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 <[e-mail]>: (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

···
 /debian/
 
 #
+# tar directory (make tar*-pkg)
+#
+/tar-install/
+
+#
 # git files that we don't want to ignore even it they are dot-files
 #
 !.gitignore

Documentation/filesystems/proc.txt

···
  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
···
 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
[phone] 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
[phone] default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
[phone] default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
[phone] 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

···
 	int bpt_nsaved;
 	unsigned long bpt_addr[2];		/* breakpoint handling  */
 	unsigned int bpt_insn[2];
-
-	struct restart_block	restart_block;
 };
 
 /*
···
 	.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

···
 	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

···
 	struct exec_domain *exec_domain;/* execution domain */
 	__u32 cpu;			/* current CPU */
 	unsigned long thr_ptr;		/* TLS ptr */
-	struct restart_block restart_block;
 };
 
 /*
···
 	.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

···
 	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

···
 #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

···
 #ifdef CONFIG_ARM_THUMBEE
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
···
 	.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

···
 	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,
···
 	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

···
 	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 */
 };
···
 	.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

···
 	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

···
 	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,
···
 	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

···
 						   saved by debug handler
 						   when setting up
 						   trampoline */
-	struct restart_block	restart_block;
 	__u8			supervisor_stack[0];
 };
 
···
 	.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

···
 	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

···
 	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

···
 	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
···
 	.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

···
 	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

···
 	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;
 };
 
 /*
···
 	.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

···
 	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

···
 	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

···
 	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

···
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 };
 
···
 	.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

···
 #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

···
 						 * 0-0xBFFFFFFF for user-thead
 						 * 0-0xFFFFFFFF for kernel-thread
 						 */
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
···
 	.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

···
 	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

···
 	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

···
 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

···
 	 * 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;
 	/*
···
 	.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

···
 	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

···
 	__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;
···
 	.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

···
 	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

···
 					 	   0-0xBFFFFFFF for user-thread
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
···
 #define TI_CPU		0x00000010
 #define TI_PRE_COUNT	0x00000014
 #define TI_ADDR_LIMIT	0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
···
 	.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

···
 	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

···
 	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__ */
 
···
 	.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

···
 	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)))
···
 	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

···
 	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__ */
···
 	.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

···
 	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

···
 	__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;
 };
···
 	.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

···
 	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

···
 						 * 0x7fffffff for user-thead
 						 * 0xffffffff for kernel-thread
 						 */
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 	long			syscall;	/* syscall number */
 };
···
 	.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

···
 	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

···
 	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

···
 	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

···
 						   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
···
 	.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

···
 	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

···
 	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

···
 					       0-0x7FFFFFFF for user-thead
 					       0-0xFFFFFFFF for kernel-thread
 					     */
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 
 	/* saved context data */
···
 	.cpu		= 0,				\
 	.preempt_count	= 1,				\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block  = {				\
-			  .fn = do_no_restart_syscall,	\
-	},						\
 	.ksp            = 0,                            \
 }
 

arch/openrisc/kernel/signal.c

···
 	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

···
 	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)			\
···
 	.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

···
 		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

···
 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

···
 			 _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

···
 #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

···
 	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 */
···
 	.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

···
 	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);
···
 #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

···
 #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

···
 	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

···
 	/* 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

···
 		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

···
 #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.
···
 		    (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))
···
 		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

···
 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

···
 		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

···
 #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

···
 	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;
···
 	.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

···
 	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

···
 	_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

···
 	 * 0-0xFFFFFFFF for kernel-thread
 	 */
 	mm_segment_t		addr_limit;
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 };
 
···
 	.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

···
 	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

···
 	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

···
 	__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];
···
 	.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

···
 	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

···
 	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;
···
 	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

···
 	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;
···
 	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

···
 	struct reg_window32	reg_window[NSWINS];	/* align for ldd! */
 	unsigned long		rwbuf_stkptrs[NSWINS];
 	unsigned long		w_saved;
-
-	struct restart_block	restart_block;
 };
 
 /*
···
 	.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 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

···
 	unsigned long		gsr[7];
 	unsigned long		xfsr[7];
 
-	struct restart_block	restart_block;
-
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
···
 #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	   */
···
 	.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

···
 	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();
 
···
 	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

···
 	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

···
 	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

···
 		     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

···
 
 	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 */
···
 	.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

···
 	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

···
 	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 */
 };
 
···
 	.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

···
 #ifdef CONFIG_UNICORE_FPU_F64
 	struct fp_state		fpstate __attribute__((aligned(8)));
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
···
 	.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

···
 	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

···
 	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

···
 
 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)
···
 
 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
···
 
 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);
 }
 
···
 	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;
 
···
 	 * 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)
 {
···
 
 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;
 }
 
···
 #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

···
 
 /* 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

···
 #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
···
 #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
  * with swap entry format. On x86 bits 6 and 7 are *not* involved
···
 /* 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
···
 {
 	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

···
 	__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 */
···
 	.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

···
 #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

···
 		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

···
 	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

···
 		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;
 		}
···
 			 * 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

···
 		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

···
 	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

···
 	__s32			preempt_count;	/* 0 => preemptable,< 0 => BUG*/
 
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block    restart_block;
 
 	unsigned long		cpenable;
 
···
 #define TI_CPU		 0x00000010
 #define TI_PRE_COUNT	 0x00000014
 #define TI_ADDR_LIMIT	 0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
···
 	.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

···
 	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

···
  * 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

···
 			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

···
 }									\
 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)
···
 	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)
···
 	}
 }
 
-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);
 
···
 	}
 
 	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;
+	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);
 
-		zs_free(meta->mem_pool, handle);
-	}
-
-	zcomp_destroy(zram->comp);
-	zram->max_comp_streams = 1;
-
-	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,
···
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(disksize);
+	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
 	if (!meta)
 		return -ENOMEM;
 
···
 		goto out_destroy_comp;
 	}
 
+	init_waitqueue_head(&zram->io_done);
+	atomic_set(&zram->refcount, 1);
 	zram->meta = meta;
 	zram->comp = comp;
 	zram->disksize = disksize;
···
 	up_write(&zram->init_lock);
 	zcomp_destroy(comp);
 out_free_meta:
-	zram_meta_free(meta);
+	zram_meta_free(meta, disksize);
 	return err;
 }
 
···
 	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;
 	}
···
 
 	/* 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;
 }
···
 {
 	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);
 }
 
···
 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;
···
 	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.
···
 
 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);
···
 	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);
 
···
 	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);
 
-	blk_cleanup_queue(zram->queue);
+		zram_reset_device(zram);
+
+		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)
···
 	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);

drivers/block/zram/zram_drv.h

···
 
 struct zram {
 	struct zram_meta *meta;
-	struct request_queue *queue;
-	struct gendisk *disk;
 	struct zcomp *comp;
-
-	/* Prevent concurrent execution of device init, reset and R/W request */
+	struct gendisk *disk;
+	/* Prevent concurrent execution of device init */
 	struct rw_semaphore init_lock;
+	/*
+	 * the number of pages zram can consume for storing compressed data
+	 */
+	unsigned long limit_pages;
+	int max_comp_streams;
+
+	struct zram_stats stats;
+	atomic_t refcount; /* refcount for zram_meta */
+	/* wait all IO under all of cpu are done */
+	wait_queue_head_t io_done;
 	/*
 	 * This is the limit on amount of *uncompressed* worth of data
 	 * we can store in a disk.
 	 */
 	u64 disksize;	/* bytes */
-	int max_comp_streams;
-	struct zram_stats stats;
-	/*
-	 * the number of pages zram can consume for storing compressed data
-	 */
-	unsigned long limit_pages;
-
 	char compressor[10];
 };
 #endif

fs/dcache.c

···
  * LRU lists entirely, while shrink_move moves it to the indicated
  * private list.
  */
-static void d_lru_isolate(struct dentry *dentry)
+static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags &= ~DCACHE_LRU_LIST;
 	this_cpu_dec(nr_dentry_unused);
-	list_del_init(&dentry->d_lru);
+	list_lru_isolate(lru, &dentry->d_lru);
 }
 
-static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
+static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
+			      struct list_head *list)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags |= DCACHE_SHRINK_LIST;
-	list_move_tail(&dentry->d_lru, list);
+	list_lru_isolate_move(lru, &dentry->d_lru, list);
 }
 
 /*
···
 	}
 }
 
-static enum lru_status
-dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status dentry_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
···
 	 * another pass through the LRU.
 	 */
 	if (dentry->d_lockref.count) {
-		d_lru_isolate(dentry);
+		d_lru_isolate(lru, dentry);
 		spin_unlock(&dentry->d_lock);
 		return LRU_REMOVED;
 	}
···
 		return LRU_ROTATE;
 	}
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;
···
 /**
  * prune_dcache_sb - shrink the dcache
  * @sb: superblock
- * @nr_to_scan : number of entries to try to free
- * @nid: which node to scan for freeable entities
+ * @sc: shrink control, passed to list_lru_shrink_walk()
  *
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
+ * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
+ * is done when we need more memory and called from the superblock shrinker
  * function.
  *
  * This function may fail to free any resources if all the dentries are in
  * use.
  */
-long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(dispose);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
+				     dentry_lru_isolate, &dispose);
 	shrink_dentry_list(&dispose);
 	return freed;
 }
 
 static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
-						spinlock_t *lru_lock, void *arg)
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
···
 	if (!spin_trylock(&dentry->d_lock))
 		return LRU_SKIP;
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;

fs/drop_caches.c

···
 	iput(toput_inode);
 }
 
-static void drop_slab(void)
-{
-	int nr_objects;
-
-	do {
-		int nid;
-
-		nr_objects = 0;
-		for_each_online_node(nid)
-			nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
-							1000, 1000);
-	} while (nr_objects > 10);
-}
-
 int drop_caches_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {

fs/gfs2/quota.c

···
 }
 
 
-static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock, void *arg)
+static enum lru_status gfs2_qd_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *dispose = arg;
 	struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
···
 
 	if (qd->qd_lockref.count == 0) {
 		lockref_mark_dead(&qd->qd_lockref);
-		list_move(&qd->qd_lru, dispose);
+		list_lru_isolate_move(lru, &qd->qd_lru, dispose);
 	}
 
 	spin_unlock(&qd->qd_lockref.lock);
···
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
-				   &dispose, &sc->nr_to_scan);
+	freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
+				     gfs2_qd_isolate, &dispose);
 
 	gfs2_qd_dispose(&dispose);
 
···
 static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
 					  struct shrink_control *sc)
 {
-	return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
+	return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
 }
 
 struct shrinker gfs2_qd_shrinker = {

fs/inode.c

···
  * LRU does not have strict ordering. Hence we don't want to reclaim inodes
  * with this flag set because they are the inodes that are out of order.
  */
-static enum lru_status
-inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status inode_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct inode	*inode = container_of(item, struct inode, i_lru);
···
 	 */
 	if (atomic_read(&inode->i_count) ||
 	    (inode->i_state & ~I_REFERENCED)) {
-		list_del_init(&inode->i_lru);
+		list_lru_isolate(lru, &inode->i_lru);
 		spin_unlock(&inode->i_lock);
 		this_cpu_dec(nr_unused);
 		return LRU_REMOVED;
···
 
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
-	list_move(&inode->i_lru, freeable);
+	list_lru_isolate_move(lru, &inode->i_lru, freeable);
 	spin_unlock(&inode->i_lock);
 
 	this_cpu_dec(nr_unused);
···
  * to trim from the LRU. Inodes to be freed are moved to a temporary list and
  * then are freed outside inode_lock by dispose_list().
  */
-long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(freeable);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
-				       &freeable, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
+				     inode_lru_isolate, &freeable);
 	dispose_list(&freeable);
 	return freed;
 }

fs/internal.h

···
 struct linux_binprm;
 struct path;
 struct mount;
+struct shrink_control;
 
 /*
  * block_dev.c
···
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
 extern void inode_add_lru(struct inode *inode);
 
 /*
···
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern int d_set_mounted(struct dentry *dentry);
-extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
 
 /*
  * read_write.c

fs/proc/array.c

···
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/string_helpers.h>
 #include <linux/user_namespace.h>
 
 #include <asm/pgtable.h>
···
 
 static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
-	int i;
-	char *buf, *end;
-	char *name;
+	char *buf;
 	char tcomm[sizeof(p->comm)];
 
 	get_task_comm(tcomm, p);
 
 	seq_puts(m, "Name:\t");
-	end = m->buf + m->size;
 	buf = m->buf + m->count;
-	name = tcomm;
-	i = sizeof(tcomm);
-	while (i && (buf < end)) {
-		unsigned char c = *name;
-		name++;
-		i--;
-		*buf = c;
-		if (!c)
-			break;
-		if (c == '\\') {
-			buf++;
-			if (buf < end)
-				*buf++ = c;
-			continue;
-		}
-		if (c == '\n') {
-			*buf++ = '\\';
-			if (buf < end)
-				*buf++ = 'n';
-			continue;
-		}
-		buf++;
-	}
+
+	/* Ignore error for now */
+	string_escape_str(tcomm, &buf, m->size - m->count,
+			  ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+
 	m->count = buf - m->buf;
 	seq_putc(m, '\n');
 }

fs/proc/generic.c

···
 			struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
-	struct proc_dir_entry *de = PROC_I(inode)->pde;
+	struct proc_dir_entry *de = PDE(inode);
 	if (de && de->nlink)
 		set_nlink(inode, de->nlink);
 

fs/proc/inode.c

···
 	put_pid(PROC_I(inode)->pid);
 
 	/* Let go of any associated proc directory entry */
-	de = PROC_I(inode)->pde;
+	de = PDE(inode);
 	if (de)
 		pde_put(de);
 	head = PROC_I(inode)->sysctl;

fs/proc/task_mmu.c

···
 	CLEAR_REFS_ANON,
 	CLEAR_REFS_MAPPED,
 	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_MM_HIWATER_RSS,
 	CLEAR_REFS_LAST,
 };
 
···
 			.mm = mm,
 			.private = &cp,
 		};
+
+		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+			/*
+			 * Writing 5 to /proc/pid/clear_refs resets the peak
+			 * resident set size to this mm's current rss value.
+			 */
+			down_write(&mm->mmap_sem);
+			reset_mm_hiwater_rss(mm);
+			up_write(&mm->mmap_sem);
+			goto out_mm;
+		}
+
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
···
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
+out_mm:
 		mmput(mm);
 	}
 	put_task_struct(task);
···
 	for_each_node_state(nid, N_MEMORY)
 		if (md->node[nid])
 			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
+
+	seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
 out:
 	seq_putc(m, '\n');
 	m_cache_vma(m, vma);

fs/select.c

···
 	if (ret == -EINTR) {
 		struct restart_block *restart_block;
 
-		restart_block = &current_thread_info()->restart_block;
+		restart_block = &current->restart_block;
 		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;

fs/super.c

···
 		return SHRINK_STOP;
 
 	if (sb->s_op->nr_cached_objects)
-		fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
+		fs_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
-	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
 	total_objects = dentries + inodes + fs_objects + 1;
 	if (!total_objects)
 		total_objects = 1;
···
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
 	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
 
 	/*
 	 * prune the dcache first as the icache is pinned by it, then
 	 * prune the icache, followed by the filesystem specific caches
+	 *
+	 * Ensure that we always scan at least one object - memcg kmem
+	 * accounting uses this to fully empty the caches.
 	 */
-	freed = prune_dcache_sb(sb, dentries, sc->nid);
-	freed += prune_icache_sb(sb, inodes, sc->nid);
+	sc->nr_to_scan = dentries + 1;
+	freed = prune_dcache_sb(sb, sc);
+	sc->nr_to_scan = inodes + 1;
+	freed += prune_icache_sb(sb, sc);
 
 	if (fs_objects) {
-		fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
-								total_objects);
-		freed += sb->s_op->free_cached_objects(sb, fs_objects,
-						       sc->nid);
+		sc->nr_to_scan = fs_objects + 1;
+		freed += sb->s_op->free_cached_objects(sb, sc);
 	}
 
 	drop_super(sb);
···
 	 * scalability bottleneck. The counts could get updated
 	 * between super_cache_count and super_cache_scan anyway.
 	 * Call to super_cache_count with shrinker_rwsem held
-	 * ensures the safety of call to list_lru_count_node() and
+	 * ensures the safety of call to list_lru_shrink_count() and
 	 * s_op->nr_cached_objects().
 	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
-		total_objects = sb->s_op->nr_cached_objects(sb,
-						 sc->nid);
+		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	total_objects += list_lru_count_node(&sb->s_dentry_lru,
-						 sc->nid);
-	total_objects += list_lru_count_node(&sb->s_inode_lru,
-						 sc->nid);
+	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
 
 	total_objects = vfs_pressure_ratio(total_objects);
 	return total_objects;
···
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	INIT_LIST_HEAD(&s->s_inodes);
 
-	if (list_lru_init(&s->s_dentry_lru))
+	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
-	if (list_lru_init(&s->s_inode_lru))
+	if (list_lru_init_memcg(&s->s_inode_lru))
 		goto fail;
 
 	init_rwsem(&s->s_umount);
···
 	s->s_shrink.scan_objects = super_cache_scan;
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
-	s->s_shrink.flags = SHRINKER_NUMA_AWARE;
+	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
 	return s;
 
 fail:
···
 		cleancache_invalidate_fs(s);
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
+
+		/*
+		 * Since list_lru_destroy() may sleep, we cannot call it from
+		 * put_super(), where we hold the sb_lock. Therefore we destroy
+		 * the lru lists right now.
+		 */
+		list_lru_destroy(&s->s_dentry_lru);
+		list_lru_destroy(&s->s_inode_lru);
 
 		put_filesystem(fs);
 		put_super(s);

fs/xfs/xfs_buf.c

···
 static enum lru_status
 xfs_buftarg_wait_rele(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 
···
 	 */
 	atomic_set(&bp->b_lru_ref, 0);
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
···
 static enum lru_status
 xfs_buftarg_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 {
···
 	}
 
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
···
 					struct xfs_buftarg, bt_shrinker);
 	LIST_HEAD(dispose);
 	unsigned long		freed;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
-	freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&btp->bt_lru, sc,
+				     xfs_buftarg_isolate, &dispose);
 
 	while (!list_empty(&dispose)) {
 		struct xfs_buf *bp;
···
 {
 	struct xfs_buftarg	*btp = container_of(shrink,
 					struct xfs_buftarg, bt_shrinker);
-	return list_lru_count_node(&btp->bt_lru, sc->nid);
+	return list_lru_shrink_count(&btp->bt_lru, sc);
 }
 
 void

fs/xfs/xfs_qm.c

···
 static enum lru_status
 xfs_qm_dquot_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 		__releases(lru_lock) __acquires(lru_lock)
···
 		XFS_STATS_INC(xs_qm_dqwants);
 
 		trace_xfs_dqreclaim_want(dqp);
-		list_del_init(&dqp->q_lru);
+		list_lru_isolate(lru, &dqp->q_lru);
 		XFS_STATS_DEC(xs_qm_dquot_unused);
 		return LRU_REMOVED;
 	}
···
 	xfs_dqunlock(dqp);
 
 	ASSERT(dqp->q_nrefs == 0);
-	list_move_tail(&dqp->q_lru, &isol->dispose);
+	list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose);
 	XFS_STATS_DEC(xs_qm_dquot_unused);
 	trace_xfs_dqreclaim_done(dqp);
 	XFS_STATS_INC(xs_qm_dqreclaims);
···
 	struct xfs_qm_isolate	isol;
 	unsigned long		freed;
 	int			error;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
 	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
 		return 0;
···
 	INIT_LIST_HEAD(&isol.buffers);
 	INIT_LIST_HEAD(&isol.dispose);
 
-	freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
-					&nr_to_scan);
+	freed = list_lru_shrink_walk(&qi->qi_lru, sc,
+				     xfs_qm_dquot_isolate, &isol);
 
 	error = xfs_buf_delwri_submit(&isol.buffers);
 	if (error)
···
 	struct xfs_quotainfo	*qi = container_of(shrink,
 					struct xfs_quotainfo, qi_shrinker);
 
-	return list_lru_count_node(&qi->qi_lru, sc->nid);
+	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
 /*

fs/xfs/xfs_super.c

···
 static long
 xfs_fs_nr_cached_objects(
 	struct super_block	*sb,
-	int			nid)
+	struct shrink_control	*sc)
 {
 	return xfs_reclaim_inodes_count(XFS_M(sb));
 }
···
 static long
 xfs_fs_free_cached_objects(
 	struct super_block	*sb,
-	long			nr_to_scan,
-	int			nid)
+	struct shrink_control	*sc)
 {
-	return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+	return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
 }
 
 static const struct super_operations xfs_super_operations = {

include/acpi/acoutput.h

···
 /*
  * If ACPI_GET_FUNCTION_NAME was not defined in the compiler-dependent header,
  * define it now. This is the case where there the compiler does not support
- * a __FUNCTION__ macro or equivalent.
+ * a __func__ macro or equivalent.
  */
 #ifndef ACPI_GET_FUNCTION_NAME
 #define ACPI_GET_FUNCTION_NAME          _acpi_function_name
···
  * The Name parameter should be the procedure name as a quoted string.
  * The function name is also used by the function exit macros below.
  * Note: (const char) is used to be compatible with the debug interfaces
- * and macros such as __FUNCTION__.
+ * and macros such as __func__.
  */
 #define ACPI_FUNCTION_NAME(name)        static const char _acpi_function_name[] = #name;
 
 #else
-/* Compiler supports __FUNCTION__ (or equivalent) -- Ignore this macro */
+/* Compiler supports __func__ (or equivalent) -- Ignore this macro */
 
 #define ACPI_FUNCTION_NAME(name)
 #endif				/* ACPI_GET_FUNCTION_NAME */

include/asm-generic/pgtable.h

···
 # define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
-#ifndef pte_present_nonuma
-#define pte_present_nonuma(pte) pte_present(pte)
-#endif
-
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
···
 #endif
 }
 
-#ifdef CONFIG_NUMA_BALANCING
+#ifndef CONFIG_NUMA_BALANCING
 /*
- * _PAGE_NUMA distinguishes between an unmapped page table entry, an entry that
- * is protected for PROT_NONE and a NUMA hinting fault entry. If the
- * architecture defines __PAGE_PROTNONE then it should take that into account
- * but those that do not can rely on the fact that the NUMA hinting scanner
- * skips inaccessible VMAs.
- *
- * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
- * fault triggers on those regions if pte/pmd_numa returns true
- * (because _PAGE_PRESENT is not set).
+ * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
+ * the only case the kernel cares is for NUMA balancing and is only ever set
+ * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
+ * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * is the responsibility of the caller to distinguish between PROT_NONE
+ * protections and NUMA hinting fault protections.
  */
-#ifndef pte_numa
-static inline int pte_numa(pte_t pte)
-{
-	return ptenuma_flags(pte) == _PAGE_NUMA;
-}
-#endif
-
-#ifndef pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
-	return pmdnuma_flags(pmd) == _PAGE_NUMA;
-}
-#endif
-
-/*
- * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
- * because they're called by the NUMA hinting minor page fault. If we
- * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
- * would be forced to set it later while filling the TLB after we
- * return to userland. That would trigger a second write to memory
- * that we optimize away by setting _PAGE_ACCESSED here.
- */
-#ifndef pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	pteval_t val = pte_val(pte);
-
-	val &= ~_PAGE_NUMA;
-	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
-	return __pte(val);
-}
-#endif
-
-#ifndef pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
-	pmdval_t val = pmd_val(pmd);
-
-	val &= ~_PAGE_NUMA;
-	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
-
-	return __pmd(val);
-}
-#endif
-
-#ifndef pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	pteval_t val = pte_val(pte);
-
-	VM_BUG_ON(!(val & _PAGE_PRESENT));
-
-	val &= ~_PAGE_PRESENT;
-	val |= _PAGE_NUMA;
-
-	return __pte(val);
-}
-#endif
-
-#ifndef ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	pte_t ptent = *ptep;
-
-	ptent = pte_mknuma(ptent);
-	set_pte_at(mm, addr, ptep, ptent);
-	return;
-}
-#endif
-
-#ifndef pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
-	pmdval_t val = pmd_val(pmd);
-
-	val &= ~_PAGE_PRESENT;
-	val |= _PAGE_NUMA;
-
-	return __pmd(val);
-}
-#endif
-
-#ifndef pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	pmd_t pmd = *pmdp;
-
-	pmd = pmd_mknuma(pmd);
-	set_pmd_at(mm, addr, pmdp, pmd);
-	return;
-}
-#endif
-#else
-static inline int pmd_numa(pmd_t pmd)
+static inline int pte_protnone(pte_t pte)
 {
 	return 0;
 }
 
-static inline int pte_numa(pte_t pte)
+static inline int pmd_protnone(pmd_t pmd)
 {
 	return 0;
-}
-
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	return pte;
-}
-
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	return pte;
-}
-
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	return;
-}
-
-
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	return ;
 }
 #endif /* CONFIG_NUMA_BALANCING */
 

include/linux/bitmap.h

···
 extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
 			unsigned long *dst, int nbits);
 extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
-		const unsigned long *old, const unsigned long *new, int bits);
+		const unsigned long *old, const unsigned long *new, unsigned int nbits);
 extern int bitmap_bitremap(int oldbit,
 		const unsigned long *old, const unsigned long *new, int bits);
 extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
-		const unsigned long *relmap, int bits);
+		const unsigned long *relmap, unsigned int bits);
 extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
-		int sz, int bits);
+		unsigned int sz, unsigned int nbits);
 extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
 extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
-extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
+extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits);
 extern int bitmap_print_to_pagebuf(bool list, char *buf,
 				   const unsigned long *maskp, int nmaskbits);
 
···
 #define small_const_nbits(nbits) \
 	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
 
-static inline void bitmap_zero(unsigned long *dst, int nbits)
+static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = 0UL;
 	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
 		memset(dst, 0, len);
 	}
 }
 
-static inline void bitmap_fill(unsigned long *dst, int nbits)
+static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	size_t nlongs = BITS_TO_LONGS(nbits);
+	unsigned int nlongs = BITS_TO_LONGS(nbits);
 	if (!small_const_nbits(nbits)) {
-		int len = (nlongs - 1) * sizeof(unsigned long);
+		unsigned int len = (nlongs - 1) * sizeof(unsigned long);
 		memset(dst, 0xff,  len);
 	}
 	dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
 }
 
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-			int nbits)
+			unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src;
 	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
 		memcpy(dst, src, len);
 	}
 }

include/linux/cpumask.h

···
 }
 
 #define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS)
-static inline void __cpus_setall(cpumask_t *dstp, int nbits)
+static inline void __cpus_setall(cpumask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
-static inline void __cpus_clear(cpumask_t *dstp, int nbits)
+static inline void __cpus_clear(cpumask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
···
 
 #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
 static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
 static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS)
 static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
···
 #define cpus_andnot(dst, src1, src2) \
 				__cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
 static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_equal(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_intersects(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_subset(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_empty(src) __cpus_empty(&(src), NR_CPUS)
-static inline int __cpus_empty(const cpumask_t *srcp, int nbits)
+static inline int __cpus_empty(const cpumask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS)
-static inline int __cpus_weight(const cpumask_t *srcp, int nbits)
+static inline int __cpus_weight(const cpumask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }

include/linux/cryptohash.h

···
 #ifndef __CRYPTOHASH_H
 #define __CRYPTOHASH_H
 
+#include <uapi/linux/types.h>
+
 #define SHA_DIGEST_WORDS 5
 #define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
 #define SHA_WORKSPACE_WORDS 16

include/linux/fs.h

···
 	struct dquot **(*get_dquots)(struct inode *);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
-	long (*nr_cached_objects)(struct super_block *, int);
-	long (*free_cached_objects)(struct super_block *, long, int);
+	long (*nr_cached_objects)(struct super_block *,
+				  struct shrink_control *);
+	long (*free_cached_objects)(struct super_block *,
+				    struct shrink_control *);
 };
 
 /*

include/linux/init_task.h

···
 	.nr_cpus_allowed= NR_CPUS,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
+	.restart_block = {						\
+		.fn = do_no_restart_syscall,				\
+	},								\
 	.se		= {						\
 		.group_node 	= LIST_HEAD_INIT(tsk.se.group_node),	\
 	},								\

include/linux/kernel.h

···
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
 
-/* Trap pasters of __FUNCTION__ at compile-time */
-#define __FUNCTION__ (__func__)
-
 /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD

include/linux/list_lru.h

···
 
 #include <linux/list.h>
 #include <linux/nodemask.h>
+#include <linux/shrinker.h>
+
+struct mem_cgroup;
 
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
···
 				   internally, but has to return locked. */
 };
 
-struct list_lru_node {
-	spinlock_t		lock;
+struct list_lru_one {
 	struct list_head	list;
-	/* kept as signed so we can catch imbalance bugs */
+	/* may become negative during memcg reparenting */
 	long			nr_items;
+};
+
+struct list_lru_memcg {
+	/* array of per cgroup lists, indexed by memcg_cache_id */
+	struct list_lru_one	*lru[0];
+};
+
+struct list_lru_node {
+	/* protects all lists on the node, including per cgroup */
+	spinlock_t		lock;
+	/* global list, used for the root cgroup in cgroup aware lrus */
+	struct list_lru_one	lru;
+#ifdef CONFIG_MEMCG_KMEM
+	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+	struct list_lru_memcg	*memcg_lrus;
+#endif
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
 	struct list_lru_node	*node;
-	nodemask_t		active_nodes;
+#ifdef CONFIG_MEMCG_KMEM
+	struct list_head	list;
+#endif
 };
 
 void list_lru_destroy(struct list_lru *lru);
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
-static inline int list_lru_init(struct list_lru *lru)
-{
-	return list_lru_init_key(lru, NULL);
-}
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+		    struct lock_class_key *key);
+
+#define list_lru_init(lru)		__list_lru_init((lru), false, NULL)
+#define list_lru_init_key(lru, key)	__list_lru_init((lru), false, (key))
+#define list_lru_init_memcg(lru)	__list_lru_init((lru), true, NULL)
+
+int memcg_update_all_list_lrus(int num_memcgs);
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx);
 
 /**
  * list_lru_add: add an element to the lru list's tail
···
 bool list_lru_del(struct list_lru *lru, struct list_head *item);
 
 /**
- * list_lru_count_node: return the number of objects currently held by @lru
+ * list_lru_count_one: return the number of objects currently held by @lru
  * @lru: the lru pointer.
  * @nid: the node id to count from.
+ * @memcg: the cgroup to count from.
  *
  * Always return a non-negative number, 0 for empty lists. There is no
  * guarantee that the list is not updated while the count is being computed.
  * Callers that want such a guarantee need to provide an outer lock.
  */
+unsigned long list_lru_count_one(struct list_lru *lru,
+				 int nid, struct mem_cgroup *memcg);
 unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+						  struct shrink_control *sc)
+{
+	return list_lru_count_one(lru, sc->nid, sc->memcg);
+}
+
 static inline unsigned long list_lru_count(struct list_lru *lru)
 {
 	long count = 0;
 	int nid;
 
-	for_each_node_mask(nid, lru->active_nodes)
+	for_each_node_state(nid, N_NORMAL_MEMORY)
 		count += list_lru_count_node(lru, nid);
 
 	return count;
 }
 
-typedef enum lru_status
-(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+			   struct list_head *head);
+
+typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
+		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
+
 /**
- * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
+ * @memcg: the cgroup to scan from.
  * @isolate: callback function that is resposible for deciding what to do with
  *  the item currently being scanned
  * @cb_arg: opaque type that will be passed to @isolate
···
  *
  * Return value: the number of objects effectively removed from the LRU.
  */
+unsigned long list_lru_walk_one(struct list_lru *lru,
+				int nid, struct mem_cgroup *memcg,
+				list_lru_walk_cb isolate, void *cb_arg,
+				unsigned long *nr_to_walk);
 unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
 				 list_lru_walk_cb isolate, void *cb_arg,
 				 unsigned long *nr_to_walk);
+
+static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+		     list_lru_walk_cb isolate, void *cb_arg)
+{
+	return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg,
+				 &sc->nr_to_scan);
+}
 
 static inline unsigned long
 list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
···
 	long isolated = 0;
 	int nid;
 
-	for_each_node_mask(nid, lru->active_nodes) {
+	for_each_node_state(nid, N_NORMAL_MEMORY) {
 		isolated += list_lru_walk_node(lru, nid, isolate,
 					       cb_arg, &nr_to_walk);
 		if (nr_to_walk <= 0)

include/linux/memcontrol.h

···
 #ifdef CONFIG_MEMCG_KMEM
 extern struct static_key memcg_kmem_enabled_key;
 
-extern int memcg_limited_groups_array_size;
+extern int memcg_nr_cache_ids;
+extern void memcg_get_cache_ids(void);
+extern void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
···
  * the slab_mutex must be held when looping through those caches
  */
 #define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
+	for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
 
 static inline bool memcg_kmem_enabled(void)
 {
 	return static_key_false(&memcg_kmem_enabled_key);
 }
+
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
 
 /*
  * In general, we'll do everything in our power to not incur in any overhead
···
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-void memcg_update_array_size(int num_groups);
-
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
+
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
 
 int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		      unsigned long nr_pages);
···
 	if (memcg_kmem_enabled())
 		__memcg_kmem_put_cache(cachep);
 }
+
+static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+	if (!memcg_kmem_enabled())
+		return NULL;
+	return __mem_cgroup_from_kmem(ptr);
+}
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
 
 static inline bool memcg_kmem_enabled(void)
+{
+	return false;
+}
+
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 {
 	return false;
 }
···
 	return -1;
 }
 
+static inline void memcg_get_cache_ids(void)
+{
+}
+
+static inline void memcg_put_cache_ids(void)
+{
+}
+
 static inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
···
 
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
+}
+
+static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+	return NULL;
 }
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */

include/linux/migrate.h

···
 
 #ifdef CONFIG_NUMA_BALANCING
 extern bool pmd_trans_migrating(pmd_t pmd);
-extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
 extern int migrate_misplaced_page(struct page *page,
 				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
···
 static inline bool pmd_trans_migrating(pmd_t pmd)
 {
 	return false;
-}
-static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
-{
 }
 static inline int migrate_misplaced_page(struct page *page,
 					 struct vm_area_struct *vma, int node)

include/linux/mm.h

···
 		mm->hiwater_vm = mm->total_vm;
 }
 
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+	mm->hiwater_rss = get_mm_rss(mm);
+}
+
 static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 					 struct mm_struct *mm)
 {
···
 int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
 #endif
 
-#ifdef __PAGETABLE_PMD_FOLDED
+#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
 static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 						unsigned long address)
 {
 	return 0;
 }
+
+static inline void mm_nr_pmds_init(struct mm_struct *mm) {}
 
 static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
 {
···
 
 #else
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+
+static inline void mm_nr_pmds_init(struct mm_struct *mm)
+{
+	atomic_long_set(&mm->nr_pmds, 0);
+}
 
 static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
 {
···
 					void __user *, size_t *, loff_t *);
 #endif
 
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
-				unsigned long nr_scanned,
-				unsigned long nr_eligible);
+void drop_slab(void);
+void drop_slab_node(int nid);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0

include/linux/nodemask.h

···
 }
 
 #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
-static inline void __nodes_setall(nodemask_t *dstp, int nbits)
+static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
-static inline void __nodes_clear(nodemask_t *dstp, int nbits)
+static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
···
 #define nodes_and(dst, src1, src2) \
 			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_or(dst, src1, src2) \
 			__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_xor(dst, src1, src2) \
 			__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_andnot(dst, src1, src2) \
 			__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_complement(dst, src) \
 			__nodes_complement(&(dst), &(src), MAX_NUMNODES)
 static inline void __nodes_complement(nodemask_t *dstp,
-					const nodemask_t *srcp, int nbits)
+					const nodemask_t *srcp, unsigned int nbits)
 {
 	bitmap_complement(dstp->bits, srcp->bits, nbits);
 }
···
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_equal(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_intersects(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
 }
···
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_subset(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, int nbits)
+static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, int nbits)
+static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
 
 #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_weight(const nodemask_t *srcp, int nbits)
+static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }

include/linux/printk.h

···
 	DUMP_PREFIX_ADDRESS,
 	DUMP_PREFIX_OFFSET
 };
-extern void hex_dump_to_buffer(const void *buf, size_t len,
-			       int rowsize, int groupsize,
-			       char *linebuf, size_t linebuflen, bool ascii);
+extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
+			      int groupsize, char *linebuf, size_t linebuflen,
+			      bool ascii);
 #ifdef CONFIG_PRINTK
 extern void print_hex_dump(const char *level, const char *prefix_str,
 			   int prefix_type, int rowsize, int groupsize,

include/linux/sched.h

···
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
+	struct restart_block restart_block;
+
 	pid_t pid;
 	pid_t tgid;
 
···
  */
 extern u64 cpu_clock(int cpu);
 extern u64 local_clock(void);
+extern u64 running_clock(void);
 extern u64 sched_clock_cpu(int cpu);
 
 

include/linux/shrinker.h

···
 
 	/* current node being shrunk (for NUMA aware shrinkers) */
 	int nid;
+
+	/* current memcg being shrunk (for memcg aware shrinkers) */
+	struct mem_cgroup *memcg;
 };
 
 #define SHRINK_STOP (~0UL)
···
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
 
 /* Flags */
-#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_NUMA_AWARE	(1 << 0)
+#define SHRINKER_MEMCG_AWARE	(1 << 1)
 
 extern int register_shrinker(struct shrinker *);
 extern void unregister_shrinker(struct shrinker *);

include/linux/slab.h

···
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
-#ifdef CONFIG_MEMCG_KMEM
-void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
-void memcg_destroy_kmem_caches(struct mem_cgroup *);
-#endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
-void kmem_cache_free(struct kmem_cache *, void *);
+
+void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
+void memcg_deactivate_kmem_caches(struct mem_cgroup *);
+void memcg_destroy_kmem_caches(struct mem_cgroup *);
 
 /*
  * Please use this macro to create slab caches. Simply specify the
···
 
 void *__kmalloc(size_t size, gfp_t flags);
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags);
+void kmem_cache_free(struct kmem_cache *, void *);
 
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node);
···
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
+
+struct memcg_cache_array {
+	struct rcu_head rcu;
+	struct kmem_cache *entries[0];
+};
+
 /*
  * This is the main placeholder for memcg-related information in kmem caches.
- * struct kmem_cache will hold a pointer to it, so the memory cost while
- * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
- * would otherwise be if that would be bundled in kmem_cache: we'll need an
- * extra pointer chase. But the trade off clearly lays in favor of not
- * penalizing non-users.
- *
  * Both the root cache and the child caches will have it. For the root cache,
  * this will hold a dynamically allocated array large enough to hold
  * information about the currently limited memcgs in the system. To allow the
···
  *
  * @memcg: pointer to the memcg this cache belongs to
  * @root_cache: pointer to the global, root cache, this cache was derived from
+ *
+ * Both root and child caches of the same kind are linked into a list chained
+ * through @list.
  */
 struct memcg_cache_params {
 	bool is_root_cache;
+	struct list_head list;
 	union {
-		struct {
-			struct rcu_head rcu_head;
-			struct kmem_cache *memcg_caches[0];
-		};
+		struct memcg_cache_array __rcu *memcg_caches;
 		struct {
 			struct mem_cgroup *memcg;
 			struct kmem_cache *root_cache;

include/linux/slab_def.h

···
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 #endif
 
 	struct kmem_cache_node *node[MAX_NUMNODES];

include/linux/slub_def.h

···
 	struct kobject kobj;	/* For sysfs */
 #endif
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
 #ifdef CONFIG_SYSFS
 	struct kset *memcg_kset;

include/linux/string.h

···
 #ifndef __HAVE_ARCH_STRNCMP
 extern int strncmp(const char *,const char *,__kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_STRNICMP
-#define strnicmp strncasecmp
-#endif
 #ifndef __HAVE_ARCH_STRCASECMP
 extern int strcasecmp(const char *s1, const char *s2);
 #endif

include/linux/string_helpers.h

···
 	STRING_UNITS_2,		/* use binary powers of 2^10 */
 };
 
-int string_get_size(u64 size, enum string_size_units units,
-		    char *buf, int len);
+void string_get_size(u64 size, enum string_size_units units,
+		     char *buf, int len);
 
 #define UNESCAPE_SPACE		0x01
 #define UNESCAPE_OCTAL		0x02

include/linux/swapops.h

···
 /* check whether a pte points to a swap entry */
 static inline int is_swap_pte(pte_t pte)
 {
-	return !pte_none(pte) && !pte_present_nonuma(pte);
+	return !pte_none(pte) && !pte_present(pte);
 }
 #endif
 

include/linux/types.h

···
 #endif
 
 /*
- * The type of an index into the pagecache.  Use a #define so asm/types.h
- * can override it.
+ * The type of an index into the pagecache.
  */
-#ifndef pgoff_t
 #define pgoff_t unsigned long
-#endif
 
 /* A dma_addr_t can hold any valid DMA or bus address for the platform */
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT

include/linux/zpool.h

···
 	ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
 };
 
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+struct zpool *zpool_create_pool(char *type, char *name,
+			gfp_t gfp, struct zpool_ops *ops);
 
 char *zpool_get_type(struct zpool *pool);
 
···
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+	void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops);
 	void (*destroy)(void *pool);
 
 	int (*malloc)(void *pool, size_t size, gfp_t gfp,

include/linux/zsmalloc.h

···
 
 struct zs_pool;
 
-struct zs_pool *zs_create_pool(gfp_t flags);
+struct zs_pool *zs_create_pool(char *name, gfp_t flags);
 void zs_destroy_pool(struct zs_pool *pool);
 
 unsigned long zs_malloc(struct zs_pool *pool, size_t size);

include/net/sock.h

···
 	return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
 }
 
-static inline bool memcg_proto_activated(struct cg_proto *cg_proto)
-{
-	return test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags);
-}
-
 #ifdef SOCK_REFCNT_DEBUG
 static inline void sk_refcnt_debug_inc(struct sock *sk)
 {

include/uapi/linux/mempolicy.h

···
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
-#define MPOL_F_MORON	(1 << 4) /* Migrate On pte_numa Reference On Node */
+#define MPOL_F_MORON	(1 << 4) /* Migrate On protnone Reference On Node */
 
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */

kernel/cgroup.c

···
 {
 	struct cgroup_subsys_state *css =
 		container_of(work, struct cgroup_subsys_state, destroy_work);
+	struct cgroup_subsys *ss = css->ss;
 	struct cgroup *cgrp = css->cgroup;
 
 	percpu_ref_exit(&css->refcnt);
 
-	if (css->ss) {
+	if (ss) {
 		/* css free path */
+		int id = css->id;
+
 		if (css->parent)
 			css_put(css->parent);
 
-		css->ss->css_free(css);
+		ss->css_free(css);
+		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
 	} else {
 		/* cgroup free path */
···
 
 	if (ss) {
 		/* css release path */
-		cgroup_idr_remove(&ss->css_idr, css->id);
+		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
 	} else {

kernel/compat.c

···
 	 * core implementation decides to return random nonsense.
 	 */
 	if (ret == -ERESTART_RESTARTBLOCK) {
-		struct restart_block *restart
-			= &current_thread_info()->restart_block;
+		struct restart_block *restart = &current->restart_block;
 
 		restart->fn = compat_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
···
 		return -EFAULT;
 
 	if (err == -ERESTART_RESTARTBLOCK) {
-		restart = &current_thread_info()->restart_block;
+		restart = &current->restart_block;
 		restart->fn = compat_clock_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
 	}

kernel/cpuset.c

···
 	 */
 }
 
-void cpuset_init_current_mems_allowed(void)
+void __init cpuset_init_current_mems_allowed(void)
 {
 	nodes_setall(current->mems_allowed);
 }

kernel/fork.c

···
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
-#ifndef __PAGETABLE_PMD_FOLDED
-	atomic_long_set(&mm->nr_pmds, 0);
-#endif
+	mm_nr_pmds_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
 	mm->pinned_vm = 0;

kernel/futex.c

···
 	if (!abs_time)
 		goto out;
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;

kernel/printk/printk.c

···
 
 early_param("ignore_loglevel", ignore_loglevel_setup);
 module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to"
-	"print all kernel messages to the console.");
+MODULE_PARM_DESC(ignore_loglevel,
+		 "ignore loglevel setting (prints all kernel messages to the console)");
 
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 
···
 }
 
 /*
- * Zap console related locks when oopsing. Only zap at most once
- * every 10 seconds, to leave time for slow consoles to print a
- * full oops.
+ * Zap console related locks when oopsing.
+ * To leave time for slow consoles to print a full oops,
+ * only zap at most once every 30 seconds.
  */
 static void zap_locks(void)
 {
 	static unsigned long oops_timestamp;
 
 	if (time_after_eq(jiffies, oops_timestamp) &&
-			!time_after(jiffies, oops_timestamp + 30 * HZ))
+	    !time_after(jiffies, oops_timestamp + 30 * HZ))
 		return;
 
 	oops_timestamp = jiffies;

kernel/sched/clock.c

···
 
 EXPORT_SYMBOL_GPL(cpu_clock);
 EXPORT_SYMBOL_GPL(local_clock);
+
+/*
+ * Running clock - returns the time that has elapsed while a guest has been
+ * running.
+ * On a guest this value should be local_clock minus the time the guest was
+ * suspended by the hypervisor (for any reason).
+ * On bare metal this function should return the same as local_clock.
+ * Architectures and sub-architectures can override this.
+ */
+u64 __weak running_clock(void)
+{
+	return local_clock();
+}

kernel/signal.c

···
  */
 SYSCALL_DEFINE0(restart_syscall)
 {
-	struct restart_block *restart = &current_thread_info()->restart_block;
+	struct restart_block *restart = &current->restart_block;
 	return restart->fn(restart);
 }
 

kernel/time/alarmtimer.c

···
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp.tv64;

kernel/time/hrtimer.c

···
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.rmtp = rmtp;

kernel/time/posix-cpu-timers.c

···
 static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
-	struct restart_block *restart_block =
-		&current_thread_info()->restart_block;
+	struct restart_block *restart_block = &current->restart_block;
 	struct itimerspec it;
 	int error;
 

kernel/watchdog.c

···
  */
 static unsigned long get_timestamp(void)
 {
-	return local_clock() >> 30LL;  /* 2^30 ~= 10^9 */
+	return running_clock() >> 30LL;  /* 2^30 ~= 10^9 */
 }
 
 static void set_sample_period(void)

lib/Kconfig.debug

···
 
 	  If unsure, say N.
 
+config TEST_HEXDUMP
+	tristate "Test functions located in the hexdump module at runtime"
+
 config TEST_STRING_HELPERS
 	tristate "Test functions located in the string_helpers module at runtime"
 

lib/Makefile

···
 obj-y	+= lockref.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
-	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
+	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
+obj-y += hexdump.o
+obj-$(CONFIG_TEST_HEXDUMP) += test-hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LKM) += test_module.o

lib/bitmap.c

···
 /**
  * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
  *	@buf: pointer to a bitmap
- *	@pos: a bit position in @buf (0 <= @pos < @bits)
- *	@bits: number of valid bit positions in @buf
+ *	@pos: a bit position in @buf (0 <= @pos < @nbits)
+ *	@nbits: number of valid bit positions in @buf
  *
- * Map the bit at position @pos in @buf (of length @bits) to the
+ * Map the bit at position @pos in @buf (of length @nbits) to the
  * ordinal of which set bit it is.  If it is not set or if @pos
  * is not a valid bit position, map to -1.
  *
···
  *
  * The bit positions 0 through @bits are valid positions in @buf.
  */
-static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
+static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits)
 {
-	int i, ord;
-
-	if (pos < 0 || pos >= bits || !test_bit(pos, buf))
+	if (pos >= nbits || !test_bit(pos, buf))
 		return -1;
 
-	i = find_first_bit(buf, bits);
-	ord = 0;
-	while (i < pos) {
-		i = find_next_bit(buf, bits, i + 1);
-	     	ord++;
-	}
-	BUG_ON(i != pos);
-
-	return ord;
+	return __bitmap_weight(buf, pos);
 }
 
 /**
  * bitmap_ord_to_pos - find position of n-th set bit in bitmap
  *	@buf: pointer to bitmap
  *	@ord: ordinal bit position (n-th set bit, n >= 0)
- *	@bits: number of valid bit positions in @buf
+ *	@nbits: number of valid bit positions in @buf
  *
  * Map the ordinal offset of bit @ord in @buf to its position in @buf.
- * Value of @ord should be in range 0 <= @ord < weight(buf), else
- * results are undefined.
+ * Value of @ord should be in range 0 <= @ord < weight(buf). If @ord
+ * >= weight(buf), returns @nbits.
  *
  * If for example, just bits 4 through 7 are set in @buf, then @ord
  * values 0 through 3 will get mapped to 4 through 7, respectively,
- * and all other @ord values return undefined values.  When @ord value 3
+ * and all other @ord values returns @nbits.  When @ord value 3
  * gets mapped to (returns) @pos value 7 in this example, that means
  * that the 3rd set bit (starting with 0th) is at position 7 in @buf.
  *
- * The bit positions 0 through @bits are valid positions in @buf.
+ * The bit positions 0 through @nbits-1 are valid positions in @buf.
  */
-int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
+unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits)
 {
-	int pos = 0;
+	unsigned int pos;
 
-	if (ord >= 0 && ord < bits) {
-		int i;
-
-		for (i = find_first_bit(buf, bits);
-		     i < bits && ord > 0;
-		     i = find_next_bit(buf, bits, i + 1))
-	     		ord--;
-		if (i < bits && ord == 0)
-			pos = i;
-	}
+	for (pos = find_first_bit(buf, nbits);
+	     pos < nbits && ord;
+	     pos = find_next_bit(buf, nbits, pos + 1))
+		ord--;
 
 	return pos;
 }
···
  *	@src: subset to be remapped
  *	@old: defines domain of map
  *	@new: defines range of map
- *	@bits: number of bits in each of these bitmaps
+ *	@nbits: number of bits in each of these bitmaps
  *
  * Let @old and @new define a mapping of bit positions, such that
  * whatever position is held by the n-th set bit in @old is mapped
···
  */
 void bitmap_remap(unsigned long *dst, const unsigned long *src,
 		const unsigned long *old, const unsigned long *new,
-		int bits)
+		unsigned int nbits)
 {
-	int oldbit, w;
+	unsigned int oldbit, w;
 
 	if (dst == src)		/* following doesn't handle inplace remaps */
 		return;
-	bitmap_zero(dst, bits);
+	bitmap_zero(dst, nbits);
 
-	w = bitmap_weight(new, bits);
-	for_each_set_bit(oldbit, src, bits) {
-	     	int n = bitmap_pos_to_ord(old, oldbit, bits);
+	w = bitmap_weight(new, nbits);
+	for_each_set_bit(oldbit, src, nbits) {
+		int n = bitmap_pos_to_ord(old, oldbit, nbits);
 
 		if (n < 0 || w == 0)
 			set_bit(oldbit, dst);	/* identity map */
 		else
-			set_bit(bitmap_ord_to_pos(new, n % w, bits), dst);
+			set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst);
 	}
 }
 EXPORT_SYMBOL(bitmap_remap);
···
  * All bits in @dst not set by the above rule are cleared.
  */
 void bitmap_onto(unsigned long *dst, const unsigned long *orig,
-			const unsigned long *relmap, int bits)
+			const unsigned long *relmap, unsigned int bits)
 {
-	int n, m;       	/* same meaning as in above comment */
+	unsigned int n, m;	/* same meaning as in above comment */
 
 	if (dst == orig)	/* following doesn't handle inplace mappings */
 		return;
···
  *	@dst: resulting smaller bitmap
  *	@orig: original larger bitmap
  *	@sz: specified size
- *	@bits: number of bits in each of these bitmaps
+ *	@nbits: number of bits in each of these bitmaps
  *
  * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
  * Clear all other bits in @dst.  See further the comment and
  * Example [2] for bitmap_onto() for why and how to use this.
  */
 void bitmap_fold(unsigned long *dst, const unsigned long *orig,
-			int sz, int bits)
+			unsigned int sz, unsigned int nbits)
 {
-	int oldbit;
+	unsigned int oldbit;
 
 	if (dst == orig)	/* following doesn't handle inplace mappings */
 		return;
-	bitmap_zero(dst, bits);
+	bitmap_zero(dst, nbits);
 
-	for_each_set_bit(oldbit, orig, bits)
+	for_each_set_bit(oldbit, orig, nbits)
 		set_bit(oldbit % sz, dst);
 }
 EXPORT_SYMBOL(bitmap_fold);

lib/dynamic_queue_limits.c

···
  *
  * Copyright (c) 2011, Tom Herbert <[e-mail]>
  */
-#include <linux/module.h>
 #include <linux/types.h>
-#include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
 #include <linux/dynamic_queue_limits.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
 #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)

lib/genalloc.c

···
 #include <linux/rculist.h>
 #include <linux/interrupt.h>
 #include <linux/genalloc.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 
 static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
···
 			size_t size)
 {
 	bool found = false;
-	unsigned long end = start + size;
+	unsigned long end = start + size - 1;
 	struct gen_pool_chunk *chunk;
 
 	rcu_read_lock();

lib/halfmd4.c

···
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/cryptohash.h>
 

lib/hexdump.c

···
  *
  * example output buffer:
  * 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f  @ABCDEFGHIJKLMNO
+ *
+ * Return:
+ * The amount of bytes placed in the buffer without terminating NUL. If the
+ * output was truncated, then the return value is the number of bytes
+ * (excluding the terminating NUL) which would have been written to the final
+ * string if enough space had been available.
  */
-void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
-			int groupsize, char *linebuf, size_t linebuflen,
-			bool ascii)
+int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize,
+		       char *linebuf, size_t linebuflen, bool ascii)
 {
 	const u8 *ptr = buf;
+	int ngroups;
 	u8 ch;
 	int j, lx = 0;
 	int ascii_column;
+	int ret;
 
 	if (rowsize != 16 && rowsize != 32)
 		rowsize = 16;
 
-	if (!len)
-		goto nil;
 	if (len > rowsize)		/* limit to one line at a time */
 		len = rowsize;
+	if (!is_power_of_2(groupsize) || groupsize > 8)
+		groupsize = 1;
 	if ((len % groupsize) != 0)	/* no mixed size output */
 		groupsize = 1;
 
-	switch (groupsize) {
-	case 8: {
+	ngroups = len / groupsize;
+	ascii_column = rowsize * 2 + rowsize / groupsize + 1;
+
+	if (!linebuflen)
+		goto overflow1;
+
+	if (!len)
+		goto nil;
+
+	if (groupsize == 8) {
 		const u64 *ptr8 = buf;
-		int ngroups = len / groupsize;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%16.16llx", j ? " " : "",
-					(unsigned long long)*(ptr8 + j));
-		ascii_column = 17 * ngroups + 2;
-		break;
-	}
-
-	case 4: {
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%16.16llx", j ? " " : "",
+				       (unsigned long long)*(ptr8 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else if (groupsize == 4) {
 		const u32 *ptr4 = buf;
-		int ngroups = len / groupsize;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%8.8x", j ? " " : "", *(ptr4 + j));
-		ascii_column = 9 * ngroups + 2;
-		break;
-	}
-
-	case 2: {
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%8.8x", j ? " " : "",
+				       *(ptr4 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else if (groupsize == 2) {
 		const u16 *ptr2 = buf;
-		int ngroups = len / groupsize;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%4.4x", j ? " " : "", *(ptr2 + j));
-		ascii_column = 5 * ngroups + 2;
-		break;
-	}
-
-	default:
-		for (j = 0; (j < len) && (lx + 3) <= linebuflen; j++) {
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%4.4x", j ? " " : "",
+				       *(ptr2 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else {
+		for (j = 0; j < len; j++) {
+			if (linebuflen < lx + 3)
+				goto overflow2;
 			ch = ptr[j];
 			linebuf[lx++] = hex_asc_hi(ch);
 			linebuf[lx++] = hex_asc_lo(ch);
···
 		}
 		if (j)
 			lx--;
-
-		ascii_column = 3 * rowsize + 2;
-		break;
 	}
 	if (!ascii)
 		goto nil;
 
-	while (lx < (linebuflen - 1) && lx < (ascii_column - 1))
+	while (lx < ascii_column) {
+		if (linebuflen < lx + 2)
+			goto overflow2;
 		linebuf[lx++] = ' ';
-	for (j = 0; (j < len) && (lx + 2) < linebuflen; j++) {
+	}
+	for (j = 0; j < len; j++) {
+		if (linebuflen < lx + 2)
+			goto overflow2;
 		ch = ptr[j];
 		linebuf[lx++] = (isascii(ch) && isprint(ch)) ? ch : '.';
 	}
 nil:
+	linebuf[lx] = '\0';
+	return lx;
+overflow2:
 	linebuf[lx++] = '\0';
+overflow1:
+	return ascii ? ascii_column + len : (groupsize * 2 + 1) * ngroups - 1;
 }
 EXPORT_SYMBOL(hex_dump_to_buffer);
 

lib/idr.c

···
 #include <linux/idr.h>
 #include <linux/spinlock.h>
 #include <linux/percpu.h>
-#include <linux/hardirq.h>
 
 #define MAX_IDR_SHIFT		(sizeof(int) * 8 - 1)
 #define MAX_IDR_BIT		(1U << MAX_IDR_SHIFT)

lib/interval_tree.c

···
-#include <linux/init.h>
 #include <linux/interval_tree.h>
 #include <linux/interval_tree_generic.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 #define START(node) ((node)->start)
 #define LAST(node)  ((node)->last)

lib/kobject_uevent.c

···
 #include <linux/export.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/user_namespace.h>
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>

lib/lcm.c

···
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/gcd.h>
 #include <linux/export.h>
 #include <linux/lcm.h>

lib/list_sort.c

···
 #define pr_fmt(fmt) "list_sort_test: " fmt
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/string.h>
 #include <linux/list_sort.h>
-#include <linux/slab.h>
 #include <linux/list.h>
 
 #define MAX_LIST_LENGTH_BITS 20
···
 
 #ifdef CONFIG_TEST_LIST_SORT
 
+#include <linux/slab.h>
 #include <linux/random.h>
 
 /*

lib/llist.c

···
  */
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <linux/interrupt.h>
 #include <linux/llist.h>
 
 

lib/md5.c

···
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/cryptohash.h>
 

lib/nlattr.c

···
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/jiffies.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/string.h>
 #include <linux/types.h>

lib/percpu_ida.c

···
 #include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/export.h>
-#include <linux/hardirq.h>
-#include <linux/idr.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/percpu_ida.h>

lib/plist.c

···
 
 #include <linux/bug.h>
 #include <linux/plist.h>
-#include <linux/spinlock.h>
 
 #ifdef CONFIG_DEBUG_PI_LIST
 

lib/radix-tree.c

···
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
-#include <linux/hardirq.h>		/* in_interrupt() */
+#include <linux/preempt_mask.h>		/* in_interrupt() */
 
 
 /*

lib/show_mem.c

···
  */
 
 #include <linux/mm.h>
-#include <linux/nmi.h>
 #include <linux/quicklist.h>
 #include <linux/cma.h>
 

lib/sort.c

···
  * Jan 23 2005  Matt Mackall <[e-mail]>
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/export.h>
 #include <linux/sort.h>
-#include <linux/slab.h>
 
 static void u32_swap(void *a, void *b, int size)
 {
···
 EXPORT_SYMBOL(sort);
 
 #if 0
+#include <linux/slab.h>
 /* a simple boot-time regression test */
 
 int cmpint(const void *a, const void *b)

lib/stmp_device.c

···
 #include <linux/io.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/stmp_device.h>
 
 #define STMP_MODULE_CLKGATE	(1 << 30)

lib/string.c

···
 }
 EXPORT_SYMBOL(strncasecmp);
 #endif
-#ifndef __HAVE_ARCH_STRNICMP
-#undef strnicmp
-int strnicmp(const char *s1, const char *s2, size_t len)
-{
-	return strncasecmp(s1, s2, len);
-}
-EXPORT_SYMBOL(strnicmp);
-#endif
 
 #ifndef __HAVE_ARCH_STRCASECMP
 int strcasecmp(const char *s1, const char *s2)

lib/string_helpers.c

···
  * @len:	length of buffer
  *
  * This function returns a string formatted to 3 significant figures
- * giving the size in the required units.  Returns 0 on success or
- * error on failure.  @buf is always zero terminated.
+ * giving the size in the required units.  @buf should have room for
+ * at least 9 bytes and will always be zero terminated.
  *
  */
-int string_get_size(u64 size, const enum string_size_units units,
-		    char *buf, int len)
+void string_get_size(u64 size, const enum string_size_units units,
+		     char *buf, int len)
 {
 	static const char *const units_10[] = {
-		"B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB", NULL
+		"B", "kB", "MB", "GB", "TB", "PB", "EB"
 	};
 	static const char *const units_2[] = {
-		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB",
-		NULL
+		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB"
 	};
 	static const char *const *const units_str[] = {
 		[STRING_UNITS_10] = units_10,
···
 		[STRING_UNITS_2] = 1024,
 	};
 	int i, j;
-	u64 remainder = 0, sf_cap;
+	u32 remainder = 0, sf_cap;
 	char tmp[8];
 
 	tmp[0] = '\0';
 	i = 0;
 	if (size >= divisor[units]) {
-		while (size >= divisor[units] && units_str[units][i]) {
+		while (size >= divisor[units]) {
 			remainder = do_div(size, divisor[units]);
 			i++;
 		}
···
 
 		if (j) {
 			remainder *= 1000;
-			do_div(remainder, divisor[units]);
-			snprintf(tmp, sizeof(tmp), ".%03lld",
-				 (unsigned long long)remainder);
+			remainder /= divisor[units];
+			snprintf(tmp, sizeof(tmp), ".%03u", remainder);
 			tmp[j+1] = '\0';
 		}
 	}
 
-	snprintf(buf, len, "%lld%s %s", (unsigned long long)size,
+	snprintf(buf, len, "%u%s %s", (u32)size,
 		 tmp, units_str[units][i]);
-
-	return 0;
 }
 EXPORT_SYMBOL(string_get_size);
 

lib/strncpy_from_user.c

···
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>

lib/test-hexdump.c

···
+/*
+ * Test cases for lib/hexdump.c module.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/string.h>
+
+static const unsigned char data_b[] = {
+	'\xbe', '\x32', '\xdb', '\x7b', '\x0a', '\x18', '\x93', '\xb2',	/* 00 - 07 */
+	'\x70', '\xba', '\xc4', '\x24', '\x7d', '\x83', '\x34', '\x9b',	/* 08 - 0f */
+	'\xa6', '\x9c', '\x31', '\xad', '\x9c', '\x0f', '\xac', '\xe9',	/* 10 - 17 */
+	'\x4c', '\xd1', '\x19', '\x99', '\x43', '\xb1', '\xaf', '\x0c',	/* 18 - 1f */
+};
+
+static const unsigned char data_a[] = ".2.{....p..$}.4...1.....L...C...";
+
+static const char *test_data_1_le[] __initconst = {
+	"be", "32", "db", "7b", "0a", "18", "93", "b2",
+	"70", "ba", "c4", "24", "7d", "83", "34", "9b",
+	"a6", "9c", "31", "ad", "9c", "0f", "ac", "e9",
+	"4c", "d1", "19", "99", "43", "b1", "af", "0c",
+};
+
+static const char *test_data_2_le[] __initconst = {
+	"32be", "7bdb", "180a", "b293",
+	"ba70", "24c4", "837d", "9b34",
+	"9ca6", "ad31", "0f9c", "e9ac",
+	"d14c", "9919", "b143", "0caf",
+};
+
+static const char *test_data_4_le[] __initconst = {
+	"7bdb32be", "b293180a", "24c4ba70", "9b34837d",
+	"ad319ca6", "e9ac0f9c", "9919d14c", "0cafb143",
+};
+
+static const char *test_data_8_le[] __initconst = {
+	"b293180a7bdb32be", "9b34837d24c4ba70",
+	"e9ac0f9cad319ca6", "0cafb1439919d14c",
+};
+
+static void __init test_hexdump(size_t len, int rowsize, int groupsize,
+				bool ascii)
+{
+	char test[32 * 3 + 2 + 32 + 1];
+	char real[32 * 3 + 2 + 32 + 1];
+	char *p;
+	const char **result;
+	size_t l = len;
+	int gs = groupsize, rs = rowsize;
+	unsigned int i;
+
+	hex_dump_to_buffer(data_b, l, rs, gs, real, sizeof(real), ascii);
+
+	if (rs != 16 && rs != 32)
+		rs = 16;
+
+	if (l > rs)
+		l = rs;
+
+	if (!is_power_of_2(gs) || gs > 8 || (len % gs != 0))
+		gs = 1;
+
+	if (gs == 8)
+		result = test_data_8_le;
+	else if (gs == 4)
+		result = test_data_4_le;
+	else if (gs == 2)
+		result = test_data_2_le;
+	else
+		result = test_data_1_le;
+
+	memset(test, ' ', sizeof(test));
+
+	/* hex dump */
+	p = test;
+	for (i = 0; i < l / gs; i++) {
+		const char *q = *result++;
+		size_t amount = strlen(q);
+
+		strncpy(p, q, amount);
+		p += amount + 1;
+	}
+	if (i)
+		p--;
+
+	/* ASCII part */
+	if (ascii) {
+		p = test + rs * 2 + rs / gs + 1;
+		strncpy(p, data_a, l);
+		p += l;
+	}
+
+	*p = '\0';
+
+	if (strcmp(test, real)) {
+		pr_err("Len: %zu row: %d group: %d\n", len, rowsize, groupsize);
+		pr_err("Result: '%s'\n", real);
+		pr_err("Expect: '%s'\n", test);
+	}
+}
+
+static void __init test_hexdump_set(int rowsize, bool ascii)
+{
+	size_t d = min_t(size_t, sizeof(data_b), rowsize);
+	size_t len = get_random_int() % d + 1;
+
+	test_hexdump(len, rowsize, 4, ascii);
+	test_hexdump(len, rowsize, 2, ascii);
+	test_hexdump(len, rowsize, 8, ascii);
+	test_hexdump(len, rowsize, 1, ascii);
+}
+
+static void __init test_hexdump_overflow(bool ascii)
+{
+	char buf[56];
+	const char *t = test_data_1_le[0];
+	size_t l = get_random_int() % sizeof(buf);
+	bool a;
+	int e, r;
+
+	memset(buf, ' ', sizeof(buf));
+
+	r = hex_dump_to_buffer(data_b, 1, 16, 1, buf, l, ascii);
+
+	if (ascii)
+		e = 50;
+	else
+		e = 2;
+	buf[e + 2] = '\0';
+
+	if (!l) {
+		a = r == e && buf[0] == ' ';
+	} else if (l < 3) {
+		a = r == e && buf[0] == '\0';
+	} else if (l < 4) {
+		a = r == e && !strcmp(buf, t);
+	} else if (ascii) {
+		if (l < 51)
+			a = r == e && buf[l - 1] == '\0' && buf[l - 2] == ' ';
+		else
+			a = r == e && buf[50] == '\0' && buf[49] == '.';
+	} else {
+		a = r == e && buf[e] == '\0';
+	}
+
+	if (!a) {
+		pr_err("Len: %zu rc: %u strlen: %zu\n", l, r, strlen(buf));
+		pr_err("Result: '%s'\n", buf);
+	}
+}
+
+static int __init test_hexdump_init(void)
+{
+	unsigned int i;
+	int rowsize;
+
+	pr_info("Running tests...\n");
+
+	rowsize = (get_random_int() % 2 + 1) * 16;
+	for (i = 0; i < 16; i++)
+		test_hexdump_set(rowsize, false);
+
+	rowsize = (get_random_int() % 2 + 1) * 16;
+	for (i = 0; i < 16; i++)
+		test_hexdump_set(rowsize, true);
+
+	for (i = 0; i < 16; i++)
+		test_hexdump_overflow(false);
+
+	for (i = 0; i < 16; i++)
+		test_hexdump_overflow(true);
+
+	return -EINVAL;
+}
+module_init(test_hexdump_init);
+MODULE_LICENSE("Dual BSD/GPL");

lib/vsprintf.c

···
 {
 	int i = 0;
 
-	while (isdigit(**s))
+	do {
 		i = i*10 + *((*s)++) - '0';
+	} while (isdigit(**s));
 
 	return i;
 }
···
 
 	case 'p':
 		spec->type = FORMAT_TYPE_PTR;
-		return fmt - start;
-		/* skip alnum */
+		return ++fmt - start;
 
 	case '%':
 		spec->type = FORMAT_TYPE_PERCENT_CHAR;
···
 
 	/* Reject out-of-range values early.  Large positive sizes are
 	   used for unknown buffer sizes. */
-	if (WARN_ON_ONCE((int) size < 0))
+	if (WARN_ON_ONCE(size > INT_MAX))
 		return 0;
 
 	str = buf;
···
 			break;
 
 		case FORMAT_TYPE_PTR:
-			str = pointer(fmt+1, str, end, va_arg(args, void *),
+			str = pointer(fmt, str, end, va_arg(args, void *),
 				      spec);
 			while (isalnum(*fmt))
 				fmt++;
···
 		}
 
 		case FORMAT_TYPE_PTR:
-			str = pointer(fmt+1, str, end, get_arg(void *), spec);
+			str = pointer(fmt, str, end, get_arg(void *), spec);
 			while (isalnum(*fmt))
 				fmt++;
 			break;

mm/Kconfig

···
 	  You can check speed with zsmalloc benchmark:
 	  https://github.com/spartacus06/zsmapbench
 
+config ZSMALLOC_STAT
+	bool "Export zsmalloc statistics"
+	depends on ZSMALLOC
+	select DEBUG_FS
+	help
+	  This option enables code in the zsmalloc to collect various
+	  statistics about whats happening in zsmalloc and exports that
+	  information to userspace via debugfs.
+	  If unsure, say N.
+
 config GENERIC_EARLY_IOREMAP
 	bool
 

mm/compaction.c

···
 
 		/* If a page was split, advance to the end of it */
 		if (isolated) {
+			cc->nr_freepages += isolated;
+			if (!strict &&
+				cc->nr_migratepages <= cc->nr_freepages) {
+				blockpfn += isolated;
+				break;
+			}
+
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
 			continue;
···
 	unsigned long isolate_start_pfn; /* exact pfn we start at */
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
-	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
···
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+	for (; block_start_pfn >= low_pfn &&
+			cc->nr_migratepages > cc->nr_freepages;
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
-		unsigned long isolated;
 
 		/*
 		 * This can iterate a massively long zone without finding any
···
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+		isolate_freepages_block(cc, &isolate_start_pfn,
 					block_end_pfn, freelist, false);
-		nr_freepages += isolated;
 
 		/*
 		 * Remember where the free scanner should restart next time,
···
 	 */
 	if (block_start_pfn < low_pfn)
 		cc->free_pfn = cc->migrate_pfn;
-
-	cc->nr_freepages = nr_freepages;
 }
 
 /*
···
 		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
 								isolate_mode);
 
-		if (!low_pfn || cc->contended)
+		if (!low_pfn || cc->contended) {
+			acct_isolated(zone, cc);
 			return ISOLATE_ABORT;
+		}
 
 		/*
 		 * Either we isolated something and proceed with migration. Or
···
 			return COMPACT_PARTIAL;
 
 		/* Job done if allocation would set block type */
-		if (cc->order >= pageblock_order && area->nr_free)
+		if (order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
 	}
 

mm/gup.c

···
 		migration_entry_wait(mm, pmd, address);
 		goto retry;
 	}
-	if ((flags & FOLL_NUMA) && pte_numa(pte))
+	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
 		pte_unmap_unlock(ptep, ptl);
···
 			return page;
 		return no_page_table(vma, flags);
 	}
-	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
···
 
 		/*
 		 * Similar to the PMD case below, NUMA hinting must take slow
-		 * path
+		 * path using the pte_protnone check.
 		 */
 		if (!pte_present(pte) || pte_special(pte) ||
-			pte_numa(pte) || (write && !pte_write(pte)))
+			pte_protnone(pte) || (write && !pte_write(pte)))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
···
 			 * 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, pmdp, addr, next, write,

mm/huge_memory.c

···
 		return ERR_PTR(-EFAULT);
 
 	/* Full NUMA hinting faults to serialise migration in fault paths */
-	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		goto out;
 
 	page = pmd_page(*pmd);
···
 	bool migrated = false;
 	int flags = 0;
 
+	/* A PROT_NONE fault should not end up here */
+	BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
+
 	ptl = pmd_lock(mm, pmdp);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
···
 	 * check_same as the page may no longer be mapped.
 	 */
 	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		page = pmd_page(*pmdp);
 		spin_unlock(ptl);
-		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		wait_on_page_locked(page);
 		goto out;
 	}
 
···
 
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
-	 * and pmd_numa cleared.
+	 * and access rights restored.
 	 */
 	spin_unlock(ptl);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
···
 	goto out;
 clear_pmdnuma:
 	BUG_ON(!PageLocked(page));
-	pmd = pmd_mknonnuma(pmd);
+	pmd = pmd_modify(pmd, vma->vm_page_prot);
 	set_pmd_at(mm, haddr, pmdp, pmd);
-	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
 	unlock_page(page);
 out_unlock:
···
 
 	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
-		ret = 1;
-		if (!prot_numa) {
+
+		/*
+		 * Avoid trapping faults against the zero page. The read-only
+		 * data is likely to be read-cached on the local CPU and
+		 * local/remote hits to the zero page are not interesting.
+		 */
+		if (prot_numa && is_huge_zero_pmd(*pmd)) {
+			spin_unlock(ptl);
+			return 0;
+		}
+
+		if (!prot_numa || !pmd_protnone(*pmd)) {
+			ret = 1;
 			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
-			if (pmd_numa(entry))
-				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
 			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
-		} else {
-			struct page *page = pmd_page(*pmd);
-
-			/*
-			 * Do not trap faults against the zero page. The
-			 * read-only data is likely to be read-cached on the
-			 * local CPU cache and it is less useful to know about
-			 * local vs remote hits on the zero page.
-			 */
-			if (!is_huge_zero_page(page) &&
-			    !pmd_numa(*pmd)) {
-				pmdp_set_numa(mm, addr, pmd);
-				ret = HPAGE_PMD_NR;
-			}
 		}
 		spin_unlock(ptl);
 	}
···
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
 			/*
-			 * Note that pmd_numa is not transferred deliberately
-			 * to avoid any possibility that pte_numa leaks to
-			 * a PROT_NONE VMA by accident.
+			 * Note that NUMA hinting access restrictions are not
+			 * transferred to avoid any possibility of altering
+			 * permissions across VMAs.
 			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);

mm/internal.h

···
 #define mminit_dprintk(level, prefix, fmt, arg...) \
 do { \
 	if (level < mminit_loglevel) { \
-		printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
-		printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
+		if (level <= MMINIT_WARNING) \
+			printk(KERN_WARNING "mminit::" prefix " " fmt, ##arg); \
+		else \
+			printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
 	} \
 } while (0)
 

mm/list_lru.c

···
 #include <linux/mm.h>
 #include <linux/list_lru.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/memcontrol.h>
+
+#ifdef CONFIG_MEMCG_KMEM
+static LIST_HEAD(list_lrus);
+static DEFINE_MUTEX(list_lrus_mutex);
+
+static void list_lru_register(struct list_lru *lru)
+{
+	mutex_lock(&list_lrus_mutex);
+	list_add(&lru->list, &list_lrus);
+	mutex_unlock(&list_lrus_mutex);
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+	mutex_lock(&list_lrus_mutex);
+	list_del(&lru->list);
+	mutex_unlock(&list_lrus_mutex);
+}
+#else
+static void list_lru_register(struct list_lru *lru)
+{
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return !!lru->node[0].memcg_lrus;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+{
+	/*
+	 * The lock protects the array of per cgroup lists from relocation
+	 * (see memcg_update_list_lru_node).
+	 */
+	lockdep_assert_held(&nlru->lock);
+	if (nlru->memcg_lrus && idx >= 0)
+		return nlru->memcg_lrus->lru[idx];
+
+	return &nlru->lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
+{
+	struct mem_cgroup *memcg;
+
+	if (!nlru->memcg_lrus)
+		return &nlru->lru;
+
+	memcg = mem_cgroup_from_kmem(ptr);
+	if (!memcg)
+		return &nlru->lru;
+
+	return list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg));
+}
+#else
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return false;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+{
+	return &nlru->lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
+{
+	return &nlru->lru;
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 bool list_lru_add(struct list_lru *lru, struct list_head *item)
 {
 	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
-	WARN_ON_ONCE(nlru->nr_items < 0);
+	l = list_lru_from_kmem(nlru, item);
 	if (list_empty(item)) {
-		list_add_tail(item, &nlru->list);
-		if (nlru->nr_items++ == 0)
-			node_set(nid, lru->active_nodes);
+		list_add_tail(item, &l->list);
+		l->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
···
 {
 	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
+	l = list_lru_from_kmem(nlru, item);
 	if (!list_empty(item)) {
 		list_del_init(item);
-		if (--nlru->nr_items == 0)
-			node_clear(nid, lru->active_nodes);
-		WARN_ON_ONCE(nlru->nr_items < 0);
+		l->nr_items--;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
···
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
-unsigned long
-list_lru_count_node(struct list_lru *lru, int nid)
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
 {
-	unsigned long count = 0;
+	list_del_init(item);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate);
+
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+			   struct list_head *head)
+{
+	list_move(item, head);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate_move);
+
+static unsigned long __list_lru_count_one(struct list_lru *lru,
+					  int nid, int memcg_idx)
+{
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
+	unsigned long count;
 
 	spin_lock(&nlru->lock);
-	WARN_ON_ONCE(nlru->nr_items < 0);
-	count += nlru->nr_items;
+	l = list_lru_from_memcg_idx(nlru, memcg_idx);
+	count = l->nr_items;
 	spin_unlock(&nlru->lock);
 
 	return count;
 }
+
+unsigned long list_lru_count_one(struct list_lru *lru,
+				 int nid, struct mem_cgroup *memcg)
+{
+	return __list_lru_count_one(lru, nid, memcg_cache_id(memcg));
+}
+EXPORT_SYMBOL_GPL(list_lru_count_one);
+
+unsigned long list_lru_count_node(struct list_lru *lru, int nid)
+{
+	long count = 0;
+	int memcg_idx;
+
+	count += __list_lru_count_one(lru, nid, -1);
+	if (list_lru_memcg_aware(lru)) {
+		for_each_memcg_cache_index(memcg_idx)
+			count += __list_lru_count_one(lru, nid, memcg_idx);
+	}
+	return count;
+}
 EXPORT_SYMBOL_GPL(list_lru_count_node);
 
-unsigned long
-list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
-		   void *cb_arg, unsigned long *nr_to_walk)
+static unsigned long
+__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
+		    list_lru_walk_cb isolate, void *cb_arg,
+		    unsigned long *nr_to_walk)
 {
 
-	struct list_lru_node	*nlru = &lru->node[nid];
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 	struct list_head *item, *n;
 	unsigned long isolated = 0;
 
 	spin_lock(&nlru->lock);
+	l = list_lru_from_memcg_idx(nlru, memcg_idx);
 restart:
-	list_for_each_safe(item, n, &nlru->list) {
+	list_for_each_safe(item, n, &l->list) {
 		enum lru_status ret;
 
 		/*
···
 			break;
 		--*nr_to_walk;
 
-		ret = isolate(item, &nlru->lock, cb_arg);
+		ret = isolate(item, l, &nlru->lock, cb_arg);
 		switch (ret) {
 		case LRU_REMOVED_RETRY:
 			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
-			if (--nlru->nr_items == 0)
-				node_clear(nid, lru->active_nodes);
-			WARN_ON_ONCE(nlru->nr_items < 0);
 			isolated++;
 			/*
 			 * If the lru lock has been dropped, our list
···
 				goto restart;
 			break;
 		case LRU_ROTATE:
-			list_move_tail(item, &nlru->list);
+			list_move_tail(item, &l->list);
 			break;
 		case LRU_SKIP:
 			break;
···
 	spin_unlock(&nlru->lock);
 	return isolated;
 }
+
+unsigned long
+list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		  list_lru_walk_cb isolate, void *cb_arg,
+		  unsigned long *nr_to_walk)
+{
+	return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg),
+				   isolate, cb_arg, nr_to_walk);
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_one);
+
+unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
+				 list_lru_walk_cb isolate, void *cb_arg,
+				 unsigned long *nr_to_walk)
+{
+	long isolated = 0;
+	int memcg_idx;
+
+	isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg,
+					nr_to_walk);
+	if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) {
+		for_each_memcg_cache_index(memcg_idx) {
+			isolated += __list_lru_walk_one(lru, nid, memcg_idx,
+						isolate, cb_arg, nr_to_walk);
+			if (*nr_to_walk <= 0)
+				break;
+		}
+	}
+	return isolated;
+}
 EXPORT_SYMBOL_GPL(list_lru_walk_node);
 
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
+static void init_one_lru(struct list_lru_one *l)
+{
+	INIT_LIST_HEAD(&l->list);
+	l->nr_items = 0;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus,
+					  int begin, int end)
+{
+	int i;
+
+	for (i = begin; i < end; i++)
+		kfree(memcg_lrus->lru[i]);
+}
+
+static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
+				      int begin, int end)
+{
+	int i;
+
+	for (i = begin; i < end; i++) {
+		struct list_lru_one *l;
+
+		l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL);
+		if (!l)
+			goto fail;
+
+		init_one_lru(l);
+		memcg_lrus->lru[i] = l;
+	}
+	return 0;
+fail:
+	__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
+	return -ENOMEM;
+}
+
+static int memcg_init_list_lru_node(struct list_lru_node *nlru)
+{
+	int size = memcg_nr_cache_ids;
+
+	nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL);
+	if (!nlru->memcg_lrus)
+		return -ENOMEM;
+
+	if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
+		kfree(nlru->memcg_lrus);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
+{
+	__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
+	kfree(nlru->memcg_lrus);
+}
+
+static int memcg_update_list_lru_node(struct list_lru_node *nlru,
+				      int old_size, int new_size)
+{
+	struct list_lru_memcg *old, *new;
+
+	BUG_ON(old_size > new_size);
+
+	old = nlru->memcg_lrus;
+	new = kmalloc(new_size * sizeof(void *), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	if (__memcg_init_list_lru_node(new, old_size, new_size)) {
+		kfree(new);
+		return -ENOMEM;
+	}
+
+	memcpy(new, old, old_size * sizeof(void *));
+
+	/*
+	 * The lock guarantees that we won't race with a reader
+	 * (see list_lru_from_memcg_idx).
+	 *
+	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+	 * we have to use IRQ-safe primitives here to avoid deadlock.
+	 */
+	spin_lock_irq(&nlru->lock);
+	nlru->memcg_lrus = new;
+	spin_unlock_irq(&nlru->lock);
+
+	kfree(old);
+	return 0;
+}
+
+static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru,
+					      int old_size, int new_size)
+{
+	/* do not bother shrinking the array back to the old size, because we
+	 * cannot handle allocation failures here */
+	__memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size);
+}
+
+static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+	int i;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		if (!memcg_aware)
+			lru->node[i].memcg_lrus = NULL;
+		else if (memcg_init_list_lru_node(&lru->node[i]))
+			goto fail;
+	}
+	return 0;
+fail:
+	for (i = i - 1; i >= 0; i--)
+		memcg_destroy_list_lru_node(&lru->node[i]);
+	return -ENOMEM;
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_destroy_list_lru_node(&lru->node[i]);
+}
+
+static int memcg_update_list_lru(struct list_lru *lru,
+				 int old_size, int new_size)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return 0;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		if (memcg_update_list_lru_node(&lru->node[i],
+					       old_size, new_size))
+			goto fail;
+	}
+	return 0;
+fail:
+	for (i = i - 1; i >= 0; i--)
+		memcg_cancel_update_list_lru_node(&lru->node[i],
+						  old_size, new_size);
+	return -ENOMEM;
+}
+
+static void memcg_cancel_update_list_lru(struct list_lru *lru,
+					 int old_size, int new_size)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_cancel_update_list_lru_node(&lru->node[i],
+						  old_size, new_size);
+}
+
+int memcg_update_all_list_lrus(int new_size)
+{
+	int ret = 0;
+	struct list_lru *lru;
+	int old_size = memcg_nr_cache_ids;
+
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &list_lrus, list) {
+		ret = memcg_update_list_lru(lru, old_size, new_size);
+		if (ret)
+			goto fail;
+	}
+out:
+	mutex_unlock(&list_lrus_mutex);
+	return ret;
+fail:
+	list_for_each_entry_continue_reverse(lru, &list_lrus, list)
+		memcg_cancel_update_list_lru(lru, old_size, new_size);
+	goto out;
+}
+
+static void memcg_drain_list_lru_node(struct list_lru_node *nlru,
+				      int src_idx, int dst_idx)
+{
+	struct list_lru_one *src, *dst;
+
+	/*
+	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+	 * we have to use IRQ-safe primitives here to avoid deadlock.
+	 */
+	spin_lock_irq(&nlru->lock);
+
+	src = list_lru_from_memcg_idx(nlru, src_idx);
+	dst = list_lru_from_memcg_idx(nlru, dst_idx);
+
+	list_splice_init(&src->list, &dst->list);
+	dst->nr_items += src->nr_items;
+	src->nr_items = 0;
+
+	spin_unlock_irq(&nlru->lock);
+}
+
+static void memcg_drain_list_lru(struct list_lru *lru,
+				 int src_idx, int dst_idx)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx);
+}
+
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx)
+{
+	struct list_lru *lru;
+
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &list_lrus, list)
+		memcg_drain_list_lru(lru, src_idx, dst_idx);
+	mutex_unlock(&list_lrus_mutex);
+}
+#else
+static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+	return 0;
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+		    struct lock_class_key *key)
 {
 	int i;
 	size_t size = sizeof(*lru->node) * nr_node_ids;
+	int err = -ENOMEM;
+
+	memcg_get_cache_ids();
 
 	lru->node = kzalloc(size, GFP_KERNEL);
 	if (!lru->node)
-		return -ENOMEM;
+		goto out;
 
-	nodes_clear(lru->active_nodes);
 	for (i = 0; i < nr_node_ids; i++) {
 		spin_lock_init(&lru->node[i].lock);
 		if (key)
 			lockdep_set_class(&lru->node[i].lock, key);
-		INIT_LIST_HEAD(&lru->node[i].list);
-		lru->node[i].nr_items = 0;
+		init_one_lru(&lru->node[i].lru);
 	}
-	return 0;
+
+	err = memcg_init_list_lru(lru, memcg_aware);
+	if (err) {
+		kfree(lru->node);
+		goto out;
+	}
+
+	list_lru_register(lru);
+out:
+	memcg_put_cache_ids();
+	return err;
 }
-EXPORT_SYMBOL_GPL(list_lru_init_key);
+EXPORT_SYMBOL_GPL(__list_lru_init);
 
 void list_lru_destroy(struct list_lru *lru)
 {
+	/* Already destroyed or not yet initialized? */
+	if (!lru->node)
+		return;
+
+	memcg_get_cache_ids();
+
+	list_lru_unregister(lru);
+
+	memcg_destroy_list_lru(lru);
 	kfree(lru->node);
+	lru->node = NULL;
+
+	memcg_put_cache_ids();
 }
 EXPORT_SYMBOL_GPL(list_lru_destroy);

mm/memcontrol.c

···
 	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
-        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
+	bool kmem_acct_activated;
+	bool kmem_acct_active;
 #endif
 
 	int last_scanned_node;
···
 };
 
 #ifdef CONFIG_MEMCG_KMEM
-static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 {
-	return memcg->kmemcg_id >= 0;
+	return memcg->kmem_acct_active;
 }
 #endif
 
···
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 
-static void disarm_sock_keys(struct mem_cgroup *memcg)
-{
-	if (!memcg_proto_activated(&memcg->tcp_mem))
-		return;
-	static_key_slow_dec(&memcg_socket_limit_enabled);
-}
-#else
-static void disarm_sock_keys(struct mem_cgroup *memcg)
-{
-}
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
 /*
- * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
  * The main reason for not using cgroup id for this:
  *  this works better in sparse environments, where we have a lot of memcgs,
  *  but only a few kmem-limited. Or also, if we have, for instance, 200
  *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
  *  200 entry array for that.
  *
- * The current size of the caches array is stored in
- * memcg_limited_groups_array_size.  It will double each time we have to
- * increase it.
+ * The current size of the caches array is stored in memcg_nr_cache_ids. It
+ * will double each time we have to increase it.
  */
-static DEFINE_IDA(kmem_limited_groups);
-int memcg_limited_groups_array_size;
+static DEFINE_IDA(memcg_cache_ida);
+int memcg_nr_cache_ids;
+
+/* Protects memcg_nr_cache_ids */
+static DECLARE_RWSEM(memcg_cache_ids_sem);
+
+void memcg_get_cache_ids(void)
+{
+	down_read(&memcg_cache_ids_sem);
+}
+
+void memcg_put_cache_ids(void)
+{
+	up_read(&memcg_cache_ids_sem);
+}
 
 /*
  * MIN_SIZE is different than 1, because we would like to avoid going through
···
 struct static_key memcg_kmem_enabled_key;
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
-static void memcg_free_cache_id(int id);
-
-static void disarm_kmem_keys(struct mem_cgroup *memcg)
-{
-	if (memcg_kmem_is_active(memcg)) {
-		static_key_slow_dec(&memcg_kmem_enabled_key);
-		memcg_free_cache_id(memcg->kmemcg_id);
-	}
-	/*
-	 * This check can't live in kmem destruction function,
-	 * since the charges will outlive the cgroup
-	 */
-	WARN_ON(page_counter_read(&memcg->kmem));
-}
-#else
-static void disarm_kmem_keys(struct mem_cgroup *memcg)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
-
-static void disarm_static_keys(struct mem_cgroup *memcg)
-{
-	disarm_sock_keys(memcg);
-	disarm_kmem_keys(memcg);
-}
 
 static struct mem_cgroup_per_zone *
 mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
···
 	int id, size;
 	int err;
 
-	id = ida_simple_get(&kmem_limited_groups,
+	id = ida_simple_get(&memcg_cache_ida,
 			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
 	if (id < 0)
 		return id;
 
-	if (id < memcg_limited_groups_array_size)
+	if (id < memcg_nr_cache_ids)
 		return id;
 
 	/*
 	 * There's no space for the new id in memcg_caches arrays,
 	 * so we have to grow them.
 	 */
+	down_write(&memcg_cache_ids_sem);
 
 	size = 2 * (id + 1);
 	if (size < MEMCG_CACHES_MIN_SIZE)
···
 		size = MEMCG_CACHES_MAX_SIZE;
 
 	err = memcg_update_all_caches(size);
+	if (!err)
+		err = memcg_update_all_list_lrus(size);
+	if (!err)
+		memcg_nr_cache_ids = size;
+
+	up_write(&memcg_cache_ids_sem);
+
 	if (err) {
-		ida_simple_remove(&kmem_limited_groups, id);
+		ida_simple_remove(&memcg_cache_ida, id);
 		return err;
 	}
 	return id;
···
 
 static void memcg_free_cache_id(int id)
 {
-	ida_simple_remove(&kmem_limited_groups, id);
-}
-
-/*
- * We should update the current array size iff all caches updates succeed. This
- * can only be done from the slab side. The slab mutex needs to be held when
- * calling this.
- */
-void memcg_update_array_size(int num)
-{
-	memcg_limited_groups_array_size = num;
+	ida_simple_remove(&memcg_cache_ida, id);
 }
 
 struct memcg_kmem_cache_create_work {
···
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
+	int kmemcg_id;
 
-	VM_BUG_ON(!cachep->memcg_params);
-	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+	VM_BUG_ON(!is_root_cache(cachep));
 
 	if (current->memcg_kmem_skip_account)
 		return cachep;
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
-	if (!memcg_kmem_is_active(memcg))
+	kmemcg_id = ACCESS_ONCE(memcg->kmemcg_id);
+	if (kmemcg_id < 0)
 		goto out;
 
-	memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));
+	memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id);
 	if (likely(memcg_cachep))
 		return memcg_cachep;
 
···
 void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 	if (!is_root_cache(cachep))
-		css_put(&cachep->memcg_params->memcg->css);
+		css_put(&cachep->memcg_params.memcg->css);
 }
 
 /*
···
 
 	memcg_uncharge_kmem(memcg, 1 << order);
 	page->mem_cgroup = NULL;
+}
+
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct kmem_cache *cachep;
+	struct page *page;
+
+	page = virt_to_head_page(ptr);
+	if (PageSlab(page)) {
+		cachep = page->slab_cache;
+		if (!is_root_cache(cachep))
+			memcg = cachep->memcg_params.memcg;
+	} else
+		/* page allocated by alloc_kmem_pages */
+		memcg = page->mem_cgroup;
+
+	return memcg;
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
···
 	int err = 0;
 	int memcg_id;
 
-	if (memcg_kmem_is_active(memcg))
-		return 0;
+	BUG_ON(memcg->kmemcg_id >= 0);
+	BUG_ON(memcg->kmem_acct_activated);
+	BUG_ON(memcg->kmem_acct_active);
 
 	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
···
 	 * patched.
 	 */
 	memcg->kmemcg_id = memcg_id;
+	memcg->kmem_acct_activated = true;
+	memcg->kmem_acct_active = true;
 out:
 	return err;
 }
···
 	return mem_cgroup_sockets_init(memcg, ss);
 }
 
+static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
+{
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *parent, *child;
+	int kmemcg_id;
+
+	if (!memcg->kmem_acct_active)
+		return;
+
+	/*
+	 * Clear the 'active' flag before clearing memcg_caches arrays entries.
+	 * Since we take the slab_mutex in memcg_deactivate_kmem_caches(), it
+	 * guarantees no cache will be created for this cgroup after we are
+	 * done (see memcg_create_kmem_cache()).
+	 */
+	memcg->kmem_acct_active = false;
+
+	memcg_deactivate_kmem_caches(memcg);
+
+	kmemcg_id = memcg->kmemcg_id;
+	BUG_ON(kmemcg_id < 0);
+
+	parent = parent_mem_cgroup(memcg);
+	if (!parent)
+		parent = root_mem_cgroup;
+
+	/*
+	 * Change kmemcg_id of this cgroup and all its descendants to the
+	 * parent's id, and then move all entries from this cgroup's list_lrus
+	 * to ones of the parent. After we have finished, all list_lrus
+	 * corresponding to this cgroup are guaranteed to remain empty. The
+	 * ordering is imposed by list_lru_node->lock taken by
+	 * memcg_drain_all_list_lrus().
+	 */
+	css_for_each_descendant_pre(css, &memcg->css) {
+		child = mem_cgroup_from_css(css);
+		BUG_ON(child->kmemcg_id != kmemcg_id);
+		child->kmemcg_id = parent->kmemcg_id;
+		if (!memcg->use_hierarchy)
+			break;
+	}
+	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
+
+	memcg_free_cache_id(kmemcg_id);
+}
+
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
-	memcg_destroy_kmem_caches(memcg);
+	if (memcg->kmem_acct_activated) {
+		memcg_destroy_kmem_caches(memcg);
+		static_key_slow_dec(&memcg_kmem_enabled_key);
+		WARN_ON(page_counter_read(&memcg->kmem));
+	}
 	mem_cgroup_sockets_destroy(memcg);
 }
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return 0;
+}
+
+static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
+{
 }
 
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
···
 		free_mem_cgroup_per_zone_info(memcg, node);
 
 	free_percpu(memcg->stat);
-
-	disarm_static_keys(memcg);
 	kfree(memcg);
 }
 
···
 	spin_unlock(&memcg->event_list_lock);
 
 	vmpressure_cleanup(&memcg->vmpressure);
+
+	memcg_deactivate_kmem(memcg);
 }
 
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)

mm/memory-failure.c

···
 	 * Only call shrink_node_slabs here (which would also shrink
 	 * other caches) if access is not potentially fatal.
 	 */
-	if (access) {
-		int nr;
-		int nid = page_to_nid(p);
-		do {
-			nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000);
-			if (page_count(p) == 1)
-				break;
-		} while (nr > 10);
-	}
+	if (access)
+		drop_slab_node(page_to_nid(p));
 }
 EXPORT_SYMBOL_GPL(shake_page);
 
···
 			 * source page should be freed back to buddy before
 			 * setting PG_hwpoison.
 			 */
-			if (!is_free_buddy_page(page))
-				lru_add_drain_all();
 			if (!is_free_buddy_page(page))
 				drain_all_pages(page_zone(page));
 			SetPageHWPoison(page);

mm/memory.c

···
 	bool migrated = false;
 	int flags = 0;
 
+	/* A PROT_NONE fault should not end up here */
+	BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
+
 	/*
 	* The "pte" at this point cannot be used safely without
 	* validation through pte_unmap_same(). It's of NUMA type but
 	* the pfn may be screwed if the read is non atomic.
 	*
-	* ptep_modify_prot_start is not called as this is clearing
-	* the _PAGE_NUMA bit and it is not really expected that there
-	* would be concurrent hardware modifications to the PTE.
+	* We can safely just do a "set_pte_at()", because the old
+	* page table entry is not accessible, so there would be no
+	* concurrent hardware modifications to the PTE.
 	*/
 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
···
 		goto out;
 	}
 
-	pte = pte_mknonnuma(pte);
+	/* Make it present again */
+	pte = pte_modify(pte, vma->vm_page_prot);
+	pte = pte_mkyoung(pte);
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
 
···
 		pte_unmap_unlock(ptep, ptl);
 		return 0;
 	}
-	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
 	/*
 	 * Avoid grouping on DSO/COW pages in specific and RO pages
···
 					pte, pmd, flags, entry);
 	}
 
-	if (pte_numa(entry))
+	if (pte_protnone(entry))
 		return do_numa_page(mm, vma, address, entry, pte, pmd);
 
 	ptl = pte_lockptr(mm, pmd);
···
 			if (pmd_trans_splitting(orig_pmd))
 				return 0;
 
-			if (pmd_numa(orig_pmd))
+			if (pmd_protnone(orig_pmd))
 				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
 
···
 	if (follow_phys(vma, addr, write, &prot, &phys_addr))
 		return -EINVAL;
 
-	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else

mm/mempolicy.c

···
 {
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
+	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 

mm/migrate.c

···
 	return PageLocked(page);
 }
 
-void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
-{
-	struct page *page = pmd_page(*pmd);
-	wait_on_page_locked(page);
-}
-
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
···
 out_dropref:
 	ptl = pmd_lock(mm, pmd);
 	if (pmd_same(*pmd, entry)) {
-		entry = pmd_mknonnuma(entry);
+		entry = pmd_modify(entry, vma->vm_page_prot);
 		set_pmd_at(mm, mmun_start, pmd, entry);
 		update_mmu_cache_pmd(vma, address, &entry);
 	}

mm/mm_init.c

···
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
-int mminit_loglevel;
+int __meminitdata mminit_loglevel;
 
 #ifndef SECTIONS_SHIFT
 #define SECTIONS_SHIFT	0
 #endif
 
 /* The zonelists are simply reported, validation is manual. */
-void mminit_verify_zonelist(void)
+void __init mminit_verify_zonelist(void)
 {
 	int nid;
 

mm/mprotect.c

···
 		oldpte = *pte;
 		if (pte_present(oldpte)) {
 			pte_t ptent;
-			bool updated = false;
 
-			if (!prot_numa) {
-				ptent = ptep_modify_prot_start(mm, addr, pte);
-				if (pte_numa(ptent))
-					ptent = pte_mknonnuma(ptent);
-				ptent = pte_modify(ptent, newprot);
-				/*
-				 * Avoid taking write faults for pages we
-				 * know to be dirty.
-				 */
-				if (dirty_accountable && pte_dirty(ptent) &&
-				    (pte_soft_dirty(ptent) ||
-				     !(vma->vm_flags & VM_SOFTDIRTY)))
-					ptent = pte_mkwrite(ptent);
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
-				updated = true;
-			} else {
+			/*
+			 * Avoid trapping faults against the zero or KSM
+			 * pages. See similar comment in change_huge_pmd.
+			 */
+			if (prot_numa) {
 				struct page *page;
 
 				page = vm_normal_page(vma, addr, oldpte);
-				if (page && !PageKsm(page)) {
-					if (!pte_numa(oldpte)) {
-						ptep_set_numa(mm, addr, pte);
-						updated = true;
-					}
-				}
+				if (!page || PageKsm(page))
+					continue;
+
+				/* Avoid TLB flush if possible */
+				if (pte_protnone(oldpte))
+					continue;
 			}
-			if (updated)
-				pages++;
+
+			ptent = ptep_modify_prot_start(mm, addr, pte);
+			ptent = pte_modify(ptent, newprot);
+
+			/* Avoid taking write faults for known dirty pages */
+			if (dirty_accountable && pte_dirty(ptent) &&
+					(pte_soft_dirty(ptent) ||
+					 !(vma->vm_flags & VM_SOFTDIRTY))) {
+				ptent = pte_mkwrite(ptent);
+			}
+			ptep_modify_prot_commit(mm, addr, pte, ptent);
+			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 

mm/page_alloc.c

···
  *	1G machine -> (16M dma, 784M normal, 224M high)
  *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
  *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
- *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
+ *	HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
  *
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
···
 	return 0;
 }
 
+static noinline void __init
+build_all_zonelists_init(void)
+{
+	__build_all_zonelists(NULL);
+	mminit_verify_zonelist();
+	cpuset_init_current_mems_allowed();
+}
+
 /*
  * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
+ *
+ * __ref due to (1) call of __meminit annotated setup_zone_pageset
+ * [we're only called with non-NULL zone through __meminit paths] and
+ * (2) call of __init annotated helper build_all_zonelists_init
+ * [protected by SYSTEM_BOOTING].
  */
 void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 {
 	set_zonelist_order();
 
 	if (system_state == SYSTEM_BOOTING) {
-		__build_all_zonelists(NULL);
-		mminit_verify_zonelist();
-		cpuset_init_current_mems_allowed();
+		build_all_zonelists_init();
 	} else {
 #ifdef CONFIG_MEMORY_HOTPLUG
 		if (zone)

mm/pgtable-generic.c

···
 		     pmd_t *pmdp)
 {
 	pmd_t entry = *pmdp;
-	if (pmd_numa(entry))
-		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }

mm/slab.c

···
 	return nr_freed;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *cachep)
+int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 {
 	int ret = 0;
 	int node;
···
 {
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep);
+	int rc = __kmem_cache_shrink(cachep, false);
 
 	if (rc)
 		return rc;
···
 				int batchcount, int shared, gfp_t gfp)
 {
 	int ret;
-	struct kmem_cache *c = NULL;
-	int i = 0;
+	struct kmem_cache *c;
 
 	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
 
···
 	if ((ret < 0) || !is_root_cache(cachep))
 		return ret;
 
-	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(cachep, i);
-		if (c)
-			/* return value determined by the parent cache only */
-			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
+	lockdep_assert_held(&slab_mutex);
+	for_each_memcg_cache(c, cachep) {
+		/* return value determined by the root cache only */
+		__do_tune_cpucache(c, limit, batchcount, shared, gfp);
 	}
 
 	return ret;

mm/slab.h

···
 extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
-struct mem_cgroup;
-
 int slab_unmergeable(struct kmem_cache *s);
 struct kmem_cache *find_mergeable(size_t size, size_t align,
 		unsigned long flags, const char *name, void (*ctor)(void *));
···
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
-int __kmem_cache_shrink(struct kmem_cache *);
+int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
···
 		       size_t count, loff_t *ppos);
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * Iterate over all memcg caches of the given root cache. The caller must hold
+ * slab_mutex.
+ */
+#define for_each_memcg_cache(iter, root) \
+	list_for_each_entry(iter, &(root)->memcg_params.list, \
+			    memcg_params.list)
+
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \
+				 memcg_params.list)
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
-	return !s->memcg_params || s->memcg_params->is_root_cache;
+	return s->memcg_params.is_root_cache;
 }
 
 static inline bool slab_equal_or_root(struct kmem_cache *s,
-					struct kmem_cache *p)
+				      struct kmem_cache *p)
 {
-	return (p == s) ||
-		(s->memcg_params && (p == s->memcg_params->root_cache));
+	return p == s || p == s->memcg_params.root_cache;
 }
 
 /*
···
 static inline const char *cache_name(struct kmem_cache *s)
 {
 	if (!is_root_cache(s))
-		return s->memcg_params->root_cache->name;
+		s = s->memcg_params.root_cache;
 	return s->name;
 }
 
 /*
  * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
- * That said the caller must assure the memcg's cache won't go away. Since once
- * created a memcg's cache is destroyed only along with the root cache, it is
- * true if we are going to allocate from the cache or hold a reference to the
- * root cache by other means. Otherwise, we should hold either the slab_mutex
- * or the memcg's slab_caches_mutex while calling this function and accessing
- * the returned value.
+ * That said the caller must assure the memcg's cache won't go away by either
+ * taking a css reference to the owner cgroup, or holding the slab_mutex.
  */
 static inline struct kmem_cache *
 cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	struct kmem_cache *cachep;
-	struct memcg_cache_params *params;
-
-	if (!s->memcg_params)
-		return NULL;
+	struct memcg_cache_array *arr;
 
 	rcu_read_lock();
-	params = rcu_dereference(s->memcg_params);
+	arr = rcu_dereference(s->memcg_params.memcg_caches);
 
 	/*
 	 * Make sure we will access the up-to-date value. The code updating
 	 * memcg_caches issues a write barrier to match this (see
-	 * memcg_register_cache()).
+	 * memcg_create_kmem_cache()).
 	 */
-	cachep = lockless_dereference(params->memcg_caches[idx]);
+	cachep = lockless_dereference(arr->entries[idx]);
 	rcu_read_unlock();
 
 	return cachep;
···
 {
 	if (is_root_cache(s))
 		return s;
-	return s->memcg_params->root_cache;
+	return s->memcg_params.root_cache;
 }
 
 static __always_inline int memcg_charge_slab(struct kmem_cache *s,
···
 		return 0;
 	if (is_root_cache(s))
 		return 0;
-	return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order);
+	return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order);
 }
 
 static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
···
 		return;
 	if (is_root_cache(s))
 		return;
-	memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order);
+	memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order);
 }
-#else
+
+extern void slab_init_memcg_params(struct kmem_cache *);
+
+#else /* !CONFIG_MEMCG_KMEM */
+
+#define for_each_memcg_cache(iter, root) \
+	for ((void)(iter), (void)(root); 0; )
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	for ((void)(iter), (void)(tmp), (void)(root); 0; )
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
···
 static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 {
 }
-#endif
+
+static inline void slab_init_memcg_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {

mm/slab_common.c

···
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
-static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
+void slab_init_memcg_params(struct kmem_cache *s)
 {
-	size_t size;
+	s->memcg_params.is_root_cache = true;
+	INIT_LIST_HEAD(&s->memcg_params.list);
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
+}
 
-	if (!memcg_kmem_enabled())
-		return 0;
-
-	if (!memcg) {
-		size = offsetof(struct memcg_cache_params, memcg_caches);
-		size += memcg_limited_groups_array_size * sizeof(void *);
-	} else
-		size = sizeof(struct memcg_cache_params);
-
-	s->memcg_params = kzalloc(size, GFP_KERNEL);
-	if (!s->memcg_params)
-		return -ENOMEM;
+static int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct memcg_cache_array *arr;
 
 	if (memcg) {
-		s->memcg_params->memcg = memcg;
-		s->memcg_params->root_cache = root_cache;
-	} else
-		s->memcg_params->is_root_cache = true;
+		s->memcg_params.is_root_cache = false;
+		s->memcg_params.memcg = memcg;
+		s->memcg_params.root_cache = root_cache;
+		return 0;
+	}
 
+	slab_init_memcg_params(s);
+
+	if (!memcg_nr_cache_ids)
+		return 0;
+
+	arr = kzalloc(sizeof(struct memcg_cache_array) +
+		      memcg_nr_cache_ids * sizeof(void *),
+		      GFP_KERNEL);
+	if (!arr)
+		return -ENOMEM;
+
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
 	return 0;
 }
 
-static void memcg_free_cache_params(struct kmem_cache *s)
+static void destroy_memcg_params(struct kmem_cache *s)
 {
-	kfree(s->memcg_params);
+	if (is_root_cache(s))
+		kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
 }
 
-static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
+static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 {
-	int size;
-	struct memcg_cache_params *new_params, *cur_params;
+	struct memcg_cache_array *old, *new;
 
-	BUG_ON(!is_root_cache(s));
+	if (!is_root_cache(s))
+		return 0;
 
-	size = offsetof(struct memcg_cache_params, memcg_caches);
-	size += num_memcgs * sizeof(void *);
-
-	new_params = kzalloc(size, GFP_KERNEL);
-	if (!new_params)
+	new = kzalloc(sizeof(struct memcg_cache_array) +
+		      new_array_size * sizeof(void *), GFP_KERNEL);
+	if (!new)
 		return -ENOMEM;
 
-	cur_params = s->memcg_params;
-	memcpy(new_params->memcg_caches, cur_params->memcg_caches,
-	       memcg_limited_groups_array_size * sizeof(void *));
+	old = rcu_dereference_protected(s->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+	if (old)
+		memcpy(new->entries, old->entries,
+		       memcg_nr_cache_ids * sizeof(void *));
 
-	new_params->is_root_cache = true;
-
-	rcu_assign_pointer(s->memcg_params, new_params);
-	if (cur_params)
-		kfree_rcu(cur_params, rcu_head);
-
+	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
+	if (old)
+		kfree_rcu(old, rcu);
 	return 0;
 }
 
···
 {
 	struct kmem_cache *s;
 	int ret = 0;
+
 	mutex_lock(&slab_mutex);
-
 	list_for_each_entry(s, &slab_caches, list) {
-		if (!is_root_cache(s))
-			continue;
-
-		ret = memcg_update_cache_params(s, num_memcgs);
+		ret = update_memcg_params(s, num_memcgs);
 		/*
 		 * Instead of freeing the memory, we'll just leave the caches
 		 * up to this point in an updated state.
 		 */
 		if (ret)
-			goto out;
+			break;
 	}
-
-	memcg_update_array_size(num_memcgs);
-out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
 #else
-static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
+static inline int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
 {
 	return 0;
 }
 
-static inline void memcg_free_cache_params(struct kmem_cache *s)
+static inline void destroy_memcg_params(struct kmem_cache *s)
 {
 }
 #endif /* CONFIG_MEMCG_KMEM */
···
 	s->align = align;
 	s->ctor = ctor;
 
-	err = memcg_alloc_cache_params(memcg, s, root_cache);
+	err = init_memcg_params(s, memcg, root_cache);
 	if (err)
 		goto out_free_cache;
 
···
 	return s;
 
 out_free_cache:
-	memcg_free_cache_params(s);
+	destroy_memcg_params(s);
 	kmem_cache_free(kmem_cache, s);
 	goto out;
 }
···
 
 	get_online_cpus();
 	get_online_mems();
+	memcg_get_cache_ids();
 
 	mutex_lock(&slab_mutex);
 
···
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
+	memcg_put_cache_ids();
 	put_online_mems();
 	put_online_cpus();
 
···
 		*need_rcu_barrier = true;
 
 #ifdef CONFIG_MEMCG_KMEM
-	if (!is_root_cache(s)) {
-		struct kmem_cache *root_cache = s->memcg_params->root_cache;
-		int memcg_id = memcg_cache_id(s->memcg_params->memcg);
-
-		BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s);
-		root_cache->memcg_params->memcg_caches[memcg_id] = NULL;
-	}
+	if (!is_root_cache(s))
+		list_del(&s->memcg_params.list);
 #endif
 	list_move(&s->list, release);
 	return 0;
···
 			     struct kmem_cache *root_cache)
 {
 	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
-	int memcg_id = memcg_cache_id(memcg);
+	struct cgroup_subsys_state *css = mem_cgroup_css(memcg);
+	struct memcg_cache_array *arr;
 	struct kmem_cache *s = NULL;
 	char *cache_name;
+	int idx;
 
 	get_online_cpus();
 	get_online_mems();
···
 	mutex_lock(&slab_mutex);
 
 	/*
+	 * The memory cgroup could have been deactivated while the cache
+	 * creation work was pending.
+	 */
+	if (!memcg_kmem_is_active(memcg))
+		goto out_unlock;
+
+	idx = memcg_cache_id(memcg);
+	arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+
+	/*
 	 * Since per-memcg caches are created asynchronously on first
 	 * allocation (see memcg_kmem_get_cache()), several threads can try to
 	 * create the same cache, but only one of them may succeed.
 	 */
-	if (cache_from_memcg_idx(root_cache, memcg_id))
+	if (arr->entries[idx])
 		goto out_unlock;
 
-	cgroup_name(mem_cgroup_css(memcg)->cgroup,
-		    memcg_name_buf, sizeof(memcg_name_buf));
+	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
 	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
-			       memcg_cache_id(memcg), memcg_name_buf);
+			       css->id, memcg_name_buf);
 	if (!cache_name)
 		goto out_unlock;
 
···
 		goto out_unlock;
 	}
 
+	list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
+
 	/*
 	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
 	 * initialized.
 	 */
 	smp_wmb();
-	root_cache->memcg_params->memcg_caches[memcg_id] = s;
+	arr->entries[idx] = s;
 
 out_unlock:
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+}
+
+void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
+{
+	int idx;
+	struct memcg_cache_array *arr;
+	struct kmem_cache *s, *c;
+
+	idx = memcg_cache_id(memcg);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
+						lockdep_is_held(&slab_mutex));
+		c = arr->entries[idx];
+		if (!c)
+			continue;
+
+		__kmem_cache_shrink(c, true);
+		arr->entries[idx] = NULL;
+	}
 	mutex_unlock(&slab_mutex);
 
 	put_online_mems();
···
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry_safe(s, s2, &slab_caches, list) {
-		if (is_root_cache(s) || s->memcg_params->memcg != memcg)
+		if (is_root_cache(s) || s->memcg_params.memcg != memcg)
 			continue;
 		/*
 		 * The cgroup is about to be freed and therefore has no charges
···
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
-	memcg_free_cache_params(s);
+	destroy_memcg_params(s);
 	kfree(s->name);
 	kmem_cache_free(kmem_cache, s);
 }
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	int i;
+	struct kmem_cache *c, *c2;
 	LIST_HEAD(release);
 	bool need_rcu_barrier = false;
 	bool busy = false;
+
+	BUG_ON(!is_root_cache(s));
 
 	get_online_cpus();
 	get_online_mems();
···
 	if (s->refcount)
 		goto out_unlock;
 
-	for_each_memcg_cache_index(i) {
-		struct kmem_cache *c = cache_from_memcg_idx(s, i);
-
-		if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
+	for_each_memcg_cache_safe(c, c2, s) {
+		if (do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
 			busy = true;
 	}
 
···
 
 	get_online_cpus();
 	get_online_mems();
-	ret = __kmem_cache_shrink(cachep);
+	ret = __kmem_cache_shrink(cachep, false);
 	put_online_mems();
 	put_online_cpus();
 	return ret;
···
 	s->name = name;
 	s->size = s->object_size = size;
 	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	slab_init_memcg_params(s);
+
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
···
 {
 	struct kmem_cache *c;
 	struct slabinfo sinfo;
-	int i;
 
 	if (!is_root_cache(s))
 		return;
 
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(s, i);
-		if (!c)
-			continue;
-
+	for_each_memcg_cache(c, s) {
 		memset(&sinfo, 0, sizeof(sinfo));
 		get_slabinfo(c, &sinfo);
 
···
 
 	if (p == slab_caches.next)
 		print_slabinfo_header(m);
-	if (!is_root_cache(s) && s->memcg_params->memcg == memcg)
+	if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
 		cache_show(s, m);
 	return 0;
 }

mm/slob.c

···
 	return 0;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *d)
+int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;
 }

mm/slub.c

···
 	int pages;
 	int pobjects;
 
+	preempt_disable();
 	do {
 		pages = 0;
 		pobjects = 0;
···
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
 								!= oldpage);
+	if (unlikely(!s->cpu_partial)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
+		local_irq_restore(flags);
+	}
+	preempt_enable();
 #endif
 }
 
···
 }
 EXPORT_SYMBOL(kfree);
 
+#define SHRINK_PROMOTE_MAX 32
+
 /*
- * kmem_cache_shrink removes empty slabs from the partial lists and sorts
- * the remaining slabs by the number of items in use. The slabs with the
- * most items in use come first. New allocations will then fill those up
- * and thus they can be removed from the partial lists.
+ * kmem_cache_shrink discards empty slabs and promotes the slabs filled
+ * up most to the head of the partial lists. New allocations will then
+ * fill those up and thus they can be removed from the partial lists.
  *
  * The slabs with the least items are placed last. This results in them
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
 {
 	int node;
 	int i;
 	struct kmem_cache_node *n;
 	struct page *page;
 	struct page *t;
-	int objects = oo_objects(s->max);
-	struct list_head *slabs_by_inuse =
-		kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
+	struct list_head discard;
+	struct list_head promote[SHRINK_PROMOTE_MAX];
 	unsigned long flags;
+	int ret = 0;
 
-	if (!slabs_by_inuse)
-		return -ENOMEM;
+	if (deactivate) {
+		/*
+		 * Disable empty slabs caching. Used to avoid pinning offline
+		 * memory cgroups by kmem pages that can be freed.
+		 */
+		s->cpu_partial = 0;
+		s->min_partial = 0;
+
+		/*
+		 * s->cpu_partial is checked locklessly (see put_cpu_partial),
+		 * so we have to make sure the change is visible.
+		 */
+		kick_all_cpus_sync();
+	}
 
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
-		if (!n->nr_partial)
-			continue;
-
-		for (i = 0; i < objects; i++)
-			INIT_LIST_HEAD(slabs_by_inuse + i);
+		INIT_LIST_HEAD(&discard);
+		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
+			INIT_LIST_HEAD(promote + i);
 
 		spin_lock_irqsave(&n->list_lock, flags);
 
 		/*
-		 * Build lists indexed by the items in use in each slab.
+		 * Build lists of slabs to discard or promote.
 		 *
 		 * Note that concurrent frees may occur while we hold the
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			list_move(&page->lru, slabs_by_inuse + page->inuse);
-			if (!page->inuse)
+			int free = page->objects - page->inuse;
+
+			/* Do not reread page->inuse */
+			barrier();
+
+			/* We do not keep full slabs on the list */
+			BUG_ON(free <= 0);
+
+			if (free == page->objects) {
+				list_move(&page->lru, &discard);
 				n->nr_partial--;
+			} else if (free <= SHRINK_PROMOTE_MAX)
+				list_move(&page->lru, promote + free - 1);
 		}
 
 		/*
-		 * Rebuild the partial list with the slabs filled up most
-		 * first and the least used slabs at the end.
+		 * Promote the slabs filled up most to the head of the
+		 * partial list.
 		 */
-		for (i = objects - 1; i > 0; i--)
-			list_splice(slabs_by_inuse + i, n->partial.prev);
+		for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--)
+			list_splice(promote + i, &n->partial);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
 
 		/* Release empty slabs */
-		list_for_each_entry_safe(page, t, slabs_by_inuse, lru)
+		list_for_each_entry_safe(page, t, &discard, lru)
 			discard_slab(s, page);
+
+		if (slabs_node(s, node))
+			ret = 1;
 	}
 
-	kfree(slabs_by_inuse);
-	return 0;
+	return ret;
 }
 
 static int slab_mem_going_offline_callback(void *arg)
···
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+		__kmem_cache_shrink(s, false);
 	mutex_unlock(&slab_mutex);
 
 	return 0;
···
 			p->slab_cache = s;
 #endif
 	}
+	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
 	return s;
 }
···
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s;
+	struct kmem_cache *s, *c;
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
-		int i;
-		struct kmem_cache *c;
-
 		s->refcount++;
 
 		/*
···
 		s->object_size = max(s->object_size, (int)size);
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 
-		for_each_memcg_cache_index(i) {
-			c = cache_from_memcg_idx(s, i);
-			if (!c)
-				continue;
+		for_each_memcg_cache(c, s) {
 			c->object_size = s->object_size;
 			c->inuse = max_t(int, c->inuse,
 					 ALIGN(size, sizeof(void *)));
···
 static ssize_t shrink_store(struct kmem_cache *s,
 			const char *buf, size_t length)
 {
-	if (buf[0] == '1') {
-		int rc = kmem_cache_shrink(s);
-
-		if (rc)
-			return rc;
-	} else
+	if (buf[0] == '1')
+		kmem_cache_shrink(s);
+	else
 		return -EINVAL;
 	return length;
 }
···
 	err = attribute->store(s, buf, len);
 #ifdef CONFIG_MEMCG_KMEM
 	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-		int i;
+		struct kmem_cache *c;
 
 		mutex_lock(&slab_mutex);
 		if (s->max_attr_size < len)
···
 		 * directly either failed or succeeded, in which case we loop
 		 * through the descendants with best-effort propagation.
 		 */
-		for_each_memcg_cache_index(i) {
-			struct kmem_cache *c = cache_from_memcg_idx(s, i);
-			if (c)
-				attribute->store(c, buf, len);
-		}
+		for_each_memcg_cache(c, s)
+			attribute->store(c, buf, len);
 		mutex_unlock(&slab_mutex);
 	}
 #endif
···
 	if (is_root_cache(s))
 		return;
 
-	root_cache = s->memcg_params->root_cache;
+	root_cache = s->memcg_params.root_cache;
 
 	/*
 	 * This mean this cache had no attribute written. Therefore, no point
···
 {
 #ifdef CONFIG_MEMCG_KMEM
 	if (!is_root_cache(s))
-		return s->memcg_params->root_cache->memcg_kset;
+		return s->memcg_params.root_cache->memcg_kset;
 #endif
 	return slab_kset;
 }

mm/vmscan.c

···
 
 #define SHRINK_BATCH 128
 
-static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
-				  struct shrinker *shrinker,
-				  unsigned long nr_scanned,
-				  unsigned long nr_eligible)
+static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
+				    struct shrinker *shrinker,
+				    unsigned long nr_scanned,
+				    unsigned long nr_eligible)
 {
 	unsigned long freed = 0;
 	unsigned long long delta;
···
 }
 
 /**
- * shrink_node_slabs - shrink slab caches of a given node
+ * shrink_slab - shrink slab caches
  * @gfp_mask: allocation context
  * @nid: node whose slab caches to target
+ * @memcg: memory cgroup whose slab caches to target
  * @nr_scanned: pressure numerator
  * @nr_eligible: pressure denominator
  *
···
  *
  * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
  * unaware shrinkers will receive a node id of 0 instead.
+ *
+ * @memcg specifies the memory cgroup to target. If it is not NULL,
+ * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
+ * objects from the memory cgroup specified. Otherwise all shrinkers
+ * are called, and memcg aware shrinkers are supposed to scan the
+ * global list then.
  *
  * @nr_scanned and @nr_eligible form a ratio that indicate how much of
  * the available objects should be scanned.  Page reclaim for example
···
  *
  * Returns the number of reclaimed slab objects.
  */
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
-				unsigned long nr_scanned,
-				unsigned long nr_eligible)
+static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
+				 struct mem_cgroup *memcg,
+				 unsigned long nr_scanned,
+				 unsigned long nr_eligible)
 {
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
+
+	if (memcg && !memcg_kmem_is_active(memcg))
+		return 0;
 
 	if (nr_scanned == 0)
 		nr_scanned = SWAP_CLUSTER_MAX;
···
 		struct shrink_control sc = {
 			.gfp_mask = gfp_mask,
 			.nid = nid,
+			.memcg = memcg,
 		};
+
+		if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE))
+			continue;
 
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
 			sc.nid = 0;
 
-		freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible);
+		freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
 	}
 
 	up_read(&shrinker_rwsem);
 out:
 	cond_resched();
 	return freed;
+}
+
+void drop_slab_node(int nid)
+{
+	unsigned long freed;
+
+	do {
+		struct mem_cgroup *memcg = NULL;
+
+		freed = 0;
+		do {
+			freed += shrink_slab(GFP_KERNEL, nid, memcg,
+					     1000, 1000);
+		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+	} while (freed > 10);
+}
+
+void drop_slab(void)
+{
+	int nid;
+
+	for_each_online_node(nid)
+		drop_slab_node(nid);
 }
 
 static inline int is_page_cache_freeable(struct page *page)
···
 static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			bool is_classzone)
 {
+	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_reclaimed, nr_scanned;
 	bool reclaimable = false;
 
···
 		memcg = mem_cgroup_iter(root, NULL, &reclaim);
 		do {
 			unsigned long lru_pages;
+			unsigned long scanned;
 			struct lruvec *lruvec;
 			int swappiness;
 
···
 
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 			swappiness = mem_cgroup_swappiness(memcg);
+			scanned = sc->nr_scanned;
 
 			shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
 			zone_lru_pages += lru_pages;
+
+			if (memcg && is_classzone)
+				shrink_slab(sc->gfp_mask, zone_to_nid(zone),
+					    memcg, sc->nr_scanned - scanned,
+					    lru_pages);
 
 			/*
 			 * Direct reclaim and kswapd have to scan all memory
···
 		 * Shrink the slab caches in the same proportion that
 		 * the eligible LRU pages were scanned.
 		 */
-		if (global_reclaim(sc) && is_classzone) {
-			struct reclaim_state *reclaim_state;
+		if (global_reclaim(sc) && is_classzone)
+			shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
+				    sc->nr_scanned - nr_scanned,
+				    zone_lru_pages);
 
-			shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone),
-					  sc->nr_scanned - nr_scanned,
-					  zone_lru_pages);
-
-			reclaim_state = current->reclaim_state;
-			if (reclaim_state) {
-				sc->nr_reclaimed +=
-					reclaim_state->reclaimed_slab;
-				reclaim_state->reclaimed_slab = 0;
-			}
+		if (reclaim_state) {
+			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+			reclaim_state->reclaimed_slab = 0;
 		}
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,

mm/workingset.c

···
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
 	local_irq_enable();
 
 	pages = node_present_pages(sc->nid);
···
 }
 
 static enum lru_status shadow_lru_isolate(struct list_head *item,
+					  struct list_lru_one *lru,
 					  spinlock_t *lru_lock,
 					  void *arg)
 {
···
 		goto out;
 	}
 
-	list_del_init(item);
+	list_lru_isolate(lru, item);
 	spin_unlock(lru_lock);
 
 	/*
···
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
-				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	ret =  list_lru_shrink_walk(&workingset_shadow_nodes, sc,
+				    shadow_lru_isolate, NULL);
 	local_irq_enable();
 	return ret;
 }

mm/zbud.c

···
 	.evict =	zbud_zpool_evict
 };
 
-static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zbud_zpool_create(char *name, gfp_t gfp,
+			struct zpool_ops *zpool_ops)
 {
 	return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
 }

mm/zpool.c

···
 /**
  * zpool_create_pool() - Create a new zpool
  * @type	The type of the zpool to create (e.g. zbud, zsmalloc)
+ * @name	The name of the zpool (e.g. zram0, zswap)
  * @gfp		The GFP flags to use when allocating the pool.
  * @ops		The optional ops callback.
  *
···
  *
  * Returns: New zpool on success, NULL on failure.
  */
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
+struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+		struct zpool_ops *ops)
 {
 	struct zpool_driver *driver;
 	struct zpool *zpool;
···
 
 	zpool->type = driver->type;
 	zpool->driver = driver;
-	zpool->pool = driver->create(gfp, ops);
+	zpool->pool = driver->create(name, gfp, ops);
 	zpool->ops = ops;
 
 	if (!zpool->pool) {

mm/zsmalloc.c

···
 #include <linux/hardirq.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/debugfs.h>
 #include <linux/zsmalloc.h>
 #include <linux/zpool.h>
 
···
 	ZS_FULL
 };
 
+enum zs_stat_type {
+	OBJ_ALLOCATED,
+	OBJ_USED,
+	NR_ZS_STAT_TYPE,
+};
+
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static struct dentry *zs_stat_root;
+
+struct zs_size_stat {
+	unsigned long objs[NR_ZS_STAT_TYPE];
+};
+
+#endif
+
 /*
  * number of size_classes
  */
···
 	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
 	int pages_per_zspage;
 
+#ifdef CONFIG_ZSMALLOC_STAT
+	struct zs_size_stat stats;
+#endif
+
 	spinlock_t lock;
 
 	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
···
 };
 
 struct zs_pool {
+	char *name;
+
 	struct size_class **size_class;
 
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
+
+#ifdef CONFIG_ZSMALLOC_STAT
+	struct dentry *stat_dentry;
+#endif
 };
 
 /*
···
 
 #ifdef CONFIG_ZPOOL
 
-static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops)
 {
-	return zs_create_pool(gfp);
+	return zs_create_pool(name, gfp);
 }
 
 static void zs_zpool_destroy(void *pool)
···
 	return true;
 }
 
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static inline void zs_stat_inc(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+	class->stats.objs[type] += cnt;
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+	class->stats.objs[type] -= cnt;
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+				enum zs_stat_type type)
+{
+	return class->stats.objs[type];
+}
+
+static int __init zs_stat_init(void)
+{
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
+	if (!zs_stat_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+	debugfs_remove_recursive(zs_stat_root);
+}
+
+static int zs_stats_size_show(struct seq_file *s, void *v)
+{
+	int i;
+	struct zs_pool *pool = s->private;
+	struct size_class *class;
+	int objs_per_zspage;
+	unsigned long obj_allocated, obj_used, pages_used;
+	unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
+
+	seq_printf(s, " %5s %5s %13s %10s %10s\n", "class", "size",
+				"obj_allocated", "obj_used", "pages_used");
+
+	for (i = 0; i < zs_size_classes; i++) {
+		class = pool->size_class[i];
+
+		if (class->index != i)
+			continue;
+
+		spin_lock(&class->lock);
+		obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
+		obj_used = zs_stat_get(class, OBJ_USED);
+		spin_unlock(&class->lock);
+
+		objs_per_zspage = get_maxobj_per_zspage(class->size,
+				class->pages_per_zspage);
+		pages_used = obj_allocated / objs_per_zspage *
+				class->pages_per_zspage;
+
+		seq_printf(s, " %5u %5u    %10lu %10lu %10lu\n", i,
+			class->size, obj_allocated, obj_used, pages_used);
+
+		total_objs += obj_allocated;
+		total_used_objs += obj_used;
+		total_pages += pages_used;
+	}
+
+	seq_puts(s, "\n");
+	seq_printf(s, " %5s %5s    %10lu %10lu %10lu\n", "Total", "",
+			total_objs, total_used_objs, total_pages);
+
+	return 0;
+}
+
+static int zs_stats_size_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, zs_stats_size_show, inode->i_private);
+}
+
+static const struct file_operations zs_stat_size_ops = {
+	.open           = zs_stats_size_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+static int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+	struct dentry *entry;
+
+	if (!zs_stat_root)
+		return -ENODEV;
+
+	entry = debugfs_create_dir(name, zs_stat_root);
+	if (!entry) {
+		pr_warn("debugfs dir <%s> creation failed\n", name);
+		return -ENOMEM;
+	}
+	pool->stat_dentry = entry;
+
+	entry = debugfs_create_file("obj_in_classes", S_IFREG | S_IRUGO,
+			pool->stat_dentry, pool, &zs_stat_size_ops);
+	if (!entry) {
+		pr_warn("%s: debugfs file entry <%s> creation failed\n",
+				name, "obj_in_classes");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+	debugfs_remove_recursive(pool->stat_dentry);
+}
+
+#else /* CONFIG_ZSMALLOC_STAT */
+
+static inline void zs_stat_inc(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+				enum zs_stat_type type)
+{
+	return 0;
+}
+
+static int __init zs_stat_init(void)
+{
+	return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+}
+
+static inline int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+	return 0;
+}
+
+static inline void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+}
+
+#endif
+
 unsigned long zs_get_total_pages(struct zs_pool *pool)
 {
 	return atomic_long_read(&pool->pages_allocated);
···
 		set_zspage_mapping(first_page, class->index, ZS_EMPTY);
 		atomic_long_add(class->pages_per_zspage,
 					&pool->pages_allocated);
+
 		spin_lock(&class->lock);
+		zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+				class->size, class->pages_per_zspage));
 	}
 
 	obj = (unsigned long)first_page->freelist;
···
 	kunmap_atomic(vaddr);
 
 	first_page->inuse++;
+	zs_stat_inc(class, OBJ_USED, 1);
 	/* Now move the zspage to another fullness group, if required */
 	fix_fullness_group(pool, first_page);
 	spin_unlock(&class->lock);
···
 
 	first_page->inuse--;
 	fullness = fix_fullness_group(pool, first_page);
+
+	zs_stat_dec(class, OBJ_USED, 1);
+	if (fullness == ZS_EMPTY)
+		zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+				class->size, class->pages_per_zspage));
+
 	spin_unlock(&class->lock);
 
 	if (fullness == ZS_EMPTY) {
···
  * On success, a pointer to the newly created pool is returned,
  * otherwise NULL.
  */
-struct zs_pool *zs_create_pool(gfp_t flags)
+struct zs_pool *zs_create_pool(char *name, gfp_t flags)
 {
 	int i;
 	struct zs_pool *pool;
···
 	if (!pool)
 		return NULL;
 
+	pool->name = kstrdup(name, GFP_KERNEL);
+	if (!pool->name) {
+		kfree(pool);
+		return NULL;
+	}
+
 	pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *),
 			GFP_KERNEL);
 	if (!pool->size_class) {
+		kfree(pool->name);
 		kfree(pool);
 		return NULL;
 	}
···
 
 	pool->flags = flags;
 
+	if (zs_pool_stat_create(name, pool))
+		goto err;
+
 	return pool;
 
 err:
···
 void zs_destroy_pool(struct zs_pool *pool)
 {
 	int i;
+
+	zs_pool_stat_destroy(pool);
 
 	for (i = 0; i < zs_size_classes; i++) {
 		int fg;
···
 	}
 
 	kfree(pool->size_class);
+	kfree(pool->name);
 	kfree(pool);
 }
 EXPORT_SYMBOL_GPL(zs_destroy_pool);
···
 {
 	int ret = zs_register_cpu_notifier();
 
-	if (ret) {
-		zs_unregister_cpu_notifier();
-		return ret;
-	}
+	if (ret)
+		goto notifier_fail;
 
 	init_zs_size_classes();
 
 #ifdef CONFIG_ZPOOL
 	zpool_register_driver(&zs_zpool_driver);
 #endif
+
+	ret = zs_stat_init();
+	if (ret) {
+		pr_err("zs stat initialization failed\n");
+		goto stat_fail;
+	}
 	return 0;
+
+stat_fail:
+#ifdef CONFIG_ZPOOL
+	zpool_unregister_driver(&zs_zpool_driver);
+#endif
+notifier_fail:
+	zs_unregister_cpu_notifier();
+
+	return ret;
 }
 
 static void __exit zs_exit(void)
···
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zs_unregister_cpu_notifier();
+
+	zs_stat_exit();
 }
 
 module_init(zs_init);

mm/zswap.c

···
 
 	pr_info("loading zswap\n");
 
-	zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, &zswap_zpool_ops);
+	zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
+					&zswap_zpool_ops);
 	if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
 		pr_info("%s zpool not available\n", zswap_zpool_type);
 		zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
-		zswap_pool = zpool_create_pool(zswap_zpool_type, gfp,
+		zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
 					&zswap_zpool_ops);
 	}
 	if (!zswap_pool) {

net/ipv4/tcp_memcontrol.c

···
 		return;
 
 	percpu_counter_destroy(&cg_proto->sockets_allocated);
+
+	if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
+		static_key_slow_dec(&memcg_socket_limit_enabled);
+
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);