We need to call task_isolation_enter() from prepare_exit_to_usermode(),
so that we can both ensure we do it last before returning to
userspace, and we also are able to re-run signal handling, etc.,
if something occurs while task_isolation_enter() has interrupts
enabled. To do this we add _TIF_NOHZ to the _TIF_WORK_MASK if
we have CONFIG_TASK_ISOLATION enabled, which brings us into
prepare_exit_to_usermode() on all return to userspace. But we
don't put _TIF_NOHZ in the flags that we use to loop back and
recheck, since we don't need to loop back only because the flag
is set. Instead we unconditionally call task_isolation_enter()
at the end of the loop if any other work is done.
To make the assembly code continue to be as optimized as before,
we renumber the _TIF flags so that both _TIF_WORK_MASK and
_TIF_SYSCALL_WORK still have contiguous runs of bits in the
immediate operand for the "and" instruction, as required by the
ARM64 ISA. Since TIF_NOHZ is in both masks, it must be the
middle bit in the contiguous run that starts with the
_TIF_WORK_MASK bits and ends with the _TIF_SYSCALL_WORK bits.
We tweak syscall_trace_enter() slightly to carry the "flags"
value from current_thread_info()->flags for each of the tests,
rather than doing a volatile read from memory for each one. This
avoids a small overhead for each test, and in particular avoids
that overhead for TIF_NOHZ when TASK_ISOLATION is not enabled.
We instrument the smp_cross_call() routine so that it checks for
isolated tasks and generates a suitable warning if we are about
to disturb one of them in strict or debug mode.
Finally, add an explicit check for STRICT mode in do_mem_abort()
to handle the case of page faults.
Signed-off-by: Chris Metcalf <cmetc...@ezchip.com>
---
arch/arm64/include/asm/thread_info.h | 18 ++++++++++++------
arch/arm64/kernel/ptrace.c | 12 +++++++++---
arch/arm64/kernel/signal.c | 7 +++++--
arch/arm64/kernel/smp.c | 2 ++
arch/arm64/mm/fault.c | 4 ++++
5 files changed, 32 insertions(+), 11 deletions(-)
diff --git a/arch/arm64/include/asm/thread_info.h
b/arch/arm64/include/asm/thread_info.h
index 90c7ff233735..94a98e9e29ef 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -103,11 +103,11 @@ static inline struct thread_info
*current_thread_info(void)
#define TIF_NEED_RESCHED 1
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
-#define TIF_NOHZ 7
-#define TIF_SYSCALL_TRACE 8
-#define TIF_SYSCALL_AUDIT 9
-#define TIF_SYSCALL_TRACEPOINT 10
-#define TIF_SECCOMP 11
+#define TIF_NOHZ 4
+#define TIF_SYSCALL_TRACE 5
+#define TIF_SYSCALL_AUDIT 6
+#define TIF_SYSCALL_TRACEPOINT 7
+#define TIF_SECCOMP 8
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_FREEZE 19
#define TIF_RESTORE_SIGMASK 20
@@ -125,9 +125,15 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_32BIT (1 << TIF_32BIT)
-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+#define _TIF_WORK_LOOP_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+#ifdef CONFIG_TASK_ISOLATION
+# define _TIF_WORK_MASK (_TIF_WORK_LOOP_MASK | _TIF_NOHZ)
+#else
+# define _TIF_WORK_MASK _TIF_WORK_LOOP_MASK
+#endif
+
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
_TIF_NOHZ)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 1971f491bb90..69ed3ba81650 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -37,6 +37,7 @@
#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/elf.h>
+#include <linux/isolation.h>
#include <asm/compat.h>
#include <asm/debug-monitors.h>
@@ -1240,14 +1241,19 @@ static void tracehook_report_syscall(struct pt_regs
*regs,
asmlinkage int syscall_trace_enter(struct pt_regs *regs)
{
- /* Do the secure computing check first; failures should be fast. */
+ unsigned long work = ACCESS_ONCE(current_thread_info()->flags);
+
+ if ((work & _TIF_NOHZ) && task_isolation_check_syscall(regs->syscallno))
+ return -1;
+
+ /* Do the secure computing check early; failures should be fast. */
if (secure_computing() == -1)
return -1;
- if (test_thread_flag(TIF_SYSCALL_TRACE))
+ if (work & _TIF_SYSCALL_TRACE)
tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
- if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ if (work & _TIF_SYSCALL_TRACEPOINT)
trace_sys_enter(regs, regs->syscallno);
audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1],
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index fde59c1139a9..641c828653c7 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -25,6 +25,7 @@
#include <linux/uaccess.h>
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
+#include <linux/isolation.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
@@ -419,10 +420,12 @@ asmlinkage void prepare_exit_to_usermode(struct pt_regs
*regs,
if (thread_flags & _TIF_FOREIGN_FPSTATE)
fpsimd_restore_current_state();
+ task_isolation_enter();
+
local_irq_disable();
thread_flags = READ_ONCE(current_thread_info()->flags) &
- _TIF_WORK_MASK;
+ _TIF_WORK_LOOP_MASK;
- } while (thread_flags);
+ } while (thread_flags || !task_isolation_ready());
}
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b1adc51b2c2e..dcb3282d04a2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -37,6 +37,7 @@
#include <linux/completion.h>
#include <linux/of.h>
#include <linux/irq_work.h>
+#include <linux/isolation.h>
#include <asm/alternative.h>
#include <asm/atomic.h>
@@ -632,6 +633,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
{
trace_ipi_raise(target, ipi_types[ipinr]);
+ task_isolation_debug_cpumask(target);
__smp_cross_call(target, ipinr);
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 92ddac1e8ca2..fbc78035b2af 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -29,6 +29,7 @@
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
+#include <linux/isolation.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
@@ -466,6 +467,9 @@ asmlinkage void __exception do_mem_abort(unsigned long
addr, unsigned int esr,
const struct fault_info *inf = fault_info + (esr & 63);
struct siginfo info;
+ if (user_mode(regs))
+ task_isolation_check_exception("%s at %#lx", inf->name, addr);
+
if (!inf->fn(addr, esr, regs))
return;
--
2.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
