr.h>
#include <asm/kprobes.h>
#include <asm/ptrace.h>
#include <linux/interrupt.h>
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#define __exception_irq_entry __irq_entry
#else
#define __exception_irq_entry __kprobes
#endif
static inline u32 disr_to_esr(u64 disr)
{
unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
if ((disr & DISR_EL1_IDS) == 0)
esr |= (disr & DISR_EL1_ESR_MASK);
else
esr |= (disr & ESR_ELx_ISS_MASK);
return esr;
}
asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs);
asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs);
asmlinkage void enter_from_user_mode(void);
asmlinkage void exit_to_user_mode(void);
void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
void do_undefinstr(struct pt_regs *regs);
void do_bti(struct pt_regs *regs);
asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
struct pt_regs *regs);
void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
void do_sve_acc(unsigned int esr, struct pt_regs *regs);
void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
void do_sysinstr(unsigned int esr, struct pt_regs *regs);
void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
void do_cp15instr(unsigned int esr, struct pt_regs *regs);
void do_el0_svc(struct pt_regs *regs);
void do_el0_svc_compat(struct pt_regs *regs);
void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr);
#endif /* __ASM_EXCEPTION_H */