From: Chris Metcalf <cmetcalf@mellanox.com>
To: Gilad Ben Yossef <giladb@ezchip.com>, Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@kernel.org>, Peter Zijlstra <peterz@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Rik van Riel" <riel@redhat.com>, Tejun Heo <tj@kernel.org>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        Christoph Lameter <cl@linux.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Andy Lutomirski <luto@amacapital.net>, <linux-kernel@vger.kernel.org>
CC: Chris Metcalf <cmetcalf@mellanox.com>
Subject: [PATCH v12 11/13] arch/tile: enable task isolation functionality
Date: Tue, 5 Apr 2016 13:38:40 -0400
Message-ID: <1459877922-15512-12-git-send-email-cmetcalf@mellanox.com>
In-Reply-To: <1459877922-15512-1-git-send-email-cmetcalf@mellanox.com>
References: <1459877922-15512-1-git-send-email-cmetcalf@mellanox.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 05 Apr 2016 17:39:35.5058
 (UTC)
X-MS-Exchange-CrossTenant-Id: a652971c-7d2e-4d9b-a6a4-d149256f461b
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=a652971c-7d2e-4d9b-a6a4-d149256f461b;Ip=[12.216.194.146];Helo=[ld-1.internal.tilera.com]
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM4PR05MB1684
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 9281
Lines: 287

We add the necessary call to task_isolation_enter() in the
prepare_exit_to_usermode() routine.  We already unconditionally
call into this routine if TIF_NOHZ is set, since that's where
we do the user_enter() call.

We add calls to task_isolation_check_exception() in places
where exceptions may not generate signals to the application.

Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
---
 arch/tile/Kconfig                   |  1 +
 arch/tile/include/asm/thread_info.h |  4 +++-
 arch/tile/kernel/process.c          |  9 +++++++++
 arch/tile/kernel/ptrace.c           |  7 +++++++
 arch/tile/kernel/single_step.c      |  5 +++++
 arch/tile/kernel/smp.c              | 28 ++++++++++++++++------------
 arch/tile/kernel/unaligned.c        |  3 +++
 arch/tile/mm/fault.c                |  3 +++
 arch/tile/mm/homecache.c            |  2 ++
 9 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 81719302b056..322ba76c8631 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -33,6 +33,7 @@ config TILE
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TASK_ISOLATION
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 4b7cef9e94e0..ea7fbd0d879d 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -126,6 +126,7 @@ extern void _cpu_idle(void);
 #define TIF_SYSCALL_TRACEPOINT	9	/* syscall tracepoint instrumentation */
 #define TIF_POLLING_NRFLAG	10	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_NOHZ		11	/* in adaptive nohz mode */
+#define TIF_TASK_ISOLATION	12	/* in task isolation mode */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -139,11 +140,12 @@ extern void _cpu_idle(void);
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
+#define _TIF_TASK_ISOLATION	(1<<TIF_TASK_ISOLATION)
 
 /* Work to do as we loop to exit to user space. */
 #define _TIF_WORK_MASK \
 	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
-	 _TIF_ASYNC_TLB | _TIF_NOTIFY_RESUME)
+	 _TIF_ASYNC_TLB | _TIF_NOTIFY_RESUME | _TIF_TASK_ISOLATION)
 
 /* Work to do on any return to user space. */
 #define _TIF_ALLWORK_MASK \
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index b5f30d376ce1..e752f6c2b645 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/signal.h>
 #include <linux/delay.h>
 #include <linux/context_tracking.h>
+#include <linux/isolation.h>
 #include <asm/stack.h>
 #include <asm/switch_to.h>
 #include <asm/homecache.h>
@@ -495,9 +496,17 @@ void prepare_exit_to_usermode(struct pt_regs *regs, u32 thread_info_flags)
 			tracehook_notify_resume(regs);
 		}
 
+		if (thread_info_flags & _TIF_TASK_ISOLATION)
+			task_isolation_enter();
+
 		local_irq_disable();
 		thread_info_flags = READ_ONCE(current_thread_info()->flags);
 
+		/* Clear task isolation from cached_flags manually. */
+		if ((thread_info_flags & _TIF_TASK_ISOLATION) &&
+		    task_isolation_ready())
+			thread_info_flags &= ~_TIF_TASK_ISOLATION;
+
 	} while (thread_info_flags & _TIF_WORK_MASK);
 
 	if (thread_info_flags & _TIF_SINGLESTEP) {
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index 54e7b723db99..475a362415fb 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -23,6 +23,7 @@
 #include <linux/elf.h>
 #include <linux/tracehook.h>
 #include <linux/context_tracking.h>
+#include <linux/isolation.h>
 #include <asm/traps.h>
 #include <arch/chip.h>
 
@@ -255,6 +256,12 @@ int do_syscall_trace_enter(struct pt_regs *regs)
 {
 	u32 work = ACCESS_ONCE(current_thread_info()->flags);
 
+	/* In isolation mode, we may prevent the syscall from running. */
+	if (work & _TIF_TASK_ISOLATION) {
+		if (task_isolation_syscall(regs->regs[TREG_SYSCALL_NR]) == -1)
+			return -1;
+	}
+
 	if (secure_computing() == -1)
 		return -1;
 
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 862973074bf9..3baa7230149e 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/err.h>
 #include <linux/prctl.h>
+#include <linux/isolation.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -320,6 +321,8 @@ void single_step_once(struct pt_regs *regs)
 	int size = 0, sign_ext = 0;  /* happy compiler */
 	int align_ctl;
 
+	task_isolation_exception("single step at %#lx", regs->pc);
+
 	align_ctl = unaligned_fixup;
 	switch (task_thread_info(current)->align_ctl) {
 	case PR_UNALIGN_NOPRINT:
@@ -767,6 +770,8 @@ void single_step_once(struct pt_regs *regs)
 	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
 
+	task_isolation_exception("single step at %#lx", regs->pc);
+
 	*ss_pc = regs->pc;
 	control |= SPR_SINGLE_STEP_CONTROL_1__CANCELED_MASK;
 	control |= SPR_SINGLE_STEP_CONTROL_1__INHIBIT_MASK;
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index 07e3ff5cc740..da1eb240fc57 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/irq.h>
 #include <linux/irq_work.h>
 #include <linux/module.h>
+#include <linux/isolation.h>
 #include <asm/cacheflush.h>
 #include <asm/homecache.h>
 
@@ -67,6 +68,7 @@ void send_IPI_single(int cpu, int tag)
 		.x = cpu % smp_width,
 		.state = HV_TO_BE_SENT
 	};
+	task_isolation_debug(cpu);
 	__send_IPI_many(&recip, 1, tag);
 }
 
@@ -84,6 +86,7 @@ void send_IPI_many(const struct cpumask *mask, int tag)
 		r->x = cpu % smp_width;
 		r->state = HV_TO_BE_SENT;
 	}
+	task_isolation_debug_cpumask(mask);
 	__send_IPI_many(recip, nrecip, tag);
 }
 
@@ -181,10 +184,11 @@ void flush_icache_range(unsigned long start, unsigned long end)
 	struct ipi_flush flush = { start, end };
 
 	/* If invoked with irqs disabled, we can not issue IPIs. */
-	if (irqs_disabled())
+	if (irqs_disabled()) {
+		task_isolation_debug_cpumask(task_isolation_map);
 		flush_remote(0, HV_FLUSH_EVICT_L1I, NULL, 0, 0, 0,
 			NULL, NULL, 0);
-	else {
+	} else {
 		preempt_disable();
 		on_each_cpu(ipi_flush_icache_range, &flush, 1);
 		preempt_enable();
@@ -258,10 +262,8 @@ void __init ipi_init(void)
 
 #if CHIP_HAS_IPI()
 
-void smp_send_reschedule(int cpu)
+static void __smp_send_reschedule(int cpu)
 {
-	WARN_ON(cpu_is_offline(cpu));
-
 	/*
 	 * We just want to do an MMIO store.  The traditional writeq()
 	 * functions aren't really correct here, since they're always
@@ -273,15 +275,17 @@ void smp_send_reschedule(int cpu)
 
 #else
 
-void smp_send_reschedule(int cpu)
+static void __smp_send_reschedule(int cpu)
 {
-	HV_Coord coord;
-
-	WARN_ON(cpu_is_offline(cpu));
-
-	coord.y = cpu_y(cpu);
-	coord.x = cpu_x(cpu);
+	HV_Coord coord = { .y = cpu_y(cpu), .x = cpu_x(cpu) };
 	hv_trigger_ipi(coord, IRQ_RESCHEDULE);
 }
 
 #endif /* CHIP_HAS_IPI() */
+
+void smp_send_reschedule(int cpu)
+{
+	WARN_ON(cpu_is_offline(cpu));
+	task_isolation_debug(cpu);
+	__smp_send_reschedule(cpu);
+}
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 0db5f7c9d9e5..754204987532 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/compat.h>
 #include <linux/prctl.h>
+#include <linux/isolation.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -1545,6 +1546,8 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 		return;
 	}
 
+	task_isolation_exception("unaligned JIT at %#lx", regs->pc);
+
 	if (!info->unalign_jit_base) {
 		void __user *user_page;
 
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 26734214818c..7f910e4061f1 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -35,6 +35,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/isolation.h>
 
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
@@ -844,6 +845,8 @@ static inline void __do_page_fault(struct pt_regs *regs, int fault_num,
 void do_page_fault(struct pt_regs *regs, int fault_num,
 		   unsigned long address, unsigned long write)
 {
+	task_isolation_exception("page fault interrupt %d at %#lx (%#lx)",
+				       fault_num, regs->pc, address);
 	__do_page_fault(regs, fault_num, address, write);
 }
 
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 40ca30a9fee3..e044e8dd8372 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -31,6 +31,7 @@
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/hugetlb.h>
+#include <linux/isolation.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -83,6 +84,7 @@ static void hv_flush_update(const struct cpumask *cache_cpumask,
 	 * Don't bother to update atomically; losing a count
 	 * here is not that critical.
 	 */
+	task_isolation_debug_cpumask(&mask);
 	for_each_cpu(cpu, &mask)
 		++per_cpu(irq_stat, cpu).irq_hv_flush_count;
 }
-- 
2.7.2