Merge git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile

Pull arch/tile updates from Chris Metcalf:
 "This is a grab bag of changes that includes some NOHZ and
  context-tracking related changes, some debugging improvements,
  JUMP_LABEL support, and some fixes for tilepro allmodconfig support.

  We also remove the now-unused node_has_online_mem() definitions both
  for tile's asm/topology.h as well as in linux/topology.h itself"

* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
  numa: remove stale node_has_online_mem() define
  arch/tile: move user_exit() to early kernel entry sequence
  tile: fix bug in setting PT_FLAGS_DISABLE_IRQ on kernel entry
  tile: fix tilepro casts for readl, writel, etc
  tile: fix a -Wframe-larger-than warning
  tile: include the syscall number in the backtrace
  MAINTAINERS: add git URL for tile
  arch/tile: adopt prepare_exit_to_usermode() model from x86
  tile/jump_label: add jump label support for TILE-Gx
  tile: define a macro ktext_writable_addr to get writable kernel text address

23 files changed, 309 insertions, 184 deletions

diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index be05b4ae02b6..6bfbe8b71e7e 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -141,6 +141,7 @@ config TILEGX
 	select HAVE_KRETPROBES
 	select HAVE_ARCH_KGDB
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select HAVE_ARCH_JUMP_LABEL
 
 config TILEPRO
 	def_bool !TILEGX
diff --git a/arch/tile/include/asm/insn.h b/arch/tile/include/asm/insn.h
new file mode 100644
index 000000000000..f78ba5c16722
--- /dev/null
+++ b/arch/tile/include/asm/insn.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright 2015 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+#ifndef __ASM_TILE_INSN_H
+#define __ASM_TILE_INSN_H
+
+#include <arch/opcode.h>
+
+static inline tilegx_bundle_bits NOP(void)
+{
+	return create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+		create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+		create_Opcode_X0(RRR_0_OPCODE_X0) |
+		create_UnaryOpcodeExtension_X1(NOP_UNARY_OPCODE_X1) |
+		create_RRROpcodeExtension_X1(UNARY_RRR_0_OPCODE_X1) |
+		create_Opcode_X1(RRR_0_OPCODE_X1);
+}
+
+static inline tilegx_bundle_bits tilegx_gen_branch(unsigned long pc,
+					    unsigned long addr,
+					    bool link)
+{
+	tilegx_bundle_bits opcode_x0, opcode_x1;
+	long pcrel_by_instr = (addr - pc) >> TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES;
+
+	if (link) {
+		/* opcode: jal addr */
+		opcode_x1 =
+			create_Opcode_X1(JUMP_OPCODE_X1) |
+			create_JumpOpcodeExtension_X1(JAL_JUMP_OPCODE_X1) |
+			create_JumpOff_X1(pcrel_by_instr);
+	} else {
+		/* opcode: j addr */
+		opcode_x1 =
+			create_Opcode_X1(JUMP_OPCODE_X1) |
+			create_JumpOpcodeExtension_X1(J_JUMP_OPCODE_X1) |
+			create_JumpOff_X1(pcrel_by_instr);
+	}
+
+	/* opcode: fnop */
+	opcode_x0 =
+		create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+		create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+		create_Opcode_X0(RRR_0_OPCODE_X0);
+
+	return opcode_x1 | opcode_x0;
+}
+
+#endif /* __ASM_TILE_INSN_H */
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 322b5fe94781..30f4a210d148 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -161,14 +161,14 @@ extern void _tile_writew(u16 val, unsigned long addr);
 extern void _tile_writel(u32 val, unsigned long addr);
 extern void _tile_writeq(u64 val, unsigned long addr);
 
-#define __raw_readb(addr) _tile_readb((unsigned long)addr)
-#define __raw_readw(addr) _tile_readw((unsigned long)addr)
-#define __raw_readl(addr) _tile_readl((unsigned long)addr)
-#define __raw_readq(addr) _tile_readq((unsigned long)addr)
-#define __raw_writeb(val, addr) _tile_writeb(val, (unsigned long)addr)
-#define __raw_writew(val, addr) _tile_writew(val, (unsigned long)addr)
-#define __raw_writel(val, addr) _tile_writel(val, (unsigned long)addr)
-#define __raw_writeq(val, addr) _tile_writeq(val, (unsigned long)addr)
+#define __raw_readb(addr) _tile_readb((unsigned long)(addr))
+#define __raw_readw(addr) _tile_readw((unsigned long)(addr))
+#define __raw_readl(addr) _tile_readl((unsigned long)(addr))
+#define __raw_readq(addr) _tile_readq((unsigned long)(addr))
+#define __raw_writeb(val, addr) _tile_writeb(val, (unsigned long)(addr))
+#define __raw_writew(val, addr) _tile_writew(val, (unsigned long)(addr))
+#define __raw_writel(val, addr) _tile_writel(val, (unsigned long)(addr))
+#define __raw_writeq(val, addr) _tile_writeq(val, (unsigned long)(addr))
 
 #else /* CONFIG_PCI */
 
diff --git a/arch/tile/include/asm/jump_label.h b/arch/tile/include/asm/jump_label.h
new file mode 100644
index 000000000000..cde7573f397b
--- /dev/null
+++ b/arch/tile/include/asm/jump_label.h
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2015 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_JUMP_LABEL_H
+#define _ASM_TILE_JUMP_LABEL_H
+
+#include <arch/opcode.h>
+
+#define JUMP_LABEL_NOP_SIZE	TILE_BUNDLE_SIZE_IN_BYTES
+
+static __always_inline bool arch_static_branch(struct static_key *key,
+					       bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		"nop" "\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		".quad 1b, %l[l_yes], %0 + %1 \n\t"
+		".popsection\n\t"
+		: :  "i" (key), "i" (branch) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+						    bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		"j %l[l_yes]" "\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		".quad 1b, %l[l_yes], %0 + %1 \n\t"
+		".popsection\n\t"
+		: :  "i" (key), "i" (branch) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
+
+typedef u64 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif /* _ASM_TILE_JUMP_LABEL_H */
diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h
index 8eca6a0e1762..498a5f71245d 100644
--- a/arch/tile/include/asm/page.h
+++ b/arch/tile/include/asm/page.h
@@ -321,6 +321,16 @@ static inline int pfn_valid(unsigned long pfn)
 #define virt_to_page(kaddr) pfn_to_page(kaddr_to_pfn((void *)(kaddr)))
 #define page_to_virt(page) pfn_to_kaddr(page_to_pfn(page))
 
+/*
+ * The kernel text is mapped at MEM_SV_START as read-only.  To allow
+ * modifying kernel text, it is also mapped at PAGE_OFFSET as read-write.
+ * This macro converts a kernel address to its writable kernel text mapping,
+ * which is used to modify the text code on a running kernel by kgdb,
+ * ftrace, kprobe, jump label, etc.
+ */
+#define ktext_writable_addr(kaddr) \
+	((unsigned long)(kaddr) - MEM_SV_START + PAGE_OFFSET)
+
 struct mm_struct;
 extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
 extern pte_t *virt_to_kpte(unsigned long kaddr);
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 139dfdee0134..0684e88aacd8 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -212,7 +212,7 @@ static inline void release_thread(struct task_struct *dead_task)
 	/* Nothing for now */
 }
 
-extern int do_work_pending(struct pt_regs *regs, u32 flags);
+extern void prepare_exit_to_usermode(struct pt_regs *regs, u32 flags);
 
 
 /*
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index dc1fb28d9636..4b7cef9e94e0 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -140,10 +140,14 @@ extern void _cpu_idle(void);
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
 
+/* 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)
+
 /* 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_NOHZ)
+	(_TIF_WORK_MASK | _TIF_SINGLESTEP | _TIF_NOHZ)
 
 /* Work to do at syscall entry. */
 #define _TIF_SYSCALL_ENTRY_WORK \
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index 76b0d0ebb244..b11d5fcd2c41 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -44,9 +44,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 /* For now, use numa node -1 for global allocation. */
 #define pcibus_to_node(bus)		((void)(bus), -1)
 
-/* By definition, we create nodes based on online memory. */
-#define node_has_online_mem(nid) 1
-
 #endif /* CONFIG_NUMA */
 
 #include <asm-generic/topology.h>
diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile
index 21f77bf68c69..09936d0bcb42 100644
--- a/arch/tile/kernel/Makefile
+++ b/arch/tile/kernel/Makefile
@@ -32,5 +32,6 @@ obj-$(CONFIG_TILE_HVGLUE_TRACE)	+= hvglue_trace.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o mcount_64.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
 obj-y				+= vdso/
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
index 0c0996175b1e..4a572088b270 100644
--- a/arch/tile/kernel/ftrace.c
+++ b/arch/tile/kernel/ftrace.c
@@ -20,21 +20,12 @@
 #include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <asm/sections.h>
+#include <asm/insn.h>
 
 #include <arch/opcode.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-static inline tilegx_bundle_bits NOP(void)
-{
-	return create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
-		create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
-		create_Opcode_X0(RRR_0_OPCODE_X0) |
-		create_UnaryOpcodeExtension_X1(NOP_UNARY_OPCODE_X1) |
-		create_RRROpcodeExtension_X1(UNARY_RRR_0_OPCODE_X1) |
-		create_Opcode_X1(RRR_0_OPCODE_X1);
-}
-
 static int machine_stopped __read_mostly;
 
 int ftrace_arch_code_modify_prepare(void)
@@ -117,7 +108,7 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 		return -EINVAL;
 
 	/* Operate on writable kernel text mapping. */
-	pc_wr = pc - MEM_SV_START + PAGE_OFFSET;
+	pc_wr = ktext_writable_addr(pc);
 
 	if (probe_kernel_write((void *)pc_wr, &new, MCOUNT_INSN_SIZE))
 		return -EPERM;
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index fbbe2ea882ea..9ff75e3a318a 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -572,7 +572,7 @@ intvec_\vecname:
 	}
 	wh64    r52
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
 	.ifnc \function,handle_nmi
 	/*
 	 * We finally have enough state set up to notify the irq
@@ -588,6 +588,9 @@ intvec_\vecname:
 	{ move r32, r2; move r33, r3 }
 	.endif
 	TRACE_IRQS_OFF
+#ifdef CONFIG_CONTEXT_TRACKING
+	jal     context_tracking_user_exit
+#endif
 	.ifnc \function,handle_syscall
 	{ move r0, r30; move r1, r31 }
 	{ move r2, r32; move r3, r33 }
@@ -846,18 +849,6 @@ STD_ENTRY(interrupt_return)
 	FEEDBACK_REENTER(interrupt_return)
 
 	/*
-	 * Use r33 to hold whether we have already loaded the callee-saves
-	 * into ptregs.  We don't want to do it twice in this loop, since
-	 * then we'd clobber whatever changes are made by ptrace, etc.
-	 * Get base of stack in r32.
-	 */
-	{
-	 GET_THREAD_INFO(r32)
-	 movei  r33, 0
-	}
-
-.Lretry_work_pending:
-	/*
 	 * Disable interrupts so as to make sure we don't
 	 * miss an interrupt that sets any of the thread flags (like
 	 * need_resched or sigpending) between sampling and the iret.
@@ -867,33 +858,27 @@ STD_ENTRY(interrupt_return)
 	IRQ_DISABLE(r20, r21)
 	TRACE_IRQS_OFF  /* Note: clobbers registers r0-r29 */
 
-
-	/* Check to see if there is any work to do before returning to user. */
+	/*
+	 * See if there are any work items (including single-shot items)
+	 * to do.  If so, save the callee-save registers to pt_regs
+	 * and then dispatch to C code.
+	 */
+	GET_THREAD_INFO(r21)
 	{
-	 addi   r29, r32, THREAD_INFO_FLAGS_OFFSET
-	 moveli r1, lo16(_TIF_ALLWORK_MASK)
+	 addi   r22, r21, THREAD_INFO_FLAGS_OFFSET
+	 moveli r20, lo16(_TIF_ALLWORK_MASK)
 	}
 	{
-	 lw     r29, r29
-	 auli   r1, r1, ha16(_TIF_ALLWORK_MASK)
+	 lw     r22, r22
+	 auli   r20, r20, ha16(_TIF_ALLWORK_MASK)
 	}
-	and     r1, r29, r1
-	bzt     r1, .Lrestore_all
-
-	/*
-	 * Make sure we have all the registers saved for signal
-	 * handling, notify-resume, or single-step.  Call out to C
-	 * code to figure out exactly what we need to do for each flag bit,
-	 * then if necessary, reload the flags and recheck.
-	 */
+	and     r1, r22, r20
 	{
 	 PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-	 bnz    r33, 1f
+	 bzt    r1, .Lrestore_all
 	}
 	push_extra_callee_saves r0
-	movei   r33, 1
-1:	jal     do_work_pending
-	bnz     r0, .Lretry_work_pending
+	jal     prepare_exit_to_usermode
 
 	/*
 	 * In the NMI case we
@@ -1327,7 +1312,7 @@ STD_ENTRY(ret_from_kernel_thread)
 	FEEDBACK_REENTER(ret_from_kernel_thread)
 	{
 	 movei  r30, 0               /* not an NMI */
-	 j      .Lresume_userspace   /* jump into middle of interrupt_return */
+	 j      interrupt_return
 	}
 	STD_ENDPROC(ret_from_kernel_thread)
 
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 58964d209d4d..3b51bdf37d11 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -658,7 +658,7 @@ intvec_\vecname:
 	 */
 	mfspr   r32, SPR_EX_CONTEXT_K_1
 	{
-	 IS_KERNEL_EX1(r22, r22)
+	 IS_KERNEL_EX1(r32, r32)
 	 PTREGS_PTR(r21, PTREGS_OFFSET_FLAGS)
 	}
 	beqzt   r32, 1f       /* zero if from user space */
@@ -753,7 +753,7 @@ intvec_\vecname:
 	}
 	wh64    r52
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
 	.ifnc \function,handle_nmi
 	/*
 	 * We finally have enough state set up to notify the irq
@@ -769,6 +769,9 @@ intvec_\vecname:
 	{ move r32, r2; move r33, r3 }
 	.endif
 	TRACE_IRQS_OFF
+#ifdef CONFIG_CONTEXT_TRACKING
+	jal     context_tracking_user_exit
+#endif
 	.ifnc \function,handle_syscall
 	{ move r0, r30; move r1, r31 }
 	{ move r2, r32; move r3, r33 }
@@ -879,20 +882,6 @@ STD_ENTRY(interrupt_return)
 	FEEDBACK_REENTER(interrupt_return)
 
 	/*
-	 * Use r33 to hold whether we have already loaded the callee-saves
-	 * into ptregs.  We don't want to do it twice in this loop, since
-	 * then we'd clobber whatever changes are made by ptrace, etc.
-	 */
-	{
-	 movei  r33, 0
-	 move   r32, sp
-	}
-
-	/* Get base of stack in r32. */
-	EXTRACT_THREAD_INFO(r32)
-
-.Lretry_work_pending:
-	/*
 	 * Disable interrupts so as to make sure we don't
 	 * miss an interrupt that sets any of the thread flags (like
 	 * need_resched or sigpending) between sampling and the iret.
@@ -902,33 +891,28 @@ STD_ENTRY(interrupt_return)
 	IRQ_DISABLE(r20, r21)
 	TRACE_IRQS_OFF  /* Note: clobbers registers r0-r29 */
 
-
-	/* Check to see if there is any work to do before returning to user. */
+	/*
+	 * See if there are any work items (including single-shot items)
+	 * to do.  If so, save the callee-save registers to pt_regs
+	 * and then dispatch to C code.
+	 */
+	move    r21, sp
+	EXTRACT_THREAD_INFO(r21)
 	{
-	 addi   r29, r32, THREAD_INFO_FLAGS_OFFSET
-	 moveli r1, hw1_last(_TIF_ALLWORK_MASK)
+	 addi   r22, r21, THREAD_INFO_FLAGS_OFFSET
+	 moveli r20, hw1_last(_TIF_ALLWORK_MASK)
 	}
 	{
-	 ld     r29, r29
-	 shl16insli r1, r1, hw0(_TIF_ALLWORK_MASK)
+	 ld     r22, r22
+	 shl16insli r20, r20, hw0(_TIF_ALLWORK_MASK)
 	}
-	and     r1, r29, r1
-	beqzt   r1, .Lrestore_all
-
-	/*
-	 * Make sure we have all the registers saved for signal
-	 * handling or notify-resume.  Call out to C code to figure out
-	 * exactly what we need to do for each flag bit, then if
-	 * necessary, reload the flags and recheck.
-	 */
+	and     r1, r22, r20
 	{
 	 PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-	 bnez   r33, 1f
+	 beqzt  r1, .Lrestore_all
 	}
 	push_extra_callee_saves r0
-	movei   r33, 1
-1:	jal     do_work_pending
-	bnez    r0, .Lretry_work_pending
+	jal     prepare_exit_to_usermode
 
 	/*
 	 * In the NMI case we
@@ -1411,7 +1395,7 @@ STD_ENTRY(ret_from_kernel_thread)
 	FEEDBACK_REENTER(ret_from_kernel_thread)
 	{
 	 movei  r30, 0               /* not an NMI */
-	 j      .Lresume_userspace   /* jump into middle of interrupt_return */
+	 j      interrupt_return
 	}
 	STD_ENDPROC(ret_from_kernel_thread)
 
diff --git a/arch/tile/kernel/jump_label.c b/arch/tile/kernel/jump_label.c
new file mode 100644
index 000000000000..07802d586988
--- /dev/null
+++ b/arch/tile/kernel/jump_label.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2015 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * jump label TILE-Gx support
+ */
+
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <asm/cacheflush.h>
+#include <asm/insn.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __jump_label_transform(struct jump_entry *e,
+				   enum jump_label_type type)
+{
+	tilegx_bundle_bits opcode;
+	/* Operate on writable kernel text mapping. */
+	unsigned long pc_wr = ktext_writable_addr(e->code);
+
+	if (type == JUMP_LABEL_JMP)
+		opcode = tilegx_gen_branch(e->code, e->target, false);
+	else
+		opcode = NOP();
+
+	*(tilegx_bundle_bits *)pc_wr = opcode;
+	/* Make sure that above mem writes were issued towards the memory. */
+	smp_wmb();
+}
+
+void arch_jump_label_transform(struct jump_entry *e,
+				enum jump_label_type type)
+{
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+
+	__jump_label_transform(e, type);
+	flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits));
+
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+__init_or_module void arch_jump_label_transform_static(struct jump_entry *e,
+						enum jump_label_type type)
+{
+	__jump_label_transform(e, type);
+}
+
+#endif /* HAVE_JUMP_LABEL */
diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c
index ff5335ae050d..a506c2c28943 100644
--- a/arch/tile/kernel/kgdb.c
+++ b/arch/tile/kernel/kgdb.c
@@ -164,7 +164,7 @@ static unsigned long writable_address(unsigned long addr)
 	unsigned long ret = 0;
 
 	if (core_kernel_text(addr))
-		ret = addr - MEM_SV_START + PAGE_OFFSET;
+		ret = ktext_writable_addr(addr);
 	else if (is_module_text_address(addr))
 		ret = addr;
 	else
diff --git a/arch/tile/kernel/kprobes.c b/arch/tile/kernel/kprobes.c
index f8a45c51e9e4..c68694bb1ad2 100644
--- a/arch/tile/kernel/kprobes.c
+++ b/arch/tile/kernel/kprobes.c
@@ -116,7 +116,7 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
 	unsigned long addr_wr;
 
 	/* Operate on writable kernel text mapping. */
-	addr_wr = (unsigned long)p->addr - MEM_SV_START + PAGE_OFFSET;
+	addr_wr = ktext_writable_addr(p->addr);
 
 	if (probe_kernel_write((void *)addr_wr, &breakpoint_insn,
 		sizeof(breakpoint_insn)))
@@ -131,7 +131,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *kp)
 	unsigned long addr_wr;
 
 	/* Operate on writable kernel text mapping. */
-	addr_wr = (unsigned long)kp->addr - MEM_SV_START + PAGE_OFFSET;
+	addr_wr = ktext_writable_addr(kp->addr);
 
 	if (probe_kernel_write((void *)addr_wr, &kp->opcode,
 		sizeof(kp->opcode)))
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 7d5769310bef..b5f30d376ce1 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -462,54 +462,57 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 
 /*
  * This routine is called on return from interrupt if any of the
- * TIF_WORK_MASK flags are set in thread_info->flags.  It is
- * entered with interrupts disabled so we don't miss an event
- * that modified the thread_info flags.  If any flag is set, we
- * handle it and return, and the calling assembly code will
- * re-disable interrupts, reload the thread flags, and call back
- * if more flags need to be handled.
- *
- * We return whether we need to check the thread_info flags again
- * or not.  Note that we don't clear TIF_SINGLESTEP here, so it's
- * important that it be tested last, and then claim that we don't
- * need to recheck the flags.
+ * TIF_ALLWORK_MASK flags are set in thread_info->flags.  It is
+ * entered with interrupts disabled so we don't miss an event that
+ * modified the thread_info flags.  We loop until all the tested flags
+ * are clear.  Note that the function is called on certain conditions
+ * that are not listed in the loop condition here (e.g. SINGLESTEP)
+ * which guarantees we will do those things once, and redo them if any
+ * of the other work items is re-done, but won't continue looping if
+ * all the other work is done.
  */
-int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
+void prepare_exit_to_usermode(struct pt_regs *regs, u32 thread_info_flags)
 {
-	/* If we enter in kernel mode, do nothing and exit the caller loop. */
-	if (!user_mode(regs))
-		return 0;
+	if (WARN_ON(!user_mode(regs)))
+		return;
 
-	user_exit();
+	do {
+		local_irq_enable();
 
-	/* Enable interrupts; they are disabled again on return to caller. */
-	local_irq_enable();
+		if (thread_info_flags & _TIF_NEED_RESCHED)
+			schedule();
 
-	if (thread_info_flags & _TIF_NEED_RESCHED) {
-		schedule();
-		return 1;
-	}
 #if CHIP_HAS_TILE_DMA()
-	if (thread_info_flags & _TIF_ASYNC_TLB) {
-		do_async_page_fault(regs);
-		return 1;
-	}
+		if (thread_info_flags & _TIF_ASYNC_TLB)
+			do_async_page_fault(regs);
 #endif
-	if (thread_info_flags & _TIF_SIGPENDING) {
-		do_signal(regs);
-		return 1;
-	}
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-		return 1;
-	}
-	if (thread_info_flags & _TIF_SINGLESTEP)
+
+		if (thread_info_flags & _TIF_SIGPENDING)
+			do_signal(regs);
+
+		if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+		}
+
+		local_irq_disable();
+		thread_info_flags = READ_ONCE(current_thread_info()->flags);
+
+	} while (thread_info_flags & _TIF_WORK_MASK);
+
+	if (thread_info_flags & _TIF_SINGLESTEP) {
 		single_step_once(regs);
+#ifndef __tilegx__
+		/*
+		 * FIXME: on tilepro, since we enable interrupts in
+		 * this routine, it's possible that we miss a signal
+		 * or other asynchronous event.
+		 */
+		local_irq_disable();
+#endif
+	}
 
 	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 bdc126faf741..54e7b723db99 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -255,13 +255,6 @@ int do_syscall_trace_enter(struct pt_regs *regs)
 {
 	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 (secure_computing() == -1)
 		return -1;
 
@@ -281,12 +274,6 @@ 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
@@ -322,7 +309,5 @@ 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 6b755d125783..bbb855de6569 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -882,7 +882,7 @@ static int __init node_neighbors(int node, int cpu,
 
 static void __init setup_numa_mapping(void)
 {
-	int distance[MAX_NUMNODES][NR_CPUS];
+	u8 distance[MAX_NUMNODES][NR_CPUS];
 	HV_Coord coord;
 	int cpu, node, cpus, i, x, y;
 	int num_nodes = num_online_nodes();
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 53f7b9def07b..862973074bf9 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -23,7 +23,6 @@
 #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>
@@ -739,7 +738,6 @@ 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);
@@ -756,7 +754,6 @@ 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/stack.c b/arch/tile/kernel/stack.c
index 402b9c85a894..22bbbd3ff4a3 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -78,8 +78,7 @@ static bool read_memory_func(void *result, unsigned long address,
 /* Return a pt_regs pointer for a valid fault handler frame */
 static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 {
-	const char *fault = NULL;  /* happy compiler */
-	char fault_buf[64];
+	char fault[64];
 	unsigned long sp = kbt->it.sp;
 	struct pt_regs *p;
 
@@ -90,14 +89,14 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 	if (!in_kernel_stack(kbt, sp + C_ABI_SAVE_AREA_SIZE + PTREGS_SIZE-1))
 		return NULL;
 	p = (struct pt_regs *)(sp + C_ABI_SAVE_AREA_SIZE);
-	if (p->faultnum == INT_SWINT_1 || p->faultnum == INT_SWINT_1_SIGRETURN)
-		fault = "syscall";
-	else {
-		if (kbt->verbose) {     /* else we aren't going to use it */
-			snprintf(fault_buf, sizeof(fault_buf),
+	if (kbt->verbose) {     /* else we aren't going to use it */
+		if (p->faultnum == INT_SWINT_1 ||
+		    p->faultnum == INT_SWINT_1_SIGRETURN)
+			snprintf(fault, sizeof(fault),
+				 "syscall %ld", p->regs[TREG_SYSCALL_NR]);
+		else
+			snprintf(fault, sizeof(fault),
 				 "interrupt %ld", p->faultnum);
-			fault = fault_buf;
-		}
 	}
 	if (EX1_PL(p->ex1) == KERNEL_PL &&
 	    __kernel_text_address(p->pc) &&
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 0011a9ff0525..4d9651c5b1ad 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -20,7 +20,6 @@
 #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>
@@ -254,7 +253,6 @@ 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;
@@ -263,7 +261,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 
 	/* Handle breakpoints, etc. */
 	if (is_kernel && fault_num == INT_ILL && do_bpt(regs))
-		goto done;
+		return;
 
 	/* Re-enable interrupts, if they were previously enabled. */
 	if (!(regs->flags & PT_FLAGS_DISABLE_IRQ))
@@ -277,7 +275,7 @@ 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 */
-			goto done;
+			return;
 		if (fault_num >= 0 &&
 		    fault_num < ARRAY_SIZE(int_name) &&
 		    int_name[fault_num] != NULL)
@@ -319,7 +317,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 	case INT_GPV:
 #if CHIP_HAS_TILE_DMA()
 		if (retry_gpv(reason))
-			goto done;
+			return;
 #endif
 		/*FALLTHROUGH*/
 	case INT_UDN_ACCESS:
@@ -346,7 +344,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 			if (!state ||
 			    (void __user *)(regs->pc) != state->buffer) {
 				single_step_once(regs);
-				goto done;
+				return;
 			}
 		}
 #endif
@@ -390,9 +388,6 @@ 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 do_nmi(struct pt_regs *regs, int fault_num, unsigned long reason)
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index d075f92ccee0..0db5f7c9d9e5 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -25,7 +25,6 @@
 #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>
@@ -1449,7 +1448,6 @@ 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();
@@ -1503,7 +1501,7 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
 				*((tilegx_bundle_bits *)(regs->pc)));
 			jit_bundle_gen(regs, bundle, align_ctl);
 		}
-		goto done;
+		return;
 	}
 
 	/*
@@ -1527,7 +1525,7 @@ 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);
-		goto done;
+		return;
 	}
 
 
@@ -1544,7 +1542,7 @@ 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);
-		goto done;
+		return;
 	}
 
 	if (!info->unalign_jit_base) {
@@ -1579,7 +1577,7 @@ 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");
-			goto done;
+			return;
 		}
 
 		/* Save the address in the thread_info struct */
@@ -1592,9 +1590,6 @@ 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/fault.c b/arch/tile/mm/fault.c
index 13eac59bf16a..26734214818c 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -35,7 +35,6 @@
 #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>
@@ -845,9 +844,7 @@ 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)
 {
-	enum ctx_state prev_state = exception_enter();
 	__do_page_fault(regs, fault_num, address, write);
-	exception_exit(prev_state);
 }
 
 #if CHIP_HAS_TILE_DMA()