From: Chris Metcalf <cmetcalf@ezchip.com>
To: Gilad Ben Yossef <giladb@ezchip.com>, Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@kernel.org>, Peter Zijlstra <peterz@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Rik van Riel" <riel@redhat.com>, Tejun Heo <tj@kernel.org>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        Christoph Lameter <cl@linux.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Andy Lutomirski <luto@amacapital.net>,
        "H. Peter Anvin" <hpa@zytor.com>, <x86@kernel.org>,
        <linux-kernel@vger.kernel.org>
CC: Chris Metcalf <cmetcalf@ezchip.com>
Subject: [PATCH v10 09/12] arch/x86: enable task isolation functionality
Date: Wed, 2 Mar 2016 15:09:33 -0500
Message-ID: <1456949376-4910-10-git-send-email-cmetcalf@ezchip.com>
In-Reply-To: <1456949376-4910-1-git-send-email-cmetcalf@ezchip.com>
References: <1456949376-4910-1-git-send-email-cmetcalf@ezchip.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 02 Mar 2016 20:10:29.7573
 (UTC)
X-MS-Exchange-CrossTenant-Id: a652971c-7d2e-4d9b-a6a4-d149256f461b
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=a652971c-7d2e-4d9b-a6a4-d149256f461b;Ip=[12.216.194.146];Helo=[ld-1.internal.tilera.com]
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: HE1PR05MB1689
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 3939
Lines: 120

In prepare_exit_to_usermode(), call task_isolation_ready()
when we are checking the thread-info flags, and after we've handled
the other work, call task_isolation_enter() unconditionally.

In syscall_trace_enter_phase1(), we add the necessary support for
strict-mode detection of syscalls.

We add strict reporting for the kernel exception types that do
not result in signals, namely non-signalling page faults and
non-signalling MPX fixups.

Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com>
---
 arch/x86/entry/common.c | 18 ++++++++++++++++--
 arch/x86/kernel/traps.c |  2 ++
 arch/x86/mm/fault.c     |  2 ++
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 03663740c866..27c71165416b 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -21,6 +21,7 @@
 #include <linux/context_tracking.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/isolation.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -91,6 +92,10 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 	 */
 	if (work & _TIF_NOHZ) {
 		enter_from_user_mode();
+		if (task_isolation_check_syscall(regs->orig_ax)) {
+			regs->orig_ax = -1;
+			return 0;
+		}
 		work &= ~_TIF_NOHZ;
 	}
 #endif
@@ -254,17 +259,26 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
 			fire_user_return_notifiers();
 
+		task_isolation_enter();
+
 		/* Disable IRQs and retry */
 		local_irq_disable();
 
 		cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags);
 
-		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS) &&
+		    task_isolation_ready())
 			break;
 
 	}
 }
 
+#ifdef CONFIG_TASK_ISOLATION
+# define EXIT_TO_USERMODE_FLAGS (EXIT_TO_USERMODE_LOOP_FLAGS | _TIF_NOHZ)
+#else
+# define EXIT_TO_USERMODE_FLAGS EXIT_TO_USERMODE_LOOP_FLAGS
+#endif
+
 /* Called with IRQs disabled. */
 __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 {
@@ -278,7 +292,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	cached_flags =
 		READ_ONCE(pt_regs_to_thread_info(regs)->flags);
 
-	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+	if (unlikely(cached_flags & EXIT_TO_USERMODE_FLAGS))
 		exit_to_usermode_loop(regs, cached_flags);
 
 	user_enter();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ade185a46b1d..82bf53ec1e98 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/isolation.h>
 
 #ifdef CONFIG_EISA
 #include <linux/ioport.h>
@@ -398,6 +399,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	case 2:	/* Bound directory has invalid entry. */
 		if (mpx_handle_bd_fault())
 			goto exit_trap;
+		task_isolation_check_exception("bounds check");
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
 		info = mpx_generate_siginfo(regs);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e830c71a1323..e2b42bc79d81 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
+#include <linux/isolation.h>		/* task_isolation_check_exception */
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -1155,6 +1156,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		local_irq_enable();
 		error_code |= PF_USER;
 		flags |= FAULT_FLAG_USER;
+		task_isolation_check_exception("page fault at %#lx", address);
 	} else {
 		if (regs->flags & X86_EFLAGS_IF)
 			local_irq_enable();
-- 
2.1.2