[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190923090557.GA8357@linux.ibm.com>
Date: Mon, 23 Sep 2019 12:05:58 +0300
From: Mike Rapoport <rppt@...ux.ibm.com>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: LKML <linux-kernel@...r.kernel.org>, x86@...nel.org,
Peter Zijlstra <peterz@...radead.org>,
Andy Lutomirski <luto@...nel.org>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Marc Zyngier <maz@...nel.org>,
Paolo Bonzini <pbonzini@...hat.com>, kvm@...r.kernel.org,
linux-arch@...r.kernel.org
Subject: Re: [RFC patch 01/15] entry: Provide generic syscall entry
functionality
On Thu, Sep 19, 2019 at 05:03:15PM +0200, Thomas Gleixner wrote:
> On syscall entry certain work needs to be done conditionally like tracing,
> seccomp etc. This code is duplicated in all architectures.
>
> Provide a generic version.
>
> Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
> ---
> arch/Kconfig | 3 +
> include/linux/entry-common.h | 122 +++++++++++++++++++++++++++++++++++++++++++
> kernel/Makefile | 1
> kernel/entry/Makefile | 3 +
> kernel/entry/common.c | 33 +++++++++++
> 5 files changed, 162 insertions(+)
>
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -27,6 +27,9 @@ config HAVE_IMA_KEXEC
> config HOTPLUG_SMT
> bool
>
> +config GENERIC_ENTRY
> + bool
> +
> config OPROFILE
> tristate "OProfile system profiling"
> depends on PROFILING
> --- /dev/null
> +++ b/include/linux/entry-common.h
> @@ -0,0 +1,122 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef __LINUX_ENTRYCOMMON_H
> +#define __LINUX_ENTRYCOMMON_H
> +
> +#include <linux/tracehook.h>
> +#include <linux/syscalls.h>
> +#include <linux/seccomp.h>
> +#include <linux/sched.h>
> +#include <linux/audit.h>
> +
> +#include <asm/entry-common.h>
> +
> +/*
> + * Define dummy _TIF work flags if not defined by the architecture or for
> + * disabled functionality.
> + */
> +#ifndef _TIF_SYSCALL_TRACE
> +# define _TIF_SYSCALL_TRACE (0)
> +#endif
> +
> +#ifndef _TIF_SYSCALL_EMU
> +# define _TIF_SYSCALL_EMU (0)
> +#endif
> +
> +#ifndef _TIF_SYSCALL_TRACEPOINT
> +# define _TIF_SYSCALL_TRACEPOINT (0)
> +#endif
> +
> +#ifndef _TIF_SECCOMP
> +# define _TIF_SECCOMP (0)
> +#endif
> +
> +#ifndef _TIF_AUDIT
> +# define _TIF_AUDIT (0)
> +#endif
> +
> +/*
> + * TIF flags handled in syscall_enter_from_usermode()
> + */
> +#ifndef ARCH_SYSCALL_ENTER_WORK
> +# define ARCH_SYSCALL_ENTER_WORK (0)
> +#endif
> +
> +#define SYSCALL_ENTER_WORK \
> + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | TIF_SECCOMP | \
> + _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU | \
> + ARCH_SYSCALL_ENTER_WORK)
> +
> +/**
> + * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry()
> + *
> + * Defaults to tracehook_report_syscall_entry(). Can be replaced by
> + * architecture specific code.
> + *
> + * Invoked from syscall_enter_from_usermode()
> + */
Nit: the kernel-doc here and in other places in the patchset lacks
parameter and return value descriptions, which will create lots of warnings
for 'make *docs'.
> +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs);
> +
> +#ifndef arch_syscall_enter_tracehook
> +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs)
> +{
> + return tracehook_report_syscall_entry(regs);
> +}
> +#endif
> +
> +/**
> + * arch_syscall_enter_seccomp - Architecture specific seccomp invocation
> + * @regs: Pointer to currents pt_regs
> + *
> + * Invoked from syscall_enter_from_usermode(). Can be replaced by
> + * architecture specific code.
> + */
> +static inline long arch_syscall_enter_seccomp(struct pt_regs *regs);
> +
> +#ifndef arch_syscall_enter_seccomp
> +static inline long arch_syscall_enter_seccomp(struct pt_regs *regs)
> +{
> + return secure_computing(NULL);
> +}
> +#endif
> +
> +/**
> + * arch_syscall_enter_audit - Architecture specific audit invocation
> + * @regs: Pointer to currents pt_regs
> + *
> + * Invoked from syscall_enter_from_usermode(). Must be replaced by
> + * architecture specific code if the architecture supports audit.
> + */
> +static inline void arch_syscall_enter_audit(struct pt_regs *regs);
> +
> +#ifndef arch_syscall_enter_audit
> +static inline void arch_syscall_enter_audit(struct pt_regs *regs) { }
> +#endif
> +
> +/* Common syscall enter function */
> +long core_syscall_enter_from_usermode(struct pt_regs *regs, long syscall);
> +
> +/**
> + * syscall_enter_from_usermode - Check and handle work before invoking
> + * a syscall
> + * @regs: Pointer to currents pt_regs
> + * @syscall: The syscall number
> + *
> + * Invoked from architecture specific syscall entry code with interrupts
> + * enabled.
> + *
> + * Returns: The original or a modified syscall number
> + */
> +static inline long syscall_enter_from_usermode(struct pt_regs *regs,
> + long syscall)
> +{
> + unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
> +
> + if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
> + BUG_ON(regs != task_pt_regs(current));
> +
> + if (ti_work & SYSCALL_ENTER_WORK)
> + syscall = core_syscall_enter_from_usermode(regs, syscall);
> + return syscall;
> +}
> +
> +#endif
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -43,6 +43,7 @@ obj-y += irq/
> obj-y += rcu/
> obj-y += livepatch/
> obj-y += dma/
> +obj-y += entry/
>
> obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
> obj-$(CONFIG_FREEZER) += freezer.o
> --- /dev/null
> +++ b/kernel/entry/Makefile
> @@ -0,0 +1,3 @@
> +# SPDX-License-Identifier: GPL-2.0
> +
> +obj-$(CONFIG_GENERIC_ENTRY) += common.o
> --- /dev/null
> +++ b/kernel/entry/common.c
> @@ -0,0 +1,33 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#include <linux/context_tracking.h>
> +#include <linux/entry-common.h>
> +
> +#define CREATE_TRACE_POINTS
> +#include <trace/events/syscalls.h>
> +
> +long core_syscall_enter_from_usermode(struct pt_regs *regs, long syscall)
> +{
> + unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
> + unsigned long ret = 0;
> +
> + if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
> + ret = arch_syscall_enter_tracehook(regs);
> + if (ret || (ti_work & _TIF_SYSCALL_EMU))
> + return -1L;
> + }
> +
> + /* Do seccomp after ptrace, to catch any tracer changes. */
> + if (ti_work & _TIF_SECCOMP) {
> + ret = arch_syscall_enter_seccomp(regs);
> + if (ret == -1L)
> + return ret;
> + }
> +
> + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
> + trace_sys_enter(regs, syscall);
> +
> + arch_syscall_enter_audit(regs);
> +
> + return ret ? : syscall;
> +}
>
>
--
Sincerely yours,
Mike.
Powered by blists - more mailing lists