[PATCH v16 08/13] arch/x86: enable task isolation functionality

[Chris Metcalf <cmetcalf@mellanox.com>]

In prepare_exit_to_usermode(), call task_isolation_start() for
TIF_TASK_ISOLATION tasks.

In syscall_trace_enter_phase1(), add the necessary support for
reporting syscalls for task-isolation processes.

Add task_isolation_remote() calls 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            | 14 ++++++++++++++
 arch/x86/include/asm/apic.h        |  3 +++
 arch/x86/include/asm/thread_info.h |  8 +++++---
 arch/x86/kernel/smp.c              |  2 ++
 arch/x86/kernel/traps.c            |  3 +++
 arch/x86/mm/fault.c                |  5 +++++
 7 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 971feac13506..45967840b81a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -114,6 +114,7 @@ config X86
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
 	select HAVE_ARCH_COMPAT_MMAP_BASES	if MMU && COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TASK_ISOLATION
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 03505ffbe1b6..2c70b915d1f2 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -24,6 +24,7 @@
 #include <linux/uprobes.h>
 #include <linux/livepatch.h>
 #include <linux/syscalls.h>
+#include <linux/isolation.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -87,6 +88,16 @@ static long syscall_trace_enter(struct pt_regs *regs)
 	if (emulated)
 		return -1L;
 
+	/*
+	 * In task isolation mode, we may prevent the syscall from
+	 * running, and if so we also deliver a signal to the process.
+	 */
+	if (work & _TIF_TASK_ISOLATION) {
+		if (task_isolation_syscall(regs->orig_ax) == -1)
+			return -1L;
+		work &= ~_TIF_TASK_ISOLATION;
+	}
+
 #ifdef CONFIG_SECCOMP
 	/*
 	 * Do seccomp after ptrace, to catch any tracer changes.
@@ -196,6 +207,9 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 		exit_to_usermode_loop(regs, cached_flags);
 
+	if (cached_flags & _TIF_TASK_ISOLATION)
+		task_isolation_start();
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 5f01671c68f2..c70cb9cacfc0 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
+#include <linux/isolation.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
@@ -618,6 +619,7 @@ extern void irq_exit(void);
 
 static inline void entering_irq(void)
 {
+	task_isolation_interrupt("irq");
 	irq_enter();
 }
 
@@ -629,6 +631,7 @@ static inline void entering_ack_irq(void)
 
 static inline void ipi_entering_ack_irq(void)
 {
+	task_isolation_interrupt("ack irq");
 	irq_enter();
 	ack_APIC_irq();
 }
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89e7eeb5cec1..aa9d9d817f8b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -85,6 +85,7 @@ struct thread_info {
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING	13	/* pending live patching update */
+#define TIF_TASK_ISOLATION	14	/* task isolation enabled for task */
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
@@ -111,6 +112,7 @@ struct thread_info {
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
+#define _TIF_TASK_ISOLATION	(1 << TIF_TASK_ISOLATION)
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
@@ -132,15 +134,15 @@ struct thread_info {
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
 	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT |	\
-	 _TIF_NOHZ)
+	 _TIF_NOHZ | _TIF_TASK_ISOLATION)
 
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK						\
 	(_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING |	\
 	 _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU |	\
 	 _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE |	\
-	 _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT |	\
-	 _TIF_FSCHECK)
+	 _TIF_PATCH_PENDING | _TIF_TASK_ISOLATION | _TIF_NOHZ |		\
+	 _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ | _TIF_FSCHECK)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 5c574dff4c1a..73bc58029292 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/gfp.h>
+#include <linux/isolation.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
@@ -128,6 +129,7 @@ static void native_smp_send_reschedule(int cpu)
 		WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
 		return;
 	}
+	task_isolation_remote(cpu, "reschedule IPI");
 	apic->send_IPI(cpu, RESCHEDULE_VECTOR);
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 67db4f43309e..a48ebfc7b98c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -37,6 +37,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/isolation.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
@@ -467,6 +468,8 @@ 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;
+		/* No signal was generated, but notify task-isolation tasks. */
+		task_isolation_interrupt("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 e2baeaa053a5..bd479142e3ca 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -15,6 +15,7 @@
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
+#include <linux/isolation.h>		/* task_isolation_interrupt	*/
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -1486,6 +1487,10 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
 	}
 
+	/* No signal was generated, but notify task-isolation tasks. */
+	if (flags & PF_USER)
+		task_isolation_interrupt("page fault at %#lx", address);
+
 	check_v8086_mode(regs, address, tsk);
 }
 NOKPROBE_SYMBOL(__do_page_fault);
-- 
2.1.2