linux/kernel/context_tracking.c

313 lines
8.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Context tracking: Probe on high level context boundaries such as kernel
* and userspace. This includes syscalls and exceptions entry/exit.
*
* This is used by RCU to remove its dependency on the timer tick while a CPU
* runs in userspace.
*
* Started by Frederic Weisbecker:
*
* Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
*
* Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton,
* Steven Rostedt, Peter Zijlstra for suggestions and improvements.
*
*/
#include <linux/context_tracking.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/export.h>
#include <linux/kprobes.h>
#ifdef CONFIG_CONTEXT_TRACKING_IDLE
noinstr void ct_idle_enter(void)
{
rcu_idle_enter();
}
EXPORT_SYMBOL_GPL(ct_idle_enter);
void ct_idle_exit(void)
{
rcu_idle_exit();
}
EXPORT_SYMBOL_GPL(ct_idle_exit);
noinstr void ct_irq_enter(void)
{
rcu_irq_enter();
}
noinstr void ct_irq_exit(void)
{
rcu_irq_exit();
}
void ct_irq_enter_irqson(void)
{
rcu_irq_enter_irqson();
}
void ct_irq_exit_irqson(void)
{
rcu_irq_exit_irqson();
}
noinstr void ct_nmi_enter(void)
{
rcu_nmi_enter();
}
noinstr void ct_nmi_exit(void)
{
rcu_nmi_exit();
}
#endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */
#ifdef CONFIG_CONTEXT_TRACKING_USER
#define CREATE_TRACE_POINTS
#include <trace/events/context_tracking.h>
DEFINE_STATIC_KEY_FALSE(context_tracking_key);
EXPORT_SYMBOL_GPL(context_tracking_key);
DEFINE_PER_CPU(struct context_tracking, context_tracking);
EXPORT_SYMBOL_GPL(context_tracking);
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
static noinstr bool context_tracking_recursion_enter(void)
{
int recursion;
recursion = __this_cpu_inc_return(context_tracking.recursion);
if (recursion == 1)
return true;
WARN_ONCE((recursion < 1), "Invalid context tracking recursion value %d\n", recursion);
__this_cpu_dec(context_tracking.recursion);
return false;
}
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
static __always_inline void context_tracking_recursion_exit(void)
{
__this_cpu_dec(context_tracking.recursion);
}
/**
* __ct_user_enter - Inform the context tracking that the CPU is going
* to enter user or guest space mode.
*
* This function must be called right before we switch from the kernel
* to user or guest space, when it's guaranteed the remaining kernel
* instructions to execute won't use any RCU read side critical section
* because this function sets RCU in extended quiescent state.
*/
void noinstr __ct_user_enter(enum ctx_state state)
{
/* Kernel threads aren't supposed to go to userspace */
WARN_ON_ONCE(!current->mm);
if (!context_tracking_recursion_enter())
return;
if ( __this_cpu_read(context_tracking.state) != state) {
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
if (__this_cpu_read(context_tracking.active)) {
/*
* At this stage, only low level arch entry code remains and
* then we'll run in userspace. We can assume there won't be
* any RCU read-side critical section until the next call to
* user_exit() or ct_irq_enter(). Let's remove RCU's dependency
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
* on the tick.
*/
if (state == CONTEXT_USER) {
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
instrumentation_begin();
trace_user_enter(0);
vtime_user_enter(current);
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
instrumentation_end();
}
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
rcu_user_enter();
}
/*
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
* Even if context tracking is disabled on this CPU, because it's outside
* the full dynticks mask for example, we still have to keep track of the
* context transitions and states to prevent inconsistency on those of
* other CPUs.
* If a task triggers an exception in userspace, sleep on the exception
* handler and then migrate to another CPU, that new CPU must know where
* the exception returns by the time we call exception_exit().
* This information can only be provided by the previous CPU when it called
* exception_enter().
* OTOH we can spare the calls to vtime and RCU when context_tracking.active
* is false because we know that CPU is not tickless.
*/
__this_cpu_write(context_tracking.state, state);
}
context_tracking_recursion_exit();
}
EXPORT_SYMBOL_GPL(__ct_user_enter);
/*
* OBSOLETE:
* This function should be noinstr but the below local_irq_restore() is
* unsafe because it involves illegal RCU uses through tracing and lockdep.
* This is unlikely to be fixed as this function is obsolete. The preferred
* way is to call __context_tracking_enter() through user_enter_irqoff()
* or context_tracking_guest_enter(). It should be the arch entry code
* responsibility to call into context tracking with IRQs disabled.
*/
void ct_user_enter(enum ctx_state state)
{
unsigned long flags;
/*
* Some contexts may involve an exception occuring in an irq,
* leading to that nesting:
* ct_irq_enter() rcu_user_exit() rcu_user_exit() ct_irq_exit()
* This would mess up the dyntick_nesting count though. And rcu_irq_*()
* helpers are enough to protect RCU uses inside the exception. So
* just return immediately if we detect we are in an IRQ.
*/
if (in_interrupt())
return;
local_irq_save(flags);
__ct_user_enter(state);
local_irq_restore(flags);
}
NOKPROBE_SYMBOL(ct_user_enter);
EXPORT_SYMBOL_GPL(ct_user_enter);
/**
* user_enter_callable() - Unfortunate ASM callable version of user_enter() for
* archs that didn't manage to check the context tracking
* static key from low level code.
*
* This OBSOLETE function should be noinstr but it unsafely calls
* local_irq_restore(), involving illegal RCU uses through tracing and lockdep.
* This is unlikely to be fixed as this function is obsolete. The preferred
* way is to call user_enter_irqoff(). It should be the arch entry code
* responsibility to call into context tracking with IRQs disabled.
*/
void user_enter_callable(void)
{
user_enter();
}
NOKPROBE_SYMBOL(user_enter_callable);
/**
* __ct_user_exit - Inform the context tracking that the CPU is
* exiting user or guest mode and entering the kernel.
*
* This function must be called after we entered the kernel from user or
* guest space before any use of RCU read side critical section. This
* potentially include any high level kernel code like syscalls, exceptions,
* signal handling, etc...
*
* This call supports re-entrancy. This way it can be called from any exception
* handler without needing to know if we came from userspace or not.
*/
void noinstr __ct_user_exit(enum ctx_state state)
{
if (!context_tracking_recursion_enter())
return;
if (__this_cpu_read(context_tracking.state) == state) {
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
if (__this_cpu_read(context_tracking.active)) {
/*
* We are going to run code that may use RCU. Inform
* RCU core about that (ie: we may need the tick again).
*/
rcu_user_exit();
if (state == CONTEXT_USER) {
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
instrumentation_begin();
vtime_user_exit(current);
trace_user_exit(0);
context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de
2020-03-04 13:05:22 +03:00
instrumentation_end();
}
context_tracking: Fix runtime CPU off-case As long as the context tracking is enabled on any CPU, even a single one, all other CPUs need to keep track of their user <-> kernel boundaries cross as well. This is because a task can sleep while servicing an exception that happened in the kernel or in userspace. Then when the task eventually wakes up and return from the exception, the CPU needs to know if we resume in userspace or in the kernel. exception_exit() get this information from exception_enter() that saved the previous state. If the CPU where the exception happened didn't keep track of these informations, exception_exit() doesn't know which state tracking to restore on the CPU where the task got migrated and we may return to userspace with the context tracking subsystem thinking that we are in kernel mode. This can be fixed in the long term if we move our context tracking probes on very low level arch fast path user <-> kernel boundary, although even that is worrisome as an exception can still happen in the few instructions between the probe and the actual iret. Also we are not yet ready to set these probes in the fast path given the potential overhead problem it induces. So let's fix this by always enable context tracking even on CPUs that are not in the full dynticks range. OTOH we can spare the rcu_user_*() and vtime_user_*() calls there because the tick runs on these CPUs and we can handle RCU state machine and cputime accounting through it. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Kevin Hilman <khilman@linaro.org>
2013-07-12 01:59:33 +04:00
}
__this_cpu_write(context_tracking.state, CONTEXT_KERNEL);
}
context_tracking_recursion_exit();
}
EXPORT_SYMBOL_GPL(__ct_user_exit);
/*
* OBSOLETE:
* This function should be noinstr but the below local_irq_save() is
* unsafe because it involves illegal RCU uses through tracing and lockdep.
* This is unlikely to be fixed as this function is obsolete. The preferred
* way is to call __context_tracking_exit() through user_exit_irqoff()
* or context_tracking_guest_exit(). It should be the arch entry code
* responsibility to call into context tracking with IRQs disabled.
*/
void ct_user_exit(enum ctx_state state)
{
unsigned long flags;
if (in_interrupt())
return;
local_irq_save(flags);
__ct_user_exit(state);
local_irq_restore(flags);
}
NOKPROBE_SYMBOL(ct_user_exit);
EXPORT_SYMBOL_GPL(ct_user_exit);
/**
* user_exit_callable() - Unfortunate ASM callable version of user_exit() for
* archs that didn't manage to check the context tracking
* static key from low level code.
*
* This OBSOLETE function should be noinstr but it unsafely calls local_irq_save(),
* involving illegal RCU uses through tracing and lockdep. This is unlikely
* to be fixed as this function is obsolete. The preferred way is to call
* user_exit_irqoff(). It should be the arch entry code responsibility to
* call into context tracking with IRQs disabled.
*/
void user_exit_callable(void)
{
user_exit();
}
NOKPROBE_SYMBOL(user_exit_callable);
void __init ct_cpu_track_user(int cpu)
{
static __initdata bool initialized = false;
if (!per_cpu(context_tracking.active, cpu)) {
per_cpu(context_tracking.active, cpu) = true;
static_branch_inc(&context_tracking_key);
}
if (initialized)
return;
#ifdef CONFIG_HAVE_TIF_NOHZ
/*
* Set TIF_NOHZ to init/0 and let it propagate to all tasks through fork
* This assumes that init is the only task at this early boot stage.
*/
set_tsk_thread_flag(&init_task, TIF_NOHZ);
#endif
WARN_ON_ONCE(!tasklist_empty());
initialized = true;
}
#ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE
void __init context_tracking_init(void)
{
int cpu;
for_each_possible_cpu(cpu)
ct_cpu_track_user(cpu);
}
#endif
#endif /* #ifdef CONFIG_CONTEXT_TRACKING_USER */