Message-ID: <20241025100700.3714552-20-ruanjinjie@huawei.com>
Date: Fri, 25 Oct 2024 18:07:00 +0800
From: Jinjie Ruan <ruanjinjie@...wei.com>
To: <oleg@...hat.com>, <linux@...linux.org.uk>, <will@...nel.org>,
	<mark.rutland@....com>, <catalin.marinas@....com>, <sstabellini@...nel.org>,
	<maz@...nel.org>, <tglx@...utronix.de>, <peterz@...radead.org>,
	<luto@...nel.org>, <kees@...nel.org>, <wad@...omium.org>,
	<akpm@...ux-foundation.org>, <samitolvanen@...gle.com>, <arnd@...db.de>,
	<ojeda@...nel.org>, <rppt@...nel.org>, <hca@...ux.ibm.com>,
	<aliceryhl@...gle.com>, <samuel.holland@...ive.com>, <paulmck@...nel.org>,
	<aquini@...hat.com>, <petr.pavlu@...e.com>, <ruanjinjie@...wei.com>,
	<viro@...iv.linux.org.uk>, <rmk+kernel@...linux.org.uk>, <ardb@...nel.org>,
	<wangkefeng.wang@...wei.com>, <surenb@...gle.com>,
	<linus.walleij@...aro.org>, <yangyj.ee@...il.com>, <broonie@...nel.org>,
	<mbenes@...e.cz>, <puranjay@...nel.org>, <pcc@...gle.com>,
	<guohanjun@...wei.com>, <sudeep.holla@....com>,
	<Jonathan.Cameron@...wei.com>, <prarit@...hat.com>, <liuwei09@...tc.cn>,
	<dwmw@...zon.co.uk>, <oliver.upton@...ux.dev>, <kristina.martsenko@....com>,
	<ptosi@...gle.com>, <frederic@...nel.org>, <vschneid@...hat.com>,
	<thiago.bauermann@...aro.org>, <joey.gouly@....com>,
	<liuyuntao12@...wei.com>, <leobras@...hat.com>,
	<linux-kernel@...r.kernel.org>, <linux-arm-kernel@...ts.infradead.org>,
	<xen-devel@...ts.xenproject.org>
Subject: [PATCH -next v4 19/19] arm64: entry: Convert to generic entry

Currently, x86, Riscv, Loongarch use the generic entry. Convert arm64
to use the generic entry infrastructure from kernel/entry/*.
The generic entry makes maintainers' work easier and codes more elegant.

The changes are below:
 - Remove TIF_SYSCALL_* flag, _TIF_WORK_MASK, _TIF_SYSCALL_WORK
 - Remove syscall_trace_enter/exit() and use generic identical functions.

Tested ok with following test cases on Qemu cortex-a53 and HiSilicon
Kunpeng-920:
 - Perf tests.
 - Different `dynamic preempt` mode switch.
 - Pseudo NMI tests.
 - Stress-ng CPU stress test.
 - MTE test case in Documentation/arch/arm64/memory-tagging-extension.rst
   and all test cases in tools/testing/selftests/arm64/mte/* (Only Qemu).

Suggested-by: Mark Rutland <mark.rutland@....com>
Signed-off-by: Jinjie Ruan <ruanjinjie@...wei.com>
---
 arch/arm64/Kconfig                    |   2 +-
 arch/arm64/include/asm/entry-common.h |  85 ++++++++++++++++++++++
 arch/arm64/include/asm/syscall.h      |   6 +-
 arch/arm64/include/asm/thread_info.h  |  23 +-----
 arch/arm64/kernel/ptrace.c            | 101 --------------------------
 arch/arm64/kernel/signal.c            |   2 +-
 arch/arm64/kernel/syscall.c           |  18 +++--
 7 files changed, 103 insertions(+), 134 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4545017cfd01..89d46d0fb18b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -146,7 +146,7 @@ config ARM64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
-	select GENERIC_IRQ_ENTRY
+	select GENERIC_ENTRY
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IOREMAP
 	select GENERIC_IRQ_IPI
diff --git a/arch/arm64/include/asm/entry-common.h b/arch/arm64/include/asm/entry-common.h
index 1cc9d966a6c3..04a31b4fc4fd 100644
--- a/arch/arm64/include/asm/entry-common.h
+++ b/arch/arm64/include/asm/entry-common.h
@@ -10,6 +10,11 @@
 #include <asm/mte.h>
 #include <asm/stacktrace.h>
 
+enum ptrace_syscall_dir {
+	PTRACE_SYSCALL_ENTER = 0,
+	PTRACE_SYSCALL_EXIT,
+};
+
 #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_MTE_ASYNC_FAULT | _TIF_FOREIGN_FPSTATE)
 
 static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
@@ -61,4 +66,84 @@ static inline bool arch_irqentry_exit_need_resched(void)
 
 #define arch_irqentry_exit_need_resched arch_irqentry_exit_need_resched
 
+static inline unsigned long arch_pre_report_syscall_entry(struct pt_regs *regs)
+{
+	unsigned long saved_reg;
+	int regno;
+
+	/*
+	 * We have some ABI weirdness here in the way that we handle syscall
+	 * exit stops because we indicate whether or not the stop has been
+	 * signalled from syscall entry or syscall exit by clobbering a general
+	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+	 * and restoring its old value after the stop. This means that:
+	 *
+	 * - Any writes by the tracer to this register during the stop are
+	 *   ignored/discarded.
+	 *
+	 * - The actual value of the register is not available during the stop,
+	 *   so the tracer cannot save it and restore it later.
+	 *
+	 * - Syscall stops behave differently to seccomp and pseudo-step traps
+	 *   (the latter do not nobble any registers).
+	 */
+	regno = (is_compat_task() ? 12 : 7);
+	saved_reg = regs->regs[regno];
+	regs->regs[regno] = PTRACE_SYSCALL_ENTER;
+
+	return saved_reg;
+}
+
+#define arch_pre_report_syscall_entry arch_pre_report_syscall_entry
+
+static inline void arch_post_report_syscall_entry(struct pt_regs *regs,
+						  unsigned long saved_reg, long ret)
+{
+	int regno = (is_compat_task() ? 12 : 7);
+
+	if (ret)
+		forget_syscall(regs);
+
+	regs->regs[regno] = saved_reg;
+}
+
+#define arch_post_report_syscall_entry arch_post_report_syscall_entry
+
+static inline unsigned long arch_pre_report_syscall_exit(struct pt_regs *regs,
+							 unsigned long work)
+{
+	unsigned long saved_reg;
+	int regno;
+
+	/* See comment for arch_pre_report_syscall_entry() */
+	regno = (is_compat_task() ? 12 : 7);
+	saved_reg = regs->regs[regno];
+	regs->regs[regno] = PTRACE_SYSCALL_EXIT;
+
+	if (report_single_step(work)) {
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		regs->regs[regno] = saved_reg;
+	}
+
+	return saved_reg;
+}
+
+#define arch_pre_report_syscall_exit arch_pre_report_syscall_exit
+
+static inline void arch_post_report_syscall_exit(struct pt_regs *regs,
+						 unsigned long saved_reg,
+						 unsigned long work)
+{
+	int regno = (is_compat_task() ? 12 : 7);
+
+	if (!report_single_step(work))
+		regs->regs[regno] = saved_reg;
+}
+
+#define arch_post_report_syscall_exit arch_post_report_syscall_exit
+
 #endif /* _ASM_ARM64_ENTRY_COMMON_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ab8e14b96f68..9891b15da4c3 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -85,7 +85,9 @@ static inline int syscall_get_arch(struct task_struct *task)
 	return AUDIT_ARCH_AARCH64;
 }
 
-int syscall_trace_enter(struct pt_regs *regs);
-void syscall_trace_exit(struct pt_regs *regs);
+static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+	return false;
+}
 
 #endif	/* __ASM_SYSCALL_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 1114c1c3300a..543fdb00d713 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -43,6 +43,7 @@ struct thread_info {
 	void			*scs_sp;
 #endif
 	u32			cpu;
+	unsigned long		syscall_work;   /* SYSCALL_WORK_ flags */
 };
 
 #define thread_saved_pc(tsk)	\
@@ -64,11 +65,6 @@ void arch_setup_new_exec(void);
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_MTE_ASYNC_FAULT	5	/* MTE Asynchronous Tag Check Fault */
 #define TIF_NOTIFY_SIGNAL	6	/* signal notifications exist */
-#define TIF_SYSCALL_TRACE	8	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
-#define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
-#define TIF_SECCOMP		11	/* syscall secure computing */
-#define TIF_SYSCALL_EMU		12	/* syscall emulation active */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
@@ -87,28 +83,13 @@ void arch_setup_new_exec(void);
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
-#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
-#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
-#define _TIF_UPROBE		(1 << TIF_UPROBE)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_UPROBE            (1 << TIF_UPROBE)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 #define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_TSC_SIGSEGV	(1 << TIF_TSC_SIGSEGV)
 
-#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
-				 _TIF_NOTIFY_SIGNAL)
-
-#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
-				 _TIF_SYSCALL_EMU)
-
 #ifdef CONFIG_SHADOW_CALL_STACK
 #define INIT_SCS							\
 	.scs_base	= init_shadow_call_stack,			\
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6ea303ab9e22..0f642ed4dbe4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -42,9 +42,6 @@
 #include <asm/traps.h>
 #include <asm/system_misc.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
 struct pt_regs_offset {
 	const char *name;
 	int offset;
@@ -2285,104 +2282,6 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ptrace_request(child, request, addr, data);
 }
 
-enum ptrace_syscall_dir {
-	PTRACE_SYSCALL_ENTER = 0,
-	PTRACE_SYSCALL_EXIT,
-};
-
-static void report_syscall_enter(struct pt_regs *regs)
-{
-	int regno;
-	unsigned long saved_reg;
-
-	/*
-	 * We have some ABI weirdness here in the way that we handle syscall
-	 * exit stops because we indicate whether or not the stop has been
-	 * signalled from syscall entry or syscall exit by clobbering a general
-	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
-	 * and restoring its old value after the stop. This means that:
-	 *
-	 * - Any writes by the tracer to this register during the stop are
-	 *   ignored/discarded.
-	 *
-	 * - The actual value of the register is not available during the stop,
-	 *   so the tracer cannot save it and restore it later.
-	 *
-	 * - Syscall stops behave differently to seccomp and pseudo-step traps
-	 *   (the latter do not nobble any registers).
-	 */
-	regno = (is_compat_task() ? 12 : 7);
-	saved_reg = regs->regs[regno];
-	regs->regs[regno] = PTRACE_SYSCALL_ENTER;
-
-	if (ptrace_report_syscall_entry(regs))
-		forget_syscall(regs);
-	regs->regs[regno] = saved_reg;
-}
-
-static void report_syscall_exit(struct pt_regs *regs)
-{
-	int regno;
-	unsigned long saved_reg;
-
-	/* See comment for report_syscall_enter() */
-	regno = (is_compat_task() ? 12 : 7);
-	saved_reg = regs->regs[regno];
-	regs->regs[regno] = PTRACE_SYSCALL_EXIT;
-
-	if (!test_thread_flag(TIF_SINGLESTEP)) {
-		ptrace_report_syscall_exit(regs, 0);
-		regs->regs[regno] = saved_reg;
-	} else {
-		regs->regs[regno] = saved_reg;
-
-		/*
-		 * Signal a pseudo-step exception since we are stepping but
-		 * tracer modifications to the registers may have rewound the
-		 * state machine.
-		 */
-		ptrace_report_syscall_exit(regs, 1);
-	}
-}
-
-int syscall_trace_enter(struct pt_regs *regs)
-{
-	unsigned long flags = read_thread_flags();
-
-	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
-		report_syscall_enter(regs);
-		if (flags & _TIF_SYSCALL_EMU)
-			return NO_SYSCALL;
-	}
-
-	/* Do the secure computing after ptrace; failures should be fast. */
-	if (secure_computing() == -1)
-		return NO_SYSCALL;
-
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
-		trace_sys_enter(regs, regs->syscallno);
-
-	audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1],
-			    regs->regs[2], regs->regs[3]);
-
-	return regs->syscallno;
-}
-
-void syscall_trace_exit(struct pt_regs *regs)
-{
-	unsigned long flags = read_thread_flags();
-
-	audit_syscall_exit(regs);
-
-	if (flags & _TIF_SYSCALL_TRACEPOINT)
-		trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
-	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
-		report_syscall_exit(regs);
-
-	rseq_syscall(regs);
-}
-
 /*
  * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a.
  * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 04b20c2f6cda..4965cb80e67e 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -8,8 +8,8 @@
 
 #include <linux/cache.h>
 #include <linux/compat.h>
+#include <linux/entry-common.h>
 #include <linux/errno.h>
-#include <linux/irq-entry-common.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/freezer.h>
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index c442fcec6b9e..ea818e3d597b 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -2,6 +2,7 @@
 
 #include <linux/compiler.h>
 #include <linux/context_tracking.h>
+#include <linux/entry-common.h>
 #include <linux/errno.h>
 #include <linux/nospec.h>
 #include <linux/ptrace.h>
@@ -65,14 +66,15 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 	choose_random_kstack_offset(get_random_u16());
 }
 
-static inline bool has_syscall_work(unsigned long flags)
+static inline bool has_syscall_work(unsigned long work)
 {
-	return unlikely(flags & _TIF_SYSCALL_WORK);
+	return unlikely(work & SYSCALL_WORK_ENTER);
 }
 
 static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 			   const syscall_fn_t syscall_table[])
 {
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 	unsigned long flags = read_thread_flags();
 
 	regs->orig_x0 = regs->regs[0];
@@ -106,7 +108,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		return;
 	}
 
-	if (has_syscall_work(flags)) {
+	if (has_syscall_work(work)) {
 		/*
 		 * The de-facto standard way to skip a system call using ptrace
 		 * is to set the system call to -1 (NO_SYSCALL) and set x0 to a
@@ -124,7 +126,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		 */
 		if (scno == NO_SYSCALL)
 			syscall_set_return_value(current, regs, -ENOSYS, 0);
-		scno = syscall_trace_enter(regs);
+		scno = syscall_trace_enter(regs, regs->syscallno, work);
 		if (scno == NO_SYSCALL)
 			goto trace_exit;
 	}
@@ -136,14 +138,14 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	 * check again. However, if we were tracing entry, then we always trace
 	 * exit regardless, as the old entry assembly did.
 	 */
-	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
-		flags = read_thread_flags();
-		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
+	if (!has_syscall_work(work) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
+		work = READ_ONCE(current_thread_info()->syscall_work);
+		if (!has_syscall_work(work) && !report_single_step(work))
 			return;
 	}
 
 trace_exit:
-	syscall_trace_exit(regs);
+	syscall_exit_work(regs, work);
 }
 
 void do_el0_svc(struct pt_regs *regs)
-- 
2.34.1

Powered by blists - more mailing lists