Merge branch 'akpm' (patches from Andrew)

Merge third set of updates from Andrew Morton:

 - the rest of MM

   [ This includes getting rid of the numa hinting bits, in favor of
     just generic protnone logic.  Yay.     - Linus ]

 - core kernel

 - procfs

 - some of lib/ (lots of lib/ material this time)

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (104 commits)
  lib/lcm.c: replace include
  lib/percpu_ida.c: remove redundant includes
  lib/strncpy_from_user.c: replace module.h include
  lib/stmp_device.c: replace module.h include
  lib/sort.c: move include inside #if 0
  lib/show_mem.c: remove redundant include
  lib/radix-tree.c: change to simpler include
  lib/plist.c: remove redundant include
  lib/nlattr.c: remove redundant include
  lib/kobject_uevent.c: remove redundant include
  lib/llist.c: remove redundant include
  lib/md5.c: simplify include
  lib/list_sort.c: rearrange includes
  lib/genalloc.c: remove redundant include
  lib/idr.c: remove redundant include
  lib/halfmd4.c: simplify includes
  lib/dynamic_queue_limits.c: simplify includes
  lib/sort.c: use simpler includes
  lib/interval_tree.c: simplify includes
  hexdump: make it return number of bytes placed in buffer
  ...

.gitignore

@@ -52,6 +52,11 @@ Module.symvers
 #
 /debian/
 
+#
+# tar directory (make tar*-pkg)
+#
+/tar-install/
+
 #
 # git files that we don't want to ignore even it they are dot-files
 #

Documentation/filesystems/proc.txt

@@ -145,6 +145,8 @@ Table 1-1: Process specific entries in /proc
  stack		Report full stack trace, enable via CONFIG_STACKTRACE
  smaps		a extension based on maps, showing the memory consumption of
 		each mapping and flags associated with it
+ numa_maps	an extension based on maps, showing the memory locality and
+		binding policy as well as mem usage (in pages) of each mapping.
 ..............................................................................
 
 For example, to get the status information of a process, all you have to do is
@@ -489,12 +491,47 @@ To clear the bits for the file mapped pages associated with the process
 To clear the soft-dirty bit
     > echo 4 > /proc/PID/clear_refs
 
+To reset the peak resident set size ("high water mark") to the process's
+current value:
+    > echo 5 > /proc/PID/clear_refs
+
 Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 using /proc/kpageflags and number of times a page is mapped using
 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 
+The /proc/pid/numa_maps is an extension based on maps, showing the memory
+locality and binding policy, as well as the memory usage (in pages) of
+each mapping. The output follows a general format where mapping details get
+summarized separated by blank spaces, one mapping per each file line:
+
+address   policy    mapping details
+
+00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
+00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
+320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
+320698b000 default file=/lib64/libc-2.12.so
+3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
+3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
+7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
+7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
+7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
+
+Where:
+"address" is the starting address for the mapping;
+"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
+"mapping details" summarizes mapping data such as mapping type, page usage counters,
+node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
+size, in KB, that is backing the mapping up.
+
 1.2 Kernel data
 ---------------
 

arch/alpha/include/asm/thread_info.h

@@ -27,8 +27,6 @@ struct thread_info {
 	int bpt_nsaved;
 	unsigned long bpt_addr[2];		/* breakpoint handling  */
 	unsigned int bpt_insn[2];
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -40,9 +38,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/alpha/kernel/signal.c

@@ -150,7 +150,7 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
 	long i, err = __get_user(regs->pc, &sc->sc_pc);
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sw->r26 = (unsigned long) ret_from_sys_call;
 

arch/arc/include/asm/thread_info.h

@@ -46,7 +46,6 @@ struct thread_info {
 	struct exec_domain *exec_domain;/* execution domain */
 	__u32 cpu;			/* current CPU */
 	unsigned long thr_ptr;		/* TLS ptr */
-	struct restart_block restart_block;
 };
 
 /*
@@ -62,9 +61,6 @@ struct thread_info {
 	.cpu        = 0,			\
 	.preempt_count  = INIT_PREEMPT_COUNT,	\
 	.addr_limit = KERNEL_DS,		\
-	.restart_block  = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info    (init_thread_union.thread_info)

arch/arc/kernel/signal.c

@@ -104,7 +104,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	struct pt_regs *regs = current_pt_regs();
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Since we stacked the signal on a word boundary,
 	 * then 'sp' should be word aligned here.  If it's

arch/arm/include/asm/pgtable-3level.h

@@ -257,7 +257,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 /* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
-#define pmd_mknotpresent(pmd)	(__pmd(0))
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return __pmd(0);
+}
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {

arch/arm/include/asm/thread_info.h

@@ -68,7 +68,6 @@ struct thread_info {
 #ifdef CONFIG_ARM_THUMBEE
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -81,9 +80,6 @@ struct thread_info {
 	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/arm/kernel/signal.c

@@ -191,7 +191,7 @@ asmlinkage int sys_sigreturn(struct pt_regs *regs)
 	struct sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -221,7 +221,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,

arch/arm64/include/asm/thread_info.h

@@ -48,7 +48,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	struct exec_domain	*exec_domain;	/* execution domain */
-	struct restart_block	restart_block;
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
 	int			cpu;		/* cpu */
 };
@@ -60,9 +59,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/arm64/kernel/signal.c

@@ -131,7 +131,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 128-bit boundary, then 'sp' should

arch/arm64/kernel/signal32.c

@@ -347,7 +347,7 @@ asmlinkage int compat_sys_sigreturn(struct pt_regs *regs)
 	struct compat_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -381,7 +381,7 @@ asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs)
 	struct compat_rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,

arch/avr32/include/asm/thread_info.h

@@ -30,7 +30,6 @@ struct thread_info {
 						   saved by debug handler
 						   when setting up
 						   trampoline */
-	struct restart_block	restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.cpu		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall				\
-	}								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/avr32/kernel/asm-offsets.c

@@ -18,7 +18,6 @@ void foo(void)
 	OFFSET(TI_preempt_count, thread_info, preempt_count);
 	OFFSET(TI_rar_saved, thread_info, rar_saved);
 	OFFSET(TI_rsr_saved, thread_info, rsr_saved);
-	OFFSET(TI_restart_block, thread_info, restart_block);
 	BLANK();
 	OFFSET(TSK_active_mm, task_struct, active_mm);
 	BLANK();

arch/avr32/kernel/signal.c

@@ -69,7 +69,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)regs->sp;
 	pr_debug("SIG return: frame = %p\n", frame);

arch/blackfin/include/asm/thread_info.h

@@ -42,7 +42,6 @@ struct thread_info {
 	int cpu;		/* cpu we're on */
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t addr_limit;	/* address limit */
-	struct restart_block restart_block;
 #ifndef CONFIG_SMP
 	struct l1_scratch_task_info l1_task_info;
 #endif
@@ -58,9 +57,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)

arch/blackfin/kernel/signal.c

@@ -44,7 +44,7 @@ rt_restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *p
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define RESTORE(x) err |= __get_user(regs->x, &sc->sc_##x)
 

arch/c6x/include/asm/thread_info.h

@@ -45,7 +45,6 @@ struct thread_info {
 	int			cpu;		/* cpu we're on */
 	int			preempt_count;	/* 0 = preemptable, <0 = BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 };
 
 /*
@@ -61,9 +60,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/c6x/kernel/signal.c

@@ -68,7 +68,7 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a dword boundary,

arch/cris/arch-v10/kernel/signal.c

@@ -67,7 +67,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore the regs from &sc->regs (same as sc, since regs is first)
 	 * (sc is already checked for VERIFY_READ since the sigframe was

arch/cris/arch-v32/kernel/signal.c

@@ -59,7 +59,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the registers from &sc->regs. sc is already checked

arch/cris/include/asm/thread_info.h

@@ -38,7 +38,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -56,9 +55,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,		\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block = {				\
-		       .fn = do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/frv/include/asm/string.h

@@ -33,7 +33,6 @@ extern void *memcpy(void *, const void *, __kernel_size_t);
 #define __HAVE_ARCH_STRNCAT 1
 #define __HAVE_ARCH_STRCMP 1
 #define __HAVE_ARCH_STRNCMP 1
-#define __HAVE_ARCH_STRNICMP 1
 #define __HAVE_ARCH_STRCHR 1
 #define __HAVE_ARCH_STRRCHR 1
 #define __HAVE_ARCH_STRSTR 1

arch/frv/include/asm/thread_info.h

@@ -41,7 +41,6 @@ struct thread_info {
 						 * 0-0xBFFFFFFF for user-thead
 						 * 0-0xFFFFFFFF for kernel-thread
 						 */
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -65,9 +64,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/frv/kernel/asm-offsets.c

@@ -40,7 +40,6 @@ void foo(void)
 	OFFSET(TI_CPU,			thread_info, cpu);
 	OFFSET(TI_PREEMPT_COUNT,	thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT,		thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK,	thread_info, restart_block);
 	BLANK();
 
 	/* offsets into register file storage */

arch/frv/kernel/signal.c

@@ -62,7 +62,7 @@ static int restore_sigcontext(struct sigcontext __user *sc, int *_gr8)
 	unsigned long tbr, psr;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	tbr = user->i.tbr;
 	psr = user->i.psr;

arch/frv/mm/extable.c

@@ -10,29 +10,6 @@ extern const void __memset_end, __memset_user_error_lr, __memset_user_error_hand
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
 extern spinlock_t modlist_lock;
 
-/*****************************************************************************/
-/*
- *
- */
-static inline unsigned long search_one_table(const struct exception_table_entry *first,
-					     const struct exception_table_entry *last,
-					     unsigned long value)
-{
-        while (first <= last) {
-		const struct exception_table_entry __attribute__((aligned(8))) *mid;
-		long diff;
-
-		mid = (last - first) / 2 + first;
-		diff = mid->insn - value;
-                if (diff == 0)
-                        return mid->fixup;
-                else if (diff < 0)
-                        first = mid + 1;
-                else
-                        last = mid - 1;
-        }
-        return 0;
-} /* end search_one_table() */
 
 /*****************************************************************************/
 /*

arch/hexagon/include/asm/thread_info.h

@@ -56,7 +56,6 @@ struct thread_info {
 	 * used for syscalls somehow;
 	 * seems to have a function pointer and four arguments
 	 */
-	struct restart_block    restart_block;
 	/* Points to the current pt_regs frame  */
 	struct pt_regs		*regs;
 	/*
@@ -83,9 +82,6 @@ struct thread_info {
 	.cpu            = 0,                    \
 	.preempt_count  = 1,                    \
 	.addr_limit     = KERNEL_DS,            \
-	.restart_block = {                      \
-		.fn = do_no_restart_syscall,    \
-	},                                      \
 	.sp = 0,				\
 	.regs = NULL,			\
 }

arch/hexagon/kernel/signal.c

@@ -239,7 +239,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	sigset_t blocked;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)pt_psp(regs);
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))

arch/ia64/include/asm/thread_info.h

@@ -27,7 +27,6 @@ struct thread_info {
 	__u32 status;			/* Thread synchronous flags */
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	__u64 ac_stamp;
 	__u64 ac_leave;
@@ -46,9 +45,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #ifndef ASM_OFFSETS_C

arch/ia64/kernel/signal.c

@@ -46,7 +46,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 	long err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore scratch that always needs gets updated during signal delivery: */
 	err  = __get_user(flags, &sc->sc_flags);

arch/m32r/include/asm/thread_info.h

@@ -34,7 +34,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thread
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -49,7 +48,6 @@ struct thread_info {
 #define TI_CPU		0x00000010
 #define TI_PRE_COUNT	0x00000014
 #define TI_ADDR_LIMIT	0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -68,9 +66,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/m32r/kernel/signal.c

@@ -48,7 +48,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define COPY(x)		err |= __get_user(regs->x, &sc->sc_##x)
 	COPY(r4);

arch/m68k/include/asm/thread_info.h

@@ -31,7 +31,6 @@ struct thread_info {
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
 	__u32			cpu;		/* should always be 0 on m68k */
 	unsigned long		tp_value;	/* thread pointer */
-	struct restart_block    restart_block;
 };
 #endif /* __ASSEMBLY__ */
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_stack		(init_thread_union.stack)

arch/m68k/kernel/signal.c

@@ -655,7 +655,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* get previous context */
 	if (copy_from_user(&context, usc, sizeof(context)))
@@ -693,7 +693,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = __get_user(temp, &uc->uc_mcontext.version);
 	if (temp != MCONTEXT_VERSION)

arch/metag/include/asm/thread_info.h

@@ -35,9 +35,8 @@ struct thread_info {
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 
 	mm_segment_t addr_limit;	/* thread address space */
-	struct restart_block restart_block;
 
-	u8 supervisor_stack[0];
+	u8 supervisor_stack[0] __aligned(8);
 };
 
 #else /* !__ASSEMBLY__ */
@@ -74,9 +73,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/metag/kernel/signal.c

@@ -48,7 +48,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = metag_gp_regs_copyin(regs, 0, sizeof(struct user_gp_regs), NULL,
 				   &sc->regs);

arch/microblaze/include/asm/thread_info.h

@@ -71,7 +71,6 @@ struct thread_info {
 	__u32			cpu; /* current CPU */
 	__s32			preempt_count; /* 0 => preemptable,< 0 => BUG*/
 	mm_segment_t		addr_limit; /* thread address space */
-	struct restart_block	restart_block;
 
 	struct cpu_context	cpu_context;
 };
@@ -87,9 +86,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/microblaze/kernel/signal.c

@@ -89,7 +89,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	int rval;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;

arch/mips/include/asm/thread_info.h

@@ -34,7 +34,6 @@ struct thread_info {
 						 * 0x7fffffff for user-thead
 						 * 0xffffffff for kernel-thread
 						 */
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 	long			syscall;	/* syscall number */
 };
@@ -50,9 +49,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/mips/kernel/asm-offsets.c

@@ -98,7 +98,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);

arch/mips/kernel/signal.c

@@ -243,7 +243,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 

arch/mips/kernel/signal32.c

@@ -220,7 +220,7 @@ static int restore_sigcontext32(struct pt_regs *regs,
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 	err |= __get_user(regs->hi, &sc->sc_mdhi);

arch/mn10300/include/asm/thread_info.h

@@ -50,7 +50,6 @@ struct thread_info {
 						   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -80,9 +79,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/mn10300/kernel/asm-offsets.c

@@ -28,7 +28,6 @@ void foo(void)
 	OFFSET(TI_cpu,			thread_info, cpu);
 	OFFSET(TI_preempt_count,	thread_info, preempt_count);
 	OFFSET(TI_addr_limit,		thread_info, addr_limit);
-	OFFSET(TI_restart_block,	thread_info, restart_block);
 	BLANK();
 
 	OFFSET(REG_D0,			pt_regs, d0);

arch/mn10300/kernel/signal.c

@@ -40,7 +40,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (is_using_fpu(current))
 		fpu_kill_state(current);

arch/openrisc/include/asm/thread_info.h

@@ -57,7 +57,6 @@ struct thread_info {
 					       0-0x7FFFFFFF for user-thead
 					       0-0xFFFFFFFF for kernel-thread
 					     */
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 
 	/* saved context data */
@@ -79,9 +78,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= 1,				\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block  = {				\
-			  .fn = do_no_restart_syscall,	\
-	},						\
 	.ksp            = 0,                            \
 }
 

arch/openrisc/kernel/signal.c

@@ -46,7 +46,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the regs from &sc->regs.

arch/parisc/include/asm/thread_info.h

@@ -14,7 +14,6 @@ struct thread_info {
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	__u32 cpu;			/* current CPU */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -25,9 +24,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-  	.restart_block	= {			\
-		.fn = do_no_restart_syscall	\
-	}					\
 }
 
 #define init_thread_info        (init_thread_union.thread_info)

arch/parisc/kernel/signal.c

@@ -99,7 +99,7 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall)
 		sigframe_size = PARISC_RT_SIGFRAME_SIZE32;
 #endif
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Unwind the user stack to get the rt_sigframe structure. */
 	frame = (struct rt_sigframe __user *)

arch/powerpc/include/asm/pgtable.h

@@ -40,63 +40,27 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-static inline int pte_present(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_NUMA_MASK;
-}
-
-#define pte_present_nonuma pte_present_nonuma
-static inline int pte_present_nonuma(pte_t pte)
-{
-	return pte_val(pte) & (_PAGE_PRESENT);
-}
-
-#define ptep_set_numa ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
-	return;
-}
-
-#define pmdp_set_numa pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
-	return;
-}
-
 /*
- * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
- * which was inherited from x86. For the purposes of powerpc pte_basic_t and
- * pmd_t are equivalent
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
  */
-#define pteval_t pte_basic_t
-#define pmdval_t pmd_t
-static inline pteval_t ptenuma_flags(pte_t pte)
+static inline int pte_protnone(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_NUMA_MASK;
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
 }
 
-static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+static inline int pmd_protnone(pmd_t pmd)
 {
-	return pmd_val(pmd) & _PAGE_NUMA_MASK;
+	return pte_protnone(pmd_pte(pmd));
 }
-
-# else
+#endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_PRESENT;
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
 /* Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.

arch/powerpc/include/asm/pte-common.h

@@ -104,11 +104,6 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
-#ifdef CONFIG_NUMA_BALANCING
-/* Mask of bits that distinguish present and numa ptes */
-#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
-#endif
-
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable

arch/powerpc/include/asm/pte-hash64.h

@@ -27,12 +27,6 @@
 #define _PAGE_RW		0x0200 /* software: user write access allowed */
 #define _PAGE_BUSY		0x0800 /* software: PTE & hash are busy */
 
-/*
- * Used for tracking numa faults
- */
-#define _PAGE_NUMA	0x00000010 /* Gather numa placement stats */
-
-
 /* No separate kernel read-only */
 #define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
 #define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW

arch/powerpc/include/asm/thread_info.h

@@ -43,7 +43,6 @@ struct thread_info {
 	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
-	struct restart_block restart_block;
 	unsigned long	local_flags;		/* private flags for thread */
 
 	/* low level flags - has atomic operations done on it */
@@ -59,9 +58,6 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.flags =	0,			\
 }
 

arch/powerpc/kernel/signal_32.c

@@ -1231,7 +1231,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
@@ -1504,7 +1504,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
 	sc = &sf->sctx;

arch/powerpc/kernel/signal_64.c

@@ -666,7 +666,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
 		goto badframe;

arch/powerpc/kernel/time.c

@@ -621,6 +621,38 @@ unsigned long long sched_clock(void)
 	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
 }
 
+
+#ifdef CONFIG_PPC_PSERIES
+
+/*
+ * Running clock - attempts to give a view of time passing for a virtualised
+ * kernels.
+ * Uses the VTB register if available otherwise a next best guess.
+ */
+unsigned long long running_clock(void)
+{
+	/*
+	 * Don't read the VTB as a host since KVM does not switch in host
+	 * timebase into the VTB when it takes a guest off the CPU, reading the
+	 * VTB would result in reading 'last switched out' guest VTB.
+	 *
+	 * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it
+	 * would be unsafe to rely only on the #ifdef above.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+
+	/*
+	 * This is a next best approximation without a VTB.
+	 * On a host which is running bare metal there should never be any stolen
+	 * time and on a host which doesn't do any virtualisation TB *should* equal
+	 * VTB so it makes no difference anyway.
+	 */
+	return local_clock() - cputime_to_nsecs(kcpustat_this_cpu->cpustat[CPUTIME_STEAL]);
+}
+#endif
+
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -212,7 +212,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Look up the Linux PTE for the backing page */
 	pte_size = psize;
 	pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
-	if (pte_present(pte) && !pte_numa(pte)) {
+	if (pte_present(pte) && !pte_protnone(pte)) {
 		if (writing && !pte_write(pte))
 			/* make the actual HPTE be read-only */
 			ptel = hpte_make_readonly(ptel);

arch/powerpc/mm/copro_fault.c

@@ -64,10 +64,14 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (!(vma->vm_flags & VM_WRITE))
 			goto out_unlock;
 	} else {
-		if (dsisr & DSISR_PROTFAULT)
-			goto out_unlock;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto out_unlock;
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(dsisr & DSISR_PROTFAULT);
 	}
 
 	ret = 0;

arch/powerpc/mm/fault.c

@@ -389,19 +389,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 #endif /* CONFIG_8xx */
 
 	if (is_exec) {
-#ifdef CONFIG_PPC_STD_MMU
-		/* Protection fault on exec go straight to failure on
-		 * Hash based MMUs as they either don't support per-page
-		 * execute permission, or if they do, it's handled already
-		 * at the hash level. This test would probably have to
-		 * be removed if we change the way this works to make hash
-		 * processors use the same I/D cache coherency mechanism
-		 * as embedded.
-		 */
-		if (error_code & DSISR_PROTFAULT)
-			goto bad_area;
-#endif /* CONFIG_PPC_STD_MMU */
-
 		/*
 		 * Allow execution from readable areas if the MMU does not
 		 * provide separate controls over reading and executing.
@@ -416,6 +403,14 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		    (cpu_has_feature(CPU_FTR_NOEXECUTE) ||
 		     !(vma->vm_flags & (VM_READ | VM_WRITE))))
 			goto bad_area;
+#ifdef CONFIG_PPC_STD_MMU
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
+#endif /* CONFIG_PPC_STD_MMU */
 	/* a write */
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -423,11 +418,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
-		/* protection fault */
-		if (error_code & 0x08000000)
-			goto bad_area;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 	}
 
 	/*

arch/powerpc/mm/pgtable.c

@@ -172,9 +172,14 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		pte_t pte)
 {
-#ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_val(*ptep) & _PAGE_PRESENT);
-#endif
+	/*
+	 * When handling numa faults, we already have the pte marked
+	 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
+	 * Hence we can use set_pte_at for them.
+	 */
+	VM_WARN_ON((pte_val(*ptep) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
+
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
 	 * is called.

arch/powerpc/mm/pgtable_64.c

@@ -718,7 +718,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT);
+	WARN_ON((pmd_val(*pmdp) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif

arch/s390/include/asm/string.h

@@ -44,7 +44,6 @@ extern char *strstr(const char *, const char *);
 #undef __HAVE_ARCH_STRCHR
 #undef __HAVE_ARCH_STRNCHR
 #undef __HAVE_ARCH_STRNCMP
-#undef __HAVE_ARCH_STRNICMP
 #undef __HAVE_ARCH_STRPBRK
 #undef __HAVE_ARCH_STRSEP
 #undef __HAVE_ARCH_STRSPN

arch/s390/include/asm/thread_info.h

@@ -39,7 +39,6 @@ struct thread_info {
 	unsigned long		sys_call_table;	/* System call table address */
 	unsigned int		cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-	struct restart_block	restart_block;
 	unsigned int		system_call;
 	__u64			user_timer;
 	__u64			system_timer;
@@ -56,9 +55,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/s390/kernel/compat_signal.c

@@ -209,7 +209,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	int i;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs)))
 		return -EFAULT;

arch/s390/kernel/signal.c

@@ -162,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	_sigregs user_sregs;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs)))
 		return -EFAULT;

arch/score/include/asm/thread_info.h

@@ -42,7 +42,6 @@ struct thread_info {
 	 * 0-0xFFFFFFFF for kernel-thread
 	 */
 	mm_segment_t		addr_limit;
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 };
 
@@ -58,9 +57,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= 1,			\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/score/kernel/asm-offsets.c

@@ -106,7 +106,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(KERNEL_STACK_SIZE, THREAD_SIZE);
 	DEFINE(KERNEL_STACK_MASK, THREAD_MASK);

arch/score/kernel/signal.c

@@ -141,7 +141,7 @@ score_rt_sigreturn(struct pt_regs *regs)
 	int sig;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *) regs->regs[0];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))

arch/sh/include/asm/thread_info.h

@@ -33,7 +33,6 @@ struct thread_info {
 	__u32			cpu;
 	int			preempt_count; /* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 	unsigned long		previous_sp;	/* sp of previous stack in case
 						   of nested IRQ stacks */
 	__u8			supervisor_stack[0];
@@ -63,9 +62,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/sh/kernel/asm-offsets.c

@@ -25,7 +25,6 @@ int main(void)
 	DEFINE(TI_FLAGS,	offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
 	DEFINE(TI_PRE_COUNT,	offsetof(struct thread_info, preempt_count));
-	DEFINE(TI_RESTART_BLOCK,offsetof(struct thread_info, restart_block));
 	DEFINE(TI_SIZE,		sizeof(struct thread_info));
 
 #ifdef CONFIG_HIBERNATION

arch/sh/kernel/signal_32.c

@@ -156,7 +156,7 @@ asmlinkage int sys_sigreturn(void)
 	int r0;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -186,7 +186,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	int r0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;

arch/sh/kernel/signal_64.c

@@ -260,7 +260,7 @@ asmlinkage int sys_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -294,7 +294,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;

arch/sparc/include/asm/thread_info_32.h

@@ -47,8 +47,6 @@ struct thread_info {
 	struct reg_window32	reg_window[NSWINS];	/* align for ldd! */
 	unsigned long		rwbuf_stkptrs[NSWINS];
 	unsigned long		w_saved;
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -62,9 +60,6 @@ struct thread_info {
 	.flags		=	0,			\
 	.cpu		=	0,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -103,7 +98,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TI_REG_WINDOW	0x30
 #define TI_RWIN_SPTRS	0x230
 #define TI_W_SAVED	0x250
-/* #define TI_RESTART_BLOCK 0x25n */ /* Nobody cares */
 
 /*
  * thread information flag bit numbers

arch/sparc/include/asm/thread_info_64.h

@@ -58,8 +58,6 @@ struct thread_info {
 	unsigned long		gsr[7];
 	unsigned long		xfsr[7];
 
-	struct restart_block	restart_block;
-
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
@@ -92,10 +90,9 @@ struct thread_info {
 #define TI_RWIN_SPTRS	0x000003c8
 #define TI_GSR		0x00000400
 #define TI_XFSR		0x00000438
-#define TI_RESTART_BLOCK 0x00000470
-#define TI_KUNA_REGS	0x000004a0
-#define TI_KUNA_INSN	0x000004a8
-#define TI_FPREGS	0x000004c0
+#define TI_KUNA_REGS	0x00000470
+#define TI_KUNA_INSN	0x00000478
+#define TI_FPREGS	0x00000480
 
 /* We embed this in the uppermost byte of thread_info->flags */
 #define FAULT_CODE_WRITE	0x01	/* Write access, implies D-TLB	   */
@@ -124,9 +121,6 @@ struct thread_info {
 	.current_ds	=	ASI_P,			\
 	.exec_domain	=	&default_exec_domain,	\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/sparc/kernel/signal32.c

@@ -150,7 +150,7 @@ void do_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 
@@ -235,7 +235,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 	regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;

arch/sparc/kernel/signal_32.c

@@ -70,7 +70,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 

arch/sparc/kernel/signal_64.c

@@ -254,7 +254,7 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack ();
 	sf = (struct rt_signal_frame __user *)

arch/sparc/kernel/traps_64.c

@@ -2730,8 +2730,6 @@ void __init trap_init(void)
 		     TI_NEW_CHILD != offsetof(struct thread_info, new_child) ||
 		     TI_CURRENT_DS != offsetof(struct thread_info,
 						current_ds) ||
-		     TI_RESTART_BLOCK != offsetof(struct thread_info,
-						  restart_block) ||
 		     TI_KUNA_REGS != offsetof(struct thread_info,
 					      kern_una_regs) ||
 		     TI_KUNA_INSN != offsetof(struct thread_info,

arch/tile/include/asm/thread_info.h

@@ -36,7 +36,6 @@ struct thread_info {
 
 	mm_segment_t		addr_limit;	/* thread address space
 						   (KERNEL_DS or USER_DS) */
-	struct restart_block	restart_block;
 	struct single_step_state *step_state;	/* single step state
 						   (if non-zero) */
 	int			align_ctl;	/* controls unaligned access */
@@ -57,9 +56,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.step_state	= NULL,			\
 	.align_ctl	= 0,			\
 }

arch/tile/kernel/signal.c

@@ -48,7 +48,7 @@ int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Enforce that sigcontext is like pt_regs, and doesn't mess

arch/um/include/asm/thread_info.h

@@ -22,7 +22,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* thread address space:
 					 	   0-0xBFFFFFFF for user
 						   0-0xFFFFFFFF for kernel */
-	struct restart_block    restart_block;
 	struct thread_info	*real_thread;    /* Points to non-IRQ stack */
 };
 
@@ -34,9 +33,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit =	KERNEL_DS,		\
-	.restart_block =  {			\
-		.fn =  do_no_restart_syscall,	\
-	},					\
 	.real_thread = NULL,			\
 }
 

arch/unicore32/include/asm/thread_info.h

@@ -79,7 +79,6 @@ struct thread_info {
 #ifdef CONFIG_UNICORE_FPU_F64
 	struct fp_state		fpstate __attribute__((aligned(8)));
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -89,9 +88,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/unicore32/kernel/signal.c

@@ -105,7 +105,7 @@ asmlinkage int __sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,

arch/x86/ia32/ia32_signal.c

@@ -169,7 +169,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	u32 tmp;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 		/*

arch/x86/include/asm/pgtable.h

@@ -132,13 +132,7 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	/*
-	 * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
-	 * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
-	 * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL.
-	 */
-	return (pte_flags(pte) & _PAGE_SPECIAL) &&
-		(pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
+	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
@@ -300,7 +294,7 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
@@ -442,13 +436,6 @@ static inline int pte_same(pte_t a, pte_t b)
 }
 
 static inline int pte_present(pte_t a)
-{
-	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
-			       _PAGE_NUMA);
-}
-
-#define pte_present_nonuma pte_present_nonuma
-static inline int pte_present_nonuma(pte_t a)
 {
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
@@ -459,7 +446,7 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 	if (pte_flags(a) & _PAGE_PRESENT)
 		return true;
 
-	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+	if ((pte_flags(a) & _PAGE_PROTNONE) &&
 			mm_tlb_flush_pending(mm))
 		return true;
 
@@ -479,10 +466,25 @@ static inline int pmd_present(pmd_t pmd)
 	 * the _PAGE_PSE flag will remain set at all times while the
 	 * _PAGE_PRESENT bit is clear).
 	 */
-	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE |
-				 _PAGE_NUMA);
+	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_PROTNONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_PROTNONE;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 static inline int pmd_none(pmd_t pmd)
 {
 	/* Only check low word on 32-bit platforms, since it might be
@@ -539,11 +541,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-#ifdef CONFIG_NUMA_BALANCING
-	/* pmd_numa check */
-	if ((pmd_flags(pmd) & (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA)
-		return 0;
-#endif
 	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
 }
 
@@ -862,19 +859,16 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 
 static inline int pte_swp_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
 }
 
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 #endif

arch/x86/include/asm/pgtable_64.h

@@ -142,12 +142,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 /* Encode and de-code a swap entry */
 #define SWP_TYPE_BITS 5
-#ifdef CONFIG_NUMA_BALANCING
-/* Automatic NUMA balancing needs to be distinguishable from swap entries */
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2)
-#else
 #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
-#endif
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 

arch/x86/include/asm/pgtable_types.h

@@ -27,14 +27,6 @@
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
-/*
- * Swap offsets on configurations that allow automatic NUMA balancing use the
- * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from
- * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the
- * maximum possible swap space from 16TB to 8TB.
- */
-#define _PAGE_BIT_NUMA		(_PAGE_BIT_GLOBAL+1)
-
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
 /* - if the user mapped it with PROT_NONE; pte_present gives true */
 #define _PAGE_BIT_PROTNONE	_PAGE_BIT_GLOBAL
@@ -75,21 +67,6 @@
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
-/*
- * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page
- * that is not present. The hinting fault gathers numa placement statistics
- * (see pte_numa()). The bit is always zero when the PTE is not present.
- *
- * The bit picked must be always zero when the pmd is present and not
- * present, so that we don't lose information when we set it while
- * atomically clearing the present bit.
- */
-#ifdef CONFIG_NUMA_BALANCING
-#define _PAGE_NUMA	(_AT(pteval_t, 1) << _PAGE_BIT_NUMA)
-#else
-#define _PAGE_NUMA	(_AT(pteval_t, 0))
-#endif
-
 /*
  * Tracking soft dirty bit when a page goes to a swap is tricky.
  * We need a bit which can be stored in pte _and_ not conflict
@@ -122,8 +99,8 @@
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_NUMA)
-#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
+			 _PAGE_SOFT_DIRTY)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
  * The cache modes defined here are used to translate between pure SW usage
@@ -324,20 +301,6 @@ static inline pteval_t pte_flags(pte_t pte)
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-/* Set of bits that distinguishes present, prot_none and numa ptes */
-#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
-static inline pteval_t ptenuma_flags(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_NUMA_MASK;
-}
-
-static inline pmdval_t pmdnuma_flags(pmd_t pmd)
-{
-	return pmd_flags(pmd) & _PAGE_NUMA_MASK;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 

arch/x86/include/asm/thread_info.h

@@ -31,7 +31,6 @@ struct thread_info {
 	__u32			cpu;		/* current CPU */
 	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
-	struct restart_block    restart_block;
 	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
@@ -45,9 +44,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/x86/kernel/hpet.c

@@ -168,7 +168,7 @@ static void _hpet_print_config(const char *function, int line)
 #define hpet_print_config()					\
 do {								\
 	if (hpet_verbose)					\
-		_hpet_print_config(__FUNCTION__, __LINE__);	\
+		_hpet_print_config(__func__, __LINE__);	\
 } while (0)
 
 /*

arch/x86/kernel/rtc.c

@@ -49,11 +49,11 @@ int mach_set_rtc_mmss(const struct timespec *now)
 		retval = set_rtc_time(&tm);
 		if (retval)
 			printk(KERN_ERR "%s: RTC write failed with error %d\n",
-			       __FUNCTION__, retval);
+			       __func__, retval);
 	} else {
 		printk(KERN_ERR
 		       "%s: Invalid RTC value: write of %lx to RTC failed\n",
-			__FUNCTION__, nowtime);
+			__func__, nowtime);
 		retval = -EINVAL;
 	}
 	return retval;

arch/x86/kernel/signal.c

@@ -69,7 +69,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 

arch/x86/mm/gup.c

@@ -84,7 +84,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		struct page *page;
 
 		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_numa(pte)) {
+		if (pte_protnone(pte)) {
 			pte_unmap(ptep);
 			return 0;
 		}
@@ -178,7 +178,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 			 * slowpath for accounting purposes and so that they
 			 * can be serialised against THP migration.
 			 */
-			if (pmd_numa(pmd))
+			if (pmd_protnone(pmd))
 				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;

arch/x86/platform/intel-mid/intel_mid_vrtc.c

@@ -110,7 +110,7 @@ int vrtc_set_mmss(const struct timespec *now)
 		spin_unlock_irqrestore(&rtc_lock, flags);
 	} else {
 		pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n",
-			__FUNCTION__, now->tv_sec);
+			__func__, now->tv_sec);
 		retval = -EINVAL;
 	}
 	return retval;

arch/x86/um/signal.c

@@ -157,7 +157,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 	int err, pid;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = copy_from_user(&sc, from, sizeof(sc));
 	if (err)

arch/xtensa/include/asm/thread_info.h

@@ -51,7 +51,6 @@ struct thread_info {
 	__s32			preempt_count;	/* 0 => preemptable,< 0 => BUG*/
 
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block    restart_block;
 
 	unsigned long		cpenable;
 
@@ -72,7 +71,6 @@ struct thread_info {
 #define TI_CPU		 0x00000010
 #define TI_PRE_COUNT	 0x00000014
 #define TI_ADDR_LIMIT	 0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -90,9 +88,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/xtensa/kernel/signal.c

@@ -245,7 +245,7 @@ asmlinkage long xtensa_rt_sigreturn(long a0, long a1, long a2, long a3,
 	int ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (regs->depc > 64)
 		panic("rt_sigreturn in double exception!\n");

drivers/acpi/acpica/utdebug.c

@@ -111,8 +111,8 @@ void acpi_ut_track_stack_ptr(void)
  * RETURN:      Updated pointer to the function name
  *
  * DESCRIPTION: Remove the "Acpi" prefix from the function name, if present.
- *              This allows compiler macros such as __FUNCTION__ to be used
- *              with no change to the debug output.
+ *              This allows compiler macros such as __func__ to be used with no
+ *              change to the debug output.
  *
  ******************************************************************************/
 

drivers/block/xen-blkfront.c

@@ -1391,7 +1391,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 			if (major != XENVBD_MAJOR) {
 				printk(KERN_INFO
 						"%s: HVM does not support vbd %d as xen block device\n",
-						__FUNCTION__, vdevice);
+						__func__, vdevice);
 				return -ENODEV;
 			}
 		}

drivers/block/zram/zram_drv.c

@@ -53,9 +53,9 @@ static ssize_t name##_show(struct device *d,		\
 }									\
 static DEVICE_ATTR_RO(name);
 
-static inline int init_done(struct zram *zram)
+static inline bool init_done(struct zram *zram)
 {
-	return zram->meta != NULL;
+	return zram->disksize;
 }
 
 static inline struct zram *dev_to_zram(struct device *dev)
@@ -307,42 +307,67 @@ static inline int valid_io_request(struct zram *zram,
 	return 1;
 }
 
-static void zram_meta_free(struct zram_meta *meta)
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
 {
+	size_t num_pages = disksize >> PAGE_SHIFT;
+	size_t index;
+
+	/* Free all pages that are still in this zram device */
+	for (index = 0; index < num_pages; index++) {
+		unsigned long handle = meta->table[index].handle;
+
+		if (!handle)
+			continue;
+
+		zs_free(meta->mem_pool, handle);
+	}
+
 	zs_destroy_pool(meta->mem_pool);
 	vfree(meta->table);
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(u64 disksize)
+static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
 {
 	size_t num_pages;
+	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+
 	if (!meta)
-		goto out;
+		return NULL;
 
 	num_pages = disksize >> PAGE_SHIFT;
 	meta->table = vzalloc(num_pages * sizeof(*meta->table));
 	if (!meta->table) {
 		pr_err("Error allocating zram address table\n");
-		goto free_meta;
+		goto out_error;
 	}
 
-	meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
+	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
-		goto free_table;
+		goto out_error;
 	}
 
 	return meta;
 
-free_table:
+out_error:
 	vfree(meta->table);
-free_meta:
 	kfree(meta);
-	meta = NULL;
-out:
-	return meta;
+	return NULL;
+}
+
+static inline bool zram_meta_get(struct zram *zram)
+{
+	if (atomic_inc_not_zero(&zram->refcount))
+		return true;
+	return false;
+}
+
+static inline void zram_meta_put(struct zram *zram)
+{
+	atomic_dec(&zram->refcount);
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -704,10 +729,11 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 }
 
-static void zram_reset_device(struct zram *zram, bool reset_capacity)
+static void zram_reset_device(struct zram *zram)
 {
-	size_t index;
 	struct zram_meta *meta;
+	struct zcomp *comp;
+	u64 disksize;
 
 	down_write(&zram->init_lock);
 
@@ -719,36 +745,30 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	}
 
 	meta = zram->meta;
-	/* Free all pages that are still in this zram device */
-	for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
-		unsigned long handle = meta->table[index].handle;
-		if (!handle)
-			continue;
-
-		zs_free(meta->mem_pool, handle);
-	}
-
-	zcomp_destroy(zram->comp);
-	zram->max_comp_streams = 1;
+	comp = zram->comp;
+	disksize = zram->disksize;
+	/*
+	 * Refcount will go down to 0 eventually and r/w handler
+	 * cannot handle further I/O so it will bail out by
+	 * check zram_meta_get.
+	 */
+	zram_meta_put(zram);
+	/*
+	 * We want to free zram_meta in process context to avoid
+	 * deadlock between reclaim path and any other locks.
+	 */
+	wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
 
-	zram_meta_free(zram->meta);
-	zram->meta = NULL;
 	/* Reset stats */
 	memset(&zram->stats, 0, sizeof(zram->stats));
-
 	zram->disksize = 0;
-	if (reset_capacity)
-		set_capacity(zram->disk, 0);
+	zram->max_comp_streams = 1;
+	set_capacity(zram->disk, 0);
 
 	up_write(&zram->init_lock);
-
-	/*
-	 * Revalidate disk out of the init_lock to avoid lockdep splat.
-	 * It's okay because disk's capacity is protected by init_lock
-	 * so that revalidate_disk always sees up-to-date capacity.
-	 */
-	if (reset_capacity)
-		revalidate_disk(zram->disk);
+	/* I/O operation under all of CPU are done so let's free */
+	zram_meta_free(meta, disksize);
+	zcomp_destroy(comp);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -765,7 +785,7 @@ static ssize_t disksize_store(struct device *dev,
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(disksize);
+	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
 	if (!meta)
 		return -ENOMEM;
 
@@ -784,6 +804,8 @@ static ssize_t disksize_store(struct device *dev,
 		goto out_destroy_comp;
 	}
 
+	init_waitqueue_head(&zram->io_done);
+	atomic_set(&zram->refcount, 1);
 	zram->meta = meta;
 	zram->comp = comp;
 	zram->disksize = disksize;
@@ -803,7 +825,7 @@ static ssize_t disksize_store(struct device *dev,
 	up_write(&zram->init_lock);
 	zcomp_destroy(comp);
 out_free_meta:
-	zram_meta_free(meta);
+	zram_meta_free(meta, disksize);
 	return err;
 }
 
@@ -821,8 +843,9 @@ static ssize_t reset_store(struct device *dev,
 	if (!bdev)
 		return -ENOMEM;
 
+	mutex_lock(&bdev->bd_mutex);
 	/* Do not reset an active device! */
-	if (bdev->bd_holders) {
+	if (bdev->bd_openers) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -838,12 +861,16 @@ static ssize_t reset_store(struct device *dev,
 
 	/* Make sure all pending I/O is finished */
 	fsync_bdev(bdev);
+	zram_reset_device(zram);
+
+	mutex_unlock(&bdev->bd_mutex);
+	revalidate_disk(zram->disk);
 	bdput(bdev);
 
-	zram_reset_device(zram, true);
 	return len;
 
 out:
+	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	return ret;
 }
@@ -909,23 +936,21 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram)))
+	if (unlikely(!zram_meta_get(zram)))
 		goto error;
 
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		goto error;
+		goto put_zram;
 	}
 
 	__zram_make_request(zram, bio);
-	up_read(&zram->init_lock);
-
+	zram_meta_put(zram);
 	return;
-
+put_zram:
+	zram_meta_put(zram);
 error:
-	up_read(&zram->init_lock);
 	bio_io_error(bio);
 }
 
@@ -947,21 +972,19 @@ static void zram_slot_free_notify(struct block_device *bdev,
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, int rw)
 {
-	int offset, err;
+	int offset, err = -EIO;
 	u32 index;
 	struct zram *zram;
 	struct bio_vec bv;
 
 	zram = bdev->bd_disk->private_data;
+	if (unlikely(!zram_meta_get(zram)))
+		goto out;
+
 	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		return -EINVAL;
-	}
-
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram))) {
-		err = -EIO;
-		goto out_unlock;
+		err = -EINVAL;
+		goto put_zram;
 	}
 
 	index = sector >> SECTORS_PER_PAGE_SHIFT;
@@ -972,8 +995,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_offset = 0;
 
 	err = zram_bvec_rw(zram, &bv, index, offset, rw);
-out_unlock:
-	up_read(&zram->init_lock);
+put_zram:
+	zram_meta_put(zram);
+out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
 	 * calling page_endio.
@@ -1039,19 +1063,19 @@ static struct attribute_group zram_disk_attr_group = {
 
 static int create_device(struct zram *zram, int device_id)
 {
+	struct request_queue *queue;
 	int ret = -ENOMEM;
 
 	init_rwsem(&zram->init_lock);
 
-	zram->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!zram->queue) {
+	queue = blk_alloc_queue(GFP_KERNEL);
+	if (!queue) {
 		pr_err("Error allocating disk queue for device %d\n",
 			device_id);
 		goto out;
 	}
 
-	blk_queue_make_request(zram->queue, zram_make_request);
-	zram->queue->queuedata = zram;
+	blk_queue_make_request(queue, zram_make_request);
 
 	 /* gendisk structure */
 	zram->disk = alloc_disk(1);
@@ -1064,7 +1088,8 @@ static int create_device(struct zram *zram, int device_id)
 	zram->disk->major = zram_major;
 	zram->disk->first_minor = device_id;
 	zram->disk->fops = &zram_devops;
-	zram->disk->queue = zram->queue;
+	zram->disk->queue = queue;
+	zram->disk->queue->queuedata = zram;
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
 
@@ -1115,20 +1140,35 @@ static int create_device(struct zram *zram, int device_id)
 	del_gendisk(zram->disk);
 	put_disk(zram->disk);
 out_free_queue:
-	blk_cleanup_queue(zram->queue);
+	blk_cleanup_queue(queue);
 out:
 	return ret;
 }
 
-static void destroy_device(struct zram *zram)
+static void destroy_devices(unsigned int nr)
 {
-	sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
-			&zram_disk_attr_group);
+	struct zram *zram;
+	unsigned int i;
 
-	del_gendisk(zram->disk);
-	put_disk(zram->disk);
+	for (i = 0; i < nr; i++) {
+		zram = &zram_devices[i];
+		/*
+		 * Remove sysfs first, so no one will perform a disksize
+		 * store while we destroy the devices
+		 */
+		sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+				&zram_disk_attr_group);
+
+		zram_reset_device(zram);
 
-	blk_cleanup_queue(zram->queue);
+		blk_cleanup_queue(zram->disk->queue);
+		del_gendisk(zram->disk);
+		put_disk(zram->disk);
+	}
+
+	kfree(zram_devices);
+	unregister_blkdev(zram_major, "zram");
+	pr_info("Destroyed %u device(s)\n", nr);
 }
 
 static int __init zram_init(void)
@@ -1138,64 +1178,39 @@ static int __init zram_init(void)
 	if (num_devices > max_num_devices) {
 		pr_warn("Invalid value for num_devices: %u\n",
 				num_devices);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	zram_major = register_blkdev(0, "zram");
 	if (zram_major <= 0) {
 		pr_warn("Unable to get major number\n");
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	/* Allocate the device array and initialize each one */
 	zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
 	if (!zram_devices) {
-		ret = -ENOMEM;
-		goto unregister;
+		unregister_blkdev(zram_major, "zram");
+		return -ENOMEM;
 	}
 
 	for (dev_id = 0; dev_id < num_devices; dev_id++) {
 		ret = create_device(&zram_devices[dev_id], dev_id);
 		if (ret)
-			goto free_devices;
+			goto out_error;
 	}
 
-	pr_info("Created %u device(s) ...\n", num_devices);
-
+	pr_info("Created %u device(s)\n", num_devices);
 	return 0;
 
-free_devices:
-	while (dev_id)
-		destroy_device(&zram_devices[--dev_id]);
-	kfree(zram_devices);
-unregister:
-	unregister_blkdev(zram_major, "zram");
-out:
+out_error:
+	destroy_devices(dev_id);
 	return ret;
 }
 
 static void __exit zram_exit(void)
 {
-	int i;
-	struct zram *zram;
-
-	for (i = 0; i < num_devices; i++) {
-		zram = &zram_devices[i];
-
-		destroy_device(zram);
-		/*
-		 * Shouldn't access zram->disk after destroy_device
-		 * because destroy_device already released zram->disk.
-		 */
-		zram_reset_device(zram, false);
-	}
-
-	unregister_blkdev(zram_major, "zram");
-
-	kfree(zram_devices);
-	pr_debug("Cleanup done!\n");
+	destroy_devices(num_devices);
 }
 
 module_init(zram_init);