* [PATCH 6.1.y 2/5] entry: Split generic entry into generic exception and syscall entry
2026-09-08 12:20 ` [PATCH 6.1.y 1/5] entry: Inline syscall_exit_to_user_mode() Sasha Levin
@ 2026-09-08 12:20 ` Sasha Levin
2026-09-08 12:20 ` [PATCH 6.1.y 3/5] entry: Remove syscall_enter_from_user_mode_prepare() Sasha Levin
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Sasha Levin @ 2026-09-08 12:20 UTC (permalink / raw)
To: stable
Cc: Jinjie Ruan, Mark Rutland, Linus Walleij, Thomas Gleixner,
Sasha Levin
From: Jinjie Ruan <ruanjinjie@huawei.com>
[ Upstream commit a70e9f647f501e36a6a092888b1ea7386b7c5664 ]
Currently CONFIG_GENERIC_ENTRY enables both the generic exception
entry logic and the generic syscall entry logic, which are otherwise
loosely coupled.
Introduce separate config options for these so that architectures can
select the two independently. This will make it easier for
architectures to migrate to generic entry code.
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/20250213130007.1418890-2-ruanjinjie@huawei.com
Link: https://lore.kernel.org/all/20250624-generic-entry-split-v1-1-53d5ef4f94df@linaro.org
[Linus Walleij: rebase onto v6.16-rc1]
Stable-dep-of: 4a3591287fb7 ("entry: Fix seccomp bypass after ptrace with TSYNC")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
MAINTAINERS | 1 +
arch/Kconfig | 9 +
include/linux/entry-common.h | 415 +++----------------------------
include/linux/irq-entry-common.h | 394 +++++++++++++++++++++++++++++
kernel/entry/Makefile | 3 +-
kernel/entry/common.c | 121 +--------
kernel/entry/syscall-common.c | 86 +++++++
kernel/sched/core.c | 8 +-
8 files changed, 535 insertions(+), 502 deletions(-)
create mode 100644 include/linux/irq-entry-common.h
create mode 100644 kernel/entry/syscall-common.c
diff --git a/MAINTAINERS b/MAINTAINERS
index a02522a3ec08a..33cf298ef9751 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8562,6 +8562,7 @@ S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/entry
F: include/linux/entry-common.h
F: include/linux/entry-kvm.h
+F: include/linux/irq-entry-common.h
F: kernel/entry/
GENERIC GPIO I2C DRIVER
diff --git a/arch/Kconfig b/arch/Kconfig
index e959abf969ec3..4367fc069126d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -45,8 +45,17 @@ config HOTPLUG_SMT
config SMT_NUM_THREADS_DYNAMIC
bool
+config GENERIC_IRQ_ENTRY
+ bool
+
+config GENERIC_SYSCALL
+ bool
+ depends on GENERIC_IRQ_ENTRY
+
config GENERIC_ENTRY
bool
+ select GENERIC_IRQ_ENTRY
+ select GENERIC_SYSCALL
config KPROBES
bool "Kprobes"
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 4533799c13cda..ed08489e1d329 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -2,32 +2,16 @@
#ifndef __LINUX_ENTRYCOMMON_H
#define __LINUX_ENTRYCOMMON_H
-#include <linux/static_call_types.h>
+#include <linux/irq-entry-common.h>
#include <linux/ptrace.h>
-#include <linux/syscalls.h>
#include <linux/seccomp.h>
#include <linux/sched.h>
-#include <linux/context_tracking.h>
#include <linux/livepatch.h>
#include <linux/resume_user_mode.h>
-#include <linux/tick.h>
-#include <linux/kmsan.h>
#include <asm/entry-common.h>
#include <asm/syscall.h>
-/*
- * Define dummy _TIF work flags if not defined by the architecture or for
- * disabled functionality.
- */
-#ifndef _TIF_PATCH_PENDING
-# define _TIF_PATCH_PENDING (0)
-#endif
-
-#ifndef _TIF_UPROBE
-# define _TIF_UPROBE (0)
-#endif
-
/*
* SYSCALL_WORK flags handled in syscall_enter_from_user_mode()
*/
@@ -57,65 +41,51 @@
ARCH_SYSCALL_WORK_EXIT)
/*
- * TIF flags handled in exit_to_user_mode_loop()
+ * Keep the newer permit-style name used by the target while retaining the
+ * stable tree's ptrace return convention (zero permits the syscall).
*/
-#ifndef ARCH_EXIT_TO_USER_MODE_WORK
-# define ARCH_EXIT_TO_USER_MODE_WORK (0)
+#ifndef arch_ptrace_report_syscall_permit_entry
+#define arch_ptrace_report_syscall_permit_entry(regs) \
+ (!ptrace_report_syscall_entry(regs))
#endif
-#define EXIT_TO_USER_MODE_WORK \
- (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \
- ARCH_EXIT_TO_USER_MODE_WORK)
+bool syscall_user_dispatch(struct pt_regs *regs);
+long syscall_enter_audit(struct pt_regs *regs, long syscall,
+ unsigned long work);
-/**
- * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
- * @regs: Pointer to currents pt_regs
- *
- * Defaults to an empty implementation. Can be replaced by architecture
- * specific code.
- *
- * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
- * section. Use __always_inline so the compiler cannot push it out of line
- * and make it instrumentable.
- */
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
+static __always_inline long syscall_trace_enter(struct pt_regs *regs, long syscall,
+ unsigned long work)
+{
+ long ret = 0;
-#ifndef arch_enter_from_user_mode
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
-#endif
+ /*
+ * 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;
+ }
-/**
- * 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
- *
- * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and interrupts are still
- * disabled. The subsequent functions can be instrumented.
- *
- * This is invoked when there is architecture specific functionality to be
- * done between establishing state and enabling interrupts. The caller must
- * enable interrupts before invoking syscall_enter_from_user_mode_work().
- */
-static __always_inline void enter_from_user_mode(struct pt_regs *regs)
-{
- arch_enter_from_user_mode(regs);
- lockdep_hardirqs_off(CALLER_ADDR0);
+ /* Handle ptrace */
+ if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
+ if (!arch_ptrace_report_syscall_permit_entry(regs) ||
+ (work & SYSCALL_WORK_SYSCALL_EMU))
+ return -1L;
+ }
- CT_WARN_ON(__ct_state() != CONTEXT_USER);
- user_exit_irqoff();
+ /* Do seccomp after ptrace, to catch any tracer changes. */
+ if (work & SYSCALL_WORK_SECCOMP) {
+ ret = __secure_computing(NULL);
+ if (ret == -1L)
+ return ret;
+ }
- instrumentation_begin();
- kmsan_unpoison_entry_regs(regs);
- trace_hardirqs_off_finish();
- instrumentation_end();
+ /* Either of the above might have changed the syscall number */
+ syscall = syscall_get_nr(current, regs);
+
+ return syscall_enter_audit(regs, syscall, work);
}
/**
@@ -135,9 +105,6 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
*/
void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
-long syscall_trace_enter(struct pt_regs *regs, long syscall,
- unsigned long work);
-
/**
* syscall_enter_from_user_mode_work - Check and handle work before invoking
* a syscall
@@ -202,171 +169,6 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
return ret;
}
-/**
- * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
- * @ti_work: Cached TIF flags gathered with interrupts disabled
- *
- * Defaults to local_irq_enable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
-
-#ifndef local_irq_enable_exit_to_user
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
-{
- local_irq_enable();
-}
-#endif
-
-/**
- * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
- *
- * Defaults to local_irq_disable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_disable_exit_to_user(void);
-
-#ifndef local_irq_disable_exit_to_user
-static inline void local_irq_disable_exit_to_user(void)
-{
- local_irq_disable();
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
- * to user mode.
- * @regs: Pointer to currents pt_regs
- * @ti_work: Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_loop() with interrupt enabled
- *
- * Defaults to NOOP. Can be supplied by architecture specific code.
- */
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
- unsigned long ti_work);
-
-#ifndef arch_exit_to_user_mode_work
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
- unsigned long ti_work)
-{
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_prepare - Architecture specific preparation for
- * exit to user mode.
- * @regs: Pointer to currents pt_regs
- * @ti_work: Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- */
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
- unsigned long ti_work);
-
-#ifndef arch_exit_to_user_mode_prepare
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
- unsigned long ti_work)
-{
-}
-#endif
-
-/**
- * arch_exit_to_user_mode - Architecture specific final work before
- * exit to user mode.
- *
- * Invoked from exit_to_user_mode() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- *
- * This needs to be __always_inline because it is non-instrumentable code
- * invoked after context tracking switched to user mode.
- *
- * An architecture implementation must not do anything complex, no locking
- * etc. The main purpose is for speculation mitigations.
- */
-static __always_inline void arch_exit_to_user_mode(void);
-
-#ifndef arch_exit_to_user_mode
-static __always_inline void arch_exit_to_user_mode(void) { }
-#endif
-
-/**
- * arch_do_signal_or_restart - Architecture specific signal delivery function
- * @regs: Pointer to currents pt_regs
- *
- * Invoked from exit_to_user_mode_loop().
- */
-void arch_do_signal_or_restart(struct pt_regs *regs);
-
-/**
- * exit_to_user_mode_loop - do any pending work before leaving to user space
- */
-unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
- unsigned long ti_work);
-
-/**
- * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
- * @regs: Pointer to pt_regs on entry stack
- *
- * 1) check that interrupts are disabled
- * 2) call tick_nohz_user_enter_prepare()
- * 3) call exit_to_user_mode_loop() if any flags from
- * EXIT_TO_USER_MODE_WORK are set
- * 4) check that interrupts are still disabled
- */
-static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
- unsigned long ti_work;
-
- lockdep_assert_irqs_disabled();
-
- /* Flush pending rcuog wakeup before the last need_resched() check */
- tick_nohz_user_enter_prepare();
-
- ti_work = read_thread_flags();
- if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
- ti_work = exit_to_user_mode_loop(regs, ti_work);
-
- arch_exit_to_user_mode_prepare(regs, ti_work);
-
- /* Ensure that the address limit is intact and no locks are held */
- addr_limit_user_check();
- kmap_assert_nomap();
- lockdep_assert_irqs_disabled();
- lockdep_sys_exit();
-}
-
-/**
- * exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interrupt 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.: arch_exit_to_user_mode()
- * 4) Tell lockdep that interrupts are enabled
- *
- * Invoked from architecture specific code when syscall_exit_to_user_mode()
- * is not suitable as the last step before returning to userspace. Must be
- * invoked with interrupts disabled and the caller must be
- * non-instrumentable.
- * The caller has to invoke syscall_exit_to_user_mode_work() before this.
- */
-static __always_inline void exit_to_user_mode(void)
-{
- instrumentation_begin();
- trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare();
- instrumentation_end();
-
- user_enter_irqoff();
- arch_exit_to_user_mode();
- lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
/**
* syscall_exit_work - Handle work before returning to user mode
* @regs: Pointer to current pt_regs
@@ -445,145 +247,4 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
*/
void syscall_exit_to_user_mode(struct pt_regs *regs);
-/**
- * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
- * @regs: Pointer to currents pt_regs
- *
- * Invoked from architecture specific entry code with interrupts disabled.
- * Can only be called when the interrupt entry came from user mode. The
- * calling code must be non-instrumentable. When the function returns all
- * state is correct and the subsequent functions can be instrumented.
- *
- * The function establishes state (lockdep, RCU (context tracking), tracing)
- */
-void irqentry_enter_from_user_mode(struct pt_regs *regs);
-
-/**
- * irqentry_exit_to_user_mode - Interrupt exit work
- * @regs: Pointer to current's pt_regs
- *
- * Invoked with interrupts disabled and fully valid regs. Returns with all
- * work handled, interrupts disabled such that the caller can immediately
- * switch to user mode. Called from architecture specific interrupt
- * handling code.
- *
- * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
- * Interrupt exit is not invoking #1 which is the syscall specific one time
- * work.
- */
-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 ct_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 {
- union {
- bool exit_rcu;
- bool lockdep;
- };
-} irqentry_state_t;
-#endif
-
-/**
- * irqentry_enter - Handle state tracking on ordinary interrupt entries
- * @regs: Pointer to pt_regs of interrupted context
- *
- * Invokes:
- * - lockdep irqflag state tracking as low level ASM entry disabled
- * interrupts.
- *
- * - Context tracking if the exception hit user mode.
- *
- * - The hardirq tracer to keep the state consistent as low level ASM
- * entry disabled interrupts.
- *
- * As a precondition, this requires that the entry came from user mode,
- * idle, or a kernel context in which RCU is watching.
- *
- * For kernel mode entries RCU handling is done conditional. If RCU is
- * watching then the only RCU requirement is to check whether the tick has
- * to be restarted. If RCU is not watching then ct_irq_enter() has to be
- * invoked on entry and ct_irq_exit() on exit.
- *
- * Avoiding the ct_irq_enter/exit() calls is an optimization but also
- * solves the problem of kernel mode pagefaults which can schedule, which
- * is not possible after invoking ct_irq_enter() without undoing it.
- *
- * For user mode entries irqentry_enter_from_user_mode() is invoked to
- * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
- * would not be possible.
- *
- * Returns: An opaque object that must be passed to idtentry_exit()
- */
-irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
-
-/**
- * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
- *
- * Conditional reschedule with additional sanity checks.
- */
-void raw_irqentry_exit_cond_resched(void);
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched
-#define irqentry_exit_cond_resched_dynamic_disabled NULL
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)()
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void);
-#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched()
-#endif
-#else /* CONFIG_PREEMPT_DYNAMIC */
-#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched()
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
-/**
- * irqentry_exit - Handle return from exception that used irqentry_enter()
- * @regs: Pointer to pt_regs (exception entry regs)
- * @state: Return value from matching call to irqentry_enter()
- *
- * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and required and returns to
- * the caller with interrupts disabled and no further work pending.
- *
- * This is the last action before returning to the low level ASM code which
- * just needs to return to the appropriate context.
- *
- * Counterpart to irqentry_enter().
- */
-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 assembly code.
- *
- * Counterpart to irqentry_nmi_enter().
- */
-void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
-
#endif
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
new file mode 100644
index 0000000000000..f2920724d8940
--- /dev/null
+++ b/include/linux/irq-entry-common.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_IRQENTRYCOMMON_H
+#define __LINUX_IRQENTRYCOMMON_H
+
+#include <linux/highmem.h>
+#include <linux/static_call_types.h>
+#include <linux/syscalls.h>
+#include <linux/context_tracking.h>
+#include <linux/tick.h>
+#include <linux/kmsan.h>
+
+#include <asm/entry-common.h>
+
+/*
+ * Define dummy _TIF work flags if not defined by the architecture or for
+ * disabled functionality.
+ */
+#ifndef _TIF_PATCH_PENDING
+# define _TIF_PATCH_PENDING (0)
+#endif
+
+#ifndef _TIF_UPROBE
+# define _TIF_UPROBE (0)
+#endif
+
+/*
+ * TIF flags handled in exit_to_user_mode_loop()
+ */
+#ifndef ARCH_EXIT_TO_USER_MODE_WORK
+# define ARCH_EXIT_TO_USER_MODE_WORK (0)
+#endif
+
+#define EXIT_TO_USER_MODE_WORK \
+ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+ _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \
+ ARCH_EXIT_TO_USER_MODE_WORK)
+
+/**
+ * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
+ * @regs: Pointer to currents pt_regs
+ *
+ * Defaults to an empty implementation. Can be replaced by architecture
+ * specific code.
+ *
+ * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
+ * section. Use __always_inline so the compiler cannot push it out of line
+ * and make it instrumentable.
+ */
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
+
+#ifndef arch_enter_from_user_mode
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
+#endif
+
+/**
+ * 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
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and interrupts are still
+ * disabled. The subsequent functions can be instrumented.
+ *
+ * This is invoked when there is architecture specific functionality to be
+ * done between establishing state and enabling interrupts. The caller must
+ * enable interrupts before invoking syscall_enter_from_user_mode_work().
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+ arch_enter_from_user_mode(regs);
+ lockdep_hardirqs_off(CALLER_ADDR0);
+
+ CT_WARN_ON(__ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+
+ instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
+ trace_hardirqs_off_finish();
+ instrumentation_end();
+}
+
+/**
+ * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
+ * @ti_work: Cached TIF flags gathered with interrupts disabled
+ *
+ * Defaults to local_irq_enable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
+
+#ifndef local_irq_enable_exit_to_user
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
+{
+ local_irq_enable();
+}
+#endif
+
+/**
+ * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
+ *
+ * Defaults to local_irq_disable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_disable_exit_to_user(void);
+
+#ifndef local_irq_disable_exit_to_user
+static inline void local_irq_disable_exit_to_user(void)
+{
+ local_irq_disable();
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
+ * to user mode.
+ * @regs: Pointer to currents pt_regs
+ * @ti_work: Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_loop() with interrupt enabled
+ *
+ * Defaults to NOOP. Can be supplied by architecture specific code.
+ */
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+ unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_work
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+ unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_prepare - Architecture specific preparation for
+ * exit to user mode.
+ * @regs: Pointer to currents pt_regs
+ * @ti_work: Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ */
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+ unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_prepare
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+ unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode - Architecture specific final work before
+ * exit to user mode.
+ *
+ * Invoked from exit_to_user_mode() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ *
+ * This needs to be __always_inline because it is non-instrumentable code
+ * invoked after context tracking switched to user mode.
+ *
+ * An architecture implementation must not do anything complex, no locking
+ * etc. The main purpose is for speculation mitigations.
+ */
+static __always_inline void arch_exit_to_user_mode(void);
+
+#ifndef arch_exit_to_user_mode
+static __always_inline void arch_exit_to_user_mode(void) { }
+#endif
+
+/**
+ * arch_do_signal_or_restart - Architecture specific signal delivery function
+ * @regs: Pointer to currents pt_regs
+ *
+ * Invoked from exit_to_user_mode_loop().
+ */
+void arch_do_signal_or_restart(struct pt_regs *regs);
+
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+ unsigned long ti_work);
+
+/**
+ * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs: Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ * EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ */
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+ unsigned long ti_work;
+
+ lockdep_assert_irqs_disabled();
+
+ /* Flush pending rcuog wakeup before the last need_resched() check */
+ tick_nohz_user_enter_prepare();
+
+ ti_work = read_thread_flags();
+ if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+ ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+ arch_exit_to_user_mode_prepare(regs, ti_work);
+
+ /* Ensure that the address limit is intact and no locks are held */
+ addr_limit_user_check();
+ kmap_assert_nomap();
+ lockdep_assert_irqs_disabled();
+ lockdep_sys_exit();
+}
+
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interrupt 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.: arch_exit_to_user_mode()
+ * 4) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code when syscall_exit_to_user_mode()
+ * is not suitable as the last step before returning to userspace. Must be
+ * invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+ instrumentation_begin();
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare();
+ instrumentation_end();
+
+ user_enter_irqoff();
+ arch_exit_to_user_mode();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/**
+ * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
+ * @regs: Pointer to currents pt_regs
+ *
+ * Invoked from architecture specific entry code with interrupts disabled.
+ * Can only be called when the interrupt entry came from user mode. The
+ * calling code must be non-instrumentable. When the function returns all
+ * state is correct and the subsequent functions can be instrumented.
+ *
+ * The function establishes state (lockdep, RCU (context tracking), tracing)
+ */
+void irqentry_enter_from_user_mode(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_to_user_mode - Interrupt exit work
+ * @regs: Pointer to current's pt_regs
+ *
+ * Invoked with interrupts disabled and fully valid regs. Returns with all
+ * work handled, interrupts disabled such that the caller can immediately
+ * switch to user mode. Called from architecture specific interrupt
+ * handling code.
+ *
+ * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
+ * Interrupt exit is not invoking #1 which is the syscall specific one time
+ * work.
+ */
+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 ct_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 {
+ union {
+ bool exit_rcu;
+ bool lockdep;
+ };
+} irqentry_state_t;
+#endif
+
+/**
+ * irqentry_enter - Handle state tracking on ordinary interrupt entries
+ * @regs: Pointer to pt_regs of interrupted context
+ *
+ * Invokes:
+ * - lockdep irqflag state tracking as low level ASM entry disabled
+ * interrupts.
+ *
+ * - Context tracking if the exception hit user mode.
+ *
+ * - The hardirq tracer to keep the state consistent as low level ASM
+ * entry disabled interrupts.
+ *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then ct_irq_enter() has to be
+ * invoked on entry and ct_irq_exit() on exit.
+ *
+ * Avoiding the ct_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking ct_irq_enter() without undoing it.
+ *
+ * For user mode entries irqentry_enter_from_user_mode() is invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: An opaque object that must be passed to idtentry_exit()
+ */
+irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
+ *
+ * Conditional reschedule with additional sanity checks.
+ */
+void raw_irqentry_exit_cond_resched(void);
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched
+#define irqentry_exit_cond_resched_dynamic_disabled NULL
+DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)()
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void);
+#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched()
+#endif
+#else /* CONFIG_PREEMPT_DYNAMIC */
+#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched()
+#endif /* CONFIG_PREEMPT_DYNAMIC */
+
+/**
+ * irqentry_exit - Handle return from exception that used irqentry_enter()
+ * @regs: Pointer to pt_regs (exception entry regs)
+ * @state: Return value from matching call to irqentry_enter()
+ *
+ * Depending on the return target (kernel/user) this runs the necessary
+ * preemption and work checks if possible and required and returns to
+ * the caller with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to irqentry_enter().
+ */
+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 assembly 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/Makefile b/kernel/entry/Makefile
index 095c775e001e2..d38f3a7e7396f 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -9,5 +9,6 @@ KCOV_INSTRUMENT := n
CFLAGS_REMOVE_common.o = -fstack-protector -fstack-protector-strong
CFLAGS_common.o += -fno-stack-protector
-obj-$(CONFIG_GENERIC_ENTRY) += common.o syscall_user_dispatch.o
+obj-$(CONFIG_GENERIC_IRQ_ENTRY) += common.o
+obj-$(CONFIG_GENERIC_SYSCALL) += syscall-common.o syscall_user_dispatch.o
obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK) += kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 4d890cf9a7c83..8b0ff4378a75d 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -1,84 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/context_tracking.h>
-#include <linux/entry-common.h>
+#include <linux/irq-entry-common.h>
#include <linux/resume_user_mode.h>
#include <linux/highmem.h>
#include <linux/jump_label.h>
#include <linux/kmsan.h>
#include <linux/livepatch.h>
-#include <linux/audit.h>
#include <linux/tick.h>
-#include "common.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
-static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
-{
- if (unlikely(audit_context())) {
- unsigned long args[6];
-
- syscall_get_arguments(current, regs, args);
- audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
- }
-}
-
-long syscall_trace_enter(struct pt_regs *regs, long syscall,
- 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 (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
- ret = ptrace_report_syscall_entry(regs);
- if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
- return -1L;
- }
-
- /* Do seccomp after ptrace, to catch any tracer changes. */
- if (work & SYSCALL_WORK_SECCOMP) {
- ret = __secure_computing(NULL);
- if (ret == -1L)
- return ret;
- }
-
- /* Either of the above might have changed the syscall number */
- syscall = syscall_get_nr(current, regs);
-
- if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
- trace_sys_enter(regs, syscall);
- /*
- * Probes or BPF hooks in the tracepoint may have changed the
- * system call number as well.
- */
- syscall = syscall_get_nr(current, regs);
- }
-
- syscall_enter_audit(regs, syscall);
-
- return ret ? : syscall;
-}
-
-noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
-{
- enter_from_user_mode(regs);
- instrumentation_begin();
- local_irq_enable();
- instrumentation_end();
-}
-
/* Workaround to allow gradual conversion of architecture code */
void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
@@ -128,54 +57,6 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
return ti_work;
}
-/*
- * If SYSCALL_EMU is set, then the only reason to report is when
- * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
- * instruction has been already reported in syscall_enter_from_user_mode().
- */
-static inline bool report_single_step(unsigned long work)
-{
- if (work & SYSCALL_WORK_SYSCALL_EMU)
- return false;
-
- return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
-}
-
-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 (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
- step = report_single_step(work);
- if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
- ptrace_report_syscall_exit(regs, step);
-}
-
-__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();
-}
-
noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
{
enter_from_user_mode(regs);
diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c
new file mode 100644
index 0000000000000..5bc39874b0b00
--- /dev/null
+++ b/kernel/entry/syscall-common.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/audit.h>
+#include <linux/entry-common.h>
+#include "common.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+long syscall_enter_audit(struct pt_regs *regs, long syscall,
+ unsigned long work)
+{
+ if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
+ trace_sys_enter(regs, syscall);
+ /*
+ * Probes or BPF hooks in the tracepoint may have changed the
+ * system call number as well.
+ */
+ syscall = syscall_get_nr(current, regs);
+ }
+
+ if (unlikely(audit_context())) {
+ unsigned long args[6];
+
+ syscall_get_arguments(current, regs, args);
+ audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+ }
+
+ return syscall;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+ enter_from_user_mode(regs);
+ instrumentation_begin();
+ local_irq_enable();
+ instrumentation_end();
+}
+
+/*
+ * If SYSCALL_EMU is set, then the only reason to report is when
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
+ * instruction has been already reported in syscall_enter_from_user_mode().
+ */
+static inline bool report_single_step(unsigned long work)
+{
+ if (work & SYSCALL_WORK_SYSCALL_EMU)
+ return false;
+
+ return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
+}
+
+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 (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
+ trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+ step = report_single_step(work);
+ if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
+ ptrace_report_syscall_exit(regs, step);
+}
+
+__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();
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fa9008e5d8bd6..6eddbcbc7ac6a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -66,8 +66,8 @@
#include <linux/workqueue_api.h>
#ifdef CONFIG_PREEMPT_DYNAMIC
-# ifdef CONFIG_GENERIC_ENTRY
-# include <linux/entry-common.h>
+# ifdef CONFIG_GENERIC_IRQ_ENTRY
+# include <linux/irq-entry-common.h>
# endif
#endif
@@ -8499,8 +8499,8 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write);
#ifdef CONFIG_PREEMPT_DYNAMIC
-#ifdef CONFIG_GENERIC_ENTRY
-#include <linux/entry-common.h>
+#ifdef CONFIG_GENERIC_IRQ_ENTRY
+#include <linux/irq-entry-common.h>
#endif
/*
--
2.53.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH 6.1.y 3/5] entry: Remove syscall_enter_from_user_mode_prepare()
2026-09-08 12:20 ` [PATCH 6.1.y 1/5] entry: Inline syscall_exit_to_user_mode() Sasha Levin
2026-09-08 12:20 ` [PATCH 6.1.y 2/5] entry: Split generic entry into generic exception and syscall entry Sasha Levin
@ 2026-09-08 12:20 ` Sasha Levin
2026-09-08 12:20 ` [PATCH 6.1.y 4/5] entry: Remove unused syscall argument from syscall_trace_enter() Sasha Levin
2026-09-08 12:20 ` [PATCH 6.1.y 5/5] entry: Fix seccomp bypass after ptrace with TSYNC Sasha Levin
3 siblings, 0 replies; 6+ messages in thread
From: Sasha Levin @ 2026-09-08 12:20 UTC (permalink / raw)
To: stable
Cc: Thomas Gleixner, Peter Zijlstra (Intel), Ingo Molnar,
Mathieu Desnoyers, Sasha Levin
From: Thomas Gleixner <tglx@linutronix.de>
[ Upstream commit 54a5ab56242f96555999aaa41228f77b4a76e386 ]
Open code the only user in the x86 syscall code and reduce the zoo of
functions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251027084306.652839989@linutronix.de
[ Stable: Open-code the helper in arch/x86/entry/common.c, where the
32-bit syscall entry code still resides. ]
[ sashal: Reduced backport -- upstream 54a5ab56242f9 touches 3 file(s), this
backport carries 3. Not backported here:
arch/x86/entry/syscall_32.c
This note is generated from the file lists only; see the resolution record
for the reasoning. ]
Stable-dep-of: 4a3591287fb7 ("entry: Fix seccomp bypass after ptrace with TSYNC")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/x86/entry/common.c | 3 ++-
include/linux/entry-common.h | 26 +++++---------------------
kernel/entry/syscall-common.c | 8 --------
3 files changed, 7 insertions(+), 30 deletions(-)
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 3c88bdf96e7a5..cbc335c61df1d 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -236,9 +236,10 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
* fetch EBP before invoking any of the syscall entry work
* functions.
*/
- syscall_enter_from_user_mode_prepare(regs);
+ enter_from_user_mode(regs);
instrumentation_begin();
+ local_irq_enable();
/* Fetch EBP from where the vDSO stashed it. */
if (IS_ENABLED(CONFIG_X86_64)) {
/*
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index ed08489e1d329..0d5dc199ed8ca 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -88,23 +88,6 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, long sysca
return syscall_enter_audit(regs, syscall, work);
}
-/**
- * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
- * @regs: Pointer to currents pt_regs
- *
- * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct, interrupts are enabled and the
- * subsequent functions can be instrumented.
- *
- * This handles lockdep, RCU (context tracking) and tracing state, i.e.
- * the functionality provided by enter_from_user_mode().
- *
- * This is invoked when there is extra architecture specific functionality
- * to be done between establishing state and handling user mode entry work.
- */
-void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
-
/**
* syscall_enter_from_user_mode_work - Check and handle work before invoking
* a syscall
@@ -112,8 +95,8 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
* @syscall: The syscall number
*
* Invoked from architecture specific syscall entry code with interrupts
- * enabled after invoking syscall_enter_from_user_mode_prepare() and extra
- * architecture specific work.
+ * enabled after invoking enter_from_user_mode(), enabling interrupts and
+ * extra architecture specific work.
*
* Returns: The original or a modified syscall number
*
@@ -149,8 +132,9 @@ static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *re
* function returns all state is correct, interrupts are enabled and the
* subsequent functions can be instrumented.
*
- * This is combination of syscall_enter_from_user_mode_prepare() and
- * syscall_enter_from_user_mode_work().
+ * This is the combination of enter_from_user_mode() and
+ * syscall_enter_from_user_mode_work() to be used when there is no
+ * architecture specific work to be done between the two.
*
* Returns: The original or a modified syscall number. See
* syscall_enter_from_user_mode_work() for further explanation.
diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c
index 5bc39874b0b00..1570b2f221460 100644
--- a/kernel/entry/syscall-common.c
+++ b/kernel/entry/syscall-common.c
@@ -29,14 +29,6 @@ long syscall_enter_audit(struct pt_regs *regs, long syscall,
return syscall;
}
-noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
-{
- enter_from_user_mode(regs);
- instrumentation_begin();
- local_irq_enable();
- instrumentation_end();
-}
-
/*
* If SYSCALL_EMU is set, then the only reason to report is when
* SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
--
2.53.0
^ permalink raw reply related [flat|nested] 6+ messages in thread