Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "14 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  rapidio/tsi721: fix incorrect detection of address translation condition
  rapidio/documentation/mport_cdev: add missing parameter description
  kernel/fork: fix CLONE_CHILD_CLEARTID regression in nscd
  MAINTAINERS: Vladimir has moved
  mm, mempolicy: task->mempolicy must be NULL before dropping final reference
  printk/nmi: avoid direct printk()-s from __printk_nmi_flush()
  treewide: remove references to the now unnecessary DEFINE_PCI_DEVICE_TABLE
  drivers/scsi/wd719x.c: remove last declaration using DEFINE_PCI_DEVICE_TABLE
  mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator
  lib/test_hash.c: fix warning in preprocessor symbol evaluation
  lib/test_hash.c: fix warning in two-dimensional array init
  kconfig: tinyconfig: provide whole choice blocks to avoid warnings
  kexec: fix double-free when failing to relocate the purgatory
  mm, oom: prevent premature OOM killer invocation for high order request

.mailmap

@@ -158,6 +158,8 @@ Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
 Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>

Documentation/PCI/pci.txt

@@ -124,7 +124,6 @@ initialization with a pointer to a structure describing the driver
 
 The ID table is an array of struct pci_device_id entries ending with an
 all-zero entry.  Definitions with static const are generally preferred.
-Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided.
 
 Each entry consists of:
 

Documentation/rapidio/mport_cdev.txt

@@ -80,6 +80,10 @@ functionality of their platform when planning to use this driver:
 
 III. Module parameters
 
+- 'dma_timeout' - DMA transfer completion timeout (in msec, default value 3000).
+        This parameter set a maximum completion wait time for SYNC mode DMA
+        transfer requests and for RIO_WAIT_FOR_ASYNC ioctl requests.
+
 - 'dbg_level' - This parameter allows to control amount of debug information
         generated by this device driver. This parameter is formed by set of
         bit masks that correspond to the specific functional blocks.

MAINTAINERS

@@ -3247,7 +3247,7 @@ F:	kernel/cpuset.c
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
-M:	Vladimir Davydov <vdavydov@virtuozzo.com>
+M:	Vladimir Davydov <vdavydov.dev@gmail.com>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained

arch/x86/configs/tiny.config

@@ -1 +1,3 @@
 CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set

drivers/rapidio/devices/tsi721.c

@@ -1161,7 +1161,7 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 		} else if (ibw_start < (ib_win->rstart + ib_win->size) &&
 			   (ibw_start + ibw_size) > ib_win->rstart) {
 			/* Return error if address translation involved */
-			if (direct && ib_win->xlat) {
+			if (!direct || ib_win->xlat) {
 				ret = -EFAULT;
 				break;
 			}

drivers/scsi/wd719x.c

@@ -962,7 +962,7 @@ static void wd719x_pci_remove(struct pci_dev *pdev)
 	scsi_host_put(sh);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(wd719x_pci_table) = {
+static const struct pci_device_id wd719x_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_WD, 0x3296) },
 	{}
 };

include/linux/mempolicy.h

@@ -195,6 +195,7 @@ static inline bool vma_migratable(struct vm_area_struct *vma)
 }
 
 extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+extern void mpol_put_task_policy(struct task_struct *);
 
 #else
 
@@ -297,5 +298,8 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
 	return -1; /* no node preference */
 }
 
+static inline void mpol_put_task_policy(struct task_struct *task)
+{
+}
 #endif /* CONFIG_NUMA */
 #endif

include/linux/mmzone.h

@@ -828,9 +828,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
  */
 #define zone_idx(zone)		((zone) - (zone)->zone_pgdat->node_zones)
 
-static inline int populated_zone(struct zone *zone)
+/*
+ * Returns true if a zone has pages managed by the buddy allocator.
+ * All the reclaim decisions have to use this function rather than
+ * populated_zone(). If the whole zone is reserved then we can easily
+ * end up with populated_zone() && !managed_zone().
+ */
+static inline bool managed_zone(struct zone *zone)
 {
-	return (!!zone->present_pages);
+	return zone->managed_pages;
+}
+
+/* Returns true if a zone has memory */
+static inline bool populated_zone(struct zone *zone)
+{
+	return zone->present_pages;
 }
 
 extern int movable_zone;

include/linux/pci.h

@@ -682,15 +682,6 @@ struct pci_driver {
 
 #define	to_pci_driver(drv) container_of(drv, struct pci_driver, driver)
 
-/**
- * DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table
- * @_table: device table name
- *
- * This macro is deprecated and should not be used in new code.
- */
-#define DEFINE_PCI_DEVICE_TABLE(_table) \
-	const struct pci_device_id _table[]
-
 /**
  * PCI_DEVICE - macro used to describe a specific pci device
  * @vend: the 16 bit PCI Vendor ID

kernel/configs/tiny.config

@@ -1,4 +1,12 @@
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
 CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
 CONFIG_SLOB=y

kernel/exit.c

@@ -848,12 +848,7 @@ void do_exit(long code)
 	TASKS_RCU(preempt_enable());
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
-#ifdef CONFIG_NUMA
-	task_lock(tsk);
-	mpol_put(tsk->mempolicy);
-	tsk->mempolicy = NULL;
-	task_unlock(tsk);
-#endif
+	mpol_put_task_policy(tsk);
 #ifdef CONFIG_FUTEX
 	if (unlikely(current->pi_state_cache))
 		kfree(current->pi_state_cache);

kernel/fork.c

@@ -936,14 +936,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * If we're exiting normally, clear a user-space tid field if
-	 * requested.  We leave this alone when dying by signal, to leave
-	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has

kernel/kexec_file.c

@@ -887,7 +887,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min,
 	return 0;
 out:
 	vfree(pi->sechdrs);
+	pi->sechdrs = NULL;
+
 	vfree(pi->purgatory_buf);
+	pi->purgatory_buf = NULL;
 	return ret;
 }
 

kernel/printk/nmi.c

@@ -99,26 +99,32 @@ again:
 	return add;
 }
 
-/*
- * printk one line from the temporary buffer from @start index until
- * and including the @end index.
- */
-static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void printk_nmi_flush_line(const char *text, int len)
 {
-	const char *buf = s->buffer + start;
-
 	/*
 	 * The buffers are flushed in NMI only on panic.  The messages must
 	 * go only into the ring buffer at this stage.  Consoles will get
 	 * explicitly called later when a crashdump is not generated.
 	 */
 	if (in_nmi())
-		printk_deferred("%.*s", (end - start) + 1, buf);
+		printk_deferred("%.*s", len, text);
 	else
-		printk("%.*s", (end - start) + 1, buf);
+		printk("%.*s", len, text);
 
 }
 
+/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
+					int start, int end)
+{
+	const char *buf = s->buffer + start;
+
+	printk_nmi_flush_line(buf, (end - start) + 1);
+}
+
 /*
  * Flush data from the associated per_CPU buffer. The function
  * can be called either via IRQ work or independently.
@@ -150,9 +156,11 @@ more:
 	 * the buffer an unexpected way. If we printed something then
 	 * @len must only increase.
 	 */
-	if (i && i >= len)
-		pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
-		       i, len);
+	if (i && i >= len) {
+		const char *msg = "printk_nmi_flush: internal error\n";
+
+		printk_nmi_flush_line(msg, strlen(msg));
+	}
 
 	if (!len)
 		goto out; /* Someone else has already flushed the buffer. */
@@ -166,14 +174,14 @@ more:
 	/* Print line by line. */
 	for (; i < size; i++) {
 		if (s->buffer[i] == '\n') {
-			print_nmi_seq_line(s, last_i, i);
+			printk_nmi_flush_seq_line(s, last_i, i);
 			last_i = i + 1;
 		}
 	}
 	/* Check if there was a partial line. */
 	if (last_i < size) {
-		print_nmi_seq_line(s, last_i, size - 1);
-		pr_cont("\n");
+		printk_nmi_flush_seq_line(s, last_i, size - 1);
+		printk_nmi_flush_line("\n", strlen("\n"));
 	}
 
 	/*

lib/test_hash.c

@@ -143,7 +143,7 @@ static int __init
 test_hash_init(void)
 {
 	char buf[SIZE+1];
-	u32 string_or = 0, hash_or[2][33] = { 0 };
+	u32 string_or = 0, hash_or[2][33] = { { 0, } };
 	unsigned tests = 0;
 	unsigned long long h64 = 0;
 	int i, j;
@@ -219,21 +219,27 @@ test_hash_init(void)
 	}
 
 	/* Issue notices about skipped tests. */
-#ifndef HAVE_ARCH__HASH_32
-	pr_info("__hash_32() has no arch implementation to test.");
-#elif HAVE_ARCH__HASH_32 != 1
+#ifdef HAVE_ARCH__HASH_32
+#if HAVE_ARCH__HASH_32 != 1
 	pr_info("__hash_32() is arch-specific; not compared to generic.");
 #endif
-#ifndef HAVE_ARCH_HASH_32
-	pr_info("hash_32() has no arch implementation to test.");
-#elif HAVE_ARCH_HASH_32 != 1
+#else
+	pr_info("__hash_32() has no arch implementation to test.");
+#endif
+#ifdef HAVE_ARCH_HASH_32
+#if HAVE_ARCH_HASH_32 != 1
 	pr_info("hash_32() is arch-specific; not compared to generic.");
 #endif
-#ifndef HAVE_ARCH_HASH_64
-	pr_info("hash_64() has no arch implementation to test.");
-#elif HAVE_ARCH_HASH_64 != 1
+#else
+	pr_info("hash_32() has no arch implementation to test.");
+#endif
+#ifdef HAVE_ARCH_HASH_64
+#if HAVE_ARCH_HASH_64 != 1
 	pr_info("hash_64() is arch-specific; not compared to generic.");
 #endif
+#else
+	pr_info("hash_64() has no arch implementation to test.");
+#endif
 
 	pr_notice("%u tests passed.", tests);
 

mm/mempolicy.c

@@ -2336,6 +2336,23 @@ out:
 	return ret;
 }
 
+/*
+ * Drop the (possibly final) reference to task->mempolicy.  It needs to be
+ * dropped after task->mempolicy is set to NULL so that any allocation done as
+ * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
+ * policy.
+ */
+void mpol_put_task_policy(struct task_struct *task)
+{
+	struct mempolicy *pol;
+
+	task_lock(task);
+	pol = task->mempolicy;
+	task->mempolicy = NULL;
+	task_unlock(task);
+	mpol_put(pol);
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);

mm/page_alloc.c

@@ -3137,54 +3137,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	return NULL;
 }
 
-static inline bool
-should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
-		     enum compact_result compact_result,
-		     enum compact_priority *compact_priority,
-		     int compaction_retries)
-{
-	int max_retries = MAX_COMPACT_RETRIES;
-
-	if (!order)
-		return false;
-
-	/*
-	 * compaction considers all the zone as desperately out of memory
-	 * so it doesn't really make much sense to retry except when the
-	 * failure could be caused by insufficient priority
-	 */
-	if (compaction_failed(compact_result)) {
-		if (*compact_priority > MIN_COMPACT_PRIORITY) {
-			(*compact_priority)--;
-			return true;
-		}
-		return false;
-	}
-
-	/*
-	 * make sure the compaction wasn't deferred or didn't bail out early
-	 * due to locks contention before we declare that we should give up.
-	 * But do not retry if the given zonelist is not suitable for
-	 * compaction.
-	 */
-	if (compaction_withdrawn(compact_result))
-		return compaction_zonelist_suitable(ac, order, alloc_flags);
-
-	/*
-	 * !costly requests are much more important than __GFP_REPEAT
-	 * costly ones because they are de facto nofail and invoke OOM
-	 * killer to move on while costly can fail and users are ready
-	 * to cope with that. 1/4 retries is rather arbitrary but we
-	 * would need much more detailed feedback from compaction to
-	 * make a better decision.
-	 */
-	if (order > PAGE_ALLOC_COSTLY_ORDER)
-		max_retries /= 4;
-	if (compaction_retries <= max_retries)
-		return true;
-
-	return false;
-}
 #else
 static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
@@ -3195,6 +3147,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	return NULL;
 }
 
+#endif /* CONFIG_COMPACTION */
+
 static inline bool
 should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
 		     enum compact_result compact_result,
@@ -3221,7 +3175,6 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 	}
 	return false;
 }
-#endif /* CONFIG_COMPACTION */
 
 /* Perform direct synchronous page reclaim */
 static int
@@ -4407,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
 	do {
 		zone_type--;
 		zone = pgdat->node_zones + zone_type;
-		if (populated_zone(zone)) {
+		if (managed_zone(zone)) {
 			zoneref_set_zone(zone,
 				&zonelist->_zonerefs[nr_zones++]);
 			check_highest_zone(zone_type);
@@ -4645,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 		for (j = 0; j < nr_nodes; j++) {
 			node = node_order[j];
 			z = &NODE_DATA(node)->node_zones[zone_type];
-			if (populated_zone(z)) {
+			if (managed_zone(z)) {
 				zoneref_set_zone(z,
 					&zonelist->_zonerefs[pos++]);
 				check_highest_zone(zone_type);

mm/vmscan.c

@@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec,
 
 	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
 		zone = &pgdat->node_zones[zid];
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
@@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 		struct zone *zone = &pgdat->node_zones[zid];
 		unsigned long inactive_zone, active_zone;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		inactive_zone = zone_page_state(zone,
@@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 
 		for (z = 0; z < MAX_NR_ZONES; z++) {
 			struct zone *zone = &pgdat->node_zones[z];
-			if (!populated_zone(zone))
+			if (!managed_zone(zone))
 				continue;
 
 			total_high_wmark += high_wmark_pages(zone);
@@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	/* If compaction would go ahead or the allocation would succeed, stop */
 	for (z = 0; z <= sc->reclaim_idx; z++) {
 		struct zone *zone = &pgdat->node_zones[z];
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
@@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
-		if (!populated_zone(zone) ||
+		if (!managed_zone(zone) ||
 		    pgdat_reclaimable_pages(pgdat) == 0)
 			continue;
 
@@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	for (i = 0; i <= classzone_idx; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (!zone_balanced(zone, order, classzone_idx))
@@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
 	sc->nr_to_reclaim = 0;
 	for (z = 0; z <= sc->reclaim_idx; z++) {
 		zone = pgdat->node_zones + z;
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
@@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		if (buffer_heads_over_limit) {
 			for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
 				zone = pgdat->node_zones + i;
-				if (!populated_zone(zone))
+				if (!managed_zone(zone))
 					continue;
 
 				sc.reclaim_idx = i;
@@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 */
 		for (i = classzone_idx; i >= 0; i--) {
 			zone = pgdat->node_zones + i;
-			if (!populated_zone(zone))
+			if (!managed_zone(zone))
 				continue;
 
 			if (zone_balanced(zone, sc.order, classzone_idx))
@@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	pg_data_t *pgdat;
 	int z;
 
-	if (!populated_zone(zone))
+	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
@@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	/* Only wake kswapd if all zones are unbalanced */
 	for (z = 0; z <= classzone_idx; z++) {
 		zone = pgdat->node_zones + z;
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (zone_balanced(zone, order, classzone_idx))

scripts/checkpatch.pl

@@ -3570,15 +3570,6 @@ sub process {
 			}
 		}
 
-# check for uses of DEFINE_PCI_DEVICE_TABLE
-		if ($line =~ /\bDEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=/) {
-			if (WARN("DEFINE_PCI_DEVICE_TABLE",
-				 "Prefer struct pci_device_id over deprecated DEFINE_PCI_DEVICE_TABLE\n" . $herecurr) &&
-			    $fix) {
-				$fixed[$fixlinenr] =~ s/\b(?:static\s+|)DEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=\s*/static const struct pci_device_id $1\[\] = /;
-			}
-		}
-
 # check for new typedefs, only function parameters and sparse annotations
 # make sense.
 		if ($line =~ /\btypedef\s/ &&