From: Chris Metcalf <cmetcalf@mellanox.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@mellanox.com>
Subject: [PATCH v12 10/13] arch/x86: enable task isolation functionality
Date: Tue, 5 Apr 2016 13:38:39 -0400
Message-ID: <1459877922-15512-11-git-send-email-cmetcalf@mellanox.com>
In-Reply-To: <1459877922-15512-1-git-send-email-cmetcalf@mellanox.com>
References: <1459877922-15512-1-git-send-email-cmetcalf@mellanox.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 05 Apr 2016 17:39:31.5824
 (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: HE1PR05MB1531
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 5558
Lines: 150

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

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@mellanox.com>
---
 arch/x86/Kconfig                   |  1 +
 arch/x86/entry/common.c            | 18 +++++++++++++++++-
 arch/x86/include/asm/thread_info.h |  2 ++
 arch/x86/kernel/traps.c            |  2 ++
 arch/x86/mm/fault.c                |  2 ++
 5 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2dc18605831f..760401ba3df0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,6 +89,7 @@ config X86
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY		if X86_64
+	select HAVE_ARCH_TASK_ISOLATION
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_BPF_JIT			if X86_64
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index e79d93d44ecd..31dfe4ff8915 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>
@@ -87,6 +88,13 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 
 	work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
+	/* In isolation mode, we may prevent the syscall from running. */
+	if (work & _TIF_TASK_ISOLATION) {
+		if (task_isolation_syscall(regs->orig_ax) == -1)
+			return -1;
+		work &= ~_TIF_TASK_ISOLATION;
+	}
+
 #ifdef CONFIG_SECCOMP
 	/*
 	 * Do seccomp first -- it should minimize exposure of other
@@ -202,7 +210,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS				\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
+	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_TASK_ISOLATION)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
@@ -236,11 +244,19 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
 			fire_user_return_notifiers();
 
+		if (cached_flags & _TIF_TASK_ISOLATION)
+			task_isolation_enter();
+
 		/* Disable IRQs and retry */
 		local_irq_disable();
 
 		cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags);
 
+		/* Clear task isolation from cached_flags manually. */
+		if ((cached_flags & _TIF_TASK_ISOLATION) &&
+		    task_isolation_ready())
+			cached_flags &= ~_TIF_TASK_ISOLATION;
+
 		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 			break;
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 82866697fcf1..057176ae597f 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -97,6 +97,7 @@ struct thread_info {
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
+#define TIF_TASK_ISOLATION	13	/* task isolation enabled for task */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -121,6 +122,7 @@ struct thread_info {
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_TASK_ISOLATION	(1 << TIF_TASK_ISOLATION)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 06cbe25861f1..b02205085571 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>
@@ -382,6 +383,7 @@ 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_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 5ce1ed02f7e8..025e9d2850c1 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_exception	*/
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -1259,6 +1260,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		local_irq_enable();
 		error_code |= PF_USER;
 		flags |= FAULT_FLAG_USER;
+		task_isolation_exception("page fault at %#lx", address);
 	} else {
 		if (regs->flags & X86_EFLAGS_IF)
 			local_irq_enable();
-- 
2.7.2