[PATCH v4 09/13] task_isolation: arch/arm: enable task isolation functionality

[Alex Belits <abelits@marvell.com>]

From: Francis Giraldeau <francis.giraldeau@gmail.com>

This patch is a port of the task isolation functionality to the arm 32-bit
architecture. The task isolation needs an additional thread flag that
requires to change the entry assembly code to accept a bitfield larger than
one byte. The constants _TIF_SYSCALL_WORK and _TIF_WORK_MASK are now
defined in the literal pool. The rest of the patch is straightforward and
reflects what is done on other architectures.

To avoid problems with the tst instruction in the v7m build, we renumber
TIF_SECCOMP to bit 8 and let TIF_TASK_ISOLATION use bit 7.

Early kernel entry relies on task_isolation_kernel_enter().

vector_swi to label __sys_trace
  -> syscall_trace_enter() when task isolation is enabled,
  -> task_isolation_kernel_enter()

nvic_handle_irq()
  -> handle_IRQ() -> __handle_domain_irq() -> task_isolation_kernel_enter()

__fiq_svc, __fiq_abt __fiq_usr
  -> handle_fiq_as_nmi() -> uses nmi_enter() / nmi_exit()

__irq_svc -> irq_handler
__irq_usr -> irq_handler
  irq_handler
    -> (handle_arch_irq or
    (arch_irq_handler_default -> (asm_do_IRQ() -> __handle_domain_irq())
      or do_IPI() -> handle_IPI())
  asm_do_IRQ()
    -> __handle_domain_irq() -> task_isolation_kernel_enter()
  do_IPI()
    -> handle_IPI() -> task_isolation_kernel_enter()

handle_arch_irq for arm-specific controllers calls
  (handle_IRQ() -> __handle_domain_irq() -> task_isolation_kernel_enter())
    or (handle_domain_irq() -> __handle_domain_irq()
      -> task_isolation_kernel_enter())

Not covered:
__dabt_svc -> dabt_helper
__dabt_usr -> dabt_helper
  dabt_helper -> CPU_DABORT_HANDLER (cpu-specific)
    -> do_DataAbort or PROCESSOR_DABT_FUNC
    -> _data_abort (cpu-specific) -> do_DataAbort

__pabt_svc -> pabt_helper
__pabt_usr -> pabt_helper
  pabt_helper -> CPU_PABORT_HANDLER (cpu-specific)
    -> do_PrefetchAbort or PROCESSOR_PABT_FUNC
    -> _prefetch_abort (cpu-specific) -> do_PrefetchAbort

Signed-off-by: Francis Giraldeau <francis.giraldeau@gmail.com>
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com> [with modifications]
[abelits@marvell.com: modified for kernel 5.6, added isolation cleanup]
Signed-off-by: Alex Belits <abelits@marvell.com>
---
 arch/arm/Kconfig                   |  1 +
 arch/arm/include/asm/barrier.h     |  2 ++
 arch/arm/include/asm/thread_info.h | 10 +++++++---
 arch/arm/kernel/entry-common.S     | 15 ++++++++++-----
 arch/arm/kernel/ptrace.c           | 12 ++++++++++++
 arch/arm/kernel/signal.c           | 13 ++++++++++++-
 arch/arm/kernel/smp.c              |  6 ++++++
 arch/arm/mm/fault.c                |  8 +++++++-
 8 files changed, 57 insertions(+), 10 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2ac74904a3ce..f06d0e0e4fe9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -67,6 +67,7 @@ config ARM
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
+	select HAVE_ARCH_TASK_ISOLATION
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARM_SMCCC if CPU_V7
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 83ae97c049d9..3c603df6c290 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -66,12 +66,14 @@ extern void arm_heavy_mb(void);
 #define wmb()		__arm_heavy_mb(st)
 #define dma_rmb()	dmb(osh)
 #define dma_wmb()	dmb(oshst)
+#define instr_sync()	isb()
 #else
 #define mb()		barrier()
 #define rmb()		barrier()
 #define wmb()		barrier()
 #define dma_rmb()	barrier()
 #define dma_wmb()	barrier()
+#define instr_sync()	barrier()
 #endif
 
 #define __smp_mb()	dmb(ish)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 3609a6980c34..ec0f11e1bb4c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -139,7 +139,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define TIF_SYSCALL_TRACE	4	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+#define TIF_TASK_ISOLATION	7	/* task isolation enabled for task */
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
 
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
@@ -152,18 +153,21 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_TASK_ISOLATION	(1 << TIF_TASK_ISOLATION)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_USING_IWMMXT	(1 << TIF_USING_IWMMXT)
 
 /* Checks for any syscall work in entry-common.S */
 #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-			   _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+			   _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
+			   _TIF_TASK_ISOLATION)
 
 /*
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_TASK_ISOLATION)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 271cb8a1eba1..6ceb5cb808a9 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -53,7 +53,8 @@ __ret_fast_syscall:
 	cmp	r2, #TASK_SIZE
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	ldr	r2, =_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, r2
 	bne	fast_work_pending
 
 
@@ -90,7 +91,8 @@ __ret_fast_syscall:
 	cmp	r2, #TASK_SIZE
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	ldr	r2, =_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, r2
 	beq	no_work_pending
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
@@ -98,7 +100,8 @@ ENDPROC(ret_fast_syscall)
 	/* Slower path - fall through to work_pending */
 #endif
 
-	tst	r1, #_TIF_SYSCALL_WORK
+	ldr	r2, =_TIF_SYSCALL_WORK
+	tst	r1, r2
 	bne	__sys_trace_return_nosave
 slow_work_pending:
 	mov	r0, sp				@ 'regs'
@@ -131,7 +134,8 @@ ENTRY(ret_to_user_from_irq)
 	cmp	r2, #TASK_SIZE
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]
-	tst	r1, #_TIF_WORK_MASK
+	ldr	r2, =_TIF_WORK_MASK
+	tst	r1, r2
 	bne	slow_work_pending
 no_work_pending:
 	asm_trace_hardirqs_on save = 0
@@ -251,7 +255,8 @@ local_restart:
 	ldr	r10, [tsk, #TI_FLAGS]		@ check for syscall tracing
 	stmdb	sp!, {r4, r5}			@ push fifth and sixth args
 
-	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
+	ldr	r11, =_TIF_SYSCALL_WORK		@ are we tracing syscalls?
+	tst	r10, r11
 	bne	__sys_trace
 
 	invoke_syscall tbl, scno, r10, __ret_fast_syscall
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index d0f7c8896c96..7b4fe15ba376 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -24,6 +24,7 @@
 #include <linux/audit.h>
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
+#include <linux/isolation.h>
 
 #include <asm/traps.h>
 
@@ -917,9 +918,20 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 {
 	current_thread_info()->syscall = scno;
 
+	task_isolation_kernel_enter();
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 
+	/*
+	 * In task isolation mode, we may prevent the syscall from
+	 * running, and if so we also deliver a signal to the process.
+	 */
+	if (test_thread_flag(TIF_TASK_ISOLATION)) {
+		if (task_isolation_syscall(scno) == -1)
+			return -1;
+	}
+
 	/* Do seccomp after ptrace; syscall may have changed. */
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 	if (secure_computing() == -1)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab2568996ddb..29ccef8403cd 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -12,6 +12,7 @@
 #include <linux/tracehook.h>
 #include <linux/uprobes.h>
 #include <linux/syscalls.h>
+#include <linux/isolation.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -639,6 +640,9 @@ static int do_signal(struct pt_regs *regs, int syscall)
 	return 0;
 }
 
+#define WORK_PENDING_LOOP_FLAGS	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |	\
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+
 asmlinkage int
 do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
@@ -648,6 +652,9 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	 * Update the trace code with the current status.
 	 */
 	trace_hardirqs_off();
+
+	task_isolation_check_run_cleanup();
+
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
@@ -676,7 +683,11 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 		}
 		local_irq_disable();
 		thread_flags = current_thread_info()->flags;
-	} while (thread_flags & _TIF_WORK_MASK);
+	} while (thread_flags & WORK_PENDING_LOOP_FLAGS);
+
+	if (thread_flags & _TIF_TASK_ISOLATION)
+		task_isolation_start();
+
 	return 0;
 }
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 9a6432557871..6a7a4ba02cc4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -26,6 +26,7 @@
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
 #include <linux/irq_work.h>
+#include <linux/isolation.h>
 
 #include <linux/atomic.h>
 #include <asm/bugs.h>
@@ -559,6 +560,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 {
+	task_isolation_remote_cpumask(mask, "wakeup IPI");
 	smp_cross_call(mask, IPI_WAKEUP);
 }
 
@@ -578,6 +580,7 @@ void arch_irq_work_raise(void)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 void tick_broadcast(const struct cpumask *mask)
 {
+	task_isolation_remote_cpumask(mask, "timer IPI");
 	smp_cross_call(mask, IPI_TIMER);
 }
 #endif
@@ -633,6 +636,8 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	unsigned int cpu = smp_processor_id();
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
+	task_isolation_kernel_enter();
+
 	if ((unsigned)ipinr < NR_IPI) {
 		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
@@ -701,6 +706,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 void smp_send_reschedule(int cpu)
 {
+	task_isolation_remote(cpu, "reschedule IPI");
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c6550eddfce1..23bb383e479e 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/sched/debug.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/isolation.h>
 
 #include <asm/system_misc.h>
 #include <asm/system_info.h>
@@ -330,8 +331,13 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR
 	 */
-	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
+	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
+			      VM_FAULT_BADACCESS)))) {
+		/* No signal was generated, but notify task-isolation tasks. */
+		if (user_mode(regs))
+			task_isolation_interrupt("page fault at %#lx", addr);
 		return 0;
+	}
 
 	/*
 	 * If we are in kernel mode at this point, we
-- 
2.26.2