summaryrefslogtreecommitdiff
path: root/kernel/entry
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/entry')
-rw-r--r--kernel/entry/Makefile2
-rw-r--r--kernel/entry/common.c192
-rw-r--r--kernel/entry/common.h7
-rw-r--r--kernel/entry/kvm.c3
-rw-r--r--kernel/entry/syscall_user_dispatch.c104
5 files changed, 246 insertions, 62 deletions
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
index 34c8a3f1c735..095c775e001e 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -9,5 +9,5 @@ KCOV_INSTRUMENT := n
CFLAGS_REMOVE_common.o = -fstack-protector -fstack-protector-strong
CFLAGS_common.o += -fno-stack-protector
-obj-$(CONFIG_GENERIC_ENTRY) += common.o
+obj-$(CONFIG_GENERIC_ENTRY) += common.o syscall_user_dispatch.o
obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK) += kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 4ae1fe0898e9..378341642f94 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -6,20 +6,13 @@
#include <linux/livepatch.h>
#include <linux/audit.h>
+#include "common.h"
+
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
-/**
- * enter_from_user_mode - Establish state when coming from user mode
- *
- * Syscall/interrupt entry disables interrupts, but user mode is traced as
- * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
- *
- * 1) Tell lockdep that interrupts are disabled
- * 2) Invoke context tracking if enabled to reactivate RCU
- * 3) Trace interrupts off state
- */
-static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+/* See comment for enter_from_user_mode() in entry-common.h */
+static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
{
arch_check_user_regs(regs);
lockdep_hardirqs_off(CALLER_ADDR0);
@@ -32,6 +25,11 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
instrumentation_end();
}
+void noinstr enter_from_user_mode(struct pt_regs *regs)
+{
+ __enter_from_user_mode(regs);
+}
+
static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
{
if (unlikely(audit_context())) {
@@ -43,19 +41,29 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
}
static long syscall_trace_enter(struct pt_regs *regs, long syscall,
- unsigned long ti_work)
+ unsigned long work)
{
long ret = 0;
+ /*
+ * Handle Syscall User Dispatch. This must comes first, since
+ * the ABI here can be something that doesn't make sense for
+ * other syscall_work features.
+ */
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (syscall_user_dispatch(regs))
+ return -1L;
+ }
+
/* Handle ptrace */
- if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+ if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
ret = arch_syscall_enter_tracehook(regs);
- if (ret || (ti_work & _TIF_SYSCALL_EMU))
+ if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
return -1L;
}
/* Do seccomp after ptrace, to catch any tracer changes. */
- if (ti_work & _TIF_SECCOMP) {
+ if (work & SYSCALL_WORK_SECCOMP) {
ret = __secure_computing(NULL);
if (ret == -1L)
return ret;
@@ -64,7 +72,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
/* Either of the above might have changed the syscall number */
syscall = syscall_get_nr(current, regs);
- if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
+ if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
trace_sys_enter(regs, syscall);
syscall_enter_audit(regs, syscall);
@@ -75,11 +83,10 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
static __always_inline long
__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
{
- unsigned long ti_work;
+ unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
- ti_work = READ_ONCE(current_thread_info()->flags);
- if (ti_work & SYSCALL_ENTER_WORK)
- syscall = syscall_trace_enter(regs, syscall, ti_work);
+ if (work & SYSCALL_WORK_ENTER)
+ syscall = syscall_trace_enter(regs, syscall, work);
return syscall;
}
@@ -93,7 +100,7 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
{
long ret;
- enter_from_user_mode(regs);
+ __enter_from_user_mode(regs);
instrumentation_begin();
local_irq_enable();
@@ -105,25 +112,14 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
{
- enter_from_user_mode(regs);
+ __enter_from_user_mode(regs);
instrumentation_begin();
local_irq_enable();
instrumentation_end();
}
-/**
- * exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interupt exit enables interrupts, but the kernel state is
- * interrupts disabled when this is invoked. Also tell RCU about it.
- *
- * 1) Trace interrupts on state
- * 2) Invoke context tracking if enabled to adjust RCU state
- * 3) Invoke architecture specific last minute exit code, e.g. speculation
- * mitigations, etc.
- * 4) Tell lockdep that interrupts are enabled
- */
-static __always_inline void exit_to_user_mode(void)
+/* See comment for exit_to_user_mode() in entry-common.h */
+static __always_inline void __exit_to_user_mode(void)
{
instrumentation_begin();
trace_hardirqs_on_prepare();
@@ -135,8 +131,21 @@ static __always_inline void exit_to_user_mode(void)
lockdep_hardirqs_on(CALLER_ADDR0);
}
+void noinstr exit_to_user_mode(void)
+{
+ __exit_to_user_mode();
+}
+
/* Workaround to allow gradual conversion of architecture code */
-void __weak arch_do_signal(struct pt_regs *regs) { }
+void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
+
+static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work)
+{
+ if (ti_work & _TIF_NOTIFY_SIGNAL)
+ tracehook_notify_signal();
+
+ arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING);
+}
static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
unsigned long ti_work)
@@ -158,8 +167,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
if (ti_work & _TIF_PATCH_PENDING)
klp_update_patch_state(current);
- if (ti_work & _TIF_SIGPENDING)
- arch_do_signal(regs);
+ if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+ handle_signal_work(regs, ti_work);
if (ti_work & _TIF_NOTIFY_RESUME) {
tracehook_notify_resume(regs);
@@ -201,35 +210,50 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
}
#ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
{
return false;
}
#else
/*
- * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * If SYSCALL_EMU is set, then the only reason to report is when
* TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
* instruction has been already reported in syscall_enter_from_user_mode().
*/
-#define SYSEMU_STEP (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
-
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
{
- return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+ if (!(work & SYSCALL_WORK_SYSCALL_EMU))
+ return false;
+
+ return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
}
#endif
-static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
{
bool step;
+ /*
+ * If the syscall was rolled back due to syscall user dispatching,
+ * then the tracers below are not invoked for the same reason as
+ * the entry side was not invoked in syscall_trace_enter(): The ABI
+ * of these syscalls is unknown.
+ */
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (unlikely(current->syscall_dispatch.on_dispatch)) {
+ current->syscall_dispatch.on_dispatch = false;
+ return;
+ }
+ }
+
audit_syscall_exit(regs);
- if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+ if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
trace_sys_exit(regs, syscall_get_return_value(current, regs));
- step = report_single_step(ti_work);
- if (step || ti_work & _TIF_SYSCALL_TRACE)
+ step = report_single_step(work);
+ if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
arch_syscall_exit_tracehook(regs, step);
}
@@ -239,7 +263,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
*/
static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
{
- u32 cached_flags = READ_ONCE(current_thread_info()->flags);
+ unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
unsigned long nr = syscall_get_nr(current, regs);
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -256,23 +280,33 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
* enabled, we want to run them exactly once per syscall exit with
* interrupts enabled.
*/
- if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
- syscall_exit_work(regs, cached_flags);
+ if (unlikely(work & SYSCALL_WORK_EXIT))
+ syscall_exit_work(regs, work);
}
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
{
- instrumentation_begin();
syscall_exit_to_user_mode_prepare(regs);
local_irq_disable_exit_to_user();
exit_to_user_mode_prepare(regs);
+}
+
+void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+ __syscall_exit_to_user_mode_work(regs);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+ instrumentation_begin();
+ __syscall_exit_to_user_mode_work(regs);
instrumentation_end();
- exit_to_user_mode();
+ __exit_to_user_mode();
}
noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
{
- enter_from_user_mode(regs);
+ __enter_from_user_mode(regs);
}
noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
@@ -280,7 +314,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
instrumentation_begin();
exit_to_user_mode_prepare(regs);
instrumentation_end();
- exit_to_user_mode();
+ __exit_to_user_mode();
}
noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
@@ -298,7 +332,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* If this entry hit the idle task invoke rcu_irq_enter() whether
* RCU is watching or not.
*
- * Interupts can nest when the first interrupt invokes softirq
+ * Interrupts can nest when the first interrupt invokes softirq
* processing on return which enables interrupts.
*
* Scheduler ticks in the idle task can mark quiescent state and
@@ -309,7 +343,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* interrupt to invoke rcu_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
* assume that it is the first interupt and eventually claim
- * quiescient state and end grace periods prematurely.
+ * quiescent state and end grace periods prematurely.
*
* Unconditionally invoke rcu_irq_enter() so RCU state stays
* consistent.
@@ -321,7 +355,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
/*
* If RCU is not watching then the same careful
* sequence vs. lockdep and tracing is required
- * as in irq_enter_from_user_mode().
+ * as in irqentry_enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
rcu_irq_enter();
@@ -339,10 +373,10 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
* already contains a warning when RCU is not watching, so no point
* in having another one here.
*/
+ lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
rcu_irq_enter_check_tick();
- /* Use the combo lockdep/tracing function */
- trace_hardirqs_off();
+ trace_hardirqs_off_finish();
instrumentation_end();
return ret;
@@ -399,3 +433,39 @@ 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();
+}
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
new file mode 100644
index 000000000000..f6e6d02f07fe
--- /dev/null
+++ b/kernel/entry/common.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COMMON_H
+#define _COMMON_H
+
+bool syscall_user_dispatch(struct pt_regs *regs);
+
+#endif
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index b6678a5e3cf6..49972ee99aff 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -8,6 +8,9 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
do {
int ret;
+ if (ti_work & _TIF_NOTIFY_SIGNAL)
+ tracehook_notify_signal();
+
if (ti_work & _TIF_SIGPENDING) {
kvm_handle_signal_exit(vcpu);
return -EINTR;
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
new file mode 100644
index 000000000000..b0338a5625d9
--- /dev/null
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/syscall.h>
+
+#include "common.h"
+
+static void trigger_sigsys(struct pt_regs *regs)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSYS;
+ info.si_code = SYS_USER_DISPATCH;
+ info.si_call_addr = (void __user *)KSTK_EIP(current);
+ info.si_errno = 0;
+ info.si_arch = syscall_get_arch(current);
+ info.si_syscall = syscall_get_nr(current, regs);
+
+ force_sig_info(&info);
+}
+
+bool syscall_user_dispatch(struct pt_regs *regs)
+{
+ struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+ char state;
+
+ if (likely(instruction_pointer(regs) - sd->offset < sd->len))
+ return false;
+
+ if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+ return false;
+
+ if (likely(sd->selector)) {
+ /*
+ * access_ok() is performed once, at prctl time, when
+ * the selector is loaded by userspace.
+ */
+ if (unlikely(__get_user(state, sd->selector)))
+ do_exit(SIGSEGV);
+
+ if (likely(state == PR_SYS_DISPATCH_OFF))
+ return false;
+
+ if (state != PR_SYS_DISPATCH_ON)
+ do_exit(SIGSYS);
+ }
+
+ sd->on_dispatch = true;
+ syscall_rollback(current, regs);
+ trigger_sigsys(regs);
+
+ return true;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+ unsigned long len, char __user *selector)
+{
+ switch (mode) {
+ case PR_SYS_DISPATCH_OFF:
+ if (offset || len || selector)
+ return -EINVAL;
+ break;
+ case PR_SYS_DISPATCH_ON:
+ /*
+ * Validate the direct dispatcher region just for basic
+ * sanity against overflow and a 0-sized dispatcher
+ * region. If the user is able to submit a syscall from
+ * an address, that address is obviously valid.
+ */
+ if (offset && offset + len <= offset)
+ return -EINVAL;
+
+ if (selector && !access_ok(selector, sizeof(*selector)))
+ return -EFAULT;
+
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ current->syscall_dispatch.selector = selector;
+ current->syscall_dispatch.offset = offset;
+ current->syscall_dispatch.len = len;
+ current->syscall_dispatch.on_dispatch = false;
+
+ if (mode == PR_SYS_DISPATCH_ON)
+ set_syscall_work(SYSCALL_USER_DISPATCH);
+ else
+ clear_syscall_work(SYSCALL_USER_DISPATCH);
+
+ return 0;
+}
generated by cgit (git 2.34.1) at 2024-06-14 20:46:25 +0000