Merge Linus master into drm-next

The merge is clean, but the arm build fails afterwards,
due to API changes in the regulator tree.

I've included the patch into the merge to fix the build.

Signed-off-by: Dave Airlie <airlied@redhat.com>

27 files changed, 228 insertions, 100 deletions

diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 7cca41842a9e..a07e31b50d3f 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -27,6 +27,7 @@ config TILE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DEBUG_STACKOVERFLOW
 	select ARCH_WANT_FRAME_POINTERS
+	select HAVE_CONTEXT_TRACKING
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
@@ -147,6 +148,11 @@ config ARCH_DEFCONFIG
 	default "arch/tile/configs/tilepro_defconfig" if !TILEGX
 	default "arch/tile/configs/tilegx_defconfig" if TILEGX
 
+config PGTABLE_LEVELS
+	int
+	default 3 if 64BIT
+	default 2
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c
index 6f00e9850636..ee186e13dfe6 100644
--- a/arch/tile/gxio/mpipe.c
+++ b/arch/tile/gxio/mpipe.c
@@ -456,7 +456,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 EXPORT_SYMBOL_GPL(gxio_mpipe_equeue_init);
 
 int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context,
-			     const struct timespec *ts)
+			     const struct timespec64 *ts)
 {
 	cycles_t cycles = get_cycles();
 	return gxio_mpipe_set_timestamp_aux(context, (uint64_t)ts->tv_sec,
@@ -466,7 +466,7 @@ int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context,
 EXPORT_SYMBOL_GPL(gxio_mpipe_set_timestamp);
 
 int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context,
-			     struct timespec *ts)
+			     struct timespec64 *ts)
 {
 	int ret;
 	cycles_t cycles_prev, cycles_now, clock_rate;
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index b4c488b65745..f5433e0e34e0 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
-generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/tile/include/asm/ftrace.h b/arch/tile/include/asm/ftrace.h
index 13a9bb81a8ab..738d239b792f 100644
--- a/arch/tile/include/asm/ftrace.h
+++ b/arch/tile/include/asm/ftrace.h
@@ -23,6 +23,8 @@
 #ifndef __ASSEMBLY__
 extern void __mcount(void);
 
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
diff --git a/arch/tile/include/asm/irq_work.h b/arch/tile/include/asm/irq_work.h
new file mode 100644
index 000000000000..48af33a61a2c
--- /dev/null
+++ b/arch/tile/include/asm/irq_work.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+#ifdef CONFIG_SMP
+	extern bool self_interrupt_ok;
+	return self_interrupt_ok;
+#else
+	return false;
+#endif
+}
+
+#endif /* __ASM_IRQ_WORK_H */
diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h
index 9a326b64f7ae..735e7f144733 100644
--- a/arch/tile/include/asm/smp.h
+++ b/arch/tile/include/asm/smp.h
@@ -69,6 +69,7 @@ static inline int xy_to_cpu(int x, int y)
 #define MSG_TAG_STOP_CPU		2
 #define MSG_TAG_CALL_FUNCTION_MANY	3
 #define MSG_TAG_CALL_FUNCTION_SINGLE	4
+#define MSG_TAG_IRQ_WORK		5
 
 /* Hook for the generic smp_call_function_many() routine. */
 static inline void arch_send_call_function_ipi_mask(struct cpumask *mask)
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 96c14c1430d8..f804c39a5e4d 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -26,7 +26,6 @@
  */
 struct thread_info {
 	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
 	unsigned long		flags;		/* low level flags */
 	unsigned long		status;		/* thread-synchronous flags */
 	__u32			homecache_cpu;	/* CPU we are homecached on */
@@ -51,7 +50,6 @@ struct thread_info {
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,			\
-	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
@@ -126,6 +124,7 @@ extern void _cpu_idle(void);
 #define TIF_NOTIFY_RESUME	8	/* callback before returning to user */
 #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_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -138,14 +137,16 @@ extern void _cpu_idle(void);
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_NOHZ		(1<<TIF_NOHZ)
 
 /* Work to do on any return to user space. */
 #define _TIF_ALLWORK_MASK \
-  (_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SINGLESTEP|\
-   _TIF_ASYNC_TLB|_TIF_NOTIFY_RESUME)
+	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_SINGLESTEP | \
+	 _TIF_ASYNC_TLB | _TIF_NOTIFY_RESUME | _TIF_NOHZ)
 
 /* Work to do at syscall entry. */
-#define _TIF_SYSCALL_ENTRY_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_ENTRY_WORK \
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
 
 /* Work to do at syscall exit. */
 #define _TIF_SYSCALL_EXIT_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT)
diff --git a/arch/tile/include/gxio/mpipe.h b/arch/tile/include/gxio/mpipe.h
index e37cf4f0cffd..73e83a187866 100644
--- a/arch/tile/include/gxio/mpipe.h
+++ b/arch/tile/include/gxio/mpipe.h
@@ -1830,7 +1830,7 @@ extern int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr,
  *  code.
  */
 extern int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context,
-				    struct timespec *ts);
+				    struct timespec64 *ts);
 
 /* Set the timestamp of mPIPE.
  *
@@ -1840,7 +1840,7 @@ extern int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context,
  *  code.
  */
 extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context,
-				    const struct timespec *ts);
+				    const struct timespec64 *ts);
 
 /* Adjust the timestamp of mPIPE.
  *
diff --git a/arch/tile/include/hv/hypervisor.h b/arch/tile/include/hv/hypervisor.h
index dfcdeb61ba34..e0e6af4e783b 100644
--- a/arch/tile/include/hv/hypervisor.h
+++ b/arch/tile/include/hv/hypervisor.h
@@ -961,7 +961,11 @@ typedef enum {
   HV_INQ_TILES_HFH_CACHE       = 2,
 
   /** The set of tiles that can be legally used as a LOTAR for a PTE. */
-  HV_INQ_TILES_LOTAR           = 3
+  HV_INQ_TILES_LOTAR           = 3,
+
+  /** The set of "shared" driver tiles that the hypervisor may
+   *  periodically interrupt. */
+  HV_INQ_TILES_SHARED          = 4
 } HV_InqTileSet;
 
 /** Returns specific information about various sets of tiles within the
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 8c5abf2e4794..e8c2c04143cd 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -68,7 +68,7 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr
 	if (from->si_code < 0) {
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr);
+		err |= __put_user(from->si_int, &to->si_int);
 	} else {
 		/*
 		 * First 32bits of unions are always present:
@@ -93,8 +93,7 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr
 			break;
 		case __SI_TIMER >> 16:
 			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(ptr_to_compat(from->si_ptr),
-					  &to->si_ptr);
+			err |= __put_user(from->si_int, &to->si_int);
 			break;
 			 /* This is not generated by the kernel as of now.  */
 		case __SI_RT >> 16:
@@ -110,19 +109,19 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
 	int err;
-	u32 ptr32;
 
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
+	memset(to, 0, sizeof(*to));
+
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);
 
 	err |= __get_user(to->si_pid, &from->si_pid);
 	err |= __get_user(to->si_uid, &from->si_uid);
-	err |= __get_user(ptr32, &from->si_ptr);
-	to->si_ptr = compat_ptr(ptr32);
+	err |= __get_user(to->si_int, &from->si_int);
 
 	return err;
 }
@@ -196,19 +195,12 @@ int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	unsigned long restorer;
 	struct compat_rt_sigframe __user *frame;
 	int err = 0, sig = ksig->sig;
-	int usig;
 
 	frame = compat_get_sigframe(&ksig->ka, regs, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto err;
 
-	usig = current_thread_info()->exec_domain
-		&& current_thread_info()->exec_domain->signal_invmap
-		&& sig < 32
-		? current_thread_info()->exec_domain->signal_invmap[sig]
-		: sig;
-
 	/* Always write at least the signal number for the stack backtracer. */
 	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
 		/* At sigreturn time, restore the callee-save registers too. */
@@ -243,7 +235,7 @@ int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */
 	regs->sp = ptr_to_compat_reg(frame);
 	regs->lr = restorer;
-	regs->regs[0] = (unsigned long) usig;
+	regs->regs[0] = (unsigned long) sig;
 	regs->regs[1] = ptr_to_compat_reg(&frame->info);
 	regs->regs[2] = ptr_to_compat_reg(&frame->uc);
 	regs->flags |= PT_FLAGS_CALLER_SAVES;
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
index 8d52d83cc516..0c0996175b1e 100644
--- a/arch/tile/kernel/ftrace.c
+++ b/arch/tile/kernel/ftrace.c
@@ -74,7 +74,11 @@ static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
 			create_JumpOff_X1(pcrel_by_instr);
 	}
 
-	if (addr == FTRACE_ADDR) {
+	/*
+	 * Also put { move r10, lr; jal ftrace_stub } in a bundle, which
+	 * is used to replace the instruction in address ftrace_call.
+	 */
+	if (addr == FTRACE_ADDR || addr == (unsigned long)ftrace_stub) {
 		/* opcode: or r10, lr, zero */
 		opcode_x0 =
 			create_Dest_X0(10) |
diff --git a/arch/tile/kernel/mcount_64.S b/arch/tile/kernel/mcount_64.S
index 3c2b8d5e1d1a..6c6702451962 100644
--- a/arch/tile/kernel/mcount_64.S
+++ b/arch/tile/kernel/mcount_64.S
@@ -81,7 +81,12 @@ STD_ENTRY(ftrace_caller)
 
 	/* arg1: self return address */
 	/* arg2: parent's return address */
-	{ move	r0, lr; move	r1, r10 }
+	/* arg3: ftrace_ops */
+	/* arg4: regs (but make it NULL) */
+	{ move	r0, lr;  moveli        r2, hw2_last(function_trace_op) }
+	{ move	r1, r10; shl16insli    r2, r2, hw1(function_trace_op) }
+	{ movei	r3, 0;   shl16insli    r2, r2, hw0(function_trace_op) }
+	ld	r2,r2
 
 	.global	ftrace_call
 ftrace_call:
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index 325df47f114d..9475a74cd53a 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -339,6 +339,8 @@ int __init pcibios_init(void)
 			struct pci_bus *next_bus;
 			struct pci_dev *dev;
 
+			pci_bus_add_devices(root_bus);
+
 			list_for_each_entry(dev, &root_bus->devices, bus_list) {
 				/*
 				 * Find the PCI host controller, ie. the 1st
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index 2c95f37ebbed..b1df847d0686 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -1030,6 +1030,8 @@ int __init pcibios_init(void)
 alloc_mem_map_failed:
 			break;
 		}
+
+		pci_bus_add_devices(root_bus);
 	}
 
 	return 0;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 48e5773dd0b7..b403c2e3e263 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/tracehook.h>
 #include <linux/signal.h>
+#include <linux/context_tracking.h>
 #include <asm/stack.h>
 #include <asm/switch_to.h>
 #include <asm/homecache.h>
@@ -474,6 +475,8 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 	if (!user_mode(regs))
 		return 0;
 
+	user_exit();
+
 	/* Enable interrupts; they are disabled again on return to caller. */
 	local_irq_enable();
 
@@ -496,11 +499,12 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 		tracehook_notify_resume(regs);
 		return 1;
 	}
-	if (thread_info_flags & _TIF_SINGLESTEP) {
+	if (thread_info_flags & _TIF_SINGLESTEP)
 		single_step_once(regs);
-		return 0;
-	}
-	panic("work_pending: bad flags %#x\n", thread_info_flags);
+
+	user_enter();
+
+	return 0;
 }
 
 unsigned long get_wchan(struct task_struct *p)
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index de98c6ddf136..f84eed8243da 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/regset.h>
 #include <linux/elf.h>
 #include <linux/tracehook.h>
+#include <linux/context_tracking.h>
 #include <asm/traps.h>
 #include <arch/chip.h>
 
@@ -252,12 +253,21 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 int do_syscall_trace_enter(struct pt_regs *regs)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
+	u32 work = ACCESS_ONCE(current_thread_info()->flags);
+
+	/*
+	 * If TIF_NOHZ is set, we are required to call user_exit() before
+	 * doing anything that could touch RCU.
+	 */
+	if (work & _TIF_NOHZ)
+		user_exit();
+
+	if (work & _TIF_SYSCALL_TRACE) {
 		if (tracehook_report_syscall_entry(regs))
 			regs->regs[TREG_SYSCALL_NR] = -1;
 	}
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (work & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_enter(regs, regs->regs[TREG_SYSCALL_NR]);
 
 	return regs->regs[TREG_SYSCALL_NR];
@@ -268,6 +278,12 @@ void do_syscall_trace_exit(struct pt_regs *regs)
 	long errno;
 
 	/*
+	 * We may come here right after calling schedule_user()
+	 * in which case we can be in RCU user mode.
+	 */
+	user_exit();
+
+	/*
 	 * The standard tile calling convention returns the value (or negative
 	 * errno) in r0, and zero (or positive errno) in r1.
 	 * It saves a couple of cycles on the hot path to do this work in
@@ -303,5 +319,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs)
 /* Handle synthetic interrupt delivered only by the simulator. */
 void __kprobes do_breakpoint(struct pt_regs* regs, int fault_num)
 {
+	enum ctx_state prev_state = exception_enter();
 	send_sigtrap(current, regs);
+	exception_exit(prev_state);
 }
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index f1f579914952..7833b2ccdfbc 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -32,6 +32,7 @@
 #include <linux/hugetlb.h>
 #include <linux/start_kernel.h>
 #include <linux/screen_info.h>
+#include <linux/tick.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -1390,6 +1391,28 @@ static int __init dataplane(char *str)
 
 early_param("dataplane", dataplane);
 
+#ifdef CONFIG_NO_HZ_FULL
+/* Warn if hypervisor shared cpus are marked as nohz_full. */
+static int __init check_nohz_full_cpus(void)
+{
+	struct cpumask shared;
+	int cpu;
+
+	if (hv_inquire_tiles(HV_INQ_TILES_SHARED,
+			     (HV_VirtAddr) shared.bits, sizeof(shared)) < 0) {
+		pr_warn("WARNING: No support for inquiring hv shared tiles\n");
+		return 0;
+	}
+	for_each_cpu(cpu, &shared) {
+		if (tick_nohz_full_cpu(cpu))
+			pr_warn("WARNING: nohz_full cpu %d receives hypervisor interrupts!\n",
+			       cpu);
+	}
+	return 0;
+}
+arch_initcall(check_nohz_full_cpus);
+#endif
+
 #ifdef CONFIG_CMDLINE_BOOL
 static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
 #endif
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 8a524e332c1a..87299a6cfec8 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -151,19 +151,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	unsigned long restorer;
 	struct rt_sigframe __user *frame;
 	int err = 0, sig = ksig->sig;
-	int usig;
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto err;
 
-	usig = current_thread_info()->exec_domain
-		&& current_thread_info()->exec_domain->signal_invmap
-		&& sig < 32
-		? current_thread_info()->exec_domain->signal_invmap[sig]
-		: sig;
-
 	/* Always write at least the signal number for the stack backtracer. */
 	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
 		/* At sigreturn time, restore the callee-save registers too. */
@@ -198,7 +191,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */
 	regs->sp = (unsigned long) frame;
 	regs->lr = restorer;
-	regs->regs[0] = (unsigned long) usig;
+	regs->regs[0] = (unsigned long) sig;
 	regs->regs[1] = (unsigned long) &frame->info;
 	regs->regs[2] = (unsigned long) &frame->uc;
 	regs->flags |= PT_FLAGS_CALLER_SAVES;
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 862973074bf9..53f7b9def07b 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/context_tracking.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -738,6 +739,7 @@ static DEFINE_PER_CPU(unsigned long, ss_saved_pc);
 
 void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 {
+	enum ctx_state prev_state = exception_enter();
 	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	struct thread_info *info = (void *)current_thread_info();
 	int is_single_step = test_ti_thread_flag(info, TIF_SINGLESTEP);
@@ -754,6 +756,7 @@ void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 		__insn_mtspr(SPR_SINGLE_STEP_CONTROL_K, control);
 		send_sigtrap(current, regs);
 	}
+	exception_exit(prev_state);
 }
 
 
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index d3c4ed780ce2..07e3ff5cc740 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/irq_work.h>
 #include <linux/module.h>
 #include <asm/cacheflush.h>
 #include <asm/homecache.h>
@@ -33,6 +34,8 @@ EXPORT_SYMBOL(smp_topology);
 static unsigned long __iomem *ipi_mappings[NR_CPUS];
 #endif
 
+/* Does messaging work correctly to the local cpu? */
+bool self_interrupt_ok;
 
 /*
  * Top-level send_IPI*() functions to send messages to other cpus.
@@ -147,6 +150,10 @@ void evaluate_message(int tag)
 		generic_smp_call_function_single_interrupt();
 		break;
 
+	case MSG_TAG_IRQ_WORK: /* Invoke IRQ work */
+		irq_work_run();
+		break;
+
 	default:
 		panic("Unknown IPI message tag %d", tag);
 		break;
@@ -186,6 +193,15 @@ void flush_icache_range(unsigned long start, unsigned long end)
 EXPORT_SYMBOL(flush_icache_range);
 
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	if (arch_irq_work_has_interrupt())
+		send_IPI_single(smp_processor_id(), MSG_TAG_IRQ_WORK);
+}
+#endif
+
+
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
@@ -203,8 +219,22 @@ static struct irqaction resched_action = {
 
 void __init ipi_init(void)
 {
+	int cpu = smp_processor_id();
+	HV_Recipient recip = { .y = cpu_y(cpu), .x = cpu_x(cpu),
+			       .state = HV_TO_BE_SENT };
+	int tag = MSG_TAG_CALL_FUNCTION_SINGLE;
+
+	/*
+	 * Test if we can message ourselves for arch_irq_work_raise.
+	 * This functionality is only available in the Tilera hypervisor
+	 * in versions 4.3.4 and following.
+	 */
+	if (hv_send_message(&recip, 1, (HV_VirtAddr)&tag, sizeof(tag)) == 1)
+		self_interrupt_ok = true;
+	else
+		pr_warn("Older hypervisor: disabling fast irq_work_raise\n");
+
 #if CHIP_HAS_IPI()
-	int cpu;
 	/* Map IPI trigger MMIO addresses. */
 	for_each_possible_cpu(cpu) {
 		HV_Coord tile;
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 7ff5afdbd3aa..c42dce50acd8 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -108,14 +108,15 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 		   p->sp < PAGE_OFFSET && p->sp != 0) {
 		if (kbt->verbose)
 			pr_err("  <%s while in user mode>\n", fault);
-	} else if (kbt->verbose) {
-		pr_err("  (odd fault: pc %#lx, sp %#lx, ex1 %#lx?)\n",
-		       p->pc, p->sp, p->ex1);
-		p = NULL;
+	} else {
+		if (kbt->verbose)
+			pr_err("  (odd fault: pc %#lx, sp %#lx, ex1 %#lx?)\n",
+			       p->pc, p->sp, p->ex1);
+		return NULL;
 	}
-	if (!kbt->profile || ((1ULL << p->faultnum) & QUEUED_INTERRUPTS) == 0)
-		return p;
-	return NULL;
+	if (kbt->profile && ((1ULL << p->faultnum) & QUEUED_INTERRUPTS) != 0)
+		return NULL;
+	return p;
 }
 
 /* Is the pc pointing to a sigreturn trampoline? */
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index d412b0856c0a..00178ecf9aea 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -257,34 +257,34 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	if (tk->tkr.clock != &cycle_counter_cs)
+	if (tk->tkr_mono.clock != &cycle_counter_cs)
 		return;
 
 	write_seqcount_begin(&vdso_data->tb_seq);
 
-	vdso_data->cycle_last		= tk->tkr.cycle_last;
-	vdso_data->mask			= tk->tkr.mask;
-	vdso_data->mult			= tk->tkr.mult;
-	vdso_data->shift		= tk->tkr.shift;
+	vdso_data->cycle_last		= tk->tkr_mono.cycle_last;
+	vdso_data->mask			= tk->tkr_mono.mask;
+	vdso_data->mult			= tk->tkr_mono.mult;
+	vdso_data->shift		= tk->tkr_mono.shift;
 
 	vdso_data->wall_time_sec	= tk->xtime_sec;
-	vdso_data->wall_time_snsec	= tk->tkr.xtime_nsec;
+	vdso_data->wall_time_snsec	= tk->tkr_mono.xtime_nsec;
 
 	vdso_data->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
-	vdso_data->monotonic_time_snsec	= tk->tkr.xtime_nsec
+	vdso_data->monotonic_time_snsec	= tk->tkr_mono.xtime_nsec
 					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->tkr.shift);
+						<< tk->tkr_mono.shift);
 	while (vdso_data->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
+					(((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
 		vdso_data->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->tkr.shift;
+					((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
 		vdso_data->monotonic_time_sec++;
 	}
 
 	vdso_data->wall_time_coarse_sec	= tk->xtime_sec;
-	vdso_data->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >>
-						 tk->tkr.shift);
+	vdso_data->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
+						 tk->tkr_mono.shift);
 
 	vdso_data->monotonic_time_coarse_sec =
 		vdso_data->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index bf841ca517bb..312fc134c1cb 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -20,6 +20,7 @@
 #include <linux/reboot.h>
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
+#include <linux/context_tracking.h>
 #include <asm/stack.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
@@ -253,6 +254,7 @@ static int do_bpt(struct pt_regs *regs)
 void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 		       unsigned long reason)
 {
+	enum ctx_state prev_state = exception_enter();
 	siginfo_t info = { 0 };
 	int signo, code;
 	unsigned long address = 0;
@@ -261,7 +263,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 
 	/* Handle breakpoints, etc. */
 	if (is_kernel && fault_num == INT_ILL && do_bpt(regs))
-		return;
+		goto done;
 
 	/* Re-enable interrupts, if they were previously enabled. */
 	if (!(regs->flags & PT_FLAGS_DISABLE_IRQ))
@@ -275,7 +277,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 		const char *name;
 		char buf[100];
 		if (fixup_exception(regs))  /* ILL_TRANS or UNALIGN_DATA */
-			return;
+			goto done;
 		if (fault_num >= 0 &&
 		    fault_num < ARRAY_SIZE(int_name) &&
 		    int_name[fault_num] != NULL)
@@ -294,7 +296,6 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 			 fault_num, name, regs->pc, buf);
 		show_regs(regs);
 		do_exit(SIGKILL);  /* FIXME: implement i386 die() */
-		return;
 	}
 
 	switch (fault_num) {
@@ -308,7 +309,6 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 			pr_err("Unreadable instruction for INT_ILL: %#lx\n",
 			       regs->pc);
 			do_exit(SIGKILL);
-			return;
 		}
 		if (!special_ill(instr, &signo, &code)) {
 			signo = SIGILL;
@@ -319,7 +319,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 	case INT_GPV:
 #if CHIP_HAS_TILE_DMA()
 		if (retry_gpv(reason))
-			return;
+			goto done;
 #endif
 		/*FALLTHROUGH*/
 	case INT_UDN_ACCESS:
@@ -346,7 +346,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 			if (!state ||
 			    (void __user *)(regs->pc) != state->buffer) {
 				single_step_once(regs);
-				return;
+				goto done;
 			}
 		}
 #endif
@@ -380,7 +380,6 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 #endif
 	default:
 		panic("Unexpected do_trap interrupt number %d", fault_num);
-		return;
 	}
 
 	info.si_signo = signo;
@@ -391,6 +390,9 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 	if (signo != SIGTRAP)
 		trace_unhandled_signal("trap", regs, address, signo);
 	force_sig_info(signo, &info, current);
+
+done:
+	exception_exit(prev_state);
 }
 
 void kernel_double_fault(int dummy, ulong pc, ulong lr, ulong sp, ulong r52)
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 7d9a83be0aca..d075f92ccee0 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/context_tracking.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -1448,6 +1449,7 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
 
 void do_unaligned(struct pt_regs *regs, int vecnum)
 {
+	enum ctx_state prev_state = exception_enter();
 	tilegx_bundle_bits __user  *pc;
 	tilegx_bundle_bits bundle;
 	struct thread_info *info = current_thread_info();
@@ -1487,12 +1489,11 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 						(int)unaligned_fixup,
 						(unsigned long long)regs->ex1,
 						(unsigned long long)regs->pc);
-				return;
+			} else {
+				/* Not fixable. Go panic. */
+				panic("Unalign exception in Kernel. pc=%lx",
+				      regs->pc);
 			}
-			/* Not fixable. Go panic. */
-			panic("Unalign exception in Kernel. pc=%lx",
-			      regs->pc);
-			return;
 		} else {
 			/*
 			 * Try to fix the exception. If we can't, panic the
@@ -1501,8 +1502,8 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 			bundle = GX_INSN_BSWAP(
 				*((tilegx_bundle_bits *)(regs->pc)));
 			jit_bundle_gen(regs, bundle, align_ctl);
-			return;
 		}
+		goto done;
 	}
 
 	/*
@@ -1526,7 +1527,7 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 
 		trace_unhandled_signal("unaligned fixup trap", regs, 0, SIGBUS);
 		force_sig_info(info.si_signo, &info, current);
-		return;
+		goto done;
 	}
 
 
@@ -1543,7 +1544,7 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 		trace_unhandled_signal("segfault in unalign fixup", regs,
 				       (unsigned long)info.si_addr, SIGSEGV);
 		force_sig_info(info.si_signo, &info, current);
-		return;
+		goto done;
 	}
 
 	if (!info->unalign_jit_base) {
@@ -1578,7 +1579,7 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 
 		if (IS_ERR((void __force *)user_page)) {
 			pr_err("Out of kernel pages trying do_mmap\n");
-			return;
+			goto done;
 		}
 
 		/* Save the address in the thread_info struct */
@@ -1591,6 +1592,9 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 
 	/* Generate unalign JIT */
 	jit_bundle_gen(regs, GX_INSN_BSWAP(bundle), align_ctl);
+
+done:
+	exception_exit(prev_state);
 }
 
 #endif /* __tilegx__ */
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 23f044e8a7ab..f7ddae3725a4 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -17,6 +17,7 @@
 #include <linux/binfmts.h>
 #include <linux/compat.h>
 #include <linux/mman.h>
+#include <linux/file.h>
 #include <linux/elf.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -39,30 +40,34 @@ static void sim_notify_exec(const char *binary_name)
 
 static int notify_exec(struct mm_struct *mm)
 {
+	int ret = 0;
 	char *buf, *path;
 	struct vm_area_struct *vma;
+	struct file *exe_file;
 
 	if (!sim_is_simulator())
 		return 1;
 
-	if (mm->exe_file == NULL)
-		return 0;
-
-	for (vma = current->mm->mmap; ; vma = vma->vm_next) {
-		if (vma == NULL)
-			return 0;
-		if (vma->vm_file == mm->exe_file)
-			break;
-	}
-
 	buf = (char *) __get_free_page(GFP_KERNEL);
 	if (buf == NULL)
 		return 0;
 
-	path = d_path(&mm->exe_file->f_path, buf, PAGE_SIZE);
-	if (IS_ERR(path)) {
-		free_page((unsigned long)buf);
-		return 0;
+	exe_file = get_mm_exe_file(mm);
+	if (exe_file == NULL)
+		goto done_free;
+
+	path = d_path(&exe_file->f_path, buf, PAGE_SIZE);
+	if (IS_ERR(path))
+		goto done_put;
+
+	down_read(&mm->mmap_sem);
+	for (vma = current->mm->mmap; ; vma = vma->vm_next) {
+		if (vma == NULL) {
+			up_read(&mm->mmap_sem);
+			goto done_put;
+		}
+		if (vma->vm_file == exe_file)
+			break;
 	}
 
 	/*
@@ -80,14 +85,20 @@ static int notify_exec(struct mm_struct *mm)
 			__insn_mtspr(SPR_SIM_CONTROL,
 				     (SIM_CONTROL_DLOPEN
 				      | (c << _SIM_CONTROL_OPERATOR_BITS)));
-			if (c == '\0')
+			if (c == '\0') {
+				ret = 1; /* success */
 				break;
+			}
 		}
 	}
+	up_read(&mm->mmap_sem);
 
 	sim_notify_exec(path);
+done_put:
+	fput(exe_file);
+done_free:
 	free_page((unsigned long)buf);
-	return 1;
+	return ret;
 }
 
 /* Notify a running simulator, if any, that we loaded an interpreter. */
@@ -109,8 +120,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	struct mm_struct *mm = current->mm;
 	int retval = 0;
 
-	down_write(&mm->mmap_sem);
-
 	/*
 	 * Notify the simulator that an exec just occurred.
 	 * If we can't find the filename of the mapping, just use
@@ -119,6 +128,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (!notify_exec(mm))
 		sim_notify_exec(bprm->filename);
 
+	down_write(&mm->mmap_sem);
+
 	retval = setup_vdso_pages();
 
 #ifndef __tilegx__
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 0f61a73534e6..e83cc999da02 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/context_tracking.h>
 
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
@@ -702,6 +703,7 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 		   unsigned long address, unsigned long write)
 {
 	int is_page_fault;
+	enum ctx_state prev_state = exception_enter();
 
 #ifdef CONFIG_KPROBES
 	/*
@@ -711,7 +713,7 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 	 */
 	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
 		       regs->faultnum, SIGSEGV) == NOTIFY_STOP)
-		return;
+		goto done;
 #endif
 
 #ifdef __tilegx__
@@ -750,7 +752,6 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 				 current->comm, current->pid, pc, address);
 			show_regs(regs);
 			do_group_exit(SIGKILL);
-			return;
 		}
 	}
 #else
@@ -834,12 +835,15 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 			async->is_fault = is_page_fault;
 			async->is_write = write;
 			async->address = address;
-			return;
+			goto done;
 		}
 	}
 #endif
 
 	handle_page_fault(regs, fault_num, is_page_fault, address, write);
+
+done:
+	exception_exit(prev_state);
 }
 
 
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index ace32d7d3864..5bd252e3fdc5 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -233,9 +233,12 @@ static pgprot_t __init init_pgprot(ulong address)
 	if (kdata_huge)
 		return construct_pgprot(PAGE_KERNEL, PAGE_HOME_HASH);
 
-	/* We map the aliased pages of permanent text inaccessible. */
+	/*
+	 * We map the aliased pages of permanent text so we can
+	 * update them if necessary, for ftrace, etc.
+	 */
 	if (address < (ulong) _sinittext - CODE_DELTA)
-		return PAGE_NONE;
+		return construct_pgprot(PAGE_KERNEL, PAGE_HOME_HASH);
 
 	/* We map read-only data non-coherent for performance. */
 	if ((address >= (ulong) __start_rodata &&