[PATCH 06/13] task_isolation: arch/x86: enable task isolation functionality

[Alex Belits <abelits@marvell.com>]

From: Chris Metcalf <cmetcalf@mellanox.com>

In prepare_exit_to_usermode(), run cleanup for tasks exited fromi
isolation and call task_isolation_start() for tasks that entered
TIF_TASK_ISOLATION.

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.

Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
[abelits@marvell.com: adapted for kernel 5.6]
Signed-off-by: Alex Belits <abelits@marvell.com>
---
 arch/x86/Kconfig                   |  1 +
 arch/x86/entry/common.c            | 15 +++++++++++++++
 arch/x86/include/asm/apic.h        |  3 +++
 arch/x86/include/asm/thread_info.h |  4 +++-
 arch/x86/kernel/apic/ipi.c         |  2 ++
 arch/x86/mm/fault.c                |  4 ++++
 6 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index beea77046f9b..9ea6d3e6e77d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -144,6 +144,7 @@ config X86
 	select HAVE_ARCH_COMPAT_MMAP_BASES	if MMU && COMPAT
 	select HAVE_ARCH_PREL32_RELOCATIONS
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TASK_ISOLATION
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 9747876980b5..ba8cd75dc7cf 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -26,6 +26,7 @@
 #include <linux/livepatch.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/isolation.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -86,6 +87,15 @@ static long syscall_trace_enter(struct pt_regs *regs)
 			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.
@@ -189,6 +199,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	lockdep_assert_irqs_disabled();
 	lockdep_sys_exit();
 
+	task_isolation_check_run_cleanup();
+
 	cached_flags = READ_ONCE(ti->flags);
 
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
@@ -204,6 +216,9 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
 
+	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 19e94af9cc5d..71149abbb0a0 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
+#include <linux/isolation.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
@@ -524,6 +525,7 @@ extern void irq_exit(void);
 
 static inline void entering_irq(void)
 {
+	task_isolation_interrupt("irq");
 	irq_enter();
 	kvm_set_cpu_l1tf_flush_l1d();
 }
@@ -536,6 +538,7 @@ 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();
 	kvm_set_cpu_l1tf_flush_l1d();
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index cf4327986e98..60d107f784ee 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -92,6 +92,7 @@ struct thread_info {
 #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 */
+#define TIF_TASK_ISOLATION	18	/* task isolation enabled for task */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
@@ -122,6 +123,7 @@ struct thread_info {
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_TASK_ISOLATION	(1 << TIF_TASK_ISOLATION)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
@@ -140,7 +142,7 @@ 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)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE					\
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 6ca0f91372fd..b4dfaad6a440 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -2,6 +2,7 @@
 
 #include <linux/cpumask.h>
 #include <linux/smp.h>
+#include <linux/isolation.h>
 
 #include "local.h"
 
@@ -67,6 +68,7 @@ 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/mm/fault.c b/arch/x86/mm/fault.c
index fa4ea09593ab..2175a8655a7d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_recover_from_page_fault()*/
 #include <linux/mm_types.h>
+#include <linux/isolation.h>		/* task_isolation_interrupt     */
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -1483,6 +1484,9 @@ void do_user_addr_fault(struct pt_regs *regs,
 		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
 	}
 
+	/* No signal was generated, but notify task-isolation tasks. */
+	task_isolation_interrupt("page fault at %#lx", address);
+
 	check_v8086_mode(regs, address, tsk);
 }
 NOKPROBE_SYMBOL(do_user_addr_fault);
-- 
2.20.1