kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, Paul McKenney <paulmck@kernel.org>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	"Joel Fernandes (Google)" <joel@joelfernandes.org>,
	"Steven Rostedt (VMware)" <rostedt@goodmis.org>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Alexei Starovoitov <ast@kernel.org>,
	Frederic Weisbecker <frederic@kernel.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Brian Gerst <brgerst@gmail.com>, Juergen Gross <jgross@suse.com>,
	Alexandre Chartre <alexandre.chartre@oracle.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	kvm@vger.kernel.org
Subject: [RESEND][patch V3 11/23] x86/entry: Move irq flags tracing to prepare_exit_to_usermode()
Date: Fri, 20 Mar 2020 19:00:07 +0100	[thread overview]
Message-ID: <20200320180033.481570410@linutronix.de> (raw)
In-Reply-To: 20200320175956.033706968@linutronix.de

This is another step towards more C-code and less convoluted ASM.

Similar to the entry path.

 1) invoke the tracer and the preparatory lockdep step
 2) invoke context tracking which might turn off RCU
 3) invoke the final lockdep step

Annotate the code sections in exit_to_user_mode() accordingly so objtool
won't complain about the tracer and lockdep invocation.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
V3: Convert it to noinstr

V2: New patch simplifying the conversion and addressing Alex' review
    comment of redundant tracing.
---
 arch/x86/entry/common.c          |   17 +++++++++++++++++
 arch/x86/entry/entry_32.S        |   12 ++++--------
 arch/x86/entry/entry_64.S        |    4 ----
 arch/x86/entry/entry_64_compat.S |   14 +++++---------
 4 files changed, 26 insertions(+), 21 deletions(-)

--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -71,10 +71,27 @@ static __always_inline void enter_from_u
 }
 #endif
 
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall 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) Clear CPU buffers if CPU is affected by MDS and the migitation is on.
+ * 4) Tell lockdep that interrupts are enabled
+ */
 static __always_inline void exit_to_user_mode(void)
 {
+	instr_begin();
+	__trace_hardirqs_on();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instr_end();
+
 	user_enter_irqoff();
 	mds_user_clear_cpu_buffers();
+	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 
 static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -811,8 +811,7 @@ SYM_CODE_START(ret_from_fork)
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
 	call    syscall_return_slowpath
-	STACKLEAK_ERASE
-	jmp     restore_all
+	jmp     .Lsyscall_32_done
 
 	/* kernel thread */
 1:	movl	%edi, %eax
@@ -855,7 +854,7 @@ SYM_CODE_START_LOCAL(ret_from_exception)
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
 	call	prepare_exit_to_usermode
-	jmp	restore_all
+	jmp	restore_all_switch_stack
 SYM_CODE_END(ret_from_exception)
 
 SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
@@ -968,8 +967,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	STACKLEAK_ERASE
 
-/* Opportunistic SYSEXIT */
-	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	/* Opportunistic SYSEXIT */
 
 	/*
 	 * Setup entry stack - we keep the pointer in %eax and do the
@@ -1072,11 +1070,9 @@ SYM_FUNC_START(entry_INT80_32)
 	movl	%esp, %eax
 	call	do_int80_syscall_32
 .Lsyscall_32_done:
-
 	STACKLEAK_ERASE
 
-restore_all:
-	TRACE_IRQS_ON
+restore_all_switch_stack:
 	SWITCH_TO_ENTRY_STACK
 	CHECK_AND_APPLY_ESPFIX
 
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -172,8 +172,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_h
 	movq	%rsp, %rsi
 	call	do_syscall_64		/* returns with IRQs disabled */
 
-	TRACE_IRQS_ON			/* return enables interrupts */
-
 	/*
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
@@ -340,7 +338,6 @@ SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_REGS
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
-	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
 	jmp	swapgs_restore_regs_and_return_to_usermode
 
 1:
@@ -617,7 +614,6 @@ SYM_CODE_START_LOCAL(common_interrupt)
 .Lretint_user:
 	mov	%rsp,%rdi
 	call	prepare_exit_to_usermode
-	TRACE_IRQS_ON
 
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -132,8 +132,8 @@ SYM_FUNC_START(entry_SYSENTER_compat)
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
-		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
 .Lsysenter_fix_flags:
@@ -244,8 +244,8 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_aft
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
-		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
@@ -254,7 +254,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_aft
 	 * stack. So let's erase the thread stack right now.
 	 */
 	STACKLEAK_ERASE
-	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+
 	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
 	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
 	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
@@ -393,9 +393,5 @@ SYM_CODE_START(entry_INT80_compat)
 
 	movq	%rsp, %rdi
 	call	do_int80_syscall_32
-.Lsyscall_32_done:
-
-	/* Go back to user mode. */
-	TRACE_IRQS_ON
 	jmp	swapgs_restore_regs_and_return_to_usermode
 SYM_CODE_END(entry_INT80_compat)


  parent reply	other threads:[~2020-03-20 22:06 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-20 17:59 [RESEND][patch V3 00/23] x86/entry: Consolidation part II (syscalls) Thomas Gleixner
2020-03-20 17:59 ` [RESEND][patch V3 01/23] rcu: Dont acquire lock in NMI handler in rcu_nmi_enter_common() Thomas Gleixner
2020-03-24 15:37   ` [patch " Frederic Weisbecker
2020-03-20 17:59 ` [RESEND][patch V3 02/23] rcu: Add comments marking transitions between RCU watching and not Thomas Gleixner
2020-03-24 15:38   ` [patch " Frederic Weisbecker
2020-03-20 17:59 ` [RESEND][patch V3 03/23] vmlinux.lds.h: Create section for protection against instrumentation Thomas Gleixner
2020-03-24 12:26   ` Borislav Petkov
2020-04-03  8:08   ` Alexandre Chartre
2020-03-20 18:00 ` [RESEND][patch V3 04/23] kprobes: Prevent probes in .noinstr.text section Thomas Gleixner
2020-03-23 14:00   ` [patch " Masami Hiramatsu
2020-03-23 16:03     ` Thomas Gleixner
2020-03-24  5:49       ` Masami Hiramatsu
2020-03-24  9:47         ` Thomas Gleixner
2020-03-25 13:39           ` Masami Hiramatsu
2020-03-20 18:00 ` [RESEND][patch V3 05/23] tracing: Provide lockdep less trace_hardirqs_on/off() variants Thomas Gleixner
2020-04-03  8:34   ` Alexandre Chartre
2020-03-20 18:00 ` [RESEND][patch V3 06/23] bug: Annotate WARN/BUG/stackfail as noinstr safe Thomas Gleixner
2020-04-02 21:01   ` Josh Poimboeuf
2020-04-02 21:34     ` Peter Zijlstra
2020-04-02 21:43       ` Josh Poimboeuf
2020-04-02 21:49     ` Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 07/23] lockdep: Prepare for noinstr sections Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 08/23] x86/entry: Mark enter_from_user_mode() noinstr Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 09/23] x86/entry/common: Protect against instrumentation Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 10/23] x86/entry: Move irq tracing on syscall entry to C-code Thomas Gleixner
2020-03-20 18:00 ` Thomas Gleixner [this message]
2020-03-20 18:00 ` [RESEND][patch V3 12/23] context_tracking: Ensure that the critical path cannot be instrumented Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 13/23] lib/smp_processor_id: Move it into noinstr section Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 14/23] x86/speculation/mds: Mark mds_user_clear_cpu_buffers() __always_inline Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 15/23] x86/entry/64: Check IF in __preempt_enable_notrace() thunk Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 16/23] x86/entry/64: Mark ___preempt_schedule_notrace() thunk noinstr Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 17/23] rcu/tree: Mark the idle relevant functions noinstr Thomas Gleixner
2020-03-24 16:09   ` Paul E. McKenney
2020-03-24 19:28     ` Thomas Gleixner
2020-03-24 19:58       ` Paul E. McKenney
2020-03-20 18:00 ` [RESEND][patch V3 18/23] x86/kvm: Move context tracking where it belongs Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 19/23] x86/kvm/vmx: Add hardirq tracing to guest enter/exit Thomas Gleixner
2020-03-24 23:03   ` Peter Zijlstra
2020-03-24 23:21     ` Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 20/23] x86/kvm/svm: Handle hardirqs proper on " Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 21/23] context_tracking: Make guest_enter/exit_irqoff() .noinstr ready Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 22/23] x86/kvm/vmx: Move guest enter/exit into .noinstr.text Thomas Gleixner
2020-03-20 18:00 ` [RESEND][patch V3 23/23] x86/kvm/svm: " Thomas Gleixner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200320180033.481570410@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=alexandre.chartre@oracle.com \
    --cc=ast@kernel.org \
    --cc=brgerst@gmail.com \
    --cc=frederic@kernel.org \
    --cc=jgross@suse.com \
    --cc=joel@joelfernandes.org \
    --cc=jpoimboe@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=thomas.lendacky@amd.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).