[PATCH v4 07/13] task_isolation: arch/x86: enable task isolation functionality

[Alex Belits <abelits@marvell.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(), 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.

Add task_isolation_kernel_enter() calls to interrupt and syscall
entry handlers.

This mechanism relies on calls to functions that call
task_isolation_kernel_enter() early after entry into kernel. Those
functions are:

enter_from_user_mode()
  called from do_syscall_64(), do_int80_syscall_32(),
  do_fast_syscall_32(), idtentry_enter_user(),
  idtentry_enter_cond_rcu()
idtentry_enter_cond_rcu()
  called from non-raw IDT macros and other entry points
idtentry_enter_user()
nmi_enter()
xen_call_function_interrupt()
xen_call_function_single_interrupt()
xen_irq_work_interrupt()

Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
[abelits@marvell.com: adapted for kernel 5.8]
Signed-off-by: Alex Belits <abelits@marvell.com>
---
 arch/x86/Kconfig                   |  1 +
 arch/x86/entry/common.c            | 20 +++++++++++++++++++-
 arch/x86/include/asm/barrier.h     |  2 ++
 arch/x86/include/asm/thread_info.h |  4 +++-
 arch/x86/kernel/apic/ipi.c         |  2 ++
 arch/x86/mm/fault.c                |  4 ++++
 arch/x86/xen/smp.c                 |  3 +++
 arch/x86/xen/smp_pv.c              |  2 ++
 8 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 883da0abf779..3a80142f85c8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -149,6 +149,7 @@ 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 f09288431f28..ab94d90a2bd5 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>
 
 #ifdef CONFIG_XEN_PV
 #include <xen/xen-ops.h>
@@ -86,6 +87,7 @@ static noinstr void enter_from_user_mode(void)
 {
 	enum ctx_state state = ct_state();
 
+	task_isolation_kernel_enter();
 	lockdep_hardirqs_off(CALLER_ADDR0);
 	user_exit_irqoff();
 
@@ -97,6 +99,7 @@ static noinstr void enter_from_user_mode(void)
 #else
 static __always_inline void enter_from_user_mode(void)
 {
+	task_isolation_kernel_enter();
 	lockdep_hardirqs_off(CALLER_ADDR0);
 	instrumentation_begin();
 	trace_hardirqs_off_finish();
@@ -161,6 +164,15 @@ 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.
@@ -263,6 +275,8 @@ static 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))
@@ -278,6 +292,9 @@ static 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
@@ -597,7 +614,8 @@ bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 		check_user_regs(regs);
 		enter_from_user_mode();
 		return false;
-	}
+	} else
+		task_isolation_kernel_enter();
 
 	/*
 	 * If this entry hit the idle task invoke rcu_irq_enter() whether
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7f828fe49797..5be6ca0519fc 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -4,6 +4,7 @@
 
 #include <asm/alternative.h>
 #include <asm/nops.h>
+#include <asm/processor.h>
 
 /*
  * Force strict CPU ordering.
@@ -53,6 +54,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 
 #define dma_rmb()	barrier()
 #define dma_wmb()	barrier()
+#define instr_sync()	sync_core()
 
 #ifdef CONFIG_X86_32
 #define __smp_mb()	asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc")
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8de8ceccb8bc..6dd1a5cc286d 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -93,6 +93,7 @@ struct thread_info {
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_SLD			18	/* Restore split lock detection on context switch */
+#define TIF_TASK_ISOLATION	19	/* task isolation enabled for task */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -123,6 +124,7 @@ struct thread_info {
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_SLD		(1 << TIF_SLD)
+#define _TIF_TASK_ISOLATION	(1 << TIF_TASK_ISOLATION)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
@@ -136,7 +138,7 @@ struct thread_info {
 /* Work to do before invoking the actual syscall. */
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
-	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | _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 1ead568c0101..e16a4f5c7e57 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, ...		*/
@@ -1332,6 +1333,9 @@ 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);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 2097fa0ebdb5..9a3a9bae7d06 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -4,6 +4,7 @@
 #include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
+#include <linux/isolation.h>
 
 #include <xen/events.h>
 
@@ -265,6 +266,7 @@ void xen_send_IPI_allbutself(int vector)
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 {
+	task_isolation_kernel_enter();
 	irq_enter();
 	generic_smp_call_function_interrupt();
 	inc_irq_stat(irq_call_count);
@@ -275,6 +277,7 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
 {
+	task_isolation_kernel_enter();
 	irq_enter();
 	generic_smp_call_function_single_interrupt();
 	inc_irq_stat(irq_call_count);
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 171aff1b11f2..d71d3cc36c51 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -24,6 +24,7 @@
 #include <linux/cpuhotplug.h>
 #include <linux/stackprotector.h>
 #include <linux/pgtable.h>
+#include <linux/isolation.h>
 
 #include <asm/paravirt.h>
 #include <asm/idtentry.h>
@@ -482,6 +483,7 @@ static void xen_pv_stop_other_cpus(int wait)
 
 static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
 {
+	task_isolation_kernel_enter();
 	irq_enter();
 	irq_work_run();
 	inc_irq_stat(apic_irq_work_irqs);
-- 
2.26.2