All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andy Lutomirski <luto@kernel.org>
To: x86@kernel.org
Cc: linux-kernel@vger.kernel.org, "Brian Gerst" <brgerst@gmail.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Frédéric Weisbecker" <fweisbec@gmail.com>,
	"Denys Vlasenko" <dvlasenk@redhat.com>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Andy Lutomirski" <luto@kernel.org>
Subject: [PATCH 12/12] x86/entry: Do enter_from_user_mode with IRQs off
Date: Mon,  7 Dec 2015 13:51:37 -0800	[thread overview]
Message-ID: <ef7dbc96d144821ea99ba49d9ef7145f835ac3ed.1449522077.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1449522077.git.luto@kernel.org>
In-Reply-To: <cover.1449522077.git.luto@kernel.org>

Now that slow-path syscalls always enter C before enabling
interrupts, it's straightforward to do enter_from_user_mode before
enabling interrupts rather than doing it as part of entry tracing.

With this change, we should finally be able to retire
exception_enter.

This will also enable optimizations based on knowing that we never
change context tracking state with interrupts on.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/entry/common.c            | 39 ++++++++++++++------------------------
 arch/x86/include/asm/thread_info.h |  5 ++++-
 2 files changed, 18 insertions(+), 26 deletions(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index b8a848f80b2a..016ac47c954b 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -37,14 +37,17 @@ static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
 	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
 }
 
-#ifdef CONFIG_CONTEXT_TRACKING
+#ifndef CONFIG_CONTEXT_TRACKING
+static
+#else
+__visible
+#endif
 /* Called on entry from user mode with IRQs off. */
-__visible void enter_from_user_mode(void)
+void enter_from_user_mode(void)
 {
 	CT_WARN_ON(ct_state() != CONTEXT_USER);
 	user_exit();
 }
-#endif
 
 static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
 {
@@ -84,17 +87,6 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 
 	work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
-#ifdef CONFIG_CONTEXT_TRACKING
-	/*
-	 * If TIF_NOHZ is set, we are required to call user_exit() before
-	 * doing anything that could touch RCU.
-	 */
-	if (work & _TIF_NOHZ) {
-		enter_from_user_mode();
-		work &= ~_TIF_NOHZ;
-	}
-#endif
-
 #ifdef CONFIG_SECCOMP
 	/*
 	 * Do seccomp first -- it should minimize exposure of other
@@ -350,6 +342,7 @@ __visible void do_syscall_64(struct pt_regs *regs)
 	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	unsigned long nr = regs->orig_ax;
 
+	enter_from_user_mode();
 	local_irq_enable();
 
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
@@ -372,9 +365,9 @@ __visible void do_syscall_64(struct pt_regs *regs)
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 /*
- * Does a 32-bit syscall.  Called with IRQs on and does all entry and
- * exit work and returns with IRQs off.  This function is extremely hot
- * in workloads that use it, and it's usually called from
+ * Does a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.  Does
+ * all entry and exit work and returns with IRQs off.  This function is
+ * extremely hot in workloads that use it, and it's usually called from
  * do_fast_syscall_32, so forcibly inline it to improve performance.
  */
 static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
@@ -415,6 +408,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 /* Handles int $0x80 */
 __visible void do_int80_syscall_32(struct pt_regs *regs)
 {
+	enter_from_user_mode();
 	local_irq_enable();
 	do_syscall_32_irqs_on(regs);
 }
@@ -437,11 +431,9 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 	 */
 	regs->ip = landing_pad;
 
-	/*
-	 * Fetch ECX from where the vDSO stashed it.
-	 *
-	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
-	 */
+	enter_from_user_mode();
+
+	/* Fetch ECX from where the vDSO stashed it. */
 	local_irq_enable();
 	if (
 #ifdef CONFIG_X86_64
@@ -460,9 +452,6 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 		/* User code screwed up. */
 		local_irq_disable();
 		regs->ax = -EFAULT;
-#ifdef CONFIG_CONTEXT_TRACKING
-		enter_from_user_mode();
-#endif
 		prepare_exit_to_usermode(regs);
 		return 0;	/* Keep it simple: use IRET. */
 	}
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a1ecd214d227..ae210d6159d3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -136,7 +136,10 @@ struct thread_info {
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
 #define _TIF_X32		(1 << TIF_X32)
 
-/* work to do in syscall_trace_enter() */
+/*
+ * work to do in syscall_trace_enter().  Also includes TIF_NOHZ for
+ * enter_from_user_mode()
+ */
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
 	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT |	\
-- 
2.5.0


  parent reply	other threads:[~2015-12-07 21:52 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-07 21:51 [PATCH 00/12] x86: Rewrite 64-bit syscall code Andy Lutomirski
2015-12-07 21:51 ` [PATCH 01/12] selftests/x86: Extend Makefile to allow 64-bit only tests Andy Lutomirski
2015-12-08  9:34   ` Borislav Petkov
2015-12-09 18:55     ` Andy Lutomirski
2015-12-09 19:11   ` Shuah Khan
2015-12-09 19:22     ` Andy Lutomirski
2015-12-09 19:58       ` Shuah Khan
2015-12-07 21:51 ` [PATCH 02/12] selftests/x86: Add check_initial_reg_state Andy Lutomirski
2015-12-08  9:54   ` Borislav Petkov
2015-12-09 18:56     ` Andy Lutomirski
2015-12-09 19:09       ` Borislav Petkov
2015-12-09 19:20         ` Andy Lutomirski
2015-12-09 19:28           ` Borislav Petkov
2015-12-07 21:51 ` [PATCH 03/12] x86/syscalls: Refactor syscalltbl.sh Andy Lutomirski
2015-12-07 21:51 ` [PATCH 04/12] x86/syscalls: Remove __SYSCALL_COMMON and __SYSCALL_X32 Andy Lutomirski
2015-12-07 21:51 ` [PATCH 05/12] x86/syscalls: Move compat syscall entry handling into syscalltbl.sh Andy Lutomirski
2015-12-07 21:51 ` [PATCH 06/12] x86/syscalls: Add syscall entry qualifiers Andy Lutomirski
2015-12-07 21:51 ` [PATCH 07/12] x86/entry/64: Always run ptregs-using syscalls on the slow path Andy Lutomirski
2015-12-08  0:50   ` Brian Gerst
2015-12-08  0:54     ` Brian Gerst
2015-12-08  1:12       ` Andy Lutomirski
2015-12-08 13:07         ` Brian Gerst
2015-12-08 18:56           ` Ingo Molnar
2015-12-08 21:51             ` Andy Lutomirski
2015-12-09  4:43   ` Brian Gerst
2015-12-09  5:45     ` Andy Lutomirski
2015-12-09  6:21       ` Andy Lutomirski
2015-12-09 12:52         ` Brian Gerst
2015-12-09 13:02         ` [PATCH] x86/entry/64: Remove duplicate syscall table for fast path Brian Gerst
2015-12-09 18:53           ` Andy Lutomirski
2015-12-09 21:08             ` Brian Gerst
2015-12-09 21:15               ` Andy Lutomirski
2015-12-09 23:50                 ` Andy Lutomirski
2015-12-10  5:42                   ` Brian Gerst
2015-12-10  5:54                     ` Andy Lutomirski
2015-12-09 19:30           ` Andy Lutomirski
2015-12-07 21:51 ` [PATCH 08/12] x86/entry/64: Call all native slow-path syscalls with full pt-regs Andy Lutomirski
2015-12-07 21:51 ` [PATCH 09/12] x86/entry/64: Stop using int_ret_from_sys_call in ret_from_fork Andy Lutomirski
2015-12-07 21:51 ` [PATCH 10/12] x86/entry/64: Migrate the 64-bit syscall slow path to C Andy Lutomirski
2015-12-07 21:51 ` [PATCH 11/12] x86/entry/32: Change INT80 to be an interrupt gate Andy Lutomirski
2016-04-01  1:45   ` Rusty Russell
2016-04-01  7:40     ` [tip:x86/urgent] lguest, x86/entry/32: Fix handling of guest syscalls using interrupt gates tip-bot for Rusty Russell
2015-12-07 21:51 ` Andy Lutomirski [this message]
2015-12-07 22:55 ` [PATCH 00/12] x86: Rewrite 64-bit syscall code Andy Lutomirski
2015-12-08  4:42   ` Ingo Molnar
2015-12-08  5:42     ` Andy Lutomirski
2015-12-08  7:00       ` Ingo Molnar

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=ef7dbc96d144821ea99ba49d9ef7145f835ac3ed.1449522077.git.luto@kernel.org \
    --to=luto@kernel.org \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=dvlasenk@redhat.com \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.