[tip: core/entry] x86/entry: Move nmi entry/exit into common code

From: tip-bot2 for Thomas Gleixner
Date: Wed Nov 04 2020 - 17:06:53 EST


The following commit has been merged into the core/entry branch of tip:

Commit-ID: b6be002bcd1dd1dedb926abf3c90c794eacb77dc
Gitweb: https://git.kernel.org/tip/b6be002bcd1dd1dedb926abf3c90c794eacb77dc
Author: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
AuthorDate: Mon, 02 Nov 2020 12:53:16 -08:00
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitterDate: Wed, 04 Nov 2020 22:55:36 +01:00

x86/entry: Move nmi entry/exit into common code

Lockdep state handling on NMI enter and exit is nothing specific to X86. It's
not any different on other architectures. Also the extra state type is not
necessary, irqentry_state_t can carry the necessary information as well.

Move it to common code and extend irqentry_state_t to carry lockdep state.

[ Ira: Make exit_rcu and lockdep a union as they are mutually exclusive
between the IRQ and NMI exceptions, and add kernel documentation for
struct irqentry_state_t ]

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20201102205320.1458656-7-ira.weiny@xxxxxxxxx
---
arch/x86/entry/common.c | 34 +----------------------------
arch/x86/include/asm/idtentry.h | 3 +--
arch/x86/kernel/cpu/mce/core.c | 6 ++---
arch/x86/kernel/nmi.c | 6 ++---
arch/x86/kernel/traps.c | 13 +++++------
include/linux/entry-common.h | 39 +++++++++++++++++++++++++++++++-
kernel/entry/common.c | 36 ++++++++++++++++++++++++++++++-
7 files changed, 87 insertions(+), 50 deletions(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 870efee..18d8f17 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -209,40 +209,6 @@ SYSCALL_DEFINE0(ni_syscall)
return -ENOSYS;
}

-noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
-{
- bool irq_state = lockdep_hardirqs_enabled();
-
- __nmi_enter();
- lockdep_hardirqs_off(CALLER_ADDR0);
- lockdep_hardirq_enter();
- rcu_nmi_enter();
-
- instrumentation_begin();
- trace_hardirqs_off_finish();
- ftrace_nmi_enter();
- instrumentation_end();
-
- return irq_state;
-}
-
-noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
-{
- instrumentation_begin();
- ftrace_nmi_exit();
- if (restore) {
- trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
- }
- instrumentation_end();
-
- rcu_nmi_exit();
- lockdep_hardirq_exit();
- if (restore)
- lockdep_hardirqs_on(CALLER_ADDR0);
- __nmi_exit();
-}
-
#ifdef CONFIG_XEN_PV
#ifndef CONFIG_PREEMPTION
/*
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index b2442eb..247a60a 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -11,9 +11,6 @@

#include <asm/irq_stack.h>

-bool idtentry_enter_nmi(struct pt_regs *regs);
-void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
-
/**
* DECLARE_IDTENTRY - Declare functions for simple IDT entry points
* No error code pushed by hardware
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4102b86..f5c860b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1983,7 +1983,7 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;

static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
{
- bool irq_state;
+ irqentry_state_t irq_state;

WARN_ON_ONCE(user_mode(regs));

@@ -1995,7 +1995,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
mce_check_crashing_cpu())
return;

- irq_state = idtentry_enter_nmi(regs);
+ irq_state = irqentry_nmi_enter(regs);
/*
* The call targets are marked noinstr, but objtool can't figure
* that out because it's an indirect call. Annotate it.
@@ -2006,7 +2006,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
if (regs->flags & X86_EFLAGS_IF)
trace_hardirqs_on_prepare();
instrumentation_end();
- idtentry_exit_nmi(regs, irq_state);
+ irqentry_nmi_exit(regs, irq_state);
}

static __always_inline void exc_machine_check_user(struct pt_regs *regs)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4bc77aa..bf250a3 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -475,7 +475,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);

DEFINE_IDTENTRY_RAW(exc_nmi)
{
- bool irq_state;
+ irqentry_state_t irq_state;

/*
* Re-enable NMIs right here when running as an SEV-ES guest. This might
@@ -502,14 +502,14 @@ nmi_restart:

this_cpu_write(nmi_dr7, local_db_save());

- irq_state = idtentry_enter_nmi(regs);
+ irq_state = irqentry_nmi_enter(regs);

inc_irq_stat(__nmi_count);

if (!ignore_nmis)
default_do_nmi(regs);

- idtentry_exit_nmi(regs, irq_state);
+ irqentry_nmi_exit(regs, irq_state);

local_db_restore(this_cpu_read(nmi_dr7));

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e19df6c..e1b7882 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -405,7 +405,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
}
#endif

- idtentry_enter_nmi(regs);
+ irqentry_nmi_enter(regs);
instrumentation_begin();
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);

@@ -651,12 +651,13 @@ DEFINE_IDTENTRY_RAW(exc_int3)
instrumentation_end();
irqentry_exit_to_user_mode(regs);
} else {
- bool irq_state = idtentry_enter_nmi(regs);
+ irqentry_state_t irq_state = irqentry_nmi_enter(regs);
+
instrumentation_begin();
if (!do_int3(regs))
die("int3", regs, 0);
instrumentation_end();
- idtentry_exit_nmi(regs, irq_state);
+ irqentry_nmi_exit(regs, irq_state);
}
}

@@ -851,7 +852,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
* includes the entry stack is excluded for everything.
*/
unsigned long dr7 = local_db_save();
- bool irq_state = idtentry_enter_nmi(regs);
+ irqentry_state_t irq_state = irqentry_nmi_enter(regs);
instrumentation_begin();

/*
@@ -908,7 +909,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
regs->flags &= ~X86_EFLAGS_TF;
out:
instrumentation_end();
- idtentry_exit_nmi(regs, irq_state);
+ irqentry_nmi_exit(regs, irq_state);

local_db_restore(dr7);
}
@@ -926,7 +927,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,

/*
* NB: We can't easily clear DR7 here because
- * idtentry_exit_to_usermode() can invoke ptrace, schedule, access
+ * irqentry_exit_to_usermode() can invoke ptrace, schedule, access
* user memory, etc. This means that a recursive #DB is possible. If
* this happens, that #DB will hit exc_debug_kernel() and clear DR7.
* Since we're not on the IST stack right now, everything will be
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index b9711e8..1a128ba 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -346,8 +346,26 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs);
void irqentry_exit_to_user_mode(struct pt_regs *regs);

#ifndef irqentry_state
+/**
+ * struct irqentry_state - Opaque object for exception state storage
+ * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
+ * exit path has to invoke rcu_irq_exit().
+ * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
+ * lockdep state is restored correctly on exit from nmi.
+ *
+ * This opaque object is filled in by the irqentry_*_enter() functions and
+ * must be passed back into the corresponding irqentry_*_exit() functions
+ * when the exception is complete.
+ *
+ * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
+ * and all members private. Descriptions of the members are provided to aid in
+ * the maintenance of the irqentry_*() functions.
+ */
typedef struct irqentry_state {
- bool exit_rcu;
+ union {
+ bool exit_rcu;
+ bool lockdep;
+ };
} irqentry_state_t;
#endif

@@ -407,4 +425,23 @@ void irqentry_exit_cond_resched(void);
*/
void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);

+/**
+ * irqentry_nmi_enter - Handle NMI entry
+ * @regs: Pointer to currents pt_regs
+ *
+ * Similar to irqentry_enter() but taking care of the NMI constraints.
+ */
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_nmi_exit - Handle return from NMI handling
+ * @regs: Pointer to pt_regs (NMI entry regs)
+ * @irq_state: Return value from matching call to irqentry_nmi_enter()
+ *
+ * Last action before returning to the low level assmenbly code.
+ *
+ * Counterpart to irqentry_nmi_enter().
+ */
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+
#endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 3a1dfec..bc75c11 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -405,3 +405,39 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
rcu_irq_exit();
}
}
+
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
+{
+ irqentry_state_t irq_state;
+
+ irq_state.lockdep = lockdep_hardirqs_enabled();
+
+ __nmi_enter();
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ lockdep_hardirq_enter();
+ rcu_nmi_enter();
+
+ instrumentation_begin();
+ trace_hardirqs_off_finish();
+ ftrace_nmi_enter();
+ instrumentation_end();
+
+ return irq_state;
+}
+
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
+{
+ instrumentation_begin();
+ ftrace_nmi_exit();
+ if (irq_state.lockdep) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ }
+ instrumentation_end();
+
+ rcu_nmi_exit();
+ lockdep_hardirq_exit();
+ if (irq_state.lockdep)
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ __nmi_exit();
+}