Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  scripts/gdb: make lx-dmesg command work (reliably)
  mm: consider memblock reservations for deferred memory initialization sizing
  mm/hugetlb: report -EHWPOISON not -EFAULT when FOLL_HWPOISON is specified
  mlock: fix mlock count can not decrease in race condition
  mm/migrate: fix refcount handling when !hugepage_migration_supported()
  dax: fix race between colliding PMD & PTE entries
  mm: avoid spurious 'bad pmd' warning messages
  mm/page_alloc.c: make sure OOM victim can try allocations with no watermarks once
  pcmcia: remove left-over %Z format
  slub/memcg: cure the brainless abuse of sysfs attributes
  initramfs: fix disabling of initramfs (and its compression)
  mm: clarify why we want kmalloc before falling backto vmallock
  frv: declare jiffies to be located in the .data section
  include/linux/gfp.h: fix ___GFP_NOLOCKDEP value
  ksm: prevent crash after write_protect_page fails

arch/frv/include/asm/timex.h

@@ -16,5 +16,11 @@ static inline cycles_t get_cycles(void)
 #define vxtime_lock()		do {} while (0)
 #define vxtime_unlock()		do {} while (0)
 
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data	__attribute__((__section__(".data")))
+
 #endif
 

drivers/char/pcmcia/cm4040_cs.c

@@ -374,7 +374,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 
 	rc = write_sync_reg(SCR_HOST_TO_READER_START, dev);
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;
@@ -387,7 +387,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	for (i = 0; i < bytes_to_write; i++) {
 		rc = wait_for_bulk_out_ready(dev);
 		if (rc <= 0) {
-			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2Zx\n",
+			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n",
 			       rc);
 			DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 			if (rc == -ERESTARTSYS)
@@ -403,7 +403,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev);
 
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;

fs/dax.c

@@ -1154,6 +1154,17 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 		goto out;
 	}
 
+	/*
+	 * It is possible, particularly with mixed reads & writes to private
+	 * mappings, that we have raced with a PMD fault that overlaps with
+	 * the PTE we need to set up.  If so just return and the fault will be
+	 * retried.
+	 */
+	if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
+		vmf_ret = VM_FAULT_NOPAGE;
+		goto unlock_entry;
+	}
+
 	/*
 	 * Note that we don't bother to use iomap_apply here: DAX required
 	 * the file system block size to be equal the page size, which means
@@ -1397,6 +1408,18 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	if (IS_ERR(entry))
 		goto fallback;
 
+	/*
+	 * It is possible, particularly with mixed reads & writes to private
+	 * mappings, that we have raced with a PTE fault that overlaps with
+	 * the PMD we need to set up.  If so just return and the fault will be
+	 * retried.
+	 */
+	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
+			!pmd_devmap(*vmf->pmd)) {
+		result = 0;
+		goto unlock_entry;
+	}
+
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way

include/linux/gfp.h

@@ -41,7 +41,7 @@ struct vm_area_struct;
 #define ___GFP_WRITE		0x800000u
 #define ___GFP_KSWAPD_RECLAIM	0x1000000u
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x4000000u
+#define ___GFP_NOLOCKDEP	0x2000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif

include/linux/jiffies.h

@@ -64,13 +64,17 @@ extern int register_refined_jiffies(long clock_tick_rate);
 /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
 #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
 
+#ifndef __jiffy_arch_data
+#define __jiffy_arch_data
+#endif
+
 /*
  * The 64-bit value is not atomic - you MUST NOT read it
  * without sampling the sequence number in jiffies_lock.
  * get_jiffies_64() will do this for you as appropriate.
  */
 extern u64 __cacheline_aligned_in_smp jiffies_64;
-extern unsigned long volatile __cacheline_aligned_in_smp jiffies;
+extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies;
 
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void);

include/linux/memblock.h

@@ -425,12 +425,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end)
 }
 #endif
 
+extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+		phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
 	return 0;
 }
 
+static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+		phys_addr_t end_addr)
+{
+	return 0;
+}
+
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */

include/linux/mm.h

@@ -2327,6 +2327,17 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
 #define FOLL_COW	0x4000	/* internal GUP flag */
 
+static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
+{
+	if (vm_fault & VM_FAULT_OOM)
+		return -ENOMEM;
+	if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+		return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT;
+	if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
+		return -EFAULT;
+	return 0;
+}
+
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,

include/linux/mmzone.h

@@ -678,6 +678,7 @@ typedef struct pglist_data {
 	 * is the first PFN that needs to be initialised.
 	 */
 	unsigned long first_deferred_pfn;
+	unsigned long static_init_size;
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

mm/gup.c

@@ -407,12 +407,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 
 	ret = handle_mm_fault(vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, *flags);
+
+		if (err)
+			return err;
 		BUG();
 	}
 
@@ -723,12 +721,10 @@ retry:
 	ret = handle_mm_fault(vma, address, fault_flags);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return -EHWPOISON;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, 0);
+
+		if (err)
+			return err;
 		BUG();
 	}
 

mm/hugetlb.c

@@ -4170,6 +4170,11 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
 			if (ret & VM_FAULT_ERROR) {
+				int err = vm_fault_to_errno(ret, flags);
+
+				if (err)
+					return err;
+
 				remainder = 0;
 				break;
 			}

mm/ksm.c

@@ -1028,8 +1028,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 		goto out;
 
 	if (PageTransCompound(page)) {
-		err = split_huge_page(page);
-		if (err)
+		if (split_huge_page(page))
 			goto out_unlock;
 	}
 

mm/memblock.c

@@ -1739,6 +1739,29 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+	struct memblock_region *rgn;
+	unsigned long size = 0;
+	int idx;
+
+	for_each_memblock_type((&memblock.reserved), rgn) {
+		phys_addr_t start, end;
+
+		if (rgn->base + rgn->size < start_addr)
+			continue;
+		if (rgn->base > end_addr)
+			continue;
+
+		start = rgn->base;
+		end = start + rgn->size;
+		size += end - start;
+	}
+
+	return size;
+}
+
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");

mm/memory-failure.c

@@ -1595,12 +1595,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
 			pfn, ret, page->flags, &page->flags);
-		/*
-		 * We know that soft_offline_huge_page() tries to migrate
-		 * only one hugepage pointed to by hpage, so we need not
-		 * run through the pagelist here.
-		 */
-		putback_active_hugepage(hpage);
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
 		if (ret > 0)
 			ret = -EIO;
 	} else {

mm/memory.c

@@ -3029,6 +3029,17 @@ static int __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 static int pte_alloc_one_map(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3052,18 +3063,27 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 map_pte:
 	/*
 	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
-	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
-	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
-	 * in a different thread of this mm, in turn leading to a misleading
-	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
-	 * regular pmd that we can walk with pte_offset_map() and we can do that
-	 * through an atomic read in C, which is what pmd_trans_unstable()
-	 * provides.
+	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault in a different thread of
+	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+	 * All we have to ensure is that it is a regular pmd that we can walk
+	 * with pte_offset_map() and we can do that through an atomic read in
+	 * C, which is what pmd_trans_unstable() provides.
 	 */
-	if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+	if (pmd_devmap_trans_unstable(vmf->pmd))
 		return VM_FAULT_NOPAGE;
 
+	/*
+	 * At this point we know that our vmf->pmd points to a page of ptes
+	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
+	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+	 * be valid and we will re-check to make sure the vmf->pte isn't
+	 * pte_none() under vmf->ptl protection when we return to
+	 * alloc_set_pte().
+	 */
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	return 0;
@@ -3690,7 +3710,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
 		vmf->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge

mm/mlock.c

@@ -284,7 +284,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
@@ -304,6 +304,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 				continue;
 			else
 				__munlock_isolation_failed(page);
+		} else {
+			delta_munlocked++;
 		}
 
 		/*
@@ -315,7 +317,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(zone_lru_lock(zone));
 

mm/page_alloc.c

@@ -292,6 +292,26 @@ int page_group_by_mobility_disabled __read_mostly;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
+	unsigned long max_initialise;
+	unsigned long reserved_lowmem;
+
+	/*
+	 * Initialise at least 2G of a node but also take into account that
+	 * two large system hashes that can take up 1GB for 0.25TB/node.
+	 */
+	max_initialise = max(2UL << (30 - PAGE_SHIFT),
+		(pgdat->node_spanned_pages >> 8));
+
+	/*
+	 * Compensate the all the memblock reservations (e.g. crash kernel)
+	 * from the initial estimation to make sure we will initialize enough
+	 * memory to boot.
+	 */
+	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+			pgdat->node_start_pfn + max_initialise);
+	max_initialise += reserved_lowmem;
+
+	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -314,20 +334,11 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 				unsigned long pfn, unsigned long zone_end,
 				unsigned long *nr_initialised)
 {
-	unsigned long max_initialise;
-
 	/* Always populate low zones for address-contrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-	/*
-	 * Initialise at least 2G of a node but also take into account that
-	 * two large system hashes that can take up 1GB for 0.25TB/node.
-	 */
-	max_initialise = max(2UL << (30 - PAGE_SHIFT),
-		(pgdat->node_spanned_pages >> 8));
-
 	(*nr_initialised)++;
-	if ((*nr_initialised > max_initialise) &&
+	if ((*nr_initialised > pgdat->static_init_size) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -3870,7 +3881,9 @@ retry:
 		goto got_pg;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE))
+	if (test_thread_flag(TIF_MEMDIE) &&
+	    (alloc_flags == ALLOC_NO_WATERMARKS ||
+	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
 	/* Retry as long as the OOM killer is making progress */
@@ -6136,7 +6149,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
-	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 	pgdat->per_cpu_nodestats = NULL;
@@ -6158,6 +6170,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
+	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 

mm/slub.c

@@ -5512,6 +5512,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		char mbuf[64];
 		char *buf;
 		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+		ssize_t len;
 
 		if (!attr || !attr->store || !attr->show)
 			continue;
@@ -5536,8 +5537,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(root_cache, buf);
-		attr->store(s, buf, strlen(buf));
+		len = attr->show(root_cache, buf);
+		if (len > 0)
+			attr->store(s, buf, len);
 	}
 
 	if (buffer)

mm/util.c

@@ -357,8 +357,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
 
 	/*
-	 * Make sure that larger requests are not too disruptive - no OOM
-	 * killer and no allocation failure warnings as we have a fallback
+	 * We want to attempt a large physically contiguous block first because
+	 * it is less likely to fragment multiple larger blocks and therefore
+	 * contribute to a long term fragmentation less than vmalloc fallback.
+	 * However make sure that larger requests are not too disruptive - no
+	 * OOM killer and no allocation failure warnings as we have a fallback.
 	 */
 	if (size > PAGE_SIZE) {
 		kmalloc_flags |= __GFP_NOWARN;

scripts/gdb/linux/dmesg.py

@@ -23,10 +23,11 @@ class LxDmesg(gdb.Command):
         super(LxDmesg, self).__init__("lx-dmesg", gdb.COMMAND_DATA)
 
     def invoke(self, arg, from_tty):
-        log_buf_addr = int(str(gdb.parse_and_eval("log_buf")).split()[0], 16)
-        log_first_idx = int(gdb.parse_and_eval("log_first_idx"))
-        log_next_idx = int(gdb.parse_and_eval("log_next_idx"))
-        log_buf_len = int(gdb.parse_and_eval("log_buf_len"))
+        log_buf_addr = int(str(gdb.parse_and_eval(
+            "'printk.c'::log_buf")).split()[0], 16)
+        log_first_idx = int(gdb.parse_and_eval("'printk.c'::log_first_idx"))
+        log_next_idx = int(gdb.parse_and_eval("'printk.c'::log_next_idx"))
+        log_buf_len = int(gdb.parse_and_eval("'printk.c'::log_buf_len"))
 
         inf = gdb.inferiors()[0]
         start = log_buf_addr + log_first_idx

usr/Kconfig

@@ -220,6 +220,7 @@ config INITRAMFS_COMPRESSION_LZ4
 endchoice
 
 config INITRAMFS_COMPRESSION
+	depends on INITRAMFS_SOURCE!=""
 	string
 	default ""      if INITRAMFS_COMPRESSION_NONE
 	default ".gz"   if INITRAMFS_COMPRESSION_GZIP